diff options
Diffstat (limited to 'tools/perf/pmu-events')
157 files changed, 13054 insertions, 9998 deletions
diff --git a/tools/perf/pmu-events/arch/arm64/hisilicon/hip08/uncore-ddrc.json b/tools/perf/pmu-events/arch/arm64/hisilicon/hip08/uncore-ddrc.json index 2b3cb55df288..014454d78293 100644 --- a/tools/perf/pmu-events/arch/arm64/hisilicon/hip08/uncore-ddrc.json +++ b/tools/perf/pmu-events/arch/arm64/hisilicon/hip08/uncore-ddrc.json @@ -3,56 +3,48 @@ "ConfigCode": "0x00", "EventName": "flux_wr", "BriefDescription": "DDRC total write operations", - "PublicDescription": "DDRC total write operations", "Unit": "hisi_sccl,ddrc" }, { "ConfigCode": "0x01", "EventName": "flux_rd", "BriefDescription": "DDRC total read operations", - "PublicDescription": "DDRC total read operations", "Unit": "hisi_sccl,ddrc" }, { "ConfigCode": "0x02", "EventName": "flux_wcmd", "BriefDescription": "DDRC write commands", - "PublicDescription": "DDRC write commands", "Unit": "hisi_sccl,ddrc" }, { "ConfigCode": "0x03", "EventName": "flux_rcmd", "BriefDescription": "DDRC read commands", - "PublicDescription": "DDRC read commands", "Unit": "hisi_sccl,ddrc" }, { "ConfigCode": "0x04", "EventName": "pre_cmd", "BriefDescription": "DDRC precharge commands", - "PublicDescription": "DDRC precharge commands", "Unit": "hisi_sccl,ddrc" }, { "ConfigCode": "0x05", "EventName": "act_cmd", "BriefDescription": "DDRC active commands", - "PublicDescription": "DDRC active commands", "Unit": "hisi_sccl,ddrc" }, { "ConfigCode": "0x06", "EventName": "rnk_chg", "BriefDescription": "DDRC rank commands", - "PublicDescription": "DDRC rank commands", "Unit": "hisi_sccl,ddrc" }, { "ConfigCode": "0x07", "EventName": "rw_chg", "BriefDescription": "DDRC read and write changes", - "PublicDescription": "DDRC read and write changes", "Unit": "hisi_sccl,ddrc" } ] diff --git a/tools/perf/pmu-events/arch/arm64/hisilicon/hip08/uncore-hha.json b/tools/perf/pmu-events/arch/arm64/hisilicon/hip08/uncore-hha.json index 9a7ec7af2060..b2b895fa670e 100644 --- a/tools/perf/pmu-events/arch/arm64/hisilicon/hip08/uncore-hha.json +++ b/tools/perf/pmu-events/arch/arm64/hisilicon/hip08/uncore-hha.json @@ -3,42 +3,41 @@ "ConfigCode": "0x00", "EventName": "rx_ops_num", "BriefDescription": "The number of all operations received by the HHA", - "PublicDescription": "The number of all operations received by the HHA", "Unit": "hisi_sccl,hha" }, { "ConfigCode": "0x01", "EventName": "rx_outer", "BriefDescription": "The number of all operations received by the HHA from another socket", - "PublicDescription": "The number of all operations received by the HHA from another socket", "Unit": "hisi_sccl,hha" }, { "ConfigCode": "0x02", "EventName": "rx_sccl", "BriefDescription": "The number of all operations received by the HHA from another SCCL in this socket", - "PublicDescription": "The number of all operations received by the HHA from another SCCL in this socket", "Unit": "hisi_sccl,hha" }, { "ConfigCode": "0x03", "EventName": "rx_ccix", "BriefDescription": "Count of the number of operations that HHA has received from CCIX", - "PublicDescription": "Count of the number of operations that HHA has received from CCIX", "Unit": "hisi_sccl,hha" }, { "ConfigCode": "0x4", "EventName": "rx_wbi", + "BriefDescription": "Count of the number of WriteBackI operations that HHA has received", "Unit": "hisi_sccl,hha" }, { "ConfigCode": "0x5", "EventName": "rx_wbip", + "BriefDescription": "Count of the number of WriteBackIPtl operations that HHA has received", "Unit": "hisi_sccl,hha" }, { "ConfigCode": "0x11", + "BriefDescription": "Count of the number of WriteThruIStash operations that HHA has received", "EventName": "rx_wtistash", "Unit": "hisi_sccl,hha" }, @@ -46,107 +45,114 @@ "ConfigCode": "0x1c", "EventName": "rd_ddr_64b", "BriefDescription": "The number of read operations sent by HHA to DDRC which size is 64 bytes", - "PublicDescription": "The number of read operations sent by HHA to DDRC which size is 64bytes", "Unit": "hisi_sccl,hha" }, { "ConfigCode": "0x1d", "EventName": "wr_ddr_64b", "BriefDescription": "The number of write operations sent by HHA to DDRC which size is 64 bytes", - "PublicDescription": "The number of write operations sent by HHA to DDRC which size is 64 bytes", "Unit": "hisi_sccl,hha" }, { "ConfigCode": "0x1e", "EventName": "rd_ddr_128b", "BriefDescription": "The number of read operations sent by HHA to DDRC which size is 128 bytes", - "PublicDescription": "The number of read operations sent by HHA to DDRC which size is 128 bytes", "Unit": "hisi_sccl,hha" }, { "ConfigCode": "0x1f", "EventName": "wr_ddr_128b", "BriefDescription": "The number of write operations sent by HHA to DDRC which size is 128 bytes", - "PublicDescription": "The number of write operations sent by HHA to DDRC which size is 128 bytes", "Unit": "hisi_sccl,hha" }, { "ConfigCode": "0x20", "EventName": "spill_num", "BriefDescription": "Count of the number of spill operations that the HHA has sent", - "PublicDescription": "Count of the number of spill operations that the HHA has sent", "Unit": "hisi_sccl,hha" }, { "ConfigCode": "0x21", "EventName": "spill_success", "BriefDescription": "Count of the number of successful spill operations that the HHA has sent", - "PublicDescription": "Count of the number of successful spill operations that the HHA has sent", "Unit": "hisi_sccl,hha" }, { "ConfigCode": "0x23", "EventName": "bi_num", + "BriefDescription": "Count of the number of HHA BackInvalid operations", "Unit": "hisi_sccl,hha" }, { "ConfigCode": "0x32", "EventName": "mediated_num", + "BriefDescription": "Count of the number of Mediated operations that the HHA has forwarded", "Unit": "hisi_sccl,hha" }, { "ConfigCode": "0x33", "EventName": "tx_snp_num", + "BriefDescription": "Count of the number of Snoop operations that the HHA has sent", "Unit": "hisi_sccl,hha" }, { "ConfigCode": "0x34", "EventName": "tx_snp_outer", + "BriefDescription": "Count of the number of Snoop operations that the HHA has sent to another socket", "Unit": "hisi_sccl,hha" }, { "ConfigCode": "0x35", "EventName": "tx_snp_ccix", + "BriefDescription": "Count of the number of Snoop operations that the HHA has sent to CCIX", "Unit": "hisi_sccl,hha" }, { "ConfigCode": "0x38", "EventName": "rx_snprspdata", + "BriefDescription": "Count of the number of SnprspData flit operations that HHA has received", "Unit": "hisi_sccl,hha" }, { "ConfigCode": "0x3c", "EventName": "rx_snprsp_outer", + "BriefDescription": "Count of the number of SnprspData operations that HHA has received from another socket", "Unit": "hisi_sccl,hha" }, { "ConfigCode": "0x40", "EventName": "sdir-lookup", + "BriefDescription": "Count of the number of HHA S-Dir lookup operations", "Unit": "hisi_sccl,hha" }, { "ConfigCode": "0x41", "EventName": "edir-lookup", + "BriefDescription": "Count of the number of HHA E-Dir lookup operations", "Unit": "hisi_sccl,hha" }, { "ConfigCode": "0x42", "EventName": "sdir-hit", + "BriefDescription": "Count of the number of HHA S-Dir hit operations", "Unit": "hisi_sccl,hha" }, { "ConfigCode": "0x43", "EventName": "edir-hit", + "BriefDescription": "Count of the number of HHA E-Dir hit operations", "Unit": "hisi_sccl,hha" }, { "ConfigCode": "0x4c", "EventName": "sdir-home-migrate", + "BriefDescription": "Count of the number of HHA S-Dir read home migrate operations", "Unit": "hisi_sccl,hha" }, { "ConfigCode": "0x4d", "EventName": "edir-home-migrate", + "BriefDescription": "Count of the number of HHA E-Dir read home migrate operations", "Unit": "hisi_sccl,hha" } ] diff --git a/tools/perf/pmu-events/arch/arm64/hisilicon/hip08/uncore-l3c.json b/tools/perf/pmu-events/arch/arm64/hisilicon/hip08/uncore-l3c.json index e3479b65be9a..d83c22eb1d15 100644 --- a/tools/perf/pmu-events/arch/arm64/hisilicon/hip08/uncore-l3c.json +++ b/tools/perf/pmu-events/arch/arm64/hisilicon/hip08/uncore-l3c.json @@ -3,91 +3,78 @@ "ConfigCode": "0x00", "EventName": "rd_cpipe", "BriefDescription": "Total read accesses", - "PublicDescription": "Total read accesses", "Unit": "hisi_sccl,l3c" }, { "ConfigCode": "0x01", "EventName": "wr_cpipe", "BriefDescription": "Total write accesses", - "PublicDescription": "Total write accesses", "Unit": "hisi_sccl,l3c" }, { "ConfigCode": "0x02", "EventName": "rd_hit_cpipe", "BriefDescription": "Total read hits", - "PublicDescription": "Total read hits", "Unit": "hisi_sccl,l3c" }, { "ConfigCode": "0x03", "EventName": "wr_hit_cpipe", "BriefDescription": "Total write hits", - "PublicDescription": "Total write hits", "Unit": "hisi_sccl,l3c" }, { "ConfigCode": "0x04", "EventName": "victim_num", "BriefDescription": "l3c precharge commands", - "PublicDescription": "l3c precharge commands", "Unit": "hisi_sccl,l3c" }, { "ConfigCode": "0x20", "EventName": "rd_spipe", "BriefDescription": "Count of the number of read lines that come from this cluster of CPU core in spipe", - "PublicDescription": "Count of the number of read lines that come from this cluster of CPU core in spipe", "Unit": "hisi_sccl,l3c" }, { "ConfigCode": "0x21", "EventName": "wr_spipe", "BriefDescription": "Count of the number of write lines that come from this cluster of CPU core in spipe", - "PublicDescription": "Count of the number of write lines that come from this cluster of CPU core in spipe", "Unit": "hisi_sccl,l3c" }, { "ConfigCode": "0x22", "EventName": "rd_hit_spipe", "BriefDescription": "Count of the number of read lines that hits in spipe of this L3C", - "PublicDescription": "Count of the number of read lines that hits in spipe of this L3C", "Unit": "hisi_sccl,l3c" }, { "ConfigCode": "0x23", "EventName": "wr_hit_spipe", "BriefDescription": "Count of the number of write lines that hits in spipe of this L3C", - "PublicDescription": "Count of the number of write lines that hits in spipe of this L3C", "Unit": "hisi_sccl,l3c" }, { "ConfigCode": "0x29", "EventName": "back_invalid", "BriefDescription": "Count of the number of L3C back invalid operations", - "PublicDescription": "Count of the number of L3C back invalid operations", "Unit": "hisi_sccl,l3c" }, { "ConfigCode": "0x40", "EventName": "retry_cpu", "BriefDescription": "Count of the number of retry that L3C suppresses the CPU operations", - "PublicDescription": "Count of the number of retry that L3C suppresses the CPU operations", "Unit": "hisi_sccl,l3c" }, { "ConfigCode": "0x41", "EventName": "retry_ring", "BriefDescription": "Count of the number of retry that L3C suppresses the ring operations", - "PublicDescription": "Count of the number of retry that L3C suppresses the ring operations", "Unit": "hisi_sccl,l3c" }, { "ConfigCode": "0x42", "EventName": "prefetch_drop", "BriefDescription": "Count of the number of prefetch drops from this L3C", - "PublicDescription": "Count of the number of prefetch drops from this L3C", "Unit": "hisi_sccl,l3c" } ] diff --git a/tools/perf/pmu-events/arch/x86/alderlake/adl-metrics.json b/tools/perf/pmu-events/arch/x86/alderlake/adl-metrics.json index 147379cae37b..377dfecd96bd 100644 --- a/tools/perf/pmu-events/arch/x86/alderlake/adl-metrics.json +++ b/tools/perf/pmu-events/arch/x86/alderlake/adl-metrics.json @@ -103,7 +103,7 @@ "MetricExpr": "tma_core_bound", "MetricGroup": "TopdownL3;tma_L3_group;tma_core_bound_group", "MetricName": "tma_allocation_restriction", - "MetricThreshold": "(tma_allocation_restriction >0.10) & ((tma_core_bound >0.10) & ((tma_backend_bound >0.10)))", + "MetricThreshold": "tma_allocation_restriction > 0.1 & (tma_core_bound > 0.1 & tma_backend_bound > 0.1)", "ScaleUnit": "100%", "Unit": "cpu_atom" }, @@ -113,7 +113,7 @@ "MetricExpr": "cpu_atom@TOPDOWN_BE_BOUND.ALL@ / (5 * cpu_atom@CPU_CLK_UNHALTED.CORE@)", "MetricGroup": "Default;TopdownL1;tma_L1_group", "MetricName": "tma_backend_bound", - "MetricThreshold": "(tma_backend_bound >0.10)", + "MetricThreshold": "tma_backend_bound > 0.1", "MetricgroupNoGroup": "TopdownL1;Default", "PublicDescription": "Counts the total number of issue slots that were not consumed by the backend due to backend stalls. Note that uops must be available for consumption in order for this event to count. If a uop is not available (IQ is empty), this event will not count", "ScaleUnit": "100%", @@ -125,7 +125,7 @@ "MetricExpr": "(5 * cpu_atom@CPU_CLK_UNHALTED.CORE@ - (cpu_atom@TOPDOWN_FE_BOUND.ALL@ + cpu_atom@TOPDOWN_BE_BOUND.ALL@ + cpu_atom@TOPDOWN_RETIRING.ALL@)) / (5 * cpu_atom@CPU_CLK_UNHALTED.CORE@)", "MetricGroup": "Default;TopdownL1;tma_L1_group", "MetricName": "tma_bad_speculation", - "MetricThreshold": "(tma_bad_speculation >0.15)", + "MetricThreshold": "tma_bad_speculation > 0.15", "MetricgroupNoGroup": "TopdownL1;Default", "PublicDescription": "Counts the total number of issue slots that were not consumed by the backend because allocation is stalled due to a mispredicted jump or a machine clear. Only issue slots wasted due to fast nukes such as memory ordering nukes are counted. Other nukes are not accounted for. Counts all issue slots blocked during this recovery window including relevant microcode flows and while uops are not yet available in the instruction queue (IQ). Also includes the issue slots that were consumed by the backend but were thrown away because they were younger than the mispredict or machine clear.", "ScaleUnit": "100%", @@ -136,7 +136,7 @@ "MetricExpr": "cpu_atom@TOPDOWN_FE_BOUND.BRANCH_DETECT@ / (5 * cpu_atom@CPU_CLK_UNHALTED.CORE@)", "MetricGroup": "TopdownL3;tma_L3_group;tma_ifetch_latency_group", "MetricName": "tma_branch_detect", - "MetricThreshold": "(tma_branch_detect >0.05) & ((tma_ifetch_latency >0.15) & ((tma_frontend_bound >0.20)))", + "MetricThreshold": "tma_branch_detect > 0.05 & (tma_ifetch_latency > 0.15 & tma_frontend_bound > 0.2)", "PublicDescription": "Counts the number of issue slots that were not delivered by the frontend due to BACLEARS, which occurs when the Branch Target Buffer (BTB) prediction or lack thereof, was corrected by a later branch predictor in the frontend. Includes BACLEARS due to all branch types including conditional and unconditional jumps, returns, and indirect branches.", "ScaleUnit": "100%", "Unit": "cpu_atom" @@ -146,7 +146,7 @@ "MetricExpr": "cpu_atom@TOPDOWN_BAD_SPECULATION.MISPREDICT@ / (5 * cpu_atom@CPU_CLK_UNHALTED.CORE@)", "MetricGroup": "TopdownL2;tma_L2_group;tma_bad_speculation_group", "MetricName": "tma_branch_mispredicts", - "MetricThreshold": "(tma_branch_mispredicts >0.05) & ((tma_bad_speculation >0.15))", + "MetricThreshold": "tma_branch_mispredicts > 0.05 & tma_bad_speculation > 0.15", "MetricgroupNoGroup": "TopdownL2", "ScaleUnit": "100%", "Unit": "cpu_atom" @@ -156,7 +156,7 @@ "MetricExpr": "cpu_atom@TOPDOWN_FE_BOUND.BRANCH_RESTEER@ / (5 * cpu_atom@CPU_CLK_UNHALTED.CORE@)", "MetricGroup": "TopdownL3;tma_L3_group;tma_ifetch_latency_group", "MetricName": "tma_branch_resteer", - "MetricThreshold": "(tma_branch_resteer >0.05) & ((tma_ifetch_latency >0.15) & ((tma_frontend_bound >0.20)))", + "MetricThreshold": "tma_branch_resteer > 0.05 & (tma_ifetch_latency > 0.15 & tma_frontend_bound > 0.2)", "ScaleUnit": "100%", "Unit": "cpu_atom" }, @@ -165,7 +165,7 @@ "MetricExpr": "cpu_atom@TOPDOWN_FE_BOUND.CISC@ / (5 * cpu_atom@CPU_CLK_UNHALTED.CORE@)", "MetricGroup": "TopdownL3;tma_L3_group;tma_ifetch_bandwidth_group", "MetricName": "tma_cisc", - "MetricThreshold": "(tma_cisc >0.05) & ((tma_ifetch_bandwidth >0.10) & ((tma_frontend_bound >0.20)))", + "MetricThreshold": "tma_cisc > 0.05 & (tma_ifetch_bandwidth > 0.1 & tma_frontend_bound > 0.2)", "ScaleUnit": "100%", "Unit": "cpu_atom" }, @@ -174,7 +174,7 @@ "MetricExpr": "cpu_atom@TOPDOWN_BE_BOUND.ALLOC_RESTRICTIONS@ / (5 * cpu_atom@CPU_CLK_UNHALTED.CORE@)", "MetricGroup": "TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_core_bound", - "MetricThreshold": "(tma_core_bound >0.10) & ((tma_backend_bound >0.10))", + "MetricThreshold": "tma_core_bound > 0.1 & tma_backend_bound > 0.1", "MetricgroupNoGroup": "TopdownL2", "ScaleUnit": "100%", "Unit": "cpu_atom" @@ -184,7 +184,7 @@ "MetricExpr": "cpu_atom@TOPDOWN_FE_BOUND.DECODE@ / (5 * cpu_atom@CPU_CLK_UNHALTED.CORE@)", "MetricGroup": "TopdownL3;tma_L3_group;tma_ifetch_bandwidth_group", "MetricName": "tma_decode", - "MetricThreshold": "(tma_decode >0.05) & ((tma_ifetch_bandwidth >0.10) & ((tma_frontend_bound >0.20)))", + "MetricThreshold": "tma_decode > 0.05 & (tma_ifetch_bandwidth > 0.1 & tma_frontend_bound > 0.2)", "ScaleUnit": "100%", "Unit": "cpu_atom" }, @@ -193,7 +193,7 @@ "MetricExpr": "cpu_atom@TOPDOWN_BAD_SPECULATION.FASTNUKE@ / (5 * cpu_atom@CPU_CLK_UNHALTED.CORE@)", "MetricGroup": "TopdownL3;tma_L3_group;tma_machine_clears_group", "MetricName": "tma_fast_nuke", - "MetricThreshold": "(tma_fast_nuke >0.05) & ((tma_machine_clears >0.05) & ((tma_bad_speculation >0.15)))", + "MetricThreshold": "tma_fast_nuke > 0.05 & (tma_machine_clears > 0.05 & tma_bad_speculation > 0.15)", "ScaleUnit": "100%", "Unit": "cpu_atom" }, @@ -203,7 +203,7 @@ "MetricExpr": "cpu_atom@TOPDOWN_FE_BOUND.ALL@ / (5 * cpu_atom@CPU_CLK_UNHALTED.CORE@)", "MetricGroup": "Default;TopdownL1;tma_L1_group", "MetricName": "tma_frontend_bound", - "MetricThreshold": "(tma_frontend_bound >0.20)", + "MetricThreshold": "tma_frontend_bound > 0.2", "MetricgroupNoGroup": "TopdownL1;Default", "ScaleUnit": "100%", "Unit": "cpu_atom" @@ -213,7 +213,7 @@ "MetricExpr": "cpu_atom@TOPDOWN_FE_BOUND.ICACHE@ / (5 * cpu_atom@CPU_CLK_UNHALTED.CORE@)", "MetricGroup": "TopdownL3;tma_L3_group;tma_ifetch_latency_group", "MetricName": "tma_icache_misses", - "MetricThreshold": "(tma_icache_misses >0.05) & ((tma_ifetch_latency >0.15) & ((tma_frontend_bound >0.20)))", + "MetricThreshold": "tma_icache_misses > 0.05 & (tma_ifetch_latency > 0.15 & tma_frontend_bound > 0.2)", "ScaleUnit": "100%", "Unit": "cpu_atom" }, @@ -222,7 +222,7 @@ "MetricExpr": "cpu_atom@TOPDOWN_FE_BOUND.FRONTEND_BANDWIDTH@ / (5 * cpu_atom@CPU_CLK_UNHALTED.CORE@)", "MetricGroup": "TopdownL2;tma_L2_group;tma_frontend_bound_group", "MetricName": "tma_ifetch_bandwidth", - "MetricThreshold": "(tma_ifetch_bandwidth >0.10) & ((tma_frontend_bound >0.20))", + "MetricThreshold": "tma_ifetch_bandwidth > 0.1 & tma_frontend_bound > 0.2", "MetricgroupNoGroup": "TopdownL2", "ScaleUnit": "100%", "Unit": "cpu_atom" @@ -232,7 +232,7 @@ "MetricExpr": "cpu_atom@TOPDOWN_FE_BOUND.FRONTEND_LATENCY@ / (5 * cpu_atom@CPU_CLK_UNHALTED.CORE@)", "MetricGroup": "TopdownL2;tma_L2_group;tma_frontend_bound_group", "MetricName": "tma_ifetch_latency", - "MetricThreshold": "(tma_ifetch_latency >0.15) & ((tma_frontend_bound >0.20))", + "MetricThreshold": "tma_ifetch_latency > 0.15 & tma_frontend_bound > 0.2", "MetricgroupNoGroup": "TopdownL2", "ScaleUnit": "100%", "Unit": "cpu_atom" @@ -567,7 +567,7 @@ "BriefDescription": "PerfMon Event Multiplexing accuracy indicator", "MetricExpr": "cpu_atom@CPU_CLK_UNHALTED.CORE_P@ / cpu_atom@CPU_CLK_UNHALTED.CORE@", "MetricName": "tma_info_system_mux", - "MetricThreshold": "((tma_info_system_mux > 1.1)|(tma_info_system_mux < 0.9))", + "MetricThreshold": "tma_info_system_mux > 1.1 | tma_info_system_mux < 0.9", "Unit": "cpu_atom" }, { @@ -606,7 +606,7 @@ "MetricExpr": "cpu_atom@TOPDOWN_FE_BOUND.ITLB@ / (5 * cpu_atom@CPU_CLK_UNHALTED.CORE@)", "MetricGroup": "TopdownL3;tma_L3_group;tma_ifetch_latency_group", "MetricName": "tma_itlb_misses", - "MetricThreshold": "(tma_itlb_misses >0.05) & ((tma_ifetch_latency >0.15) & ((tma_frontend_bound >0.20)))", + "MetricThreshold": "tma_itlb_misses > 0.05 & (tma_ifetch_latency > 0.15 & tma_frontend_bound > 0.2)", "ScaleUnit": "100%", "Unit": "cpu_atom" }, @@ -615,7 +615,7 @@ "MetricExpr": "cpu_atom@TOPDOWN_BAD_SPECULATION.MACHINE_CLEARS@ / (5 * cpu_atom@CPU_CLK_UNHALTED.CORE@)", "MetricGroup": "TopdownL2;tma_L2_group;tma_bad_speculation_group", "MetricName": "tma_machine_clears", - "MetricThreshold": "(tma_machine_clears >0.05) & ((tma_bad_speculation >0.15))", + "MetricThreshold": "tma_machine_clears > 0.05 & tma_bad_speculation > 0.15", "MetricgroupNoGroup": "TopdownL2", "ScaleUnit": "100%", "Unit": "cpu_atom" @@ -625,7 +625,7 @@ "MetricExpr": "cpu_atom@TOPDOWN_BE_BOUND.MEM_SCHEDULER@ / (5 * cpu_atom@CPU_CLK_UNHALTED.CORE@)", "MetricGroup": "TopdownL3;tma_L3_group;tma_resource_bound_group", "MetricName": "tma_mem_scheduler", - "MetricThreshold": "(tma_mem_scheduler >0.10) & ((tma_resource_bound >0.20) & ((tma_backend_bound >0.10)))", + "MetricThreshold": "tma_mem_scheduler > 0.1 & (tma_resource_bound > 0.2 & tma_backend_bound > 0.1)", "ScaleUnit": "100%", "Unit": "cpu_atom" }, @@ -634,7 +634,7 @@ "MetricExpr": "cpu_atom@TOPDOWN_BE_BOUND.NON_MEM_SCHEDULER@ / (5 * cpu_atom@CPU_CLK_UNHALTED.CORE@)", "MetricGroup": "TopdownL3;tma_L3_group;tma_resource_bound_group", "MetricName": "tma_non_mem_scheduler", - "MetricThreshold": "(tma_non_mem_scheduler >0.10) & ((tma_resource_bound >0.20) & ((tma_backend_bound >0.10)))", + "MetricThreshold": "tma_non_mem_scheduler > 0.1 & (tma_resource_bound > 0.2 & tma_backend_bound > 0.1)", "ScaleUnit": "100%", "Unit": "cpu_atom" }, @@ -643,7 +643,7 @@ "MetricExpr": "cpu_atom@TOPDOWN_BAD_SPECULATION.NUKE@ / (5 * cpu_atom@CPU_CLK_UNHALTED.CORE@)", "MetricGroup": "TopdownL3;tma_L3_group;tma_machine_clears_group", "MetricName": "tma_nuke", - "MetricThreshold": "(tma_nuke >0.05) & ((tma_machine_clears >0.05) & ((tma_bad_speculation >0.15)))", + "MetricThreshold": "tma_nuke > 0.05 & (tma_machine_clears > 0.05 & tma_bad_speculation > 0.15)", "ScaleUnit": "100%", "Unit": "cpu_atom" }, @@ -652,7 +652,7 @@ "MetricExpr": "cpu_atom@TOPDOWN_FE_BOUND.OTHER@ / (5 * cpu_atom@CPU_CLK_UNHALTED.CORE@)", "MetricGroup": "TopdownL3;tma_L3_group;tma_ifetch_bandwidth_group", "MetricName": "tma_other_fb", - "MetricThreshold": "(tma_other_fb >0.05) & ((tma_ifetch_bandwidth >0.10) & ((tma_frontend_bound >0.20)))", + "MetricThreshold": "tma_other_fb > 0.05 & (tma_ifetch_bandwidth > 0.1 & tma_frontend_bound > 0.2)", "ScaleUnit": "100%", "Unit": "cpu_atom" }, @@ -661,7 +661,7 @@ "MetricExpr": "cpu_atom@TOPDOWN_FE_BOUND.PREDECODE@ / (5 * cpu_atom@CPU_CLK_UNHALTED.CORE@)", "MetricGroup": "TopdownL3;tma_L3_group;tma_ifetch_bandwidth_group", "MetricName": "tma_predecode", - "MetricThreshold": "(tma_predecode >0.05) & ((tma_ifetch_bandwidth >0.10) & ((tma_frontend_bound >0.20)))", + "MetricThreshold": "tma_predecode > 0.05 & (tma_ifetch_bandwidth > 0.1 & tma_frontend_bound > 0.2)", "ScaleUnit": "100%", "Unit": "cpu_atom" }, @@ -670,7 +670,7 @@ "MetricExpr": "cpu_atom@TOPDOWN_BE_BOUND.REGISTER@ / (5 * cpu_atom@CPU_CLK_UNHALTED.CORE@)", "MetricGroup": "TopdownL3;tma_L3_group;tma_resource_bound_group", "MetricName": "tma_register", - "MetricThreshold": "(tma_register >0.10) & ((tma_resource_bound >0.20) & ((tma_backend_bound >0.10)))", + "MetricThreshold": "tma_register > 0.1 & (tma_resource_bound > 0.2 & tma_backend_bound > 0.1)", "ScaleUnit": "100%", "Unit": "cpu_atom" }, @@ -679,7 +679,7 @@ "MetricExpr": "cpu_atom@TOPDOWN_BE_BOUND.REORDER_BUFFER@ / (5 * cpu_atom@CPU_CLK_UNHALTED.CORE@)", "MetricGroup": "TopdownL3;tma_L3_group;tma_resource_bound_group", "MetricName": "tma_reorder_buffer", - "MetricThreshold": "(tma_reorder_buffer >0.10) & ((tma_resource_bound >0.20) & ((tma_backend_bound >0.10)))", + "MetricThreshold": "tma_reorder_buffer > 0.1 & (tma_resource_bound > 0.2 & tma_backend_bound > 0.1)", "ScaleUnit": "100%", "Unit": "cpu_atom" }, @@ -688,7 +688,7 @@ "MetricExpr": "tma_backend_bound - tma_core_bound", "MetricGroup": "TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_resource_bound", - "MetricThreshold": "(tma_resource_bound >0.20) & ((tma_backend_bound >0.10))", + "MetricThreshold": "tma_resource_bound > 0.2 & tma_backend_bound > 0.1", "MetricgroupNoGroup": "TopdownL2", "ScaleUnit": "100%", "Unit": "cpu_atom" @@ -699,7 +699,7 @@ "MetricExpr": "cpu_atom@TOPDOWN_RETIRING.ALL@ / (5 * cpu_atom@CPU_CLK_UNHALTED.CORE@)", "MetricGroup": "Default;TopdownL1;tma_L1_group", "MetricName": "tma_retiring", - "MetricThreshold": "(tma_retiring >0.75)", + "MetricThreshold": "tma_retiring > 0.75", "MetricgroupNoGroup": "TopdownL1;Default", "ScaleUnit": "100%", "Unit": "cpu_atom" @@ -709,7 +709,7 @@ "MetricExpr": "cpu_atom@TOPDOWN_BE_BOUND.SERIALIZATION@ / (5 * cpu_atom@CPU_CLK_UNHALTED.CORE@)", "MetricGroup": "TopdownL3;tma_L3_group;tma_resource_bound_group", "MetricName": "tma_serialization", - "MetricThreshold": "(tma_serialization >0.10) & ((tma_resource_bound >0.20) & ((tma_backend_bound >0.10)))", + "MetricThreshold": "tma_serialization > 0.1 & (tma_resource_bound > 0.2 & tma_backend_bound > 0.1)", "ScaleUnit": "100%", "Unit": "cpu_atom" }, @@ -721,7 +721,7 @@ "Unit": "cpu_core" }, { - "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution ports for ALU operations", + "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution ports for ALU operations.", "MetricExpr": "(cpu_core@UOPS_DISPATCHED.PORT_0@ + cpu_core@UOPS_DISPATCHED.PORT_1@ + cpu_core@UOPS_DISPATCHED.PORT_5_11@ + cpu_core@UOPS_DISPATCHED.PORT_6@) / (5 * tma_info_core_core_clks)", "MetricGroup": "TopdownL5;tma_L5_group;tma_ports_utilized_3m_group", "MetricName": "tma_alu_op_utilization", @@ -734,13 +734,13 @@ "MetricExpr": "78 * cpu_core@ASSISTS.ANY@ / tma_info_thread_slots", "MetricGroup": "BvIO;TopdownL4;tma_L4_group;tma_microcode_sequencer_group", "MetricName": "tma_assists", - "MetricThreshold": "tma_assists > 0.1 & tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1", + "MetricThreshold": "tma_assists > 0.1 & (tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1)", "PublicDescription": "This metric estimates fraction of slots the CPU retired uops delivered by the Microcode_Sequencer as a result of Assists. Assists are long sequences of uops that are required in certain corner-cases for operations that cannot be handled natively by the execution pipeline. For example; when working with very small floating point values (so-called Denormals); the FP units are not set up to perform these operations natively. Instead; a sequence of instructions to perform the computation on the Denormals is injected into the pipeline. Since these microcode sequences might be dozens of uops long; Assists can be extremely deleterious to performance and they can be avoided in many cases. Sample with: ASSISTS.ANY", "ScaleUnit": "100%", "Unit": "cpu_core" }, { - "BriefDescription": "This metric estimates fraction of slots the CPU retired uops as a result of handing SSE to AVX* or AVX* to SSE transition Assists", + "BriefDescription": "This metric estimates fraction of slots the CPU retired uops as a result of handing SSE to AVX* or AVX* to SSE transition Assists.", "MetricExpr": "63 * cpu_core@ASSISTS.SSE_AVX_MIX@ / tma_info_thread_slots", "MetricGroup": "HPC;TopdownL5;tma_L5_group;tma_assists_group", "MetricName": "tma_avx_assists", @@ -751,7 +751,7 @@ { "BriefDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend", "DefaultMetricgroupName": "TopdownL1", - "MetricExpr": "topdown\\-be\\-bound / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * slots", + "MetricExpr": "cpu_core@topdown\\-be\\-bound@ / (cpu_core@topdown\\-fe\\-bound@ + cpu_core@topdown\\-bad\\-spec@ + cpu_core@topdown\\-retiring@ + cpu_core@topdown\\-be\\-bound@) + 0 * tma_info_thread_slots", "MetricGroup": "BvOB;Default;TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_backend_bound", "MetricThreshold": "tma_backend_bound > 0.2", @@ -768,13 +768,13 @@ "MetricName": "tma_bad_speculation", "MetricThreshold": "tma_bad_speculation > 0.15", "MetricgroupNoGroup": "TopdownL1;Default", - "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example", + "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.", "ScaleUnit": "100%", "Unit": "cpu_core" }, { "BriefDescription": "Total pipeline cost of instruction fetch related bottlenecks by large code footprint programs (i-side cache; TLB and BTB misses)", - "MetricExpr": "100 * tma_fetch_latency * (tma_itlb_misses + tma_icache_misses + tma_unknown_branches) / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches)", + "MetricExpr": "100 * tma_fetch_latency * (tma_itlb_misses + tma_icache_misses + tma_unknown_branches) / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches)", "MetricGroup": "BigFootprint;BvBC;Fed;Frontend;IcMiss;MemoryTLB", "MetricName": "tma_bottleneck_big_code", "MetricThreshold": "tma_bottleneck_big_code > 20", @@ -791,7 +791,7 @@ }, { "BriefDescription": "Total pipeline cost of external Memory- or Cache-Bandwidth related bottlenecks", - "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_mem_bandwidth / (tma_mem_bandwidth + tma_mem_latency)) + tma_memory_bound * (tma_l3_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_sq_full / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_memory_bound * (tma_l1_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_fb_full / (tma_dtlb_load + tma_store_fwd_blk + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_fb_full)))", + "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_mem_bandwidth / (tma_mem_bandwidth + tma_mem_latency)) + tma_memory_bound * (tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_sq_full / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_fb_full / (tma_dtlb_load + tma_fb_full + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)))", "MetricGroup": "BvMB;Mem;MemoryBW;Offcore;tma_issueBW", "MetricName": "tma_bottleneck_cache_memory_bandwidth", "MetricThreshold": "tma_bottleneck_cache_memory_bandwidth > 20", @@ -800,7 +800,7 @@ }, { "BriefDescription": "Total pipeline cost of external Memory- or Cache-Latency related bottlenecks", - "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_mem_latency / (tma_mem_bandwidth + tma_mem_latency)) + tma_memory_bound * (tma_l3_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_l3_hit_latency / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_memory_bound * tma_l2_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound) + tma_memory_bound * (tma_l1_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_l1_latency_dependency / (tma_dtlb_load + tma_store_fwd_blk + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_fb_full)) + tma_memory_bound * (tma_l1_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_lock_latency / (tma_dtlb_load + tma_store_fwd_blk + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_fb_full)) + tma_memory_bound * (tma_l1_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_split_loads / (tma_dtlb_load + tma_store_fwd_blk + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_fb_full)) + tma_memory_bound * (tma_store_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_split_stores / (tma_store_latency + tma_false_sharing + tma_split_stores + tma_streaming_stores + tma_dtlb_store)) + tma_memory_bound * (tma_store_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_store_latency / (tma_store_latency + tma_false_sharing + tma_split_stores + tma_streaming_stores + tma_dtlb_store)))", + "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_mem_latency / (tma_mem_bandwidth + tma_mem_latency)) + tma_memory_bound * (tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_l3_hit_latency / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_memory_bound * tma_l2_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) + tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_l1_latency_dependency / (tma_dtlb_load + tma_fb_full + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_lock_latency / (tma_dtlb_load + tma_fb_full + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_split_loads / (tma_dtlb_load + tma_fb_full + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_memory_bound * (tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_split_stores / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency + tma_streaming_stores)) + tma_memory_bound * (tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_store_latency / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency + tma_streaming_stores)))", "MetricGroup": "BvML;Mem;MemoryLat;Offcore;tma_issueLat", "MetricName": "tma_bottleneck_cache_memory_latency", "MetricThreshold": "tma_bottleneck_cache_memory_latency > 20", @@ -809,16 +809,16 @@ }, { "BriefDescription": "Total pipeline cost when the execution is compute-bound - an estimation", - "MetricExpr": "100 * (tma_core_bound * tma_divider / (tma_divider + tma_serializing_operation + tma_ports_utilization) + tma_core_bound * (tma_ports_utilization / (tma_divider + tma_serializing_operation + tma_ports_utilization)) * (tma_ports_utilized_3m / (tma_ports_utilized_0 + tma_ports_utilized_1 + tma_ports_utilized_2 + tma_ports_utilized_3m)))", + "MetricExpr": "100 * (tma_core_bound * tma_divider / (tma_divider + tma_ports_utilization + tma_serializing_operation) + tma_core_bound * (tma_ports_utilization / (tma_divider + tma_ports_utilization + tma_serializing_operation)) * (tma_ports_utilized_3m / (tma_ports_utilized_0 + tma_ports_utilized_1 + tma_ports_utilized_2 + tma_ports_utilized_3m)))", "MetricGroup": "BvCB;Cor;tma_issueComp", "MetricName": "tma_bottleneck_compute_bound_est", "MetricThreshold": "tma_bottleneck_compute_bound_est > 20", - "PublicDescription": "Total pipeline cost when the execution is compute-bound - an estimation. Covers Core Bound when High ILP as well as when long-latency execution units are busy", + "PublicDescription": "Total pipeline cost when the execution is compute-bound - an estimation. Covers Core Bound when High ILP as well as when long-latency execution units are busy. Related metrics: ", "Unit": "cpu_core" }, { "BriefDescription": "Total pipeline cost of instruction fetch bandwidth related bottlenecks (when the front-end could not sustain operations delivery to the back-end)", - "MetricExpr": "100 * (tma_frontend_bound - (1 - 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts) * tma_fetch_latency * tma_mispredicts_resteers / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches) - (1 - cpu_core@INST_RETIRED.REP_ITERATION@ / cpu_core@UOPS_RETIRED.MS\\,cmask\\=0x1@) * (tma_fetch_latency * (tma_ms_switches + tma_branch_resteers * (tma_clears_resteers + tma_mispredicts_resteers * tma_other_mispredicts / tma_branch_mispredicts) / (tma_mispredicts_resteers + tma_clears_resteers + tma_unknown_branches)) / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches) + tma_fetch_bandwidth * tma_ms / (tma_mite + tma_dsb + tma_lsd + tma_ms))) - tma_bottleneck_big_code", + "MetricExpr": "100 * (tma_frontend_bound - (1 - 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts) * tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) - (1 - cpu_core@INST_RETIRED.REP_ITERATION@ / cpu_core@UOPS_RETIRED.MS\\,cmask\\=1@) * (tma_fetch_latency * (tma_ms_switches + tma_branch_resteers * (tma_clears_resteers + tma_mispredicts_resteers * tma_other_mispredicts / tma_branch_mispredicts) / (tma_clears_resteers + tma_mispredicts_resteers + tma_unknown_branches)) / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) + tma_fetch_bandwidth * tma_ms / (tma_dsb + tma_lsd + tma_mite + tma_ms))) - tma_bottleneck_big_code", "MetricGroup": "BvFB;Fed;FetchBW;Frontend", "MetricName": "tma_bottleneck_instruction_fetch_bw", "MetricThreshold": "tma_bottleneck_instruction_fetch_bw > 20", @@ -826,7 +826,7 @@ }, { "BriefDescription": "Total pipeline cost of irregular execution (e.g", - "MetricExpr": "100 * ((1 - cpu_core@INST_RETIRED.REP_ITERATION@ / cpu_core@UOPS_RETIRED.MS\\,cmask\\=0x1@) * (tma_fetch_latency * (tma_ms_switches + tma_branch_resteers * (tma_clears_resteers + tma_mispredicts_resteers * tma_other_mispredicts / tma_branch_mispredicts) / (tma_mispredicts_resteers + tma_clears_resteers + tma_unknown_branches)) / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches) + tma_fetch_bandwidth * tma_ms / (tma_mite + tma_dsb + tma_lsd + tma_ms)) + 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts * tma_branch_mispredicts + tma_machine_clears * tma_other_nukes / tma_other_nukes + tma_core_bound * (tma_serializing_operation + cpu_core@RS.EMPTY_RESOURCE@ / tma_info_thread_clks * tma_ports_utilized_0) / (tma_divider + tma_serializing_operation + tma_ports_utilization) + tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * tma_heavy_operations)", + "MetricExpr": "100 * ((1 - cpu_core@INST_RETIRED.REP_ITERATION@ / cpu_core@UOPS_RETIRED.MS\\,cmask\\=1@) * (tma_fetch_latency * (tma_ms_switches + tma_branch_resteers * (tma_clears_resteers + tma_mispredicts_resteers * tma_other_mispredicts / tma_branch_mispredicts) / (tma_clears_resteers + tma_mispredicts_resteers + tma_unknown_branches)) / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) + tma_fetch_bandwidth * tma_ms / (tma_dsb + tma_lsd + tma_mite + tma_ms)) + 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts * tma_branch_mispredicts + tma_machine_clears * tma_other_nukes / tma_other_nukes + tma_core_bound * (tma_serializing_operation + cpu_core@RS.EMPTY_RESOURCE@ / tma_info_thread_clks * tma_ports_utilized_0) / (tma_divider + tma_ports_utilization + tma_serializing_operation) + tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * tma_heavy_operations)", "MetricGroup": "Bad;BvIO;Cor;Ret;tma_issueMS", "MetricName": "tma_bottleneck_irregular_overhead", "MetricThreshold": "tma_bottleneck_irregular_overhead > 10", @@ -835,7 +835,7 @@ }, { "BriefDescription": "Total pipeline cost of Memory Address Translation related bottlenecks (data-side TLBs)", - "MetricExpr": "100 * (tma_memory_bound * (tma_l1_bound / max(tma_memory_bound, tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_dtlb_load / max(tma_l1_bound, tma_dtlb_load + tma_store_fwd_blk + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_fb_full)) + tma_memory_bound * (tma_store_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_dtlb_store / (tma_store_latency + tma_false_sharing + tma_split_stores + tma_streaming_stores + tma_dtlb_store)))", + "MetricExpr": "100 * (tma_memory_bound * (tma_l1_bound / max(tma_memory_bound, tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_dtlb_load / max(tma_l1_bound, tma_dtlb_load + tma_fb_full + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_memory_bound * (tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_dtlb_store / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency + tma_streaming_stores)))", "MetricGroup": "BvMT;Mem;MemoryTLB;Offcore;tma_issueTLB", "MetricName": "tma_bottleneck_memory_data_tlbs", "MetricThreshold": "tma_bottleneck_memory_data_tlbs > 20", @@ -844,16 +844,16 @@ }, { "BriefDescription": "Total pipeline cost of Memory Synchronization related bottlenecks (data transfers and coherency updates across processors)", - "MetricExpr": "100 * (tma_memory_bound * (tma_l3_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound) * (tma_contested_accesses + tma_data_sharing) / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full) + tma_store_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound) * tma_false_sharing / (tma_store_latency + tma_false_sharing + tma_split_stores + tma_streaming_stores + tma_dtlb_store - tma_store_latency)) + tma_machine_clears * (1 - tma_other_nukes / tma_other_nukes))", + "MetricExpr": "100 * (tma_memory_bound * (tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_contested_accesses + tma_data_sharing) / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full) + tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * tma_false_sharing / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency + tma_streaming_stores - tma_store_latency)) + tma_machine_clears * (1 - tma_other_nukes / tma_other_nukes))", "MetricGroup": "BvMS;LockCont;Mem;Offcore;tma_issueSyncxn", "MetricName": "tma_bottleneck_memory_synchronization", "MetricThreshold": "tma_bottleneck_memory_synchronization > 10", - "PublicDescription": "Total pipeline cost of Memory Synchronization related bottlenecks (data transfers and coherency updates across processors). Related metrics: tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_machine_clears", + "PublicDescription": "Total pipeline cost of Memory Synchronization related bottlenecks (data transfers and coherency updates across processors). Related metrics: tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_machine_clears, tma_remote_cache", "Unit": "cpu_core" }, { "BriefDescription": "Total pipeline cost of Branch Misprediction related bottlenecks", - "MetricExpr": "100 * (1 - 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts) * (tma_branch_mispredicts + tma_fetch_latency * tma_mispredicts_resteers / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches))", + "MetricExpr": "100 * (1 - 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts) * (tma_branch_mispredicts + tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches))", "MetricGroup": "Bad;BadSpec;BrMispredicts;BvMP;tma_issueBM", "MetricName": "tma_bottleneck_mispredictions", "MetricThreshold": "tma_bottleneck_mispredictions > 20", @@ -866,11 +866,11 @@ "MetricGroup": "BvOB;Cor;Offcore", "MetricName": "tma_bottleneck_other_bottlenecks", "MetricThreshold": "tma_bottleneck_other_bottlenecks > 20", - "PublicDescription": "Total pipeline cost of remaining bottlenecks in the back-end. Examples include data-dependencies (Core Bound when Low ILP) and other unlisted memory-related stalls", + "PublicDescription": "Total pipeline cost of remaining bottlenecks in the back-end. Examples include data-dependencies (Core Bound when Low ILP) and other unlisted memory-related stalls.", "Unit": "cpu_core" }, { - "BriefDescription": "Total pipeline cost of \"useful operations\" - the portion of Retiring category not covered by Branching_Overhead nor Irregular_Overhead", + "BriefDescription": "Total pipeline cost of \"useful operations\" - the portion of Retiring category not covered by Branching_Overhead nor Irregular_Overhead.", "MetricExpr": "100 * (tma_retiring - (cpu_core@BR_INST_RETIRED.ALL_BRANCHES@ + 2 * cpu_core@BR_INST_RETIRED.NEAR_CALL@ + cpu_core@INST_RETIRED.NOP@) / tma_info_thread_slots - tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * tma_heavy_operations)", "MetricGroup": "BvUW;Ret", "MetricName": "tma_bottleneck_useful_work", @@ -879,7 +879,7 @@ }, { "BriefDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction", - "MetricExpr": "topdown\\-br\\-mispredict / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * slots", + "MetricExpr": "cpu_core@topdown\\-br\\-mispredict@ / (cpu_core@topdown\\-fe\\-bound@ + cpu_core@topdown\\-bad\\-spec@ + cpu_core@topdown\\-retiring@ + cpu_core@topdown\\-be\\-bound@) + 0 * tma_info_thread_slots", "MetricGroup": "BadSpec;BrMispredicts;BvMP;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueBM", "MetricName": "tma_branch_mispredicts", "MetricThreshold": "tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", @@ -893,26 +893,26 @@ "MetricExpr": "cpu_core@INT_MISC.CLEAR_RESTEER_CYCLES@ / tma_info_thread_clks + tma_unknown_branches", "MetricGroup": "FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group", "MetricName": "tma_branch_resteers", - "MetricThreshold": "tma_branch_resteers > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", - "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers. Branch Resteers estimates the Frontend delay in fetching operations from corrected path; following all sorts of miss-predicted branches. For example; branchy code with lots of miss-predictions might get categorized under Branch Resteers. Note the value of this node may overlap with its siblings. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_l3_hit_latency, tma_store_latency", + "MetricThreshold": "tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers. Branch Resteers estimates the Frontend delay in fetching operations from corrected path; following all sorts of miss-predicted branches. For example; branchy code with lots of miss-predictions might get categorized under Branch Resteers. Note the value of this node may overlap with its siblings. Sample with: BR_MISP_RETIRED.ALL_BRANCHES", "ScaleUnit": "100%", "Unit": "cpu_core" }, { - "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due staying in C0.1 power-performance optimized state (Faster wakeup time; Smaller power savings)", + "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due staying in C0.1 power-performance optimized state (Faster wakeup time; Smaller power savings).", "MetricExpr": "cpu_core@CPU_CLK_UNHALTED.C01@ / tma_info_thread_clks", "MetricGroup": "C0Wait;TopdownL4;tma_L4_group;tma_serializing_operation_group", "MetricName": "tma_c01_wait", - "MetricThreshold": "tma_c01_wait > 0.05 & tma_serializing_operation > 0.1 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_c01_wait > 0.05 & (tma_serializing_operation > 0.1 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", "ScaleUnit": "100%", "Unit": "cpu_core" }, { - "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due staying in C0.2 power-performance optimized state (Slower wakeup time; Larger power savings)", + "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due staying in C0.2 power-performance optimized state (Slower wakeup time; Larger power savings).", "MetricExpr": "cpu_core@CPU_CLK_UNHALTED.C02@ / tma_info_thread_clks", "MetricGroup": "C0Wait;TopdownL4;tma_L4_group;tma_serializing_operation_group", "MetricName": "tma_c02_wait", - "MetricThreshold": "tma_c02_wait > 0.05 & tma_serializing_operation > 0.1 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_c02_wait > 0.05 & (tma_serializing_operation > 0.1 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -921,7 +921,7 @@ "MetricExpr": "max(0, tma_microcode_sequencer - tma_assists)", "MetricGroup": "TopdownL4;tma_L4_group;tma_microcode_sequencer_group", "MetricName": "tma_cisc", - "MetricThreshold": "tma_cisc > 0.1 & tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1", + "MetricThreshold": "tma_cisc > 0.1 & (tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1)", "PublicDescription": "This metric estimates fraction of cycles the CPU retired uops originated from CISC (complex instruction set computer) instruction. A CISC instruction has multiple uops that are required to perform the instruction's functionality as in the case of read-modify-write as an example. Since these instructions require multiple uops they may or may not imply sub-optimal use of machine resources. Sample with: FRONTEND_RETIRED.MS_FLOWS", "ScaleUnit": "100%", "Unit": "cpu_core" @@ -931,26 +931,26 @@ "MetricExpr": "(1 - tma_branch_mispredicts / tma_bad_speculation) * cpu_core@INT_MISC.CLEAR_RESTEER_CYCLES@ / tma_info_thread_clks", "MetricGroup": "BadSpec;MachineClears;TopdownL4;tma_L4_group;tma_branch_resteers_group;tma_issueMC", "MetricName": "tma_clears_resteers", - "MetricThreshold": "tma_clears_resteers > 0.05 & tma_branch_resteers > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricThreshold": "tma_clears_resteers > 0.05 & (tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))", "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Machine Clears. Sample with: INT_MISC.CLEAR_RESTEER_CYCLES. Related metrics: tma_l1_bound, tma_machine_clears, tma_microcode_sequencer, tma_ms_switches", "ScaleUnit": "100%", "Unit": "cpu_core" }, { - "BriefDescription": "This metric estimates fraction of cycles the CPU was stalled due to instruction cache misses that hit in the L2 cache", + "BriefDescription": "This metric estimates fraction of cycles the CPU was stalled due to instruction cache misses that hit in the L2 cache.", "MetricExpr": "max(0, tma_icache_misses - tma_code_l2_miss)", "MetricGroup": "FetchLat;IcMiss;Offcore;TopdownL4;tma_L4_group;tma_icache_misses_group", "MetricName": "tma_code_l2_hit", - "MetricThreshold": "tma_code_l2_hit > 0.05 & tma_icache_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricThreshold": "tma_code_l2_hit > 0.05 & (tma_icache_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))", "ScaleUnit": "100%", "Unit": "cpu_core" }, { - "BriefDescription": "This metric estimates fraction of cycles the CPU was stalled due to instruction cache misses that miss in the L2 cache", + "BriefDescription": "This metric estimates fraction of cycles the CPU was stalled due to instruction cache misses that miss in the L2 cache.", "MetricExpr": "cpu_core@OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_CODE_RD@ / tma_info_thread_clks", "MetricGroup": "FetchLat;IcMiss;Offcore;TopdownL4;tma_L4_group;tma_icache_misses_group", "MetricName": "tma_code_l2_miss", - "MetricThreshold": "tma_code_l2_miss > 0.05 & tma_icache_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricThreshold": "tma_code_l2_miss > 0.05 & (tma_icache_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -959,7 +959,7 @@ "MetricExpr": "max(0, tma_itlb_misses - tma_code_stlb_miss)", "MetricGroup": "FetchLat;MemoryTLB;TopdownL4;tma_L4_group;tma_itlb_misses_group", "MetricName": "tma_code_stlb_hit", - "MetricThreshold": "tma_code_stlb_hit > 0.05 & tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricThreshold": "tma_code_stlb_hit > 0.05 & (tma_itlb_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -968,35 +968,36 @@ "MetricExpr": "cpu_core@ITLB_MISSES.WALK_ACTIVE@ / tma_info_thread_clks", "MetricGroup": "FetchLat;MemoryTLB;TopdownL4;tma_L4_group;tma_itlb_misses_group", "MetricName": "tma_code_stlb_miss", - "MetricThreshold": "tma_code_stlb_miss > 0.05 & tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricThreshold": "tma_code_stlb_miss > 0.05 & (tma_itlb_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))", "ScaleUnit": "100%", "Unit": "cpu_core" }, { - "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 2 or 4 MB pages for (instruction) code accesses", + "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 2 or 4 MB pages for (instruction) code accesses.", "MetricExpr": "tma_code_stlb_miss * cpu_core@ITLB_MISSES.WALK_COMPLETED_2M_4M@ / (cpu_core@ITLB_MISSES.WALK_COMPLETED_4K@ + cpu_core@ITLB_MISSES.WALK_COMPLETED_2M_4M@)", "MetricGroup": "FetchLat;MemoryTLB;TopdownL5;tma_L5_group;tma_code_stlb_miss_group", "MetricName": "tma_code_stlb_miss_2m", - "MetricThreshold": "tma_code_stlb_miss_2m > 0.05 & tma_code_stlb_miss > 0.05 & tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricThreshold": "tma_code_stlb_miss_2m > 0.05 & (tma_code_stlb_miss > 0.05 & (tma_itlb_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)))", "ScaleUnit": "100%", "Unit": "cpu_core" }, { - "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 4 KB pages for (instruction) code accesses", + "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 4 KB pages for (instruction) code accesses.", "MetricExpr": "tma_code_stlb_miss * cpu_core@ITLB_MISSES.WALK_COMPLETED_4K@ / (cpu_core@ITLB_MISSES.WALK_COMPLETED_4K@ + cpu_core@ITLB_MISSES.WALK_COMPLETED_2M_4M@)", "MetricGroup": "FetchLat;MemoryTLB;TopdownL5;tma_L5_group;tma_code_stlb_miss_group", "MetricName": "tma_code_stlb_miss_4k", - "MetricThreshold": "tma_code_stlb_miss_4k > 0.05 & tma_code_stlb_miss > 0.05 & tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricThreshold": "tma_code_stlb_miss_4k > 0.05 & (tma_code_stlb_miss > 0.05 & (tma_itlb_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)))", "ScaleUnit": "100%", "Unit": "cpu_core" }, { "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses", - "MetricExpr": "((28 * tma_info_system_core_frequency - 3 * tma_info_system_core_frequency) * (cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD@ * (cpu_core@OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM@ / (cpu_core@OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM@ + cpu_core@OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD@))) + (27 * tma_info_system_core_frequency - 3 * tma_info_system_core_frequency) * cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS@) * (1 + cpu_core@MEM_LOAD_RETIRED.FB_HIT@ / cpu_core@MEM_LOAD_RETIRED.L1_MISS@ / 2) / tma_info_thread_clks", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "(25 * tma_info_system_core_frequency * (cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD@ * (cpu_core@OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM@ / (cpu_core@OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM@ + cpu_core@OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD@))) + 24 * tma_info_system_core_frequency * cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS@) * (1 + cpu_core@MEM_LOAD_RETIRED.FB_HIT@ / cpu_core@MEM_LOAD_RETIRED.L1_MISS@ / 2) / tma_info_thread_clks", "MetricGroup": "BvMS;DataSharing;LockCont;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group", "MetricName": "tma_contested_accesses", - "MetricThreshold": "tma_contested_accesses > 0.05 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", - "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses. Contested accesses occur when data written by one Logical Processor are read by another Logical Processor on a different Physical Core. Examples of contested accesses include synchronizations such as locks; true data sharing such as modified locked variables; and false sharing. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD, MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS. Related metrics: tma_bottleneck_memory_synchronization, tma_data_sharing, tma_false_sharing, tma_machine_clears", + "MetricThreshold": "tma_contested_accesses > 0.05 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses. Contested accesses occur when data written by one Logical Processor are read by another Logical Processor on a different Physical Core. Examples of contested accesses include synchronizations such as locks; true data sharing such as modified locked variables; and false sharing. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD;MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS. Related metrics: tma_bottleneck_memory_synchronization, tma_data_sharing, tma_false_sharing, tma_machine_clears, tma_remote_cache", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -1007,26 +1008,27 @@ "MetricName": "tma_core_bound", "MetricThreshold": "tma_core_bound > 0.1 & tma_backend_bound > 0.2", "MetricgroupNoGroup": "TopdownL2", - "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck. Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations)", + "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck. Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations).", "ScaleUnit": "100%", "Unit": "cpu_core" }, { "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses", - "MetricExpr": "(27 * tma_info_system_core_frequency - 3 * tma_info_system_core_frequency) * (cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_NO_FWD@ + cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD@ * (1 - cpu_core@OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM@ / (cpu_core@OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM@ + cpu_core@OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD@))) * (1 + cpu_core@MEM_LOAD_RETIRED.FB_HIT@ / cpu_core@MEM_LOAD_RETIRED.L1_MISS@ / 2) / tma_info_thread_clks", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "24 * tma_info_system_core_frequency * (cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_NO_FWD@ + cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD@ * (1 - cpu_core@OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM@ / (cpu_core@OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM@ + cpu_core@OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD@))) * (1 + cpu_core@MEM_LOAD_RETIRED.FB_HIT@ / cpu_core@MEM_LOAD_RETIRED.L1_MISS@ / 2) / tma_info_thread_clks", "MetricGroup": "BvMS;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group", "MetricName": "tma_data_sharing", - "MetricThreshold": "tma_data_sharing > 0.05 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", - "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses. Data shared by multiple Logical Processors (even just read shared) may cause increased access latency due to cache coherency. Excessive data sharing can drastically harm multithreaded performance. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_NO_FWD. Related metrics: tma_bottleneck_memory_synchronization, tma_contested_accesses, tma_false_sharing, tma_machine_clears", + "MetricThreshold": "tma_data_sharing > 0.05 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses. Data shared by multiple Logical Processors (even just read shared) may cause increased access latency due to cache coherency. Excessive data sharing can drastically harm multithreaded performance. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_NO_FWD. Related metrics: tma_bottleneck_memory_synchronization, tma_contested_accesses, tma_false_sharing, tma_machine_clears, tma_remote_cache", "ScaleUnit": "100%", "Unit": "cpu_core" }, { "BriefDescription": "This metric represents fraction of cycles where decoder-0 was the only active decoder", - "MetricExpr": "(cpu_core@INST_DECODED.DECODERS\\,cmask\\=0x1@ - cpu_core@INST_DECODED.DECODERS\\,cmask\\=0x2@) / tma_info_core_core_clks / 2", + "MetricExpr": "(cpu_core@INST_DECODED.DECODERS\\,cmask\\=1@ - cpu_core@INST_DECODED.DECODERS\\,cmask\\=2@) / tma_info_core_core_clks / 2", "MetricGroup": "DSBmiss;FetchBW;TopdownL4;tma_L4_group;tma_issueD0;tma_mite_group", "MetricName": "tma_decoder0_alone", - "MetricThreshold": "tma_decoder0_alone > 0.1 & tma_mite > 0.1 & tma_fetch_bandwidth > 0.2", + "MetricThreshold": "tma_decoder0_alone > 0.1 & (tma_mite > 0.1 & tma_fetch_bandwidth > 0.2)", "PublicDescription": "This metric represents fraction of cycles where decoder-0 was the only active decoder. Related metrics: tma_few_uops_instructions", "ScaleUnit": "100%", "Unit": "cpu_core" @@ -1036,7 +1038,7 @@ "MetricExpr": "cpu_core@ARITH.DIV_ACTIVE@ / tma_info_thread_clks", "MetricGroup": "BvCB;TopdownL3;tma_L3_group;tma_core_bound_group", "MetricName": "tma_divider", - "MetricThreshold": "tma_divider > 0.2 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_divider > 0.2 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)", "PublicDescription": "This metric represents fraction of cycles where the Divider unit was active. Divide and square root instructions are performed by the Divider unit and can take considerably longer latency than integer or Floating Point addition; subtraction; or multiplication. Sample with: ARITH.DIVIDER_ACTIVE", "ScaleUnit": "100%", "Unit": "cpu_core" @@ -1046,7 +1048,7 @@ "MetricExpr": "cpu_core@MEMORY_ACTIVITY.STALLS_L3_MISS@ / tma_info_thread_clks", "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_dram_bound", - "MetricThreshold": "tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", "PublicDescription": "This metric estimates how often the CPU was stalled on accesses to external memory (DRAM) by loads. Better caching can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L3_MISS", "ScaleUnit": "100%", "Unit": "cpu_core" @@ -1057,7 +1059,7 @@ "MetricGroup": "DSB;FetchBW;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group", "MetricName": "tma_dsb", "MetricThreshold": "tma_dsb > 0.15 & tma_fetch_bandwidth > 0.2", - "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to DSB (decoded uop cache) fetch pipeline. For example; inefficient utilization of the DSB cache structure or bank conflict when reading from it; are categorized here", + "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to DSB (decoded uop cache) fetch pipeline. For example; inefficient utilization of the DSB cache structure or bank conflict when reading from it; are categorized here.", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -1066,28 +1068,28 @@ "MetricExpr": "cpu_core@DSB2MITE_SWITCHES.PENALTY_CYCLES@ / tma_info_thread_clks", "MetricGroup": "DSBmiss;FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueFB", "MetricName": "tma_dsb_switches", - "MetricThreshold": "tma_dsb_switches > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", - "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines. The DSB (decoded i-cache) is a Uop Cache where the front-end directly delivers Uops (micro operations) avoiding heavy x86 decoding. The DSB pipeline has shorter latency and delivered higher bandwidth than the MITE (legacy instruction decode pipeline). Switching between the two pipelines can cause penalties hence this metric measures the exposed penalty. Sample with: FRONTEND_RETIRED.DSB_MISS. Related metrics: tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp", + "MetricThreshold": "tma_dsb_switches > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines. The DSB (decoded i-cache) is a Uop Cache where the front-end directly delivers Uops (micro operations) avoiding heavy x86 decoding. The DSB pipeline has shorter latency and delivered higher bandwidth than the MITE (legacy instruction decode pipeline). Switching between the two pipelines can cause penalties hence this metric measures the exposed penalty. Sample with: FRONTEND_RETIRED.DSB_MISS_PS. Related metrics: tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp", "ScaleUnit": "100%", "Unit": "cpu_core" }, { "BriefDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses", - "MetricExpr": "min(7 * cpu_core@DTLB_LOAD_MISSES.STLB_HIT\\,cmask\\=0x1@ + cpu_core@DTLB_LOAD_MISSES.WALK_ACTIVE@, max(cpu_core@CYCLE_ACTIVITY.CYCLES_MEM_ANY@ - cpu_core@MEMORY_ACTIVITY.CYCLES_L1D_MISS@, 0)) / tma_info_thread_clks", + "MetricExpr": "min(7 * cpu_core@DTLB_LOAD_MISSES.STLB_HIT\\,cmask\\=1@ + cpu_core@DTLB_LOAD_MISSES.WALK_ACTIVE@, max(cpu_core@CYCLE_ACTIVITY.CYCLES_MEM_ANY@ - cpu_core@MEMORY_ACTIVITY.CYCLES_L1D_MISS@, 0)) / tma_info_thread_clks", "MetricGroup": "BvMT;MemoryTLB;TopdownL4;tma_L4_group;tma_issueTLB;tma_l1_bound_group", "MetricName": "tma_dtlb_load", - "MetricThreshold": "tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", - "PublicDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses. TLBs (Translation Look-aside Buffers) are processor caches for recently used entries out of the Page Tables that are used to map virtual- to physical-addresses by the operating system. This metric approximates the potential delay of demand loads missing the first-level data TLB (assuming worst case scenario with back to back misses to different pages). This includes hitting in the second-level TLB (STLB) as well as performing a hardware page walk on an STLB miss. Sample with: MEM_INST_RETIRED.STLB_MISS_LOADS. Related metrics: tma_bottleneck_memory_data_tlbs, tma_dtlb_store", + "MetricThreshold": "tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses. TLBs (Translation Look-aside Buffers) are processor caches for recently used entries out of the Page Tables that are used to map virtual- to physical-addresses by the operating system. This metric approximates the potential delay of demand loads missing the first-level data TLB (assuming worst case scenario with back to back misses to different pages). This includes hitting in the second-level TLB (STLB) as well as performing a hardware page walk on an STLB miss. Sample with: MEM_INST_RETIRED.STLB_MISS_LOADS_PS. Related metrics: tma_bottleneck_memory_data_tlbs, tma_dtlb_store", "ScaleUnit": "100%", "Unit": "cpu_core" }, { "BriefDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses", - "MetricExpr": "(7 * cpu_core@DTLB_STORE_MISSES.STLB_HIT\\,cmask\\=0x1@ + cpu_core@DTLB_STORE_MISSES.WALK_ACTIVE@) / tma_info_core_core_clks", + "MetricExpr": "(7 * cpu_core@DTLB_STORE_MISSES.STLB_HIT\\,cmask\\=1@ + cpu_core@DTLB_STORE_MISSES.WALK_ACTIVE@) / tma_info_core_core_clks", "MetricGroup": "BvMT;MemoryTLB;TopdownL4;tma_L4_group;tma_issueTLB;tma_store_bound_group", "MetricName": "tma_dtlb_store", - "MetricThreshold": "tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", - "PublicDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses. As with ordinary data caching; focus on improving data locality and reducing working-set size to reduce DTLB overhead. Additionally; consider using profile-guided optimization (PGO) to collocate frequently-used data on the same page. Try using larger page sizes for large amounts of frequently-used data. Sample with: MEM_INST_RETIRED.STLB_MISS_STORES. Related metrics: tma_bottleneck_memory_data_tlbs, tma_dtlb_load", + "MetricThreshold": "tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses. As with ordinary data caching; focus on improving data locality and reducing working-set size to reduce DTLB overhead. Additionally; consider using profile-guided optimization (PGO) to collocate frequently-used data on the same page. Try using larger page sizes for large amounts of frequently-used data. Sample with: MEM_INST_RETIRED.STLB_MISS_STORES_PS. Related metrics: tma_bottleneck_memory_data_tlbs, tma_dtlb_load", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -1096,8 +1098,8 @@ "MetricExpr": "28 * tma_info_system_core_frequency * cpu_core@OCR.DEMAND_RFO.L3_HIT.SNOOP_HITM@ / tma_info_thread_clks", "MetricGroup": "BvMS;DataSharing;LockCont;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_store_bound_group", "MetricName": "tma_false_sharing", - "MetricThreshold": "tma_false_sharing > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", - "PublicDescription": "This metric roughly estimates how often CPU was handling synchronizations due to False Sharing. False Sharing is a multithreading hiccup; where multiple Logical Processors contend on different data-elements mapped into the same cache line. Sample with: OCR.DEMAND_RFO.L3_HIT.SNOOP_HITM. Related metrics: tma_bottleneck_memory_synchronization, tma_contested_accesses, tma_data_sharing, tma_machine_clears", + "MetricThreshold": "tma_false_sharing > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric roughly estimates how often CPU was handling synchronizations due to False Sharing. False Sharing is a multithreading hiccup; where multiple Logical Processors contend on different data-elements mapped into the same cache line. Sample with: OCR.DEMAND_RFO.L3_HIT.SNOOP_HITM. Related metrics: tma_bottleneck_memory_synchronization, tma_contested_accesses, tma_data_sharing, tma_machine_clears, tma_remote_cache", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -1118,18 +1120,18 @@ "MetricName": "tma_fetch_bandwidth", "MetricThreshold": "tma_fetch_bandwidth > 0.2", "MetricgroupNoGroup": "TopdownL2", - "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues. For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Sample with: FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1, FRONTEND_RETIRED.LATENCY_GE_1, FRONTEND_RETIRED.LATENCY_GE_2. Related metrics: tma_dsb_switches, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp", + "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues. For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Sample with: FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1;FRONTEND_RETIRED.LATENCY_GE_1;FRONTEND_RETIRED.LATENCY_GE_2. Related metrics: tma_dsb_switches, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp", "ScaleUnit": "100%", "Unit": "cpu_core" }, { "BriefDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues", - "MetricExpr": "topdown\\-fetch\\-lat / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) - cpu_core@INT_MISC.UOP_DROPPING@ / tma_info_thread_slots", + "MetricExpr": "cpu_core@topdown\\-fetch\\-lat@ / (cpu_core@topdown\\-fe\\-bound@ + cpu_core@topdown\\-bad\\-spec@ + cpu_core@topdown\\-retiring@ + cpu_core@topdown\\-be\\-bound@) - cpu_core@INT_MISC.UOP_DROPPING@ / tma_info_thread_slots", "MetricGroup": "Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group", "MetricName": "tma_fetch_latency", "MetricThreshold": "tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", "MetricgroupNoGroup": "TopdownL2", - "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues. For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: FRONTEND_RETIRED.LATENCY_GE_16, FRONTEND_RETIRED.LATENCY_GE_8", + "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues. For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: FRONTEND_RETIRED.LATENCY_GE_16_PS;FRONTEND_RETIRED.LATENCY_GE_8_PS", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -1149,7 +1151,7 @@ "MetricGroup": "HPC;TopdownL3;tma_L3_group;tma_light_operations_group", "MetricName": "tma_fp_arith", "MetricThreshold": "tma_fp_arith > 0.2 & tma_light_operations > 0.6", - "PublicDescription": "This metric represents overall arithmetic floating-point (FP) operations fraction the CPU has executed (retired). Note this metric's value may exceed its parent due to use of \"Uops\" CountDomain and FMA double-counting", + "PublicDescription": "This metric represents overall arithmetic floating-point (FP) operations fraction the CPU has executed (retired). Note this metric's value may exceed its parent due to use of \"Uops\" CountDomain and FMA double-counting.", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -1159,16 +1161,16 @@ "MetricGroup": "HPC;TopdownL5;tma_L5_group;tma_assists_group", "MetricName": "tma_fp_assists", "MetricThreshold": "tma_fp_assists > 0.1", - "PublicDescription": "This metric roughly estimates fraction of slots the CPU retired uops as a result of handing Floating Point (FP) Assists. FP Assist may apply when working with very small floating point values (so-called Denormals)", + "PublicDescription": "This metric roughly estimates fraction of slots the CPU retired uops as a result of handing Floating Point (FP) Assists. FP Assist may apply when working with very small floating point values (so-called Denormals).", "ScaleUnit": "100%", "Unit": "cpu_core" }, { - "BriefDescription": "This metric represents fraction of cycles where the Floating-Point Divider unit was active", + "BriefDescription": "This metric represents fraction of cycles where the Floating-Point Divider unit was active.", "MetricExpr": "cpu_core@ARITH.FPDIV_ACTIVE@ / tma_info_thread_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_divider_group", "MetricName": "tma_fp_divider", - "MetricThreshold": "tma_fp_divider > 0.2 & tma_divider > 0.2 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_fp_divider > 0.2 & (tma_divider > 0.2 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -1177,8 +1179,8 @@ "MetricExpr": "cpu_core@FP_ARITH_INST_RETIRED.SCALAR@ / (tma_retiring * tma_info_thread_slots)", "MetricGroup": "Compute;Flops;TopdownL4;tma_L4_group;tma_fp_arith_group;tma_issue2P", "MetricName": "tma_fp_scalar", - "MetricThreshold": "tma_fp_scalar > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6", - "PublicDescription": "This metric approximates arithmetic floating-point (FP) scalar uops fraction the CPU has retired. May overcount due to FMA double counting. Related metrics: tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_6, tma_ports_utilized_2", + "MetricThreshold": "tma_fp_scalar > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6)", + "PublicDescription": "This metric approximates arithmetic floating-point (FP) scalar uops fraction the CPU has retired. May overcount due to FMA double counting. Related metrics: tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -1187,8 +1189,8 @@ "MetricExpr": "cpu_core@FP_ARITH_INST_RETIRED.VECTOR@ / (tma_retiring * tma_info_thread_slots)", "MetricGroup": "Compute;Flops;TopdownL4;tma_L4_group;tma_fp_arith_group;tma_issue2P", "MetricName": "tma_fp_vector", - "MetricThreshold": "tma_fp_vector > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6", - "PublicDescription": "This metric approximates arithmetic floating-point (FP) vector uops fraction the CPU has retired aggregated across all vector widths. May overcount due to FMA double counting. Related metrics: tma_fp_scalar, tma_fp_vector_128b, tma_fp_vector_256b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_6, tma_ports_utilized_2", + "MetricThreshold": "tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6)", + "PublicDescription": "This metric approximates arithmetic floating-point (FP) vector uops fraction the CPU has retired aggregated across all vector widths. May overcount due to FMA double counting. Related metrics: tma_fp_scalar, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -1197,8 +1199,8 @@ "MetricExpr": "(cpu_core@FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE@ + cpu_core@FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE@) / (tma_retiring * tma_info_thread_slots)", "MetricGroup": "Compute;Flops;TopdownL5;tma_L5_group;tma_fp_vector_group;tma_issue2P", "MetricName": "tma_fp_vector_128b", - "MetricThreshold": "tma_fp_vector_128b > 0.1 & tma_fp_vector > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6", - "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 128-bit wide vectors. May overcount due to FMA double counting prior to LNL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_256b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_6, tma_ports_utilized_2", + "MetricThreshold": "tma_fp_vector_128b > 0.1 & (tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6))", + "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 128-bit wide vectors. May overcount due to FMA double counting prior to LNL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -1207,41 +1209,41 @@ "MetricExpr": "(cpu_core@FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE@ + cpu_core@FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE@) / (tma_retiring * tma_info_thread_slots)", "MetricGroup": "Compute;Flops;TopdownL5;tma_L5_group;tma_fp_vector_group;tma_issue2P", "MetricName": "tma_fp_vector_256b", - "MetricThreshold": "tma_fp_vector_256b > 0.1 & tma_fp_vector > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6", - "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 256-bit wide vectors. May overcount due to FMA double counting prior to LNL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_6, tma_ports_utilized_2", + "MetricThreshold": "tma_fp_vector_256b > 0.1 & (tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6))", + "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 256-bit wide vectors. May overcount due to FMA double counting prior to LNL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%", "Unit": "cpu_core" }, { "BriefDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend", "DefaultMetricgroupName": "TopdownL1", - "MetricExpr": "topdown\\-fe\\-bound / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) - cpu_core@INT_MISC.UOP_DROPPING@ / tma_info_thread_slots", + "MetricExpr": "cpu_core@topdown\\-fe\\-bound@ / (cpu_core@topdown\\-fe\\-bound@ + cpu_core@topdown\\-bad\\-spec@ + cpu_core@topdown\\-retiring@ + cpu_core@topdown\\-be\\-bound@) - cpu_core@INT_MISC.UOP_DROPPING@ / tma_info_thread_slots", "MetricGroup": "BvFB;BvIO;Default;PGO;TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_frontend_bound", "MetricThreshold": "tma_frontend_bound > 0.15", "MetricgroupNoGroup": "TopdownL1;Default", - "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound. Sample with: FRONTEND_RETIRED.LATENCY_GE_4", + "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound. Sample with: FRONTEND_RETIRED.LATENCY_GE_4_PS", "ScaleUnit": "100%", "Unit": "cpu_core" }, { - "BriefDescription": "This metric represents fraction of slots where the CPU was retiring fused instructions , where one uop can represent multiple contiguous instructions", + "BriefDescription": "This metric represents fraction of slots where the CPU was retiring fused instructions -- where one uop can represent multiple contiguous instructions", "MetricExpr": "tma_light_operations * cpu_core@INST_RETIRED.MACRO_FUSED@ / (tma_retiring * tma_info_thread_slots)", "MetricGroup": "Branches;BvBO;Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group", "MetricName": "tma_fused_instructions", "MetricThreshold": "tma_fused_instructions > 0.1 & tma_light_operations > 0.6", - "PublicDescription": "This metric represents fraction of slots where the CPU was retiring fused instructions , where one uop can represent multiple contiguous instructions. CMP+JCC or DEC+JCC are common examples of legacy fusions. {([MTL] Note new MOV+OP and Load+OP fusions appear under Other_Light_Ops in MTL!)}", + "PublicDescription": "This metric represents fraction of slots where the CPU was retiring fused instructions -- where one uop can represent multiple contiguous instructions. CMP+JCC or DEC+JCC are common examples of legacy fusions. {([MTL] Note new MOV+OP and Load+OP fusions appear under Other_Light_Ops in MTL!)}", "ScaleUnit": "100%", "Unit": "cpu_core" }, { - "BriefDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations , instructions that require two or more uops or micro-coded sequences", - "MetricExpr": "topdown\\-heavy\\-ops / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * slots", + "BriefDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences", + "MetricExpr": "cpu_core@topdown\\-heavy\\-ops@ / (cpu_core@topdown\\-fe\\-bound@ + cpu_core@topdown\\-bad\\-spec@ + cpu_core@topdown\\-retiring@ + cpu_core@topdown\\-be\\-bound@) + 0 * tma_info_thread_slots", "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_heavy_operations", "MetricThreshold": "tma_heavy_operations > 0.1", "MetricgroupNoGroup": "TopdownL2", - "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations , instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences.([ICL+] Note this may overcount due to approximation using indirect events; [ADL+]). Sample with: UOPS_RETIRED.HEAVY", + "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences.([ICL+] Note this may overcount due to approximation using indirect events; [ADL+]). Sample with: UOPS_RETIRED.HEAVY", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -1250,8 +1252,8 @@ "MetricExpr": "cpu_core@ICACHE_DATA.STALLS@ / tma_info_thread_clks", "MetricGroup": "BigFootprint;BvBC;FetchLat;IcMiss;TopdownL3;tma_L3_group;tma_fetch_latency_group", "MetricName": "tma_icache_misses", - "MetricThreshold": "tma_icache_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", - "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to instruction cache misses. Sample with: FRONTEND_RETIRED.L2_MISS, FRONTEND_RETIRED.L1I_MISS", + "MetricThreshold": "tma_icache_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to instruction cache misses. Sample with: FRONTEND_RETIRED.L2_MISS_PS;FRONTEND_RETIRED.L1I_MISS_PS", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -1264,7 +1266,7 @@ "Unit": "cpu_core" }, { - "BriefDescription": "Instructions per retired Mispredicts for conditional non-taken branches (lower number means higher occurrence rate)", + "BriefDescription": "Instructions per retired Mispredicts for conditional non-taken branches (lower number means higher occurrence rate).", "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / cpu_core@BR_MISP_RETIRED.COND_NTAKEN@", "MetricGroup": "Bad;BrMispredicts", "MetricName": "tma_info_bad_spec_ipmisp_cond_ntaken", @@ -1272,7 +1274,7 @@ "Unit": "cpu_core" }, { - "BriefDescription": "Instructions per retired Mispredicts for conditional taken branches (lower number means higher occurrence rate)", + "BriefDescription": "Instructions per retired Mispredicts for conditional taken branches (lower number means higher occurrence rate).", "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / cpu_core@BR_MISP_RETIRED.COND_TAKEN@", "MetricGroup": "Bad;BrMispredicts", "MetricName": "tma_info_bad_spec_ipmisp_cond_taken", @@ -1280,15 +1282,15 @@ "Unit": "cpu_core" }, { - "BriefDescription": "Instructions per retired Mispredicts for indirect CALL or JMP branches (lower number means higher occurrence rate)", + "BriefDescription": "Instructions per retired Mispredicts for indirect CALL or JMP branches (lower number means higher occurrence rate).", "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / cpu_core@BR_MISP_RETIRED.INDIRECT@", "MetricGroup": "Bad;BrMispredicts", "MetricName": "tma_info_bad_spec_ipmisp_indirect", - "MetricThreshold": "tma_info_bad_spec_ipmisp_indirect < 1000", + "MetricThreshold": "tma_info_bad_spec_ipmisp_indirect < 1e3", "Unit": "cpu_core" }, { - "BriefDescription": "Instructions per retired Mispredicts for return branches (lower number means higher occurrence rate)", + "BriefDescription": "Instructions per retired Mispredicts for return branches (lower number means higher occurrence rate).", "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / cpu_core@BR_MISP_RETIRED.RET@", "MetricGroup": "Bad;BrMispredicts", "MetricName": "tma_info_bad_spec_ipmisp_ret", @@ -1320,7 +1322,7 @@ }, { "BriefDescription": "Total pipeline cost of DSB (uop cache) hits - subset of the Instruction_Fetch_BW Bottleneck", - "MetricExpr": "100 * (tma_frontend_bound * (tma_fetch_bandwidth / (tma_fetch_latency + tma_fetch_bandwidth)) * (tma_dsb / (tma_mite + tma_dsb + tma_lsd + tma_ms)))", + "MetricExpr": "100 * (tma_frontend_bound * (tma_fetch_bandwidth / (tma_fetch_bandwidth + tma_fetch_latency)) * (tma_dsb / (tma_dsb + tma_lsd + tma_mite + tma_ms)))", "MetricGroup": "DSB;Fed;FetchBW;tma_issueFB", "MetricName": "tma_info_botlnk_l2_dsb_bandwidth", "MetricThreshold": "tma_info_botlnk_l2_dsb_bandwidth > 10", @@ -1329,7 +1331,7 @@ }, { "BriefDescription": "Total pipeline cost of DSB (uop cache) misses - subset of the Instruction_Fetch_BW Bottleneck", - "MetricExpr": "100 * (tma_fetch_latency * tma_dsb_switches / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches) + tma_fetch_bandwidth * tma_mite / (tma_mite + tma_dsb + tma_lsd + tma_ms))", + "MetricExpr": "100 * (tma_fetch_latency * tma_dsb_switches / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) + tma_fetch_bandwidth * tma_mite / (tma_dsb + tma_lsd + tma_mite + tma_ms))", "MetricGroup": "DSBmiss;Fed;tma_issueFB", "MetricName": "tma_info_botlnk_l2_dsb_misses", "MetricThreshold": "tma_info_botlnk_l2_dsb_misses > 10", @@ -1338,10 +1340,11 @@ }, { "BriefDescription": "Total pipeline cost of Instruction Cache misses - subset of the Big_Code Bottleneck", - "MetricExpr": "100 * (tma_fetch_latency * tma_icache_misses / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches))", + "MetricExpr": "100 * (tma_fetch_latency * tma_icache_misses / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches))", "MetricGroup": "Fed;FetchLat;IcMiss;tma_issueFL", "MetricName": "tma_info_botlnk_l2_ic_misses", "MetricThreshold": "tma_info_botlnk_l2_ic_misses > 5", + "PublicDescription": "Total pipeline cost of Instruction Cache misses - subset of the Big_Code Bottleneck. Related metrics: ", "Unit": "cpu_core" }, { @@ -1412,12 +1415,12 @@ "MetricExpr": "(cpu_core@FP_ARITH_DISPATCHED.PORT_0@ + cpu_core@FP_ARITH_DISPATCHED.PORT_1@ + cpu_core@FP_ARITH_DISPATCHED.PORT_5@) / (2 * tma_info_core_core_clks)", "MetricGroup": "Cor;Flops;HPC", "MetricName": "tma_info_core_fp_arith_utilization", - "PublicDescription": "Actual per-core usage of the Floating Point non-X87 execution units (regardless of precision or vector-width). Values > 1 are possible due to ([BDW+] Fused-Multiply Add (FMA) counting - common; [ADL+] use all of ADD/MUL/FMA in Scalar or 128/256-bit vectors - less common)", + "PublicDescription": "Actual per-core usage of the Floating Point non-X87 execution units (regardless of precision or vector-width). Values > 1 are possible due to ([BDW+] Fused-Multiply Add (FMA) counting - common; [ADL+] use all of ADD/MUL/FMA in Scalar or 128/256-bit vectors - less common).", "Unit": "cpu_core" }, { "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is execution) per thread (logical-processor)", - "MetricExpr": "cpu_core@UOPS_EXECUTED.THREAD@ / cpu_core@UOPS_EXECUTED.THREAD\\,cmask\\=0x1@", + "MetricExpr": "cpu_core@UOPS_EXECUTED.THREAD@ / cpu_core@UOPS_EXECUTED.THREAD\\,cmask\\=1@", "MetricGroup": "Backend;Cor;Pipeline;PortsUtil", "MetricName": "tma_info_core_ilp", "Unit": "cpu_core" @@ -1432,22 +1435,22 @@ "Unit": "cpu_core" }, { - "BriefDescription": "Average number of cycles of a switch from the DSB fetch-unit to MITE fetch unit - see DSB_Switches tree node for details", - "MetricExpr": "cpu_core@DSB2MITE_SWITCHES.PENALTY_CYCLES@ / cpu_core@DSB2MITE_SWITCHES.PENALTY_CYCLES\\,cmask\\=0x1\\,edge\\=0x1@", + "BriefDescription": "Average number of cycles of a switch from the DSB fetch-unit to MITE fetch unit - see DSB_Switches tree node for details.", + "MetricExpr": "cpu_core@DSB2MITE_SWITCHES.PENALTY_CYCLES@ / cpu_core@DSB2MITE_SWITCHES.PENALTY_CYCLES\\,cmask\\=1\\,edge@", "MetricGroup": "DSBmiss", "MetricName": "tma_info_frontend_dsb_switch_cost", "Unit": "cpu_core" }, { "BriefDescription": "Average number of Uops issued by front-end when it issued something", - "MetricExpr": "cpu_core@UOPS_ISSUED.ANY@ / cpu_core@UOPS_ISSUED.ANY\\,cmask\\=0x1@", + "MetricExpr": "cpu_core@UOPS_ISSUED.ANY@ / cpu_core@UOPS_ISSUED.ANY\\,cmask\\=1@", "MetricGroup": "Fed;FetchBW", "MetricName": "tma_info_frontend_fetch_upc", "Unit": "cpu_core" }, { "BriefDescription": "Average Latency for L1 instruction cache misses", - "MetricExpr": "cpu_core@ICACHE_DATA.STALLS@ / cpu_core@ICACHE_DATA.STALLS\\,cmask\\=0x1\\,edge\\=0x1@", + "MetricExpr": "cpu_core@ICACHE_DATA.STALLS@ / cpu_core@ICACHE_DATA.STALLS\\,cmask\\=1\\,edge@", "MetricGroup": "Fed;FetchLat;IcMiss", "MetricName": "tma_info_frontend_icache_miss_latency", "Unit": "cpu_core" @@ -1497,14 +1500,14 @@ }, { "BriefDescription": "Average number of cycles the front-end was delayed due to an Unknown Branch detection", - "MetricExpr": "cpu_core@INT_MISC.UNKNOWN_BRANCH_CYCLES@ / cpu_core@INT_MISC.UNKNOWN_BRANCH_CYCLES\\,cmask\\=0x1\\,edge\\=0x1@", + "MetricExpr": "cpu_core@INT_MISC.UNKNOWN_BRANCH_CYCLES@ / cpu_core@INT_MISC.UNKNOWN_BRANCH_CYCLES\\,cmask\\=1\\,edge@", "MetricGroup": "Fed", "MetricName": "tma_info_frontend_unknown_branch_cost", - "PublicDescription": "Average number of cycles the front-end was delayed due to an Unknown Branch detection. See Unknown_Branches node", + "PublicDescription": "Average number of cycles the front-end was delayed due to an Unknown Branch detection. See Unknown_Branches node.", "Unit": "cpu_core" }, { - "BriefDescription": "Branch instructions per taken branch", + "BriefDescription": "Branch instructions per taken branch.", "MetricExpr": "cpu_core@BR_INST_RETIRED.ALL_BRANCHES@ / cpu_core@BR_INST_RETIRED.NEAR_TAKEN@", "MetricGroup": "Branches;Fed;PGO", "MetricName": "tma_info_inst_mix_bptkbranch", @@ -1524,7 +1527,7 @@ "MetricGroup": "Flops;InsType", "MetricName": "tma_info_inst_mix_iparith", "MetricThreshold": "tma_info_inst_mix_iparith < 10", - "PublicDescription": "Instructions per FP Arithmetic instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting. Approximated prior to BDW", + "PublicDescription": "Instructions per FP Arithmetic instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting. Approximated prior to BDW.", "Unit": "cpu_core" }, { @@ -1533,7 +1536,7 @@ "MetricGroup": "Flops;FpVector;InsType", "MetricName": "tma_info_inst_mix_iparith_avx128", "MetricThreshold": "tma_info_inst_mix_iparith_avx128 < 10", - "PublicDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting", + "PublicDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting.", "Unit": "cpu_core" }, { @@ -1542,7 +1545,7 @@ "MetricGroup": "Flops;FpVector;InsType", "MetricName": "tma_info_inst_mix_iparith_avx256", "MetricThreshold": "tma_info_inst_mix_iparith_avx256 < 10", - "PublicDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting", + "PublicDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting.", "Unit": "cpu_core" }, { @@ -1551,7 +1554,7 @@ "MetricGroup": "Flops;FpScalar;InsType", "MetricName": "tma_info_inst_mix_iparith_scalar_dp", "MetricThreshold": "tma_info_inst_mix_iparith_scalar_dp < 10", - "PublicDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting", + "PublicDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting.", "Unit": "cpu_core" }, { @@ -1560,7 +1563,7 @@ "MetricGroup": "Flops;FpScalar;InsType", "MetricName": "tma_info_inst_mix_iparith_scalar_sp", "MetricThreshold": "tma_info_inst_mix_iparith_scalar_sp < 10", - "PublicDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting", + "PublicDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting.", "Unit": "cpu_core" }, { @@ -1623,7 +1626,7 @@ "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / cpu_core@BR_INST_RETIRED.NEAR_TAKEN@", "MetricGroup": "Branches;Fed;FetchBW;Frontend;PGO;tma_issueFB", "MetricName": "tma_info_inst_mix_iptb", - "MetricThreshold": "tma_info_inst_mix_iptb < 6 * 2 + 1", + "MetricThreshold": "tma_info_inst_mix_iptb < 13", "PublicDescription": "Instructions per taken branch. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_lcp", "Unit": "cpu_core" }, @@ -1769,7 +1772,7 @@ }, { "BriefDescription": "Average Parallel L2 cache miss demand Loads", - "MetricExpr": "cpu_core@OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD@ / cpu_core@OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD\\,cmask\\=0x1@", + "MetricExpr": "cpu_core@OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD@ / cpu_core@OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD\\,cmask\\=1@", "MetricGroup": "Memory_BW;Offcore", "MetricName": "tma_info_memory_latency_load_l2_mlp", "Unit": "cpu_core" @@ -1849,7 +1852,7 @@ }, { "BriefDescription": "", - "MetricExpr": "cpu_core@UOPS_EXECUTED.THREAD@ / (cpu_core@UOPS_EXECUTED.CORE_CYCLES_GE_1@ / 2 if #SMT_on else cpu_core@UOPS_EXECUTED.THREAD\\,cmask\\=0x1@)", + "MetricExpr": "cpu_core@UOPS_EXECUTED.THREAD@ / (cpu_core@UOPS_EXECUTED.CORE_CYCLES_GE_1@ / 2 if #SMT_on else cpu_core@UOPS_EXECUTED.THREAD\\,cmask\\=1@)", "MetricGroup": "Cor;Pipeline;PortsUtil;SMT", "MetricName": "tma_info_pipeline_execute", "Unit": "cpu_core" @@ -1880,20 +1883,20 @@ "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / cpu_core@ASSISTS.ANY@", "MetricGroup": "MicroSeq;Pipeline;Ret;Retire", "MetricName": "tma_info_pipeline_ipassist", - "MetricThreshold": "tma_info_pipeline_ipassist < 100000", + "MetricThreshold": "tma_info_pipeline_ipassist < 100e3", "PublicDescription": "Instructions per a microcode Assist invocation. See Assists tree node for details (lower number means higher occurrence rate)", "Unit": "cpu_core" }, { - "BriefDescription": "Average number of Uops retired in cycles where at least one uop has retired", - "MetricExpr": "tma_retiring * tma_info_thread_slots / cpu_core@UOPS_RETIRED.SLOTS\\,cmask\\=0x1@", + "BriefDescription": "Average number of Uops retired in cycles where at least one uop has retired.", + "MetricExpr": "tma_retiring * tma_info_thread_slots / cpu_core@UOPS_RETIRED.SLOTS\\,cmask\\=1@", "MetricGroup": "Pipeline;Ret", "MetricName": "tma_info_pipeline_retire", "Unit": "cpu_core" }, { "BriefDescription": "Estimated fraction of retirement-cycles dealing with repeat instructions", - "MetricExpr": "cpu_core@INST_RETIRED.REP_ITERATION@ / cpu_core@UOPS_RETIRED.SLOTS\\,cmask\\=0x1@", + "MetricExpr": "cpu_core@INST_RETIRED.REP_ITERATION@ / cpu_core@UOPS_RETIRED.SLOTS\\,cmask\\=1@", "MetricGroup": "MicroSeq;Pipeline;Ret", "MetricName": "tma_info_pipeline_strings_cycles", "MetricThreshold": "tma_info_pipeline_strings_cycles > 0.1", @@ -1946,23 +1949,22 @@ }, { "BriefDescription": "Instructions per Far Branch ( Far Branches apply upon transition from application to operating system, handling interrupts, exceptions) [lower number means higher occurrence rate]", - "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / BR_INST_RETIRED.FAR_BRANCH:u", + "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / cpu_core@BR_INST_RETIRED.FAR_BRANCH@u", "MetricGroup": "Branches;OS", "MetricName": "tma_info_system_ipfarbranch", - "MetricThreshold": "tma_info_system_ipfarbranch < 1000000", + "MetricThreshold": "tma_info_system_ipfarbranch < 1e6", "Unit": "cpu_core" }, { "BriefDescription": "Cycles Per Instruction for the Operating System (OS) Kernel mode", - "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P:k / INST_RETIRED.ANY_P:k", + "MetricExpr": "cpu_core@CPU_CLK_UNHALTED.THREAD_P@k / cpu_core@INST_RETIRED.ANY_P@k", "MetricGroup": "OS", "MetricName": "tma_info_system_kernel_cpi", - "ScaleUnit": "1per_instr", "Unit": "cpu_core" }, { "BriefDescription": "Fraction of cycles spent in the Operating System (OS) Kernel mode", - "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P:k / cpu_core@CPU_CLK_UNHALTED.THREAD@", + "MetricExpr": "cpu_core@CPU_CLK_UNHALTED.THREAD_P@k / cpu_core@CPU_CLK_UNHALTED.THREAD@", "MetricGroup": "OS", "MetricName": "tma_info_system_kernel_utilization", "MetricThreshold": "tma_info_system_kernel_utilization > 0.05", @@ -2030,7 +2032,7 @@ "Unit": "cpu_core" }, { - "BriefDescription": "Per-Logical Processor actual clocks when the Logical Processor is active", + "BriefDescription": "Per-Logical Processor actual clocks when the Logical Processor is active.", "MetricExpr": "cpu_core@CPU_CLK_UNHALTED.THREAD@", "MetricGroup": "Pipeline", "MetricName": "tma_info_thread_clks", @@ -2041,7 +2043,6 @@ "MetricExpr": "1 / tma_info_thread_ipc", "MetricGroup": "Mem;Pipeline", "MetricName": "tma_info_thread_cpi", - "ScaleUnit": "1per_instr", "Unit": "cpu_core" }, { @@ -2049,7 +2050,7 @@ "MetricExpr": "cpu_core@UOPS_EXECUTED.THREAD@ / cpu_core@UOPS_ISSUED.ANY@", "MetricGroup": "Cor;Pipeline", "MetricName": "tma_info_thread_execute_per_issue", - "PublicDescription": "The ratio of Executed- by Issued-Uops. Ratio > 1 suggests high rate of uop micro-fusions. Ratio < 1 suggest high rate of \"execute\" at rename stage", + "PublicDescription": "The ratio of Executed- by Issued-Uops. Ratio > 1 suggests high rate of uop micro-fusions. Ratio < 1 suggest high rate of \"execute\" at rename stage.", "Unit": "cpu_core" }, { @@ -2061,14 +2062,14 @@ }, { "BriefDescription": "Total issue-pipeline slots (per-Physical Core till ICL; per-Logical Processor ICL onward)", - "MetricExpr": "slots", + "MetricExpr": "cpu_core@TOPDOWN.SLOTS@", "MetricGroup": "TmaL1;tma_L1_group", "MetricName": "tma_info_thread_slots", "Unit": "cpu_core" }, { "BriefDescription": "Fraction of Physical Core issue-slots utilized by this Logical Processor", - "MetricExpr": "(tma_info_thread_slots / (slots / 2) if #SMT_on else 1)", + "MetricExpr": "(tma_info_thread_slots / (cpu_core@TOPDOWN.SLOTS@ / 2) if #SMT_on else 1)", "MetricGroup": "SMT;TmaL1;tma_L1_group", "MetricName": "tma_info_thread_slots_utilization", "Unit": "cpu_core" @@ -2086,15 +2087,15 @@ "MetricExpr": "tma_retiring * tma_info_thread_slots / cpu_core@BR_INST_RETIRED.NEAR_TAKEN@", "MetricGroup": "Branches;Fed;FetchBW", "MetricName": "tma_info_thread_uptb", - "MetricThreshold": "tma_info_thread_uptb < 6 * 1.5", + "MetricThreshold": "tma_info_thread_uptb < 9", "Unit": "cpu_core" }, { - "BriefDescription": "This metric represents fraction of cycles where the Integer Divider unit was active", + "BriefDescription": "This metric represents fraction of cycles where the Integer Divider unit was active.", "MetricExpr": "tma_divider - tma_fp_divider", "MetricGroup": "TopdownL4;tma_L4_group;tma_divider_group", "MetricName": "tma_int_divider", - "MetricThreshold": "tma_int_divider > 0.2 & tma_divider > 0.2 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_int_divider > 0.2 & (tma_divider > 0.2 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -2104,7 +2105,7 @@ "MetricGroup": "Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group", "MetricName": "tma_int_operations", "MetricThreshold": "tma_int_operations > 0.1 & tma_light_operations > 0.6", - "PublicDescription": "This metric represents overall Integer (Int) select operations fraction the CPU has executed (retired). Vector/Matrix Int operations and shuffles are counted. Note this metric's value may exceed its parent due to use of \"Uops\" CountDomain", + "PublicDescription": "This metric represents overall Integer (Int) select operations fraction the CPU has executed (retired). Vector/Matrix Int operations and shuffles are counted. Note this metric's value may exceed its parent due to use of \"Uops\" CountDomain.", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -2113,8 +2114,8 @@ "MetricExpr": "(cpu_core@INT_VEC_RETIRED.ADD_128@ + cpu_core@INT_VEC_RETIRED.VNNI_128@) / (tma_retiring * tma_info_thread_slots)", "MetricGroup": "Compute;IntVector;Pipeline;TopdownL4;tma_L4_group;tma_int_operations_group;tma_issue2P", "MetricName": "tma_int_vector_128b", - "MetricThreshold": "tma_int_vector_128b > 0.1 & tma_int_operations > 0.1 & tma_light_operations > 0.6", - "PublicDescription": "This metric represents 128-bit vector Integer ADD/SUB/SAD or VNNI (Vector Neural Network Instructions) uops fraction the CPU has retired. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_6, tma_ports_utilized_2", + "MetricThreshold": "tma_int_vector_128b > 0.1 & (tma_int_operations > 0.1 & tma_light_operations > 0.6)", + "PublicDescription": "This metric represents 128-bit vector Integer ADD/SUB/SAD or VNNI (Vector Neural Network Instructions) uops fraction the CPU has retired. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -2123,8 +2124,8 @@ "MetricExpr": "(cpu_core@INT_VEC_RETIRED.ADD_256@ + cpu_core@INT_VEC_RETIRED.MUL_256@ + cpu_core@INT_VEC_RETIRED.VNNI_256@) / (tma_retiring * tma_info_thread_slots)", "MetricGroup": "Compute;IntVector;Pipeline;TopdownL4;tma_L4_group;tma_int_operations_group;tma_issue2P", "MetricName": "tma_int_vector_256b", - "MetricThreshold": "tma_int_vector_256b > 0.1 & tma_int_operations > 0.1 & tma_light_operations > 0.6", - "PublicDescription": "This metric represents 256-bit vector Integer ADD/SUB/SAD/MUL or VNNI (Vector Neural Network Instructions) uops fraction the CPU has retired. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_int_vector_128b, tma_port_0, tma_port_1, tma_port_6, tma_ports_utilized_2", + "MetricThreshold": "tma_int_vector_256b > 0.1 & (tma_int_operations > 0.1 & tma_light_operations > 0.6)", + "PublicDescription": "This metric represents 256-bit vector Integer ADD/SUB/SAD/MUL or VNNI (Vector Neural Network Instructions) uops fraction the CPU has retired. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -2133,8 +2134,8 @@ "MetricExpr": "cpu_core@ICACHE_TAG.STALLS@ / tma_info_thread_clks", "MetricGroup": "BigFootprint;BvBC;FetchLat;MemoryTLB;TopdownL3;tma_L3_group;tma_fetch_latency_group", "MetricName": "tma_itlb_misses", - "MetricThreshold": "tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", - "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Instruction TLB (ITLB) misses. Sample with: FRONTEND_RETIRED.STLB_MISS, FRONTEND_RETIRED.ITLB_MISS", + "MetricThreshold": "tma_itlb_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Instruction TLB (ITLB) misses. Sample with: FRONTEND_RETIRED.STLB_MISS_PS;FRONTEND_RETIRED.ITLB_MISS_PS", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -2143,7 +2144,7 @@ "MetricExpr": "max((cpu_core@EXE_ACTIVITY.BOUND_ON_LOADS@ - cpu_core@MEMORY_ACTIVITY.STALLS_L1D_MISS@) / tma_info_thread_clks, 0)", "MetricGroup": "CacheHits;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_issueL1;tma_issueMC;tma_memory_bound_group", "MetricName": "tma_l1_bound", - "MetricThreshold": "tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", "PublicDescription": "This metric estimates how often the CPU was stalled without loads missing the L1 Data (L1D) cache. The L1D cache typically has the shortest latency. However; in certain cases like loads blocked on older stores; a load might suffer due to high latency even though it is being satisfied by the L1D. Another example is loads who miss in the TLB. These cases are characterized by execution unit stalls; while some non-completed demand load lives in the machine without having that demand load missing the L1 cache. Sample with: MEM_LOAD_RETIRED.L1_HIT. Related metrics: tma_clears_resteers, tma_machine_clears, tma_microcode_sequencer, tma_ms_switches, tma_ports_utilized_1", "ScaleUnit": "100%", "Unit": "cpu_core" @@ -2153,7 +2154,7 @@ "MetricExpr": "min(2 * (cpu_core@MEM_INST_RETIRED.ALL_LOADS@ - cpu_core@MEM_LOAD_RETIRED.FB_HIT@ - cpu_core@MEM_LOAD_RETIRED.L1_MISS@) * 20 / 100, max(cpu_core@CYCLE_ACTIVITY.CYCLES_MEM_ANY@ - cpu_core@MEMORY_ACTIVITY.CYCLES_L1D_MISS@, 0)) / tma_info_thread_clks", "MetricGroup": "BvML;MemoryLat;TopdownL4;tma_L4_group;tma_l1_bound_group", "MetricName": "tma_l1_latency_dependency", - "MetricThreshold": "tma_l1_latency_dependency > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_l1_latency_dependency > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", "PublicDescription": "This metric([SKL+] roughly; [LNL]) estimates fraction of cycles with demand load accesses that hit the L1D cache. The short latency of the L1D cache may be exposed in pointer-chasing memory access patterns as an example. Sample with: MEM_LOAD_RETIRED.L1_HIT", "ScaleUnit": "100%", "Unit": "cpu_core" @@ -2163,17 +2164,18 @@ "MetricExpr": "(cpu_core@MEMORY_ACTIVITY.STALLS_L1D_MISS@ - cpu_core@MEMORY_ACTIVITY.STALLS_L2_MISS@) / tma_info_thread_clks", "MetricGroup": "BvML;CacheHits;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_l2_bound", - "MetricThreshold": "tma_l2_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_l2_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", "PublicDescription": "This metric estimates how often the CPU was stalled due to L2 cache accesses by loads. Avoiding cache misses (i.e. L1 misses/L2 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L2_HIT", "ScaleUnit": "100%", "Unit": "cpu_core" }, { "BriefDescription": "This metric represents fraction of cycles with demand load accesses that hit the L2 cache under unloaded scenarios (possibly L2 latency limited)", + "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "3 * tma_info_system_core_frequency * cpu_core@MEM_LOAD_RETIRED.L2_HIT@ * (1 + cpu_core@MEM_LOAD_RETIRED.FB_HIT@ / cpu_core@MEM_LOAD_RETIRED.L1_MISS@ / 2) / tma_info_thread_clks", "MetricGroup": "MemoryLat;TopdownL4;tma_L4_group;tma_l2_bound_group", "MetricName": "tma_l2_hit_latency", - "MetricThreshold": "tma_l2_hit_latency > 0.05 & tma_l2_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_l2_hit_latency > 0.05 & (tma_l2_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", "PublicDescription": "This metric represents fraction of cycles with demand load accesses that hit the L2 cache under unloaded scenarios (possibly L2 latency limited). Avoiding L1 cache misses (i.e. L1 misses/L2 hits) will improve the latency. Sample with: MEM_LOAD_RETIRED.L2_HIT", "ScaleUnit": "100%", "Unit": "cpu_core" @@ -2183,18 +2185,19 @@ "MetricExpr": "(cpu_core@MEMORY_ACTIVITY.STALLS_L2_MISS@ - cpu_core@MEMORY_ACTIVITY.STALLS_L3_MISS@) / tma_info_thread_clks", "MetricGroup": "CacheHits;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_l3_bound", - "MetricThreshold": "tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", - "PublicDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core. Avoiding cache misses (i.e. L2 misses/L3 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L3_HIT", + "MetricThreshold": "tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", + "PublicDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core. Avoiding cache misses (i.e. L2 misses/L3 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L3_HIT_PS", "ScaleUnit": "100%", "Unit": "cpu_core" }, { "BriefDescription": "This metric estimates fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited)", - "MetricExpr": "(12 * tma_info_system_core_frequency - 3 * tma_info_system_core_frequency) * (cpu_core@MEM_LOAD_RETIRED.L3_HIT@ * (1 + cpu_core@MEM_LOAD_RETIRED.FB_HIT@ / cpu_core@MEM_LOAD_RETIRED.L1_MISS@ / 2)) / tma_info_thread_clks", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "9 * tma_info_system_core_frequency * (cpu_core@MEM_LOAD_RETIRED.L3_HIT@ * (1 + cpu_core@MEM_LOAD_RETIRED.FB_HIT@ / cpu_core@MEM_LOAD_RETIRED.L1_MISS@ / 2)) / tma_info_thread_clks", "MetricGroup": "BvML;MemoryLat;TopdownL4;tma_L4_group;tma_issueLat;tma_l3_bound_group", "MetricName": "tma_l3_hit_latency", - "MetricThreshold": "tma_l3_hit_latency > 0.1 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", - "PublicDescription": "This metric estimates fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited). Avoiding private cache misses (i.e. L2 misses/L3 hits) will improve the latency; reduce contention with sibling physical cores and increase performance. Note the value of this node may overlap with its siblings. Sample with: MEM_LOAD_RETIRED.L3_HIT. Related metrics: tma_bottleneck_cache_memory_latency, tma_branch_resteers, tma_mem_latency, tma_store_latency", + "MetricThreshold": "tma_l3_hit_latency > 0.1 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric estimates fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited). Avoiding private cache misses (i.e. L2 misses/L3 hits) will improve the latency; reduce contention with sibling physical cores and increase performance. Note the value of this node may overlap with its siblings. Sample with: MEM_LOAD_RETIRED.L3_HIT_PS. Related metrics: tma_bottleneck_cache_memory_latency, tma_mem_latency", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -2203,19 +2206,19 @@ "MetricExpr": "cpu_core@DECODE.LCP@ / tma_info_thread_clks", "MetricGroup": "FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueFB", "MetricName": "tma_lcp", - "MetricThreshold": "tma_lcp > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", - "PublicDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs). Using proper compiler flags or Intel Compiler by default will certainly avoid this. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb", + "MetricThreshold": "tma_lcp > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", + "PublicDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs). Using proper compiler flags or Intel Compiler by default will certainly avoid this. #Link: Optimization Guide about LCP BKMs. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb", "ScaleUnit": "100%", "Unit": "cpu_core" }, { - "BriefDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations , instructions that require no more than one uop (micro-operation)", + "BriefDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation)", "MetricExpr": "max(0, tma_retiring - tma_heavy_operations)", "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_light_operations", "MetricThreshold": "tma_light_operations > 0.6", "MetricgroupNoGroup": "TopdownL2", - "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations , instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized code running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. ([ICL+] Note this may undercount due to approximation using indirect events; [ADL+] .). Sample with: INST_RETIRED.PREC_DIST", + "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized code running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. ([ICL+] Note this may undercount due to approximation using indirect events; [ADL+] .). Sample with: INST_RETIRED.PREC_DIST", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -2234,7 +2237,7 @@ "MetricExpr": "tma_dtlb_load - tma_load_stlb_miss", "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_load_group", "MetricName": "tma_load_stlb_hit", - "MetricThreshold": "tma_load_stlb_hit > 0.05 & tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_load_stlb_hit > 0.05 & (tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -2243,34 +2246,34 @@ "MetricExpr": "cpu_core@DTLB_LOAD_MISSES.WALK_ACTIVE@ / tma_info_thread_clks", "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_load_group", "MetricName": "tma_load_stlb_miss", - "MetricThreshold": "tma_load_stlb_miss > 0.05 & tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_load_stlb_miss > 0.05 & (tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))", "ScaleUnit": "100%", "Unit": "cpu_core" }, { - "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 1 GB pages for data load accesses", + "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 1 GB pages for data load accesses.", "MetricExpr": "tma_load_stlb_miss * cpu_core@DTLB_LOAD_MISSES.WALK_COMPLETED_1G@ / (cpu_core@DTLB_LOAD_MISSES.WALK_COMPLETED_4K@ + cpu_core@DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M@ + cpu_core@DTLB_LOAD_MISSES.WALK_COMPLETED_1G@)", "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_load_stlb_miss_group", "MetricName": "tma_load_stlb_miss_1g", - "MetricThreshold": "tma_load_stlb_miss_1g > 0.05 & tma_load_stlb_miss > 0.05 & tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_load_stlb_miss_1g > 0.05 & (tma_load_stlb_miss > 0.05 & (tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))))", "ScaleUnit": "100%", "Unit": "cpu_core" }, { - "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 2 or 4 MB pages for data load accesses", + "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 2 or 4 MB pages for data load accesses.", "MetricExpr": "tma_load_stlb_miss * cpu_core@DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M@ / (cpu_core@DTLB_LOAD_MISSES.WALK_COMPLETED_4K@ + cpu_core@DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M@ + cpu_core@DTLB_LOAD_MISSES.WALK_COMPLETED_1G@)", "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_load_stlb_miss_group", "MetricName": "tma_load_stlb_miss_2m", - "MetricThreshold": "tma_load_stlb_miss_2m > 0.05 & tma_load_stlb_miss > 0.05 & tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_load_stlb_miss_2m > 0.05 & (tma_load_stlb_miss > 0.05 & (tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))))", "ScaleUnit": "100%", "Unit": "cpu_core" }, { - "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 4 KB pages for data load accesses", + "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 4 KB pages for data load accesses.", "MetricExpr": "tma_load_stlb_miss * cpu_core@DTLB_LOAD_MISSES.WALK_COMPLETED_4K@ / (cpu_core@DTLB_LOAD_MISSES.WALK_COMPLETED_4K@ + cpu_core@DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M@ + cpu_core@DTLB_LOAD_MISSES.WALK_COMPLETED_1G@)", "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_load_stlb_miss_group", "MetricName": "tma_load_stlb_miss_4k", - "MetricThreshold": "tma_load_stlb_miss_4k > 0.05 & tma_load_stlb_miss > 0.05 & tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_load_stlb_miss_4k > 0.05 & (tma_load_stlb_miss > 0.05 & (tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))))", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -2279,7 +2282,7 @@ "MetricExpr": "(16 * max(0, cpu_core@MEM_INST_RETIRED.LOCK_LOADS@ - cpu_core@L2_RQSTS.ALL_RFO@) + cpu_core@MEM_INST_RETIRED.LOCK_LOADS@ / cpu_core@MEM_INST_RETIRED.ALL_STORES@ * (10 * cpu_core@L2_RQSTS.RFO_HIT@ + min(cpu_core@CPU_CLK_UNHALTED.THREAD@, cpu_core@OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO@))) / tma_info_thread_clks", "MetricGroup": "LockCont;Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_l1_bound_group", "MetricName": "tma_lock_latency", - "MetricThreshold": "tma_lock_latency > 0.2 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_lock_latency > 0.2 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", "PublicDescription": "This metric represents fraction of cycles the CPU spent handling cache misses due to lock operations. Due to the microarchitecture handling of locks; they are classified as L1_Bound regardless of what memory source satisfied them. Sample with: MEM_INST_RETIRED.LOCK_LOADS. Related metrics: tma_store_latency", "ScaleUnit": "100%", "Unit": "cpu_core" @@ -2290,7 +2293,7 @@ "MetricGroup": "FetchBW;LSD;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group", "MetricName": "tma_lsd", "MetricThreshold": "tma_lsd > 0.15 & tma_fetch_bandwidth > 0.2", - "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to LSD (Loop Stream Detector) unit. LSD typically does well sustaining Uop supply. However; in some rare cases; optimal uop-delivery could not be reached for small loops whose size (in terms of number of uops) does not suit well the LSD structure", + "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to LSD (Loop Stream Detector) unit. LSD typically does well sustaining Uop supply. However; in some rare cases; optimal uop-delivery could not be reached for small loops whose size (in terms of number of uops) does not suit well the LSD structure.", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -2301,16 +2304,16 @@ "MetricName": "tma_machine_clears", "MetricThreshold": "tma_machine_clears > 0.1 & tma_bad_speculation > 0.15", "MetricgroupNoGroup": "TopdownL2", - "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears. These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT. Related metrics: tma_bottleneck_memory_synchronization, tma_clears_resteers, tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_l1_bound, tma_microcode_sequencer, tma_ms_switches", + "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears. These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT. Related metrics: tma_bottleneck_memory_synchronization, tma_clears_resteers, tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_l1_bound, tma_microcode_sequencer, tma_ms_switches, tma_remote_cache", "ScaleUnit": "100%", "Unit": "cpu_core" }, { "BriefDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory - DRAM ([SPR-HBM] and/or HBM)", - "MetricExpr": "min(cpu_core@CPU_CLK_UNHALTED.THREAD@, cpu_core@OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD\\,cmask\\=0x4@) / tma_info_thread_clks", + "MetricExpr": "min(cpu_core@CPU_CLK_UNHALTED.THREAD@, cpu_core@OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD\\,cmask\\=4@) / tma_info_thread_clks", "MetricGroup": "BvMB;MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueBW", "MetricName": "tma_mem_bandwidth", - "MetricThreshold": "tma_mem_bandwidth > 0.2 & tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_mem_bandwidth > 0.2 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", "PublicDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory - DRAM ([SPR-HBM] and/or HBM). The underlying heuristic assumes that a similar off-core traffic is generated by all IA cores. This metric does not aggregate non-data-read requests by this logical processor; requests from other IA Logical Processors/Physical Cores/sockets; or other non-IA devices like GPU; hence the maximum external memory bandwidth limits may or may not be approached when this metric is flagged (see Uncore counters for that). Related metrics: tma_bottleneck_cache_memory_bandwidth, tma_fb_full, tma_info_system_dram_bw_use, tma_sq_full", "ScaleUnit": "100%", "Unit": "cpu_core" @@ -2320,34 +2323,34 @@ "MetricExpr": "min(cpu_core@CPU_CLK_UNHALTED.THREAD@, cpu_core@OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD@) / tma_info_thread_clks - tma_mem_bandwidth", "MetricGroup": "BvML;MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueLat", "MetricName": "tma_mem_latency", - "MetricThreshold": "tma_mem_latency > 0.1 & tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_mem_latency > 0.1 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", "PublicDescription": "This metric estimates fraction of cycles where the performance was likely hurt due to latency from external memory - DRAM ([SPR-HBM] and/or HBM). This metric does not aggregate requests from other Logical Processors/Physical Cores/sockets (see Uncore counters for that). Related metrics: tma_bottleneck_cache_memory_latency, tma_l3_hit_latency", "ScaleUnit": "100%", "Unit": "cpu_core" }, { "BriefDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck", - "MetricExpr": "topdown\\-mem\\-bound / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * slots", + "MetricExpr": "cpu_core@topdown\\-mem\\-bound@ / (cpu_core@topdown\\-fe\\-bound@ + cpu_core@topdown\\-bad\\-spec@ + cpu_core@topdown\\-retiring@ + cpu_core@topdown\\-be\\-bound@) + 0 * tma_info_thread_slots", "MetricGroup": "Backend;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_memory_bound", "MetricThreshold": "tma_memory_bound > 0.2 & tma_backend_bound > 0.2", "MetricgroupNoGroup": "TopdownL2", - "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck. Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two)", + "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck. Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two).", "ScaleUnit": "100%", "Unit": "cpu_core" }, { - "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to LFENCE Instructions", + "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to LFENCE Instructions.", "MetricConstraint": "NO_GROUP_EVENTS_NMI", "MetricExpr": "13 * cpu_core@MISC2_RETIRED.LFENCE@ / tma_info_thread_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_serializing_operation_group", "MetricName": "tma_memory_fence", - "MetricThreshold": "tma_memory_fence > 0.05 & tma_serializing_operation > 0.1 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_memory_fence > 0.05 & (tma_serializing_operation > 0.1 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", "ScaleUnit": "100%", "Unit": "cpu_core" }, { - "BriefDescription": "This metric represents fraction of slots where the CPU was retiring memory operations , uops for memory load or store accesses", + "BriefDescription": "This metric represents fraction of slots where the CPU was retiring memory operations -- uops for memory load or store accesses.", "MetricExpr": "tma_light_operations * cpu_core@MEM_UOP_RETIRED.ANY@ / (tma_retiring * tma_info_thread_slots)", "MetricGroup": "Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group", "MetricName": "tma_memory_operations", @@ -2370,7 +2373,7 @@ "MetricExpr": "tma_branch_mispredicts / tma_bad_speculation * cpu_core@INT_MISC.CLEAR_RESTEER_CYCLES@ / tma_info_thread_clks", "MetricGroup": "BadSpec;BrMispredicts;BvMP;TopdownL4;tma_L4_group;tma_branch_resteers_group;tma_issueBM", "MetricName": "tma_mispredicts_resteers", - "MetricThreshold": "tma_mispredicts_resteers > 0.05 & tma_branch_resteers > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricThreshold": "tma_mispredicts_resteers > 0.05 & (tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))", "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Branch Misprediction at execution stage. Sample with: INT_MISC.CLEAR_RESTEER_CYCLES. Related metrics: tma_bottleneck_mispredictions, tma_branch_mispredicts, tma_info_bad_spec_branch_misprediction_cost", "ScaleUnit": "100%", "Unit": "cpu_core" @@ -2386,18 +2389,18 @@ "Unit": "cpu_core" }, { - "BriefDescription": "This metric estimates penalty in terms of percentage of([SKL+] injected blend uops out of all Uops Issued , the Count Domain; [ADL+] cycles)", + "BriefDescription": "This metric estimates penalty in terms of percentage of([SKL+] injected blend uops out of all Uops Issued -- the Count Domain; [ADL+] cycles)", "MetricExpr": "160 * cpu_core@ASSISTS.SSE_AVX_MIX@ / tma_info_thread_clks", "MetricGroup": "TopdownL5;tma_L5_group;tma_issueMV;tma_ports_utilized_0_group", "MetricName": "tma_mixing_vectors", "MetricThreshold": "tma_mixing_vectors > 0.05", - "PublicDescription": "This metric estimates penalty in terms of percentage of([SKL+] injected blend uops out of all Uops Issued , the Count Domain; [ADL+] cycles). Usually a Mixing_Vectors over 5% is worth investigating. Read more in Appendix B1 of the Optimizations Guide for this topic. Related metrics: tma_ms_switches", + "PublicDescription": "This metric estimates penalty in terms of percentage of([SKL+] injected blend uops out of all Uops Issued -- the Count Domain; [ADL+] cycles). Usually a Mixing_Vectors over 5% is worth investigating. Read more in Appendix B1 of the Optimizations Guide for this topic. Related metrics: tma_ms_switches", "ScaleUnit": "100%", "Unit": "cpu_core" }, { - "BriefDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to the Microcode Sequencer (MS) unit - see Microcode_Sequencer node for details", - "MetricExpr": "max(cpu_core@IDQ.MS_CYCLES_ANY@, cpu_core@UOPS_RETIRED.MS\\,cmask\\=0x1@ / (cpu_core@UOPS_RETIRED.SLOTS@ / cpu_core@UOPS_ISSUED.ANY@)) / tma_info_core_core_clks / 2", + "BriefDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to the Microcode Sequencer (MS) unit - see Microcode_Sequencer node for details.", + "MetricExpr": "max(cpu_core@IDQ.MS_CYCLES_ANY@, cpu_core@UOPS_RETIRED.MS\\,cmask\\=1@ / (cpu_core@UOPS_RETIRED.SLOTS@ / cpu_core@UOPS_ISSUED.ANY@)) / tma_info_core_core_clks / 2", "MetricGroup": "MicroSeq;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group", "MetricName": "tma_ms", "MetricThreshold": "tma_ms > 0.05 & tma_fetch_bandwidth > 0.2", @@ -2406,10 +2409,10 @@ }, { "BriefDescription": "This metric estimates the fraction of cycles when the CPU was stalled due to switches of uop delivery to the Microcode Sequencer (MS)", - "MetricExpr": "3 * cpu_core@UOPS_RETIRED.MS\\,cmask\\=0x1\\,edge\\=0x1@ / (cpu_core@UOPS_RETIRED.SLOTS@ / cpu_core@UOPS_ISSUED.ANY@) / tma_info_thread_clks", + "MetricExpr": "3 * cpu_core@UOPS_RETIRED.MS\\,cmask\\=1\\,edge@ / (cpu_core@UOPS_RETIRED.SLOTS@ / cpu_core@UOPS_ISSUED.ANY@) / tma_info_thread_clks", "MetricGroup": "FetchLat;MicroSeq;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueMC;tma_issueMS;tma_issueMV;tma_issueSO", "MetricName": "tma_ms_switches", - "MetricThreshold": "tma_ms_switches > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricThreshold": "tma_ms_switches > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", "PublicDescription": "This metric estimates the fraction of cycles when the CPU was stalled due to switches of uop delivery to the Microcode Sequencer (MS). Commonly used instructions are optimized for delivery by the DSB (decoded i-cache) or MITE (legacy instruction decode) pipelines. Certain operations cannot be handled natively by the execution pipeline; and must be performed by microcode (small programs injected into the execution stream). Switching to the MS too often can negatively impact performance. The MS is designated to deliver long uop flows required by CISC instructions like CPUID; or uncommon conditions like Floating Point Assists when dealing with Denormals. Sample with: FRONTEND_RETIRED.MS_FLOWS. Related metrics: tma_bottleneck_irregular_overhead, tma_clears_resteers, tma_l1_bound, tma_machine_clears, tma_microcode_sequencer, tma_mixing_vectors, tma_serializing_operation", "ScaleUnit": "100%", "Unit": "cpu_core" @@ -2420,7 +2423,7 @@ "MetricGroup": "Branches;BvBO;Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group", "MetricName": "tma_non_fused_branches", "MetricThreshold": "tma_non_fused_branches > 0.1 & tma_light_operations > 0.6", - "PublicDescription": "This metric represents fraction of slots where the CPU was retiring branch instructions that were not fused. Non-conditional branches like direct JMP or CALL would count here. Can be used to examine fusible conditional jumps that were not fused", + "PublicDescription": "This metric represents fraction of slots where the CPU was retiring branch instructions that were not fused. Non-conditional branches like direct JMP or CALL would count here. Can be used to examine fusible conditional jumps that were not fused.", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -2429,7 +2432,7 @@ "MetricExpr": "tma_light_operations * cpu_core@INST_RETIRED.NOP@ / (tma_retiring * tma_info_thread_slots)", "MetricGroup": "BvBO;Pipeline;TopdownL4;tma_L4_group;tma_other_light_ops_group", "MetricName": "tma_nop_instructions", - "MetricThreshold": "tma_nop_instructions > 0.1 & tma_other_light_ops > 0.3 & tma_light_operations > 0.6", + "MetricThreshold": "tma_nop_instructions > 0.1 & (tma_other_light_ops > 0.3 & tma_light_operations > 0.6)", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring NOP (no op) instructions. Compilers often use NOPs for certain address alignments - e.g. start address of a function or loop body. Sample with: INST_RETIRED.NOP", "ScaleUnit": "100%", "Unit": "cpu_core" @@ -2445,20 +2448,20 @@ "Unit": "cpu_core" }, { - "BriefDescription": "This metric estimates fraction of slots the CPU was stalled due to other cases of misprediction (non-retired x86 branches or other types)", + "BriefDescription": "This metric estimates fraction of slots the CPU was stalled due to other cases of misprediction (non-retired x86 branches or other types).", "MetricExpr": "max(tma_branch_mispredicts * (1 - cpu_core@BR_MISP_RETIRED.ALL_BRANCHES@ / (cpu_core@INT_MISC.CLEARS_COUNT@ - cpu_core@MACHINE_CLEARS.COUNT@)), 0.0001)", "MetricGroup": "BrMispredicts;BvIO;TopdownL3;tma_L3_group;tma_branch_mispredicts_group", "MetricName": "tma_other_mispredicts", - "MetricThreshold": "tma_other_mispredicts > 0.05 & tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", + "MetricThreshold": "tma_other_mispredicts > 0.05 & (tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15)", "ScaleUnit": "100%", "Unit": "cpu_core" }, { - "BriefDescription": "This metric represents fraction of slots the CPU has wasted due to Nukes (Machine Clears) not related to memory ordering", + "BriefDescription": "This metric represents fraction of slots the CPU has wasted due to Nukes (Machine Clears) not related to memory ordering.", "MetricExpr": "max(tma_machine_clears * (1 - cpu_core@MACHINE_CLEARS.MEMORY_ORDERING@ / cpu_core@MACHINE_CLEARS.COUNT@), 0.0001)", "MetricGroup": "BvIO;Machine_Clears;TopdownL3;tma_L3_group;tma_machine_clears_group", "MetricName": "tma_other_nukes", - "MetricThreshold": "tma_other_nukes > 0.05 & tma_machine_clears > 0.1 & tma_bad_speculation > 0.15", + "MetricThreshold": "tma_other_nukes > 0.05 & (tma_machine_clears > 0.1 & tma_bad_speculation > 0.15)", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -2468,7 +2471,7 @@ "MetricGroup": "TopdownL5;tma_L5_group;tma_assists_group", "MetricName": "tma_page_faults", "MetricThreshold": "tma_page_faults > 0.05", - "PublicDescription": "This metric roughly estimates fraction of slots the CPU retired uops as a result of handing Page Faults. A Page Fault may apply on first application access to a memory page. Note operating system handling of page faults accounts for the majority of its cost", + "PublicDescription": "This metric roughly estimates fraction of slots the CPU retired uops as a result of handing Page Faults. A Page Fault may apply on first application access to a memory page. Note operating system handling of page faults accounts for the majority of its cost.", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -2478,7 +2481,7 @@ "MetricGroup": "Compute;TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P", "MetricName": "tma_port_0", "MetricThreshold": "tma_port_0 > 0.6", - "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 0 ([SNB+] ALU; [HSW+] ALU and 2nd branch). Sample with: UOPS_DISPATCHED.PORT_0. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_int_vector_128b, tma_int_vector_256b, tma_port_1, tma_port_6, tma_ports_utilized_2", + "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 0 ([SNB+] ALU; [HSW+] ALU and 2nd branch). Sample with: UOPS_DISPATCHED.PORT_0. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -2488,7 +2491,7 @@ "MetricGroup": "TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P", "MetricName": "tma_port_1", "MetricThreshold": "tma_port_1 > 0.6", - "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 1 (ALU). Sample with: UOPS_DISPATCHED.PORT_1. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_6, tma_ports_utilized_2", + "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 1 (ALU). Sample with: UOPS_DISPATCHED.PORT_1. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_5, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -2498,7 +2501,7 @@ "MetricGroup": "TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P", "MetricName": "tma_port_6", "MetricThreshold": "tma_port_6 > 0.6", - "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 6 ([HSW+] Primary Branch and simple ALU). Sample with: UOPS_DISPATCHED.PORT_1. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_ports_utilized_2", + "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 6 ([HSW+] Primary Branch and simple ALU). Sample with: UOPS_DISPATCHED.PORT_1. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_ports_utilized_2", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -2507,8 +2510,8 @@ "MetricExpr": "((tma_ports_utilized_0 * tma_info_thread_clks + (cpu_core@EXE_ACTIVITY.1_PORTS_UTIL@ + tma_retiring * cpu_core@EXE_ACTIVITY.2_3_PORTS_UTIL@)) / tma_info_thread_clks if cpu_core@ARITH.DIV_ACTIVE@ < cpu_core@CYCLE_ACTIVITY.STALLS_TOTAL@ - cpu_core@EXE_ACTIVITY.BOUND_ON_LOADS@ else (cpu_core@EXE_ACTIVITY.1_PORTS_UTIL@ + tma_retiring * cpu_core@EXE_ACTIVITY.2_3_PORTS_UTIL@) / tma_info_thread_clks)", "MetricGroup": "PortsUtil;TopdownL3;tma_L3_group;tma_core_bound_group", "MetricName": "tma_ports_utilization", - "MetricThreshold": "tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", - "PublicDescription": "This metric estimates fraction of cycles the CPU performance was potentially limited due to Core computation issues (non divider-related). Two distinct categories can be attributed into this metric: (1) heavy data-dependency among contiguous instructions would manifest in this metric - such cases are often referred to as low Instruction Level Parallelism (ILP). (2) Contention on some hardware execution unit other than Divider. For example; when there are too many multiply operations", + "MetricThreshold": "tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)", + "PublicDescription": "This metric estimates fraction of cycles the CPU performance was potentially limited due to Core computation issues (non divider-related). Two distinct categories can be attributed into this metric: (1) heavy data-dependency among contiguous instructions would manifest in this metric - such cases are often referred to as low Instruction Level Parallelism (ILP). (2) Contention on some hardware execution unit other than Divider. For example; when there are too many multiply operations.", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -2517,8 +2520,8 @@ "MetricExpr": "(cpu_core@EXE_ACTIVITY.EXE_BOUND_0_PORTS@ + max(cpu_core@RS.EMPTY_RESOURCE@ - cpu_core@RESOURCE_STALLS.SCOREBOARD@, 0)) / tma_info_thread_clks * (cpu_core@CYCLE_ACTIVITY.STALLS_TOTAL@ - cpu_core@EXE_ACTIVITY.BOUND_ON_LOADS@) / tma_info_thread_clks", "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group", "MetricName": "tma_ports_utilized_0", - "MetricThreshold": "tma_ports_utilized_0 > 0.2 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", - "PublicDescription": "This metric represents fraction of cycles CPU executed no uops on any execution port (Logical Processor cycles since ICL, Physical Core cycles otherwise). Long-latency instructions like divides may contribute to this metric", + "MetricThreshold": "tma_ports_utilized_0 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric represents fraction of cycles CPU executed no uops on any execution port (Logical Processor cycles since ICL, Physical Core cycles otherwise). Long-latency instructions like divides may contribute to this metric.", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -2527,7 +2530,7 @@ "MetricExpr": "cpu_core@EXE_ACTIVITY.1_PORTS_UTIL@ / tma_info_thread_clks", "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_issueL1;tma_ports_utilization_group", "MetricName": "tma_ports_utilized_1", - "MetricThreshold": "tma_ports_utilized_1 > 0.2 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_ports_utilized_1 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", "PublicDescription": "This metric represents fraction of cycles where the CPU executed total of 1 uop per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise). This can be due to heavy data-dependency among software instructions; or over oversubscribing a particular hardware resource. In some other cases with high 1_Port_Utilized and L1_Bound; this metric can point to L1 data-cache latency bottleneck that may not necessarily manifest with complete execution starvation (due to the short L1 latency e.g. walking a linked list) - looking at the assembly can be helpful. Sample with: EXE_ACTIVITY.1_PORTS_UTIL. Related metrics: tma_l1_bound", "ScaleUnit": "100%", "Unit": "cpu_core" @@ -2538,8 +2541,8 @@ "MetricExpr": "cpu_core@EXE_ACTIVITY.2_PORTS_UTIL@ / tma_info_thread_clks", "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_issue2P;tma_ports_utilization_group", "MetricName": "tma_ports_utilized_2", - "MetricThreshold": "tma_ports_utilized_2 > 0.15 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", - "PublicDescription": "This metric represents fraction of cycles CPU executed total of 2 uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise). Loop Vectorization -most compilers feature auto-Vectorization options today- reduces pressure on the execution ports as multiple elements are calculated with same uop. Sample with: EXE_ACTIVITY.2_PORTS_UTIL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_6", + "MetricThreshold": "tma_ports_utilized_2 > 0.15 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric represents fraction of cycles CPU executed total of 2 uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise). Loop Vectorization -most compilers feature auto-Vectorization options today- reduces pressure on the execution ports as multiple elements are calculated with same uop. Sample with: EXE_ACTIVITY.2_PORTS_UTIL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_port_6", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -2549,7 +2552,7 @@ "MetricExpr": "cpu_core@UOPS_EXECUTED.CYCLES_GE_3@ / tma_info_thread_clks", "MetricGroup": "BvCB;PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group", "MetricName": "tma_ports_utilized_3m", - "MetricThreshold": "tma_ports_utilized_3m > 0.4 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_ports_utilized_3m > 0.4 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", "PublicDescription": "This metric represents fraction of cycles CPU executed total of 3 or more uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise). Sample with: UOPS_EXECUTED.CYCLES_GE_3", "ScaleUnit": "100%", "Unit": "cpu_core" @@ -2557,7 +2560,7 @@ { "BriefDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired", "DefaultMetricgroupName": "TopdownL1", - "MetricExpr": "topdown\\-retiring / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * slots", + "MetricExpr": "cpu_core@topdown\\-retiring@ / (cpu_core@topdown\\-fe\\-bound@ + cpu_core@topdown\\-bad\\-spec@ + cpu_core@topdown\\-retiring@ + cpu_core@topdown\\-be\\-bound@) + 0 * tma_info_thread_slots", "MetricGroup": "BvUW;Default;TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_retiring", "MetricThreshold": "tma_retiring > 0.7 | tma_heavy_operations > 0.1", @@ -2571,7 +2574,7 @@ "MetricExpr": "cpu_core@RESOURCE_STALLS.SCOREBOARD@ / tma_info_thread_clks + tma_c02_wait", "MetricGroup": "BvIO;PortsUtil;TopdownL3;tma_L3_group;tma_core_bound_group;tma_issueSO", "MetricName": "tma_serializing_operation", - "MetricThreshold": "tma_serializing_operation > 0.1 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_serializing_operation > 0.1 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)", "PublicDescription": "This metric represents fraction of cycles the CPU issue-pipeline was stalled due to serializing operations. Instructions like CPUID; WRMSR or LFENCE serialize the out-of-order execution which may limit performance. Sample with: RESOURCE_STALLS.SCOREBOARD. Related metrics: tma_ms_switches", "ScaleUnit": "100%", "Unit": "cpu_core" @@ -2581,8 +2584,8 @@ "MetricExpr": "tma_light_operations * cpu_core@INT_VEC_RETIRED.SHUFFLES@ / (tma_retiring * tma_info_thread_slots)", "MetricGroup": "HPC;Pipeline;TopdownL4;tma_L4_group;tma_other_light_ops_group", "MetricName": "tma_shuffles_256b", - "MetricThreshold": "tma_shuffles_256b > 0.1 & tma_other_light_ops > 0.3 & tma_light_operations > 0.6", - "PublicDescription": "This metric represents fraction of slots where the CPU was retiring Shuffle operations of 256-bit vector size (FP or Integer). Shuffles may incur slow cross \"vector lane\" data transfers", + "MetricThreshold": "tma_shuffles_256b > 0.1 & (tma_other_light_ops > 0.3 & tma_light_operations > 0.6)", + "PublicDescription": "This metric represents fraction of slots where the CPU was retiring Shuffle operations of 256-bit vector size (FP or Integer). Shuffles may incur slow cross \"vector lane\" data transfers.", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -2592,7 +2595,7 @@ "MetricExpr": "cpu_core@CPU_CLK_UNHALTED.PAUSE@ / tma_info_thread_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_serializing_operation_group", "MetricName": "tma_slow_pause", - "MetricThreshold": "tma_slow_pause > 0.05 & tma_serializing_operation > 0.1 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_slow_pause > 0.05 & (tma_serializing_operation > 0.1 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to PAUSE Instructions. Sample with: CPU_CLK_UNHALTED.PAUSE_INST", "ScaleUnit": "100%", "Unit": "cpu_core" @@ -2603,7 +2606,7 @@ "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group", "MetricName": "tma_split_loads", "MetricThreshold": "tma_split_loads > 0.3", - "PublicDescription": "This metric estimates fraction of cycles handling memory load split accesses - load that cross 64-byte cache line boundary. Sample with: MEM_INST_RETIRED.SPLIT_LOADS", + "PublicDescription": "This metric estimates fraction of cycles handling memory load split accesses - load that cross 64-byte cache line boundary. Sample with: MEM_INST_RETIRED.SPLIT_LOADS_PS", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -2612,8 +2615,8 @@ "MetricExpr": "cpu_core@MEM_INST_RETIRED.SPLIT_STORES@ / tma_info_core_core_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_issueSpSt;tma_store_bound_group", "MetricName": "tma_split_stores", - "MetricThreshold": "tma_split_stores > 0.2 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", - "PublicDescription": "This metric represents rate of split store accesses. Consider aligning your data to the 64-byte cache line granularity. Sample with: MEM_INST_RETIRED.SPLIT_STORES", + "MetricThreshold": "tma_split_stores > 0.2 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric represents rate of split store accesses. Consider aligning your data to the 64-byte cache line granularity. Sample with: MEM_INST_RETIRED.SPLIT_STORES_PS. Related metrics: tma_port_4", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -2622,7 +2625,7 @@ "MetricExpr": "(cpu_core@XQ.FULL_CYCLES@ + cpu_core@L1D_PEND_MISS.L2_STALLS@) / tma_info_thread_clks", "MetricGroup": "BvMB;MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_issueBW;tma_l3_bound_group", "MetricName": "tma_sq_full", - "MetricThreshold": "tma_sq_full > 0.3 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_sq_full > 0.3 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", "PublicDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors). Related metrics: tma_bottleneck_cache_memory_bandwidth, tma_fb_full, tma_info_system_dram_bw_use, tma_mem_bandwidth", "ScaleUnit": "100%", "Unit": "cpu_core" @@ -2632,8 +2635,8 @@ "MetricExpr": "cpu_core@EXE_ACTIVITY.BOUND_ON_STORES@ / tma_info_thread_clks", "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_store_bound", - "MetricThreshold": "tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", - "PublicDescription": "This metric estimates how often CPU was stalled due to RFO store memory accesses; RFO store issue a read-for-ownership request before the write. Even though store accesses do not typically stall out-of-order CPUs; there are few cases where stores can lead to actual stalls. This metric will be flagged should RFO stores be a bottleneck. Sample with: MEM_INST_RETIRED.ALL_STORES", + "MetricThreshold": "tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", + "PublicDescription": "This metric estimates how often CPU was stalled due to RFO store memory accesses; RFO store issue a read-for-ownership request before the write. Even though store accesses do not typically stall out-of-order CPUs; there are few cases where stores can lead to actual stalls. This metric will be flagged should RFO stores be a bottleneck. Sample with: MEM_INST_RETIRED.ALL_STORES_PS", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -2642,8 +2645,8 @@ "MetricExpr": "13 * cpu_core@LD_BLOCKS.STORE_FORWARD@ / tma_info_thread_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group", "MetricName": "tma_store_fwd_blk", - "MetricThreshold": "tma_store_fwd_blk > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", - "PublicDescription": "This metric roughly estimates fraction of cycles when the memory subsystem had loads blocked since they could not forward data from earlier (in program order) overlapping stores. To streamline memory operations in the pipeline; a load can avoid waiting for memory if a prior in-flight store is writing the data that the load wants to read (store forwarding process). However; in some cases the load may be blocked for a significant time pending the store forward. For example; when the prior store is writing a smaller region than the load is reading", + "MetricThreshold": "tma_store_fwd_blk > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric roughly estimates fraction of cycles when the memory subsystem had loads blocked since they could not forward data from earlier (in program order) overlapping stores. To streamline memory operations in the pipeline; a load can avoid waiting for memory if a prior in-flight store is writing the data that the load wants to read (store forwarding process). However; in some cases the load may be blocked for a significant time pending the store forward. For example; when the prior store is writing a smaller region than the load is reading.", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -2652,8 +2655,8 @@ "MetricExpr": "(cpu_core@MEM_STORE_RETIRED.L2_HIT@ * 10 * (1 - cpu_core@MEM_INST_RETIRED.LOCK_LOADS@ / cpu_core@MEM_INST_RETIRED.ALL_STORES@) + (1 - cpu_core@MEM_INST_RETIRED.LOCK_LOADS@ / cpu_core@MEM_INST_RETIRED.ALL_STORES@) * min(cpu_core@CPU_CLK_UNHALTED.THREAD@, cpu_core@OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO@)) / tma_info_thread_clks", "MetricGroup": "BvML;LockCont;MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_issueSL;tma_store_bound_group", "MetricName": "tma_store_latency", - "MetricThreshold": "tma_store_latency > 0.1 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", - "PublicDescription": "This metric estimates fraction of cycles the CPU spent handling L1D store misses. Store accesses usually less impact out-of-order core performance; however; holding resources for longer time can lead into undesired implications (e.g. contention on L1D fill-buffer entries - see FB_Full). Related metrics: tma_branch_resteers, tma_fb_full, tma_l3_hit_latency, tma_lock_latency", + "MetricThreshold": "tma_store_latency > 0.1 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric estimates fraction of cycles the CPU spent handling L1D store misses. Store accesses usually less impact out-of-order core performance; however; holding resources for longer time can lead into undesired implications (e.g. contention on L1D fill-buffer entries - see FB_Full). Related metrics: tma_fb_full, tma_lock_latency", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -2672,7 +2675,7 @@ "MetricExpr": "tma_dtlb_store - tma_store_stlb_miss", "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_store_group", "MetricName": "tma_store_stlb_hit", - "MetricThreshold": "tma_store_stlb_hit > 0.05 & tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_store_stlb_hit > 0.05 & (tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -2681,34 +2684,34 @@ "MetricExpr": "cpu_core@DTLB_STORE_MISSES.WALK_ACTIVE@ / tma_info_core_core_clks", "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_store_group", "MetricName": "tma_store_stlb_miss", - "MetricThreshold": "tma_store_stlb_miss > 0.05 & tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_store_stlb_miss > 0.05 & (tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))", "ScaleUnit": "100%", "Unit": "cpu_core" }, { - "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 1 GB pages for data store accesses", + "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 1 GB pages for data store accesses.", "MetricExpr": "tma_store_stlb_miss * cpu_core@DTLB_STORE_MISSES.WALK_COMPLETED_1G@ / (cpu_core@DTLB_STORE_MISSES.WALK_COMPLETED_4K@ + cpu_core@DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M@ + cpu_core@DTLB_STORE_MISSES.WALK_COMPLETED_1G@)", "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_store_stlb_miss_group", "MetricName": "tma_store_stlb_miss_1g", - "MetricThreshold": "tma_store_stlb_miss_1g > 0.05 & tma_store_stlb_miss > 0.05 & tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_store_stlb_miss_1g > 0.05 & (tma_store_stlb_miss > 0.05 & (tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))))", "ScaleUnit": "100%", "Unit": "cpu_core" }, { - "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 2 or 4 MB pages for data store accesses", + "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 2 or 4 MB pages for data store accesses.", "MetricExpr": "tma_store_stlb_miss * cpu_core@DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M@ / (cpu_core@DTLB_STORE_MISSES.WALK_COMPLETED_4K@ + cpu_core@DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M@ + cpu_core@DTLB_STORE_MISSES.WALK_COMPLETED_1G@)", "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_store_stlb_miss_group", "MetricName": "tma_store_stlb_miss_2m", - "MetricThreshold": "tma_store_stlb_miss_2m > 0.05 & tma_store_stlb_miss > 0.05 & tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_store_stlb_miss_2m > 0.05 & (tma_store_stlb_miss > 0.05 & (tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))))", "ScaleUnit": "100%", "Unit": "cpu_core" }, { - "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 4 KB pages for data store accesses", + "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 4 KB pages for data store accesses.", "MetricExpr": "tma_store_stlb_miss * cpu_core@DTLB_STORE_MISSES.WALK_COMPLETED_4K@ / (cpu_core@DTLB_STORE_MISSES.WALK_COMPLETED_4K@ + cpu_core@DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M@ + cpu_core@DTLB_STORE_MISSES.WALK_COMPLETED_1G@)", "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_store_stlb_miss_group", "MetricName": "tma_store_stlb_miss_4k", - "MetricThreshold": "tma_store_stlb_miss_4k > 0.05 & tma_store_stlb_miss > 0.05 & tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_store_stlb_miss_4k > 0.05 & (tma_store_stlb_miss > 0.05 & (tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))))", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -2717,7 +2720,7 @@ "MetricExpr": "9 * cpu_core@OCR.STREAMING_WR.ANY_RESPONSE@ / tma_info_thread_clks", "MetricGroup": "MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_issueSmSt;tma_store_bound_group", "MetricName": "tma_streaming_stores", - "MetricThreshold": "tma_streaming_stores > 0.2 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_streaming_stores > 0.2 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", "PublicDescription": "This metric estimates how often CPU was stalled due to Streaming store memory accesses; Streaming store optimize out a read request required by RFO stores. Even though store accesses do not typically stall out-of-order CPUs; there are few cases where stores can lead to actual stalls. This metric will be flagged should Streaming stores be a bottleneck. Sample with: OCR.STREAMING_WR.ANY_RESPONSE. Related metrics: tma_fb_full", "ScaleUnit": "100%", "Unit": "cpu_core" @@ -2727,7 +2730,7 @@ "MetricExpr": "cpu_core@INT_MISC.UNKNOWN_BRANCH_CYCLES@ / tma_info_thread_clks", "MetricGroup": "BigFootprint;BvBC;FetchLat;TopdownL4;tma_L4_group;tma_branch_resteers_group", "MetricName": "tma_unknown_branches", - "MetricThreshold": "tma_unknown_branches > 0.05 & tma_branch_resteers > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricThreshold": "tma_unknown_branches > 0.05 & (tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))", "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to new branch address clears. These are fetched branches the Branch Prediction Unit was unable to recognize (e.g. first time the branch is fetched or hitting BTB capacity limit) hence called Unknown Branches. Sample with: FRONTEND_RETIRED.UNKNOWN_BRANCH", "ScaleUnit": "100%", "Unit": "cpu_core" @@ -2737,8 +2740,8 @@ "MetricExpr": "tma_retiring * cpu_core@UOPS_EXECUTED.X87@ / cpu_core@UOPS_EXECUTED.THREAD@", "MetricGroup": "Compute;TopdownL4;tma_L4_group;tma_fp_arith_group", "MetricName": "tma_x87_use", - "MetricThreshold": "tma_x87_use > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6", - "PublicDescription": "This metric serves as an approximation of legacy x87 usage. It accounts for instructions beyond X87 FP arithmetic operations; hence may be used as a thermometer to avoid X87 high usage and preferably upgrade to modern ISA. See Tip under Tuning Hint", + "MetricThreshold": "tma_x87_use > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6)", + "PublicDescription": "This metric serves as an approximation of legacy x87 usage. It accounts for instructions beyond X87 FP arithmetic operations; hence may be used as a thermometer to avoid X87 high usage and preferably upgrade to modern ISA. See Tip under Tuning Hint.", "ScaleUnit": "100%", "Unit": "cpu_core" } diff --git a/tools/perf/pmu-events/arch/x86/alderlake/cache.json b/tools/perf/pmu-events/arch/x86/alderlake/cache.json index a20e19738046..c2802fbb853b 100644 --- a/tools/perf/pmu-events/arch/x86/alderlake/cache.json +++ b/tools/perf/pmu-events/arch/x86/alderlake/cache.json @@ -4,6 +4,7 @@ "Counter": "0,1,2,3", "EventCode": "0x51", "EventName": "L1D.HWPF_MISS", + "PublicDescription": "L1D.HWPF_MISS Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x20", "Unit": "cpu_core" @@ -13,7 +14,7 @@ "Counter": "0,1,2,3", "EventCode": "0x51", "EventName": "L1D.REPLACEMENT", - "PublicDescription": "Counts L1D data line replacements including opportunistic replacements, and replacements that require stall-for-replace or block-for-replace.", + "PublicDescription": "Counts L1D data line replacements including opportunistic replacements, and replacements that require stall-for-replace or block-for-replace. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1", "Unit": "cpu_core" @@ -23,7 +24,7 @@ "Counter": "0,1,2,3", "EventCode": "0x48", "EventName": "L1D_PEND_MISS.FB_FULL", - "PublicDescription": "Counts number of cycles a demand request has waited due to L1D Fill Buffer (FB) unavailability. Demand requests include cacheable/uncacheable demand load, store, lock or SW prefetch accesses.", + "PublicDescription": "Counts number of cycles a demand request has waited due to L1D Fill Buffer (FB) unavailability. Demand requests include cacheable/uncacheable demand load, store, lock or SW prefetch accesses. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x2", "Unit": "cpu_core" @@ -35,7 +36,7 @@ "EdgeDetect": "1", "EventCode": "0x48", "EventName": "L1D_PEND_MISS.FB_FULL_PERIODS", - "PublicDescription": "Counts number of phases a demand request has waited due to L1D Fill Buffer (FB) unavailability. Demand requests include cacheable/uncacheable demand load, store, lock or SW prefetch accesses.", + "PublicDescription": "Counts number of phases a demand request has waited due to L1D Fill Buffer (FB) unavailability. Demand requests include cacheable/uncacheable demand load, store, lock or SW prefetch accesses. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x2", "Unit": "cpu_core" @@ -46,6 +47,7 @@ "Deprecated": "1", "EventCode": "0x48", "EventName": "L1D_PEND_MISS.L2_STALL", + "PublicDescription": "This event is deprecated. Refer to new event L1D_PEND_MISS.L2_STALLS Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x4", "Unit": "cpu_core" @@ -55,7 +57,7 @@ "Counter": "0,1,2,3", "EventCode": "0x48", "EventName": "L1D_PEND_MISS.L2_STALLS", - "PublicDescription": "Counts number of cycles a demand request has waited due to L1D due to lack of L2 resources. Demand requests include cacheable/uncacheable demand load, store, lock or SW prefetch accesses.", + "PublicDescription": "Counts number of cycles a demand request has waited due to L1D due to lack of L2 resources. Demand requests include cacheable/uncacheable demand load, store, lock or SW prefetch accesses. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x4", "Unit": "cpu_core" @@ -65,7 +67,7 @@ "Counter": "0,1,2,3", "EventCode": "0x48", "EventName": "L1D_PEND_MISS.PENDING", - "PublicDescription": "Counts number of L1D misses that are outstanding in each cycle, that is each cycle the number of Fill Buffers (FB) outstanding required by Demand Reads. FB either is held by demand loads, or it is held by non-demand loads and gets hit at least once by demand. The valid outstanding interval is defined until the FB deallocation by one of the following ways: from FB allocation, if FB is allocated by demand from the demand Hit FB, if it is allocated by hardware or software prefetch. Note: In the L1D, a Demand Read contains cacheable or noncacheable demand loads, including ones causing cache-line splits and reads due to page walks resulted from any request type.", + "PublicDescription": "Counts number of L1D misses that are outstanding in each cycle, that is each cycle the number of Fill Buffers (FB) outstanding required by Demand Reads. FB either is held by demand loads, or it is held by non-demand loads and gets hit at least once by demand. The valid outstanding interval is defined until the FB deallocation by one of the following ways: from FB allocation, if FB is allocated by demand from the demand Hit FB, if it is allocated by hardware or software prefetch. Note: In the L1D, a Demand Read contains cacheable or noncacheable demand loads, including ones causing cache-line splits and reads due to page walks resulted from any request type. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x1", "Unit": "cpu_core" @@ -76,7 +78,7 @@ "CounterMask": "1", "EventCode": "0x48", "EventName": "L1D_PEND_MISS.PENDING_CYCLES", - "PublicDescription": "Counts duration of L1D miss outstanding in cycles.", + "PublicDescription": "Counts duration of L1D miss outstanding in cycles. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x1", "Unit": "cpu_core" @@ -86,7 +88,7 @@ "Counter": "0,1,2,3", "EventCode": "0x25", "EventName": "L2_LINES_IN.ALL", - "PublicDescription": "Counts the number of L2 cache lines filling the L2. Counting does not cover rejects.", + "PublicDescription": "Counts the number of L2 cache lines filling the L2. Counting does not cover rejects. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1f", "Unit": "cpu_core" @@ -96,7 +98,7 @@ "Counter": "0,1,2,3", "EventCode": "0x26", "EventName": "L2_LINES_OUT.NON_SILENT", - "PublicDescription": "Counts the number of lines that are evicted by L2 cache when triggered by an L2 cache fill. Those lines are in Modified state. Modified lines are written back to L3", + "PublicDescription": "Counts the number of lines that are evicted by L2 cache when triggered by an L2 cache fill. Those lines are in Modified state. Modified lines are written back to L3 Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0x2", "Unit": "cpu_core" @@ -106,7 +108,7 @@ "Counter": "0,1,2,3", "EventCode": "0x26", "EventName": "L2_LINES_OUT.SILENT", - "PublicDescription": "Counts the number of lines that are silently dropped by L2 cache. These lines are typically in Shared or Exclusive state. A non-threaded event.", + "PublicDescription": "Counts the number of lines that are silently dropped by L2 cache. These lines are typically in Shared or Exclusive state. A non-threaded event. Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0x1", "Unit": "cpu_core" @@ -116,7 +118,7 @@ "Counter": "0,1,2,3", "EventCode": "0x26", "EventName": "L2_LINES_OUT.USELESS_HWPF", - "PublicDescription": "Counts the number of cache lines that have been prefetched by the L2 hardware prefetcher but not used by demand access when evicted from the L2 cache", + "PublicDescription": "Counts the number of cache lines that have been prefetched by the L2 hardware prefetcher but not used by demand access when evicted from the L2 cache Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0x4", "Unit": "cpu_core" @@ -135,7 +137,7 @@ "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_REQUEST.ALL", - "PublicDescription": "Counts all requests that were hit or true misses in L2 cache. True-miss excludes misses that were merged with ongoing L2 misses. [This event is alias to L2_RQSTS.REFERENCES]", + "PublicDescription": "Counts all requests that were hit or true misses in L2 cache. True-miss excludes misses that were merged with ongoing L2 misses. [This event is alias to L2_RQSTS.REFERENCES] Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0xff", "Unit": "cpu_core" @@ -165,7 +167,7 @@ "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_REQUEST.MISS", - "PublicDescription": "Counts read requests of any type with true-miss in the L2 cache. True-miss excludes L2 misses that were merged with ongoing L2 misses. [This event is alias to L2_RQSTS.MISS]", + "PublicDescription": "Counts read requests of any type with true-miss in the L2 cache. True-miss excludes L2 misses that were merged with ongoing L2 misses. [This event is alias to L2_RQSTS.MISS] Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0x3f", "Unit": "cpu_core" @@ -175,7 +177,7 @@ "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_RQSTS.ALL_CODE_RD", - "PublicDescription": "Counts the total number of L2 code requests.", + "PublicDescription": "Counts the total number of L2 code requests. Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0xe4", "Unit": "cpu_core" @@ -185,7 +187,7 @@ "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_RQSTS.ALL_DEMAND_DATA_RD", - "PublicDescription": "Counts Demand Data Read requests accessing the L2 cache. These requests may hit or miss L2 cache. True-miss exclude misses that were merged with ongoing L2 misses. An access is counted once.", + "PublicDescription": "Counts Demand Data Read requests accessing the L2 cache. These requests may hit or miss L2 cache. True-miss exclude misses that were merged with ongoing L2 misses. An access is counted once. Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0xe1", "Unit": "cpu_core" @@ -195,7 +197,7 @@ "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_RQSTS.ALL_DEMAND_MISS", - "PublicDescription": "Counts demand requests that miss L2 cache.", + "PublicDescription": "Counts demand requests that miss L2 cache. Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0x27", "Unit": "cpu_core" @@ -205,6 +207,7 @@ "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_RQSTS.ALL_HWPF", + "PublicDescription": "L2_RQSTS.ALL_HWPF Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0xf0", "Unit": "cpu_core" @@ -214,7 +217,7 @@ "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_RQSTS.ALL_RFO", - "PublicDescription": "Counts the total number of RFO (read for ownership) requests to L2 cache. L2 RFO requests include both L1D demand RFO misses as well as L1D RFO prefetches.", + "PublicDescription": "Counts the total number of RFO (read for ownership) requests to L2 cache. L2 RFO requests include both L1D demand RFO misses as well as L1D RFO prefetches. Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0xe2", "Unit": "cpu_core" @@ -224,7 +227,7 @@ "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_RQSTS.CODE_RD_HIT", - "PublicDescription": "Counts L2 cache hits when fetching instructions, code reads.", + "PublicDescription": "Counts L2 cache hits when fetching instructions, code reads. Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0xc4", "Unit": "cpu_core" @@ -234,7 +237,7 @@ "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_RQSTS.CODE_RD_MISS", - "PublicDescription": "Counts L2 cache misses when fetching instructions.", + "PublicDescription": "Counts L2 cache misses when fetching instructions. Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0x24", "Unit": "cpu_core" @@ -244,7 +247,7 @@ "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_RQSTS.DEMAND_DATA_RD_HIT", - "PublicDescription": "Counts the number of demand Data Read requests initiated by load instructions that hit L2 cache.", + "PublicDescription": "Counts the number of demand Data Read requests initiated by load instructions that hit L2 cache. Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0xc1", "Unit": "cpu_core" @@ -254,7 +257,7 @@ "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_RQSTS.DEMAND_DATA_RD_MISS", - "PublicDescription": "Counts demand Data Read requests with true-miss in the L2 cache. True-miss excludes misses that were merged with ongoing L2 misses. An access is counted once.", + "PublicDescription": "Counts demand Data Read requests with true-miss in the L2 cache. True-miss excludes misses that were merged with ongoing L2 misses. An access is counted once. Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0x21", "Unit": "cpu_core" @@ -264,6 +267,7 @@ "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_RQSTS.HWPF_MISS", + "PublicDescription": "L2_RQSTS.HWPF_MISS Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0x30", "Unit": "cpu_core" @@ -273,7 +277,7 @@ "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_RQSTS.MISS", - "PublicDescription": "Counts read requests of any type with true-miss in the L2 cache. True-miss excludes L2 misses that were merged with ongoing L2 misses. [This event is alias to L2_REQUEST.MISS]", + "PublicDescription": "Counts read requests of any type with true-miss in the L2 cache. True-miss excludes L2 misses that were merged with ongoing L2 misses. [This event is alias to L2_REQUEST.MISS] Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0x3f", "Unit": "cpu_core" @@ -283,7 +287,7 @@ "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_RQSTS.REFERENCES", - "PublicDescription": "Counts all requests that were hit or true misses in L2 cache. True-miss excludes misses that were merged with ongoing L2 misses. [This event is alias to L2_REQUEST.ALL]", + "PublicDescription": "Counts all requests that were hit or true misses in L2 cache. True-miss excludes misses that were merged with ongoing L2 misses. [This event is alias to L2_REQUEST.ALL] Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0xff", "Unit": "cpu_core" @@ -293,7 +297,7 @@ "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_RQSTS.RFO_HIT", - "PublicDescription": "Counts the RFO (Read-for-Ownership) requests that hit L2 cache.", + "PublicDescription": "Counts the RFO (Read-for-Ownership) requests that hit L2 cache. Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0xc2", "Unit": "cpu_core" @@ -303,7 +307,7 @@ "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_RQSTS.RFO_MISS", - "PublicDescription": "Counts the RFO (Read-for-Ownership) requests that miss L2 cache.", + "PublicDescription": "Counts the RFO (Read-for-Ownership) requests that miss L2 cache. Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0x22", "Unit": "cpu_core" @@ -313,7 +317,7 @@ "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_RQSTS.SWPF_HIT", - "PublicDescription": "Counts Software prefetch requests that hit the L2 cache. Accounts for PREFETCHNTA and PREFETCHT0/1/2 instructions when FB is not full.", + "PublicDescription": "Counts Software prefetch requests that hit the L2 cache. Accounts for PREFETCHNTA and PREFETCHT0/1/2 instructions when FB is not full. Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0xc8", "Unit": "cpu_core" @@ -323,7 +327,7 @@ "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_RQSTS.SWPF_MISS", - "PublicDescription": "Counts Software prefetch requests that miss the L2 cache. Accounts for PREFETCHNTA and PREFETCHT0/1/2 instructions when FB is not full.", + "PublicDescription": "Counts Software prefetch requests that miss the L2 cache. Accounts for PREFETCHNTA and PREFETCHT0/1/2 instructions when FB is not full. Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0x28", "Unit": "cpu_core" @@ -333,7 +337,7 @@ "Counter": "0,1,2,3", "EventCode": "0x23", "EventName": "L2_TRANS.L2_WB", - "PublicDescription": "Counts L2 writebacks that access L2 cache.", + "PublicDescription": "Counts L2 writebacks that access L2 cache. Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0x40", "Unit": "cpu_core" @@ -353,7 +357,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0x2e", "EventName": "LONGEST_LAT_CACHE.MISS", - "PublicDescription": "Counts core-originated cacheable requests that miss the L3 cache (Longest Latency cache). Requests include data and code reads, Reads-for-Ownership (RFOs), speculative accesses and hardware prefetches to the L1 and L2. It does not include hardware prefetches to the L3, and may not count other types of requests to the L3.", + "PublicDescription": "Counts core-originated cacheable requests that miss the L3 cache (Longest Latency cache). Requests include data and code reads, Reads-for-Ownership (RFOs), speculative accesses and hardware prefetches to the L1 and L2. It does not include hardware prefetches to the L3, and may not count other types of requests to the L3. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x41", "Unit": "cpu_core" @@ -373,7 +377,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0x2e", "EventName": "LONGEST_LAT_CACHE.REFERENCE", - "PublicDescription": "Counts core-originated cacheable requests to the L3 cache (Longest Latency cache). Requests include data and code reads, Reads-for-Ownership (RFOs), speculative accesses and hardware prefetches to the L1 and L2. It does not include hardware prefetches to the L3, and may not count other types of requests to the L3.", + "PublicDescription": "Counts core-originated cacheable requests to the L3 cache (Longest Latency cache). Requests include data and code reads, Reads-for-Ownership (RFOs), speculative accesses and hardware prefetches to the L1 and L2. It does not include hardware prefetches to the L3, and may not count other types of requests to the L3. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x4f", "Unit": "cpu_core" @@ -461,7 +465,7 @@ "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_INST_RETIRED.ALL_LOADS", - "PublicDescription": "Counts all retired load instructions. This event accounts for SW prefetch instructions of PREFETCHNTA or PREFETCHT0/1/2 or PREFETCHW.", + "PublicDescription": "Counts all retired load instructions. This event accounts for SW prefetch instructions of PREFETCHNTA or PREFETCHT0/1/2 or PREFETCHW. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x81", "Unit": "cpu_core" @@ -472,7 +476,7 @@ "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_INST_RETIRED.ALL_STORES", - "PublicDescription": "Counts all retired store instructions.", + "PublicDescription": "Counts all retired store instructions. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x82", "Unit": "cpu_core" @@ -483,7 +487,7 @@ "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_INST_RETIRED.ANY", - "PublicDescription": "Counts all retired memory instructions - loads and stores.", + "PublicDescription": "Counts all retired memory instructions - loads and stores. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x83", "Unit": "cpu_core" @@ -494,7 +498,7 @@ "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_INST_RETIRED.LOCK_LOADS", - "PublicDescription": "Counts retired load instructions with locked access.", + "PublicDescription": "Counts retired load instructions with locked access. Available PDIST counters: 0", "SampleAfterValue": "100007", "UMask": "0x21", "Unit": "cpu_core" @@ -505,7 +509,7 @@ "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_INST_RETIRED.SPLIT_LOADS", - "PublicDescription": "Counts retired load instructions that split across a cacheline boundary.", + "PublicDescription": "Counts retired load instructions that split across a cacheline boundary. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x41", "Unit": "cpu_core" @@ -516,7 +520,7 @@ "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_INST_RETIRED.SPLIT_STORES", - "PublicDescription": "Counts retired store instructions that split across a cacheline boundary.", + "PublicDescription": "Counts retired store instructions that split across a cacheline boundary. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x42", "Unit": "cpu_core" @@ -527,7 +531,7 @@ "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_INST_RETIRED.STLB_MISS_LOADS", - "PublicDescription": "Number of retired load instructions that (start a) miss in the 2nd-level TLB (STLB).", + "PublicDescription": "Number of retired load instructions that (start a) miss in the 2nd-level TLB (STLB). Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x11", "Unit": "cpu_core" @@ -538,7 +542,7 @@ "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_INST_RETIRED.STLB_MISS_STORES", - "PublicDescription": "Number of retired store instructions that (start a) miss in the 2nd-level TLB (STLB).", + "PublicDescription": "Number of retired store instructions that (start a) miss in the 2nd-level TLB (STLB). Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x12", "Unit": "cpu_core" @@ -548,7 +552,7 @@ "Counter": "0,1,2,3", "EventCode": "0x43", "EventName": "MEM_LOAD_COMPLETED.L1_MISS_ANY", - "PublicDescription": "Number of completed demand load requests that missed the L1 data cache including shadow misses (FB hits, merge to an ongoing L1D miss)", + "PublicDescription": "Number of completed demand load requests that missed the L1 data cache including shadow misses (FB hits, merge to an ongoing L1D miss) Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0xfd", "Unit": "cpu_core" @@ -559,7 +563,7 @@ "Data_LA": "1", "EventCode": "0xd2", "EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD", - "PublicDescription": "Counts retired load instructions whose data sources were HitM responses from shared L3.", + "PublicDescription": "Counts retired load instructions whose data sources were HitM responses from shared L3. Available PDIST counters: 0", "SampleAfterValue": "20011", "UMask": "0x4", "Unit": "cpu_core" @@ -570,7 +574,7 @@ "Data_LA": "1", "EventCode": "0xd2", "EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_HIT", - "PublicDescription": "Counts retired load instructions whose data sources were L3 and cross-core snoop hits in on-pkg core cache.", + "PublicDescription": "Counts retired load instructions whose data sources were L3 and cross-core snoop hits in on-pkg core cache. Available PDIST counters: 0", "SampleAfterValue": "20011", "UMask": "0x2", "Unit": "cpu_core" @@ -581,7 +585,7 @@ "Data_LA": "1", "EventCode": "0xd2", "EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM", - "PublicDescription": "Counts retired load instructions whose data sources were HitM responses from shared L3.", + "PublicDescription": "Counts retired load instructions whose data sources were HitM responses from shared L3. Available PDIST counters: 0", "SampleAfterValue": "20011", "UMask": "0x4", "Unit": "cpu_core" @@ -592,7 +596,7 @@ "Data_LA": "1", "EventCode": "0xd2", "EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS", - "PublicDescription": "Counts the retired load instructions whose data sources were L3 hit and cross-core snoop missed in on-pkg core cache.", + "PublicDescription": "Counts the retired load instructions whose data sources were L3 hit and cross-core snoop missed in on-pkg core cache. Available PDIST counters: 0", "SampleAfterValue": "20011", "UMask": "0x1", "Unit": "cpu_core" @@ -603,7 +607,7 @@ "Data_LA": "1", "EventCode": "0xd2", "EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_NONE", - "PublicDescription": "Counts retired load instructions whose data sources were hits in L3 without snoops required.", + "PublicDescription": "Counts retired load instructions whose data sources were hits in L3 without snoops required. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x8", "Unit": "cpu_core" @@ -614,7 +618,7 @@ "Data_LA": "1", "EventCode": "0xd2", "EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_NO_FWD", - "PublicDescription": "Counts retired load instructions whose data sources were L3 and cross-core snoop hits in on-pkg core cache.", + "PublicDescription": "Counts retired load instructions whose data sources were L3 and cross-core snoop hits in on-pkg core cache. Available PDIST counters: 0", "SampleAfterValue": "20011", "UMask": "0x2", "Unit": "cpu_core" @@ -625,7 +629,7 @@ "Data_LA": "1", "EventCode": "0xd3", "EventName": "MEM_LOAD_L3_MISS_RETIRED.LOCAL_DRAM", - "PublicDescription": "Retired load instructions which data sources missed L3 but serviced from local DRAM.", + "PublicDescription": "Retired load instructions which data sources missed L3 but serviced from local DRAM. Available PDIST counters: 0", "SampleAfterValue": "100007", "UMask": "0x1", "Unit": "cpu_core" @@ -636,7 +640,7 @@ "Data_LA": "1", "EventCode": "0xd4", "EventName": "MEM_LOAD_MISC_RETIRED.UC", - "PublicDescription": "Retired instructions with at least one load to uncacheable memory-type, or at least one cache-line split locked access (Bus Lock).", + "PublicDescription": "Retired instructions with at least one load to uncacheable memory-type, or at least one cache-line split locked access (Bus Lock). Available PDIST counters: 0", "SampleAfterValue": "100007", "UMask": "0x4", "Unit": "cpu_core" @@ -647,7 +651,7 @@ "Data_LA": "1", "EventCode": "0xd1", "EventName": "MEM_LOAD_RETIRED.FB_HIT", - "PublicDescription": "Counts retired load instructions with at least one uop was load missed in L1 but hit FB (Fill Buffers) due to preceding miss to the same cache line with data not ready.", + "PublicDescription": "Counts retired load instructions with at least one uop was load missed in L1 but hit FB (Fill Buffers) due to preceding miss to the same cache line with data not ready. Available PDIST counters: 0", "SampleAfterValue": "100007", "UMask": "0x40", "Unit": "cpu_core" @@ -658,7 +662,7 @@ "Data_LA": "1", "EventCode": "0xd1", "EventName": "MEM_LOAD_RETIRED.L1_HIT", - "PublicDescription": "Counts retired load instructions with at least one uop that hit in the L1 data cache. This event includes all SW prefetches and lock instructions regardless of the data source.", + "PublicDescription": "Counts retired load instructions with at least one uop that hit in the L1 data cache. This event includes all SW prefetches and lock instructions regardless of the data source. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x1", "Unit": "cpu_core" @@ -669,7 +673,7 @@ "Data_LA": "1", "EventCode": "0xd1", "EventName": "MEM_LOAD_RETIRED.L1_MISS", - "PublicDescription": "Counts retired load instructions with at least one uop that missed in the L1 cache.", + "PublicDescription": "Counts retired load instructions with at least one uop that missed in the L1 cache. Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0x8", "Unit": "cpu_core" @@ -680,7 +684,7 @@ "Data_LA": "1", "EventCode": "0xd1", "EventName": "MEM_LOAD_RETIRED.L2_HIT", - "PublicDescription": "Counts retired load instructions with L2 cache hits as data sources.", + "PublicDescription": "Counts retired load instructions with L2 cache hits as data sources. Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0x2", "Unit": "cpu_core" @@ -691,7 +695,7 @@ "Data_LA": "1", "EventCode": "0xd1", "EventName": "MEM_LOAD_RETIRED.L2_MISS", - "PublicDescription": "Counts retired load instructions missed L2 cache as data sources.", + "PublicDescription": "Counts retired load instructions missed L2 cache as data sources. Available PDIST counters: 0", "SampleAfterValue": "100021", "UMask": "0x10", "Unit": "cpu_core" @@ -702,7 +706,7 @@ "Data_LA": "1", "EventCode": "0xd1", "EventName": "MEM_LOAD_RETIRED.L3_HIT", - "PublicDescription": "Counts retired load instructions with at least one uop that hit in the L3 cache.", + "PublicDescription": "Counts retired load instructions with at least one uop that hit in the L3 cache. Available PDIST counters: 0", "SampleAfterValue": "100021", "UMask": "0x4", "Unit": "cpu_core" @@ -713,7 +717,7 @@ "Data_LA": "1", "EventCode": "0xd1", "EventName": "MEM_LOAD_RETIRED.L3_MISS", - "PublicDescription": "Counts retired load instructions with at least one uop that missed in the L3 cache.", + "PublicDescription": "Counts retired load instructions with at least one uop that missed in the L3 cache. Available PDIST counters: 0", "SampleAfterValue": "50021", "UMask": "0x20", "Unit": "cpu_core" @@ -724,6 +728,7 @@ "Data_LA": "1", "EventCode": "0xd1", "EventName": "MEM_LOAD_UOPS_RETIRED.DRAM_HIT", + "PublicDescription": "Counts the number of load uops retired that hit in DRAM. Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0x80", "Unit": "cpu_atom" @@ -734,6 +739,7 @@ "Data_LA": "1", "EventCode": "0xd1", "EventName": "MEM_LOAD_UOPS_RETIRED.HITM", + "PublicDescription": "Counts the number of load uops retired that hit in the L3 cache, in which a snoop was required and modified data was forwarded from another core or module. Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0x20", "Unit": "cpu_atom" @@ -744,6 +750,7 @@ "Data_LA": "1", "EventCode": "0xd1", "EventName": "MEM_LOAD_UOPS_RETIRED.L1_HIT", + "PublicDescription": "Counts the number of load uops retired that hit in the L1 data cache. Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0x1", "Unit": "cpu_atom" @@ -754,6 +761,7 @@ "Data_LA": "1", "EventCode": "0xd1", "EventName": "MEM_LOAD_UOPS_RETIRED.L1_MISS", + "PublicDescription": "Counts the number of load uops retired that miss in the L1 data cache. Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0x8", "Unit": "cpu_atom" @@ -764,6 +772,7 @@ "Data_LA": "1", "EventCode": "0xd1", "EventName": "MEM_LOAD_UOPS_RETIRED.L2_HIT", + "PublicDescription": "Counts the number of load uops retired that hit in the L2 cache. Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0x2", "Unit": "cpu_atom" @@ -774,6 +783,7 @@ "Data_LA": "1", "EventCode": "0xd1", "EventName": "MEM_LOAD_UOPS_RETIRED.L2_MISS", + "PublicDescription": "Counts the number of load uops retired that miss in the L2 cache. Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0x10", "Unit": "cpu_atom" @@ -784,6 +794,7 @@ "Data_LA": "1", "EventCode": "0xd1", "EventName": "MEM_LOAD_UOPS_RETIRED.L3_HIT", + "PublicDescription": "Counts the number of load uops retired that hit in the L3 cache. Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0x4", "Unit": "cpu_atom" @@ -794,6 +805,7 @@ "Data_LA": "1", "EventCode": "0xd2", "EventName": "MEM_LOAD_UOPS_RETIRED_MISC.HIT_E_F", + "PublicDescription": "Counts the number of load uops retired that hit in the L3 cache, in which a snoop was required, and non-modified data was forwarded. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x40", "Unit": "cpu_atom" @@ -804,6 +816,7 @@ "Data_LA": "1", "EventCode": "0xd2", "EventName": "MEM_LOAD_UOPS_RETIRED_MISC.L3_MISS", + "PublicDescription": "Counts the number of load uops retired that miss in the L3 cache. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x20", "Unit": "cpu_atom" @@ -849,6 +862,7 @@ "Counter": "0,1,2,3", "EventCode": "0x44", "EventName": "MEM_STORE_RETIRED.L2_HIT", + "PublicDescription": "MEM_STORE_RETIRED.L2_HIT Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0x1", "Unit": "cpu_core" @@ -859,7 +873,7 @@ "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_UOPS_RETIRED.ALL_LOADS", - "PublicDescription": "Counts the total number of load uops retired.", + "PublicDescription": "Counts the total number of load uops retired. Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0x81", "Unit": "cpu_atom" @@ -870,7 +884,7 @@ "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_UOPS_RETIRED.ALL_STORES", - "PublicDescription": "Counts the total number of store uops retired.", + "PublicDescription": "Counts the total number of store uops retired. Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0x82", "Unit": "cpu_atom" @@ -883,7 +897,7 @@ "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_128", "MSRIndex": "0x3F6", "MSRValue": "0x80", - "PublicDescription": "Counts the number of tagged loads with an instruction latency that exceeds or equals the threshold of 128 cycles as defined in MEC_CR_PEBS_LD_LAT_THRESHOLD (3F6H). Only counts with PEBS enabled. If a PEBS record is generated, will populate the PEBS Latency and PEBS Data Source fields accordingly.", + "PublicDescription": "Counts the number of tagged loads with an instruction latency that exceeds or equals the threshold of 128 cycles as defined in MEC_CR_PEBS_LD_LAT_THRESHOLD (3F6H). Only counts with PEBS enabled. If a PEBS record is generated, will populate the PEBS Latency and PEBS Data Source fields accordingly. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x5", "Unit": "cpu_atom" @@ -896,7 +910,7 @@ "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_16", "MSRIndex": "0x3F6", "MSRValue": "0x10", - "PublicDescription": "Counts the number of tagged loads with an instruction latency that exceeds or equals the threshold of 16 cycles as defined in MEC_CR_PEBS_LD_LAT_THRESHOLD (3F6H). Only counts with PEBS enabled. If a PEBS record is generated, will populate the PEBS Latency and PEBS Data Source fields accordingly.", + "PublicDescription": "Counts the number of tagged loads with an instruction latency that exceeds or equals the threshold of 16 cycles as defined in MEC_CR_PEBS_LD_LAT_THRESHOLD (3F6H). Only counts with PEBS enabled. If a PEBS record is generated, will populate the PEBS Latency and PEBS Data Source fields accordingly. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x5", "Unit": "cpu_atom" @@ -909,7 +923,7 @@ "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_256", "MSRIndex": "0x3F6", "MSRValue": "0x100", - "PublicDescription": "Counts the number of tagged loads with an instruction latency that exceeds or equals the threshold of 256 cycles as defined in MEC_CR_PEBS_LD_LAT_THRESHOLD (3F6H). Only counts with PEBS enabled. If a PEBS record is generated, will populate the PEBS Latency and PEBS Data Source fields accordingly.", + "PublicDescription": "Counts the number of tagged loads with an instruction latency that exceeds or equals the threshold of 256 cycles as defined in MEC_CR_PEBS_LD_LAT_THRESHOLD (3F6H). Only counts with PEBS enabled. If a PEBS record is generated, will populate the PEBS Latency and PEBS Data Source fields accordingly. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x5", "Unit": "cpu_atom" @@ -922,7 +936,7 @@ "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_32", "MSRIndex": "0x3F6", "MSRValue": "0x20", - "PublicDescription": "Counts the number of tagged loads with an instruction latency that exceeds or equals the threshold of 32 cycles as defined in MEC_CR_PEBS_LD_LAT_THRESHOLD (3F6H). Only counts with PEBS enabled. If a PEBS record is generated, will populate the PEBS Latency and PEBS Data Source fields accordingly.", + "PublicDescription": "Counts the number of tagged loads with an instruction latency that exceeds or equals the threshold of 32 cycles as defined in MEC_CR_PEBS_LD_LAT_THRESHOLD (3F6H). Only counts with PEBS enabled. If a PEBS record is generated, will populate the PEBS Latency and PEBS Data Source fields accordingly. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x5", "Unit": "cpu_atom" @@ -935,7 +949,7 @@ "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_4", "MSRIndex": "0x3F6", "MSRValue": "0x4", - "PublicDescription": "Counts the number of tagged loads with an instruction latency that exceeds or equals the threshold of 4 cycles as defined in MEC_CR_PEBS_LD_LAT_THRESHOLD (3F6H). Only counts with PEBS enabled. If a PEBS record is generated, will populate the PEBS Latency and PEBS Data Source fields accordingly.", + "PublicDescription": "Counts the number of tagged loads with an instruction latency that exceeds or equals the threshold of 4 cycles as defined in MEC_CR_PEBS_LD_LAT_THRESHOLD (3F6H). Only counts with PEBS enabled. If a PEBS record is generated, will populate the PEBS Latency and PEBS Data Source fields accordingly. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x5", "Unit": "cpu_atom" @@ -948,7 +962,7 @@ "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_512", "MSRIndex": "0x3F6", "MSRValue": "0x200", - "PublicDescription": "Counts the number of tagged loads with an instruction latency that exceeds or equals the threshold of 512 cycles as defined in MEC_CR_PEBS_LD_LAT_THRESHOLD (3F6H). Only counts with PEBS enabled. If a PEBS record is generated, will populate the PEBS Latency and PEBS Data Source fields accordingly.", + "PublicDescription": "Counts the number of tagged loads with an instruction latency that exceeds or equals the threshold of 512 cycles as defined in MEC_CR_PEBS_LD_LAT_THRESHOLD (3F6H). Only counts with PEBS enabled. If a PEBS record is generated, will populate the PEBS Latency and PEBS Data Source fields accordingly. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x5", "Unit": "cpu_atom" @@ -961,7 +975,7 @@ "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_64", "MSRIndex": "0x3F6", "MSRValue": "0x40", - "PublicDescription": "Counts the number of tagged loads with an instruction latency that exceeds or equals the threshold of 64 cycles as defined in MEC_CR_PEBS_LD_LAT_THRESHOLD (3F6H). Only counts with PEBS enabled. If a PEBS record is generated, will populate the PEBS Latency and PEBS Data Source fields accordingly.", + "PublicDescription": "Counts the number of tagged loads with an instruction latency that exceeds or equals the threshold of 64 cycles as defined in MEC_CR_PEBS_LD_LAT_THRESHOLD (3F6H). Only counts with PEBS enabled. If a PEBS record is generated, will populate the PEBS Latency and PEBS Data Source fields accordingly. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x5", "Unit": "cpu_atom" @@ -974,7 +988,7 @@ "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_8", "MSRIndex": "0x3F6", "MSRValue": "0x8", - "PublicDescription": "Counts the number of tagged loads with an instruction latency that exceeds or equals the threshold of 8 cycles as defined in MEC_CR_PEBS_LD_LAT_THRESHOLD (3F6H). Only counts with PEBS enabled. If a PEBS record is generated, will populate the PEBS Latency and PEBS Data Source fields accordingly.", + "PublicDescription": "Counts the number of tagged loads with an instruction latency that exceeds or equals the threshold of 8 cycles as defined in MEC_CR_PEBS_LD_LAT_THRESHOLD (3F6H). Only counts with PEBS enabled. If a PEBS record is generated, will populate the PEBS Latency and PEBS Data Source fields accordingly. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x5", "Unit": "cpu_atom" @@ -985,6 +999,7 @@ "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_UOPS_RETIRED.LOCK_LOADS", + "PublicDescription": "Counts the number of load uops retired that performed one or more locks. Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0x21", "Unit": "cpu_atom" @@ -995,6 +1010,7 @@ "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_UOPS_RETIRED.SPLIT_LOADS", + "PublicDescription": "Counts the number of retired split load uops. Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0x41", "Unit": "cpu_atom" @@ -1005,6 +1021,7 @@ "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_UOPS_RETIRED.STLB_MISS", + "PublicDescription": "Counts the total number of load and store uops retired that missed in the second level TLB. Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0x13", "Unit": "cpu_atom" @@ -1015,6 +1032,7 @@ "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_UOPS_RETIRED.STLB_MISS_LOADS", + "PublicDescription": "Counts the number of load ops retired that miss in the second Level TLB. Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0x11", "Unit": "cpu_atom" @@ -1025,6 +1043,7 @@ "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_UOPS_RETIRED.STLB_MISS_STORES", + "PublicDescription": "Counts the number of store ops retired that miss in the second level TLB. Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0x12", "Unit": "cpu_atom" @@ -1035,7 +1054,7 @@ "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_UOPS_RETIRED.STORE_LATENCY", - "PublicDescription": "Counts the number of stores uops retired. Counts with or without PEBS enabled. If PEBS is enabled and a PEBS record is generated, will populate PEBS Latency and PEBS Data Source fields accordingly.", + "PublicDescription": "Counts the number of stores uops retired. Counts with or without PEBS enabled. If PEBS is enabled and a PEBS record is generated, will populate PEBS Latency and PEBS Data Source fields accordingly. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x6", "Unit": "cpu_atom" @@ -1045,18 +1064,43 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xe5", "EventName": "MEM_UOP_RETIRED.ANY", - "PublicDescription": "Number of retired micro-operations (uops) for load or store memory accesses", + "PublicDescription": "Number of retired micro-operations (uops) for load or store memory accesses Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x3", "Unit": "cpu_core" }, { + "BriefDescription": "Counts modified writebacks from L1 cache and L2 cache that have any type of response.", + "Counter": "0,1,2,3,4,5", + "EventCode": "0xB7", + "EventName": "OCR.COREWB_M.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x10008", + "PublicDescription": "Counts modified writebacks from L1 cache and L2 cache that have any type of response. Available PDIST counters: 0", + "SampleAfterValue": "100003", + "UMask": "0x1", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that have any type of response.", + "Counter": "0,1,2,3,4,5", + "EventCode": "0xB7", + "EventName": "OCR.DEMAND_CODE_RD.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x10004", + "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that have any type of response. Available PDIST counters: 0", + "SampleAfterValue": "100003", + "UMask": "0x1", + "Unit": "cpu_atom" + }, + { "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were supplied by the L3 cache.", "Counter": "0,1,2,3,4,5", "EventCode": "0xB7", "EventName": "OCR.DEMAND_CODE_RD.L3_HIT", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x1F803C0004", + "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were supplied by the L3 cache. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1", "Unit": "cpu_atom" @@ -1068,6 +1112,7 @@ "EventName": "OCR.DEMAND_CODE_RD.L3_HIT.SNOOP_HITM", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x10003C0004", + "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were supplied by the L3 cache where a snoop was sent, the snoop hit, and modified data was forwarded. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1", "Unit": "cpu_atom" @@ -1079,6 +1124,7 @@ "EventName": "OCR.DEMAND_CODE_RD.L3_HIT.SNOOP_HIT_NO_FWD", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x4003C0004", + "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were supplied by the L3 cache where a snoop was sent, the snoop hit, but no data was forwarded. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1", "Unit": "cpu_atom" @@ -1090,17 +1136,43 @@ "EventName": "OCR.DEMAND_CODE_RD.L3_HIT.SNOOP_HIT_WITH_FWD", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x8003C0004", + "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were supplied by the L3 cache where a snoop was sent, the snoop hit, and non-modified data was forwarded. Available PDIST counters: 0", + "SampleAfterValue": "100003", + "UMask": "0x1", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts demand data reads that have any type of response.", + "Counter": "0,1,2,3,4,5", + "EventCode": "0xB7", + "EventName": "OCR.DEMAND_DATA_RD.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x10001", + "PublicDescription": "Counts demand data reads that have any type of response. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1", "Unit": "cpu_atom" }, { + "BriefDescription": "Counts demand data reads that have any type of response.", + "Counter": "0,1,2,3", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.DEMAND_DATA_RD.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x10001", + "PublicDescription": "Counts demand data reads that have any type of response. Available PDIST counters: 0", + "SampleAfterValue": "100003", + "UMask": "0x1", + "Unit": "cpu_core" + }, + { "BriefDescription": "Counts demand data reads that were supplied by the L3 cache.", "Counter": "0,1,2,3,4,5", "EventCode": "0xB7", "EventName": "OCR.DEMAND_DATA_RD.L3_HIT", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x1F803C0001", + "PublicDescription": "Counts demand data reads that were supplied by the L3 cache. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1", "Unit": "cpu_atom" @@ -1112,6 +1184,7 @@ "EventName": "OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x10003C0001", + "PublicDescription": "Counts demand data reads that were supplied by the L3 cache where a snoop was sent, the snoop hit, and modified data was forwarded. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1", "Unit": "cpu_atom" @@ -1123,6 +1196,7 @@ "EventName": "OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x10003C0001", + "PublicDescription": "Counts demand data reads that resulted in a snoop hit in another cores caches, data forwarding is required as the data is modified. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1", "Unit": "cpu_core" @@ -1134,6 +1208,7 @@ "EventName": "OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_NO_FWD", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x4003C0001", + "PublicDescription": "Counts demand data reads that were supplied by the L3 cache where a snoop was sent, the snoop hit, but no data was forwarded. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1", "Unit": "cpu_atom" @@ -1145,6 +1220,7 @@ "EventName": "OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x8003C0001", + "PublicDescription": "Counts demand data reads that were supplied by the L3 cache where a snoop was sent, the snoop hit, and non-modified data was forwarded. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1", "Unit": "cpu_atom" @@ -1156,6 +1232,31 @@ "EventName": "OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x8003C0001", + "PublicDescription": "Counts demand data reads that resulted in a snoop hit in another cores caches which forwarded the unmodified data to the requesting core. Available PDIST counters: 0", + "SampleAfterValue": "100003", + "UMask": "0x1", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that have any type of response.", + "Counter": "0,1,2,3,4,5", + "EventCode": "0xB7", + "EventName": "OCR.DEMAND_RFO.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x10002", + "PublicDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that have any type of response. Available PDIST counters: 0", + "SampleAfterValue": "100003", + "UMask": "0x1", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts demand read for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that have any type of response.", + "Counter": "0,1,2,3", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.DEMAND_RFO.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x10002", + "PublicDescription": "Counts demand read for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that have any type of response. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1", "Unit": "cpu_core" @@ -1167,6 +1268,7 @@ "EventName": "OCR.DEMAND_RFO.L3_HIT", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x1F803C0002", + "PublicDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that were supplied by the L3 cache. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1", "Unit": "cpu_atom" @@ -1178,6 +1280,7 @@ "EventName": "OCR.DEMAND_RFO.L3_HIT.SNOOP_HITM", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x10003C0002", + "PublicDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that were supplied by the L3 cache where a snoop was sent, the snoop hit, and modified data was forwarded. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1", "Unit": "cpu_atom" @@ -1189,6 +1292,7 @@ "EventName": "OCR.DEMAND_RFO.L3_HIT.SNOOP_HITM", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x10003C0002", + "PublicDescription": "Counts demand read for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that resulted in a snoop hit in another cores caches, data forwarding is required as the data is modified. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1", "Unit": "cpu_core" @@ -1200,6 +1304,7 @@ "EventName": "OCR.DEMAND_RFO.L3_HIT.SNOOP_HIT_NO_FWD", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x4003C0002", + "PublicDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that were supplied by the L3 cache where a snoop was sent, the snoop hit, but no data was forwarded. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1", "Unit": "cpu_atom" @@ -1211,6 +1316,19 @@ "EventName": "OCR.DEMAND_RFO.L3_HIT.SNOOP_HIT_WITH_FWD", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x8003C0002", + "PublicDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that were supplied by the L3 cache where a snoop was sent, the snoop hit, and non-modified data was forwarded. Available PDIST counters: 0", + "SampleAfterValue": "100003", + "UMask": "0x1", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts L1 data cache software prefetches which include T0/T1/T2 and NTA (except PREFETCHW) that have any type of response.", + "Counter": "0,1,2,3,4,5", + "EventCode": "0xB7", + "EventName": "OCR.SWPF_RD.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x14000", + "PublicDescription": "Counts L1 data cache software prefetches which include T0/T1/T2 and NTA (except PREFETCHW) that have any type of response. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1", "Unit": "cpu_atom" @@ -1222,6 +1340,7 @@ "EventName": "OCR.SWPF_RD.L3_HIT", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x1F803C4000", + "PublicDescription": "Counts L1 data cache software prefetches which include T0/T1/T2 and NTA (except PREFETCHW) that were supplied by the L3 cache. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1", "Unit": "cpu_atom" @@ -1233,6 +1352,7 @@ "EventName": "OCR.SWPF_RD.L3_HIT.SNOOP_HITM", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x10003C4000", + "PublicDescription": "Counts L1 data cache software prefetches which include T0/T1/T2 and NTA (except PREFETCHW) that were supplied by the L3 cache where a snoop was sent, the snoop hit, and modified data was forwarded. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1", "Unit": "cpu_atom" @@ -1244,6 +1364,7 @@ "EventName": "OCR.SWPF_RD.L3_HIT.SNOOP_HIT_NO_FWD", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x4003C4000", + "PublicDescription": "Counts L1 data cache software prefetches which include T0/T1/T2 and NTA (except PREFETCHW) that were supplied by the L3 cache where a snoop was sent, the snoop hit, but no data was forwarded. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1", "Unit": "cpu_atom" @@ -1255,6 +1376,7 @@ "EventName": "OCR.SWPF_RD.L3_HIT.SNOOP_HIT_WITH_FWD", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x8003C4000", + "PublicDescription": "Counts L1 data cache software prefetches which include T0/T1/T2 and NTA (except PREFETCHW) that were supplied by the L3 cache where a snoop was sent, the snoop hit, and non-modified data was forwarded. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1", "Unit": "cpu_atom" @@ -1264,6 +1386,7 @@ "Counter": "0,1,2,3", "EventCode": "0x21", "EventName": "OFFCORE_REQUESTS.ALL_REQUESTS", + "PublicDescription": "OFFCORE_REQUESTS.ALL_REQUESTS Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x80", "Unit": "cpu_core" @@ -1273,7 +1396,7 @@ "Counter": "0,1,2,3", "EventCode": "0x21", "EventName": "OFFCORE_REQUESTS.DATA_RD", - "PublicDescription": "Counts the demand and prefetch data reads. All Core Data Reads include cacheable 'Demands' and L2 prefetchers (not L3 prefetchers). Counting also covers reads due to page walks resulted from any request type.", + "PublicDescription": "Counts the demand and prefetch data reads. All Core Data Reads include cacheable 'Demands' and L2 prefetchers (not L3 prefetchers). Counting also covers reads due to page walks resulted from any request type. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x8", "Unit": "cpu_core" @@ -1283,7 +1406,7 @@ "Counter": "0,1,2,3", "EventCode": "0x21", "EventName": "OFFCORE_REQUESTS.DEMAND_CODE_RD", - "PublicDescription": "Counts both cacheable and non-cacheable code read requests.", + "PublicDescription": "Counts both cacheable and non-cacheable code read requests. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x2", "Unit": "cpu_core" @@ -1293,7 +1416,7 @@ "Counter": "0,1,2,3", "EventCode": "0x21", "EventName": "OFFCORE_REQUESTS.DEMAND_DATA_RD", - "PublicDescription": "Counts the Demand Data Read requests sent to uncore. Use it in conjunction with OFFCORE_REQUESTS_OUTSTANDING to determine average latency in the uncore.", + "PublicDescription": "Counts the Demand Data Read requests sent to uncore. Use it in conjunction with OFFCORE_REQUESTS_OUTSTANDING to determine average latency in the uncore. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1", "Unit": "cpu_core" @@ -1303,7 +1426,7 @@ "Counter": "0,1,2,3", "EventCode": "0x21", "EventName": "OFFCORE_REQUESTS.DEMAND_RFO", - "PublicDescription": "Counts the demand RFO (read for ownership) requests including regular RFOs, locks, ItoM.", + "PublicDescription": "Counts the demand RFO (read for ownership) requests including regular RFOs, locks, ItoM. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x4", "Unit": "cpu_core" @@ -1315,6 +1438,7 @@ "Errata": "ADL038", "EventCode": "0x20", "EventName": "OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD", + "PublicDescription": "This event is deprecated. Refer to new event OFFCORE_REQUESTS_OUTSTANDING.DATA_RD Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x8", "Unit": "cpu_core" @@ -1326,6 +1450,7 @@ "Errata": "ADL038", "EventCode": "0x20", "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD", + "PublicDescription": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x8", "Unit": "cpu_core" @@ -1336,7 +1461,7 @@ "CounterMask": "1", "EventCode": "0x20", "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_CODE_RD", - "PublicDescription": "Counts the number of offcore outstanding Code Reads transactions in the super queue every cycle. The 'Offcore outstanding' state of the transaction lasts from the L2 miss until the sending transaction completion to requestor (SQ deallocation). See the corresponding Umask under OFFCORE_REQUESTS.", + "PublicDescription": "Counts the number of offcore outstanding Code Reads transactions in the super queue every cycle. The 'Offcore outstanding' state of the transaction lasts from the L2 miss until the sending transaction completion to requestor (SQ deallocation). See the corresponding Umask under OFFCORE_REQUESTS. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x2", "Unit": "cpu_core" @@ -1347,6 +1472,7 @@ "CounterMask": "1", "EventCode": "0x20", "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_DATA_RD", + "PublicDescription": "Cycles where at least 1 outstanding demand data read request is pending. Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x1", "Unit": "cpu_core" @@ -1357,7 +1483,7 @@ "CounterMask": "1", "EventCode": "0x20", "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO", - "PublicDescription": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO", + "PublicDescription": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x4", "Unit": "cpu_core" @@ -1368,6 +1494,7 @@ "Errata": "ADL038", "EventCode": "0x20", "EventName": "OFFCORE_REQUESTS_OUTSTANDING.DATA_RD", + "PublicDescription": "OFFCORE_REQUESTS_OUTSTANDING.DATA_RD Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x8", "Unit": "cpu_core" @@ -1377,7 +1504,7 @@ "Counter": "0,1,2,3", "EventCode": "0x20", "EventName": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_CODE_RD", - "PublicDescription": "Counts the number of offcore outstanding Code Reads transactions in the super queue every cycle. The 'Offcore outstanding' state of the transaction lasts from the L2 miss until the sending transaction completion to requestor (SQ deallocation). See the corresponding Umask under OFFCORE_REQUESTS.", + "PublicDescription": "Counts the number of offcore outstanding Code Reads transactions in the super queue every cycle. The 'Offcore outstanding' state of the transaction lasts from the L2 miss until the sending transaction completion to requestor (SQ deallocation). See the corresponding Umask under OFFCORE_REQUESTS. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x2", "Unit": "cpu_core" @@ -1387,7 +1514,7 @@ "Counter": "0,1,2,3", "EventCode": "0x20", "EventName": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD", - "PublicDescription": "For every cycle, increments by the number of outstanding demand data read requests pending. Requests are considered outstanding from the time they miss the core's L2 cache until the transaction completion message is sent to the requestor.", + "PublicDescription": "For every cycle, increments by the number of outstanding demand data read requests pending. Requests are considered outstanding from the time they miss the core's L2 cache until the transaction completion message is sent to the requestor. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x1", "Unit": "cpu_core" @@ -1397,7 +1524,7 @@ "Counter": "0,1,2,3", "EventCode": "0x2c", "EventName": "SQ_MISC.BUS_LOCK", - "PublicDescription": "Counts the more expensive bus lock needed to enforce cache coherency for certain memory accesses that need to be done atomically. Can be created by issuing an atomic instruction (via the LOCK prefix) which causes a cache line split or accesses uncacheable memory.", + "PublicDescription": "Counts the more expensive bus lock needed to enforce cache coherency for certain memory accesses that need to be done atomically. Can be created by issuing an atomic instruction (via the LOCK prefix) which causes a cache line split or accesses uncacheable memory. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x10", "Unit": "cpu_core" @@ -1407,6 +1534,7 @@ "Counter": "0,1,2,3", "EventCode": "0x40", "EventName": "SW_PREFETCH_ACCESS.ANY", + "PublicDescription": "Counts the number of PREFETCHNTA, PREFETCHW, PREFETCHT0, PREFETCHT1 or PREFETCHT2 instructions executed. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0xf", "Unit": "cpu_core" @@ -1416,7 +1544,7 @@ "Counter": "0,1,2,3", "EventCode": "0x40", "EventName": "SW_PREFETCH_ACCESS.NTA", - "PublicDescription": "Counts the number of PREFETCHNTA instructions executed.", + "PublicDescription": "Counts the number of PREFETCHNTA instructions executed. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1", "Unit": "cpu_core" @@ -1426,7 +1554,7 @@ "Counter": "0,1,2,3", "EventCode": "0x40", "EventName": "SW_PREFETCH_ACCESS.PREFETCHW", - "PublicDescription": "Counts the number of PREFETCHW instructions executed.", + "PublicDescription": "Counts the number of PREFETCHW instructions executed. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x8", "Unit": "cpu_core" @@ -1436,7 +1564,7 @@ "Counter": "0,1,2,3", "EventCode": "0x40", "EventName": "SW_PREFETCH_ACCESS.T0", - "PublicDescription": "Counts the number of PREFETCHT0 instructions executed.", + "PublicDescription": "Counts the number of PREFETCHT0 instructions executed. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x2", "Unit": "cpu_core" @@ -1446,7 +1574,7 @@ "Counter": "0,1,2,3", "EventCode": "0x40", "EventName": "SW_PREFETCH_ACCESS.T1_T2", - "PublicDescription": "Counts the number of PREFETCHT1 or PREFETCHT2 instructions executed.", + "PublicDescription": "Counts the number of PREFETCHT1 or PREFETCHT2 instructions executed. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x4", "Unit": "cpu_core" diff --git a/tools/perf/pmu-events/arch/x86/alderlake/floating-point.json b/tools/perf/pmu-events/arch/x86/alderlake/floating-point.json index 62fd70f220e5..ce570b96360a 100644 --- a/tools/perf/pmu-events/arch/x86/alderlake/floating-point.json +++ b/tools/perf/pmu-events/arch/x86/alderlake/floating-point.json @@ -14,6 +14,7 @@ "CounterMask": "1", "EventCode": "0xb0", "EventName": "ARITH.FPDIV_ACTIVE", + "PublicDescription": "ARITH.FPDIV_ACTIVE Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x1", "Unit": "cpu_core" @@ -32,7 +33,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc1", "EventName": "ASSISTS.FP", - "PublicDescription": "Counts all microcode Floating Point assists.", + "PublicDescription": "Counts all microcode Floating Point assists. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x2", "Unit": "cpu_core" @@ -42,6 +43,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc1", "EventName": "ASSISTS.SSE_AVX_MIX", + "PublicDescription": "ASSISTS.SSE_AVX_MIX Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x10", "Unit": "cpu_core" @@ -51,6 +53,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xb3", "EventName": "FP_ARITH_DISPATCHED.PORT_0", + "PublicDescription": "FP_ARITH_DISPATCHED.PORT_0 [This event is alias to FP_ARITH_DISPATCHED.V0] Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x1", "Unit": "cpu_core" @@ -60,6 +63,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xb3", "EventName": "FP_ARITH_DISPATCHED.PORT_1", + "PublicDescription": "FP_ARITH_DISPATCHED.PORT_1 [This event is alias to FP_ARITH_DISPATCHED.V1] Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x2", "Unit": "cpu_core" @@ -69,6 +73,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xb3", "EventName": "FP_ARITH_DISPATCHED.PORT_5", + "PublicDescription": "FP_ARITH_DISPATCHED.PORT_5 [This event is alias to FP_ARITH_DISPATCHED.V2] Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x4", "Unit": "cpu_core" @@ -78,6 +83,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xb3", "EventName": "FP_ARITH_DISPATCHED.V0", + "PublicDescription": "FP_ARITH_DISPATCHED.V0 [This event is alias to FP_ARITH_DISPATCHED.PORT_0] Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x1", "Unit": "cpu_core" @@ -87,6 +93,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xb3", "EventName": "FP_ARITH_DISPATCHED.V1", + "PublicDescription": "FP_ARITH_DISPATCHED.V1 [This event is alias to FP_ARITH_DISPATCHED.PORT_1] Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x2", "Unit": "cpu_core" @@ -96,6 +103,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xb3", "EventName": "FP_ARITH_DISPATCHED.V2", + "PublicDescription": "FP_ARITH_DISPATCHED.V2 [This event is alias to FP_ARITH_DISPATCHED.PORT_5] Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x4", "Unit": "cpu_core" @@ -105,7 +113,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc7", "EventName": "FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE", - "PublicDescription": "Number of SSE/AVX computational 128-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 2 computation operations, one for each element. Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.", + "PublicDescription": "Number of SSE/AVX computational 128-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 2 computation operations, one for each element. Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x4", "Unit": "cpu_core" @@ -115,7 +123,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc7", "EventName": "FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE", - "PublicDescription": "Number of SSE/AVX computational 128-bit packed single precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 4 computation operations, one for each element. Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT RSQRT RCP DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.", + "PublicDescription": "Number of SSE/AVX computational 128-bit packed single precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 4 computation operations, one for each element. Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT RSQRT RCP DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x8", "Unit": "cpu_core" @@ -125,7 +133,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc7", "EventName": "FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE", - "PublicDescription": "Number of SSE/AVX computational 256-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 4 computation operations, one for each element. Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.", + "PublicDescription": "Number of SSE/AVX computational 256-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 4 computation operations, one for each element. Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x10", "Unit": "cpu_core" @@ -135,7 +143,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc7", "EventName": "FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE", - "PublicDescription": "Number of SSE/AVX computational 256-bit packed single precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 8 computation operations, one for each element. Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT RSQRT RCP DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.", + "PublicDescription": "Number of SSE/AVX computational 256-bit packed single precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 8 computation operations, one for each element. Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT RSQRT RCP DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x20", "Unit": "cpu_core" @@ -145,7 +153,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc7", "EventName": "FP_ARITH_INST_RETIRED.4_FLOPS", - "PublicDescription": "Number of SSE/AVX computational 128-bit packed single precision and 256-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 2 or/and 4 computation operations, one for each element. Applies to SSE* and AVX* packed single precision floating-point and packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX RCP14 RSQRT14 SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.", + "PublicDescription": "Number of SSE/AVX computational 128-bit packed single precision and 256-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 2 or/and 4 computation operations, one for each element. Applies to SSE* and AVX* packed single precision floating-point and packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX RCP14 RSQRT14 SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x18", "Unit": "cpu_core" @@ -155,7 +163,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc7", "EventName": "FP_ARITH_INST_RETIRED.SCALAR", - "PublicDescription": "Number of SSE/AVX computational scalar single precision and double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 1 computational operation. Applies to SSE* and AVX* scalar single precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT RSQRT RCP FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.", + "PublicDescription": "Number of SSE/AVX computational scalar single precision and double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 1 computational operation. Applies to SSE* and AVX* scalar single precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT RSQRT RCP FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x3", "Unit": "cpu_core" @@ -165,7 +173,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc7", "EventName": "FP_ARITH_INST_RETIRED.SCALAR_DOUBLE", - "PublicDescription": "Number of SSE/AVX computational scalar double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 1 computational operation. Applies to SSE* and AVX* scalar double precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.", + "PublicDescription": "Number of SSE/AVX computational scalar double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 1 computational operation. Applies to SSE* and AVX* scalar double precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1", "Unit": "cpu_core" @@ -175,7 +183,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc7", "EventName": "FP_ARITH_INST_RETIRED.SCALAR_SINGLE", - "PublicDescription": "Number of SSE/AVX computational scalar single precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 1 computational operation. Applies to SSE* and AVX* scalar single precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT RSQRT RCP FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.", + "PublicDescription": "Number of SSE/AVX computational scalar single precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 1 computational operation. Applies to SSE* and AVX* scalar single precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT RSQRT RCP FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x2", "Unit": "cpu_core" @@ -185,7 +193,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc7", "EventName": "FP_ARITH_INST_RETIRED.VECTOR", - "PublicDescription": "Number of any Vector retired FP arithmetic instructions. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.", + "PublicDescription": "Number of any Vector retired FP arithmetic instructions. The DAZ and FTZ flags in the MXCSR register need to be set when using these events. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0xfc", "Unit": "cpu_core" @@ -205,6 +213,7 @@ "Counter": "0,1,2,3,4,5", "EventCode": "0xc2", "EventName": "UOPS_RETIRED.FPDIV", + "PublicDescription": "Counts the number of floating point divide uops retired (x87 and SSE, including x87 sqrt). Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x8", "Unit": "cpu_atom" diff --git a/tools/perf/pmu-events/arch/x86/alderlake/frontend.json b/tools/perf/pmu-events/arch/x86/alderlake/frontend.json index c5b3818ad479..dae3174a74fb 100644 --- a/tools/perf/pmu-events/arch/x86/alderlake/frontend.json +++ b/tools/perf/pmu-events/arch/x86/alderlake/frontend.json @@ -14,7 +14,7 @@ "Counter": "0,1,2,3", "EventCode": "0x60", "EventName": "BACLEARS.ANY", - "PublicDescription": "Number of times the front-end is resteered when it finds a branch instruction in a fetch line. This is called Unknown Branch which occurs for the first time a branch instruction is fetched or when the branch is not tracked by the BPU (Branch Prediction Unit) anymore.", + "PublicDescription": "Number of times the front-end is resteered when it finds a branch instruction in a fetch line. This is called Unknown Branch which occurs for the first time a branch instruction is fetched or when the branch is not tracked by the BPU (Branch Prediction Unit) anymore. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1", "Unit": "cpu_core" @@ -24,7 +24,7 @@ "Counter": "0,1,2,3", "EventCode": "0x87", "EventName": "DECODE.LCP", - "PublicDescription": "Counts cycles that the Instruction Length decoder (ILD) stalls occurred due to dynamically changing prefix length of the decoded instruction (by operand size prefix instruction 0x66, address size prefix instruction 0x67 or REX.W for Intel64). Count is proportional to the number of prefixes in a 16B-line. This may result in a three-cycle penalty for each LCP (Length changing prefix) in a 16-byte chunk.", + "PublicDescription": "Counts cycles that the Instruction Length decoder (ILD) stalls occurred due to dynamically changing prefix length of the decoded instruction (by operand size prefix instruction 0x66, address size prefix instruction 0x67 or REX.W for Intel64). Count is proportional to the number of prefixes in a 16B-line. This may result in a three-cycle penalty for each LCP (Length changing prefix) in a 16-byte chunk. Available PDIST counters: 0", "SampleAfterValue": "500009", "UMask": "0x1", "Unit": "cpu_core" @@ -34,6 +34,7 @@ "Counter": "0,1,2,3", "EventCode": "0x87", "EventName": "DECODE.MS_BUSY", + "PublicDescription": "Cycles the Microcode Sequencer is busy. Available PDIST counters: 0", "SampleAfterValue": "500009", "UMask": "0x2", "Unit": "cpu_core" @@ -43,7 +44,7 @@ "Counter": "0,1,2,3", "EventCode": "0x61", "EventName": "DSB2MITE_SWITCHES.PENALTY_CYCLES", - "PublicDescription": "Decode Stream Buffer (DSB) is a Uop-cache that holds translations of previously fetched instructions that were decoded by the legacy x86 decode pipeline (MITE). This event counts fetch penalty cycles when a transition occurs from DSB to MITE.", + "PublicDescription": "Decode Stream Buffer (DSB) is a Uop-cache that holds translations of previously fetched instructions that were decoded by the legacy x86 decode pipeline (MITE). This event counts fetch penalty cycles when a transition occurs from DSB to MITE. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x2", "Unit": "cpu_core" @@ -55,7 +56,7 @@ "EventName": "FRONTEND_RETIRED.ANY_DSB_MISS", "MSRIndex": "0x3F7", "MSRValue": "0x1", - "PublicDescription": "Counts retired Instructions that experienced DSB (Decode stream buffer i.e. the decoded instruction-cache) miss.", + "PublicDescription": "Counts retired Instructions that experienced DSB (Decode stream buffer i.e. the decoded instruction-cache) miss. Available PDIST counters: 0", "SampleAfterValue": "100007", "UMask": "0x1", "Unit": "cpu_core" @@ -67,7 +68,7 @@ "EventName": "FRONTEND_RETIRED.DSB_MISS", "MSRIndex": "0x3F7", "MSRValue": "0x11", - "PublicDescription": "Number of retired Instructions that experienced a critical DSB (Decode stream buffer i.e. the decoded instruction-cache) miss. Critical means stalls were exposed to the back-end as a result of the DSB miss.", + "PublicDescription": "Number of retired Instructions that experienced a critical DSB (Decode stream buffer i.e. the decoded instruction-cache) miss. Critical means stalls were exposed to the back-end as a result of the DSB miss. Available PDIST counters: 0", "SampleAfterValue": "100007", "UMask": "0x1", "Unit": "cpu_core" @@ -79,7 +80,7 @@ "EventName": "FRONTEND_RETIRED.ITLB_MISS", "MSRIndex": "0x3F7", "MSRValue": "0x14", - "PublicDescription": "Counts retired Instructions that experienced iTLB (Instruction TLB) true miss.", + "PublicDescription": "Counts retired Instructions that experienced iTLB (Instruction TLB) true miss. Available PDIST counters: 0", "SampleAfterValue": "100007", "UMask": "0x1", "Unit": "cpu_core" @@ -91,7 +92,7 @@ "EventName": "FRONTEND_RETIRED.L1I_MISS", "MSRIndex": "0x3F7", "MSRValue": "0x12", - "PublicDescription": "Counts retired Instructions who experienced Instruction L1 Cache true miss.", + "PublicDescription": "Counts retired Instructions who experienced Instruction L1 Cache true miss. Available PDIST counters: 0", "SampleAfterValue": "100007", "UMask": "0x1", "Unit": "cpu_core" @@ -103,7 +104,7 @@ "EventName": "FRONTEND_RETIRED.L2_MISS", "MSRIndex": "0x3F7", "MSRValue": "0x13", - "PublicDescription": "Counts retired Instructions who experienced Instruction L2 Cache true miss.", + "PublicDescription": "Counts retired Instructions who experienced Instruction L2 Cache true miss. Available PDIST counters: 0", "SampleAfterValue": "100007", "UMask": "0x1", "Unit": "cpu_core" @@ -115,7 +116,7 @@ "EventName": "FRONTEND_RETIRED.LATENCY_GE_1", "MSRIndex": "0x3F7", "MSRValue": "0x600106", - "PublicDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of at least 1 cycle which was not interrupted by a back-end stall.", + "PublicDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of at least 1 cycle which was not interrupted by a back-end stall. Available PDIST counters: 0", "SampleAfterValue": "100007", "UMask": "0x1", "Unit": "cpu_core" @@ -127,7 +128,7 @@ "EventName": "FRONTEND_RETIRED.LATENCY_GE_128", "MSRIndex": "0x3F7", "MSRValue": "0x608006", - "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 128 cycles which was not interrupted by a back-end stall.", + "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 128 cycles which was not interrupted by a back-end stall. Available PDIST counters: 0", "SampleAfterValue": "100007", "UMask": "0x1", "Unit": "cpu_core" @@ -139,7 +140,7 @@ "EventName": "FRONTEND_RETIRED.LATENCY_GE_16", "MSRIndex": "0x3F7", "MSRValue": "0x601006", - "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 16 cycles. During this period the front-end delivered no uops.", + "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 16 cycles. During this period the front-end delivered no uops. Available PDIST counters: 0", "SampleAfterValue": "100007", "UMask": "0x1", "Unit": "cpu_core" @@ -151,7 +152,7 @@ "EventName": "FRONTEND_RETIRED.LATENCY_GE_2", "MSRIndex": "0x3F7", "MSRValue": "0x600206", - "PublicDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of at least 2 cycles which was not interrupted by a back-end stall.", + "PublicDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of at least 2 cycles which was not interrupted by a back-end stall. Available PDIST counters: 0", "SampleAfterValue": "100007", "UMask": "0x1", "Unit": "cpu_core" @@ -163,7 +164,7 @@ "EventName": "FRONTEND_RETIRED.LATENCY_GE_256", "MSRIndex": "0x3F7", "MSRValue": "0x610006", - "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 256 cycles which was not interrupted by a back-end stall.", + "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 256 cycles which was not interrupted by a back-end stall. Available PDIST counters: 0", "SampleAfterValue": "100007", "UMask": "0x1", "Unit": "cpu_core" @@ -175,7 +176,7 @@ "EventName": "FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1", "MSRIndex": "0x3F7", "MSRValue": "0x100206", - "PublicDescription": "Counts retired instructions that are delivered to the back-end after the front-end had at least 1 bubble-slot for a period of 2 cycles. A bubble-slot is an empty issue-pipeline slot while there was no RAT stall.", + "PublicDescription": "Counts retired instructions that are delivered to the back-end after the front-end had at least 1 bubble-slot for a period of 2 cycles. A bubble-slot is an empty issue-pipeline slot while there was no RAT stall. Available PDIST counters: 0", "SampleAfterValue": "100007", "UMask": "0x1", "Unit": "cpu_core" @@ -187,7 +188,7 @@ "EventName": "FRONTEND_RETIRED.LATENCY_GE_32", "MSRIndex": "0x3F7", "MSRValue": "0x602006", - "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 32 cycles. During this period the front-end delivered no uops.", + "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 32 cycles. During this period the front-end delivered no uops. Available PDIST counters: 0", "SampleAfterValue": "100007", "UMask": "0x1", "Unit": "cpu_core" @@ -199,7 +200,7 @@ "EventName": "FRONTEND_RETIRED.LATENCY_GE_4", "MSRIndex": "0x3F7", "MSRValue": "0x600406", - "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 4 cycles which was not interrupted by a back-end stall.", + "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 4 cycles which was not interrupted by a back-end stall. Available PDIST counters: 0", "SampleAfterValue": "100007", "UMask": "0x1", "Unit": "cpu_core" @@ -211,7 +212,7 @@ "EventName": "FRONTEND_RETIRED.LATENCY_GE_512", "MSRIndex": "0x3F7", "MSRValue": "0x620006", - "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 512 cycles which was not interrupted by a back-end stall.", + "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 512 cycles which was not interrupted by a back-end stall. Available PDIST counters: 0", "SampleAfterValue": "100007", "UMask": "0x1", "Unit": "cpu_core" @@ -223,7 +224,7 @@ "EventName": "FRONTEND_RETIRED.LATENCY_GE_64", "MSRIndex": "0x3F7", "MSRValue": "0x604006", - "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 64 cycles which was not interrupted by a back-end stall.", + "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 64 cycles which was not interrupted by a back-end stall. Available PDIST counters: 0", "SampleAfterValue": "100007", "UMask": "0x1", "Unit": "cpu_core" @@ -235,7 +236,7 @@ "EventName": "FRONTEND_RETIRED.LATENCY_GE_8", "MSRIndex": "0x3F7", "MSRValue": "0x600806", - "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 8 cycles. During this period the front-end delivered no uops.", + "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 8 cycles. During this period the front-end delivered no uops. Available PDIST counters: 0", "SampleAfterValue": "100007", "UMask": "0x1", "Unit": "cpu_core" @@ -247,6 +248,7 @@ "EventName": "FRONTEND_RETIRED.MS_FLOWS", "MSRIndex": "0x3F7", "MSRValue": "0x8", + "PublicDescription": "FRONTEND_RETIRED.MS_FLOWS Available PDIST counters: 0", "SampleAfterValue": "100007", "UMask": "0x1", "Unit": "cpu_core" @@ -258,7 +260,7 @@ "EventName": "FRONTEND_RETIRED.STLB_MISS", "MSRIndex": "0x3F7", "MSRValue": "0x15", - "PublicDescription": "Counts retired Instructions that experienced STLB (2nd level TLB) true miss.", + "PublicDescription": "Counts retired Instructions that experienced STLB (2nd level TLB) true miss. Available PDIST counters: 0", "SampleAfterValue": "100007", "UMask": "0x1", "Unit": "cpu_core" @@ -270,6 +272,7 @@ "EventName": "FRONTEND_RETIRED.UNKNOWN_BRANCH", "MSRIndex": "0x3F7", "MSRValue": "0x17", + "PublicDescription": "FRONTEND_RETIRED.UNKNOWN_BRANCH Available PDIST counters: 0", "SampleAfterValue": "100007", "UMask": "0x1", "Unit": "cpu_core" @@ -299,7 +302,7 @@ "Counter": "0,1,2,3", "EventCode": "0x80", "EventName": "ICACHE_DATA.STALLS", - "PublicDescription": "Counts cycles where a code line fetch is stalled due to an L1 instruction cache miss. The decode pipeline works at a 32 Byte granularity.", + "PublicDescription": "Counts cycles where a code line fetch is stalled due to an L1 instruction cache miss. The decode pipeline works at a 32 Byte granularity. Available PDIST counters: 0", "SampleAfterValue": "500009", "UMask": "0x4", "Unit": "cpu_core" @@ -311,6 +314,7 @@ "EdgeDetect": "1", "EventCode": "0x80", "EventName": "ICACHE_DATA.STALL_PERIODS", + "PublicDescription": "ICACHE_DATA.STALL_PERIODS Available PDIST counters: 0", "SampleAfterValue": "500009", "UMask": "0x4", "Unit": "cpu_core" @@ -320,7 +324,7 @@ "Counter": "0,1,2,3", "EventCode": "0x83", "EventName": "ICACHE_TAG.STALLS", - "PublicDescription": "Counts cycles where a code fetch is stalled due to L1 instruction cache tag miss.", + "PublicDescription": "Counts cycles where a code fetch is stalled due to L1 instruction cache tag miss. Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0x4", "Unit": "cpu_core" @@ -331,7 +335,7 @@ "CounterMask": "1", "EventCode": "0x79", "EventName": "IDQ.DSB_CYCLES_ANY", - "PublicDescription": "Counts the number of cycles uops were delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path.", + "PublicDescription": "Counts the number of cycles uops were delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path. Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x8", "Unit": "cpu_core" @@ -342,7 +346,7 @@ "CounterMask": "6", "EventCode": "0x79", "EventName": "IDQ.DSB_CYCLES_OK", - "PublicDescription": "Counts the number of cycles where optimal number of uops was delivered to the Instruction Decode Queue (IDQ) from the DSB (Decode Stream Buffer) path. Count includes uops that may 'bypass' the IDQ.", + "PublicDescription": "Counts the number of cycles where optimal number of uops was delivered to the Instruction Decode Queue (IDQ) from the DSB (Decode Stream Buffer) path. Count includes uops that may 'bypass' the IDQ. Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x8", "Unit": "cpu_core" @@ -352,7 +356,7 @@ "Counter": "0,1,2,3", "EventCode": "0x79", "EventName": "IDQ.DSB_UOPS", - "PublicDescription": "Counts the number of uops delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path.", + "PublicDescription": "Counts the number of uops delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path. Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x8", "Unit": "cpu_core" @@ -363,7 +367,7 @@ "CounterMask": "1", "EventCode": "0x79", "EventName": "IDQ.MITE_CYCLES_ANY", - "PublicDescription": "Counts the number of cycles uops were delivered to the Instruction Decode Queue (IDQ) from the MITE (legacy decode pipeline) path. During these cycles uops are not being delivered from the Decode Stream Buffer (DSB).", + "PublicDescription": "Counts the number of cycles uops were delivered to the Instruction Decode Queue (IDQ) from the MITE (legacy decode pipeline) path. During these cycles uops are not being delivered from the Decode Stream Buffer (DSB). Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x4", "Unit": "cpu_core" @@ -374,7 +378,7 @@ "CounterMask": "6", "EventCode": "0x79", "EventName": "IDQ.MITE_CYCLES_OK", - "PublicDescription": "Counts the number of cycles where optimal number of uops was delivered to the Instruction Decode Queue (IDQ) from the MITE (legacy decode pipeline) path. During these cycles uops are not being delivered from the Decode Stream Buffer (DSB).", + "PublicDescription": "Counts the number of cycles where optimal number of uops was delivered to the Instruction Decode Queue (IDQ) from the MITE (legacy decode pipeline) path. During these cycles uops are not being delivered from the Decode Stream Buffer (DSB). Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x4", "Unit": "cpu_core" @@ -384,7 +388,7 @@ "Counter": "0,1,2,3", "EventCode": "0x79", "EventName": "IDQ.MITE_UOPS", - "PublicDescription": "Counts the number of uops delivered to Instruction Decode Queue (IDQ) from the MITE path. This also means that uops are not being delivered from the Decode Stream Buffer (DSB).", + "PublicDescription": "Counts the number of uops delivered to Instruction Decode Queue (IDQ) from the MITE path. This also means that uops are not being delivered from the Decode Stream Buffer (DSB). Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x4", "Unit": "cpu_core" @@ -395,7 +399,7 @@ "CounterMask": "1", "EventCode": "0x79", "EventName": "IDQ.MS_CYCLES_ANY", - "PublicDescription": "Counts cycles during which uops are being delivered to Instruction Decode Queue (IDQ) while the Microcode Sequencer (MS) is busy. Uops maybe initiated by Decode Stream Buffer (DSB) or MITE.", + "PublicDescription": "Counts cycles during which uops are being delivered to Instruction Decode Queue (IDQ) while the Microcode Sequencer (MS) is busy. Uops maybe initiated by Decode Stream Buffer (DSB) or MITE. Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x20", "Unit": "cpu_core" @@ -407,7 +411,7 @@ "EdgeDetect": "1", "EventCode": "0x79", "EventName": "IDQ.MS_SWITCHES", - "PublicDescription": "Number of switches from DSB (Decode Stream Buffer) or MITE (legacy decode pipeline) to the Microcode Sequencer.", + "PublicDescription": "Number of switches from DSB (Decode Stream Buffer) or MITE (legacy decode pipeline) to the Microcode Sequencer. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x20", "Unit": "cpu_core" @@ -417,7 +421,7 @@ "Counter": "0,1,2,3", "EventCode": "0x79", "EventName": "IDQ.MS_UOPS", - "PublicDescription": "Counts the total number of uops delivered by the Microcode Sequencer (MS).", + "PublicDescription": "Counts the total number of uops delivered by the Microcode Sequencer (MS). Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x20", "Unit": "cpu_core" @@ -427,7 +431,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0x9c", "EventName": "IDQ_BUBBLES.CORE", - "PublicDescription": "Counts the number of uops not delivered to by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle. [This event is alias to IDQ_UOPS_NOT_DELIVERED.CORE]", + "PublicDescription": "Counts the number of uops not delivered to by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle. [This event is alias to IDQ_UOPS_NOT_DELIVERED.CORE] Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x1", "Unit": "cpu_core" @@ -438,7 +442,7 @@ "CounterMask": "6", "EventCode": "0x9c", "EventName": "IDQ_BUBBLES.CYCLES_0_UOPS_DELIV.CORE", - "PublicDescription": "Counts the number of cycles when no uops were delivered by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle. [This event is alias to IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE]", + "PublicDescription": "Counts the number of cycles when no uops were delivered by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle. [This event is alias to IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE] Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x1", "Unit": "cpu_core" @@ -450,7 +454,7 @@ "EventCode": "0x9c", "EventName": "IDQ_BUBBLES.CYCLES_FE_WAS_OK", "Invert": "1", - "PublicDescription": "Counts the number of cycles when the optimal number of uops were delivered by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle. [This event is alias to IDQ_UOPS_NOT_DELIVERED.CYCLES_FE_WAS_OK]", + "PublicDescription": "Counts the number of cycles when the optimal number of uops were delivered by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle. [This event is alias to IDQ_UOPS_NOT_DELIVERED.CYCLES_FE_WAS_OK] Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x1", "Unit": "cpu_core" @@ -460,7 +464,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0x9c", "EventName": "IDQ_UOPS_NOT_DELIVERED.CORE", - "PublicDescription": "Counts the number of uops not delivered to by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle. [This event is alias to IDQ_BUBBLES.CORE]", + "PublicDescription": "Counts the number of uops not delivered to by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle. [This event is alias to IDQ_BUBBLES.CORE] Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x1", "Unit": "cpu_core" @@ -471,7 +475,7 @@ "CounterMask": "6", "EventCode": "0x9c", "EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE", - "PublicDescription": "Counts the number of cycles when no uops were delivered by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle. [This event is alias to IDQ_BUBBLES.CYCLES_0_UOPS_DELIV.CORE]", + "PublicDescription": "Counts the number of cycles when no uops were delivered by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle. [This event is alias to IDQ_BUBBLES.CYCLES_0_UOPS_DELIV.CORE] Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x1", "Unit": "cpu_core" @@ -483,7 +487,7 @@ "EventCode": "0x9c", "EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_FE_WAS_OK", "Invert": "1", - "PublicDescription": "Counts the number of cycles when the optimal number of uops were delivered by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle. [This event is alias to IDQ_BUBBLES.CYCLES_FE_WAS_OK]", + "PublicDescription": "Counts the number of cycles when the optimal number of uops were delivered by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle. [This event is alias to IDQ_BUBBLES.CYCLES_FE_WAS_OK] Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x1", "Unit": "cpu_core" diff --git a/tools/perf/pmu-events/arch/x86/alderlake/memory.json b/tools/perf/pmu-events/arch/x86/alderlake/memory.json index fa15f5797bed..07f5786bdbc0 100644 --- a/tools/perf/pmu-events/arch/x86/alderlake/memory.json +++ b/tools/perf/pmu-events/arch/x86/alderlake/memory.json @@ -5,6 +5,7 @@ "CounterMask": "6", "EventCode": "0xa3", "EventName": "CYCLE_ACTIVITY.STALLS_L3_MISS", + "PublicDescription": "Execution stalls while L3 cache miss demand load is outstanding. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x6", "Unit": "cpu_core" @@ -78,7 +79,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc3", "EventName": "MACHINE_CLEARS.MEMORY_ORDERING", - "PublicDescription": "Counts the number of Machine Clears detected dye to memory ordering. Memory Ordering Machine Clears may apply when a memory read may not conform to the memory ordering rules of the x86 architecture", + "PublicDescription": "Counts the number of Machine Clears detected dye to memory ordering. Memory Ordering Machine Clears may apply when a memory read may not conform to the memory ordering rules of the x86 architecture Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x2", "Unit": "cpu_core" @@ -89,6 +90,7 @@ "CounterMask": "2", "EventCode": "0x47", "EventName": "MEMORY_ACTIVITY.CYCLES_L1D_MISS", + "PublicDescription": "Cycles while L1 cache miss demand load is outstanding. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x2", "Unit": "cpu_core" @@ -99,6 +101,7 @@ "CounterMask": "3", "EventCode": "0x47", "EventName": "MEMORY_ACTIVITY.STALLS_L1D_MISS", + "PublicDescription": "Execution stalls while L1 cache miss demand load is outstanding. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x3", "Unit": "cpu_core" @@ -109,7 +112,7 @@ "CounterMask": "5", "EventCode": "0x47", "EventName": "MEMORY_ACTIVITY.STALLS_L2_MISS", - "PublicDescription": "Execution stalls while L2 cache miss demand cacheable load request is outstanding (will not count for uncacheable demand requests e.g. bus lock).", + "PublicDescription": "Execution stalls while L2 cache miss demand cacheable load request is outstanding (will not count for uncacheable demand requests e.g. bus lock). Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x5", "Unit": "cpu_core" @@ -120,7 +123,7 @@ "CounterMask": "9", "EventCode": "0x47", "EventName": "MEMORY_ACTIVITY.STALLS_L3_MISS", - "PublicDescription": "Execution stalls while L3 cache miss demand cacheable load request is outstanding (will not count for uncacheable demand requests e.g. bus lock).", + "PublicDescription": "Execution stalls while L3 cache miss demand cacheable load request is outstanding (will not count for uncacheable demand requests e.g. bus lock). Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x9", "Unit": "cpu_core" @@ -248,29 +251,67 @@ "Data_LA": "1", "EventCode": "0xcd", "EventName": "MEM_TRANS_RETIRED.STORE_SAMPLE", - "PublicDescription": "Counts Retired memory accesses with at least 1 store operation. This PEBS event is the precisely-distributed (PDist) trigger covering all stores uops for sampling by the PEBS Store Latency Facility. The facility is described in Intel SDM Volume 3 section 19.9.8", + "PublicDescription": "Counts Retired memory accesses with at least 1 store operation. This PEBS event is the precisely-distributed (PDist) trigger covering all stores uops for sampling by the PEBS Store Latency Facility. The facility is described in Intel SDM Volume 3 section 19.9.8 Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x2", "Unit": "cpu_core" }, { + "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were supplied by DRAM.", + "Counter": "0,1,2,3,4,5", + "EventCode": "0xB7", + "EventName": "OCR.DEMAND_CODE_RD.DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x784000004", + "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were supplied by DRAM. Available PDIST counters: 0", + "SampleAfterValue": "100003", + "UMask": "0x1", + "Unit": "cpu_atom" + }, + { "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were not supplied by the L3 cache.", "Counter": "0,1,2,3,4,5", "EventCode": "0xB7", "EventName": "OCR.DEMAND_CODE_RD.L3_MISS", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x3F84400004", + "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were not supplied by the L3 cache. Available PDIST counters: 0", + "SampleAfterValue": "100003", + "UMask": "0x1", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts demand data reads that were supplied by DRAM.", + "Counter": "0,1,2,3,4,5", + "EventCode": "0xB7", + "EventName": "OCR.DEMAND_DATA_RD.DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x784000001", + "PublicDescription": "Counts demand data reads that were supplied by DRAM. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1", "Unit": "cpu_atom" }, { + "BriefDescription": "Counts demand data reads that were supplied by DRAM.", + "Counter": "0,1,2,3", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.DEMAND_DATA_RD.DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x184000001", + "PublicDescription": "Counts demand data reads that were supplied by DRAM. Available PDIST counters: 0", + "SampleAfterValue": "100003", + "UMask": "0x1", + "Unit": "cpu_core" + }, + { "BriefDescription": "Counts demand data reads that were not supplied by the L3 cache.", "Counter": "0,1,2,3,4,5", "EventCode": "0xB7", "EventName": "OCR.DEMAND_DATA_RD.L3_MISS", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x3F84400001", + "PublicDescription": "Counts demand data reads that were not supplied by the L3 cache. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1", "Unit": "cpu_atom" @@ -282,6 +323,7 @@ "EventName": "OCR.DEMAND_DATA_RD.L3_MISS", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x3FBFC00001", + "PublicDescription": "Counts demand data reads that were not supplied by the L3 cache. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1", "Unit": "cpu_core" @@ -293,6 +335,19 @@ "EventName": "OCR.DEMAND_DATA_RD.L3_MISS_LOCAL", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x3F84400001", + "PublicDescription": "Counts demand data reads that were not supplied by the L3 cache. [L3_MISS_LOCAL is alias to L3_MISS] Available PDIST counters: 0", + "SampleAfterValue": "100003", + "UMask": "0x1", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that were supplied by DRAM.", + "Counter": "0,1,2,3,4,5", + "EventCode": "0xB7", + "EventName": "OCR.DEMAND_RFO.DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x784000002", + "PublicDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that were supplied by DRAM. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1", "Unit": "cpu_atom" @@ -304,6 +359,7 @@ "EventName": "OCR.DEMAND_RFO.L3_MISS", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x3F84400002", + "PublicDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that were not supplied by the L3 cache. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1", "Unit": "cpu_atom" @@ -315,6 +371,7 @@ "EventName": "OCR.DEMAND_RFO.L3_MISS", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x3FBFC00002", + "PublicDescription": "Counts demand read for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that were not supplied by the L3 cache. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1", "Unit": "cpu_core" @@ -326,6 +383,19 @@ "EventName": "OCR.DEMAND_RFO.L3_MISS_LOCAL", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x3F84400002", + "PublicDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that were not supplied by the L3 cache. [L3_MISS_LOCAL is alias to L3_MISS] Available PDIST counters: 0", + "SampleAfterValue": "100003", + "UMask": "0x1", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts L1 data cache software prefetches which include T0/T1/T2 and NTA (except PREFETCHW) that were supplied by DRAM.", + "Counter": "0,1,2,3,4,5", + "EventCode": "0xB7", + "EventName": "OCR.SWPF_RD.DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x784004000", + "PublicDescription": "Counts L1 data cache software prefetches which include T0/T1/T2 and NTA (except PREFETCHW) that were supplied by DRAM. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1", "Unit": "cpu_atom" @@ -337,6 +407,7 @@ "EventName": "OCR.SWPF_RD.L3_MISS", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x3F84404000", + "PublicDescription": "Counts L1 data cache software prefetches which include T0/T1/T2 and NTA (except PREFETCHW) that were not supplied by the L3 cache. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1", "Unit": "cpu_atom" @@ -346,6 +417,7 @@ "Counter": "0,1,2,3", "EventCode": "0x21", "EventName": "OFFCORE_REQUESTS.L3_MISS_DEMAND_DATA_RD", + "PublicDescription": "Counts demand data read requests that miss the L3 cache. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x10", "Unit": "cpu_core" @@ -355,7 +427,7 @@ "Counter": "0,1,2,3", "EventCode": "0x20", "EventName": "OFFCORE_REQUESTS_OUTSTANDING.L3_MISS_DEMAND_DATA_RD", - "PublicDescription": "For every cycle, increments by the number of demand data read requests pending that are known to have missed the L3 cache. Note that this does not capture all elapsed cycles while requests are outstanding - only cycles from when the requests were known by the requesting core to have missed the L3 cache.", + "PublicDescription": "For every cycle, increments by the number of demand data read requests pending that are known to have missed the L3 cache. Note that this does not capture all elapsed cycles while requests are outstanding - only cycles from when the requests were known by the requesting core to have missed the L3 cache. Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x10", "Unit": "cpu_core" diff --git a/tools/perf/pmu-events/arch/x86/alderlake/other.json b/tools/perf/pmu-events/arch/x86/alderlake/other.json index a8b23e92408c..e4e75b088ccc 100644 --- a/tools/perf/pmu-events/arch/x86/alderlake/other.json +++ b/tools/perf/pmu-events/arch/x86/alderlake/other.json @@ -4,7 +4,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc1", "EventName": "ASSISTS.HARDWARE", - "PublicDescription": "Count all other hardware assists or traps that are not necessarily architecturally exposed (through a software handler) beyond FP; SSE-AVX mix and A/D assists who are counted by dedicated sub-events. This includes, but not limited to, assists at EXE or MEM uop writeback like AVX* load/store/gather/scatter (non-FP GSSE-assist ) , assists generated by ROB like PEBS and RTIT, Uncore trap, RAR (Remote Action Request) and CET (Control flow Enforcement Technology) assists. the event also counts for Machine Ordering count.", + "PublicDescription": "Count all other hardware assists or traps that are not necessarily architecturally exposed (through a software handler) beyond FP; SSE-AVX mix and A/D assists who are counted by dedicated sub-events. This includes, but not limited to, assists at EXE or MEM uop writeback like AVX* load/store/gather/scatter (non-FP GSSE-assist ) , assists generated by ROB like PEBS and RTIT, Uncore trap, RAR (Remote Action Request) and CET (Control flow Enforcement Technology) assists. the event also counts for Machine Ordering count. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x4", "Unit": "cpu_core" @@ -14,6 +14,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc1", "EventName": "ASSISTS.PAGE_FAULT", + "PublicDescription": "ASSISTS.PAGE_FAULT Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x8", "Unit": "cpu_core" @@ -23,6 +24,7 @@ "Counter": "0,1,2,3", "EventCode": "0x28", "EventName": "CORE_POWER.LICENSE_1", + "PublicDescription": "CORE_POWER.LICENSE_1 Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0x2", "Unit": "cpu_core" @@ -32,6 +34,7 @@ "Counter": "0,1,2,3", "EventCode": "0x28", "EventName": "CORE_POWER.LICENSE_2", + "PublicDescription": "CORE_POWER.LICENSE_2 Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0x4", "Unit": "cpu_core" @@ -41,6 +44,7 @@ "Counter": "0,1,2,3", "EventCode": "0x28", "EventName": "CORE_POWER.LICENSE_3", + "PublicDescription": "CORE_POWER.LICENSE_3 Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0x8", "Unit": "cpu_core" @@ -51,127 +55,19 @@ "Deprecated": "1", "EventCode": "0xe4", "EventName": "LBR_INSERTS.ANY", + "PublicDescription": "This event is deprecated. [This event is alias to MISC_RETIRED.LBR_INSERTS] Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x1", "Unit": "cpu_atom" }, { - "BriefDescription": "Counts modified writebacks from L1 cache and L2 cache that have any type of response.", - "Counter": "0,1,2,3,4,5", - "EventCode": "0xB7", - "EventName": "OCR.COREWB_M.ANY_RESPONSE", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x10008", - "SampleAfterValue": "100003", - "UMask": "0x1", - "Unit": "cpu_atom" - }, - { - "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that have any type of response.", - "Counter": "0,1,2,3,4,5", - "EventCode": "0xB7", - "EventName": "OCR.DEMAND_CODE_RD.ANY_RESPONSE", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x10004", - "SampleAfterValue": "100003", - "UMask": "0x1", - "Unit": "cpu_atom" - }, - { - "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were supplied by DRAM.", - "Counter": "0,1,2,3,4,5", - "EventCode": "0xB7", - "EventName": "OCR.DEMAND_CODE_RD.DRAM", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x784000004", - "SampleAfterValue": "100003", - "UMask": "0x1", - "Unit": "cpu_atom" - }, - { - "BriefDescription": "Counts demand data reads that have any type of response.", - "Counter": "0,1,2,3,4,5", - "EventCode": "0xB7", - "EventName": "OCR.DEMAND_DATA_RD.ANY_RESPONSE", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x10001", - "SampleAfterValue": "100003", - "UMask": "0x1", - "Unit": "cpu_atom" - }, - { - "BriefDescription": "Counts demand data reads that have any type of response.", - "Counter": "0,1,2,3", - "EventCode": "0x2A,0x2B", - "EventName": "OCR.DEMAND_DATA_RD.ANY_RESPONSE", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x10001", - "SampleAfterValue": "100003", - "UMask": "0x1", - "Unit": "cpu_core" - }, - { - "BriefDescription": "Counts demand data reads that were supplied by DRAM.", - "Counter": "0,1,2,3,4,5", - "EventCode": "0xB7", - "EventName": "OCR.DEMAND_DATA_RD.DRAM", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x784000001", - "SampleAfterValue": "100003", - "UMask": "0x1", - "Unit": "cpu_atom" - }, - { - "BriefDescription": "Counts demand data reads that were supplied by DRAM.", - "Counter": "0,1,2,3", - "EventCode": "0x2A,0x2B", - "EventName": "OCR.DEMAND_DATA_RD.DRAM", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x184000001", - "SampleAfterValue": "100003", - "UMask": "0x1", - "Unit": "cpu_core" - }, - { - "BriefDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that have any type of response.", - "Counter": "0,1,2,3,4,5", - "EventCode": "0xB7", - "EventName": "OCR.DEMAND_RFO.ANY_RESPONSE", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x10002", - "SampleAfterValue": "100003", - "UMask": "0x1", - "Unit": "cpu_atom" - }, - { - "BriefDescription": "Counts demand read for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that have any type of response.", - "Counter": "0,1,2,3", - "EventCode": "0x2A,0x2B", - "EventName": "OCR.DEMAND_RFO.ANY_RESPONSE", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x10002", - "SampleAfterValue": "100003", - "UMask": "0x1", - "Unit": "cpu_core" - }, - { - "BriefDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that were supplied by DRAM.", - "Counter": "0,1,2,3,4,5", - "EventCode": "0xB7", - "EventName": "OCR.DEMAND_RFO.DRAM", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x784000002", - "SampleAfterValue": "100003", - "UMask": "0x1", - "Unit": "cpu_atom" - }, - { "BriefDescription": "Counts streaming stores which modify a full 64 byte cacheline that have any type of response.", "Counter": "0,1,2,3,4,5", "EventCode": "0xB7", "EventName": "OCR.FULL_STREAMING_WR.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x800000010000", + "PublicDescription": "Counts streaming stores which modify a full 64 byte cacheline that have any type of response. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1", "Unit": "cpu_atom" @@ -183,6 +79,7 @@ "EventName": "OCR.PARTIAL_STREAMING_WR.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x400000010000", + "PublicDescription": "Counts streaming stores which modify only part of a 64 byte cacheline that have any type of response. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1", "Unit": "cpu_atom" @@ -194,6 +91,7 @@ "EventName": "OCR.STREAMING_WR.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x10800", + "PublicDescription": "Counts streaming stores that have any type of response. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1", "Unit": "cpu_atom" @@ -205,103 +103,18 @@ "EventName": "OCR.STREAMING_WR.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x10800", + "PublicDescription": "Counts streaming stores that have any type of response. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1", "Unit": "cpu_core" }, { - "BriefDescription": "Counts L1 data cache software prefetches which include T0/T1/T2 and NTA (except PREFETCHW) that have any type of response.", - "Counter": "0,1,2,3,4,5", - "EventCode": "0xB7", - "EventName": "OCR.SWPF_RD.ANY_RESPONSE", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x14000", - "SampleAfterValue": "100003", - "UMask": "0x1", - "Unit": "cpu_atom" - }, - { - "BriefDescription": "Counts L1 data cache software prefetches which include T0/T1/T2 and NTA (except PREFETCHW) that were supplied by DRAM.", - "Counter": "0,1,2,3,4,5", - "EventCode": "0xB7", - "EventName": "OCR.SWPF_RD.DRAM", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x784004000", - "SampleAfterValue": "100003", - "UMask": "0x1", - "Unit": "cpu_atom" - }, - { - "BriefDescription": "Cycles when Reservation Station (RS) is empty for the thread.", - "Counter": "0,1,2,3,4,5,6,7", - "EventCode": "0xa5", - "EventName": "RS.EMPTY", - "PublicDescription": "Counts cycles during which the reservation station (RS) is empty for this logical processor. This is usually caused when the front-end pipeline runs into starvation periods (e.g. branch mispredictions or i-cache misses)", - "SampleAfterValue": "1000003", - "UMask": "0x7", - "Unit": "cpu_core" - }, - { - "BriefDescription": "Counts end of periods where the Reservation Station (RS) was empty.", - "Counter": "0,1,2,3,4,5,6,7", - "CounterMask": "1", - "EdgeDetect": "1", - "EventCode": "0xa5", - "EventName": "RS.EMPTY_COUNT", - "Invert": "1", - "PublicDescription": "Counts end of periods where the Reservation Station (RS) was empty. Could be useful to closely sample on front-end latency issues (see the FRONTEND_RETIRED event of designated precise events)", - "SampleAfterValue": "100003", - "UMask": "0x7", - "Unit": "cpu_core" - }, - { - "BriefDescription": "Cycles when Reservation Station (RS) is empty due to a resource in the back-end", - "Counter": "0,1,2,3,4,5,6,7", - "EventCode": "0xa5", - "EventName": "RS.EMPTY_RESOURCE", - "SampleAfterValue": "1000003", - "UMask": "0x1", - "Unit": "cpu_core" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event RS.EMPTY_COUNT", - "Counter": "0,1,2,3,4,5,6,7", - "CounterMask": "1", - "Deprecated": "1", - "EdgeDetect": "1", - "EventCode": "0xa5", - "EventName": "RS_EMPTY.COUNT", - "Invert": "1", - "SampleAfterValue": "100003", - "UMask": "0x7", - "Unit": "cpu_core" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event RS.EMPTY", - "Counter": "0,1,2,3,4,5,6,7", - "Deprecated": "1", - "EventCode": "0xa5", - "EventName": "RS_EMPTY.CYCLES", - "SampleAfterValue": "1000003", - "UMask": "0x7", - "Unit": "cpu_core" - }, - { - "BriefDescription": "Counts the number of issue slots in a UMWAIT or TPAUSE instruction where no uop issues due to the instruction putting the CPU into the C0.1 activity state. For Tremont, UMWAIT and TPAUSE will only put the CPU into C0.1 activity state (not C0.2 activity state)", - "Counter": "0,1,2,3,4,5", - "EventCode": "0x75", - "EventName": "SERIALIZATION.C01_MS_SCB", - "SampleAfterValue": "200003", - "UMask": "0x4", - "Unit": "cpu_atom" - }, - { "BriefDescription": "Cycles the uncore cannot take further requests", "Counter": "0,1,2,3", "CounterMask": "1", "EventCode": "0x2d", "EventName": "XQ.FULL_CYCLES", - "PublicDescription": "number of cycles when the thread is active and the uncore cannot take any further requests (for example prefetches, loads or stores initiated by the Core that miss the L2 cache).", + "PublicDescription": "number of cycles when the thread is active and the uncore cannot take any further requests (for example prefetches, loads or stores initiated by the Core that miss the L2 cache). Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x1", "Unit": "cpu_core" diff --git a/tools/perf/pmu-events/arch/x86/alderlake/pipeline.json b/tools/perf/pmu-events/arch/x86/alderlake/pipeline.json index f5bf0816f190..7e0e33792c45 100644 --- a/tools/perf/pmu-events/arch/x86/alderlake/pipeline.json +++ b/tools/perf/pmu-events/arch/x86/alderlake/pipeline.json @@ -6,6 +6,7 @@ "Deprecated": "1", "EventCode": "0xb0", "EventName": "ARITH.DIVIDER_ACTIVE", + "PublicDescription": "This event is deprecated. Refer to new event ARITH.DIV_ACTIVE Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x9", "Unit": "cpu_core" @@ -26,7 +27,7 @@ "CounterMask": "1", "EventCode": "0xb0", "EventName": "ARITH.DIV_ACTIVE", - "PublicDescription": "Counts cycles when divide unit is busy executing divide or square root operations. Accounts for integer and floating-point operations.", + "PublicDescription": "Counts cycles when divide unit is busy executing divide or square root operations. Accounts for integer and floating-point operations. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x9", "Unit": "cpu_core" @@ -56,6 +57,7 @@ "Deprecated": "1", "EventCode": "0xb0", "EventName": "ARITH.FP_DIVIDER_ACTIVE", + "PublicDescription": "This event is deprecated. Refer to new event ARITH.FPDIV_ACTIVE Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x1", "Unit": "cpu_core" @@ -76,6 +78,7 @@ "CounterMask": "1", "EventCode": "0xb0", "EventName": "ARITH.IDIV_ACTIVE", + "PublicDescription": "This event counts the cycles the integer divider is busy. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x8", "Unit": "cpu_core" @@ -105,6 +108,7 @@ "Deprecated": "1", "EventCode": "0xb0", "EventName": "ARITH.INT_DIVIDER_ACTIVE", + "PublicDescription": "This event is deprecated. Refer to new event ARITH.IDIV_ACTIVE Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x8", "Unit": "cpu_core" @@ -114,7 +118,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc1", "EventName": "ASSISTS.ANY", - "PublicDescription": "Counts the number of occurrences where a microcode assist is invoked by hardware. Examples include AD (page Access Dirty), FP and AVX related assists.", + "PublicDescription": "Counts the number of occurrences where a microcode assist is invoked by hardware. Examples include AD (page Access Dirty), FP and AVX related assists. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1b", "Unit": "cpu_core" @@ -124,7 +128,7 @@ "Counter": "0,1,2,3,4,5", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.ALL_BRANCHES", - "PublicDescription": "Counts the total number of instructions in which the instruction pointer (IP) of the processor is resteered due to a branch instruction and the branch instruction successfully retires. All branch type instructions are accounted for.", + "PublicDescription": "Counts the total number of instructions in which the instruction pointer (IP) of the processor is resteered due to a branch instruction and the branch instruction successfully retires. All branch type instructions are accounted for. Available PDIST counters: 0", "SampleAfterValue": "200003", "Unit": "cpu_atom" }, @@ -133,7 +137,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.ALL_BRANCHES", - "PublicDescription": "Counts all branch instructions retired.", + "PublicDescription": "Counts all branch instructions retired. Available PDIST counters: 0", "SampleAfterValue": "400009", "Unit": "cpu_core" }, @@ -143,6 +147,7 @@ "Deprecated": "1", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.CALL", + "PublicDescription": "This event is deprecated. Refer to new event BR_INST_RETIRED.NEAR_CALL Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0xf9", "Unit": "cpu_atom" @@ -152,6 +157,7 @@ "Counter": "0,1,2,3,4,5", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.COND", + "PublicDescription": "Counts the number of retired JCC (Jump on Conditional Code) branch instructions retired, includes both taken and not taken branches. Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0x7e", "Unit": "cpu_atom" @@ -161,7 +167,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.COND", - "PublicDescription": "Counts conditional branch instructions retired.", + "PublicDescription": "Counts conditional branch instructions retired. Available PDIST counters: 0", "SampleAfterValue": "400009", "UMask": "0x11", "Unit": "cpu_core" @@ -171,7 +177,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.COND_NTAKEN", - "PublicDescription": "Counts not taken branch instructions retired.", + "PublicDescription": "Counts not taken branch instructions retired. Available PDIST counters: 0", "SampleAfterValue": "400009", "UMask": "0x10", "Unit": "cpu_core" @@ -181,6 +187,7 @@ "Counter": "0,1,2,3,4,5", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.COND_TAKEN", + "PublicDescription": "Counts the number of taken JCC (Jump on Conditional Code) branch instructions retired. Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0xfe", "Unit": "cpu_atom" @@ -190,7 +197,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.COND_TAKEN", - "PublicDescription": "Counts taken conditional branch instructions retired.", + "PublicDescription": "Counts taken conditional branch instructions retired. Available PDIST counters: 0", "SampleAfterValue": "400009", "UMask": "0x1", "Unit": "cpu_core" @@ -200,6 +207,7 @@ "Counter": "0,1,2,3,4,5", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.FAR_BRANCH", + "PublicDescription": "Counts the number of far branch instructions retired, includes far jump, far call and return, and interrupt call and return. Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0xbf", "Unit": "cpu_atom" @@ -209,7 +217,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.FAR_BRANCH", - "PublicDescription": "Counts far branch instructions retired.", + "PublicDescription": "Counts far branch instructions retired. Available PDIST counters: 0", "SampleAfterValue": "100007", "UMask": "0x40", "Unit": "cpu_core" @@ -219,6 +227,7 @@ "Counter": "0,1,2,3,4,5", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.INDIRECT", + "PublicDescription": "Counts the number of near indirect JMP and near indirect CALL branch instructions retired. Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0xeb", "Unit": "cpu_atom" @@ -228,7 +237,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.INDIRECT", - "PublicDescription": "Counts near indirect branch instructions retired excluding returns. TSX abort is an indirect branch.", + "PublicDescription": "Counts near indirect branch instructions retired excluding returns. TSX abort is an indirect branch. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x80", "Unit": "cpu_core" @@ -238,6 +247,7 @@ "Counter": "0,1,2,3,4,5", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.INDIRECT_CALL", + "PublicDescription": "Counts the number of near indirect CALL branch instructions retired. Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0xfb", "Unit": "cpu_atom" @@ -248,6 +258,7 @@ "Deprecated": "1", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.IND_CALL", + "PublicDescription": "This event is deprecated. Refer to new event BR_INST_RETIRED.INDIRECT_CALL Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0xfb", "Unit": "cpu_atom" @@ -258,6 +269,7 @@ "Deprecated": "1", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.JCC", + "PublicDescription": "This event is deprecated. Refer to new event BR_INST_RETIRED.COND Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0x7e", "Unit": "cpu_atom" @@ -267,6 +279,7 @@ "Counter": "0,1,2,3,4,5", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.NEAR_CALL", + "PublicDescription": "Counts the number of near CALL branch instructions retired. Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0xf9", "Unit": "cpu_atom" @@ -276,7 +289,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.NEAR_CALL", - "PublicDescription": "Counts both direct and indirect near call instructions retired.", + "PublicDescription": "Counts both direct and indirect near call instructions retired. Available PDIST counters: 0", "SampleAfterValue": "100007", "UMask": "0x2", "Unit": "cpu_core" @@ -286,6 +299,7 @@ "Counter": "0,1,2,3,4,5", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.NEAR_RETURN", + "PublicDescription": "Counts the number of near RET branch instructions retired. Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0xf7", "Unit": "cpu_atom" @@ -295,7 +309,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.NEAR_RETURN", - "PublicDescription": "Counts return instructions retired.", + "PublicDescription": "Counts return instructions retired. Available PDIST counters: 0", "SampleAfterValue": "100007", "UMask": "0x8", "Unit": "cpu_core" @@ -305,6 +319,7 @@ "Counter": "0,1,2,3,4,5", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.NEAR_TAKEN", + "PublicDescription": "Counts the number of near taken branch instructions retired. Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0xc0", "Unit": "cpu_atom" @@ -314,7 +329,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.NEAR_TAKEN", - "PublicDescription": "Counts taken branch instructions retired.", + "PublicDescription": "Counts taken branch instructions retired. Available PDIST counters: 0", "SampleAfterValue": "400009", "UMask": "0x20", "Unit": "cpu_core" @@ -325,6 +340,7 @@ "Deprecated": "1", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.NON_RETURN_IND", + "PublicDescription": "This event is deprecated. Refer to new event BR_INST_RETIRED.INDIRECT Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0xeb", "Unit": "cpu_atom" @@ -334,6 +350,7 @@ "Counter": "0,1,2,3,4,5", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.REL_CALL", + "PublicDescription": "Counts the number of near relative CALL branch instructions retired. Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0xfd", "Unit": "cpu_atom" @@ -344,6 +361,7 @@ "Deprecated": "1", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.RETURN", + "PublicDescription": "This event is deprecated. Refer to new event BR_INST_RETIRED.NEAR_RETURN Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0xf7", "Unit": "cpu_atom" @@ -354,6 +372,7 @@ "Deprecated": "1", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.TAKEN_JCC", + "PublicDescription": "This event is deprecated. Refer to new event BR_INST_RETIRED.COND_TAKEN Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0xfe", "Unit": "cpu_atom" @@ -363,7 +382,7 @@ "Counter": "0,1,2,3,4,5", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.ALL_BRANCHES", - "PublicDescription": "Counts the total number of mispredicted branch instructions retired. All branch type instructions are accounted for. Prediction of the branch target address enables the processor to begin executing instructions before the non-speculative execution path is known. The branch prediction unit (BPU) predicts the target address based on the instruction pointer (IP) of the branch and on the execution path through which execution reached this IP. A branch misprediction occurs when the prediction is wrong, and results in discarding all instructions executed in the speculative path and re-fetching from the correct path.", + "PublicDescription": "Counts the total number of mispredicted branch instructions retired. All branch type instructions are accounted for. Prediction of the branch target address enables the processor to begin executing instructions before the non-speculative execution path is known. The branch prediction unit (BPU) predicts the target address based on the instruction pointer (IP) of the branch and on the execution path through which execution reached this IP. A branch misprediction occurs when the prediction is wrong, and results in discarding all instructions executed in the speculative path and re-fetching from the correct path. Available PDIST counters: 0", "SampleAfterValue": "200003", "Unit": "cpu_atom" }, @@ -372,7 +391,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.ALL_BRANCHES", - "PublicDescription": "Counts all the retired branch instructions that were mispredicted by the processor. A branch misprediction occurs when the processor incorrectly predicts the destination of the branch. When the misprediction is discovered at execution, all the instructions executed in the wrong (speculative) path must be discarded, and the processor must start fetching from the correct path.", + "PublicDescription": "Counts all the retired branch instructions that were mispredicted by the processor. A branch misprediction occurs when the processor incorrectly predicts the destination of the branch. When the misprediction is discovered at execution, all the instructions executed in the wrong (speculative) path must be discarded, and the processor must start fetching from the correct path. Available PDIST counters: 0", "SampleAfterValue": "400009", "Unit": "cpu_core" }, @@ -381,6 +400,7 @@ "Counter": "0,1,2,3,4,5", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.COND", + "PublicDescription": "Counts the number of mispredicted JCC (Jump on Conditional Code) branch instructions retired. Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0x7e", "Unit": "cpu_atom" @@ -390,7 +410,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.COND", - "PublicDescription": "Counts mispredicted conditional branch instructions retired.", + "PublicDescription": "Counts mispredicted conditional branch instructions retired. Available PDIST counters: 0", "SampleAfterValue": "400009", "UMask": "0x11", "Unit": "cpu_core" @@ -400,7 +420,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.COND_NTAKEN", - "PublicDescription": "Counts the number of conditional branch instructions retired that were mispredicted and the branch direction was not taken.", + "PublicDescription": "Counts the number of conditional branch instructions retired that were mispredicted and the branch direction was not taken. Available PDIST counters: 0", "SampleAfterValue": "400009", "UMask": "0x10", "Unit": "cpu_core" @@ -410,6 +430,7 @@ "Counter": "0,1,2,3,4,5", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.COND_TAKEN", + "PublicDescription": "Counts the number of mispredicted taken JCC (Jump on Conditional Code) branch instructions retired. Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0xfe", "Unit": "cpu_atom" @@ -419,7 +440,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.COND_TAKEN", - "PublicDescription": "Counts taken conditional mispredicted branch instructions retired.", + "PublicDescription": "Counts taken conditional mispredicted branch instructions retired. Available PDIST counters: 0", "SampleAfterValue": "400009", "UMask": "0x1", "Unit": "cpu_core" @@ -429,6 +450,7 @@ "Counter": "0,1,2,3,4,5", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.INDIRECT", + "PublicDescription": "Counts the number of mispredicted near indirect JMP and near indirect CALL branch instructions retired. Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0xeb", "Unit": "cpu_atom" @@ -438,7 +460,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.INDIRECT", - "PublicDescription": "Counts miss-predicted near indirect branch instructions retired excluding returns. TSX abort is an indirect branch.", + "PublicDescription": "Counts miss-predicted near indirect branch instructions retired excluding returns. TSX abort is an indirect branch. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x80", "Unit": "cpu_core" @@ -448,6 +470,7 @@ "Counter": "0,1,2,3,4,5", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.INDIRECT_CALL", + "PublicDescription": "Counts the number of mispredicted near indirect CALL branch instructions retired. Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0xfb", "Unit": "cpu_atom" @@ -457,7 +480,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.INDIRECT_CALL", - "PublicDescription": "Counts retired mispredicted indirect (near taken) CALL instructions, including both register and memory indirect.", + "PublicDescription": "Counts retired mispredicted indirect (near taken) CALL instructions, including both register and memory indirect. Available PDIST counters: 0", "SampleAfterValue": "400009", "UMask": "0x2", "Unit": "cpu_core" @@ -468,6 +491,7 @@ "Deprecated": "1", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.IND_CALL", + "PublicDescription": "This event is deprecated. Refer to new event BR_MISP_RETIRED.INDIRECT_CALL Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0xfb", "Unit": "cpu_atom" @@ -478,6 +502,7 @@ "Deprecated": "1", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.JCC", + "PublicDescription": "This event is deprecated. Refer to new event BR_MISP_RETIRED.COND Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0x7e", "Unit": "cpu_atom" @@ -487,6 +512,7 @@ "Counter": "0,1,2,3,4,5", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.NEAR_TAKEN", + "PublicDescription": "Counts the number of mispredicted near taken branch instructions retired. Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0x80", "Unit": "cpu_atom" @@ -496,7 +522,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.NEAR_TAKEN", - "PublicDescription": "Counts number of near branch instructions retired that were mispredicted and taken.", + "PublicDescription": "Counts number of near branch instructions retired that were mispredicted and taken. Available PDIST counters: 0", "SampleAfterValue": "400009", "UMask": "0x20", "Unit": "cpu_core" @@ -507,6 +533,7 @@ "Deprecated": "1", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.NON_RETURN_IND", + "PublicDescription": "This event is deprecated. Refer to new event BR_MISP_RETIRED.INDIRECT Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0xeb", "Unit": "cpu_atom" @@ -516,7 +543,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.RET", - "PublicDescription": "This is a non-precise version (that is, does not use PEBS) of the event that counts mispredicted return instructions retired.", + "PublicDescription": "This is a non-precise version (that is, does not use PEBS) of the event that counts mispredicted return instructions retired. Available PDIST counters: 0", "SampleAfterValue": "100007", "UMask": "0x8", "Unit": "cpu_core" @@ -526,6 +553,7 @@ "Counter": "0,1,2,3,4,5", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.RETURN", + "PublicDescription": "Counts the number of mispredicted near RET branch instructions retired. Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0xf7", "Unit": "cpu_atom" @@ -536,6 +564,7 @@ "Deprecated": "1", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.TAKEN_JCC", + "PublicDescription": "This event is deprecated. Refer to new event BR_MISP_RETIRED.COND_TAKEN Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0xfe", "Unit": "cpu_atom" @@ -545,7 +574,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xec", "EventName": "CPU_CLK_UNHALTED.C01", - "PublicDescription": "Counts core clocks when the thread is in the C0.1 light-weight slower wakeup time but more power saving optimized state. This state can be entered via the TPAUSE or UMWAIT instructions.", + "PublicDescription": "Counts core clocks when the thread is in the C0.1 light-weight slower wakeup time but more power saving optimized state. This state can be entered via the TPAUSE or UMWAIT instructions. Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x10", "Unit": "cpu_core" @@ -555,7 +584,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xec", "EventName": "CPU_CLK_UNHALTED.C02", - "PublicDescription": "Counts core clocks when the thread is in the C0.2 light-weight faster wakeup time but less power saving optimized state. This state can be entered via the TPAUSE or UMWAIT instructions.", + "PublicDescription": "Counts core clocks when the thread is in the C0.2 light-weight faster wakeup time but less power saving optimized state. This state can be entered via the TPAUSE or UMWAIT instructions. Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x20", "Unit": "cpu_core" @@ -565,7 +594,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xec", "EventName": "CPU_CLK_UNHALTED.C0_WAIT", - "PublicDescription": "Counts core clocks when the thread is in the C0.1 or C0.2 power saving optimized states (TPAUSE or UMWAIT instructions) or running the PAUSE instruction.", + "PublicDescription": "Counts core clocks when the thread is in the C0.1 or C0.2 power saving optimized states (TPAUSE or UMWAIT instructions) or running the PAUSE instruction. Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x70", "Unit": "cpu_core" @@ -593,7 +622,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xec", "EventName": "CPU_CLK_UNHALTED.DISTRIBUTED", - "PublicDescription": "This event distributes cycle counts between active hyperthreads, i.e., those in C0. A hyperthread becomes inactive when it executes the HLT or MWAIT instructions. If all other hyperthreads are inactive (or disabled or do not exist), all counts are attributed to this hyperthread. To obtain the full count when the Core is active, sum the counts from each hyperthread.", + "PublicDescription": "This event distributes cycle counts between active hyperthreads, i.e., those in C0. A hyperthread becomes inactive when it executes the HLT or MWAIT instructions. If all other hyperthreads are inactive (or disabled or do not exist), all counts are attributed to this hyperthread. To obtain the full count when the Core is active, sum the counts from each hyperthread. Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x2", "Unit": "cpu_core" @@ -603,7 +632,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0x3c", "EventName": "CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE", - "PublicDescription": "Counts Core crystal clock cycles when current thread is unhalted and the other thread is halted.", + "PublicDescription": "Counts Core crystal clock cycles when current thread is unhalted and the other thread is halted. Available PDIST counters: 0", "SampleAfterValue": "25003", "UMask": "0x2", "Unit": "cpu_core" @@ -613,6 +642,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xec", "EventName": "CPU_CLK_UNHALTED.PAUSE", + "PublicDescription": "CPU_CLK_UNHALTED.PAUSE Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x40", "Unit": "cpu_core" @@ -624,6 +654,7 @@ "EdgeDetect": "1", "EventCode": "0xec", "EventName": "CPU_CLK_UNHALTED.PAUSE_INST", + "PublicDescription": "CPU_CLK_UNHALTED.PAUSE_INST Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x40", "Unit": "cpu_core" @@ -643,7 +674,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0x3c", "EventName": "CPU_CLK_UNHALTED.REF_DISTRIBUTED", - "PublicDescription": "This event distributes Core crystal clock cycle counts between active hyperthreads, i.e., those in C0 sleep-state. A hyperthread becomes inactive when it executes the HLT or MWAIT instructions. If one thread is active in a core, all counts are attributed to this hyperthread. To obtain the full count when the Core is active, sum the counts from each hyperthread.", + "PublicDescription": "This event distributes Core crystal clock cycle counts between active hyperthreads, i.e., those in C0 sleep-state. A hyperthread becomes inactive when it executes the HLT or MWAIT instructions. If one thread is active in a core, all counts are attributed to this hyperthread. To obtain the full count when the Core is active, sum the counts from each hyperthread. Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x8", "Unit": "cpu_core" @@ -681,7 +712,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0x3c", "EventName": "CPU_CLK_UNHALTED.REF_TSC_P", - "PublicDescription": "Counts the number of reference cycles when the core is not in a halt state. The core enters the halt state when it is running the HLT instruction or the MWAIT instruction. This event is not affected by core frequency changes (for example, P states, TM2 transitions) but has the same incrementing frequency as the time stamp counter. This event can approximate elapsed time while the core was not in a halt state. It is counted on a dedicated fixed counter, leaving the four (eight when Hyperthreading is disabled) programmable counters available for other events. Note: On all current platforms this event stops counting during 'throttling (TM)' states duty off periods the processor is 'halted'. The counter update is done at a lower clock rate then the core clock the overflow status bit for this counter may appear 'sticky'. After the counter has overflowed and software clears the overflow status bit and resets the counter to less than MAX. The reset value to the counter is not clocked immediately so the overflow status bit will flip 'high (1)' and generate another PMI (if enabled) after which the reset value gets clocked into the counter. Therefore, software will get the interrupt, read the overflow status bit '1 for bit 34 while the counter value is less than MAX. Software should ignore this case.", + "PublicDescription": "Counts the number of reference cycles when the core is not in a halt state. The core enters the halt state when it is running the HLT instruction or the MWAIT instruction. This event is not affected by core frequency changes (for example, P states, TM2 transitions) but has the same incrementing frequency as the time stamp counter. This event can approximate elapsed time while the core was not in a halt state. It is counted on a dedicated fixed counter, leaving the four (eight when Hyperthreading is disabled) programmable counters available for other events. Note: On all current platforms this event stops counting during 'throttling (TM)' states duty off periods the processor is 'halted'. The counter update is done at a lower clock rate then the core clock the overflow status bit for this counter may appear 'sticky'. After the counter has overflowed and software clears the overflow status bit and resets the counter to less than MAX. The reset value to the counter is not clocked immediately so the overflow status bit will flip 'high (1)' and generate another PMI (if enabled) after which the reset value gets clocked into the counter. Therefore, software will get the interrupt, read the overflow status bit '1 for bit 34 while the counter value is less than MAX. Software should ignore this case. Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x1", "Unit": "cpu_core" @@ -718,7 +749,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0x3c", "EventName": "CPU_CLK_UNHALTED.THREAD_P", - "PublicDescription": "This is an architectural event that counts the number of thread cycles while the thread is not in a halt state. The thread enters the halt state when it is running the HLT instruction. The core frequency may change from time to time due to power or thermal throttling. For this reason, this event may have a changing ratio with regards to wall clock time.", + "PublicDescription": "This is an architectural event that counts the number of thread cycles while the thread is not in a halt state. The thread enters the halt state when it is running the HLT instruction. The core frequency may change from time to time due to power or thermal throttling. For this reason, this event may have a changing ratio with regards to wall clock time. Available PDIST counters: 0", "SampleAfterValue": "2000003", "Unit": "cpu_core" }, @@ -728,6 +759,7 @@ "CounterMask": "8", "EventCode": "0xa3", "EventName": "CYCLE_ACTIVITY.CYCLES_L1D_MISS", + "PublicDescription": "Cycles while L1 cache miss demand load is outstanding. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x8", "Unit": "cpu_core" @@ -738,6 +770,7 @@ "CounterMask": "1", "EventCode": "0xa3", "EventName": "CYCLE_ACTIVITY.CYCLES_L2_MISS", + "PublicDescription": "Cycles while L2 cache miss demand load is outstanding. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x1", "Unit": "cpu_core" @@ -748,6 +781,7 @@ "CounterMask": "16", "EventCode": "0xa3", "EventName": "CYCLE_ACTIVITY.CYCLES_MEM_ANY", + "PublicDescription": "Cycles while memory subsystem has an outstanding load. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x10", "Unit": "cpu_core" @@ -758,6 +792,7 @@ "CounterMask": "12", "EventCode": "0xa3", "EventName": "CYCLE_ACTIVITY.STALLS_L1D_MISS", + "PublicDescription": "Execution stalls while L1 cache miss demand load is outstanding. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0xc", "Unit": "cpu_core" @@ -768,6 +803,7 @@ "CounterMask": "5", "EventCode": "0xa3", "EventName": "CYCLE_ACTIVITY.STALLS_L2_MISS", + "PublicDescription": "Execution stalls while L2 cache miss demand load is outstanding. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x5", "Unit": "cpu_core" @@ -778,6 +814,7 @@ "CounterMask": "4", "EventCode": "0xa3", "EventName": "CYCLE_ACTIVITY.STALLS_TOTAL", + "PublicDescription": "Total execution stalls. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x4", "Unit": "cpu_core" @@ -787,7 +824,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xa6", "EventName": "EXE_ACTIVITY.1_PORTS_UTIL", - "PublicDescription": "Counts cycles during which a total of 1 uop was executed on all ports and Reservation Station (RS) was not empty.", + "PublicDescription": "Counts cycles during which a total of 1 uop was executed on all ports and Reservation Station (RS) was not empty. Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x2", "Unit": "cpu_core" @@ -797,6 +834,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xa6", "EventName": "EXE_ACTIVITY.2_3_PORTS_UTIL", + "PublicDescription": "Cycles total of 2 or 3 uops are executed on all ports and Reservation Station (RS) was not empty. Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0xc", "Unit": "cpu_core" @@ -806,7 +844,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xa6", "EventName": "EXE_ACTIVITY.2_PORTS_UTIL", - "PublicDescription": "Counts cycles during which a total of 2 uops were executed on all ports and Reservation Station (RS) was not empty.", + "PublicDescription": "Counts cycles during which a total of 2 uops were executed on all ports and Reservation Station (RS) was not empty. Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x4", "Unit": "cpu_core" @@ -816,7 +854,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xa6", "EventName": "EXE_ACTIVITY.3_PORTS_UTIL", - "PublicDescription": "Cycles total of 3 uops are executed on all ports and Reservation Station (RS) was not empty.", + "PublicDescription": "Cycles total of 3 uops are executed on all ports and Reservation Station (RS) was not empty. Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x8", "Unit": "cpu_core" @@ -826,7 +864,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xa6", "EventName": "EXE_ACTIVITY.4_PORTS_UTIL", - "PublicDescription": "Cycles total of 4 uops are executed on all ports and Reservation Station (RS) was not empty.", + "PublicDescription": "Cycles total of 4 uops are executed on all ports and Reservation Station (RS) was not empty. Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x10", "Unit": "cpu_core" @@ -837,6 +875,7 @@ "CounterMask": "5", "EventCode": "0xa6", "EventName": "EXE_ACTIVITY.BOUND_ON_LOADS", + "PublicDescription": "Execution stalls while memory subsystem has an outstanding load. Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x21", "Unit": "cpu_core" @@ -847,7 +886,7 @@ "CounterMask": "2", "EventCode": "0xa6", "EventName": "EXE_ACTIVITY.BOUND_ON_STORES", - "PublicDescription": "Counts cycles where the Store Buffer was full and no loads caused an execution stall.", + "PublicDescription": "Counts cycles where the Store Buffer was full and no loads caused an execution stall. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x40", "Unit": "cpu_core" @@ -857,7 +896,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xa6", "EventName": "EXE_ACTIVITY.EXE_BOUND_0_PORTS", - "PublicDescription": "Number of cycles total of 0 uops executed on all ports, Reservation Station (RS) was not empty, the Store Buffer (SB) was not full and there was no outstanding load.", + "PublicDescription": "Number of cycles total of 0 uops executed on all ports, Reservation Station (RS) was not empty, the Store Buffer (SB) was not full and there was no outstanding load. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x80", "Unit": "cpu_core" @@ -867,7 +906,7 @@ "Counter": "0,1,2,3", "EventCode": "0x75", "EventName": "INST_DECODED.DECODERS", - "PublicDescription": "Number of decoders utilized in a cycle when the MITE (legacy decode pipeline) fetches instructions.", + "PublicDescription": "Number of decoders utilized in a cycle when the MITE (legacy decode pipeline) fetches instructions. Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x1", "Unit": "cpu_core" @@ -876,7 +915,7 @@ "BriefDescription": "Counts the total number of instructions retired. (Fixed event)", "Counter": "Fixed counter 0", "EventName": "INST_RETIRED.ANY", - "PublicDescription": "Counts the total number of instructions that retired. For instructions that consist of multiple uops, this event counts the retirement of the last uop of the instruction. This event continues counting during hardware interrupts, traps, and inside interrupt handlers. This event uses fixed counter 0.", + "PublicDescription": "Counts the total number of instructions that retired. For instructions that consist of multiple uops, this event counts the retirement of the last uop of the instruction. This event continues counting during hardware interrupts, traps, and inside interrupt handlers. This event uses fixed counter 0. Available PDIST counters: 32", "SampleAfterValue": "2000003", "UMask": "0x1", "Unit": "cpu_atom" @@ -885,7 +924,7 @@ "BriefDescription": "Number of instructions retired. Fixed Counter - architectural event", "Counter": "Fixed counter 0", "EventName": "INST_RETIRED.ANY", - "PublicDescription": "Counts the number of X86 instructions retired - an Architectural PerfMon event. Counting continues during hardware interrupts, traps, and inside interrupt handlers. Notes: INST_RETIRED.ANY is counted by a designated fixed counter freeing up programmable counters to count other events. INST_RETIRED.ANY_P is counted by a programmable counter.", + "PublicDescription": "Counts the number of X86 instructions retired - an Architectural PerfMon event. Counting continues during hardware interrupts, traps, and inside interrupt handlers. Notes: INST_RETIRED.ANY is counted by a designated fixed counter freeing up programmable counters to count other events. INST_RETIRED.ANY_P is counted by a programmable counter. Available PDIST counters: 32", "SampleAfterValue": "2000003", "UMask": "0x1", "Unit": "cpu_core" @@ -895,7 +934,7 @@ "Counter": "0,1,2,3,4,5", "EventCode": "0xc0", "EventName": "INST_RETIRED.ANY_P", - "PublicDescription": "Counts the total number of instructions that retired. For instructions that consist of multiple uops, this event counts the retirement of the last uop of the instruction. This event continues counting during hardware interrupts, traps, and inside interrupt handlers. This event uses a programmable general purpose performance counter.", + "PublicDescription": "Counts the total number of instructions that retired. For instructions that consist of multiple uops, this event counts the retirement of the last uop of the instruction. This event continues counting during hardware interrupts, traps, and inside interrupt handlers. This event uses a programmable general purpose performance counter. Available PDIST counters: 0", "SampleAfterValue": "2000003", "Unit": "cpu_atom" }, @@ -913,6 +952,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc0", "EventName": "INST_RETIRED.MACRO_FUSED", + "PublicDescription": "INST_RETIRED.MACRO_FUSED Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x10", "Unit": "cpu_core" @@ -922,7 +962,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc0", "EventName": "INST_RETIRED.NOP", - "PublicDescription": "Counts all retired NOP or ENDBR32/64 instructions", + "PublicDescription": "Counts all retired NOP or ENDBR32/64 instructions Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x2", "Unit": "cpu_core" @@ -931,7 +971,7 @@ "BriefDescription": "Precise instruction retired with PEBS precise-distribution", "Counter": "Fixed counter 0", "EventName": "INST_RETIRED.PREC_DIST", - "PublicDescription": "A version of INST_RETIRED that allows for a precise distribution of samples across instructions retired. It utilizes the Precise Distribution of Instructions Retired (PDIR++) feature to fix bias in how retired instructions get sampled. Use on Fixed Counter 0.", + "PublicDescription": "A version of INST_RETIRED that allows for a precise distribution of samples across instructions retired. It utilizes the Precise Distribution of Instructions Retired (PDIR++) feature to fix bias in how retired instructions get sampled. Use on Fixed Counter 0. Available PDIST counters: 32", "SampleAfterValue": "2000003", "UMask": "0x1", "Unit": "cpu_core" @@ -941,7 +981,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc0", "EventName": "INST_RETIRED.REP_ITERATION", - "PublicDescription": "Number of iterations of Repeat (REP) string retired instructions such as MOVS, CMPS, and SCAS. Each has a byte, word, and doubleword version and string instructions can be repeated using a repetition prefix, REP, that allows their architectural execution to be repeated a number of times as specified by the RCX register. Note the number of iterations is implementation-dependent.", + "PublicDescription": "Number of iterations of Repeat (REP) string retired instructions such as MOVS, CMPS, and SCAS. Each has a byte, word, and doubleword version and string instructions can be repeated using a repetition prefix, REP, that allows their architectural execution to be repeated a number of times as specified by the RCX register. Note the number of iterations is implementation-dependent. Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x8", "Unit": "cpu_core" @@ -953,7 +993,7 @@ "EdgeDetect": "1", "EventCode": "0xad", "EventName": "INT_MISC.CLEARS_COUNT", - "PublicDescription": "Counts the number of speculative clears due to any type of branch misprediction or machine clears", + "PublicDescription": "Counts the number of speculative clears due to any type of branch misprediction or machine clears Available PDIST counters: 0", "SampleAfterValue": "500009", "UMask": "0x1", "Unit": "cpu_core" @@ -963,7 +1003,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xad", "EventName": "INT_MISC.CLEAR_RESTEER_CYCLES", - "PublicDescription": "Cycles after recovery from a branch misprediction or machine clear till the first uop is issued from the resteered path.", + "PublicDescription": "Cycles after recovery from a branch misprediction or machine clear till the first uop is issued from the resteered path. Available PDIST counters: 0", "SampleAfterValue": "500009", "UMask": "0x80", "Unit": "cpu_core" @@ -973,7 +1013,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xad", "EventName": "INT_MISC.RECOVERY_CYCLES", - "PublicDescription": "Counts core cycles when the Resource allocator was stalled due to recovery from an earlier branch misprediction or machine clear event.", + "PublicDescription": "Counts core cycles when the Resource allocator was stalled due to recovery from an earlier branch misprediction or machine clear event. Available PDIST counters: 0", "SampleAfterValue": "500009", "UMask": "0x1", "Unit": "cpu_core" @@ -985,6 +1025,7 @@ "EventName": "INT_MISC.UNKNOWN_BRANCH_CYCLES", "MSRIndex": "0x3F7", "MSRValue": "0x7", + "PublicDescription": "Bubble cycles of BAClear (Unknown Branch). Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x40", "Unit": "cpu_core" @@ -994,7 +1035,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xad", "EventName": "INT_MISC.UOP_DROPPING", - "PublicDescription": "Estimated number of Top-down Microarchitecture Analysis slots that got dropped due to non front-end reasons", + "PublicDescription": "Estimated number of Top-down Microarchitecture Analysis slots that got dropped due to non front-end reasons Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x10", "Unit": "cpu_core" @@ -1004,6 +1045,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xe7", "EventName": "INT_VEC_RETIRED.128BIT", + "PublicDescription": "INT_VEC_RETIRED.128BIT Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x13", "Unit": "cpu_core" @@ -1013,6 +1055,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xe7", "EventName": "INT_VEC_RETIRED.256BIT", + "PublicDescription": "INT_VEC_RETIRED.256BIT Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0xac", "Unit": "cpu_core" @@ -1022,7 +1065,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xe7", "EventName": "INT_VEC_RETIRED.ADD_128", - "PublicDescription": "Number of retired integer ADD/SUB (regular or horizontal), SAD 128-bit vector instructions.", + "PublicDescription": "Number of retired integer ADD/SUB (regular or horizontal), SAD 128-bit vector instructions. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x3", "Unit": "cpu_core" @@ -1032,7 +1075,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xe7", "EventName": "INT_VEC_RETIRED.ADD_256", - "PublicDescription": "Number of retired integer ADD/SUB (regular or horizontal), SAD 256-bit vector instructions.", + "PublicDescription": "Number of retired integer ADD/SUB (regular or horizontal), SAD 256-bit vector instructions. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0xc", "Unit": "cpu_core" @@ -1042,6 +1085,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xe7", "EventName": "INT_VEC_RETIRED.MUL_256", + "PublicDescription": "INT_VEC_RETIRED.MUL_256 Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x80", "Unit": "cpu_core" @@ -1051,6 +1095,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xe7", "EventName": "INT_VEC_RETIRED.SHUFFLES", + "PublicDescription": "INT_VEC_RETIRED.SHUFFLES Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x40", "Unit": "cpu_core" @@ -1060,6 +1105,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xe7", "EventName": "INT_VEC_RETIRED.VNNI_128", + "PublicDescription": "INT_VEC_RETIRED.VNNI_128 Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x10", "Unit": "cpu_core" @@ -1069,6 +1115,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xe7", "EventName": "INT_VEC_RETIRED.VNNI_256", + "PublicDescription": "INT_VEC_RETIRED.VNNI_256 Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x20", "Unit": "cpu_core" @@ -1079,6 +1126,7 @@ "Deprecated": "1", "EventCode": "0x03", "EventName": "LD_BLOCKS.4K_ALIAS", + "PublicDescription": "This event is deprecated. Refer to new event LD_BLOCKS.ADDRESS_ALIAS Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x4", "Unit": "cpu_atom" @@ -1088,6 +1136,7 @@ "Counter": "0,1,2,3,4,5", "EventCode": "0x03", "EventName": "LD_BLOCKS.ADDRESS_ALIAS", + "PublicDescription": "Counts the number of retired loads that are blocked because it initially appears to be store forward blocked, but subsequently is shown not to be blocked based on 4K alias check. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x4", "Unit": "cpu_atom" @@ -1097,7 +1146,7 @@ "Counter": "0,1,2,3", "EventCode": "0x03", "EventName": "LD_BLOCKS.ADDRESS_ALIAS", - "PublicDescription": "Counts the number of times a load got blocked due to false dependencies in MOB due to partial compare on address.", + "PublicDescription": "Counts the number of times a load got blocked due to false dependencies in MOB due to partial compare on address. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x4", "Unit": "cpu_core" @@ -1107,6 +1156,7 @@ "Counter": "0,1,2,3,4,5", "EventCode": "0x03", "EventName": "LD_BLOCKS.DATA_UNKNOWN", + "PublicDescription": "Counts the number of retired loads that are blocked because its address exactly matches an older store whose data is not ready. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x1", "Unit": "cpu_atom" @@ -1116,7 +1166,7 @@ "Counter": "0,1,2,3", "EventCode": "0x03", "EventName": "LD_BLOCKS.NO_SR", - "PublicDescription": "Counts the number of times that split load operations are temporarily blocked because all resources for handling the split accesses are in use.", + "PublicDescription": "Counts the number of times that split load operations are temporarily blocked because all resources for handling the split accesses are in use. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x88", "Unit": "cpu_core" @@ -1126,7 +1176,7 @@ "Counter": "0,1,2,3", "EventCode": "0x03", "EventName": "LD_BLOCKS.STORE_FORWARD", - "PublicDescription": "Counts the number of times where store forwarding was prevented for a load operation. The most common case is a load blocked due to the address of memory access (partially) overlapping with a preceding uncompleted store. Note: See the table of not supported store forwards in the Optimization Guide.", + "PublicDescription": "Counts the number of times where store forwarding was prevented for a load operation. The most common case is a load blocked due to the address of memory access (partially) overlapping with a preceding uncompleted store. Note: See the table of not supported store forwards in the Optimization Guide. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x82", "Unit": "cpu_core" @@ -1136,7 +1186,7 @@ "Counter": "0,1,2,3", "EventCode": "0x4c", "EventName": "LOAD_HIT_PREFETCH.SWPF", - "PublicDescription": "Counts all not software-prefetch load dispatches that hit the fill buffer (FB) allocated for the software prefetch. It can also be incremented by some lock instructions. So it should only be used with profiling so that the locks can be excluded by ASM (Assembly File) inspection of the nearby instructions.", + "PublicDescription": "Counts all not software-prefetch load dispatches that hit the fill buffer (FB) allocated for the software prefetch. It can also be incremented by some lock instructions. So it should only be used with profiling so that the locks can be excluded by ASM (Assembly File) inspection of the nearby instructions. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1", "Unit": "cpu_core" @@ -1147,7 +1197,7 @@ "CounterMask": "1", "EventCode": "0xa8", "EventName": "LSD.CYCLES_ACTIVE", - "PublicDescription": "Counts the cycles when at least one uop is delivered by the LSD (Loop-stream detector).", + "PublicDescription": "Counts the cycles when at least one uop is delivered by the LSD (Loop-stream detector). Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x1", "Unit": "cpu_core" @@ -1158,7 +1208,7 @@ "CounterMask": "6", "EventCode": "0xa8", "EventName": "LSD.CYCLES_OK", - "PublicDescription": "Counts the cycles when optimal number of uops is delivered by the LSD (Loop-stream detector).", + "PublicDescription": "Counts the cycles when optimal number of uops is delivered by the LSD (Loop-stream detector). Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x1", "Unit": "cpu_core" @@ -1168,7 +1218,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xa8", "EventName": "LSD.UOPS", - "PublicDescription": "Counts the number of uops delivered to the back-end by the LSD(Loop Stream Detector).", + "PublicDescription": "Counts the number of uops delivered to the back-end by the LSD(Loop Stream Detector). Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x1", "Unit": "cpu_core" @@ -1180,7 +1230,7 @@ "EdgeDetect": "1", "EventCode": "0xc3", "EventName": "MACHINE_CLEARS.COUNT", - "PublicDescription": "Counts the number of machine clears (nukes) of any type.", + "PublicDescription": "Counts the number of machine clears (nukes) of any type. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1", "Unit": "cpu_core" @@ -1213,8 +1263,9 @@ "Unit": "cpu_atom" }, { - "BriefDescription": "Counts the number of machine clears that flush the pipeline and restart the machine with the use of microcode due to SMC, MEMORY_ORDERING, FP_ASSISTS, PAGE_FAULT, DISAMBIGUATION, and FPC_VIRTUAL_TRAP.", + "BriefDescription": "This event is deprecated.", "Counter": "0,1,2,3,4,5", + "Deprecated": "1", "EventCode": "0xc3", "EventName": "MACHINE_CLEARS.SLOW", "SampleAfterValue": "20003", @@ -1235,7 +1286,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc3", "EventName": "MACHINE_CLEARS.SMC", - "PublicDescription": "Counts self-modifying code (SMC) detected, which causes a machine clear.", + "PublicDescription": "Counts self-modifying code (SMC) detected, which causes a machine clear. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x4", "Unit": "cpu_core" @@ -1245,7 +1296,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xe0", "EventName": "MISC2_RETIRED.LFENCE", - "PublicDescription": "number of LFENCE retired instructions", + "PublicDescription": "number of LFENCE retired instructions Available PDIST counters: 0", "SampleAfterValue": "400009", "UMask": "0x20", "Unit": "cpu_core" @@ -1255,7 +1306,7 @@ "Counter": "0,1,2,3,4,5", "EventCode": "0xe4", "EventName": "MISC_RETIRED.LBR_INSERTS", - "PublicDescription": "Counts the number of LBR entries recorded. Requires LBRs to be enabled in IA32_LBR_CTL. This event is PDIR on GP0 and NPEBS on all other GPs [This event is alias to LBR_INSERTS.ANY]", + "PublicDescription": "Counts the number of LBR entries recorded. Requires LBRs to be enabled in IA32_LBR_CTL. This event is PDIR on GP0 and NPEBS on all other GPs [This event is alias to LBR_INSERTS.ANY] Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x1", "Unit": "cpu_atom" @@ -1265,7 +1316,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xcc", "EventName": "MISC_RETIRED.LBR_INSERTS", - "PublicDescription": "Increments when an entry is added to the Last Branch Record (LBR) array (or removed from the array in case of RETURNs in call stack mode). The event requires LBR enable via IA32_DEBUGCTL MSR and branch type selection via MSR_LBR_SELECT.", + "PublicDescription": "Increments when an entry is added to the Last Branch Record (LBR) array (or removed from the array in case of RETURNs in call stack mode). The event requires LBR enable via IA32_DEBUGCTL MSR and branch type selection via MSR_LBR_SELECT. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x20", "Unit": "cpu_core" @@ -1275,7 +1326,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xa2", "EventName": "RESOURCE_STALLS.SB", - "PublicDescription": "Counts allocation stall cycles caused by the store buffer (SB) being full. This counts cycles that the pipeline back-end blocked uop delivery from the front-end.", + "PublicDescription": "Counts allocation stall cycles caused by the store buffer (SB) being full. This counts cycles that the pipeline back-end blocked uop delivery from the front-end. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x8", "Unit": "cpu_core" @@ -1285,11 +1336,79 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xa2", "EventName": "RESOURCE_STALLS.SCOREBOARD", + "PublicDescription": "Counts cycles where the pipeline is stalled due to serializing operations. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x2", "Unit": "cpu_core" }, { + "BriefDescription": "Cycles when Reservation Station (RS) is empty for the thread.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xa5", + "EventName": "RS.EMPTY", + "PublicDescription": "Counts cycles during which the reservation station (RS) is empty for this logical processor. This is usually caused when the front-end pipeline runs into starvation periods (e.g. branch mispredictions or i-cache misses) Available PDIST counters: 0", + "SampleAfterValue": "1000003", + "UMask": "0x7", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts end of periods where the Reservation Station (RS) was empty.", + "Counter": "0,1,2,3,4,5,6,7", + "CounterMask": "1", + "EdgeDetect": "1", + "EventCode": "0xa5", + "EventName": "RS.EMPTY_COUNT", + "Invert": "1", + "PublicDescription": "Counts end of periods where the Reservation Station (RS) was empty. Could be useful to closely sample on front-end latency issues (see the FRONTEND_RETIRED event of designated precise events) Available PDIST counters: 0", + "SampleAfterValue": "100003", + "UMask": "0x7", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Cycles when Reservation Station (RS) is empty due to a resource in the back-end", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xa5", + "EventName": "RS.EMPTY_RESOURCE", + "PublicDescription": "Cycles when Reservation Station (RS) is empty due to a resource in the back-end Available PDIST counters: 0", + "SampleAfterValue": "1000003", + "UMask": "0x1", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event RS.EMPTY_COUNT", + "Counter": "0,1,2,3,4,5,6,7", + "CounterMask": "1", + "Deprecated": "1", + "EdgeDetect": "1", + "EventCode": "0xa5", + "EventName": "RS_EMPTY.COUNT", + "Invert": "1", + "PublicDescription": "This event is deprecated. Refer to new event RS.EMPTY_COUNT Available PDIST counters: 0", + "SampleAfterValue": "100003", + "UMask": "0x7", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event RS.EMPTY", + "Counter": "0,1,2,3,4,5,6,7", + "Deprecated": "1", + "EventCode": "0xa5", + "EventName": "RS_EMPTY.CYCLES", + "PublicDescription": "This event is deprecated. Refer to new event RS.EMPTY Available PDIST counters: 0", + "SampleAfterValue": "1000003", + "UMask": "0x7", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts the number of issue slots in a UMWAIT or TPAUSE instruction where no uop issues due to the instruction putting the CPU into the C0.1 activity state. For Tremont, UMWAIT and TPAUSE will only put the CPU into C0.1 activity state (not C0.2 activity state)", + "Counter": "0,1,2,3,4,5", + "EventCode": "0x75", + "EventName": "SERIALIZATION.C01_MS_SCB", + "SampleAfterValue": "200003", + "UMask": "0x4", + "Unit": "cpu_atom" + }, + { "BriefDescription": "Counts the number of issue slots not consumed by the backend due to a micro-sequencer (MS) scoreboard, which stalls the front-end from issuing from the UROM until a specified older uop retires.", "Counter": "0,1,2,3,4,5", "EventCode": "0x75", @@ -1304,7 +1423,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xa4", "EventName": "TOPDOWN.BACKEND_BOUND_SLOTS", - "PublicDescription": "Number of slots in TMA method where no micro-operations were being issued from front-end to back-end of the machine due to lack of back-end resources.", + "PublicDescription": "Number of slots in TMA method where no micro-operations were being issued from front-end to back-end of the machine due to lack of back-end resources. Available PDIST counters: 0", "SampleAfterValue": "10000003", "UMask": "0x2", "Unit": "cpu_core" @@ -1314,7 +1433,7 @@ "Counter": "0", "EventCode": "0xa4", "EventName": "TOPDOWN.BAD_SPEC_SLOTS", - "PublicDescription": "Number of slots of TMA method that were wasted due to incorrect speculation. It covers all types of control-flow or data-related mis-speculations.", + "PublicDescription": "Number of slots of TMA method that were wasted due to incorrect speculation. It covers all types of control-flow or data-related mis-speculations. Available PDIST counters: 0", "SampleAfterValue": "10000003", "UMask": "0x4", "Unit": "cpu_core" @@ -1324,7 +1443,7 @@ "Counter": "0", "EventCode": "0xa4", "EventName": "TOPDOWN.BR_MISPREDICT_SLOTS", - "PublicDescription": "Number of TMA slots that were wasted due to incorrect speculation by (any type of) branch mispredictions. This event estimates number of speculative operations that were issued but not retired as well as the out-of-order engine recovery past a branch misprediction.", + "PublicDescription": "Number of TMA slots that were wasted due to incorrect speculation by (any type of) branch mispredictions. This event estimates number of speculative operations that were issued but not retired as well as the out-of-order engine recovery past a branch misprediction. Available PDIST counters: 0", "SampleAfterValue": "10000003", "UMask": "0x8", "Unit": "cpu_core" @@ -1334,6 +1453,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xa4", "EventName": "TOPDOWN.MEMORY_BOUND_SLOTS", + "PublicDescription": "TOPDOWN.MEMORY_BOUND_SLOTS Available PDIST counters: 0", "SampleAfterValue": "10000003", "UMask": "0x10", "Unit": "cpu_core" @@ -1352,7 +1472,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xa4", "EventName": "TOPDOWN.SLOTS_P", - "PublicDescription": "Counts the number of available slots for an unhalted logical processor. The event increments by machine-width of the narrowest pipeline as employed by the Top-down Microarchitecture Analysis method. The count is distributed among unhalted logical processors (hyper-threads) who share the same physical core.", + "PublicDescription": "Counts the number of available slots for an unhalted logical processor. The event increments by machine-width of the narrowest pipeline as employed by the Top-down Microarchitecture Analysis method. The count is distributed among unhalted logical processors (hyper-threads) who share the same physical core. Available PDIST counters: 0", "SampleAfterValue": "10000003", "UMask": "0x1", "Unit": "cpu_core" @@ -1561,6 +1681,7 @@ "Counter": "0,1,2,3,4,5", "EventCode": "0xc2", "EventName": "TOPDOWN_RETIRING.ALL", + "PublicDescription": "Counts the total number of consumed retirement slots. Available PDIST counters: 0", "SampleAfterValue": "1000003", "Unit": "cpu_atom" }, @@ -1569,6 +1690,7 @@ "Counter": "0,1,2,3", "EventCode": "0x76", "EventName": "UOPS_DECODED.DEC0_UOPS", + "PublicDescription": "UOPS_DECODED.DEC0_UOPS Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x1", "Unit": "cpu_core" @@ -1578,7 +1700,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xb2", "EventName": "UOPS_DISPATCHED.PORT_0", - "PublicDescription": "Number of uops dispatch to execution port 0.", + "PublicDescription": "Number of uops dispatch to execution port 0. Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x1", "Unit": "cpu_core" @@ -1588,7 +1710,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xb2", "EventName": "UOPS_DISPATCHED.PORT_1", - "PublicDescription": "Number of uops dispatch to execution port 1.", + "PublicDescription": "Number of uops dispatch to execution port 1. Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x2", "Unit": "cpu_core" @@ -1598,7 +1720,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xb2", "EventName": "UOPS_DISPATCHED.PORT_2_3_10", - "PublicDescription": "Number of uops dispatch to execution ports 2, 3 and 10", + "PublicDescription": "Number of uops dispatch to execution ports 2, 3 and 10 Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x4", "Unit": "cpu_core" @@ -1608,7 +1730,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xb2", "EventName": "UOPS_DISPATCHED.PORT_4_9", - "PublicDescription": "Number of uops dispatch to execution ports 4 and 9", + "PublicDescription": "Number of uops dispatch to execution ports 4 and 9 Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x10", "Unit": "cpu_core" @@ -1618,7 +1740,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xb2", "EventName": "UOPS_DISPATCHED.PORT_5_11", - "PublicDescription": "Number of uops dispatch to execution ports 5 and 11", + "PublicDescription": "Number of uops dispatch to execution ports 5 and 11 Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x20", "Unit": "cpu_core" @@ -1628,7 +1750,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xb2", "EventName": "UOPS_DISPATCHED.PORT_6", - "PublicDescription": "Number of uops dispatch to execution port 6.", + "PublicDescription": "Number of uops dispatch to execution port 6. Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x40", "Unit": "cpu_core" @@ -1638,7 +1760,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xb2", "EventName": "UOPS_DISPATCHED.PORT_7_8", - "PublicDescription": "Number of uops dispatch to execution ports 7 and 8.", + "PublicDescription": "Number of uops dispatch to execution ports 7 and 8. Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x80", "Unit": "cpu_core" @@ -1649,7 +1771,7 @@ "CounterMask": "1", "EventCode": "0xb1", "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_1", - "PublicDescription": "Counts cycles when at least 1 micro-op is executed from any thread on physical core.", + "PublicDescription": "Counts cycles when at least 1 micro-op is executed from any thread on physical core. Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x2", "Unit": "cpu_core" @@ -1660,7 +1782,7 @@ "CounterMask": "2", "EventCode": "0xb1", "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_2", - "PublicDescription": "Counts cycles when at least 2 micro-ops are executed from any thread on physical core.", + "PublicDescription": "Counts cycles when at least 2 micro-ops are executed from any thread on physical core. Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x2", "Unit": "cpu_core" @@ -1671,7 +1793,7 @@ "CounterMask": "3", "EventCode": "0xb1", "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_3", - "PublicDescription": "Counts cycles when at least 3 micro-ops are executed from any thread on physical core.", + "PublicDescription": "Counts cycles when at least 3 micro-ops are executed from any thread on physical core. Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x2", "Unit": "cpu_core" @@ -1682,7 +1804,7 @@ "CounterMask": "4", "EventCode": "0xb1", "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_4", - "PublicDescription": "Counts cycles when at least 4 micro-ops are executed from any thread on physical core.", + "PublicDescription": "Counts cycles when at least 4 micro-ops are executed from any thread on physical core. Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x2", "Unit": "cpu_core" @@ -1693,7 +1815,7 @@ "CounterMask": "1", "EventCode": "0xb1", "EventName": "UOPS_EXECUTED.CYCLES_GE_1", - "PublicDescription": "Cycles where at least 1 uop was executed per-thread.", + "PublicDescription": "Cycles where at least 1 uop was executed per-thread. Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x1", "Unit": "cpu_core" @@ -1704,7 +1826,7 @@ "CounterMask": "2", "EventCode": "0xb1", "EventName": "UOPS_EXECUTED.CYCLES_GE_2", - "PublicDescription": "Cycles where at least 2 uops were executed per-thread.", + "PublicDescription": "Cycles where at least 2 uops were executed per-thread. Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x1", "Unit": "cpu_core" @@ -1715,7 +1837,7 @@ "CounterMask": "3", "EventCode": "0xb1", "EventName": "UOPS_EXECUTED.CYCLES_GE_3", - "PublicDescription": "Cycles where at least 3 uops were executed per-thread.", + "PublicDescription": "Cycles where at least 3 uops were executed per-thread. Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x1", "Unit": "cpu_core" @@ -1726,7 +1848,7 @@ "CounterMask": "4", "EventCode": "0xb1", "EventName": "UOPS_EXECUTED.CYCLES_GE_4", - "PublicDescription": "Cycles where at least 4 uops were executed per-thread.", + "PublicDescription": "Cycles where at least 4 uops were executed per-thread. Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x1", "Unit": "cpu_core" @@ -1738,7 +1860,7 @@ "EventCode": "0xb1", "EventName": "UOPS_EXECUTED.STALLS", "Invert": "1", - "PublicDescription": "Counts cycles during which no uops were dispatched from the Reservation Station (RS) per thread.", + "PublicDescription": "Counts cycles during which no uops were dispatched from the Reservation Station (RS) per thread. Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x1", "Unit": "cpu_core" @@ -1751,6 +1873,7 @@ "EventCode": "0xb1", "EventName": "UOPS_EXECUTED.STALL_CYCLES", "Invert": "1", + "PublicDescription": "This event is deprecated. Refer to new event UOPS_EXECUTED.STALLS Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x1", "Unit": "cpu_core" @@ -1760,6 +1883,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xb1", "EventName": "UOPS_EXECUTED.THREAD", + "PublicDescription": "Counts the number of uops to be executed per-thread each cycle. Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x1", "Unit": "cpu_core" @@ -1769,7 +1893,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xb1", "EventName": "UOPS_EXECUTED.X87", - "PublicDescription": "Counts the number of x87 uops executed.", + "PublicDescription": "Counts the number of x87 uops executed. Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x10", "Unit": "cpu_core" @@ -1788,7 +1912,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xae", "EventName": "UOPS_ISSUED.ANY", - "PublicDescription": "Counts the number of uops that the Resource Allocation Table (RAT) issues to the Reservation Station (RS).", + "PublicDescription": "Counts the number of uops that the Resource Allocation Table (RAT) issues to the Reservation Station (RS). Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x1", "Unit": "cpu_core" @@ -1799,6 +1923,7 @@ "CounterMask": "1", "EventCode": "0xae", "EventName": "UOPS_ISSUED.CYCLES", + "PublicDescription": "UOPS_ISSUED.CYCLES Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x1", "Unit": "cpu_core" @@ -1808,6 +1933,7 @@ "Counter": "0,1,2,3,4,5", "EventCode": "0xc2", "EventName": "UOPS_RETIRED.ALL", + "PublicDescription": "Counts the total number of uops retired. Available PDIST counters: 0", "SampleAfterValue": "2000003", "Unit": "cpu_atom" }, @@ -1817,7 +1943,7 @@ "CounterMask": "1", "EventCode": "0xc2", "EventName": "UOPS_RETIRED.CYCLES", - "PublicDescription": "Counts cycles where at least one uop has retired.", + "PublicDescription": "Counts cycles where at least one uop has retired. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x2", "Unit": "cpu_core" @@ -1827,7 +1953,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc2", "EventName": "UOPS_RETIRED.HEAVY", - "PublicDescription": "Counts the number of retired micro-operations (uops) except the last uop of each instruction. An instruction that is decoded into less than two uops does not contribute to the count.", + "PublicDescription": "Counts the number of retired micro-operations (uops) except the last uop of each instruction. An instruction that is decoded into less than two uops does not contribute to the count. Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x1", "Unit": "cpu_core" @@ -1837,6 +1963,7 @@ "Counter": "0,1,2,3,4,5", "EventCode": "0xc2", "EventName": "UOPS_RETIRED.IDIV", + "PublicDescription": "Counts the number of integer divide uops retired. Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x10", "Unit": "cpu_atom" @@ -1846,7 +1973,7 @@ "Counter": "0,1,2,3,4,5", "EventCode": "0xc2", "EventName": "UOPS_RETIRED.MS", - "PublicDescription": "Counts the number of uops that are from complex flows issued by the Microcode Sequencer (MS). This includes uops from flows due to complex instructions, faults, assists, and inserted flows.", + "PublicDescription": "Counts the number of uops that are from complex flows issued by the Microcode Sequencer (MS). This includes uops from flows due to complex instructions, faults, assists, and inserted flows. Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x1", "Unit": "cpu_atom" @@ -1858,6 +1985,7 @@ "EventName": "UOPS_RETIRED.MS", "MSRIndex": "0x3F7", "MSRValue": "0x8", + "PublicDescription": "UOPS_RETIRED.MS Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x4", "Unit": "cpu_core" @@ -1867,7 +1995,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc2", "EventName": "UOPS_RETIRED.SLOTS", - "PublicDescription": "Counts the retirement slots used each cycle.", + "PublicDescription": "Counts the retirement slots used each cycle. Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x2", "Unit": "cpu_core" @@ -1879,7 +2007,7 @@ "EventCode": "0xc2", "EventName": "UOPS_RETIRED.STALLS", "Invert": "1", - "PublicDescription": "This event counts cycles without actually retired uops.", + "PublicDescription": "This event counts cycles without actually retired uops. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x2", "Unit": "cpu_core" @@ -1892,6 +2020,7 @@ "EventCode": "0xc2", "EventName": "UOPS_RETIRED.STALL_CYCLES", "Invert": "1", + "PublicDescription": "This event is deprecated. Refer to new event UOPS_RETIRED.STALLS Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x2", "Unit": "cpu_core" @@ -1901,6 +2030,7 @@ "Counter": "0,1,2,3,4,5", "EventCode": "0xc2", "EventName": "UOPS_RETIRED.X87", + "PublicDescription": "Counts the number of x87 uops retired, includes those in MS flows. Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x2", "Unit": "cpu_atom" diff --git a/tools/perf/pmu-events/arch/x86/alderlake/virtual-memory.json b/tools/perf/pmu-events/arch/x86/alderlake/virtual-memory.json index 132ce48af6d9..3d15275eca61 100644 --- a/tools/perf/pmu-events/arch/x86/alderlake/virtual-memory.json +++ b/tools/perf/pmu-events/arch/x86/alderlake/virtual-memory.json @@ -4,7 +4,7 @@ "Counter": "0,1,2,3", "EventCode": "0x12", "EventName": "DTLB_LOAD_MISSES.STLB_HIT", - "PublicDescription": "Counts loads that miss the DTLB (Data TLB) and hit the STLB (Second level TLB).", + "PublicDescription": "Counts loads that miss the DTLB (Data TLB) and hit the STLB (Second level TLB). Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x20", "Unit": "cpu_core" @@ -15,7 +15,7 @@ "CounterMask": "1", "EventCode": "0x12", "EventName": "DTLB_LOAD_MISSES.WALK_ACTIVE", - "PublicDescription": "Counts cycles when at least one PMH (Page Miss Handler) is busy with a page walk for a demand load.", + "PublicDescription": "Counts cycles when at least one PMH (Page Miss Handler) is busy with a page walk for a demand load. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x10", "Unit": "cpu_core" @@ -35,7 +35,7 @@ "Counter": "0,1,2,3", "EventCode": "0x12", "EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED", - "PublicDescription": "Counts completed page walks (all page sizes) caused by demand data loads. This implies it missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.", + "PublicDescription": "Counts completed page walks (all page sizes) caused by demand data loads. This implies it missed in the DTLB and further levels of TLB. The page walk can end with or without a fault. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0xe", "Unit": "cpu_core" @@ -45,7 +45,7 @@ "Counter": "0,1,2,3", "EventCode": "0x12", "EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED_1G", - "PublicDescription": "Counts completed page walks (1G sizes) caused by demand data loads. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.", + "PublicDescription": "Counts completed page walks (1G sizes) caused by demand data loads. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x8", "Unit": "cpu_core" @@ -55,7 +55,7 @@ "Counter": "0,1,2,3", "EventCode": "0x12", "EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M", - "PublicDescription": "Counts completed page walks (2M/4M sizes) caused by demand data loads. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.", + "PublicDescription": "Counts completed page walks (2M/4M sizes) caused by demand data loads. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x4", "Unit": "cpu_core" @@ -65,7 +65,7 @@ "Counter": "0,1,2,3", "EventCode": "0x12", "EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED_4K", - "PublicDescription": "Counts completed page walks (4K sizes) caused by demand data loads. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.", + "PublicDescription": "Counts completed page walks (4K sizes) caused by demand data loads. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x2", "Unit": "cpu_core" @@ -75,7 +75,7 @@ "Counter": "0,1,2,3", "EventCode": "0x12", "EventName": "DTLB_LOAD_MISSES.WALK_PENDING", - "PublicDescription": "Counts the number of page walks outstanding for a demand load in the PMH (Page Miss Handler) each cycle.", + "PublicDescription": "Counts the number of page walks outstanding for a demand load in the PMH (Page Miss Handler) each cycle. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x10", "Unit": "cpu_core" @@ -85,7 +85,7 @@ "Counter": "0,1,2,3", "EventCode": "0x13", "EventName": "DTLB_STORE_MISSES.STLB_HIT", - "PublicDescription": "Counts stores that miss the DTLB (Data TLB) and hit the STLB (2nd Level TLB).", + "PublicDescription": "Counts stores that miss the DTLB (Data TLB) and hit the STLB (2nd Level TLB). Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x20", "Unit": "cpu_core" @@ -96,7 +96,7 @@ "CounterMask": "1", "EventCode": "0x13", "EventName": "DTLB_STORE_MISSES.WALK_ACTIVE", - "PublicDescription": "Counts cycles when at least one PMH (Page Miss Handler) is busy with a page walk for a store.", + "PublicDescription": "Counts cycles when at least one PMH (Page Miss Handler) is busy with a page walk for a store. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x10", "Unit": "cpu_core" @@ -116,7 +116,7 @@ "Counter": "0,1,2,3", "EventCode": "0x13", "EventName": "DTLB_STORE_MISSES.WALK_COMPLETED", - "PublicDescription": "Counts completed page walks (all page sizes) caused by demand data stores. This implies it missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.", + "PublicDescription": "Counts completed page walks (all page sizes) caused by demand data stores. This implies it missed in the DTLB and further levels of TLB. The page walk can end with or without a fault. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0xe", "Unit": "cpu_core" @@ -126,7 +126,7 @@ "Counter": "0,1,2,3", "EventCode": "0x13", "EventName": "DTLB_STORE_MISSES.WALK_COMPLETED_1G", - "PublicDescription": "Counts completed page walks (1G sizes) caused by demand data stores. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.", + "PublicDescription": "Counts completed page walks (1G sizes) caused by demand data stores. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x8", "Unit": "cpu_core" @@ -136,7 +136,7 @@ "Counter": "0,1,2,3", "EventCode": "0x13", "EventName": "DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M", - "PublicDescription": "Counts completed page walks (2M/4M sizes) caused by demand data stores. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.", + "PublicDescription": "Counts completed page walks (2M/4M sizes) caused by demand data stores. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x4", "Unit": "cpu_core" @@ -146,7 +146,7 @@ "Counter": "0,1,2,3", "EventCode": "0x13", "EventName": "DTLB_STORE_MISSES.WALK_COMPLETED_4K", - "PublicDescription": "Counts completed page walks (4K sizes) caused by demand data stores. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.", + "PublicDescription": "Counts completed page walks (4K sizes) caused by demand data stores. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x2", "Unit": "cpu_core" @@ -156,7 +156,7 @@ "Counter": "0,1,2,3", "EventCode": "0x13", "EventName": "DTLB_STORE_MISSES.WALK_PENDING", - "PublicDescription": "Counts the number of page walks outstanding for a store in the PMH (Page Miss Handler) each cycle.", + "PublicDescription": "Counts the number of page walks outstanding for a store in the PMH (Page Miss Handler) each cycle. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x10", "Unit": "cpu_core" @@ -184,7 +184,7 @@ "Counter": "0,1,2,3", "EventCode": "0x11", "EventName": "ITLB_MISSES.STLB_HIT", - "PublicDescription": "Counts instruction fetch requests that miss the ITLB (Instruction TLB) and hit the STLB (Second-level TLB).", + "PublicDescription": "Counts instruction fetch requests that miss the ITLB (Instruction TLB) and hit the STLB (Second-level TLB). Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x20", "Unit": "cpu_core" @@ -195,7 +195,7 @@ "CounterMask": "1", "EventCode": "0x11", "EventName": "ITLB_MISSES.WALK_ACTIVE", - "PublicDescription": "Counts cycles when at least one PMH (Page Miss Handler) is busy with a page walk for a code (instruction fetch) request.", + "PublicDescription": "Counts cycles when at least one PMH (Page Miss Handler) is busy with a page walk for a code (instruction fetch) request. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x10", "Unit": "cpu_core" @@ -215,7 +215,7 @@ "Counter": "0,1,2,3", "EventCode": "0x11", "EventName": "ITLB_MISSES.WALK_COMPLETED", - "PublicDescription": "Counts completed page walks (all page sizes) caused by a code fetch. This implies it missed in the ITLB (Instruction TLB) and further levels of TLB. The page walk can end with or without a fault.", + "PublicDescription": "Counts completed page walks (all page sizes) caused by a code fetch. This implies it missed in the ITLB (Instruction TLB) and further levels of TLB. The page walk can end with or without a fault. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0xe", "Unit": "cpu_core" @@ -225,7 +225,7 @@ "Counter": "0,1,2,3", "EventCode": "0x11", "EventName": "ITLB_MISSES.WALK_COMPLETED_2M_4M", - "PublicDescription": "Counts completed page walks (2M/4M page sizes) caused by a code fetch. This implies it missed in the ITLB (Instruction TLB) and further levels of TLB. The page walk can end with or without a fault.", + "PublicDescription": "Counts completed page walks (2M/4M page sizes) caused by a code fetch. This implies it missed in the ITLB (Instruction TLB) and further levels of TLB. The page walk can end with or without a fault. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x4", "Unit": "cpu_core" @@ -235,7 +235,7 @@ "Counter": "0,1,2,3", "EventCode": "0x11", "EventName": "ITLB_MISSES.WALK_COMPLETED_4K", - "PublicDescription": "Counts completed page walks (4K page sizes) caused by a code fetch. This implies it missed in the ITLB (Instruction TLB) and further levels of TLB. The page walk can end with or without a fault.", + "PublicDescription": "Counts completed page walks (4K page sizes) caused by a code fetch. This implies it missed in the ITLB (Instruction TLB) and further levels of TLB. The page walk can end with or without a fault. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x2", "Unit": "cpu_core" @@ -245,7 +245,7 @@ "Counter": "0,1,2,3", "EventCode": "0x11", "EventName": "ITLB_MISSES.WALK_PENDING", - "PublicDescription": "Counts the number of page walks outstanding for an outstanding code (instruction fetch) request in the PMH (Page Miss Handler) each cycle.", + "PublicDescription": "Counts the number of page walks outstanding for an outstanding code (instruction fetch) request in the PMH (Page Miss Handler) each cycle. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x10", "Unit": "cpu_core" @@ -266,6 +266,7 @@ "Deprecated": "1", "EventCode": "0xd0", "EventName": "MEM_UOPS_RETIRED.DTLB_MISS", + "PublicDescription": "This event is deprecated. Refer to new event MEM_UOPS_RETIRED.STLB_MISS Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0x13", "Unit": "cpu_atom" @@ -277,6 +278,7 @@ "Deprecated": "1", "EventCode": "0xd0", "EventName": "MEM_UOPS_RETIRED.DTLB_MISS_LOADS", + "PublicDescription": "This event is deprecated. Refer to new event MEM_UOPS_RETIRED.STLB_MISS_LOADS Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0x11", "Unit": "cpu_atom" @@ -288,6 +290,7 @@ "Deprecated": "1", "EventCode": "0xd0", "EventName": "MEM_UOPS_RETIRED.DTLB_MISS_STORES", + "PublicDescription": "This event is deprecated. Refer to new event MEM_UOPS_RETIRED.STLB_MISS_STORES Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0x12", "Unit": "cpu_atom" diff --git a/tools/perf/pmu-events/arch/x86/alderlaken/adln-metrics.json b/tools/perf/pmu-events/arch/x86/alderlaken/adln-metrics.json index ad04b1e3881e..ce93648043ef 100644 --- a/tools/perf/pmu-events/arch/x86/alderlaken/adln-metrics.json +++ b/tools/perf/pmu-events/arch/x86/alderlaken/adln-metrics.json @@ -75,7 +75,7 @@ "MetricExpr": "tma_core_bound", "MetricGroup": "TopdownL3;tma_L3_group;tma_core_bound_group", "MetricName": "tma_allocation_restriction", - "MetricThreshold": "(tma_allocation_restriction >0.10) & ((tma_core_bound >0.10) & ((tma_backend_bound >0.10)))", + "MetricThreshold": "tma_allocation_restriction > 0.1 & (tma_core_bound > 0.1 & tma_backend_bound > 0.1)", "ScaleUnit": "100%" }, { @@ -84,7 +84,7 @@ "MetricExpr": "TOPDOWN_BE_BOUND.ALL / (5 * CPU_CLK_UNHALTED.CORE)", "MetricGroup": "Default;TopdownL1;tma_L1_group", "MetricName": "tma_backend_bound", - "MetricThreshold": "(tma_backend_bound >0.10)", + "MetricThreshold": "tma_backend_bound > 0.1", "MetricgroupNoGroup": "TopdownL1;Default", "PublicDescription": "Counts the total number of issue slots that were not consumed by the backend due to backend stalls. Note that uops must be available for consumption in order for this event to count. If a uop is not available (IQ is empty), this event will not count", "ScaleUnit": "100%" @@ -95,7 +95,7 @@ "MetricExpr": "(5 * CPU_CLK_UNHALTED.CORE - (TOPDOWN_FE_BOUND.ALL + TOPDOWN_BE_BOUND.ALL + TOPDOWN_RETIRING.ALL)) / (5 * CPU_CLK_UNHALTED.CORE)", "MetricGroup": "Default;TopdownL1;tma_L1_group", "MetricName": "tma_bad_speculation", - "MetricThreshold": "(tma_bad_speculation >0.15)", + "MetricThreshold": "tma_bad_speculation > 0.15", "MetricgroupNoGroup": "TopdownL1;Default", "PublicDescription": "Counts the total number of issue slots that were not consumed by the backend because allocation is stalled due to a mispredicted jump or a machine clear. Only issue slots wasted due to fast nukes such as memory ordering nukes are counted. Other nukes are not accounted for. Counts all issue slots blocked during this recovery window including relevant microcode flows and while uops are not yet available in the instruction queue (IQ). Also includes the issue slots that were consumed by the backend but were thrown away because they were younger than the mispredict or machine clear.", "ScaleUnit": "100%" @@ -105,7 +105,7 @@ "MetricExpr": "TOPDOWN_FE_BOUND.BRANCH_DETECT / (5 * CPU_CLK_UNHALTED.CORE)", "MetricGroup": "TopdownL3;tma_L3_group;tma_ifetch_latency_group", "MetricName": "tma_branch_detect", - "MetricThreshold": "(tma_branch_detect >0.05) & ((tma_ifetch_latency >0.15) & ((tma_frontend_bound >0.20)))", + "MetricThreshold": "tma_branch_detect > 0.05 & (tma_ifetch_latency > 0.15 & tma_frontend_bound > 0.2)", "PublicDescription": "Counts the number of issue slots that were not delivered by the frontend due to BACLEARS, which occurs when the Branch Target Buffer (BTB) prediction or lack thereof, was corrected by a later branch predictor in the frontend. Includes BACLEARS due to all branch types including conditional and unconditional jumps, returns, and indirect branches.", "ScaleUnit": "100%" }, @@ -114,7 +114,7 @@ "MetricExpr": "TOPDOWN_BAD_SPECULATION.MISPREDICT / (5 * CPU_CLK_UNHALTED.CORE)", "MetricGroup": "TopdownL2;tma_L2_group;tma_bad_speculation_group", "MetricName": "tma_branch_mispredicts", - "MetricThreshold": "(tma_branch_mispredicts >0.05) & ((tma_bad_speculation >0.15))", + "MetricThreshold": "tma_branch_mispredicts > 0.05 & tma_bad_speculation > 0.15", "MetricgroupNoGroup": "TopdownL2", "ScaleUnit": "100%" }, @@ -123,7 +123,7 @@ "MetricExpr": "TOPDOWN_FE_BOUND.BRANCH_RESTEER / (5 * CPU_CLK_UNHALTED.CORE)", "MetricGroup": "TopdownL3;tma_L3_group;tma_ifetch_latency_group", "MetricName": "tma_branch_resteer", - "MetricThreshold": "(tma_branch_resteer >0.05) & ((tma_ifetch_latency >0.15) & ((tma_frontend_bound >0.20)))", + "MetricThreshold": "tma_branch_resteer > 0.05 & (tma_ifetch_latency > 0.15 & tma_frontend_bound > 0.2)", "ScaleUnit": "100%" }, { @@ -131,7 +131,7 @@ "MetricExpr": "TOPDOWN_FE_BOUND.CISC / (5 * CPU_CLK_UNHALTED.CORE)", "MetricGroup": "TopdownL3;tma_L3_group;tma_ifetch_bandwidth_group", "MetricName": "tma_cisc", - "MetricThreshold": "(tma_cisc >0.05) & ((tma_ifetch_bandwidth >0.10) & ((tma_frontend_bound >0.20)))", + "MetricThreshold": "tma_cisc > 0.05 & (tma_ifetch_bandwidth > 0.1 & tma_frontend_bound > 0.2)", "ScaleUnit": "100%" }, { @@ -139,7 +139,7 @@ "MetricExpr": "TOPDOWN_BE_BOUND.ALLOC_RESTRICTIONS / (5 * CPU_CLK_UNHALTED.CORE)", "MetricGroup": "TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_core_bound", - "MetricThreshold": "(tma_core_bound >0.10) & ((tma_backend_bound >0.10))", + "MetricThreshold": "tma_core_bound > 0.1 & tma_backend_bound > 0.1", "MetricgroupNoGroup": "TopdownL2", "ScaleUnit": "100%" }, @@ -148,7 +148,7 @@ "MetricExpr": "TOPDOWN_FE_BOUND.DECODE / (5 * CPU_CLK_UNHALTED.CORE)", "MetricGroup": "TopdownL3;tma_L3_group;tma_ifetch_bandwidth_group", "MetricName": "tma_decode", - "MetricThreshold": "(tma_decode >0.05) & ((tma_ifetch_bandwidth >0.10) & ((tma_frontend_bound >0.20)))", + "MetricThreshold": "tma_decode > 0.05 & (tma_ifetch_bandwidth > 0.1 & tma_frontend_bound > 0.2)", "ScaleUnit": "100%" }, { @@ -156,7 +156,7 @@ "MetricExpr": "TOPDOWN_BAD_SPECULATION.FASTNUKE / (5 * CPU_CLK_UNHALTED.CORE)", "MetricGroup": "TopdownL3;tma_L3_group;tma_machine_clears_group", "MetricName": "tma_fast_nuke", - "MetricThreshold": "(tma_fast_nuke >0.05) & ((tma_machine_clears >0.05) & ((tma_bad_speculation >0.15)))", + "MetricThreshold": "tma_fast_nuke > 0.05 & (tma_machine_clears > 0.05 & tma_bad_speculation > 0.15)", "ScaleUnit": "100%" }, { @@ -165,7 +165,7 @@ "MetricExpr": "TOPDOWN_FE_BOUND.ALL / (5 * CPU_CLK_UNHALTED.CORE)", "MetricGroup": "Default;TopdownL1;tma_L1_group", "MetricName": "tma_frontend_bound", - "MetricThreshold": "(tma_frontend_bound >0.20)", + "MetricThreshold": "tma_frontend_bound > 0.2", "MetricgroupNoGroup": "TopdownL1;Default", "ScaleUnit": "100%" }, @@ -174,7 +174,7 @@ "MetricExpr": "TOPDOWN_FE_BOUND.ICACHE / (5 * CPU_CLK_UNHALTED.CORE)", "MetricGroup": "TopdownL3;tma_L3_group;tma_ifetch_latency_group", "MetricName": "tma_icache_misses", - "MetricThreshold": "(tma_icache_misses >0.05) & ((tma_ifetch_latency >0.15) & ((tma_frontend_bound >0.20)))", + "MetricThreshold": "tma_icache_misses > 0.05 & (tma_ifetch_latency > 0.15 & tma_frontend_bound > 0.2)", "ScaleUnit": "100%" }, { @@ -182,7 +182,7 @@ "MetricExpr": "TOPDOWN_FE_BOUND.FRONTEND_BANDWIDTH / (5 * CPU_CLK_UNHALTED.CORE)", "MetricGroup": "TopdownL2;tma_L2_group;tma_frontend_bound_group", "MetricName": "tma_ifetch_bandwidth", - "MetricThreshold": "(tma_ifetch_bandwidth >0.10) & ((tma_frontend_bound >0.20))", + "MetricThreshold": "tma_ifetch_bandwidth > 0.1 & tma_frontend_bound > 0.2", "MetricgroupNoGroup": "TopdownL2", "ScaleUnit": "100%" }, @@ -191,7 +191,7 @@ "MetricExpr": "TOPDOWN_FE_BOUND.FRONTEND_LATENCY / (5 * CPU_CLK_UNHALTED.CORE)", "MetricGroup": "TopdownL2;tma_L2_group;tma_frontend_bound_group", "MetricName": "tma_ifetch_latency", - "MetricThreshold": "(tma_ifetch_latency >0.15) & ((tma_frontend_bound >0.20))", + "MetricThreshold": "tma_ifetch_latency > 0.15 & tma_frontend_bound > 0.2", "MetricgroupNoGroup": "TopdownL2", "ScaleUnit": "100%" }, @@ -473,7 +473,7 @@ "BriefDescription": "PerfMon Event Multiplexing accuracy indicator", "MetricExpr": "CPU_CLK_UNHALTED.CORE_P / CPU_CLK_UNHALTED.CORE", "MetricName": "tma_info_system_mux", - "MetricThreshold": "((tma_info_system_mux > 1.1)|(tma_info_system_mux < 0.9))" + "MetricThreshold": "tma_info_system_mux > 1.1 | tma_info_system_mux < 0.9" }, { "BriefDescription": "Average Frequency Utilization relative nominal frequency", @@ -506,7 +506,7 @@ "MetricExpr": "TOPDOWN_FE_BOUND.ITLB / (5 * CPU_CLK_UNHALTED.CORE)", "MetricGroup": "TopdownL3;tma_L3_group;tma_ifetch_latency_group", "MetricName": "tma_itlb_misses", - "MetricThreshold": "(tma_itlb_misses >0.05) & ((tma_ifetch_latency >0.15) & ((tma_frontend_bound >0.20)))", + "MetricThreshold": "tma_itlb_misses > 0.05 & (tma_ifetch_latency > 0.15 & tma_frontend_bound > 0.2)", "ScaleUnit": "100%" }, { @@ -514,7 +514,7 @@ "MetricExpr": "TOPDOWN_BAD_SPECULATION.MACHINE_CLEARS / (5 * CPU_CLK_UNHALTED.CORE)", "MetricGroup": "TopdownL2;tma_L2_group;tma_bad_speculation_group", "MetricName": "tma_machine_clears", - "MetricThreshold": "(tma_machine_clears >0.05) & ((tma_bad_speculation >0.15))", + "MetricThreshold": "tma_machine_clears > 0.05 & tma_bad_speculation > 0.15", "MetricgroupNoGroup": "TopdownL2", "ScaleUnit": "100%" }, @@ -523,7 +523,7 @@ "MetricExpr": "TOPDOWN_BE_BOUND.MEM_SCHEDULER / (5 * CPU_CLK_UNHALTED.CORE)", "MetricGroup": "TopdownL3;tma_L3_group;tma_resource_bound_group", "MetricName": "tma_mem_scheduler", - "MetricThreshold": "(tma_mem_scheduler >0.10) & ((tma_resource_bound >0.20) & ((tma_backend_bound >0.10)))", + "MetricThreshold": "tma_mem_scheduler > 0.1 & (tma_resource_bound > 0.2 & tma_backend_bound > 0.1)", "ScaleUnit": "100%" }, { @@ -531,7 +531,7 @@ "MetricExpr": "TOPDOWN_BE_BOUND.NON_MEM_SCHEDULER / (5 * CPU_CLK_UNHALTED.CORE)", "MetricGroup": "TopdownL3;tma_L3_group;tma_resource_bound_group", "MetricName": "tma_non_mem_scheduler", - "MetricThreshold": "(tma_non_mem_scheduler >0.10) & ((tma_resource_bound >0.20) & ((tma_backend_bound >0.10)))", + "MetricThreshold": "tma_non_mem_scheduler > 0.1 & (tma_resource_bound > 0.2 & tma_backend_bound > 0.1)", "ScaleUnit": "100%" }, { @@ -539,7 +539,7 @@ "MetricExpr": "TOPDOWN_BAD_SPECULATION.NUKE / (5 * CPU_CLK_UNHALTED.CORE)", "MetricGroup": "TopdownL3;tma_L3_group;tma_machine_clears_group", "MetricName": "tma_nuke", - "MetricThreshold": "(tma_nuke >0.05) & ((tma_machine_clears >0.05) & ((tma_bad_speculation >0.15)))", + "MetricThreshold": "tma_nuke > 0.05 & (tma_machine_clears > 0.05 & tma_bad_speculation > 0.15)", "ScaleUnit": "100%" }, { @@ -547,7 +547,7 @@ "MetricExpr": "TOPDOWN_FE_BOUND.OTHER / (5 * CPU_CLK_UNHALTED.CORE)", "MetricGroup": "TopdownL3;tma_L3_group;tma_ifetch_bandwidth_group", "MetricName": "tma_other_fb", - "MetricThreshold": "(tma_other_fb >0.05) & ((tma_ifetch_bandwidth >0.10) & ((tma_frontend_bound >0.20)))", + "MetricThreshold": "tma_other_fb > 0.05 & (tma_ifetch_bandwidth > 0.1 & tma_frontend_bound > 0.2)", "ScaleUnit": "100%" }, { @@ -555,7 +555,7 @@ "MetricExpr": "TOPDOWN_FE_BOUND.PREDECODE / (5 * CPU_CLK_UNHALTED.CORE)", "MetricGroup": "TopdownL3;tma_L3_group;tma_ifetch_bandwidth_group", "MetricName": "tma_predecode", - "MetricThreshold": "(tma_predecode >0.05) & ((tma_ifetch_bandwidth >0.10) & ((tma_frontend_bound >0.20)))", + "MetricThreshold": "tma_predecode > 0.05 & (tma_ifetch_bandwidth > 0.1 & tma_frontend_bound > 0.2)", "ScaleUnit": "100%" }, { @@ -563,7 +563,7 @@ "MetricExpr": "TOPDOWN_BE_BOUND.REGISTER / (5 * CPU_CLK_UNHALTED.CORE)", "MetricGroup": "TopdownL3;tma_L3_group;tma_resource_bound_group", "MetricName": "tma_register", - "MetricThreshold": "(tma_register >0.10) & ((tma_resource_bound >0.20) & ((tma_backend_bound >0.10)))", + "MetricThreshold": "tma_register > 0.1 & (tma_resource_bound > 0.2 & tma_backend_bound > 0.1)", "ScaleUnit": "100%" }, { @@ -571,7 +571,7 @@ "MetricExpr": "TOPDOWN_BE_BOUND.REORDER_BUFFER / (5 * CPU_CLK_UNHALTED.CORE)", "MetricGroup": "TopdownL3;tma_L3_group;tma_resource_bound_group", "MetricName": "tma_reorder_buffer", - "MetricThreshold": "(tma_reorder_buffer >0.10) & ((tma_resource_bound >0.20) & ((tma_backend_bound >0.10)))", + "MetricThreshold": "tma_reorder_buffer > 0.1 & (tma_resource_bound > 0.2 & tma_backend_bound > 0.1)", "ScaleUnit": "100%" }, { @@ -579,7 +579,7 @@ "MetricExpr": "tma_backend_bound - tma_core_bound", "MetricGroup": "TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_resource_bound", - "MetricThreshold": "(tma_resource_bound >0.20) & ((tma_backend_bound >0.10))", + "MetricThreshold": "tma_resource_bound > 0.2 & tma_backend_bound > 0.1", "MetricgroupNoGroup": "TopdownL2", "ScaleUnit": "100%" }, @@ -589,7 +589,7 @@ "MetricExpr": "TOPDOWN_RETIRING.ALL / (5 * CPU_CLK_UNHALTED.CORE)", "MetricGroup": "Default;TopdownL1;tma_L1_group", "MetricName": "tma_retiring", - "MetricThreshold": "(tma_retiring >0.75)", + "MetricThreshold": "tma_retiring > 0.75", "MetricgroupNoGroup": "TopdownL1;Default", "ScaleUnit": "100%" }, @@ -598,7 +598,7 @@ "MetricExpr": "TOPDOWN_BE_BOUND.SERIALIZATION / (5 * CPU_CLK_UNHALTED.CORE)", "MetricGroup": "TopdownL3;tma_L3_group;tma_resource_bound_group", "MetricName": "tma_serialization", - "MetricThreshold": "(tma_serialization >0.10) & ((tma_resource_bound >0.20) & ((tma_backend_bound >0.10)))", + "MetricThreshold": "tma_serialization > 0.1 & (tma_resource_bound > 0.2 & tma_backend_bound > 0.1)", "ScaleUnit": "100%" } ] diff --git a/tools/perf/pmu-events/arch/x86/alderlaken/cache.json b/tools/perf/pmu-events/arch/x86/alderlaken/cache.json index fd9ed58c2f90..bf691aee1ef4 100644 --- a/tools/perf/pmu-events/arch/x86/alderlaken/cache.json +++ b/tools/perf/pmu-events/arch/x86/alderlaken/cache.json @@ -118,6 +118,7 @@ "Data_LA": "1", "EventCode": "0xd1", "EventName": "MEM_LOAD_UOPS_RETIRED.DRAM_HIT", + "PublicDescription": "Counts the number of load uops retired that hit in DRAM. Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0x80" }, @@ -127,6 +128,7 @@ "Data_LA": "1", "EventCode": "0xd1", "EventName": "MEM_LOAD_UOPS_RETIRED.HITM", + "PublicDescription": "Counts the number of load uops retired that hit in the L3 cache, in which a snoop was required and modified data was forwarded from another core or module. Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0x20" }, @@ -136,6 +138,7 @@ "Data_LA": "1", "EventCode": "0xd1", "EventName": "MEM_LOAD_UOPS_RETIRED.L1_HIT", + "PublicDescription": "Counts the number of load uops retired that hit in the L1 data cache. Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0x1" }, @@ -145,6 +148,7 @@ "Data_LA": "1", "EventCode": "0xd1", "EventName": "MEM_LOAD_UOPS_RETIRED.L1_MISS", + "PublicDescription": "Counts the number of load uops retired that miss in the L1 data cache. Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0x8" }, @@ -154,6 +158,7 @@ "Data_LA": "1", "EventCode": "0xd1", "EventName": "MEM_LOAD_UOPS_RETIRED.L2_HIT", + "PublicDescription": "Counts the number of load uops retired that hit in the L2 cache. Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0x2" }, @@ -163,6 +168,7 @@ "Data_LA": "1", "EventCode": "0xd1", "EventName": "MEM_LOAD_UOPS_RETIRED.L2_MISS", + "PublicDescription": "Counts the number of load uops retired that miss in the L2 cache. Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0x10" }, @@ -172,6 +178,7 @@ "Data_LA": "1", "EventCode": "0xd1", "EventName": "MEM_LOAD_UOPS_RETIRED.L3_HIT", + "PublicDescription": "Counts the number of load uops retired that hit in the L3 cache. Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0x4" }, @@ -181,6 +188,7 @@ "Data_LA": "1", "EventCode": "0xd2", "EventName": "MEM_LOAD_UOPS_RETIRED_MISC.HIT_E_F", + "PublicDescription": "Counts the number of load uops retired that hit in the L3 cache, in which a snoop was required, and non-modified data was forwarded. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x40" }, @@ -190,6 +198,7 @@ "Data_LA": "1", "EventCode": "0xd2", "EventName": "MEM_LOAD_UOPS_RETIRED_MISC.L3_MISS", + "PublicDescription": "Counts the number of load uops retired that miss in the L3 cache. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x20" }, @@ -231,7 +240,7 @@ "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_UOPS_RETIRED.ALL_LOADS", - "PublicDescription": "Counts the total number of load uops retired.", + "PublicDescription": "Counts the total number of load uops retired. Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0x81" }, @@ -241,7 +250,7 @@ "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_UOPS_RETIRED.ALL_STORES", - "PublicDescription": "Counts the total number of store uops retired.", + "PublicDescription": "Counts the total number of store uops retired. Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0x82" }, @@ -253,7 +262,7 @@ "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_128", "MSRIndex": "0x3F6", "MSRValue": "0x80", - "PublicDescription": "Counts the number of tagged loads with an instruction latency that exceeds or equals the threshold of 128 cycles as defined in MEC_CR_PEBS_LD_LAT_THRESHOLD (3F6H). Only counts with PEBS enabled. If a PEBS record is generated, will populate the PEBS Latency and PEBS Data Source fields accordingly.", + "PublicDescription": "Counts the number of tagged loads with an instruction latency that exceeds or equals the threshold of 128 cycles as defined in MEC_CR_PEBS_LD_LAT_THRESHOLD (3F6H). Only counts with PEBS enabled. If a PEBS record is generated, will populate the PEBS Latency and PEBS Data Source fields accordingly. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x5" }, @@ -265,7 +274,7 @@ "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_16", "MSRIndex": "0x3F6", "MSRValue": "0x10", - "PublicDescription": "Counts the number of tagged loads with an instruction latency that exceeds or equals the threshold of 16 cycles as defined in MEC_CR_PEBS_LD_LAT_THRESHOLD (3F6H). Only counts with PEBS enabled. If a PEBS record is generated, will populate the PEBS Latency and PEBS Data Source fields accordingly.", + "PublicDescription": "Counts the number of tagged loads with an instruction latency that exceeds or equals the threshold of 16 cycles as defined in MEC_CR_PEBS_LD_LAT_THRESHOLD (3F6H). Only counts with PEBS enabled. If a PEBS record is generated, will populate the PEBS Latency and PEBS Data Source fields accordingly. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x5" }, @@ -277,7 +286,7 @@ "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_256", "MSRIndex": "0x3F6", "MSRValue": "0x100", - "PublicDescription": "Counts the number of tagged loads with an instruction latency that exceeds or equals the threshold of 256 cycles as defined in MEC_CR_PEBS_LD_LAT_THRESHOLD (3F6H). Only counts with PEBS enabled. If a PEBS record is generated, will populate the PEBS Latency and PEBS Data Source fields accordingly.", + "PublicDescription": "Counts the number of tagged loads with an instruction latency that exceeds or equals the threshold of 256 cycles as defined in MEC_CR_PEBS_LD_LAT_THRESHOLD (3F6H). Only counts with PEBS enabled. If a PEBS record is generated, will populate the PEBS Latency and PEBS Data Source fields accordingly. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x5" }, @@ -289,7 +298,7 @@ "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_32", "MSRIndex": "0x3F6", "MSRValue": "0x20", - "PublicDescription": "Counts the number of tagged loads with an instruction latency that exceeds or equals the threshold of 32 cycles as defined in MEC_CR_PEBS_LD_LAT_THRESHOLD (3F6H). Only counts with PEBS enabled. If a PEBS record is generated, will populate the PEBS Latency and PEBS Data Source fields accordingly.", + "PublicDescription": "Counts the number of tagged loads with an instruction latency that exceeds or equals the threshold of 32 cycles as defined in MEC_CR_PEBS_LD_LAT_THRESHOLD (3F6H). Only counts with PEBS enabled. If a PEBS record is generated, will populate the PEBS Latency and PEBS Data Source fields accordingly. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x5" }, @@ -301,7 +310,7 @@ "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_4", "MSRIndex": "0x3F6", "MSRValue": "0x4", - "PublicDescription": "Counts the number of tagged loads with an instruction latency that exceeds or equals the threshold of 4 cycles as defined in MEC_CR_PEBS_LD_LAT_THRESHOLD (3F6H). Only counts with PEBS enabled. If a PEBS record is generated, will populate the PEBS Latency and PEBS Data Source fields accordingly.", + "PublicDescription": "Counts the number of tagged loads with an instruction latency that exceeds or equals the threshold of 4 cycles as defined in MEC_CR_PEBS_LD_LAT_THRESHOLD (3F6H). Only counts with PEBS enabled. If a PEBS record is generated, will populate the PEBS Latency and PEBS Data Source fields accordingly. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x5" }, @@ -313,7 +322,7 @@ "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_512", "MSRIndex": "0x3F6", "MSRValue": "0x200", - "PublicDescription": "Counts the number of tagged loads with an instruction latency that exceeds or equals the threshold of 512 cycles as defined in MEC_CR_PEBS_LD_LAT_THRESHOLD (3F6H). Only counts with PEBS enabled. If a PEBS record is generated, will populate the PEBS Latency and PEBS Data Source fields accordingly.", + "PublicDescription": "Counts the number of tagged loads with an instruction latency that exceeds or equals the threshold of 512 cycles as defined in MEC_CR_PEBS_LD_LAT_THRESHOLD (3F6H). Only counts with PEBS enabled. If a PEBS record is generated, will populate the PEBS Latency and PEBS Data Source fields accordingly. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x5" }, @@ -325,7 +334,7 @@ "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_64", "MSRIndex": "0x3F6", "MSRValue": "0x40", - "PublicDescription": "Counts the number of tagged loads with an instruction latency that exceeds or equals the threshold of 64 cycles as defined in MEC_CR_PEBS_LD_LAT_THRESHOLD (3F6H). Only counts with PEBS enabled. If a PEBS record is generated, will populate the PEBS Latency and PEBS Data Source fields accordingly.", + "PublicDescription": "Counts the number of tagged loads with an instruction latency that exceeds or equals the threshold of 64 cycles as defined in MEC_CR_PEBS_LD_LAT_THRESHOLD (3F6H). Only counts with PEBS enabled. If a PEBS record is generated, will populate the PEBS Latency and PEBS Data Source fields accordingly. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x5" }, @@ -337,7 +346,7 @@ "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_8", "MSRIndex": "0x3F6", "MSRValue": "0x8", - "PublicDescription": "Counts the number of tagged loads with an instruction latency that exceeds or equals the threshold of 8 cycles as defined in MEC_CR_PEBS_LD_LAT_THRESHOLD (3F6H). Only counts with PEBS enabled. If a PEBS record is generated, will populate the PEBS Latency and PEBS Data Source fields accordingly.", + "PublicDescription": "Counts the number of tagged loads with an instruction latency that exceeds or equals the threshold of 8 cycles as defined in MEC_CR_PEBS_LD_LAT_THRESHOLD (3F6H). Only counts with PEBS enabled. If a PEBS record is generated, will populate the PEBS Latency and PEBS Data Source fields accordingly. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x5" }, @@ -347,6 +356,7 @@ "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_UOPS_RETIRED.LOCK_LOADS", + "PublicDescription": "Counts the number of load uops retired that performed one or more locks. Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0x21" }, @@ -356,6 +366,7 @@ "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_UOPS_RETIRED.SPLIT_LOADS", + "PublicDescription": "Counts the number of retired split load uops. Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0x41" }, @@ -365,6 +376,7 @@ "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_UOPS_RETIRED.STLB_MISS", + "PublicDescription": "Counts the total number of load and store uops retired that missed in the second level TLB. Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0x13" }, @@ -374,6 +386,7 @@ "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_UOPS_RETIRED.STLB_MISS_LOADS", + "PublicDescription": "Counts the number of load ops retired that miss in the second Level TLB. Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0x11" }, @@ -383,6 +396,7 @@ "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_UOPS_RETIRED.STLB_MISS_STORES", + "PublicDescription": "Counts the number of store ops retired that miss in the second level TLB. Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0x12" }, @@ -392,17 +406,40 @@ "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_UOPS_RETIRED.STORE_LATENCY", - "PublicDescription": "Counts the number of stores uops retired. Counts with or without PEBS enabled. If PEBS is enabled and a PEBS record is generated, will populate PEBS Latency and PEBS Data Source fields accordingly.", + "PublicDescription": "Counts the number of stores uops retired. Counts with or without PEBS enabled. If PEBS is enabled and a PEBS record is generated, will populate PEBS Latency and PEBS Data Source fields accordingly. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x6" }, { + "BriefDescription": "Counts modified writebacks from L1 cache and L2 cache that have any type of response.", + "Counter": "0,1,2,3,4,5", + "EventCode": "0xB7", + "EventName": "OCR.COREWB_M.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x10008", + "PublicDescription": "Counts modified writebacks from L1 cache and L2 cache that have any type of response. Available PDIST counters: 0", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that have any type of response.", + "Counter": "0,1,2,3,4,5", + "EventCode": "0xB7", + "EventName": "OCR.DEMAND_CODE_RD.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x10004", + "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that have any type of response. Available PDIST counters: 0", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were supplied by the L3 cache.", "Counter": "0,1,2,3,4,5", "EventCode": "0xB7", "EventName": "OCR.DEMAND_CODE_RD.L3_HIT", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x1F803C0004", + "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were supplied by the L3 cache. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -413,6 +450,7 @@ "EventName": "OCR.DEMAND_CODE_RD.L3_HIT.SNOOP_HITM", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x10003C0004", + "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were supplied by the L3 cache where a snoop was sent, the snoop hit, and modified data was forwarded. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -423,6 +461,7 @@ "EventName": "OCR.DEMAND_CODE_RD.L3_HIT.SNOOP_HIT_NO_FWD", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x4003C0004", + "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were supplied by the L3 cache where a snoop was sent, the snoop hit, but no data was forwarded. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -433,6 +472,18 @@ "EventName": "OCR.DEMAND_CODE_RD.L3_HIT.SNOOP_HIT_WITH_FWD", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x8003C0004", + "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were supplied by the L3 cache where a snoop was sent, the snoop hit, and non-modified data was forwarded. Available PDIST counters: 0", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts demand data reads that have any type of response.", + "Counter": "0,1,2,3,4,5", + "EventCode": "0xB7", + "EventName": "OCR.DEMAND_DATA_RD.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x10001", + "PublicDescription": "Counts demand data reads that have any type of response. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -443,6 +494,7 @@ "EventName": "OCR.DEMAND_DATA_RD.L3_HIT", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x1F803C0001", + "PublicDescription": "Counts demand data reads that were supplied by the L3 cache. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -453,6 +505,7 @@ "EventName": "OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x10003C0001", + "PublicDescription": "Counts demand data reads that were supplied by the L3 cache where a snoop was sent, the snoop hit, and modified data was forwarded. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -463,6 +516,7 @@ "EventName": "OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_NO_FWD", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x4003C0001", + "PublicDescription": "Counts demand data reads that were supplied by the L3 cache where a snoop was sent, the snoop hit, but no data was forwarded. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -473,6 +527,18 @@ "EventName": "OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x8003C0001", + "PublicDescription": "Counts demand data reads that were supplied by the L3 cache where a snoop was sent, the snoop hit, and non-modified data was forwarded. Available PDIST counters: 0", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that have any type of response.", + "Counter": "0,1,2,3,4,5", + "EventCode": "0xB7", + "EventName": "OCR.DEMAND_RFO.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x10002", + "PublicDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that have any type of response. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -483,6 +549,7 @@ "EventName": "OCR.DEMAND_RFO.L3_HIT", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x1F803C0002", + "PublicDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that were supplied by the L3 cache. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -493,6 +560,7 @@ "EventName": "OCR.DEMAND_RFO.L3_HIT.SNOOP_HITM", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x10003C0002", + "PublicDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that were supplied by the L3 cache where a snoop was sent, the snoop hit, and modified data was forwarded. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -503,6 +571,7 @@ "EventName": "OCR.DEMAND_RFO.L3_HIT.SNOOP_HIT_NO_FWD", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x4003C0002", + "PublicDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that were supplied by the L3 cache where a snoop was sent, the snoop hit, but no data was forwarded. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -513,6 +582,18 @@ "EventName": "OCR.DEMAND_RFO.L3_HIT.SNOOP_HIT_WITH_FWD", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x8003C0002", + "PublicDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that were supplied by the L3 cache where a snoop was sent, the snoop hit, and non-modified data was forwarded. Available PDIST counters: 0", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts L1 data cache software prefetches which include T0/T1/T2 and NTA (except PREFETCHW) that have any type of response.", + "Counter": "0,1,2,3,4,5", + "EventCode": "0xB7", + "EventName": "OCR.SWPF_RD.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x14000", + "PublicDescription": "Counts L1 data cache software prefetches which include T0/T1/T2 and NTA (except PREFETCHW) that have any type of response. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -523,6 +604,7 @@ "EventName": "OCR.SWPF_RD.L3_HIT", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x1F803C4000", + "PublicDescription": "Counts L1 data cache software prefetches which include T0/T1/T2 and NTA (except PREFETCHW) that were supplied by the L3 cache. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -533,6 +615,7 @@ "EventName": "OCR.SWPF_RD.L3_HIT.SNOOP_HITM", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x10003C4000", + "PublicDescription": "Counts L1 data cache software prefetches which include T0/T1/T2 and NTA (except PREFETCHW) that were supplied by the L3 cache where a snoop was sent, the snoop hit, and modified data was forwarded. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -543,6 +626,7 @@ "EventName": "OCR.SWPF_RD.L3_HIT.SNOOP_HIT_NO_FWD", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x4003C4000", + "PublicDescription": "Counts L1 data cache software prefetches which include T0/T1/T2 and NTA (except PREFETCHW) that were supplied by the L3 cache where a snoop was sent, the snoop hit, but no data was forwarded. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -553,6 +637,7 @@ "EventName": "OCR.SWPF_RD.L3_HIT.SNOOP_HIT_WITH_FWD", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x8003C4000", + "PublicDescription": "Counts L1 data cache software prefetches which include T0/T1/T2 and NTA (except PREFETCHW) that were supplied by the L3 cache where a snoop was sent, the snoop hit, and non-modified data was forwarded. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, diff --git a/tools/perf/pmu-events/arch/x86/alderlaken/floating-point.json b/tools/perf/pmu-events/arch/x86/alderlaken/floating-point.json index ed963fcb6485..f44da31ff1f1 100644 --- a/tools/perf/pmu-events/arch/x86/alderlaken/floating-point.json +++ b/tools/perf/pmu-events/arch/x86/alderlaken/floating-point.json @@ -29,6 +29,7 @@ "Counter": "0,1,2,3,4,5", "EventCode": "0xc2", "EventName": "UOPS_RETIRED.FPDIV", + "PublicDescription": "Counts the number of floating point divide uops retired (x87 and SSE, including x87 sqrt). Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x8" } diff --git a/tools/perf/pmu-events/arch/x86/alderlaken/memory.json b/tools/perf/pmu-events/arch/x86/alderlaken/memory.json index 3b46b048dfb2..049c5e2630d7 100644 --- a/tools/perf/pmu-events/arch/x86/alderlaken/memory.json +++ b/tools/perf/pmu-events/arch/x86/alderlaken/memory.json @@ -57,12 +57,35 @@ "UMask": "0x2" }, { + "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were supplied by DRAM.", + "Counter": "0,1,2,3,4,5", + "EventCode": "0xB7", + "EventName": "OCR.DEMAND_CODE_RD.DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x784000004", + "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were supplied by DRAM. Available PDIST counters: 0", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were not supplied by the L3 cache.", "Counter": "0,1,2,3,4,5", "EventCode": "0xB7", "EventName": "OCR.DEMAND_CODE_RD.L3_MISS", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x3F84400004", + "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were not supplied by the L3 cache. Available PDIST counters: 0", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts demand data reads that were supplied by DRAM.", + "Counter": "0,1,2,3,4,5", + "EventCode": "0xB7", + "EventName": "OCR.DEMAND_DATA_RD.DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x784000001", + "PublicDescription": "Counts demand data reads that were supplied by DRAM. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -73,6 +96,7 @@ "EventName": "OCR.DEMAND_DATA_RD.L3_MISS", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x3F84400001", + "PublicDescription": "Counts demand data reads that were not supplied by the L3 cache. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -83,6 +107,18 @@ "EventName": "OCR.DEMAND_DATA_RD.L3_MISS_LOCAL", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x3F84400001", + "PublicDescription": "Counts demand data reads that were not supplied by the L3 cache. [L3_MISS_LOCAL is alias to L3_MISS] Available PDIST counters: 0", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that were supplied by DRAM.", + "Counter": "0,1,2,3,4,5", + "EventCode": "0xB7", + "EventName": "OCR.DEMAND_RFO.DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x784000002", + "PublicDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that were supplied by DRAM. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -93,6 +129,7 @@ "EventName": "OCR.DEMAND_RFO.L3_MISS", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x3F84400002", + "PublicDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that were not supplied by the L3 cache. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -103,6 +140,18 @@ "EventName": "OCR.DEMAND_RFO.L3_MISS_LOCAL", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x3F84400002", + "PublicDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that were not supplied by the L3 cache. [L3_MISS_LOCAL is alias to L3_MISS] Available PDIST counters: 0", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts L1 data cache software prefetches which include T0/T1/T2 and NTA (except PREFETCHW) that were supplied by DRAM.", + "Counter": "0,1,2,3,4,5", + "EventCode": "0xB7", + "EventName": "OCR.SWPF_RD.DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x784004000", + "PublicDescription": "Counts L1 data cache software prefetches which include T0/T1/T2 and NTA (except PREFETCHW) that were supplied by DRAM. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -113,6 +162,7 @@ "EventName": "OCR.SWPF_RD.L3_MISS", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x3F84404000", + "PublicDescription": "Counts L1 data cache software prefetches which include T0/T1/T2 and NTA (except PREFETCHW) that were not supplied by the L3 cache. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" } diff --git a/tools/perf/pmu-events/arch/x86/alderlaken/other.json b/tools/perf/pmu-events/arch/x86/alderlaken/other.json index f8c21b7f8f40..8c2b5a284f2a 100644 --- a/tools/perf/pmu-events/arch/x86/alderlaken/other.json +++ b/tools/perf/pmu-events/arch/x86/alderlaken/other.json @@ -5,86 +5,18 @@ "Deprecated": "1", "EventCode": "0xe4", "EventName": "LBR_INSERTS.ANY", + "PublicDescription": "This event is deprecated. [This event is alias to MISC_RETIRED.LBR_INSERTS] Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x1" }, { - "BriefDescription": "Counts modified writebacks from L1 cache and L2 cache that have any type of response.", - "Counter": "0,1,2,3,4,5", - "EventCode": "0xB7", - "EventName": "OCR.COREWB_M.ANY_RESPONSE", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x10008", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that have any type of response.", - "Counter": "0,1,2,3,4,5", - "EventCode": "0xB7", - "EventName": "OCR.DEMAND_CODE_RD.ANY_RESPONSE", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x10004", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were supplied by DRAM.", - "Counter": "0,1,2,3,4,5", - "EventCode": "0xB7", - "EventName": "OCR.DEMAND_CODE_RD.DRAM", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x784000004", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts demand data reads that have any type of response.", - "Counter": "0,1,2,3,4,5", - "EventCode": "0xB7", - "EventName": "OCR.DEMAND_DATA_RD.ANY_RESPONSE", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x10001", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts demand data reads that were supplied by DRAM.", - "Counter": "0,1,2,3,4,5", - "EventCode": "0xB7", - "EventName": "OCR.DEMAND_DATA_RD.DRAM", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x784000001", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that have any type of response.", - "Counter": "0,1,2,3,4,5", - "EventCode": "0xB7", - "EventName": "OCR.DEMAND_RFO.ANY_RESPONSE", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x10002", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that were supplied by DRAM.", - "Counter": "0,1,2,3,4,5", - "EventCode": "0xB7", - "EventName": "OCR.DEMAND_RFO.DRAM", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x784000002", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { "BriefDescription": "Counts streaming stores which modify a full 64 byte cacheline that have any type of response.", "Counter": "0,1,2,3,4,5", "EventCode": "0xB7", "EventName": "OCR.FULL_STREAMING_WR.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x800000010000", + "PublicDescription": "Counts streaming stores which modify a full 64 byte cacheline that have any type of response. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -95,6 +27,7 @@ "EventName": "OCR.PARTIAL_STREAMING_WR.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x400000010000", + "PublicDescription": "Counts streaming stores which modify only part of a 64 byte cacheline that have any type of response. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -105,35 +38,8 @@ "EventName": "OCR.STREAMING_WR.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x10800", + "PublicDescription": "Counts streaming stores that have any type of response. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" - }, - { - "BriefDescription": "Counts L1 data cache software prefetches which include T0/T1/T2 and NTA (except PREFETCHW) that have any type of response.", - "Counter": "0,1,2,3,4,5", - "EventCode": "0xB7", - "EventName": "OCR.SWPF_RD.ANY_RESPONSE", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x14000", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts L1 data cache software prefetches which include T0/T1/T2 and NTA (except PREFETCHW) that were supplied by DRAM.", - "Counter": "0,1,2,3,4,5", - "EventCode": "0xB7", - "EventName": "OCR.SWPF_RD.DRAM", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x784004000", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts the number of issue slots in a UMWAIT or TPAUSE instruction where no uop issues due to the instruction putting the CPU into the C0.1 activity state. For Tremont, UMWAIT and TPAUSE will only put the CPU into C0.1 activity state (not C0.2 activity state)", - "Counter": "0,1,2,3,4,5", - "EventCode": "0x75", - "EventName": "SERIALIZATION.C01_MS_SCB", - "SampleAfterValue": "200003", - "UMask": "0x4" } ] diff --git a/tools/perf/pmu-events/arch/x86/alderlaken/pipeline.json b/tools/perf/pmu-events/arch/x86/alderlaken/pipeline.json index 713ebc21cec0..9616bf0e9f1f 100644 --- a/tools/perf/pmu-events/arch/x86/alderlaken/pipeline.json +++ b/tools/perf/pmu-events/arch/x86/alderlaken/pipeline.json @@ -54,7 +54,7 @@ "Counter": "0,1,2,3,4,5", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.ALL_BRANCHES", - "PublicDescription": "Counts the total number of instructions in which the instruction pointer (IP) of the processor is resteered due to a branch instruction and the branch instruction successfully retires. All branch type instructions are accounted for.", + "PublicDescription": "Counts the total number of instructions in which the instruction pointer (IP) of the processor is resteered due to a branch instruction and the branch instruction successfully retires. All branch type instructions are accounted for. Available PDIST counters: 0", "SampleAfterValue": "200003" }, { @@ -63,6 +63,7 @@ "Deprecated": "1", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.CALL", + "PublicDescription": "This event is deprecated. Refer to new event BR_INST_RETIRED.NEAR_CALL Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0xf9" }, @@ -71,6 +72,7 @@ "Counter": "0,1,2,3,4,5", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.COND", + "PublicDescription": "Counts the number of retired JCC (Jump on Conditional Code) branch instructions retired, includes both taken and not taken branches. Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0x7e" }, @@ -79,6 +81,7 @@ "Counter": "0,1,2,3,4,5", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.COND_TAKEN", + "PublicDescription": "Counts the number of taken JCC (Jump on Conditional Code) branch instructions retired. Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0xfe" }, @@ -87,6 +90,7 @@ "Counter": "0,1,2,3,4,5", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.FAR_BRANCH", + "PublicDescription": "Counts the number of far branch instructions retired, includes far jump, far call and return, and interrupt call and return. Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0xbf" }, @@ -95,6 +99,7 @@ "Counter": "0,1,2,3,4,5", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.INDIRECT", + "PublicDescription": "Counts the number of near indirect JMP and near indirect CALL branch instructions retired. Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0xeb" }, @@ -103,6 +108,7 @@ "Counter": "0,1,2,3,4,5", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.INDIRECT_CALL", + "PublicDescription": "Counts the number of near indirect CALL branch instructions retired. Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0xfb" }, @@ -112,6 +118,7 @@ "Deprecated": "1", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.IND_CALL", + "PublicDescription": "This event is deprecated. Refer to new event BR_INST_RETIRED.INDIRECT_CALL Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0xfb" }, @@ -121,6 +128,7 @@ "Deprecated": "1", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.JCC", + "PublicDescription": "This event is deprecated. Refer to new event BR_INST_RETIRED.COND Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0x7e" }, @@ -129,6 +137,7 @@ "Counter": "0,1,2,3,4,5", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.NEAR_CALL", + "PublicDescription": "Counts the number of near CALL branch instructions retired. Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0xf9" }, @@ -137,6 +146,7 @@ "Counter": "0,1,2,3,4,5", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.NEAR_RETURN", + "PublicDescription": "Counts the number of near RET branch instructions retired. Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0xf7" }, @@ -145,6 +155,7 @@ "Counter": "0,1,2,3,4,5", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.NEAR_TAKEN", + "PublicDescription": "Counts the number of near taken branch instructions retired. Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0xc0" }, @@ -154,6 +165,7 @@ "Deprecated": "1", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.NON_RETURN_IND", + "PublicDescription": "This event is deprecated. Refer to new event BR_INST_RETIRED.INDIRECT Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0xeb" }, @@ -162,6 +174,7 @@ "Counter": "0,1,2,3,4,5", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.REL_CALL", + "PublicDescription": "Counts the number of near relative CALL branch instructions retired. Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0xfd" }, @@ -171,6 +184,7 @@ "Deprecated": "1", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.RETURN", + "PublicDescription": "This event is deprecated. Refer to new event BR_INST_RETIRED.NEAR_RETURN Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0xf7" }, @@ -180,6 +194,7 @@ "Deprecated": "1", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.TAKEN_JCC", + "PublicDescription": "This event is deprecated. Refer to new event BR_INST_RETIRED.COND_TAKEN Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0xfe" }, @@ -188,7 +203,7 @@ "Counter": "0,1,2,3,4,5", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.ALL_BRANCHES", - "PublicDescription": "Counts the total number of mispredicted branch instructions retired. All branch type instructions are accounted for. Prediction of the branch target address enables the processor to begin executing instructions before the non-speculative execution path is known. The branch prediction unit (BPU) predicts the target address based on the instruction pointer (IP) of the branch and on the execution path through which execution reached this IP. A branch misprediction occurs when the prediction is wrong, and results in discarding all instructions executed in the speculative path and re-fetching from the correct path.", + "PublicDescription": "Counts the total number of mispredicted branch instructions retired. All branch type instructions are accounted for. Prediction of the branch target address enables the processor to begin executing instructions before the non-speculative execution path is known. The branch prediction unit (BPU) predicts the target address based on the instruction pointer (IP) of the branch and on the execution path through which execution reached this IP. A branch misprediction occurs when the prediction is wrong, and results in discarding all instructions executed in the speculative path and re-fetching from the correct path. Available PDIST counters: 0", "SampleAfterValue": "200003" }, { @@ -196,6 +211,7 @@ "Counter": "0,1,2,3,4,5", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.COND", + "PublicDescription": "Counts the number of mispredicted JCC (Jump on Conditional Code) branch instructions retired. Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0x7e" }, @@ -204,6 +220,7 @@ "Counter": "0,1,2,3,4,5", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.COND_TAKEN", + "PublicDescription": "Counts the number of mispredicted taken JCC (Jump on Conditional Code) branch instructions retired. Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0xfe" }, @@ -212,6 +229,7 @@ "Counter": "0,1,2,3,4,5", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.INDIRECT", + "PublicDescription": "Counts the number of mispredicted near indirect JMP and near indirect CALL branch instructions retired. Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0xeb" }, @@ -220,6 +238,7 @@ "Counter": "0,1,2,3,4,5", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.INDIRECT_CALL", + "PublicDescription": "Counts the number of mispredicted near indirect CALL branch instructions retired. Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0xfb" }, @@ -229,6 +248,7 @@ "Deprecated": "1", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.IND_CALL", + "PublicDescription": "This event is deprecated. Refer to new event BR_MISP_RETIRED.INDIRECT_CALL Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0xfb" }, @@ -238,6 +258,7 @@ "Deprecated": "1", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.JCC", + "PublicDescription": "This event is deprecated. Refer to new event BR_MISP_RETIRED.COND Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0x7e" }, @@ -246,6 +267,7 @@ "Counter": "0,1,2,3,4,5", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.NEAR_TAKEN", + "PublicDescription": "Counts the number of mispredicted near taken branch instructions retired. Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0x80" }, @@ -255,6 +277,7 @@ "Deprecated": "1", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.NON_RETURN_IND", + "PublicDescription": "This event is deprecated. Refer to new event BR_MISP_RETIRED.INDIRECT Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0xeb" }, @@ -263,6 +286,7 @@ "Counter": "0,1,2,3,4,5", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.RETURN", + "PublicDescription": "Counts the number of mispredicted near RET branch instructions retired. Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0xf7" }, @@ -272,6 +296,7 @@ "Deprecated": "1", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.TAKEN_JCC", + "PublicDescription": "This event is deprecated. Refer to new event BR_MISP_RETIRED.COND_TAKEN Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0xfe" }, @@ -337,7 +362,7 @@ "BriefDescription": "Counts the total number of instructions retired. (Fixed event)", "Counter": "Fixed counter 0", "EventName": "INST_RETIRED.ANY", - "PublicDescription": "Counts the total number of instructions that retired. For instructions that consist of multiple uops, this event counts the retirement of the last uop of the instruction. This event continues counting during hardware interrupts, traps, and inside interrupt handlers. This event uses fixed counter 0.", + "PublicDescription": "Counts the total number of instructions that retired. For instructions that consist of multiple uops, this event counts the retirement of the last uop of the instruction. This event continues counting during hardware interrupts, traps, and inside interrupt handlers. This event uses fixed counter 0. Available PDIST counters: 32", "SampleAfterValue": "2000003", "UMask": "0x1" }, @@ -346,7 +371,7 @@ "Counter": "0,1,2,3,4,5", "EventCode": "0xc0", "EventName": "INST_RETIRED.ANY_P", - "PublicDescription": "Counts the total number of instructions that retired. For instructions that consist of multiple uops, this event counts the retirement of the last uop of the instruction. This event continues counting during hardware interrupts, traps, and inside interrupt handlers. This event uses a programmable general purpose performance counter.", + "PublicDescription": "Counts the total number of instructions that retired. For instructions that consist of multiple uops, this event counts the retirement of the last uop of the instruction. This event continues counting during hardware interrupts, traps, and inside interrupt handlers. This event uses a programmable general purpose performance counter. Available PDIST counters: 0", "SampleAfterValue": "2000003" }, { @@ -355,6 +380,7 @@ "Deprecated": "1", "EventCode": "0x03", "EventName": "LD_BLOCKS.4K_ALIAS", + "PublicDescription": "This event is deprecated. Refer to new event LD_BLOCKS.ADDRESS_ALIAS Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x4" }, @@ -363,6 +389,7 @@ "Counter": "0,1,2,3,4,5", "EventCode": "0x03", "EventName": "LD_BLOCKS.ADDRESS_ALIAS", + "PublicDescription": "Counts the number of retired loads that are blocked because it initially appears to be store forward blocked, but subsequently is shown not to be blocked based on 4K alias check. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x4" }, @@ -371,6 +398,7 @@ "Counter": "0,1,2,3,4,5", "EventCode": "0x03", "EventName": "LD_BLOCKS.DATA_UNKNOWN", + "PublicDescription": "Counts the number of retired loads that are blocked because its address exactly matches an older store whose data is not ready. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x1" }, @@ -399,8 +427,9 @@ "UMask": "0x20" }, { - "BriefDescription": "Counts the number of machine clears that flush the pipeline and restart the machine with the use of microcode due to SMC, MEMORY_ORDERING, FP_ASSISTS, PAGE_FAULT, DISAMBIGUATION, and FPC_VIRTUAL_TRAP.", + "BriefDescription": "This event is deprecated.", "Counter": "0,1,2,3,4,5", + "Deprecated": "1", "EventCode": "0xc3", "EventName": "MACHINE_CLEARS.SLOW", "SampleAfterValue": "20003", @@ -419,11 +448,19 @@ "Counter": "0,1,2,3,4,5", "EventCode": "0xe4", "EventName": "MISC_RETIRED.LBR_INSERTS", - "PublicDescription": "Counts the number of LBR entries recorded. Requires LBRs to be enabled in IA32_LBR_CTL. This event is PDIR on GP0 and NPEBS on all other GPs [This event is alias to LBR_INSERTS.ANY]", + "PublicDescription": "Counts the number of LBR entries recorded. Requires LBRs to be enabled in IA32_LBR_CTL. This event is PDIR on GP0 and NPEBS on all other GPs [This event is alias to LBR_INSERTS.ANY] Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x1" }, { + "BriefDescription": "Counts the number of issue slots in a UMWAIT or TPAUSE instruction where no uop issues due to the instruction putting the CPU into the C0.1 activity state. For Tremont, UMWAIT and TPAUSE will only put the CPU into C0.1 activity state (not C0.2 activity state)", + "Counter": "0,1,2,3,4,5", + "EventCode": "0x75", + "EventName": "SERIALIZATION.C01_MS_SCB", + "SampleAfterValue": "200003", + "UMask": "0x4" + }, + { "BriefDescription": "Counts the number of issue slots not consumed by the backend due to a micro-sequencer (MS) scoreboard, which stalls the front-end from issuing from the UROM until a specified older uop retires.", "Counter": "0,1,2,3,4,5", "EventCode": "0x75", @@ -614,6 +651,7 @@ "Counter": "0,1,2,3,4,5", "EventCode": "0xc2", "EventName": "TOPDOWN_RETIRING.ALL", + "PublicDescription": "Counts the total number of consumed retirement slots. Available PDIST counters: 0", "SampleAfterValue": "1000003" }, { @@ -629,6 +667,7 @@ "Counter": "0,1,2,3,4,5", "EventCode": "0xc2", "EventName": "UOPS_RETIRED.ALL", + "PublicDescription": "Counts the total number of uops retired. Available PDIST counters: 0", "SampleAfterValue": "2000003" }, { @@ -636,6 +675,7 @@ "Counter": "0,1,2,3,4,5", "EventCode": "0xc2", "EventName": "UOPS_RETIRED.IDIV", + "PublicDescription": "Counts the number of integer divide uops retired. Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x10" }, @@ -644,7 +684,7 @@ "Counter": "0,1,2,3,4,5", "EventCode": "0xc2", "EventName": "UOPS_RETIRED.MS", - "PublicDescription": "Counts the number of uops that are from complex flows issued by the Microcode Sequencer (MS). This includes uops from flows due to complex instructions, faults, assists, and inserted flows.", + "PublicDescription": "Counts the number of uops that are from complex flows issued by the Microcode Sequencer (MS). This includes uops from flows due to complex instructions, faults, assists, and inserted flows. Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x1" }, @@ -653,6 +693,7 @@ "Counter": "0,1,2,3,4,5", "EventCode": "0xc2", "EventName": "UOPS_RETIRED.X87", + "PublicDescription": "Counts the number of x87 uops retired, includes those in MS flows. Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x2" } diff --git a/tools/perf/pmu-events/arch/x86/alderlaken/virtual-memory.json b/tools/perf/pmu-events/arch/x86/alderlaken/virtual-memory.json index d9c737a17df0..c348046696bf 100644 --- a/tools/perf/pmu-events/arch/x86/alderlaken/virtual-memory.json +++ b/tools/perf/pmu-events/arch/x86/alderlaken/virtual-memory.json @@ -57,6 +57,7 @@ "Deprecated": "1", "EventCode": "0xd0", "EventName": "MEM_UOPS_RETIRED.DTLB_MISS", + "PublicDescription": "This event is deprecated. Refer to new event MEM_UOPS_RETIRED.STLB_MISS Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0x13" }, @@ -67,6 +68,7 @@ "Deprecated": "1", "EventCode": "0xd0", "EventName": "MEM_UOPS_RETIRED.DTLB_MISS_LOADS", + "PublicDescription": "This event is deprecated. Refer to new event MEM_UOPS_RETIRED.STLB_MISS_LOADS Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0x11" }, @@ -77,6 +79,7 @@ "Deprecated": "1", "EventCode": "0xd0", "EventName": "MEM_UOPS_RETIRED.DTLB_MISS_STORES", + "PublicDescription": "This event is deprecated. Refer to new event MEM_UOPS_RETIRED.STLB_MISS_STORES Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0x12" } diff --git a/tools/perf/pmu-events/arch/x86/arrowlake/arl-metrics.json b/tools/perf/pmu-events/arch/x86/arrowlake/arl-metrics.json index 7ddb89dd1871..b22a02450e6c 100644 --- a/tools/perf/pmu-events/arch/x86/arrowlake/arl-metrics.json +++ b/tools/perf/pmu-events/arch/x86/arrowlake/arl-metrics.json @@ -75,7 +75,7 @@ "MetricExpr": "tma_core_bound", "MetricGroup": "TopdownL3;tma_L3_group;tma_core_bound_group", "MetricName": "tma_allocation_restriction", - "MetricThreshold": "(tma_allocation_restriction >0.10) & ((tma_core_bound >0.10) & ((tma_backend_bound >0.10)))", + "MetricThreshold": "tma_allocation_restriction > 0.1 & (tma_core_bound > 0.1 & tma_backend_bound > 0.1)", "ScaleUnit": "100%", "Unit": "cpu_atom" }, @@ -85,7 +85,7 @@ "MetricExpr": "cpu_atom@TOPDOWN_BE_BOUND.ALL_P@ / (8 * cpu_atom@CPU_CLK_UNHALTED.CORE@)", "MetricGroup": "Default;TopdownL1;tma_L1_group", "MetricName": "tma_backend_bound", - "MetricThreshold": "(tma_backend_bound >0.10)", + "MetricThreshold": "tma_backend_bound > 0.1", "MetricgroupNoGroup": "TopdownL1;Default", "PublicDescription": "Counts the total number of issue slots that were not consumed by the backend due to backend stalls. Note that uops must be available for consumption in order for this event to count. If a uop is not available (IQ is empty), this event will not count", "ScaleUnit": "100%", @@ -97,7 +97,7 @@ "MetricExpr": "cpu_atom@TOPDOWN_BAD_SPECULATION.ALL_P@ / (8 * cpu_atom@CPU_CLK_UNHALTED.CORE@)", "MetricGroup": "Default;TopdownL1;tma_L1_group", "MetricName": "tma_bad_speculation", - "MetricThreshold": "(tma_bad_speculation >0.15)", + "MetricThreshold": "tma_bad_speculation > 0.15", "MetricgroupNoGroup": "TopdownL1;Default", "PublicDescription": "Counts the total number of issue slots that were not consumed by the backend because allocation is stalled due to a mispredicted jump or a machine clear. Only issue slots wasted due to fast nukes such as memory ordering nukes are counted. Other nukes are not accounted for. Counts all issue slots blocked during this recovery window including relevant microcode flows and while uops are not yet available in the instruction queue (IQ). Also includes the issue slots that were consumed by the backend but were thrown away because they were younger than the mispredict or machine clear.", "ScaleUnit": "100%", @@ -108,7 +108,7 @@ "MetricExpr": "cpu_atom@TOPDOWN_FE_BOUND.BRANCH_DETECT@ / (8 * cpu_atom@CPU_CLK_UNHALTED.CORE@)", "MetricGroup": "TopdownL3;tma_L3_group;tma_ifetch_latency_group", "MetricName": "tma_branch_detect", - "MetricThreshold": "(tma_branch_detect >0.05) & ((tma_ifetch_latency >0.15) & ((tma_frontend_bound >0.20)))", + "MetricThreshold": "tma_branch_detect > 0.05 & (tma_ifetch_latency > 0.15 & tma_frontend_bound > 0.2)", "PublicDescription": "Counts the number of issue slots that were not delivered by the frontend due to BACLEARS, which occurs when the Branch Target Buffer (BTB) prediction or lack thereof, was corrected by a later branch predictor in the frontend. Includes BACLEARS due to all branch types including conditional and unconditional jumps, returns, and indirect branches.", "ScaleUnit": "100%", "Unit": "cpu_atom" @@ -118,7 +118,7 @@ "MetricExpr": "cpu_atom@TOPDOWN_BAD_SPECULATION.MISPREDICT@ / (8 * cpu_atom@CPU_CLK_UNHALTED.CORE@)", "MetricGroup": "TopdownL2;tma_L2_group;tma_bad_speculation_group", "MetricName": "tma_branch_mispredicts", - "MetricThreshold": "(tma_branch_mispredicts >0.05) & ((tma_bad_speculation >0.15))", + "MetricThreshold": "tma_branch_mispredicts > 0.05 & tma_bad_speculation > 0.15", "MetricgroupNoGroup": "TopdownL2", "ScaleUnit": "100%", "Unit": "cpu_atom" @@ -128,7 +128,7 @@ "MetricExpr": "cpu_atom@TOPDOWN_FE_BOUND.BRANCH_RESTEER@ / (8 * cpu_atom@CPU_CLK_UNHALTED.CORE@)", "MetricGroup": "TopdownL3;tma_L3_group;tma_ifetch_latency_group", "MetricName": "tma_branch_resteer", - "MetricThreshold": "(tma_branch_resteer >0.05) & ((tma_ifetch_latency >0.15) & ((tma_frontend_bound >0.20)))", + "MetricThreshold": "tma_branch_resteer > 0.05 & (tma_ifetch_latency > 0.15 & tma_frontend_bound > 0.2)", "ScaleUnit": "100%", "Unit": "cpu_atom" }, @@ -137,7 +137,7 @@ "MetricExpr": "cpu_atom@TOPDOWN_FE_BOUND.CISC@ / (8 * cpu_atom@CPU_CLK_UNHALTED.CORE@)", "MetricGroup": "TopdownL3;tma_L3_group;tma_ifetch_bandwidth_group", "MetricName": "tma_cisc", - "MetricThreshold": "(tma_cisc >0.05) & ((tma_ifetch_bandwidth >0.10) & ((tma_frontend_bound >0.20)))", + "MetricThreshold": "tma_cisc > 0.05 & (tma_ifetch_bandwidth > 0.1 & tma_frontend_bound > 0.2)", "ScaleUnit": "100%", "Unit": "cpu_atom" }, @@ -146,7 +146,7 @@ "MetricExpr": "cpu_atom@TOPDOWN_BE_BOUND.ALLOC_RESTRICTIONS@ / (8 * cpu_atom@CPU_CLK_UNHALTED.CORE@)", "MetricGroup": "TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_core_bound", - "MetricThreshold": "(tma_core_bound >0.10) & ((tma_backend_bound >0.10))", + "MetricThreshold": "tma_core_bound > 0.1 & tma_backend_bound > 0.1", "MetricgroupNoGroup": "TopdownL2", "ScaleUnit": "100%", "Unit": "cpu_atom" @@ -156,7 +156,7 @@ "MetricExpr": "cpu_atom@TOPDOWN_FE_BOUND.DECODE@ / (8 * cpu_atom@CPU_CLK_UNHALTED.CORE@)", "MetricGroup": "TopdownL3;tma_L3_group;tma_ifetch_bandwidth_group", "MetricName": "tma_decode", - "MetricThreshold": "(tma_decode >0.05) & ((tma_ifetch_bandwidth >0.10) & ((tma_frontend_bound >0.20)))", + "MetricThreshold": "tma_decode > 0.05 & (tma_ifetch_bandwidth > 0.1 & tma_frontend_bound > 0.2)", "ScaleUnit": "100%", "Unit": "cpu_atom" }, @@ -165,7 +165,7 @@ "MetricExpr": "cpu_atom@TOPDOWN_BAD_SPECULATION.FASTNUKE@ / (8 * cpu_atom@CPU_CLK_UNHALTED.CORE@)", "MetricGroup": "TopdownL3;tma_L3_group;tma_machine_clears_group", "MetricName": "tma_fast_nuke", - "MetricThreshold": "(tma_fast_nuke >0.05) & ((tma_machine_clears >0.05) & ((tma_bad_speculation >0.15)))", + "MetricThreshold": "tma_fast_nuke > 0.05 & (tma_machine_clears > 0.05 & tma_bad_speculation > 0.15)", "ScaleUnit": "100%", "Unit": "cpu_atom" }, @@ -175,7 +175,7 @@ "MetricExpr": "cpu_atom@TOPDOWN_FE_BOUND.ALL@ / (8 * cpu_atom@CPU_CLK_UNHALTED.CORE@)", "MetricGroup": "Default;TopdownL1;tma_L1_group", "MetricName": "tma_frontend_bound", - "MetricThreshold": "(tma_frontend_bound >0.20)", + "MetricThreshold": "tma_frontend_bound > 0.2", "MetricgroupNoGroup": "TopdownL1;Default", "ScaleUnit": "100%", "Unit": "cpu_atom" @@ -185,7 +185,7 @@ "MetricExpr": "cpu_atom@TOPDOWN_FE_BOUND.ICACHE@ / (8 * cpu_atom@CPU_CLK_UNHALTED.CORE@)", "MetricGroup": "TopdownL3;tma_L3_group;tma_ifetch_latency_group", "MetricName": "tma_icache_misses", - "MetricThreshold": "(tma_icache_misses >0.05) & ((tma_ifetch_latency >0.15) & ((tma_frontend_bound >0.20)))", + "MetricThreshold": "tma_icache_misses > 0.05 & (tma_ifetch_latency > 0.15 & tma_frontend_bound > 0.2)", "ScaleUnit": "100%", "Unit": "cpu_atom" }, @@ -194,7 +194,7 @@ "MetricExpr": "cpu_atom@TOPDOWN_FE_BOUND.FRONTEND_BANDWIDTH@ / (8 * cpu_atom@CPU_CLK_UNHALTED.CORE@)", "MetricGroup": "TopdownL2;tma_L2_group;tma_frontend_bound_group", "MetricName": "tma_ifetch_bandwidth", - "MetricThreshold": "(tma_ifetch_bandwidth >0.10) & ((tma_frontend_bound >0.20))", + "MetricThreshold": "tma_ifetch_bandwidth > 0.1 & tma_frontend_bound > 0.2", "MetricgroupNoGroup": "TopdownL2", "ScaleUnit": "100%", "Unit": "cpu_atom" @@ -204,7 +204,7 @@ "MetricExpr": "cpu_atom@TOPDOWN_FE_BOUND.FRONTEND_LATENCY@ / (8 * cpu_atom@CPU_CLK_UNHALTED.CORE@)", "MetricGroup": "TopdownL2;tma_L2_group;tma_frontend_bound_group", "MetricName": "tma_ifetch_latency", - "MetricThreshold": "(tma_ifetch_latency >0.15) & ((tma_frontend_bound >0.20))", + "MetricThreshold": "tma_ifetch_latency > 0.15 & tma_frontend_bound > 0.2", "MetricgroupNoGroup": "TopdownL2", "ScaleUnit": "100%", "Unit": "cpu_atom" @@ -590,7 +590,7 @@ "BriefDescription": "PerfMon Event Multiplexing accuracy indicator", "MetricExpr": "cpu_atom@CPU_CLK_UNHALTED.CORE_P@ / cpu_atom@CPU_CLK_UNHALTED.CORE@", "MetricName": "tma_info_system_mux", - "MetricThreshold": "((tma_info_system_mux > 1.1)|(tma_info_system_mux < 0.9))", + "MetricThreshold": "tma_info_system_mux > 1.1 | tma_info_system_mux < 0.9", "Unit": "cpu_atom" }, { @@ -629,7 +629,7 @@ "MetricExpr": "cpu_atom@TOPDOWN_FE_BOUND.ITLB_MISS@ / (8 * cpu_atom@CPU_CLK_UNHALTED.CORE@)", "MetricGroup": "TopdownL3;tma_L3_group;tma_ifetch_latency_group", "MetricName": "tma_itlb_misses", - "MetricThreshold": "(tma_itlb_misses >0.05) & ((tma_ifetch_latency >0.15) & ((tma_frontend_bound >0.20)))", + "MetricThreshold": "tma_itlb_misses > 0.05 & (tma_ifetch_latency > 0.15 & tma_frontend_bound > 0.2)", "ScaleUnit": "100%", "Unit": "cpu_atom" }, @@ -638,7 +638,7 @@ "MetricExpr": "cpu_atom@TOPDOWN_BAD_SPECULATION.MACHINE_CLEARS@ / (8 * cpu_atom@CPU_CLK_UNHALTED.CORE@)", "MetricGroup": "TopdownL2;tma_L2_group;tma_bad_speculation_group", "MetricName": "tma_machine_clears", - "MetricThreshold": "(tma_machine_clears >0.05) & ((tma_bad_speculation >0.15))", + "MetricThreshold": "tma_machine_clears > 0.05 & tma_bad_speculation > 0.15", "MetricgroupNoGroup": "TopdownL2", "ScaleUnit": "100%", "Unit": "cpu_atom" @@ -648,7 +648,7 @@ "MetricExpr": "cpu_atom@TOPDOWN_BE_BOUND.MEM_SCHEDULER@ / (8 * cpu_atom@CPU_CLK_UNHALTED.CORE@)", "MetricGroup": "TopdownL3;tma_L3_group;tma_resource_bound_group", "MetricName": "tma_mem_scheduler", - "MetricThreshold": "(tma_mem_scheduler >0.10) & ((tma_resource_bound >0.20) & ((tma_backend_bound >0.10)))", + "MetricThreshold": "tma_mem_scheduler > 0.1 & (tma_resource_bound > 0.2 & tma_backend_bound > 0.1)", "ScaleUnit": "100%", "Unit": "cpu_atom" }, @@ -657,7 +657,7 @@ "MetricExpr": "cpu_atom@TOPDOWN_BE_BOUND.NON_MEM_SCHEDULER@ / (8 * cpu_atom@CPU_CLK_UNHALTED.CORE@)", "MetricGroup": "TopdownL3;tma_L3_group;tma_resource_bound_group", "MetricName": "tma_non_mem_scheduler", - "MetricThreshold": "(tma_non_mem_scheduler >0.10) & ((tma_resource_bound >0.20) & ((tma_backend_bound >0.10)))", + "MetricThreshold": "tma_non_mem_scheduler > 0.1 & (tma_resource_bound > 0.2 & tma_backend_bound > 0.1)", "ScaleUnit": "100%", "Unit": "cpu_atom" }, @@ -666,7 +666,7 @@ "MetricExpr": "cpu_atom@TOPDOWN_BAD_SPECULATION.NUKE@ / (8 * cpu_atom@CPU_CLK_UNHALTED.CORE@)", "MetricGroup": "TopdownL3;tma_L3_group;tma_machine_clears_group", "MetricName": "tma_nuke", - "MetricThreshold": "(tma_nuke >0.05) & ((tma_machine_clears >0.05) & ((tma_bad_speculation >0.15)))", + "MetricThreshold": "tma_nuke > 0.05 & (tma_machine_clears > 0.05 & tma_bad_speculation > 0.15)", "ScaleUnit": "100%", "Unit": "cpu_atom" }, @@ -675,7 +675,7 @@ "MetricExpr": "cpu_atom@TOPDOWN_FE_BOUND.OTHER@ / (8 * cpu_atom@CPU_CLK_UNHALTED.CORE@)", "MetricGroup": "TopdownL3;tma_L3_group;tma_ifetch_bandwidth_group", "MetricName": "tma_other_fb", - "MetricThreshold": "(tma_other_fb >0.05) & ((tma_ifetch_bandwidth >0.10) & ((tma_frontend_bound >0.20)))", + "MetricThreshold": "tma_other_fb > 0.05 & (tma_ifetch_bandwidth > 0.1 & tma_frontend_bound > 0.2)", "ScaleUnit": "100%", "Unit": "cpu_atom" }, @@ -684,7 +684,7 @@ "MetricExpr": "cpu_atom@TOPDOWN_FE_BOUND.PREDECODE@ / (8 * cpu_atom@CPU_CLK_UNHALTED.CORE@)", "MetricGroup": "TopdownL3;tma_L3_group;tma_ifetch_bandwidth_group", "MetricName": "tma_predecode", - "MetricThreshold": "(tma_predecode >0.05) & ((tma_ifetch_bandwidth >0.10) & ((tma_frontend_bound >0.20)))", + "MetricThreshold": "tma_predecode > 0.05 & (tma_ifetch_bandwidth > 0.1 & tma_frontend_bound > 0.2)", "ScaleUnit": "100%", "Unit": "cpu_atom" }, @@ -693,7 +693,7 @@ "MetricExpr": "cpu_atom@TOPDOWN_BE_BOUND.REGISTER@ / (8 * cpu_atom@CPU_CLK_UNHALTED.CORE@)", "MetricGroup": "TopdownL3;tma_L3_group;tma_resource_bound_group", "MetricName": "tma_register", - "MetricThreshold": "(tma_register >0.10) & ((tma_resource_bound >0.20) & ((tma_backend_bound >0.10)))", + "MetricThreshold": "tma_register > 0.1 & (tma_resource_bound > 0.2 & tma_backend_bound > 0.1)", "ScaleUnit": "100%", "Unit": "cpu_atom" }, @@ -702,7 +702,7 @@ "MetricExpr": "cpu_atom@TOPDOWN_BE_BOUND.REORDER_BUFFER@ / (8 * cpu_atom@CPU_CLK_UNHALTED.CORE@)", "MetricGroup": "TopdownL3;tma_L3_group;tma_resource_bound_group", "MetricName": "tma_reorder_buffer", - "MetricThreshold": "(tma_reorder_buffer >0.10) & ((tma_resource_bound >0.20) & ((tma_backend_bound >0.10)))", + "MetricThreshold": "tma_reorder_buffer > 0.1 & (tma_resource_bound > 0.2 & tma_backend_bound > 0.1)", "ScaleUnit": "100%", "Unit": "cpu_atom" }, @@ -711,7 +711,7 @@ "MetricExpr": "tma_backend_bound - tma_core_bound", "MetricGroup": "TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_resource_bound", - "MetricThreshold": "(tma_resource_bound >0.20) & ((tma_backend_bound >0.10))", + "MetricThreshold": "tma_resource_bound > 0.2 & tma_backend_bound > 0.1", "MetricgroupNoGroup": "TopdownL2", "ScaleUnit": "100%", "Unit": "cpu_atom" @@ -722,7 +722,7 @@ "MetricExpr": "cpu_atom@TOPDOWN_RETIRING.ALL@ / (8 * cpu_atom@CPU_CLK_UNHALTED.CORE@)", "MetricGroup": "Default;TopdownL1;tma_L1_group", "MetricName": "tma_retiring", - "MetricThreshold": "(tma_retiring >0.75)", + "MetricThreshold": "tma_retiring > 0.75", "MetricgroupNoGroup": "TopdownL1;Default", "ScaleUnit": "100%", "Unit": "cpu_atom" @@ -732,7 +732,7 @@ "MetricExpr": "cpu_atom@TOPDOWN_BE_BOUND.SERIALIZATION@ / (8 * cpu_atom@CPU_CLK_UNHALTED.CORE@)", "MetricGroup": "TopdownL3;tma_L3_group;tma_resource_bound_group", "MetricName": "tma_serialization", - "MetricThreshold": "(tma_serialization >0.10) & ((tma_resource_bound >0.20) & ((tma_backend_bound >0.10)))", + "MetricThreshold": "tma_serialization > 0.1 & (tma_resource_bound > 0.2 & tma_backend_bound > 0.1)", "ScaleUnit": "100%", "Unit": "cpu_atom" }, @@ -744,7 +744,7 @@ "Unit": "cpu_core" }, { - "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution ports for ALU operations", + "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution ports for ALU operations.", "MetricExpr": "cpu_core@UOPS_DISPATCHED.ALU@ / (6 * tma_info_thread_clks)", "MetricGroup": "TopdownL5;tma_L5_group;tma_ports_utilized_3m_group", "MetricName": "tma_alu_op_utilization", @@ -757,13 +757,13 @@ "MetricExpr": "78 * cpu_core@ASSISTS.ANY@ / tma_info_thread_slots", "MetricGroup": "BvIO;TopdownL4;tma_L4_group;tma_microcode_sequencer_group", "MetricName": "tma_assists", - "MetricThreshold": "tma_assists > 0.1 & tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1", + "MetricThreshold": "tma_assists > 0.1 & (tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1)", "PublicDescription": "This metric estimates fraction of slots the CPU retired uops delivered by the Microcode_Sequencer as a result of Assists. Assists are long sequences of uops that are required in certain corner-cases for operations that cannot be handled natively by the execution pipeline. For example; when working with very small floating point values (so-called Denormals); the FP units are not set up to perform these operations natively. Instead; a sequence of instructions to perform the computation on the Denormals is injected into the pipeline. Since these microcode sequences might be dozens of uops long; Assists can be extremely deleterious to performance and they can be avoided in many cases. Sample with: ASSISTS.ANY", "ScaleUnit": "100%", "Unit": "cpu_core" }, { - "BriefDescription": "This metric estimates fraction of slots the CPU retired uops as a result of handing SSE to AVX* or AVX* to SSE transition Assists", + "BriefDescription": "This metric estimates fraction of slots the CPU retired uops as a result of handing SSE to AVX* or AVX* to SSE transition Assists.", "MetricExpr": "63 * cpu_core@ASSISTS.SSE_AVX_MIX@ / tma_info_thread_slots", "MetricGroup": "HPC;TopdownL5;tma_L5_group;tma_assists_group", "MetricName": "tma_avx_assists", @@ -774,7 +774,7 @@ { "BriefDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend", "DefaultMetricgroupName": "TopdownL1", - "MetricExpr": "topdown\\-be\\-bound / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * slots", + "MetricExpr": "cpu_core@topdown\\-be\\-bound@ / (cpu_core@topdown\\-fe\\-bound@ + cpu_core@topdown\\-bad\\-spec@ + cpu_core@topdown\\-retiring@ + cpu_core@topdown\\-be\\-bound@) + 0 * tma_info_thread_slots", "MetricGroup": "BvOB;Default;TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_backend_bound", "MetricThreshold": "tma_backend_bound > 0.2", @@ -786,18 +786,18 @@ { "BriefDescription": "This category represents fraction of slots wasted due to incorrect speculations", "DefaultMetricgroupName": "TopdownL1", - "MetricExpr": "topdown\\-bad\\-spec / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * slots", + "MetricExpr": "cpu_core@topdown\\-bad\\-spec@ / (cpu_core@topdown\\-fe\\-bound@ + cpu_core@topdown\\-bad\\-spec@ + cpu_core@topdown\\-retiring@ + cpu_core@topdown\\-be\\-bound@) + 0 * tma_info_thread_slots", "MetricGroup": "Default;TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_bad_speculation", "MetricThreshold": "tma_bad_speculation > 0.15", "MetricgroupNoGroup": "TopdownL1;Default", - "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example", + "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.", "ScaleUnit": "100%", "Unit": "cpu_core" }, { "BriefDescription": "Total pipeline cost of instruction fetch related bottlenecks by large code footprint programs (i-side cache; TLB and BTB misses)", - "MetricExpr": "100 * tma_fetch_latency * (tma_itlb_misses + tma_icache_misses + tma_unknown_branches) / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches)", + "MetricExpr": "100 * tma_fetch_latency * (tma_itlb_misses + tma_icache_misses + tma_unknown_branches) / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches)", "MetricGroup": "BigFootprint;BvBC;Fed;Frontend;IcMiss;MemoryTLB", "MetricName": "tma_bottleneck_big_code", "MetricThreshold": "tma_bottleneck_big_code > 20", @@ -814,11 +814,11 @@ }, { "BriefDescription": "Total pipeline cost of external Memory- or Cache-Bandwidth related bottlenecks", - "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_mem_bandwidth / (tma_mem_bandwidth + tma_mem_latency)) + tma_memory_bound * (tma_l3_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_sq_full / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_memory_bound * (tma_l1_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_fb_full / (tma_dtlb_load + tma_store_fwd_blk + tma_l1_latency_dependency + tma_l1_latency_capacity + tma_lock_latency + tma_split_loads + tma_fb_full)))", + "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_mem_bandwidth / (tma_mem_bandwidth + tma_mem_latency)) + tma_memory_bound * (tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_sq_full / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_fb_full / (tma_dtlb_load + tma_fb_full + tma_l1_latency_capacity + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)))", "MetricGroup": "BvMB;Mem;MemoryBW;Offcore;tma_issueBW", "MetricName": "tma_bottleneck_cache_memory_bandwidth", "MetricThreshold": "tma_bottleneck_cache_memory_bandwidth > 20", - "PublicDescription": "Total pipeline cost of external Memory- or Cache-Bandwidth related bottlenecks. Related metrics: tma_fb_full, tma_mem_bandwidth, tma_sq_full", + "PublicDescription": "Total pipeline cost of external Memory- or Cache-Bandwidth related bottlenecks. Related metrics: tma_fb_full, tma_info_system_dram_bw_use, tma_mem_bandwidth, tma_sq_full", "Unit": "cpu_core" }, { @@ -826,22 +826,22 @@ "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_mem_latency / (tma_mem_bandwidth + tma_mem_latency)) + tma_memory_bound * (tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_l3_hit_latency / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_memory_bound * tma_l2_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) + tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_l1_latency_dependency / (tma_dtlb_load + tma_fb_full + tma_l1_latency_capacity + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_l1_latency_capacity / (tma_dtlb_load + tma_fb_full + tma_l1_latency_capacity + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_lock_latency / (tma_dtlb_load + tma_fb_full + tma_l1_latency_capacity + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_split_loads / (tma_dtlb_load + tma_fb_full + tma_l1_latency_capacity + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_memory_bound * (tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_split_stores / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency + tma_streaming_stores)) + tma_memory_bound * (tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_store_latency / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency + tma_streaming_stores)))", "MetricGroup": "BvML;Mem;MemoryLat;Offcore;tma_issueLat", "MetricName": "tma_bottleneck_cache_memory_latency", - "MetricThreshold": "(tma_bottleneck_cache_memory_latency > 20)", + "MetricThreshold": "tma_bottleneck_cache_memory_latency > 20", "PublicDescription": "Total pipeline cost of external Memory- or Cache-Latency related bottlenecks. Related metrics: tma_l3_hit_latency, tma_mem_latency", "Unit": "cpu_core" }, { "BriefDescription": "Total pipeline cost when the execution is compute-bound - an estimation", - "MetricExpr": "100 * (tma_core_bound * tma_divider / (tma_divider + tma_serializing_operation + tma_ports_utilization) + tma_core_bound * (tma_ports_utilization / (tma_divider + tma_serializing_operation + tma_ports_utilization)) * (tma_ports_utilized_3m / (tma_ports_utilized_0 + tma_ports_utilized_1 + tma_ports_utilized_2 + tma_ports_utilized_3m)))", + "MetricExpr": "100 * (tma_core_bound * tma_divider / (tma_divider + tma_ports_utilization + tma_serializing_operation) + tma_core_bound * (tma_ports_utilization / (tma_divider + tma_ports_utilization + tma_serializing_operation)) * (tma_ports_utilized_3m / (tma_ports_utilized_0 + tma_ports_utilized_1 + tma_ports_utilized_2 + tma_ports_utilized_3m)))", "MetricGroup": "BvCB;Cor;tma_issueComp", "MetricName": "tma_bottleneck_compute_bound_est", "MetricThreshold": "tma_bottleneck_compute_bound_est > 20", - "PublicDescription": "Total pipeline cost when the execution is compute-bound - an estimation. Covers Core Bound when High ILP as well as when long-latency execution units are busy", + "PublicDescription": "Total pipeline cost when the execution is compute-bound - an estimation. Covers Core Bound when High ILP as well as when long-latency execution units are busy. Related metrics: ", "Unit": "cpu_core" }, { "BriefDescription": "Total pipeline cost of instruction fetch bandwidth related bottlenecks (when the front-end could not sustain operations delivery to the back-end)", - "MetricExpr": "100 * (tma_frontend_bound - (1 - 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts) * tma_fetch_latency * tma_mispredicts_resteers / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches) - (1 - cpu_core@INST_RETIRED.REP_ITERATION@ / cpu_core@UOPS_RETIRED.MS\\,cmask\\=0x1@) * (tma_fetch_latency * (tma_ms_switches + tma_branch_resteers * (tma_clears_resteers + tma_mispredicts_resteers * tma_other_mispredicts / tma_branch_mispredicts) / (tma_mispredicts_resteers + tma_clears_resteers + tma_unknown_branches)) / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches) + tma_fetch_bandwidth * tma_ms / (tma_mite + tma_dsb + tma_lsd + tma_ms))) - tma_bottleneck_big_code", + "MetricExpr": "100 * (tma_frontend_bound - (1 - 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts) * tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) - (1 - cpu_core@INST_RETIRED.REP_ITERATION@ / cpu_core@UOPS_RETIRED.MS\\,cmask\\=1@) * (tma_fetch_latency * (tma_ms_switches + tma_branch_resteers * (tma_clears_resteers + tma_mispredicts_resteers * tma_other_mispredicts / tma_branch_mispredicts) / (tma_clears_resteers + tma_mispredicts_resteers + tma_unknown_branches)) / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) + tma_fetch_bandwidth * tma_ms / (tma_dsb + tma_lsd + tma_mite + tma_ms))) - tma_bottleneck_big_code", "MetricGroup": "BvFB;Fed;FetchBW;Frontend", "MetricName": "tma_bottleneck_instruction_fetch_bw", "MetricThreshold": "tma_bottleneck_instruction_fetch_bw > 20", @@ -849,7 +849,7 @@ }, { "BriefDescription": "Total pipeline cost of irregular execution (e.g", - "MetricExpr": "100 * ((1 - cpu_core@INST_RETIRED.REP_ITERATION@ / cpu_core@UOPS_RETIRED.MS\\,cmask\\=0x1@) * (tma_fetch_latency * (tma_ms_switches + tma_branch_resteers * (tma_clears_resteers + tma_mispredicts_resteers * tma_other_mispredicts / tma_branch_mispredicts) / (tma_mispredicts_resteers + tma_clears_resteers + tma_unknown_branches)) / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches) + tma_fetch_bandwidth * tma_ms / (tma_mite + tma_dsb + tma_lsd + tma_ms)) + 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts * tma_branch_mispredicts + tma_machine_clears * tma_other_nukes / tma_other_nukes + tma_core_bound * (tma_serializing_operation + cpu_core@RS.EMPTY_RESOURCE@ / tma_info_thread_clks * tma_ports_utilized_0) / (tma_divider + tma_serializing_operation + tma_ports_utilization) + tma_microcode_sequencer / (tma_microcode_sequencer + tma_few_uops_instructions) * (tma_assists / tma_microcode_sequencer) * tma_heavy_operations)", + "MetricExpr": "100 * ((1 - cpu_core@INST_RETIRED.REP_ITERATION@ / cpu_core@UOPS_RETIRED.MS\\,cmask\\=1@) * (tma_fetch_latency * (tma_ms_switches + tma_branch_resteers * (tma_clears_resteers + tma_mispredicts_resteers * tma_other_mispredicts / tma_branch_mispredicts) / (tma_clears_resteers + tma_mispredicts_resteers + tma_unknown_branches)) / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) + tma_fetch_bandwidth * tma_ms / (tma_dsb + tma_lsd + tma_mite + tma_ms)) + 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts * tma_branch_mispredicts + tma_machine_clears * tma_other_nukes / tma_other_nukes + tma_core_bound * (tma_serializing_operation + cpu_core@RS.EMPTY_RESOURCE@ / tma_info_thread_clks * tma_ports_utilized_0) / (tma_divider + tma_ports_utilization + tma_serializing_operation) + tma_microcode_sequencer / (tma_microcode_sequencer + tma_few_uops_instructions) * (tma_assists / tma_microcode_sequencer) * tma_heavy_operations)", "MetricGroup": "Bad;BvIO;Cor;Ret;tma_issueMS", "MetricName": "tma_bottleneck_irregular_overhead", "MetricThreshold": "tma_bottleneck_irregular_overhead > 10", @@ -861,7 +861,7 @@ "MetricExpr": "100 * (tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_dtlb_load / (tma_dtlb_load + tma_fb_full + tma_l1_latency_capacity + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_memory_bound * (tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_dtlb_store / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency + tma_streaming_stores)))", "MetricGroup": "BvMT;Mem;MemoryTLB;Offcore;tma_issueTLB", "MetricName": "tma_bottleneck_memory_data_tlbs", - "MetricThreshold": "(tma_bottleneck_memory_data_tlbs > 20)", + "MetricThreshold": "tma_bottleneck_memory_data_tlbs > 20", "PublicDescription": "Total pipeline cost of Memory Address Translation related bottlenecks (data-side TLBs). Related metrics: tma_dtlb_load, tma_dtlb_store", "Unit": "cpu_core" }, @@ -870,13 +870,13 @@ "MetricExpr": "100 * (tma_memory_bound * (tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_contested_accesses + tma_data_sharing) / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full) + tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * tma_false_sharing / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency + tma_streaming_stores - tma_store_latency)) + tma_machine_clears * (1 - tma_other_nukes / tma_other_nukes))", "MetricGroup": "BvMS;LockCont;Mem;Offcore;tma_issueSyncxn", "MetricName": "tma_bottleneck_memory_synchronization", - "MetricThreshold": "(tma_bottleneck_memory_synchronization > 10)", + "MetricThreshold": "tma_bottleneck_memory_synchronization > 10", "PublicDescription": "Total pipeline cost of Memory Synchronization related bottlenecks (data transfers and coherency updates across processors). Related metrics: tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_machine_clears, tma_remote_cache", "Unit": "cpu_core" }, { "BriefDescription": "Total pipeline cost of Branch Misprediction related bottlenecks", - "MetricExpr": "100 * (1 - 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts) * (tma_branch_mispredicts + tma_fetch_latency * tma_mispredicts_resteers / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches))", + "MetricExpr": "100 * (1 - 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts) * (tma_branch_mispredicts + tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches))", "MetricGroup": "Bad;BadSpec;BrMispredicts;BvMP;tma_issueBM", "MetricName": "tma_bottleneck_mispredictions", "MetricThreshold": "tma_bottleneck_mispredictions > 20", @@ -888,12 +888,12 @@ "MetricExpr": "100 - (tma_bottleneck_big_code + tma_bottleneck_instruction_fetch_bw + tma_bottleneck_mispredictions + tma_bottleneck_cache_memory_bandwidth + tma_bottleneck_cache_memory_latency + tma_bottleneck_memory_data_tlbs + tma_bottleneck_memory_synchronization + tma_bottleneck_compute_bound_est + tma_bottleneck_irregular_overhead + tma_bottleneck_branching_overhead + tma_bottleneck_useful_work)", "MetricGroup": "BvOB;Cor;Offcore", "MetricName": "tma_bottleneck_other_bottlenecks", - "MetricThreshold": "(tma_bottleneck_other_bottlenecks > 20)", + "MetricThreshold": "tma_bottleneck_other_bottlenecks > 20", "PublicDescription": "Total pipeline cost of remaining bottlenecks in the back-end. Examples include data-dependencies (Core Bound when Low ILP) and other unlisted memory-related stalls.", "Unit": "cpu_core" }, { - "BriefDescription": "Total pipeline cost of \"useful operations\" - the portion of Retiring category not covered by Branching_Overhead nor Irregular_Overhead", + "BriefDescription": "Total pipeline cost of \"useful operations\" - the portion of Retiring category not covered by Branching_Overhead nor Irregular_Overhead.", "MetricExpr": "100 * (tma_retiring - (cpu_core@BR_INST_RETIRED.ALL_BRANCHES@ + 2 * cpu_core@BR_INST_RETIRED.NEAR_CALL@ + cpu_core@INST_RETIRED.NOP@) / tma_info_thread_slots - tma_microcode_sequencer / (tma_microcode_sequencer + tma_few_uops_instructions) * (tma_assists / tma_microcode_sequencer) * tma_heavy_operations)", "MetricGroup": "BvUW;Ret", "MetricName": "tma_bottleneck_useful_work", @@ -902,7 +902,7 @@ }, { "BriefDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction", - "MetricExpr": "topdown\\-br\\-mispredict / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * slots", + "MetricExpr": "cpu_core@topdown\\-br\\-mispredict@ / (cpu_core@topdown\\-fe\\-bound@ + cpu_core@topdown\\-bad\\-spec@ + cpu_core@topdown\\-retiring@ + cpu_core@topdown\\-be\\-bound@) + 0 * tma_info_thread_slots", "MetricGroup": "BadSpec;BrMispredicts;BvMP;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueBM", "MetricName": "tma_branch_mispredicts", "MetricThreshold": "tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", @@ -916,26 +916,26 @@ "MetricExpr": "cpu_core@INT_MISC.CLEAR_RESTEER_CYCLES@ / tma_info_thread_clks + tma_unknown_branches", "MetricGroup": "FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group", "MetricName": "tma_branch_resteers", - "MetricThreshold": "tma_branch_resteers > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", - "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers. Branch Resteers estimates the Frontend delay in fetching operations from corrected path; following all sorts of miss-predicted branches. For example; branchy code with lots of miss-predictions might get categorized under Branch Resteers. Note the value of this node may overlap with its siblings. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_l3_hit_latency, tma_store_latency", + "MetricThreshold": "tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers. Branch Resteers estimates the Frontend delay in fetching operations from corrected path; following all sorts of miss-predicted branches. For example; branchy code with lots of miss-predictions might get categorized under Branch Resteers. Note the value of this node may overlap with its siblings. Sample with: BR_MISP_RETIRED.ALL_BRANCHES", "ScaleUnit": "100%", "Unit": "cpu_core" }, { - "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due staying in C0.1 power-performance optimized state (Faster wakeup time; Smaller power savings)", + "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due staying in C0.1 power-performance optimized state (Faster wakeup time; Smaller power savings).", "MetricExpr": "cpu_core@CPU_CLK_UNHALTED.C01@ / tma_info_thread_clks", "MetricGroup": "C0Wait;TopdownL4;tma_L4_group;tma_serializing_operation_group", "MetricName": "tma_c01_wait", - "MetricThreshold": "tma_c01_wait > 0.05 & tma_serializing_operation > 0.1 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_c01_wait > 0.05 & (tma_serializing_operation > 0.1 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", "ScaleUnit": "100%", "Unit": "cpu_core" }, { - "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due staying in C0.2 power-performance optimized state (Slower wakeup time; Larger power savings)", + "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due staying in C0.2 power-performance optimized state (Slower wakeup time; Larger power savings).", "MetricExpr": "cpu_core@CPU_CLK_UNHALTED.C02@ / tma_info_thread_clks", "MetricGroup": "C0Wait;TopdownL4;tma_L4_group;tma_serializing_operation_group", "MetricName": "tma_c02_wait", - "MetricThreshold": "tma_c02_wait > 0.05 & tma_serializing_operation > 0.1 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_c02_wait > 0.05 & (tma_serializing_operation > 0.1 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -944,8 +944,8 @@ "MetricExpr": "max(0, tma_microcode_sequencer - tma_assists)", "MetricGroup": "TopdownL4;tma_L4_group;tma_microcode_sequencer_group", "MetricName": "tma_cisc", - "MetricThreshold": "tma_cisc > 0.1 & tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1", - "PublicDescription": "This metric estimates fraction of cycles the CPU retired uops originated from CISC (complex instruction set computer) instruction. A CISC instruction has multiple uops that are required to perform the instruction's functionality as in the case of read-modify-write as an example. Since these instructions require multiple uops they may or may not imply sub-optimal use of machine resources", + "MetricThreshold": "tma_cisc > 0.1 & (tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1)", + "PublicDescription": "This metric estimates fraction of cycles the CPU retired uops originated from CISC (complex instruction set computer) instruction. A CISC instruction has multiple uops that are required to perform the instruction's functionality as in the case of read-modify-write as an example. Since these instructions require multiple uops they may or may not imply sub-optimal use of machine resources.", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -954,99 +954,100 @@ "MetricExpr": "(1 - tma_branch_mispredicts / tma_bad_speculation) * cpu_core@INT_MISC.CLEAR_RESTEER_CYCLES@ / tma_info_thread_clks", "MetricGroup": "BadSpec;MachineClears;TopdownL4;tma_L4_group;tma_branch_resteers_group;tma_issueMC", "MetricName": "tma_clears_resteers", - "MetricThreshold": "tma_clears_resteers > 0.05 & tma_branch_resteers > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricThreshold": "tma_clears_resteers > 0.05 & (tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))", "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Machine Clears. Sample with: INT_MISC.CLEAR_RESTEER_CYCLES. Related metrics: tma_l1_bound, tma_machine_clears, tma_microcode_sequencer, tma_ms_switches", "ScaleUnit": "100%", "Unit": "cpu_core" }, { - "BriefDescription": "This metric estimates fraction of cycles the CPU was stalled due to instruction cache misses that hit in the L2 cache", - "MetricExpr": "max(0, cpu_core@FRONTEND_RETIRED.L1I_MISS@ * cpu_core@frontend_retired.l1i_miss@R / tma_info_thread_clks - tma_code_l2_miss)", + "BriefDescription": "This metric estimates fraction of cycles the CPU was stalled due to instruction cache misses that hit in the L2 cache.", + "MetricExpr": "max(0, cpu_core@FRONTEND_RETIRED.L1I_MISS@ * cpu_core@FRONTEND_RETIRED.L1I_MISS@R / tma_info_thread_clks - tma_code_l2_miss)", "MetricGroup": "FetchLat;IcMiss;Offcore;TopdownL4;tma_L4_group;tma_icache_misses_group", "MetricName": "tma_code_l2_hit", - "MetricThreshold": "tma_code_l2_hit > 0.05 & tma_icache_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricThreshold": "tma_code_l2_hit > 0.05 & (tma_icache_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))", "ScaleUnit": "100%", "Unit": "cpu_core" }, { - "BriefDescription": "This metric estimates fraction of cycles the CPU was stalled due to instruction cache misses that miss in the L2 cache", - "MetricExpr": "cpu_core@FRONTEND_RETIRED.L2_MISS@ * cpu_core@frontend_retired.l2_miss@R / tma_info_thread_clks", + "BriefDescription": "This metric estimates fraction of cycles the CPU was stalled due to instruction cache misses that miss in the L2 cache.", + "MetricExpr": "cpu_core@FRONTEND_RETIRED.L2_MISS@ * cpu_core@FRONTEND_RETIRED.L2_MISS@R / tma_info_thread_clks", "MetricGroup": "FetchLat;IcMiss;Offcore;TopdownL4;tma_L4_group;tma_icache_misses_group", "MetricName": "tma_code_l2_miss", - "MetricThreshold": "tma_code_l2_miss > 0.05 & tma_icache_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricThreshold": "tma_code_l2_miss > 0.05 & (tma_icache_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))", "ScaleUnit": "100%", "Unit": "cpu_core" }, { "BriefDescription": "This metric roughly estimates the fraction of cycles where the (first level) ITLB was missed by instructions fetches, that later on hit in second-level TLB (STLB)", - "MetricExpr": "max(0, cpu_core@FRONTEND_RETIRED.ITLB_MISS@ * cpu_core@frontend_retired.itlb_miss@R / tma_info_thread_clks - tma_code_stlb_miss)", + "MetricExpr": "max(0, cpu_core@FRONTEND_RETIRED.ITLB_MISS@ * cpu_core@FRONTEND_RETIRED.ITLB_MISS@R / tma_info_thread_clks - tma_code_stlb_miss)", "MetricGroup": "FetchLat;MemoryTLB;TopdownL4;tma_L4_group;tma_itlb_misses_group", "MetricName": "tma_code_stlb_hit", - "MetricThreshold": "tma_code_stlb_hit > 0.05 & tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricThreshold": "tma_code_stlb_hit > 0.05 & (tma_itlb_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))", "ScaleUnit": "100%", "Unit": "cpu_core" }, { "BriefDescription": "This metric estimates the fraction of cycles where the Second-level TLB (STLB) was missed by instruction fetches, performing a hardware page walk", - "MetricExpr": "cpu_core@FRONTEND_RETIRED.STLB_MISS@ * cpu_core@frontend_retired.stlb_miss@R / tma_info_thread_clks", + "MetricExpr": "cpu_core@FRONTEND_RETIRED.STLB_MISS@ * cpu_core@FRONTEND_RETIRED.STLB_MISS@R / tma_info_thread_clks", "MetricGroup": "FetchLat;MemoryTLB;TopdownL4;tma_L4_group;tma_itlb_misses_group", "MetricName": "tma_code_stlb_miss", - "MetricThreshold": "tma_code_stlb_miss > 0.05 & tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricThreshold": "tma_code_stlb_miss > 0.05 & (tma_itlb_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))", "ScaleUnit": "100%", "Unit": "cpu_core" }, { - "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 2 or 4 MB pages for (instruction) code accesses", + "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 2 or 4 MB pages for (instruction) code accesses.", "MetricExpr": "cpu_core@ITLB_MISSES.WALK_ACTIVE@ / tma_info_thread_clks * cpu_core@ITLB_MISSES.WALK_COMPLETED_2M_4M@ / (cpu_core@ITLB_MISSES.WALK_COMPLETED_4K@ + cpu_core@ITLB_MISSES.WALK_COMPLETED_2M_4M@)", "MetricGroup": "FetchLat;MemoryTLB;TopdownL5;tma_L5_group;tma_code_stlb_miss_group", "MetricName": "tma_code_stlb_miss_2m", - "MetricThreshold": "tma_code_stlb_miss_2m > 0.05 & tma_code_stlb_miss > 0.05 & tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricThreshold": "tma_code_stlb_miss_2m > 0.05 & (tma_code_stlb_miss > 0.05 & (tma_itlb_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)))", "ScaleUnit": "100%", "Unit": "cpu_core" }, { - "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 4 KB pages for (instruction) code accesses", + "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 4 KB pages for (instruction) code accesses.", "MetricExpr": "cpu_core@ITLB_MISSES.WALK_ACTIVE@ / tma_info_thread_clks * cpu_core@ITLB_MISSES.WALK_COMPLETED_4K@ / (cpu_core@ITLB_MISSES.WALK_COMPLETED_4K@ + cpu_core@ITLB_MISSES.WALK_COMPLETED_2M_4M@)", "MetricGroup": "FetchLat;MemoryTLB;TopdownL5;tma_L5_group;tma_code_stlb_miss_group", "MetricName": "tma_code_stlb_miss_4k", - "MetricThreshold": "tma_code_stlb_miss_4k > 0.05 & tma_code_stlb_miss > 0.05 & tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricThreshold": "tma_code_stlb_miss_4k > 0.05 & (tma_code_stlb_miss > 0.05 & (tma_itlb_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)))", "ScaleUnit": "100%", "Unit": "cpu_core" }, { - "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to retired misprediction by non-taken conditional branches", - "MetricExpr": "cpu_core@BR_MISP_RETIRED.COND_NTAKEN_COST@ * cpu_core@br_misp_retired.cond_ntaken_cost@R / tma_info_thread_clks", + "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to retired misprediction by non-taken conditional branches.", + "MetricExpr": "cpu_core@BR_MISP_RETIRED.COND_NTAKEN_COST@ * cpu_core@BR_MISP_RETIRED.COND_NTAKEN_COST@R / tma_info_thread_clks", "MetricGroup": "BrMispredicts;TopdownL3;tma_L3_group;tma_branch_mispredicts_group", "MetricName": "tma_cond_nt_mispredicts", - "MetricThreshold": "tma_cond_nt_mispredicts > 0.05 & tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", + "MetricThreshold": "tma_cond_nt_mispredicts > 0.05 & (tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15)", "ScaleUnit": "100%", "Unit": "cpu_core" }, { - "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to misprediction by backward-taken conditional branches", - "MetricExpr": "cpu_core@BR_MISP_RETIRED.COND_TAKEN_BWD_COST@ * cpu_core@br_misp_retired.cond_taken_bwd_cost@R / tma_info_thread_clks", + "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to misprediction by backward-taken conditional branches.", + "MetricExpr": "cpu_core@BR_MISP_RETIRED.COND_TAKEN_BWD_COST@ * cpu_core@BR_MISP_RETIRED.COND_TAKEN_BWD_COST@R / tma_info_thread_clks", "MetricGroup": "BrMispredicts;TopdownL3;tma_L3_group;tma_branch_mispredicts_group", "MetricName": "tma_cond_tk_bwd_mispredicts", - "MetricThreshold": "tma_cond_tk_bwd_mispredicts > 0.05 & tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", + "MetricThreshold": "tma_cond_tk_bwd_mispredicts > 0.05 & (tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15)", "ScaleUnit": "100%", "Unit": "cpu_core" }, { - "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to misprediction by forward-taken conditional branches", - "MetricExpr": "cpu_core@BR_MISP_RETIRED.COND_TAKEN_FWD_COST@ * cpu_core@br_misp_retired.cond_taken_fwd_cost@R / tma_info_thread_clks", + "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to misprediction by forward-taken conditional branches.", + "MetricExpr": "cpu_core@BR_MISP_RETIRED.COND_TAKEN_FWD_COST@ * cpu_core@BR_MISP_RETIRED.COND_TAKEN_FWD_COST@R / tma_info_thread_clks", "MetricGroup": "BrMispredicts;TopdownL3;tma_L3_group;tma_branch_mispredicts_group", "MetricName": "tma_cond_tk_fwd_mispredicts", - "MetricThreshold": "tma_cond_tk_fwd_mispredicts > 0.05 & tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", + "MetricThreshold": "tma_cond_tk_fwd_mispredicts > 0.05 & (tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15)", "ScaleUnit": "100%", "Unit": "cpu_core" }, { "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses", - "MetricExpr": "((min(cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS@ * cpu_core@mem_load_l3_hit_retired.xsnp_miss@R, cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS@ * (27 * tma_info_system_core_frequency) - 3 * tma_info_system_core_frequency) if 0 < cpu_core@mem_load_l3_hit_retired.xsnp_miss@R else cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS@ * (27 * tma_info_system_core_frequency) - 3 * tma_info_system_core_frequency) + (min(cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM@ * cpu_core@mem_load_l3_hit_retired.xsnp_hitm@R, cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM@ * (28 * tma_info_system_core_frequency) - 3 * tma_info_system_core_frequency) if 0 < cpu_core@mem_load_l3_hit_retired.xsnp_hitm@R else cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM@ * (28 * tma_info_system_core_frequency) - 3 * tma_info_system_core_frequency)) * (1 + cpu_core@MEM_LOAD_RETIRED.FB_HIT@ / cpu_core@MEM_LOAD_RETIRED.L1_MISS@ / 2) / tma_info_thread_clks", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "(cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS@ * min(cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS@R, 24 * tma_info_system_core_frequency) + cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM@ * min(cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM@R, 25 * tma_info_system_core_frequency)) * (1 + cpu_core@MEM_LOAD_RETIRED.FB_HIT@ / cpu_core@MEM_LOAD_RETIRED.L1_MISS@ / 2) / tma_info_thread_clks", "MetricGroup": "BvMS;DataSharing;LockCont;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group", "MetricName": "tma_contested_accesses", - "MetricThreshold": "tma_contested_accesses > 0.05 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", - "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses. Contested accesses occur when data written by one Logical Processor are read by another Logical Processor on a different Physical Core. Examples of contested accesses include synchronizations such as locks; true data sharing such as modified locked variables; and false sharing. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD, MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS. Related metrics: tma_data_sharing, tma_machine_clears", + "MetricThreshold": "tma_contested_accesses > 0.05 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses. Contested accesses occur when data written by one Logical Processor are read by another Logical Processor on a different Physical Core. Examples of contested accesses include synchronizations such as locks; true data sharing such as modified locked variables; and false sharing. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD;MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS. Related metrics: tma_bottleneck_memory_synchronization, tma_data_sharing, tma_false_sharing, tma_machine_clears, tma_remote_cache", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -1057,17 +1058,18 @@ "MetricName": "tma_core_bound", "MetricThreshold": "tma_core_bound > 0.1 & tma_backend_bound > 0.2", "MetricgroupNoGroup": "TopdownL2", - "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck. Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations)", + "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck. Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations).", "ScaleUnit": "100%", "Unit": "cpu_core" }, { "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses", - "MetricExpr": "((min(cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_NO_FWD@ * cpu_core@mem_load_l3_hit_retired.xsnp_no_fwd@R, cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_NO_FWD@ * (27 * tma_info_system_core_frequency) - 3 * tma_info_system_core_frequency) if 0 < cpu_core@mem_load_l3_hit_retired.xsnp_no_fwd@R else cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_NO_FWD@ * (27 * tma_info_system_core_frequency) - 3 * tma_info_system_core_frequency) + (min(cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD@ * cpu_core@mem_load_l3_hit_retired.xsnp_fwd@R, cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD@ * (28 * tma_info_system_core_frequency) - 3 * tma_info_system_core_frequency) if 0 < cpu_core@mem_load_l3_hit_retired.xsnp_fwd@R else cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD@ * (28 * tma_info_system_core_frequency) - 3 * tma_info_system_core_frequency)) * (1 + cpu_core@MEM_LOAD_RETIRED.FB_HIT@ / cpu_core@MEM_LOAD_RETIRED.L1_MISS@ / 2) / tma_info_thread_clks", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "(cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_NO_FWD@ * min(cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_NO_FWD@R, 24 * tma_info_system_core_frequency) + cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD@ * min(cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD@R, 25 * tma_info_system_core_frequency)) * (1 + cpu_core@MEM_LOAD_RETIRED.FB_HIT@ / cpu_core@MEM_LOAD_RETIRED.L1_MISS@ / 2) / tma_info_thread_clks", "MetricGroup": "BvMS;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group", "MetricName": "tma_data_sharing", - "MetricThreshold": "tma_data_sharing > 0.05 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", - "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses. Data shared by multiple Logical Processors (even just read shared) may cause increased access latency due to cache coherency. Excessive data sharing can drastically harm multithreaded performance. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_NO_FWD. Related metrics: tma_contested_accesses, tma_machine_clears", + "MetricThreshold": "tma_data_sharing > 0.05 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses. Data shared by multiple Logical Processors (even just read shared) may cause increased access latency due to cache coherency. Excessive data sharing can drastically harm multithreaded performance. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_NO_FWD. Related metrics: tma_bottleneck_memory_synchronization, tma_contested_accesses, tma_false_sharing, tma_machine_clears, tma_remote_cache", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -1076,7 +1078,7 @@ "MetricExpr": "cpu_core@ARITH.DIV_ACTIVE@ / tma_info_thread_clks", "MetricGroup": "BvCB;TopdownL3;tma_L3_group;tma_core_bound_group", "MetricName": "tma_divider", - "MetricThreshold": "tma_divider > 0.2 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_divider > 0.2 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)", "PublicDescription": "This metric represents fraction of cycles where the Divider unit was active. Divide and square root instructions are performed by the Divider unit and can take considerably longer latency than integer or Floating Point addition; subtraction; or multiplication. Sample with: ARITH.DIV_ACTIVE", "ScaleUnit": "100%", "Unit": "cpu_core" @@ -1086,7 +1088,7 @@ "MetricExpr": "cpu_core@MEMORY_STALLS.MEM@ / tma_info_thread_clks", "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_dram_bound", - "MetricThreshold": "tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", "PublicDescription": "This metric estimates how often the CPU was stalled on accesses to external memory (DRAM) by loads. Better caching can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L3_MISS", "ScaleUnit": "100%", "Unit": "cpu_core" @@ -1097,7 +1099,7 @@ "MetricGroup": "DSB;FetchBW;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group", "MetricName": "tma_dsb", "MetricThreshold": "tma_dsb > 0.15 & tma_fetch_bandwidth > 0.2", - "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to DSB (decoded uop cache) fetch pipeline. For example; inefficient utilization of the DSB cache structure or bank conflict when reading from it; are categorized here", + "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to DSB (decoded uop cache) fetch pipeline. For example; inefficient utilization of the DSB cache structure or bank conflict when reading from it; are categorized here.", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -1106,28 +1108,28 @@ "MetricExpr": "cpu_core@DSB2MITE_SWITCHES.PENALTY_CYCLES@ / tma_info_thread_clks", "MetricGroup": "DSBmiss;FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueFB", "MetricName": "tma_dsb_switches", - "MetricThreshold": "tma_dsb_switches > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", - "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines. The DSB (decoded i-cache) is a Uop Cache where the front-end directly delivers Uops (micro operations) avoiding heavy x86 decoding. The DSB pipeline has shorter latency and delivered higher bandwidth than the MITE (legacy instruction decode pipeline). Switching between the two pipelines can cause penalties hence this metric measures the exposed penalty. Sample with: FRONTEND_RETIRED.DSB_MISS. Related metrics: tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp", + "MetricThreshold": "tma_dsb_switches > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines. The DSB (decoded i-cache) is a Uop Cache where the front-end directly delivers Uops (micro operations) avoiding heavy x86 decoding. The DSB pipeline has shorter latency and delivered higher bandwidth than the MITE (legacy instruction decode pipeline). Switching between the two pipelines can cause penalties hence this metric measures the exposed penalty. Sample with: FRONTEND_RETIRED.DSB_MISS_PS. Related metrics: tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp", "ScaleUnit": "100%", "Unit": "cpu_core" }, { "BriefDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses", - "MetricExpr": "(min(cpu_core@MEM_INST_RETIRED.STLB_HIT_LOADS@ * cpu_core@mem_inst_retired.stlb_hit_loads@R, cpu_core@MEM_INST_RETIRED.STLB_HIT_LOADS@ * 7) if 0 < cpu_core@mem_inst_retired.stlb_hit_loads@R else cpu_core@MEM_INST_RETIRED.STLB_HIT_LOADS@ * 7) / tma_info_thread_clks + tma_load_stlb_miss", + "MetricExpr": "cpu_core@MEM_INST_RETIRED.STLB_HIT_LOADS@ * min(cpu_core@MEM_INST_RETIRED.STLB_HIT_LOADS@R, 7) / tma_info_thread_clks + tma_load_stlb_miss", "MetricGroup": "BvMT;MemoryTLB;TopdownL4;tma_L4_group;tma_issueTLB;tma_l1_bound_group", "MetricName": "tma_dtlb_load", - "MetricThreshold": "tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", - "PublicDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses. TLBs (Translation Look-aside Buffers) are processor caches for recently used entries out of the Page Tables that are used to map virtual- to physical-addresses by the operating system. This metric approximates the potential delay of demand loads missing the first-level data TLB (assuming worst case scenario with back to back misses to different pages). This includes hitting in the second-level TLB (STLB) as well as performing a hardware page walk on an STLB miss. Sample with: MEM_INST_RETIRED.STLB_MISS_LOADS. Related metrics: tma_dtlb_store", + "MetricThreshold": "tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses. TLBs (Translation Look-aside Buffers) are processor caches for recently used entries out of the Page Tables that are used to map virtual- to physical-addresses by the operating system. This metric approximates the potential delay of demand loads missing the first-level data TLB (assuming worst case scenario with back to back misses to different pages). This includes hitting in the second-level TLB (STLB) as well as performing a hardware page walk on an STLB miss. Sample with: MEM_INST_RETIRED.STLB_MISS_LOADS_PS. Related metrics: tma_bottleneck_memory_data_tlbs, tma_dtlb_store", "ScaleUnit": "100%", "Unit": "cpu_core" }, { "BriefDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses", - "MetricExpr": "(min(cpu_core@MEM_INST_RETIRED.STLB_HIT_STORES@ * cpu_core@mem_inst_retired.stlb_hit_stores@R, cpu_core@MEM_INST_RETIRED.STLB_HIT_STORES@ * 7) if 0 < cpu_core@mem_inst_retired.stlb_hit_stores@R else cpu_core@MEM_INST_RETIRED.STLB_HIT_STORES@ * 7) / tma_info_thread_clks + tma_store_stlb_miss", + "MetricExpr": "cpu_core@MEM_INST_RETIRED.STLB_HIT_STORES@ * min(cpu_core@MEM_INST_RETIRED.STLB_HIT_STORES@R, 7) / tma_info_thread_clks + tma_store_stlb_miss", "MetricGroup": "BvMT;MemoryTLB;TopdownL4;tma_L4_group;tma_issueTLB;tma_store_bound_group", "MetricName": "tma_dtlb_store", - "MetricThreshold": "tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", - "PublicDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses. As with ordinary data caching; focus on improving data locality and reducing working-set size to reduce DTLB overhead. Additionally; consider using profile-guided optimization (PGO) to collocate frequently-used data on the same page. Try using larger page sizes for large amounts of frequently-used data. Sample with: MEM_INST_RETIRED.STLB_MISS_STORES. Related metrics: tma_dtlb_load", + "MetricThreshold": "tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses. As with ordinary data caching; focus on improving data locality and reducing working-set size to reduce DTLB overhead. Additionally; consider using profile-guided optimization (PGO) to collocate frequently-used data on the same page. Try using larger page sizes for large amounts of frequently-used data. Sample with: MEM_INST_RETIRED.STLB_MISS_STORES_PS. Related metrics: tma_bottleneck_memory_data_tlbs, tma_dtlb_load", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -1136,7 +1138,7 @@ "MetricExpr": "28 * tma_info_system_core_frequency * cpu_core@OCR.DEMAND_RFO.L3_HIT.SNOOP_HITM@ / tma_info_thread_clks", "MetricGroup": "BvMS;DataSharing;LockCont;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_store_bound_group", "MetricName": "tma_false_sharing", - "MetricThreshold": "(tma_false_sharing > 0.05) & ((tma_store_bound > 0.2) & ((tma_memory_bound > 0.2) & ((tma_backend_bound > 0.2))))", + "MetricThreshold": "tma_false_sharing > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", "PublicDescription": "This metric roughly estimates how often CPU was handling synchronizations due to False Sharing. False Sharing is a multithreading hiccup; where multiple Logical Processors contend on different data-elements mapped into the same cache line. Sample with: OCR.DEMAND_RFO.L3_HIT.SNOOP_HITM. Related metrics: tma_bottleneck_memory_synchronization, tma_contested_accesses, tma_data_sharing, tma_machine_clears, tma_remote_cache", "ScaleUnit": "100%", "Unit": "cpu_core" @@ -1147,7 +1149,7 @@ "MetricGroup": "BvMB;MemoryBW;TopdownL4;tma_L4_group;tma_issueBW;tma_issueSL;tma_issueSmSt;tma_l1_bound_group", "MetricName": "tma_fb_full", "MetricThreshold": "tma_fb_full > 0.3", - "PublicDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed. The higher the metric value; the deeper the memory hierarchy level the misses are satisfied from (metric values >1 are valid). Often it hints on approaching bandwidth limits (to L2 cache; L3 cache or external memory). Related metrics: tma_bottleneck_cache_memory_bandwidth, tma_mem_bandwidth, tma_sq_full, tma_store_latency, tma_streaming_stores", + "PublicDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed. The higher the metric value; the deeper the memory hierarchy level the misses are satisfied from (metric values >1 are valid). Often it hints on approaching bandwidth limits (to L2 cache; L3 cache or external memory). Related metrics: tma_bottleneck_cache_memory_bandwidth, tma_info_system_dram_bw_use, tma_mem_bandwidth, tma_sq_full, tma_store_latency, tma_streaming_stores", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -1158,18 +1160,18 @@ "MetricName": "tma_fetch_bandwidth", "MetricThreshold": "tma_fetch_bandwidth > 0.2", "MetricgroupNoGroup": "TopdownL2", - "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues. For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Related metrics: tma_dsb_switches, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp. Sample with: FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1;FRONTEND_RETIRED.LATENCY_GE_1;FRONTEND_RETIRED.LATENCY_GE_2. Related metrics: tma_dsb_switches, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp", + "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues. For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Sample with: FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1;FRONTEND_RETIRED.LATENCY_GE_1;FRONTEND_RETIRED.LATENCY_GE_2. Related metrics: tma_dsb_switches, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp", "ScaleUnit": "100%", "Unit": "cpu_core" }, { "BriefDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues", - "MetricExpr": "topdown\\-fetch\\-lat / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * slots", + "MetricExpr": "cpu_core@topdown\\-fetch\\-lat@ / (cpu_core@topdown\\-fe\\-bound@ + cpu_core@topdown\\-bad\\-spec@ + cpu_core@topdown\\-retiring@ + cpu_core@topdown\\-be\\-bound@) + 0 * tma_info_thread_slots", "MetricGroup": "Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group", "MetricName": "tma_fetch_latency", "MetricThreshold": "tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", "MetricgroupNoGroup": "TopdownL2", - "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues. For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: FRONTEND_RETIRED.LATENCY_GE_16, FRONTEND_RETIRED.LATENCY_GE_8", + "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues. For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: FRONTEND_RETIRED.LATENCY_GE_16_PS;FRONTEND_RETIRED.LATENCY_GE_8_PS", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -1179,7 +1181,7 @@ "MetricGroup": "TopdownL3;tma_L3_group;tma_heavy_operations_group;tma_issueD0", "MetricName": "tma_few_uops_instructions", "MetricThreshold": "tma_few_uops_instructions > 0.05 & tma_heavy_operations > 0.1", - "PublicDescription": "This metric represents fraction of slots where the CPU was retiring instructions that that are decoder into two or more uops. This highly-correlates with the number of uops in such instructions", + "PublicDescription": "This metric represents fraction of slots where the CPU was retiring instructions that that are decoder into two or more uops. This highly-correlates with the number of uops in such instructions. Related metrics: tma_decoder0_alone", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -1189,7 +1191,7 @@ "MetricGroup": "HPC;TopdownL3;tma_L3_group;tma_light_operations_group", "MetricName": "tma_fp_arith", "MetricThreshold": "tma_fp_arith > 0.2 & tma_light_operations > 0.6", - "PublicDescription": "This metric represents overall arithmetic floating-point (FP) operations fraction the CPU has executed (retired). Note this metric's value may exceed its parent due to use of \"Uops\" CountDomain and FMA double-counting", + "PublicDescription": "This metric represents overall arithmetic floating-point (FP) operations fraction the CPU has executed (retired). Note this metric's value may exceed its parent due to use of \"Uops\" CountDomain and FMA double-counting.", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -1199,16 +1201,16 @@ "MetricGroup": "HPC;TopdownL5;tma_L5_group;tma_assists_group", "MetricName": "tma_fp_assists", "MetricThreshold": "tma_fp_assists > 0.1", - "PublicDescription": "This metric roughly estimates fraction of slots the CPU retired uops as a result of handing Floating Point (FP) Assists. FP Assist may apply when working with very small floating point values (so-called Denormals)", + "PublicDescription": "This metric roughly estimates fraction of slots the CPU retired uops as a result of handing Floating Point (FP) Assists. FP Assist may apply when working with very small floating point values (so-called Denormals).", "ScaleUnit": "100%", "Unit": "cpu_core" }, { - "BriefDescription": "This metric represents fraction of cycles where the Floating-Point Divider unit was active", + "BriefDescription": "This metric represents fraction of cycles where the Floating-Point Divider unit was active.", "MetricExpr": "cpu_core@ARITH.FPDIV_ACTIVE@ / tma_info_thread_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_divider_group", "MetricName": "tma_fp_divider", - "MetricThreshold": "tma_fp_divider > 0.2 & tma_divider > 0.2 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_fp_divider > 0.2 & (tma_divider > 0.2 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -1217,8 +1219,8 @@ "MetricExpr": "cpu_core@FP_ARITH_INST_RETIRED.SCALAR@ / (tma_retiring * tma_info_thread_slots)", "MetricGroup": "Compute;Flops;TopdownL4;tma_L4_group;tma_fp_arith_group;tma_issue2P", "MetricName": "tma_fp_scalar", - "MetricThreshold": "tma_fp_scalar > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6", - "PublicDescription": "This metric approximates arithmetic floating-point (FP) scalar uops fraction the CPU has retired. May overcount due to FMA double counting. Related metrics: tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_int_vector_128b, tma_int_vector_256b, tma_ports_utilized_2", + "MetricThreshold": "tma_fp_scalar > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6)", + "PublicDescription": "This metric approximates arithmetic floating-point (FP) scalar uops fraction the CPU has retired. May overcount due to FMA double counting. Related metrics: tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -1227,8 +1229,8 @@ "MetricExpr": "cpu_core@FP_ARITH_INST_RETIRED.VECTOR@ / (tma_retiring * tma_info_thread_slots)", "MetricGroup": "Compute;Flops;TopdownL4;tma_L4_group;tma_fp_arith_group;tma_issue2P", "MetricName": "tma_fp_vector", - "MetricThreshold": "tma_fp_vector > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6", - "PublicDescription": "This metric approximates arithmetic floating-point (FP) vector uops fraction the CPU has retired aggregated across all vector widths. May overcount due to FMA double counting. Related metrics: tma_fp_scalar, tma_fp_vector_128b, tma_fp_vector_256b, tma_int_vector_128b, tma_int_vector_256b, tma_ports_utilized_2", + "MetricThreshold": "tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6)", + "PublicDescription": "This metric approximates arithmetic floating-point (FP) vector uops fraction the CPU has retired aggregated across all vector widths. May overcount due to FMA double counting. Related metrics: tma_fp_scalar, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -1237,8 +1239,8 @@ "MetricExpr": "(cpu_core@FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE@ + cpu_core@FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE@) / (tma_retiring * tma_info_thread_slots)", "MetricGroup": "Compute;Flops;TopdownL5;tma_L5_group;tma_fp_vector_group;tma_issue2P", "MetricName": "tma_fp_vector_128b", - "MetricThreshold": "tma_fp_vector_128b > 0.1 & tma_fp_vector > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6", - "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 128-bit wide vectors. May overcount due to FMA double counting prior to LNL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_256b, tma_int_vector_128b, tma_int_vector_256b, tma_ports_utilized_2", + "MetricThreshold": "tma_fp_vector_128b > 0.1 & (tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6))", + "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 128-bit wide vectors. May overcount due to FMA double counting prior to LNL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -1247,15 +1249,15 @@ "MetricExpr": "cpu_core@FP_ARITH_INST_RETIRED.VECTOR\\,umask\\=0x30@ / (tma_retiring * tma_info_thread_slots)", "MetricGroup": "Compute;Flops;TopdownL5;tma_L5_group;tma_fp_vector_group;tma_issue2P", "MetricName": "tma_fp_vector_256b", - "MetricThreshold": "tma_fp_vector_256b > 0.1 & tma_fp_vector > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6", - "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 256-bit wide vectors. May overcount due to FMA double counting prior to LNL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_int_vector_128b, tma_int_vector_256b, tma_ports_utilized_2", + "MetricThreshold": "tma_fp_vector_256b > 0.1 & (tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6))", + "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 256-bit wide vectors. May overcount due to FMA double counting prior to LNL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%", "Unit": "cpu_core" }, { "BriefDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend", "DefaultMetricgroupName": "TopdownL1", - "MetricExpr": "topdown\\-fe\\-bound / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * slots", + "MetricExpr": "cpu_core@topdown\\-fe\\-bound@ / (cpu_core@topdown\\-fe\\-bound@ + cpu_core@topdown\\-bad\\-spec@ + cpu_core@topdown\\-retiring@ + cpu_core@topdown\\-be\\-bound@) + 0 * tma_info_thread_slots", "MetricGroup": "BvFB;BvIO;Default;PGO;TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_frontend_bound", "MetricThreshold": "tma_frontend_bound > 0.15", @@ -1265,23 +1267,23 @@ "Unit": "cpu_core" }, { - "BriefDescription": "This metric represents fraction of slots where the CPU was retiring fused instructions , where one uop can represent multiple contiguous instructions", + "BriefDescription": "This metric represents fraction of slots where the CPU was retiring fused instructions -- where one uop can represent multiple contiguous instructions", "MetricExpr": "tma_light_operations * cpu_core@INST_RETIRED.MACRO_FUSED@ / (tma_retiring * tma_info_thread_slots)", "MetricGroup": "Branches;BvBO;Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group", "MetricName": "tma_fused_instructions", "MetricThreshold": "tma_fused_instructions > 0.1 & tma_light_operations > 0.6", - "PublicDescription": "This metric represents fraction of slots where the CPU was retiring fused instructions , where one uop can represent multiple contiguous instructions. CMP+JCC or DEC+JCC are common examples of legacy fusions. {([MTL] Note new MOV+OP and Load+OP fusions appear under Other_Light_Ops in MTL!)}", + "PublicDescription": "This metric represents fraction of slots where the CPU was retiring fused instructions -- where one uop can represent multiple contiguous instructions. CMP+JCC or DEC+JCC are common examples of legacy fusions. {([MTL] Note new MOV+OP and Load+OP fusions appear under Other_Light_Ops in MTL!)}", "ScaleUnit": "100%", "Unit": "cpu_core" }, { - "BriefDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations , instructions that require two or more uops or micro-coded sequences", - "MetricExpr": "topdown\\-heavy\\-ops / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * slots", + "BriefDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences", + "MetricExpr": "cpu_core@topdown\\-heavy\\-ops@ / (cpu_core@topdown\\-fe\\-bound@ + cpu_core@topdown\\-bad\\-spec@ + cpu_core@topdown\\-retiring@ + cpu_core@topdown\\-be\\-bound@) + 0 * tma_info_thread_slots", "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_heavy_operations", "MetricThreshold": "tma_heavy_operations > 0.1", "MetricgroupNoGroup": "TopdownL2", - "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations , instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences.([ICL+] Note this may overcount due to approximation using indirect events; [ADL+]). Sample with: UOPS_RETIRED.HEAVY", + "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences.([ICL+] Note this may overcount due to approximation using indirect events; [ADL+]). Sample with: UOPS_RETIRED.HEAVY", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -1290,26 +1292,26 @@ "MetricExpr": "cpu_core@ICACHE_DATA.STALLS@ / tma_info_thread_clks", "MetricGroup": "BigFootprint;BvBC;FetchLat;IcMiss;TopdownL3;tma_L3_group;tma_fetch_latency_group", "MetricName": "tma_icache_misses", - "MetricThreshold": "tma_icache_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", - "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to instruction cache misses. Sample with: FRONTEND_RETIRED.L2_MISS, FRONTEND_RETIRED.L1I_MISS", + "MetricThreshold": "tma_icache_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to instruction cache misses. Sample with: FRONTEND_RETIRED.L2_MISS_PS;FRONTEND_RETIRED.L1I_MISS_PS", "ScaleUnit": "100%", "Unit": "cpu_core" }, { - "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to retired misprediction by indirect CALL instructions", - "MetricExpr": "cpu_core@BR_MISP_RETIRED.INDIRECT_CALL_COST@ * cpu_core@br_misp_retired.indirect_call_cost@R / tma_info_thread_clks", + "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to retired misprediction by indirect CALL instructions.", + "MetricExpr": "cpu_core@BR_MISP_RETIRED.INDIRECT_CALL_COST@ * cpu_core@BR_MISP_RETIRED.INDIRECT_CALL_COST@R / tma_info_thread_clks", "MetricGroup": "BrMispredicts;TopdownL3;tma_L3_group;tma_branch_mispredicts_group", "MetricName": "tma_ind_call_mispredicts", - "MetricThreshold": "tma_ind_call_mispredicts > 0.05 & tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", + "MetricThreshold": "tma_ind_call_mispredicts > 0.05 & (tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15)", "ScaleUnit": "100%", "Unit": "cpu_core" }, { - "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to retired misprediction by indirect JMP instructions", - "MetricExpr": "max((cpu_core@BR_MISP_RETIRED.INDIRECT_COST@ * cpu_core@br_misp_retired.indirect_cost@R - cpu_core@BR_MISP_RETIRED.INDIRECT_CALL_COST@ * cpu_core@br_misp_retired.indirect_call_cost@R) / tma_info_thread_clks, 0)", + "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to retired misprediction by indirect JMP instructions.", + "MetricExpr": "max((cpu_core@BR_MISP_RETIRED.INDIRECT_COST@ * cpu_core@BR_MISP_RETIRED.INDIRECT_COST@R - cpu_core@BR_MISP_RETIRED.INDIRECT_CALL_COST@ * cpu_core@BR_MISP_RETIRED.INDIRECT_CALL_COST@R) / tma_info_thread_clks, 0)", "MetricGroup": "BrMispredicts;TopdownL3;tma_L3_group;tma_branch_mispredicts_group", "MetricName": "tma_ind_jump_mispredicts", - "MetricThreshold": "tma_ind_jump_mispredicts > 0.05 & tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", + "MetricThreshold": "tma_ind_jump_mispredicts > 0.05 & (tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15)", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -1322,7 +1324,7 @@ "Unit": "cpu_core" }, { - "BriefDescription": "Instructions per retired Mispredicts for conditional non-taken branches (lower number means higher occurrence rate)", + "BriefDescription": "Instructions per retired Mispredicts for conditional non-taken branches (lower number means higher occurrence rate).", "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / cpu_core@BR_MISP_RETIRED.COND_NTAKEN@", "MetricGroup": "Bad;BrMispredicts", "MetricName": "tma_info_bad_spec_ipmisp_cond_ntaken", @@ -1330,29 +1332,29 @@ "Unit": "cpu_core" }, { - "BriefDescription": "Instructions per retired Mispredicts for conditional backward-taken branches (lower number means higher occurrence rate)", + "BriefDescription": "Instructions per retired Mispredicts for conditional backward-taken branches (lower number means higher occurrence rate).", "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / cpu_core@BR_MISP_RETIRED.COND_TAKEN_BWD@", "MetricGroup": "Bad;BrMispredicts", "MetricName": "tma_info_bad_spec_ipmisp_cond_taken_bwd", "Unit": "cpu_core" }, { - "BriefDescription": "Instructions per retired Mispredicts for conditional forward-taken branches (lower number means higher occurrence rate)", + "BriefDescription": "Instructions per retired Mispredicts for conditional forward-taken branches (lower number means higher occurrence rate).", "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / cpu_core@BR_MISP_RETIRED.COND_TAKEN_FWD@", "MetricGroup": "Bad;BrMispredicts", "MetricName": "tma_info_bad_spec_ipmisp_cond_taken_fwd", "Unit": "cpu_core" }, { - "BriefDescription": "Instructions per retired Mispredicts for indirect CALL or JMP branches (lower number means higher occurrence rate)", + "BriefDescription": "Instructions per retired Mispredicts for indirect CALL or JMP branches (lower number means higher occurrence rate).", "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / cpu_core@BR_MISP_RETIRED.INDIRECT@", "MetricGroup": "Bad;BrMispredicts", "MetricName": "tma_info_bad_spec_ipmisp_indirect", - "MetricThreshold": "tma_info_bad_spec_ipmisp_indirect < 1000", + "MetricThreshold": "tma_info_bad_spec_ipmisp_indirect < 1e3", "Unit": "cpu_core" }, { - "BriefDescription": "Instructions per retired Mispredicts for return branches (lower number means higher occurrence rate)", + "BriefDescription": "Instructions per retired Mispredicts for return branches (lower number means higher occurrence rate).", "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / cpu_core@BR_MISP_RETIRED.RET@", "MetricGroup": "Bad;BrMispredicts", "MetricName": "tma_info_bad_spec_ipmisp_ret", @@ -1376,7 +1378,7 @@ }, { "BriefDescription": "Total pipeline cost of DSB (uop cache) hits - subset of the Instruction_Fetch_BW Bottleneck", - "MetricExpr": "100 * (tma_frontend_bound * (tma_fetch_bandwidth / (tma_fetch_latency + tma_fetch_bandwidth)) * (tma_dsb / (tma_mite + tma_dsb + tma_lsd + tma_ms)))", + "MetricExpr": "100 * (tma_frontend_bound * (tma_fetch_bandwidth / (tma_fetch_bandwidth + tma_fetch_latency)) * (tma_dsb / (tma_dsb + tma_lsd + tma_mite + tma_ms)))", "MetricGroup": "DSB;Fed;FetchBW;tma_issueFB", "MetricName": "tma_info_botlnk_l2_dsb_bandwidth", "MetricThreshold": "tma_info_botlnk_l2_dsb_bandwidth > 10", @@ -1385,7 +1387,7 @@ }, { "BriefDescription": "Total pipeline cost of DSB (uop cache) misses - subset of the Instruction_Fetch_BW Bottleneck", - "MetricExpr": "100 * (tma_fetch_latency * tma_dsb_switches / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches) + tma_fetch_bandwidth * tma_mite / (tma_mite + tma_dsb + tma_lsd + tma_ms))", + "MetricExpr": "100 * (tma_fetch_latency * tma_dsb_switches / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) + tma_fetch_bandwidth * tma_mite / (tma_dsb + tma_lsd + tma_mite + tma_ms))", "MetricGroup": "DSBmiss;Fed;tma_issueFB", "MetricName": "tma_info_botlnk_l2_dsb_misses", "MetricThreshold": "tma_info_botlnk_l2_dsb_misses > 10", @@ -1394,10 +1396,11 @@ }, { "BriefDescription": "Total pipeline cost of Instruction Cache misses - subset of the Big_Code Bottleneck", - "MetricExpr": "100 * (tma_fetch_latency * tma_icache_misses / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches))", + "MetricExpr": "100 * (tma_fetch_latency * tma_icache_misses / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches))", "MetricGroup": "Fed;FetchLat;IcMiss;tma_issueFL", "MetricName": "tma_info_botlnk_l2_ic_misses", "MetricThreshold": "tma_info_botlnk_l2_ic_misses > 5", + "PublicDescription": "Total pipeline cost of Instruction Cache misses - subset of the Big_Code Bottleneck. Related metrics: ", "Unit": "cpu_core" }, { @@ -1463,12 +1466,12 @@ "MetricExpr": "(cpu_core@FP_ARITH_DISPATCHED.V0@ + cpu_core@FP_ARITH_DISPATCHED.V1@ + cpu_core@FP_ARITH_DISPATCHED.V2@ + cpu_core@FP_ARITH_DISPATCHED.V3@) / (4 * tma_info_thread_clks)", "MetricGroup": "Cor;Flops;HPC", "MetricName": "tma_info_core_fp_arith_utilization", - "PublicDescription": "Actual per-core usage of the Floating Point non-X87 execution units (regardless of precision or vector-width). Values > 1 are possible due to ([BDW+] Fused-Multiply Add (FMA) counting - common; [ADL+] use all of ADD/MUL/FMA in Scalar or 128/256-bit vectors - less common)", + "PublicDescription": "Actual per-core usage of the Floating Point non-X87 execution units (regardless of precision or vector-width). Values > 1 are possible due to ([BDW+] Fused-Multiply Add (FMA) counting - common; [ADL+] use all of ADD/MUL/FMA in Scalar or 128/256-bit vectors - less common).", "Unit": "cpu_core" }, { "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is execution) per thread (logical-processor)", - "MetricExpr": "cpu_core@UOPS_EXECUTED.THREAD@ / cpu_core@UOPS_EXECUTED.THREAD\\,cmask\\=0x1@", + "MetricExpr": "cpu_core@UOPS_EXECUTED.THREAD@ / cpu_core@UOPS_EXECUTED.THREAD\\,cmask\\=1@", "MetricGroup": "Backend;Cor;Pipeline;PortsUtil", "MetricName": "tma_info_core_ilp", "Unit": "cpu_core" @@ -1483,15 +1486,15 @@ "Unit": "cpu_core" }, { - "BriefDescription": "Average number of cycles of a switch from the DSB fetch-unit to MITE fetch unit - see DSB_Switches tree node for details", - "MetricExpr": "cpu_core@DSB2MITE_SWITCHES.PENALTY_CYCLES@ / cpu_core@DSB2MITE_SWITCHES.PENALTY_CYCLES\\,cmask\\=0x1\\,edge\\=0x1@", + "BriefDescription": "Average number of cycles of a switch from the DSB fetch-unit to MITE fetch unit - see DSB_Switches tree node for details.", + "MetricExpr": "cpu_core@DSB2MITE_SWITCHES.PENALTY_CYCLES@ / cpu_core@DSB2MITE_SWITCHES.PENALTY_CYCLES\\,cmask\\=1\\,edge@", "MetricGroup": "DSBmiss", "MetricName": "tma_info_frontend_dsb_switch_cost", "Unit": "cpu_core" }, { "BriefDescription": "This metric represents fraction of cycles the CPU retirement was stalled likely due to retired DSB misses", - "MetricExpr": "cpu_core@FRONTEND_RETIRED.ANY_DSB_MISS@ * cpu_core@frontend_retired.any_dsb_miss@R / tma_info_thread_clks", + "MetricExpr": "cpu_core@FRONTEND_RETIRED.ANY_DSB_MISS@ * cpu_core@FRONTEND_RETIRED.ANY_DSB_MISS@R / tma_info_thread_clks", "MetricGroup": "DSBmiss;Fed;FetchLat", "MetricName": "tma_info_frontend_dsb_switches_ret", "MetricThreshold": "tma_info_frontend_dsb_switches_ret > 0.05", @@ -1499,7 +1502,7 @@ }, { "BriefDescription": "Average number of Uops issued by front-end when it issued something", - "MetricExpr": "cpu_core@UOPS_ISSUED.ANY@ / cpu_core@UOPS_ISSUED.ANY\\,cmask\\=0x1@", + "MetricExpr": "cpu_core@UOPS_ISSUED.ANY@ / cpu_core@UOPS_ISSUED.ANY\\,cmask\\=1@", "MetricGroup": "Fed;FetchBW", "MetricName": "tma_info_frontend_fetch_upc", "Unit": "cpu_core" @@ -1549,7 +1552,7 @@ }, { "BriefDescription": "This metric represents fraction of cycles the CPU retirement was stalled likely due to retired operations that invoke the Microcode Sequencer", - "MetricExpr": "cpu_core@FRONTEND_RETIRED.MS_FLOWS@ * cpu_core@frontend_retired.ms_flows@R / tma_info_thread_clks", + "MetricExpr": "cpu_core@FRONTEND_RETIRED.MS_FLOWS@ * cpu_core@FRONTEND_RETIRED.MS_FLOWS@R / tma_info_thread_clks", "MetricGroup": "Fed;FetchLat;MicroSeq", "MetricName": "tma_info_frontend_ms_latency_ret", "MetricThreshold": "tma_info_frontend_ms_latency_ret > 0.05", @@ -1564,21 +1567,21 @@ }, { "BriefDescription": "Average number of cycles the front-end was delayed due to an Unknown Branch detection", - "MetricExpr": "cpu_core@INT_MISC.UNKNOWN_BRANCH_CYCLES@ / cpu_core@INT_MISC.UNKNOWN_BRANCH_CYCLES\\,cmask\\=0x1\\,edge\\=0x1@", + "MetricExpr": "cpu_core@INT_MISC.UNKNOWN_BRANCH_CYCLES@ / cpu_core@INT_MISC.UNKNOWN_BRANCH_CYCLES\\,cmask\\=1\\,edge@", "MetricGroup": "Fed", "MetricName": "tma_info_frontend_unknown_branch_cost", - "PublicDescription": "Average number of cycles the front-end was delayed due to an Unknown Branch detection. See Unknown_Branches node", + "PublicDescription": "Average number of cycles the front-end was delayed due to an Unknown Branch detection. See Unknown_Branches node.", "Unit": "cpu_core" }, { "BriefDescription": "This metric represents fraction of cycles the CPU retirement was stalled likely due to retired branches who got branch address clears", - "MetricExpr": "cpu_core@FRONTEND_RETIRED.UNKNOWN_BRANCH@ * cpu_core@frontend_retired.unknown_branch@R / tma_info_thread_clks", + "MetricExpr": "cpu_core@FRONTEND_RETIRED.UNKNOWN_BRANCH@ * cpu_core@FRONTEND_RETIRED.UNKNOWN_BRANCH@R / tma_info_thread_clks", "MetricGroup": "Fed;FetchLat", "MetricName": "tma_info_frontend_unknown_branches_ret", "Unit": "cpu_core" }, { - "BriefDescription": "Branch instructions per taken branch", + "BriefDescription": "Branch instructions per taken branch.", "MetricExpr": "cpu_core@BR_INST_RETIRED.ALL_BRANCHES@ / cpu_core@BR_INST_RETIRED.NEAR_TAKEN@", "MetricGroup": "Branches;Fed;PGO", "MetricName": "tma_info_inst_mix_bptkbranch", @@ -1598,7 +1601,7 @@ "MetricGroup": "Flops;InsType", "MetricName": "tma_info_inst_mix_iparith", "MetricThreshold": "tma_info_inst_mix_iparith < 10", - "PublicDescription": "Instructions per FP Arithmetic instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting. Approximated prior to BDW", + "PublicDescription": "Instructions per FP Arithmetic instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting. Approximated prior to BDW.", "Unit": "cpu_core" }, { @@ -1607,7 +1610,7 @@ "MetricGroup": "Flops;FpVector;InsType", "MetricName": "tma_info_inst_mix_iparith_avx128", "MetricThreshold": "tma_info_inst_mix_iparith_avx128 < 10", - "PublicDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting", + "PublicDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting.", "Unit": "cpu_core" }, { @@ -1616,7 +1619,7 @@ "MetricGroup": "Flops;FpVector;InsType", "MetricName": "tma_info_inst_mix_iparith_avx256", "MetricThreshold": "tma_info_inst_mix_iparith_avx256 < 10", - "PublicDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting", + "PublicDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting.", "Unit": "cpu_core" }, { @@ -1625,7 +1628,7 @@ "MetricGroup": "Flops;FpScalar;InsType", "MetricName": "tma_info_inst_mix_iparith_scalar_dp", "MetricThreshold": "tma_info_inst_mix_iparith_scalar_dp < 10", - "PublicDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting", + "PublicDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting.", "Unit": "cpu_core" }, { @@ -1634,7 +1637,7 @@ "MetricGroup": "Flops;FpScalar;InsType", "MetricName": "tma_info_inst_mix_iparith_scalar_sp", "MetricThreshold": "tma_info_inst_mix_iparith_scalar_sp < 10", - "PublicDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting", + "PublicDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting.", "Unit": "cpu_core" }, { @@ -1697,7 +1700,7 @@ "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / cpu_core@BR_INST_RETIRED.NEAR_TAKEN@", "MetricGroup": "Branches;Fed;FetchBW;Frontend;PGO;tma_issueFB", "MetricName": "tma_info_inst_mix_iptb", - "MetricThreshold": "tma_info_inst_mix_iptb < 8 * 2 + 1", + "MetricThreshold": "tma_info_inst_mix_iptb < 17", "PublicDescription": "Instructions per taken branch. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_lcp", "Unit": "cpu_core" }, @@ -1709,6 +1712,13 @@ "Unit": "cpu_core" }, { + "BriefDescription": "Average per-thread data fill bandwidth to the L1 data cache [GB / sec]", + "MetricExpr": "64 * cpu_core@L1D.REPLACEMENT@ / 1e9 / tma_info_system_time", + "MetricGroup": "Mem;MemoryBW", + "MetricName": "tma_info_memory_l1d_cache_fill_bw", + "Unit": "cpu_core" + }, + { "BriefDescription": "Average per-thread data fill bandwidth to the Level 0 within L1D cache [GB / sec]", "MetricExpr": "64 * cpu_core@L1D.L0_REPLACEMENT@ / 1e9 / tma_info_system_time", "MetricGroup": "Mem;MemoryBW", @@ -1815,7 +1825,7 @@ }, { "BriefDescription": "Average Parallel L2 cache miss demand Loads", - "MetricExpr": "cpu_core@OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD@ / cpu_core@OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD\\,cmask\\=0x1@", + "MetricExpr": "cpu_core@OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD@ / cpu_core@OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD\\,cmask\\=1@", "MetricGroup": "Memory_BW;Offcore", "MetricName": "tma_info_memory_latency_load_l2_mlp", "Unit": "cpu_core" @@ -1873,7 +1883,7 @@ }, { "BriefDescription": "This metric represents fraction of cycles the CPU retirement was stalled likely due to STLB misses by demand loads", - "MetricExpr": "cpu_core@MEM_INST_RETIRED.STLB_MISS_LOADS@ * cpu_core@mem_inst_retired.stlb_miss_loads@R / tma_info_thread_clks", + "MetricExpr": "cpu_core@MEM_INST_RETIRED.STLB_MISS_LOADS@ * cpu_core@MEM_INST_RETIRED.STLB_MISS_LOADS@R / tma_info_thread_clks", "MetricGroup": "Mem;MemoryTLB", "MetricName": "tma_info_memory_tlb_load_stlb_miss_ret", "MetricThreshold": "tma_info_memory_tlb_load_stlb_miss_ret > 0.05", @@ -1896,7 +1906,7 @@ }, { "BriefDescription": "This metric represents fraction of cycles the CPU retirement was stalled likely due to STLB misses by demand stores", - "MetricExpr": "cpu_core@MEM_INST_RETIRED.STLB_MISS_STORES@ * cpu_core@mem_inst_retired.stlb_miss_stores@R / tma_info_thread_clks", + "MetricExpr": "cpu_core@MEM_INST_RETIRED.STLB_MISS_STORES@ * cpu_core@MEM_INST_RETIRED.STLB_MISS_STORES@R / tma_info_thread_clks", "MetricGroup": "Mem;MemoryTLB", "MetricName": "tma_info_memory_tlb_store_stlb_miss_ret", "MetricThreshold": "tma_info_memory_tlb_store_stlb_miss_ret > 0.05", @@ -1935,20 +1945,20 @@ "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / cpu_core@ASSISTS.ANY@", "MetricGroup": "MicroSeq;Pipeline;Ret;Retire", "MetricName": "tma_info_pipeline_ipassist", - "MetricThreshold": "tma_info_pipeline_ipassist < 100000", + "MetricThreshold": "tma_info_pipeline_ipassist < 100e3", "PublicDescription": "Instructions per a microcode Assist invocation. See Assists tree node for details (lower number means higher occurrence rate)", "Unit": "cpu_core" }, { - "BriefDescription": "Average number of Uops retired in cycles where at least one uop has retired", - "MetricExpr": "tma_retiring * tma_info_thread_slots / cpu_core@UOPS_RETIRED.SLOTS\\,cmask\\=0x1@", + "BriefDescription": "Average number of Uops retired in cycles where at least one uop has retired.", + "MetricExpr": "tma_retiring * tma_info_thread_slots / cpu_core@UOPS_RETIRED.SLOTS\\,cmask\\=1@", "MetricGroup": "Pipeline;Ret", "MetricName": "tma_info_pipeline_retire", "Unit": "cpu_core" }, { "BriefDescription": "Estimated fraction of retirement-cycles dealing with repeat instructions", - "MetricExpr": "cpu_core@INST_RETIRED.REP_ITERATION@ / cpu_core@UOPS_RETIRED.SLOTS\\,cmask\\=0x1@", + "MetricExpr": "cpu_core@INST_RETIRED.REP_ITERATION@ / cpu_core@UOPS_RETIRED.SLOTS\\,cmask\\=1@", "MetricGroup": "MicroSeq;Pipeline;Ret", "MetricName": "tma_info_pipeline_strings_cycles", "MetricThreshold": "tma_info_pipeline_strings_cycles > 0.1", @@ -1993,23 +2003,22 @@ }, { "BriefDescription": "Instructions per Far Branch ( Far Branches apply upon transition from application to operating system, handling interrupts, exceptions) [lower number means higher occurrence rate]", - "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / BR_INST_RETIRED.FAR_BRANCH:u", + "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / cpu_core@BR_INST_RETIRED.FAR_BRANCH@u", "MetricGroup": "Branches;OS", "MetricName": "tma_info_system_ipfarbranch", - "MetricThreshold": "tma_info_system_ipfarbranch < 1000000", + "MetricThreshold": "tma_info_system_ipfarbranch < 1e6", "Unit": "cpu_core" }, { "BriefDescription": "Cycles Per Instruction for the Operating System (OS) Kernel mode", - "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P:k / INST_RETIRED.ANY_P:k", + "MetricExpr": "cpu_core@CPU_CLK_UNHALTED.THREAD_P@k / cpu_core@INST_RETIRED.ANY_P@k", "MetricGroup": "OS", "MetricName": "tma_info_system_kernel_cpi", - "ScaleUnit": "1per_instr", "Unit": "cpu_core" }, { "BriefDescription": "Fraction of cycles spent in the Operating System (OS) Kernel mode", - "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P:k / cpu_core@CPU_CLK_UNHALTED.THREAD@", + "MetricExpr": "cpu_core@CPU_CLK_UNHALTED.THREAD_P@k / cpu_core@CPU_CLK_UNHALTED.THREAD@", "MetricGroup": "OS", "MetricName": "tma_info_system_kernel_utilization", "MetricThreshold": "tma_info_system_kernel_utilization > 0.05", @@ -2053,7 +2062,7 @@ "Unit": "cpu_core" }, { - "BriefDescription": "Per-Logical Processor actual clocks when the Logical Processor is active", + "BriefDescription": "Per-Logical Processor actual clocks when the Logical Processor is active.", "MetricExpr": "cpu_core@CPU_CLK_UNHALTED.THREAD@", "MetricGroup": "Pipeline", "MetricName": "tma_info_thread_clks", @@ -2064,7 +2073,6 @@ "MetricExpr": "1 / tma_info_thread_ipc", "MetricGroup": "Mem;Pipeline", "MetricName": "tma_info_thread_cpi", - "ScaleUnit": "1per_instr", "Unit": "cpu_core" }, { @@ -2072,7 +2080,7 @@ "MetricExpr": "cpu_core@UOPS_EXECUTED.THREAD@ / cpu_core@UOPS_ISSUED.ANY@", "MetricGroup": "Cor;Pipeline", "MetricName": "tma_info_thread_execute_per_issue", - "PublicDescription": "The ratio of Executed- by Issued-Uops. Ratio > 1 suggests high rate of uop micro-fusions. Ratio < 1 suggest high rate of \"execute\" at rename stage", + "PublicDescription": "The ratio of Executed- by Issued-Uops. Ratio > 1 suggests high rate of uop micro-fusions. Ratio < 1 suggest high rate of \"execute\" at rename stage.", "Unit": "cpu_core" }, { @@ -2084,7 +2092,7 @@ }, { "BriefDescription": "Total issue-pipeline slots (per-Physical Core till ICL; per-Logical Processor ICL onward)", - "MetricExpr": "slots", + "MetricExpr": "cpu_core@TOPDOWN.SLOTS@", "MetricGroup": "TmaL1;tma_L1_group", "MetricName": "tma_info_thread_slots", "Unit": "cpu_core" @@ -2102,15 +2110,15 @@ "MetricExpr": "tma_retiring * tma_info_thread_slots / cpu_core@BR_INST_RETIRED.NEAR_TAKEN@", "MetricGroup": "Branches;Fed;FetchBW", "MetricName": "tma_info_thread_uptb", - "MetricThreshold": "tma_info_thread_uptb < 8 * 1.5", + "MetricThreshold": "tma_info_thread_uptb < 12", "Unit": "cpu_core" }, { - "BriefDescription": "This metric represents fraction of cycles where the Integer Divider unit was active", + "BriefDescription": "This metric represents fraction of cycles where the Integer Divider unit was active.", "MetricExpr": "tma_divider - tma_fp_divider", "MetricGroup": "TopdownL4;tma_L4_group;tma_divider_group", "MetricName": "tma_int_divider", - "MetricThreshold": "tma_int_divider > 0.2 & tma_divider > 0.2 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_int_divider > 0.2 & (tma_divider > 0.2 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -2120,7 +2128,7 @@ "MetricGroup": "Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group", "MetricName": "tma_int_operations", "MetricThreshold": "tma_int_operations > 0.1 & tma_light_operations > 0.6", - "PublicDescription": "This metric represents overall Integer (Int) select operations fraction the CPU has executed (retired). Vector/Matrix Int operations and shuffles are counted. Note this metric's value may exceed its parent due to use of \"Uops\" CountDomain", + "PublicDescription": "This metric represents overall Integer (Int) select operations fraction the CPU has executed (retired). Vector/Matrix Int operations and shuffles are counted. Note this metric's value may exceed its parent due to use of \"Uops\" CountDomain.", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -2129,8 +2137,8 @@ "MetricExpr": "cpu_core@INT_VEC_RETIRED.128BIT@ / (tma_retiring * tma_info_thread_slots)", "MetricGroup": "Compute;IntVector;Pipeline;TopdownL4;tma_L4_group;tma_int_operations_group;tma_issue2P", "MetricName": "tma_int_vector_128b", - "MetricThreshold": "tma_int_vector_128b > 0.1 & tma_int_operations > 0.1 & tma_light_operations > 0.6", - "PublicDescription": "This metric represents 128-bit vector Integer ADD/SUB/SAD or VNNI (Vector Neural Network Instructions) uops fraction the CPU has retired. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_int_vector_256b, tma_ports_utilized_2", + "MetricThreshold": "tma_int_vector_128b > 0.1 & (tma_int_operations > 0.1 & tma_light_operations > 0.6)", + "PublicDescription": "This metric represents 128-bit vector Integer ADD/SUB/SAD or VNNI (Vector Neural Network Instructions) uops fraction the CPU has retired. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -2139,8 +2147,8 @@ "MetricExpr": "cpu_core@INT_VEC_RETIRED.256BIT@ / (tma_retiring * tma_info_thread_slots)", "MetricGroup": "Compute;IntVector;Pipeline;TopdownL4;tma_L4_group;tma_int_operations_group;tma_issue2P", "MetricName": "tma_int_vector_256b", - "MetricThreshold": "tma_int_vector_256b > 0.1 & tma_int_operations > 0.1 & tma_light_operations > 0.6", - "PublicDescription": "This metric represents 256-bit vector Integer ADD/SUB/SAD/MUL or VNNI (Vector Neural Network Instructions) uops fraction the CPU has retired. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_int_vector_128b, tma_ports_utilized_2", + "MetricThreshold": "tma_int_vector_256b > 0.1 & (tma_int_operations > 0.1 & tma_light_operations > 0.6)", + "PublicDescription": "This metric represents 256-bit vector Integer ADD/SUB/SAD/MUL or VNNI (Vector Neural Network Instructions) uops fraction the CPU has retired. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -2149,8 +2157,8 @@ "MetricExpr": "cpu_core@ICACHE_TAG.STALLS@ / tma_info_thread_clks", "MetricGroup": "BigFootprint;BvBC;FetchLat;MemoryTLB;TopdownL3;tma_L3_group;tma_fetch_latency_group", "MetricName": "tma_itlb_misses", - "MetricThreshold": "tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", - "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Instruction TLB (ITLB) misses. Sample with: FRONTEND_RETIRED.STLB_MISS, FRONTEND_RETIRED.ITLB_MISS", + "MetricThreshold": "tma_itlb_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Instruction TLB (ITLB) misses. Sample with: FRONTEND_RETIRED.STLB_MISS_PS;FRONTEND_RETIRED.ITLB_MISS_PS", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -2159,17 +2167,17 @@ "MetricExpr": "cpu_core@MEMORY_STALLS.L1@ / tma_info_thread_clks", "MetricGroup": "CacheHits;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_issueL1;tma_issueMC;tma_memory_bound_group", "MetricName": "tma_l1_bound", - "MetricThreshold": "tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", "PublicDescription": "This metric estimates how often the CPU was stalled without loads missing the L1 Data (L1D) cache. The L1D cache typically has the shortest latency. However; in certain cases like loads blocked on older stores; a load might suffer due to high latency even though it is being satisfied by the L1D. Another example is loads who miss in the TLB. These cases are characterized by execution unit stalls; while some non-completed demand load lives in the machine without having that demand load missing the L1 cache. Sample with: MEM_LOAD_RETIRED.L1_HIT. Related metrics: tma_clears_resteers, tma_machine_clears, tma_microcode_sequencer, tma_ms_switches, tma_ports_utilized_1", "ScaleUnit": "100%", "Unit": "cpu_core" }, { - "BriefDescription": "This metric estimates fraction of cycles with demand load accesses that hit Level 1 after missing Level 0 within the L1D cache", - "MetricExpr": "(min(cpu_core@MEM_LOAD_RETIRED.L1_HIT_L1@ * cpu_core@mem_load_retired.l1_hit_l1@R, cpu_core@MEM_LOAD_RETIRED.L1_HIT_L1@ * 9) if 0 < cpu_core@mem_load_retired.l1_hit_l1@R else cpu_core@MEM_LOAD_RETIRED.L1_HIT_L1@ * 9) / tma_info_thread_clks", + "BriefDescription": "This metric estimates fraction of cycles with demand load accesses that hit Level 1 after missing Level 0 within the L1D cache.", + "MetricExpr": "cpu_core@MEM_LOAD_RETIRED.L1_HIT_L1@ * min(cpu_core@MEM_LOAD_RETIRED.L1_HIT_L1@R, 9) / tma_info_thread_clks", "MetricGroup": "BvML;MemoryLat;TopdownL4;tma_L4_group;tma_l1_bound_group", "MetricName": "tma_l1_latency_capacity", - "MetricThreshold": "tma_l1_latency_capacity > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_l1_latency_capacity > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -2178,8 +2186,8 @@ "MetricExpr": "4 * cpu_core@DEPENDENT_LOADS.ANY@ / tma_info_thread_clks", "MetricGroup": "BvML;MemoryLat;TopdownL4;tma_L4_group;tma_l1_bound_group", "MetricName": "tma_l1_latency_dependency", - "MetricThreshold": "tma_l1_latency_dependency > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", - "PublicDescription": "This metric([SKL+] roughly; [LNL]) estimates fraction of cycles with demand load accesses that hit the L1D cache. The short latency of the L1D cache may be exposed in pointer-chasing memory access patterns as an example. Sample with: DEPENDENT_LOADS.ANY", + "MetricThreshold": "tma_l1_latency_dependency > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric([SKL+] roughly; [LNL]) estimates fraction of cycles with demand load accesses that hit the L1D cache. The short latency of the L1D cache may be exposed in pointer-chasing memory access patterns as an example. Sample with: MEM_LOAD_RETIRED.L1_HIT", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -2188,17 +2196,18 @@ "MetricExpr": "cpu_core@MEMORY_STALLS.L2@ / tma_info_thread_clks", "MetricGroup": "BvML;CacheHits;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_l2_bound", - "MetricThreshold": "tma_l2_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_l2_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", "PublicDescription": "This metric estimates how often the CPU was stalled due to L2 cache accesses by loads. Avoiding cache misses (i.e. L1 misses/L2 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L2_HIT", "ScaleUnit": "100%", "Unit": "cpu_core" }, { "BriefDescription": "This metric represents fraction of cycles with demand load accesses that hit the L2 cache under unloaded scenarios (possibly L2 latency limited)", - "MetricExpr": "(min(cpu_core@MEM_LOAD_RETIRED.L2_HIT@ * cpu_core@mem_load_retired.l2_hit@R, cpu_core@MEM_LOAD_RETIRED.L2_HIT@ * (3 * tma_info_system_core_frequency)) if 0 < cpu_core@mem_load_retired.l2_hit@R else cpu_core@MEM_LOAD_RETIRED.L2_HIT@ * (3 * tma_info_system_core_frequency)) * (1 + cpu_core@MEM_LOAD_RETIRED.FB_HIT@ / cpu_core@MEM_LOAD_RETIRED.L1_MISS@ / 2) / tma_info_thread_clks", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "cpu_core@MEM_LOAD_RETIRED.L2_HIT@ * min(cpu_core@MEM_LOAD_RETIRED.L2_HIT@R, 3 * tma_info_system_core_frequency) * (1 + cpu_core@MEM_LOAD_RETIRED.FB_HIT@ / cpu_core@MEM_LOAD_RETIRED.L1_MISS@ / 2) / tma_info_thread_clks", "MetricGroup": "MemoryLat;TopdownL4;tma_L4_group;tma_l2_bound_group", "MetricName": "tma_l2_hit_latency", - "MetricThreshold": "tma_l2_hit_latency > 0.05 & tma_l2_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_l2_hit_latency > 0.05 & (tma_l2_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", "PublicDescription": "This metric represents fraction of cycles with demand load accesses that hit the L2 cache under unloaded scenarios (possibly L2 latency limited). Avoiding L1 cache misses (i.e. L1 misses/L2 hits) will improve the latency. Sample with: MEM_LOAD_RETIRED.L2_HIT", "ScaleUnit": "100%", "Unit": "cpu_core" @@ -2208,18 +2217,19 @@ "MetricExpr": "cpu_core@MEMORY_STALLS.L3@ / tma_info_thread_clks", "MetricGroup": "CacheHits;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_l3_bound", - "MetricThreshold": "tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", - "PublicDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core. Avoiding cache misses (i.e. L2 misses/L3 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L3_HIT", + "MetricThreshold": "tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", + "PublicDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core. Avoiding cache misses (i.e. L2 misses/L3 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L3_HIT_PS", "ScaleUnit": "100%", "Unit": "cpu_core" }, { "BriefDescription": "This metric estimates fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited)", - "MetricExpr": "(min(cpu_core@MEM_LOAD_RETIRED.L3_HIT@ * cpu_core@mem_load_retired.l3_hit@R, cpu_core@MEM_LOAD_RETIRED.L3_HIT@ * (12 * tma_info_system_core_frequency) - 3 * tma_info_system_core_frequency) if 0 < cpu_core@mem_load_retired.l3_hit@R else cpu_core@MEM_LOAD_RETIRED.L3_HIT@ * (12 * tma_info_system_core_frequency) - 3 * tma_info_system_core_frequency) * (1 + cpu_core@MEM_LOAD_RETIRED.FB_HIT@ / cpu_core@MEM_LOAD_RETIRED.L1_MISS@ / 2) / tma_info_thread_clks", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "cpu_core@MEM_LOAD_RETIRED.L3_HIT@ * min(cpu_core@MEM_LOAD_RETIRED.L3_HIT@R, 9 * tma_info_system_core_frequency) * (1 + cpu_core@MEM_LOAD_RETIRED.FB_HIT@ / cpu_core@MEM_LOAD_RETIRED.L1_MISS@ / 2) / tma_info_thread_clks", "MetricGroup": "BvML;MemoryLat;TopdownL4;tma_L4_group;tma_issueLat;tma_l3_bound_group", "MetricName": "tma_l3_hit_latency", - "MetricThreshold": "tma_l3_hit_latency > 0.1 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", - "PublicDescription": "This metric estimates fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited). Avoiding private cache misses (i.e. L2 misses/L3 hits) will improve the latency; reduce contention with sibling physical cores and increase performance. Note the value of this node may overlap with its siblings. Sample with: MEM_LOAD_RETIRED.L3_HIT. Related metrics: tma_branch_resteers, tma_mem_latency, tma_store_latency", + "MetricThreshold": "tma_l3_hit_latency > 0.1 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric estimates fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited). Avoiding private cache misses (i.e. L2 misses/L3 hits) will improve the latency; reduce contention with sibling physical cores and increase performance. Note the value of this node may overlap with its siblings. Sample with: MEM_LOAD_RETIRED.L3_HIT_PS. Related metrics: tma_bottleneck_cache_memory_latency, tma_mem_latency", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -2228,19 +2238,19 @@ "MetricExpr": "cpu_core@DECODE.LCP@ / tma_info_thread_clks", "MetricGroup": "FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueFB", "MetricName": "tma_lcp", - "MetricThreshold": "tma_lcp > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", - "PublicDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs). Using proper compiler flags or Intel Compiler by default will certainly avoid this. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb", + "MetricThreshold": "tma_lcp > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", + "PublicDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs). Using proper compiler flags or Intel Compiler by default will certainly avoid this. #Link: Optimization Guide about LCP BKMs. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb", "ScaleUnit": "100%", "Unit": "cpu_core" }, { - "BriefDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations , instructions that require no more than one uop (micro-operation)", + "BriefDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation)", "MetricExpr": "max(0, tma_retiring - tma_heavy_operations)", "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_light_operations", "MetricThreshold": "tma_light_operations > 0.6", "MetricgroupNoGroup": "TopdownL2", - "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations , instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized code running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. ([ICL+] Note this may undercount due to approximation using indirect events; [ADL+] .). Sample with: INST_RETIRED.PREC_DIST", + "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized code running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. ([ICL+] Note this may undercount due to approximation using indirect events; [ADL+] .). Sample with: INST_RETIRED.PREC_DIST", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -2250,7 +2260,7 @@ "MetricGroup": "TopdownL5;tma_L5_group;tma_ports_utilized_3m_group", "MetricName": "tma_load_op_utilization", "MetricThreshold": "tma_load_op_utilization > 0.6", - "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port for Load operations. Sample with: UOPS_DISPATCHED.LOAD", + "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port for Load operations. Sample with: UOPS_DISPATCHED.PORT_2_3_10", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -2259,7 +2269,7 @@ "MetricExpr": "max(0, tma_dtlb_load - tma_load_stlb_miss)", "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_load_group", "MetricName": "tma_load_stlb_hit", - "MetricThreshold": "tma_load_stlb_hit > 0.05 & tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_load_stlb_hit > 0.05 & (tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -2268,43 +2278,43 @@ "MetricExpr": "cpu_core@DTLB_LOAD_MISSES.WALK_ACTIVE@ / tma_info_thread_clks", "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_load_group", "MetricName": "tma_load_stlb_miss", - "MetricThreshold": "tma_load_stlb_miss > 0.05 & tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_load_stlb_miss > 0.05 & (tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))", "ScaleUnit": "100%", "Unit": "cpu_core" }, { - "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 1 GB pages for data load accesses", + "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 1 GB pages for data load accesses.", "MetricExpr": "tma_load_stlb_miss * cpu_core@DTLB_LOAD_MISSES.WALK_COMPLETED_1G@ / (cpu_core@DTLB_LOAD_MISSES.WALK_COMPLETED_4K@ + cpu_core@DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M@ + cpu_core@DTLB_LOAD_MISSES.WALK_COMPLETED_1G@)", "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_load_stlb_miss_group", "MetricName": "tma_load_stlb_miss_1g", - "MetricThreshold": "tma_load_stlb_miss_1g > 0.05 & tma_load_stlb_miss > 0.05 & tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_load_stlb_miss_1g > 0.05 & (tma_load_stlb_miss > 0.05 & (tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))))", "ScaleUnit": "100%", "Unit": "cpu_core" }, { - "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 2 or 4 MB pages for data load accesses", + "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 2 or 4 MB pages for data load accesses.", "MetricExpr": "tma_load_stlb_miss * cpu_core@DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M@ / (cpu_core@DTLB_LOAD_MISSES.WALK_COMPLETED_4K@ + cpu_core@DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M@ + cpu_core@DTLB_LOAD_MISSES.WALK_COMPLETED_1G@)", "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_load_stlb_miss_group", "MetricName": "tma_load_stlb_miss_2m", - "MetricThreshold": "tma_load_stlb_miss_2m > 0.05 & tma_load_stlb_miss > 0.05 & tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_load_stlb_miss_2m > 0.05 & (tma_load_stlb_miss > 0.05 & (tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))))", "ScaleUnit": "100%", "Unit": "cpu_core" }, { - "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 4 KB pages for data load accesses", + "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 4 KB pages for data load accesses.", "MetricExpr": "tma_load_stlb_miss * cpu_core@DTLB_LOAD_MISSES.WALK_COMPLETED_4K@ / (cpu_core@DTLB_LOAD_MISSES.WALK_COMPLETED_4K@ + cpu_core@DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M@ + cpu_core@DTLB_LOAD_MISSES.WALK_COMPLETED_1G@)", "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_load_stlb_miss_group", "MetricName": "tma_load_stlb_miss_4k", - "MetricThreshold": "tma_load_stlb_miss_4k > 0.05 & tma_load_stlb_miss > 0.05 & tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_load_stlb_miss_4k > 0.05 & (tma_load_stlb_miss > 0.05 & (tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))))", "ScaleUnit": "100%", "Unit": "cpu_core" }, { "BriefDescription": "This metric represents fraction of cycles the CPU spent handling cache misses due to lock operations", - "MetricExpr": "cpu_core@MEM_INST_RETIRED.LOCK_LOADS@ * cpu_core@mem_inst_retired.lock_loads@R / tma_info_thread_clks", + "MetricExpr": "cpu_core@MEM_INST_RETIRED.LOCK_LOADS@ * cpu_core@MEM_INST_RETIRED.LOCK_LOADS@R / tma_info_thread_clks", "MetricGroup": "LockCont;Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_l1_bound_group", "MetricName": "tma_lock_latency", - "MetricThreshold": "tma_lock_latency > 0.2 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_lock_latency > 0.2 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", "PublicDescription": "This metric represents fraction of cycles the CPU spent handling cache misses due to lock operations. Due to the microarchitecture handling of locks; they are classified as L1_Bound regardless of what memory source satisfied them. Sample with: MEM_INST_RETIRED.LOCK_LOADS. Related metrics: tma_store_latency", "ScaleUnit": "100%", "Unit": "cpu_core" @@ -2315,7 +2325,7 @@ "MetricGroup": "FetchBW;LSD;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group", "MetricName": "tma_lsd", "MetricThreshold": "tma_lsd > 0.15 & tma_fetch_bandwidth > 0.2", - "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to LSD (Loop Stream Detector) unit. LSD typically does well sustaining Uop supply. However; in some rare cases; optimal uop-delivery could not be reached for small loops whose size (in terms of number of uops) does not suit well the LSD structure", + "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to LSD (Loop Stream Detector) unit. LSD typically does well sustaining Uop supply. However; in some rare cases; optimal uop-delivery could not be reached for small loops whose size (in terms of number of uops) does not suit well the LSD structure.", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -2326,17 +2336,17 @@ "MetricName": "tma_machine_clears", "MetricThreshold": "tma_machine_clears > 0.1 & tma_bad_speculation > 0.15", "MetricgroupNoGroup": "TopdownL2", - "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears. These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT. Related metrics: tma_clears_resteers, tma_contested_accesses, tma_data_sharing, tma_l1_bound, tma_microcode_sequencer, tma_ms_switches", + "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears. These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT. Related metrics: tma_bottleneck_memory_synchronization, tma_clears_resteers, tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_l1_bound, tma_microcode_sequencer, tma_ms_switches, tma_remote_cache", "ScaleUnit": "100%", "Unit": "cpu_core" }, { "BriefDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory - DRAM ([SPR-HBM] and/or HBM)", - "MetricExpr": "min(cpu_core@CPU_CLK_UNHALTED.THREAD@, cpu_core@OFFCORE_REQUESTS_OUTSTANDING.DATA_RD\\,cmask\\=0x4@) / tma_info_thread_clks", + "MetricExpr": "min(cpu_core@CPU_CLK_UNHALTED.THREAD@, cpu_core@OFFCORE_REQUESTS_OUTSTANDING.DATA_RD\\,cmask\\=4@) / tma_info_thread_clks", "MetricGroup": "BvMB;MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueBW", "MetricName": "tma_mem_bandwidth", - "MetricThreshold": "tma_mem_bandwidth > 0.2 & tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", - "PublicDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory - DRAM ([SPR-HBM] and/or HBM). The underlying heuristic assumes that a similar off-core traffic is generated by all IA cores. This metric does not aggregate non-data-read requests by this logical processor; requests from other IA Logical Processors/Physical Cores/sockets; or other non-IA devices like GPU; hence the maximum external memory bandwidth limits may or may not be approached when this metric is flagged (see Uncore counters for that). Related metrics: tma_bottleneck_cache_memory_bandwidth, tma_fb_full, tma_sq_full", + "MetricThreshold": "tma_mem_bandwidth > 0.2 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory - DRAM ([SPR-HBM] and/or HBM). The underlying heuristic assumes that a similar off-core traffic is generated by all IA cores. This metric does not aggregate non-data-read requests by this logical processor; requests from other IA Logical Processors/Physical Cores/sockets; or other non-IA devices like GPU; hence the maximum external memory bandwidth limits may or may not be approached when this metric is flagged (see Uncore counters for that). Related metrics: tma_bottleneck_cache_memory_bandwidth, tma_fb_full, tma_info_system_dram_bw_use, tma_sq_full", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -2345,34 +2355,34 @@ "MetricExpr": "min(cpu_core@CPU_CLK_UNHALTED.THREAD@, cpu_core@OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD@) / tma_info_thread_clks - tma_mem_bandwidth", "MetricGroup": "BvML;MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueLat", "MetricName": "tma_mem_latency", - "MetricThreshold": "tma_mem_latency > 0.1 & tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", - "PublicDescription": "This metric estimates fraction of cycles where the performance was likely hurt due to latency from external memory - DRAM ([SPR-HBM] and/or HBM). This metric does not aggregate requests from other Logical Processors/Physical Cores/sockets (see Uncore counters for that). Related metrics: tma_l3_hit_latency", + "MetricThreshold": "tma_mem_latency > 0.1 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric estimates fraction of cycles where the performance was likely hurt due to latency from external memory - DRAM ([SPR-HBM] and/or HBM). This metric does not aggregate requests from other Logical Processors/Physical Cores/sockets (see Uncore counters for that). Related metrics: tma_bottleneck_cache_memory_latency, tma_l3_hit_latency", "ScaleUnit": "100%", "Unit": "cpu_core" }, { "BriefDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck", - "MetricExpr": "topdown\\-mem\\-bound / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * slots", + "MetricExpr": "cpu_core@topdown\\-mem\\-bound@ / (cpu_core@topdown\\-fe\\-bound@ + cpu_core@topdown\\-bad\\-spec@ + cpu_core@topdown\\-retiring@ + cpu_core@topdown\\-be\\-bound@) + 0 * tma_info_thread_slots", "MetricGroup": "Backend;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_memory_bound", "MetricThreshold": "tma_memory_bound > 0.2 & tma_backend_bound > 0.2", "MetricgroupNoGroup": "TopdownL2", - "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck. Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two)", + "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck. Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two).", "ScaleUnit": "100%", "Unit": "cpu_core" }, { - "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to LFENCE Instructions", + "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to LFENCE Instructions.", "MetricConstraint": "NO_GROUP_EVENTS_NMI", "MetricExpr": "13 * cpu_core@MISC2_RETIRED.LFENCE@ / tma_info_thread_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_serializing_operation_group", "MetricName": "tma_memory_fence", - "MetricThreshold": "tma_memory_fence > 0.05 & tma_serializing_operation > 0.1 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_memory_fence > 0.05 & (tma_serializing_operation > 0.1 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", "ScaleUnit": "100%", "Unit": "cpu_core" }, { - "BriefDescription": "This metric represents fraction of slots where the CPU was retiring memory operations , uops for memory load or store accesses", + "BriefDescription": "This metric represents fraction of slots where the CPU was retiring memory operations -- uops for memory load or store accesses.", "MetricExpr": "tma_light_operations * cpu_core@MEM_UOP_RETIRED.ANY@ / (tma_retiring * tma_info_thread_slots)", "MetricGroup": "Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group", "MetricName": "tma_memory_operations", @@ -2395,14 +2405,14 @@ "MetricExpr": "tma_branch_mispredicts / tma_bad_speculation * cpu_core@INT_MISC.CLEAR_RESTEER_CYCLES@ / tma_info_thread_clks", "MetricGroup": "BadSpec;BrMispredicts;BvMP;TopdownL4;tma_L4_group;tma_branch_resteers_group;tma_issueBM", "MetricName": "tma_mispredicts_resteers", - "MetricThreshold": "tma_mispredicts_resteers > 0.05 & tma_branch_resteers > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricThreshold": "tma_mispredicts_resteers > 0.05 & (tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))", "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Branch Misprediction at execution stage. Sample with: INT_MISC.CLEAR_RESTEER_CYCLES. Related metrics: tma_bottleneck_mispredictions, tma_branch_mispredicts, tma_info_bad_spec_branch_misprediction_cost", "ScaleUnit": "100%", "Unit": "cpu_core" }, { "BriefDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to the MITE pipeline (the legacy decode pipeline)", - "MetricExpr": "(cpu_core@IDQ.MITE_UOPS\\,cmask\\=0x8\\,inv\\=0x1@ / tma_info_thread_clks + cpu_core@IDQ.MITE_UOPS@ / (cpu_core@IDQ.DSB_UOPS@ + cpu_core@IDQ.MITE_UOPS@) * (cpu_core@IDQ_BUBBLES.CYCLES_0_UOPS_DELIV.CORE@ - cpu_core@IDQ_BUBBLES.FETCH_LATENCY@)) / tma_info_thread_clks", + "MetricExpr": "(cpu_core@IDQ.MITE_UOPS\\,cmask\\=0x8\\,inv\\=0x1@ / 2 + cpu_core@IDQ.MITE_UOPS@ / (cpu_core@IDQ.DSB_UOPS@ + cpu_core@IDQ.MITE_UOPS@) * (cpu_core@IDQ_BUBBLES.CYCLES_0_UOPS_DELIV.CORE@ - cpu_core@IDQ_BUBBLES.FETCH_LATENCY@)) / tma_info_thread_clks", "MetricGroup": "DSBmiss;FetchBW;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group", "MetricName": "tma_mite", "MetricThreshold": "tma_mite > 0.1 & tma_fetch_bandwidth > 0.2", @@ -2411,17 +2421,17 @@ "Unit": "cpu_core" }, { - "BriefDescription": "This metric estimates penalty in terms of percentage of([SKL+] injected blend uops out of all Uops Issued , the Count Domain; [ADL+] cycles)", + "BriefDescription": "This metric estimates penalty in terms of percentage of([SKL+] injected blend uops out of all Uops Issued -- the Count Domain; [ADL+] cycles)", "MetricExpr": "160 * cpu_core@ASSISTS.SSE_AVX_MIX@ / tma_info_thread_clks", "MetricGroup": "TopdownL5;tma_L5_group;tma_issueMV;tma_ports_utilized_0_group", "MetricName": "tma_mixing_vectors", "MetricThreshold": "tma_mixing_vectors > 0.05", - "PublicDescription": "This metric estimates penalty in terms of percentage of([SKL+] injected blend uops out of all Uops Issued , the Count Domain; [ADL+] cycles). Usually a Mixing_Vectors over 5% is worth investigating. Read more in Appendix B1 of the Optimizations Guide for this topic. Related metrics: tma_ms_switches", + "PublicDescription": "This metric estimates penalty in terms of percentage of([SKL+] injected blend uops out of all Uops Issued -- the Count Domain; [ADL+] cycles). Usually a Mixing_Vectors over 5% is worth investigating. Read more in Appendix B1 of the Optimizations Guide for this topic. Related metrics: tma_ms_switches", "ScaleUnit": "100%", "Unit": "cpu_core" }, { - "BriefDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to the Microcode Sequencer (MS) unit - see Microcode_Sequencer node for details", + "BriefDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to the Microcode Sequencer (MS) unit - see Microcode_Sequencer node for details.", "MetricExpr": "cpu_core@IDQ.MS_CYCLES_ANY@ / tma_info_thread_clks", "MetricGroup": "MicroSeq;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group", "MetricName": "tma_ms", @@ -2434,7 +2444,7 @@ "MetricExpr": "3 * cpu_core@IDQ.MS_SWITCHES@ / tma_info_thread_clks", "MetricGroup": "FetchLat;MicroSeq;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueMC;tma_issueMS;tma_issueMV;tma_issueSO", "MetricName": "tma_ms_switches", - "MetricThreshold": "tma_ms_switches > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricThreshold": "tma_ms_switches > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", "PublicDescription": "This metric estimates the fraction of cycles when the CPU was stalled due to switches of uop delivery to the Microcode Sequencer (MS). Commonly used instructions are optimized for delivery by the DSB (decoded i-cache) or MITE (legacy instruction decode) pipelines. Certain operations cannot be handled natively by the execution pipeline; and must be performed by microcode (small programs injected into the execution stream). Switching to the MS too often can negatively impact performance. The MS is designated to deliver long uop flows required by CISC instructions like CPUID; or uncommon conditions like Floating Point Assists when dealing with Denormals. Sample with: IDQ.MS_SWITCHES. Related metrics: tma_bottleneck_irregular_overhead, tma_clears_resteers, tma_l1_bound, tma_machine_clears, tma_microcode_sequencer, tma_mixing_vectors, tma_serializing_operation", "ScaleUnit": "100%", "Unit": "cpu_core" @@ -2445,7 +2455,7 @@ "MetricGroup": "Branches;BvBO;Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group", "MetricName": "tma_non_fused_branches", "MetricThreshold": "tma_non_fused_branches > 0.1 & tma_light_operations > 0.6", - "PublicDescription": "This metric represents fraction of slots where the CPU was retiring branch instructions that were not fused. Non-conditional branches like direct JMP or CALL would count here. Can be used to examine fusible conditional jumps that were not fused", + "PublicDescription": "This metric represents fraction of slots where the CPU was retiring branch instructions that were not fused. Non-conditional branches like direct JMP or CALL would count here. Can be used to examine fusible conditional jumps that were not fused.", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -2454,7 +2464,7 @@ "MetricExpr": "tma_light_operations * cpu_core@INST_RETIRED.NOP@ / (tma_retiring * tma_info_thread_slots)", "MetricGroup": "BvBO;Pipeline;TopdownL4;tma_L4_group;tma_other_light_ops_group", "MetricName": "tma_nop_instructions", - "MetricThreshold": "tma_nop_instructions > 0.1 & tma_other_light_ops > 0.3 & tma_light_operations > 0.6", + "MetricThreshold": "tma_nop_instructions > 0.1 & (tma_other_light_ops > 0.3 & tma_light_operations > 0.6)", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring NOP (no op) instructions. Compilers often use NOPs for certain address alignments - e.g. start address of a function or loop body. Sample with: INST_RETIRED.NOP", "ScaleUnit": "100%", "Unit": "cpu_core" @@ -2470,20 +2480,20 @@ "Unit": "cpu_core" }, { - "BriefDescription": "This metric estimates fraction of slots the CPU was stalled due to other cases of misprediction (non-retired x86 branches or other types)", + "BriefDescription": "This metric estimates fraction of slots the CPU was stalled due to other cases of misprediction (non-retired x86 branches or other types).", "MetricExpr": "max(tma_branch_mispredicts * (1 - cpu_core@BR_MISP_RETIRED.ALL_BRANCHES@ / (cpu_core@INT_MISC.CLEARS_COUNT@ - cpu_core@MACHINE_CLEARS.COUNT@)), 0.0001)", "MetricGroup": "BrMispredicts;BvIO;TopdownL3;tma_L3_group;tma_branch_mispredicts_group", "MetricName": "tma_other_mispredicts", - "MetricThreshold": "tma_other_mispredicts > 0.05 & tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", + "MetricThreshold": "tma_other_mispredicts > 0.05 & (tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15)", "ScaleUnit": "100%", "Unit": "cpu_core" }, { - "BriefDescription": "This metric represents fraction of slots the CPU has wasted due to Nukes (Machine Clears) not related to memory ordering", + "BriefDescription": "This metric represents fraction of slots the CPU has wasted due to Nukes (Machine Clears) not related to memory ordering.", "MetricExpr": "max(tma_machine_clears * (1 - cpu_core@MACHINE_CLEARS.MEMORY_ORDERING@ / cpu_core@MACHINE_CLEARS.COUNT@), 0.0001)", "MetricGroup": "BvIO;Machine_Clears;TopdownL3;tma_L3_group;tma_machine_clears_group", "MetricName": "tma_other_nukes", - "MetricThreshold": "tma_other_nukes > 0.05 & tma_machine_clears > 0.1 & tma_bad_speculation > 0.15", + "MetricThreshold": "tma_other_nukes > 0.05 & (tma_machine_clears > 0.1 & tma_bad_speculation > 0.15)", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -2493,7 +2503,7 @@ "MetricGroup": "TopdownL5;tma_L5_group;tma_assists_group", "MetricName": "tma_page_faults", "MetricThreshold": "tma_page_faults > 0.05", - "PublicDescription": "This metric roughly estimates fraction of slots the CPU retired uops as a result of handing Page Faults. A Page Fault may apply on first application access to a memory page. Note operating system handling of page faults accounts for the majority of its cost", + "PublicDescription": "This metric roughly estimates fraction of slots the CPU retired uops as a result of handing Page Faults. A Page Fault may apply on first application access to a memory page. Note operating system handling of page faults accounts for the majority of its cost.", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -2502,8 +2512,8 @@ "MetricExpr": "((cpu_core@EXE_ACTIVITY.EXE_BOUND_0_PORTS@ + (cpu_core@EXE_ACTIVITY.1_PORTS_UTIL@ + tma_retiring * cpu_core@EXE_ACTIVITY.2_3_PORTS_UTIL@)) / tma_info_thread_clks if cpu_core@ARITH.DIV_ACTIVE@ < cpu_core@CYCLE_ACTIVITY.STALLS_TOTAL@ - cpu_core@EXE_ACTIVITY.BOUND_ON_LOADS@ else (cpu_core@EXE_ACTIVITY.1_PORTS_UTIL@ + tma_retiring * cpu_core@EXE_ACTIVITY.2_3_PORTS_UTIL@) / tma_info_thread_clks)", "MetricGroup": "PortsUtil;TopdownL3;tma_L3_group;tma_core_bound_group", "MetricName": "tma_ports_utilization", - "MetricThreshold": "tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", - "PublicDescription": "This metric estimates fraction of cycles the CPU performance was potentially limited due to Core computation issues (non divider-related). Two distinct categories can be attributed into this metric: (1) heavy data-dependency among contiguous instructions would manifest in this metric - such cases are often referred to as low Instruction Level Parallelism (ILP). (2) Contention on some hardware execution unit other than Divider. For example; when there are too many multiply operations", + "MetricThreshold": "tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)", + "PublicDescription": "This metric estimates fraction of cycles the CPU performance was potentially limited due to Core computation issues (non divider-related). Two distinct categories can be attributed into this metric: (1) heavy data-dependency among contiguous instructions would manifest in this metric - such cases are often referred to as low Instruction Level Parallelism (ILP). (2) Contention on some hardware execution unit other than Divider. For example; when there are too many multiply operations.", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -2512,8 +2522,8 @@ "MetricExpr": "cpu_core@EXE_ACTIVITY.EXE_BOUND_0_PORTS@ / tma_info_thread_clks", "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group", "MetricName": "tma_ports_utilized_0", - "MetricThreshold": "tma_ports_utilized_0 > 0.2 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", - "PublicDescription": "This metric represents fraction of cycles CPU executed no uops on any execution port (Logical Processor cycles since ICL, Physical Core cycles otherwise). Long-latency instructions like divides may contribute to this metric", + "MetricThreshold": "tma_ports_utilized_0 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric represents fraction of cycles CPU executed no uops on any execution port (Logical Processor cycles since ICL, Physical Core cycles otherwise). Long-latency instructions like divides may contribute to this metric.", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -2522,7 +2532,7 @@ "MetricExpr": "cpu_core@EXE_ACTIVITY.1_PORTS_UTIL@ / tma_info_thread_clks", "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_issueL1;tma_ports_utilization_group", "MetricName": "tma_ports_utilized_1", - "MetricThreshold": "tma_ports_utilized_1 > 0.2 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_ports_utilized_1 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", "PublicDescription": "This metric represents fraction of cycles where the CPU executed total of 1 uop per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise). This can be due to heavy data-dependency among software instructions; or over oversubscribing a particular hardware resource. In some other cases with high 1_Port_Utilized and L1_Bound; this metric can point to L1 data-cache latency bottleneck that may not necessarily manifest with complete execution starvation (due to the short L1 latency e.g. walking a linked list) - looking at the assembly can be helpful. Sample with: EXE_ACTIVITY.1_PORTS_UTIL. Related metrics: tma_l1_bound", "ScaleUnit": "100%", "Unit": "cpu_core" @@ -2533,8 +2543,8 @@ "MetricExpr": "cpu_core@EXE_ACTIVITY.2_PORTS_UTIL@ / tma_info_thread_clks", "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_issue2P;tma_ports_utilization_group", "MetricName": "tma_ports_utilized_2", - "MetricThreshold": "tma_ports_utilized_2 > 0.15 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", - "PublicDescription": "This metric represents fraction of cycles CPU executed total of 2 uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise). Loop Vectorization -most compilers feature auto-Vectorization options today- reduces pressure on the execution ports as multiple elements are calculated with same uop. Sample with: EXE_ACTIVITY.2_PORTS_UTIL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_int_vector_128b, tma_int_vector_256b", + "MetricThreshold": "tma_ports_utilized_2 > 0.15 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric represents fraction of cycles CPU executed total of 2 uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise). Loop Vectorization -most compilers feature auto-Vectorization options today- reduces pressure on the execution ports as multiple elements are calculated with same uop. Sample with: EXE_ACTIVITY.2_PORTS_UTIL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_port_6", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -2544,24 +2554,24 @@ "MetricExpr": "cpu_core@UOPS_EXECUTED.CYCLES_GE_3@ / tma_info_thread_clks", "MetricGroup": "BvCB;PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group", "MetricName": "tma_ports_utilized_3m", - "MetricThreshold": "tma_ports_utilized_3m > 0.4 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_ports_utilized_3m > 0.4 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", "PublicDescription": "This metric represents fraction of cycles CPU executed total of 3 or more uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise). Sample with: UOPS_EXECUTED.CYCLES_GE_3", "ScaleUnit": "100%", "Unit": "cpu_core" }, { - "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to retired misprediction by (indirect) RET instructions", - "MetricExpr": "cpu_core@BR_MISP_RETIRED.RET_COST@ * cpu_core@br_misp_retired.ret_cost@R / tma_info_thread_clks", + "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to retired misprediction by (indirect) RET instructions.", + "MetricExpr": "cpu_core@BR_MISP_RETIRED.RET_COST@ * cpu_core@BR_MISP_RETIRED.RET_COST@R / tma_info_thread_clks", "MetricGroup": "BrMispredicts;TopdownL3;tma_L3_group;tma_branch_mispredicts_group", "MetricName": "tma_ret_mispredicts", - "MetricThreshold": "tma_ret_mispredicts > 0.05 & tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", + "MetricThreshold": "tma_ret_mispredicts > 0.05 & (tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15)", "ScaleUnit": "100%", "Unit": "cpu_core" }, { "BriefDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired", "DefaultMetricgroupName": "TopdownL1", - "MetricExpr": "topdown\\-retiring / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * slots", + "MetricExpr": "cpu_core@topdown\\-retiring@ / (cpu_core@topdown\\-fe\\-bound@ + cpu_core@topdown\\-bad\\-spec@ + cpu_core@topdown\\-retiring@ + cpu_core@topdown\\-be\\-bound@) + 0 * tma_info_thread_slots", "MetricGroup": "BvUW;Default;TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_retiring", "MetricThreshold": "tma_retiring > 0.7 | tma_heavy_operations > 0.1", @@ -2575,8 +2585,8 @@ "MetricExpr": "(cpu_core@BE_STALLS.SCOREBOARD@ + cpu_core@CPU_CLK_UNHALTED.C02@) / tma_info_thread_clks", "MetricGroup": "BvIO;PortsUtil;TopdownL3;tma_L3_group;tma_core_bound_group;tma_issueSO", "MetricName": "tma_serializing_operation", - "MetricThreshold": "tma_serializing_operation > 0.1 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", - "PublicDescription": "This metric represents fraction of cycles the CPU issue-pipeline was stalled due to serializing operations. Instructions like CPUID; WRMSR or LFENCE serialize the out-of-order execution which may limit performance. Sample with: BE_STALLS.SCOREBOARD. Related metrics: tma_ms_switches", + "MetricThreshold": "tma_serializing_operation > 0.1 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)", + "PublicDescription": "This metric represents fraction of cycles the CPU issue-pipeline was stalled due to serializing operations. Instructions like CPUID; WRMSR or LFENCE serialize the out-of-order execution which may limit performance. Sample with: RESOURCE_STALLS.SCOREBOARD. Related metrics: tma_ms_switches", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -2585,8 +2595,8 @@ "MetricExpr": "tma_light_operations * cpu_core@INT_VEC_RETIRED.SHUFFLES@ / (tma_retiring * tma_info_thread_slots)", "MetricGroup": "HPC;Pipeline;TopdownL4;tma_L4_group;tma_other_light_ops_group", "MetricName": "tma_shuffles_256b", - "MetricThreshold": "tma_shuffles_256b > 0.1 & tma_other_light_ops > 0.3 & tma_light_operations > 0.6", - "PublicDescription": "This metric represents fraction of slots where the CPU was retiring Shuffle operations of 256-bit vector size (FP or Integer). Shuffles may incur slow cross \"vector lane\" data transfers", + "MetricThreshold": "tma_shuffles_256b > 0.1 & (tma_other_light_ops > 0.3 & tma_light_operations > 0.6)", + "PublicDescription": "This metric represents fraction of slots where the CPU was retiring Shuffle operations of 256-bit vector size (FP or Integer). Shuffles may incur slow cross \"vector lane\" data transfers.", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -2596,28 +2606,28 @@ "MetricExpr": "cpu_core@CPU_CLK_UNHALTED.PAUSE@ / tma_info_thread_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_serializing_operation_group", "MetricName": "tma_slow_pause", - "MetricThreshold": "tma_slow_pause > 0.05 & tma_serializing_operation > 0.1 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_slow_pause > 0.05 & (tma_serializing_operation > 0.1 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to PAUSE Instructions. Sample with: CPU_CLK_UNHALTED.PAUSE_INST", "ScaleUnit": "100%", "Unit": "cpu_core" }, { "BriefDescription": "This metric estimates fraction of cycles handling memory load split accesses - load that cross 64-byte cache line boundary", - "MetricExpr": "(min(cpu_core@MEM_INST_RETIRED.SPLIT_LOADS@ * cpu_core@mem_inst_retired.split_loads@R, cpu_core@MEM_INST_RETIRED.SPLIT_LOADS@ * tma_info_memory_load_miss_real_latency) if 0 < cpu_core@mem_inst_retired.split_loads@R else cpu_core@MEM_INST_RETIRED.SPLIT_LOADS@ * tma_info_memory_load_miss_real_latency) / tma_info_thread_clks", + "MetricExpr": "cpu_core@MEM_INST_RETIRED.SPLIT_LOADS@ * min(cpu_core@MEM_INST_RETIRED.SPLIT_LOADS@R, tma_info_memory_load_miss_real_latency) / tma_info_thread_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group", "MetricName": "tma_split_loads", "MetricThreshold": "tma_split_loads > 0.3", - "PublicDescription": "This metric estimates fraction of cycles handling memory load split accesses - load that cross 64-byte cache line boundary. Sample with: MEM_INST_RETIRED.SPLIT_LOADS", + "PublicDescription": "This metric estimates fraction of cycles handling memory load split accesses - load that cross 64-byte cache line boundary. Sample with: MEM_INST_RETIRED.SPLIT_LOADS_PS", "ScaleUnit": "100%", "Unit": "cpu_core" }, { "BriefDescription": "This metric represents rate of split store accesses", - "MetricExpr": "(min(cpu_core@MEM_INST_RETIRED.SPLIT_STORES@ * cpu_core@mem_inst_retired.split_stores@R, cpu_core@MEM_INST_RETIRED.SPLIT_STORES@) if 0 < cpu_core@mem_inst_retired.split_stores@R else cpu_core@MEM_INST_RETIRED.SPLIT_STORES@) / tma_info_thread_clks", + "MetricExpr": "cpu_core@MEM_INST_RETIRED.SPLIT_STORES@ * min(cpu_core@MEM_INST_RETIRED.SPLIT_STORES@R, 1) / tma_info_thread_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_issueSpSt;tma_store_bound_group", "MetricName": "tma_split_stores", - "MetricThreshold": "tma_split_stores > 0.2 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", - "PublicDescription": "This metric represents rate of split store accesses. Consider aligning your data to the 64-byte cache line granularity. Sample with: MEM_INST_RETIRED.SPLIT_STORES", + "MetricThreshold": "tma_split_stores > 0.2 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric represents rate of split store accesses. Consider aligning your data to the 64-byte cache line granularity. Sample with: MEM_INST_RETIRED.SPLIT_STORES_PS. Related metrics: tma_port_4", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -2626,8 +2636,8 @@ "MetricExpr": "(cpu_core@XQ.FULL@ + cpu_core@L1D_MISS.L2_STALLS@) / tma_info_thread_clks", "MetricGroup": "BvMB;MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_issueBW;tma_l3_bound_group", "MetricName": "tma_sq_full", - "MetricThreshold": "tma_sq_full > 0.3 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", - "PublicDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors). Related metrics: tma_bottleneck_cache_memory_bandwidth, tma_fb_full, tma_mem_bandwidth", + "MetricThreshold": "tma_sq_full > 0.3 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors). Related metrics: tma_bottleneck_cache_memory_bandwidth, tma_fb_full, tma_info_system_dram_bw_use, tma_mem_bandwidth", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -2636,8 +2646,8 @@ "MetricExpr": "cpu_core@EXE_ACTIVITY.BOUND_ON_STORES@ / tma_info_thread_clks", "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_store_bound", - "MetricThreshold": "tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", - "PublicDescription": "This metric estimates how often CPU was stalled due to RFO store memory accesses; RFO store issue a read-for-ownership request before the write. Even though store accesses do not typically stall out-of-order CPUs; there are few cases where stores can lead to actual stalls. This metric will be flagged should RFO stores be a bottleneck. Sample with: MEM_INST_RETIRED.ALL_STORES", + "MetricThreshold": "tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", + "PublicDescription": "This metric estimates how often CPU was stalled due to RFO store memory accesses; RFO store issue a read-for-ownership request before the write. Even though store accesses do not typically stall out-of-order CPUs; there are few cases where stores can lead to actual stalls. This metric will be flagged should RFO stores be a bottleneck. Sample with: MEM_INST_RETIRED.ALL_STORES_PS", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -2646,8 +2656,8 @@ "MetricExpr": "13 * cpu_core@LD_BLOCKS.STORE_FORWARD@ / tma_info_thread_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group", "MetricName": "tma_store_fwd_blk", - "MetricThreshold": "tma_store_fwd_blk > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", - "PublicDescription": "This metric roughly estimates fraction of cycles when the memory subsystem had loads blocked since they could not forward data from earlier (in program order) overlapping stores. To streamline memory operations in the pipeline; a load can avoid waiting for memory if a prior in-flight store is writing the data that the load wants to read (store forwarding process). However; in some cases the load may be blocked for a significant time pending the store forward. For example; when the prior store is writing a smaller region than the load is reading", + "MetricThreshold": "tma_store_fwd_blk > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric roughly estimates fraction of cycles when the memory subsystem had loads blocked since they could not forward data from earlier (in program order) overlapping stores. To streamline memory operations in the pipeline; a load can avoid waiting for memory if a prior in-flight store is writing the data that the load wants to read (store forwarding process). However; in some cases the load may be blocked for a significant time pending the store forward. For example; when the prior store is writing a smaller region than the load is reading.", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -2656,8 +2666,8 @@ "MetricExpr": "(cpu_core@MEM_STORE_RETIRED.L2_HIT@ * 10 * (1 - cpu_core@MEM_INST_RETIRED.LOCK_LOADS@ / cpu_core@MEM_INST_RETIRED.ALL_STORES@) + (1 - cpu_core@MEM_INST_RETIRED.LOCK_LOADS@ / cpu_core@MEM_INST_RETIRED.ALL_STORES@) * min(cpu_core@CPU_CLK_UNHALTED.THREAD@, cpu_core@OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO@)) / tma_info_thread_clks", "MetricGroup": "BvML;LockCont;MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_issueSL;tma_store_bound_group", "MetricName": "tma_store_latency", - "MetricThreshold": "tma_store_latency > 0.1 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", - "PublicDescription": "This metric estimates fraction of cycles the CPU spent handling L1D store misses. Store accesses usually less impact out-of-order core performance; however; holding resources for longer time can lead into undesired implications (e.g. contention on L1D fill-buffer entries - see FB_Full). Related metrics: tma_branch_resteers, tma_fb_full, tma_l3_hit_latency, tma_lock_latency", + "MetricThreshold": "tma_store_latency > 0.1 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric estimates fraction of cycles the CPU spent handling L1D store misses. Store accesses usually less impact out-of-order core performance; however; holding resources for longer time can lead into undesired implications (e.g. contention on L1D fill-buffer entries - see FB_Full). Related metrics: tma_fb_full, tma_lock_latency", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -2667,7 +2677,7 @@ "MetricGroup": "TopdownL5;tma_L5_group;tma_ports_utilized_3m_group", "MetricName": "tma_store_op_utilization", "MetricThreshold": "tma_store_op_utilization > 0.6", - "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port for Store operations. Sample with: UOPS_DISPATCHED.STD, UOPS_DISPATCHED.STA", + "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port for Store operations. Sample with: UOPS_DISPATCHED.PORT_7_8", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -2676,7 +2686,7 @@ "MetricExpr": "max(0, tma_dtlb_store - tma_store_stlb_miss)", "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_store_group", "MetricName": "tma_store_stlb_hit", - "MetricThreshold": "tma_store_stlb_hit > 0.05 & tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_store_stlb_hit > 0.05 & (tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -2685,34 +2695,34 @@ "MetricExpr": "cpu_core@DTLB_STORE_MISSES.WALK_ACTIVE@ / tma_info_thread_clks", "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_store_group", "MetricName": "tma_store_stlb_miss", - "MetricThreshold": "tma_store_stlb_miss > 0.05 & tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_store_stlb_miss > 0.05 & (tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))", "ScaleUnit": "100%", "Unit": "cpu_core" }, { - "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 1 GB pages for data store accesses", + "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 1 GB pages for data store accesses.", "MetricExpr": "tma_store_stlb_miss * cpu_core@DTLB_STORE_MISSES.WALK_COMPLETED_1G@ / (cpu_core@DTLB_STORE_MISSES.WALK_COMPLETED_4K@ + cpu_core@DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M@ + cpu_core@DTLB_STORE_MISSES.WALK_COMPLETED_1G@)", "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_store_stlb_miss_group", "MetricName": "tma_store_stlb_miss_1g", - "MetricThreshold": "tma_store_stlb_miss_1g > 0.05 & tma_store_stlb_miss > 0.05 & tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_store_stlb_miss_1g > 0.05 & (tma_store_stlb_miss > 0.05 & (tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))))", "ScaleUnit": "100%", "Unit": "cpu_core" }, { - "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 2 or 4 MB pages for data store accesses", + "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 2 or 4 MB pages for data store accesses.", "MetricExpr": "tma_store_stlb_miss * cpu_core@DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M@ / (cpu_core@DTLB_STORE_MISSES.WALK_COMPLETED_4K@ + cpu_core@DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M@ + cpu_core@DTLB_STORE_MISSES.WALK_COMPLETED_1G@)", "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_store_stlb_miss_group", "MetricName": "tma_store_stlb_miss_2m", - "MetricThreshold": "tma_store_stlb_miss_2m > 0.05 & tma_store_stlb_miss > 0.05 & tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_store_stlb_miss_2m > 0.05 & (tma_store_stlb_miss > 0.05 & (tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))))", "ScaleUnit": "100%", "Unit": "cpu_core" }, { - "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 4 KB pages for data store accesses", + "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 4 KB pages for data store accesses.", "MetricExpr": "tma_store_stlb_miss * cpu_core@DTLB_STORE_MISSES.WALK_COMPLETED_4K@ / (cpu_core@DTLB_STORE_MISSES.WALK_COMPLETED_4K@ + cpu_core@DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M@ + cpu_core@DTLB_STORE_MISSES.WALK_COMPLETED_1G@)", "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_store_stlb_miss_group", "MetricName": "tma_store_stlb_miss_4k", - "MetricThreshold": "tma_store_stlb_miss_4k > 0.05 & tma_store_stlb_miss > 0.05 & tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_store_stlb_miss_4k > 0.05 & (tma_store_stlb_miss > 0.05 & (tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))))", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -2721,7 +2731,7 @@ "MetricExpr": "9 * cpu_core@OCR.STREAMING_WR.ANY_RESPONSE@ / tma_info_thread_clks", "MetricGroup": "MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_issueSmSt;tma_store_bound_group", "MetricName": "tma_streaming_stores", - "MetricThreshold": "tma_streaming_stores > 0.2 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_streaming_stores > 0.2 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", "PublicDescription": "This metric estimates how often CPU was stalled due to Streaming store memory accesses; Streaming store optimize out a read request required by RFO stores. Even though store accesses do not typically stall out-of-order CPUs; there are few cases where stores can lead to actual stalls. This metric will be flagged should Streaming stores be a bottleneck. Sample with: OCR.STREAMING_WR.ANY_RESPONSE. Related metrics: tma_fb_full", "ScaleUnit": "100%", "Unit": "cpu_core" @@ -2731,7 +2741,7 @@ "MetricExpr": "cpu_core@INT_MISC.UNKNOWN_BRANCH_CYCLES@ / tma_info_thread_clks", "MetricGroup": "BigFootprint;BvBC;FetchLat;TopdownL4;tma_L4_group;tma_branch_resteers_group", "MetricName": "tma_unknown_branches", - "MetricThreshold": "tma_unknown_branches > 0.05 & tma_branch_resteers > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricThreshold": "tma_unknown_branches > 0.05 & (tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))", "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to new branch address clears. These are fetched branches the Branch Prediction Unit was unable to recognize (e.g. first time the branch is fetched or hitting BTB capacity limit) hence called Unknown Branches. Sample with: FRONTEND_RETIRED.UNKNOWN_BRANCH", "ScaleUnit": "100%", "Unit": "cpu_core" @@ -2741,8 +2751,8 @@ "MetricExpr": "tma_retiring * cpu_core@UOPS_EXECUTED.X87@ / cpu_core@UOPS_EXECUTED.THREAD@", "MetricGroup": "Compute;TopdownL4;tma_L4_group;tma_fp_arith_group", "MetricName": "tma_x87_use", - "MetricThreshold": "tma_x87_use > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6", - "PublicDescription": "This metric serves as an approximation of legacy x87 usage. It accounts for instructions beyond X87 FP arithmetic operations; hence may be used as a thermometer to avoid X87 high usage and preferably upgrade to modern ISA. See Tip under Tuning Hint", + "MetricThreshold": "tma_x87_use > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6)", + "PublicDescription": "This metric serves as an approximation of legacy x87 usage. It accounts for instructions beyond X87 FP arithmetic operations; hence may be used as a thermometer to avoid X87 high usage and preferably upgrade to modern ISA. See Tip under Tuning Hint.", "ScaleUnit": "100%", "Unit": "cpu_core" } diff --git a/tools/perf/pmu-events/arch/x86/arrowlake/cache.json b/tools/perf/pmu-events/arch/x86/arrowlake/cache.json index f63594b2cca8..70175404540d 100644 --- a/tools/perf/pmu-events/arch/x86/arrowlake/cache.json +++ b/tools/perf/pmu-events/arch/x86/arrowlake/cache.json @@ -9,6 +9,16 @@ "Unit": "cpu_atom" }, { + "BriefDescription": "Counts the number of L1D cacheline (dirty) evictions caused by load misses, stores, and prefetches.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x51", + "EventName": "DL1.DIRTY_EVICTION", + "PublicDescription": "Counts the number of L1D cacheline (dirty) evictions caused by load misses, stores, and prefetches. Does not count evictions or dirty writebacks caused by snoops. Does not count a replacement unless a (dirty) line was written back.", + "SampleAfterValue": "200003", + "UMask": "0x1", + "Unit": "cpu_lowpower" + }, + { "BriefDescription": "Counts the number of cache lines replaced in L0 data cache.", "Counter": "0,1,2,3,4,5,6,7,8,9", "EventCode": "0x51", @@ -19,6 +29,16 @@ "Unit": "cpu_core" }, { + "BriefDescription": "Cachelines replaced into the L0 and L1 d-cache. Successful replacements only (not blocked) and exclude WB-miss case", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0x51", + "EventName": "L1D.REPLACEMENT", + "PublicDescription": "Counts cachelines replaced into the L0 and L1 d-cache.", + "SampleAfterValue": "1000003", + "UMask": "0x5", + "Unit": "cpu_core" + }, + { "BriefDescription": "Number of cycles a demand request has waited due to L1D Fill Buffer (FB) unavailability.", "Counter": "0,1,2,3,4,5,6,7,8,9", "EventCode": "0x49", @@ -80,6 +100,46 @@ "Unit": "cpu_core" }, { + "BriefDescription": "Counts the number of cache lines filled into the L2 cache that are in Exclusive state", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x25", + "EventName": "L2_LINES_IN.E", + "PublicDescription": "Counts the number of cache lines filled into the L2 cache that are in Exclusive state. Counts on a per core basis.", + "SampleAfterValue": "1000003", + "UMask": "0x4", + "Unit": "cpu_lowpower" + }, + { + "BriefDescription": "Counts the number of cache lines filled into the L2 cache that are in Forward state", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x25", + "EventName": "L2_LINES_IN.F", + "PublicDescription": "Counts the number of cache lines filled into the L2 cache that are in Forward state. Counts on a per core basis.", + "SampleAfterValue": "1000003", + "UMask": "0x10", + "Unit": "cpu_lowpower" + }, + { + "BriefDescription": "Counts the number of cache lines filled into the L2 cache that are in Modified state", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x25", + "EventName": "L2_LINES_IN.M", + "PublicDescription": "Counts the number of cache lines filled into the L2 cache that are in Modified state. Counts on a per core basis.", + "SampleAfterValue": "1000003", + "UMask": "0x8", + "Unit": "cpu_lowpower" + }, + { + "BriefDescription": "Counts the number of cache lines filled into the L2 cache that are in Shared state", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x25", + "EventName": "L2_LINES_IN.S", + "PublicDescription": "Counts the number of cache lines filled into the L2 cache that are in Shared state. Counts on a per core basis.", + "SampleAfterValue": "1000003", + "UMask": "0x2", + "Unit": "cpu_lowpower" + }, + { "BriefDescription": "Modified cache lines that are evicted by L2 cache when triggered by an L2 cache fill.", "Counter": "0,1,2,3,4,5,6,7,8,9", "EventCode": "0x26", @@ -90,6 +150,16 @@ "Unit": "cpu_core" }, { + "BriefDescription": "Counts the number of L2 cache lines that are evicted due to an L2 cache fill", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x26", + "EventName": "L2_LINES_OUT.NON_SILENT", + "PublicDescription": "Counts the number of L2 cache lines that are evicted due to an L2 cache fill. Increments on the core that brought the line in originally.", + "SampleAfterValue": "1000003", + "UMask": "0x2", + "Unit": "cpu_lowpower" + }, + { "BriefDescription": "Non-modified cache lines that are silently dropped by L2 cache.", "Counter": "0,1,2,3,4,5,6,7,8,9", "EventCode": "0x26", @@ -100,6 +170,16 @@ "Unit": "cpu_core" }, { + "BriefDescription": "Counts the number of L2 cache lines that are silently dropped due to an L2 cache fill", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x26", + "EventName": "L2_LINES_OUT.SILENT", + "PublicDescription": "Counts the number of L2 cache lines that are silently dropped due to an L2 cache fill. Increments on the core that brought the line in originally.", + "SampleAfterValue": "1000003", + "UMask": "0x1", + "Unit": "cpu_lowpower" + }, + { "BriefDescription": "Cache lines that have been L2 hardware prefetched but not used by demand accesses", "Counter": "0,1,2,3,4,5,6,7,8,9", "EventCode": "0x26", @@ -129,6 +209,15 @@ "Unit": "cpu_core" }, { + "BriefDescription": "Counts the number of L2 Cache Accesses that resulted in a Hit from a front door request only (does not include rejects or recycles), per core event", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x24", + "EventName": "L2_REQUEST.HIT", + "SampleAfterValue": "200003", + "UMask": "0x2", + "Unit": "cpu_lowpower" + }, + { "BriefDescription": "Read requests with true-miss in L2 cache [This event is alias to L2_RQSTS.MISS]", "Counter": "0,1,2,3,4,5,6,7,8,9", "EventCode": "0x24", @@ -139,6 +228,34 @@ "Unit": "cpu_core" }, { + "BriefDescription": "Counts the number of total L2 Cache Accesses that resulted in a Miss from a front door request only (does not include rejects or recycles), per core event", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x24", + "EventName": "L2_REQUEST.MISS", + "SampleAfterValue": "200003", + "UMask": "0x1", + "Unit": "cpu_lowpower" + }, + { + "BriefDescription": "Counts the number of L2 Cache Accesses that miss the L2 and get BBL reject short and long rejects (includes those counted in L2_reject_XQ.any), per core event", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x24", + "EventName": "L2_REQUEST.REJECTS", + "SampleAfterValue": "200003", + "UMask": "0x4", + "Unit": "cpu_lowpower" + }, + { + "BriefDescription": "L2 code requests", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0x24", + "EventName": "L2_RQSTS.ALL_CODE_RD", + "PublicDescription": "Counts the total number of L2 code requests.", + "SampleAfterValue": "200003", + "UMask": "0xe4", + "Unit": "cpu_core" + }, + { "BriefDescription": "Demand Data Read access L2 cache", "Counter": "0,1,2,3,4,5,6,7,8,9", "EventCode": "0x24", @@ -409,12 +526,21 @@ "Unit": "cpu_lowpower" }, { + "BriefDescription": "Counts the number of unhalted cycles when the core is stalled to a store buffer full condition", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x34", + "EventName": "MEM_BOUND_STALLS_LOAD.SBFULL", + "SampleAfterValue": "1000003", + "UMask": "0x80", + "Unit": "cpu_lowpower" + }, + { "BriefDescription": "Counts all retired load instructions.", "Counter": "0,1,2,3", "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_INST_RETIRED.ALL_LOADS", - "PublicDescription": "Counts Instructions with at least one architecturally visible load retired.", + "PublicDescription": "Counts Instructions with at least one architecturally visible load retired. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x81", "Unit": "cpu_core" @@ -425,7 +551,7 @@ "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_INST_RETIRED.ALL_STORES", - "PublicDescription": "Counts all retired store instructions.", + "PublicDescription": "Counts all retired store instructions. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x82", "Unit": "cpu_core" @@ -435,7 +561,7 @@ "Counter": "0,1,2,3", "EventCode": "0xd0", "EventName": "MEM_INST_RETIRED.ALL_SWPF", - "PublicDescription": "Counts all retired software prefetch instructions.", + "PublicDescription": "Counts all retired software prefetch instructions. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x84", "Unit": "cpu_core" @@ -446,7 +572,7 @@ "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_INST_RETIRED.ANY", - "PublicDescription": "Counts all retired memory instructions - loads and stores.", + "PublicDescription": "Counts all retired memory instructions - loads and stores. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x87", "Unit": "cpu_core" @@ -457,7 +583,7 @@ "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_INST_RETIRED.LOCK_LOADS", - "PublicDescription": "Counts retired load instructions with locked access.", + "PublicDescription": "Counts retired load instructions with locked access. Available PDIST counters: 0", "SampleAfterValue": "100007", "UMask": "0x21", "Unit": "cpu_core" @@ -468,7 +594,7 @@ "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_INST_RETIRED.SPLIT_LOADS", - "PublicDescription": "Counts retired load instructions that split across a cacheline boundary.", + "PublicDescription": "Counts retired load instructions that split across a cacheline boundary. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x41", "Unit": "cpu_core" @@ -479,7 +605,7 @@ "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_INST_RETIRED.SPLIT_STORES", - "PublicDescription": "Counts retired store instructions that split across a cacheline boundary.", + "PublicDescription": "Counts retired store instructions that split across a cacheline boundary. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x42", "Unit": "cpu_core" @@ -490,7 +616,7 @@ "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_INST_RETIRED.STLB_HIT_LOADS", - "PublicDescription": "Number of retired load instructions with a clean hit in the 2nd-level TLB (STLB).", + "PublicDescription": "Number of retired load instructions with a clean hit in the 2nd-level TLB (STLB). Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x9", "Unit": "cpu_core" @@ -501,7 +627,7 @@ "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_INST_RETIRED.STLB_HIT_STORES", - "PublicDescription": "Number of retired store instructions that hit in the 2nd-level TLB (STLB).", + "PublicDescription": "Number of retired store instructions that hit in the 2nd-level TLB (STLB). Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0xa", "Unit": "cpu_core" @@ -512,7 +638,7 @@ "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_INST_RETIRED.STLB_MISS_LOADS", - "PublicDescription": "Number of retired load instructions that (start a) miss in the 2nd-level TLB (STLB).", + "PublicDescription": "Number of retired load instructions that (start a) miss in the 2nd-level TLB (STLB). Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x11", "Unit": "cpu_core" @@ -523,7 +649,7 @@ "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_INST_RETIRED.STLB_MISS_STORES", - "PublicDescription": "Number of retired store instructions that (start a) miss in the 2nd-level TLB (STLB).", + "PublicDescription": "Number of retired store instructions that (start a) miss in the 2nd-level TLB (STLB). Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x12", "Unit": "cpu_core" @@ -534,7 +660,7 @@ "Data_LA": "1", "EventCode": "0xd2", "EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD", - "PublicDescription": "Counts retired load instructions whose data sources were a cross-core Snoop hits and forwards data from an in on-package core cache (induced by NI$)", + "PublicDescription": "Counts retired load instructions whose data sources were a cross-core Snoop hits and forwards data from an in on-package core cache (induced by NI$) Available PDIST counters: 0", "SampleAfterValue": "20011", "UMask": "0x10", "Unit": "cpu_core" @@ -545,7 +671,7 @@ "Data_LA": "1", "EventCode": "0xd2", "EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM", - "PublicDescription": "Counts retired load instructions whose data sources were HitM responses from shared L3, Hit-with-FWD is normally excluded.", + "PublicDescription": "Counts retired load instructions whose data sources were HitM responses from shared L3, Hit-with-FWD is normally excluded. Available PDIST counters: 0", "SampleAfterValue": "20011", "UMask": "0x4", "Unit": "cpu_core" @@ -556,7 +682,7 @@ "Data_LA": "1", "EventCode": "0xd2", "EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS", - "PublicDescription": "Counts the retired load instructions whose data sources were L3 hit and cross-core snoop missed in on-pkg core cache.", + "PublicDescription": "Counts the retired load instructions whose data sources were L3 hit and cross-core snoop missed in on-pkg core cache. Available PDIST counters: 0", "SampleAfterValue": "20011", "UMask": "0x1", "Unit": "cpu_core" @@ -567,7 +693,7 @@ "Data_LA": "1", "EventCode": "0xd2", "EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_NO_FWD", - "PublicDescription": "Counts retired load instructions whose data sources were L3 and cross-core snoop hits in on-pkg core cache.", + "PublicDescription": "Counts retired load instructions whose data sources were L3 and cross-core snoop hits in on-pkg core cache. Available PDIST counters: 0", "SampleAfterValue": "20011", "UMask": "0x2", "Unit": "cpu_core" @@ -578,7 +704,7 @@ "Data_LA": "1", "EventCode": "0xd4", "EventName": "MEM_LOAD_MISC_RETIRED.UC", - "PublicDescription": "Retired instructions with at least one load to uncacheable memory-type, or at least one cache-line split locked access (Bus Lock).", + "PublicDescription": "Retired instructions with at least one load to uncacheable memory-type, or at least one cache-line split locked access (Bus Lock). Available PDIST counters: 0", "SampleAfterValue": "100007", "UMask": "0x4", "Unit": "cpu_core" @@ -589,7 +715,7 @@ "Data_LA": "1", "EventCode": "0xd1", "EventName": "MEM_LOAD_RETIRED.FB_HIT", - "PublicDescription": "Counts retired load instructions with at least one uop was load missed in L1 but hit FB (Fill Buffers) due to preceding miss to the same cache line with data not ready.", + "PublicDescription": "Counts retired load instructions with at least one uop was load missed in L1 but hit FB (Fill Buffers) due to preceding miss to the same cache line with data not ready. Available PDIST counters: 0", "SampleAfterValue": "100007", "UMask": "0x40", "Unit": "cpu_core" @@ -600,7 +726,7 @@ "Data_LA": "1", "EventCode": "0xd1", "EventName": "MEM_LOAD_RETIRED.L1_HIT", - "PublicDescription": "Counts retired load instructions with at least one uop that hit in the L1 data cache. This event includes all SW prefetches and lock instructions regardless of the data source.", + "PublicDescription": "Counts retired load instructions with at least one uop that hit in the L1 data cache. This event includes all SW prefetches and lock instructions regardless of the data source. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x1", "Unit": "cpu_core" @@ -610,6 +736,7 @@ "Counter": "0,1,2,3", "EventCode": "0xd1", "EventName": "MEM_LOAD_RETIRED.L1_HIT_L1", + "PublicDescription": "Counts retired load instructions with at least one uop that hit in the Level 1 of the L1 data cache. Available PDIST counters: 0", "SampleAfterValue": "1000003", "Unit": "cpu_core" }, @@ -619,7 +746,7 @@ "Data_LA": "1", "EventCode": "0xd1", "EventName": "MEM_LOAD_RETIRED.L1_MISS", - "PublicDescription": "Counts retired load instructions with at least one uop that missed in the L1 cache.", + "PublicDescription": "Counts retired load instructions with at least one uop that missed in the L1 cache. Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0x8", "Unit": "cpu_core" @@ -630,7 +757,7 @@ "Data_LA": "1", "EventCode": "0xd1", "EventName": "MEM_LOAD_RETIRED.L2_HIT", - "PublicDescription": "Counts retired load instructions with L2 cache hits as data sources.", + "PublicDescription": "Counts retired load instructions with L2 cache hits as data sources. Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0x2", "Unit": "cpu_core" @@ -641,7 +768,7 @@ "Data_LA": "1", "EventCode": "0xd1", "EventName": "MEM_LOAD_RETIRED.L2_MISS", - "PublicDescription": "Counts retired load instructions missed L2 cache as data sources.", + "PublicDescription": "Counts retired load instructions missed L2 cache as data sources. Available PDIST counters: 0", "SampleAfterValue": "100021", "UMask": "0x10", "Unit": "cpu_core" @@ -652,7 +779,7 @@ "Data_LA": "1", "EventCode": "0xd1", "EventName": "MEM_LOAD_RETIRED.L3_HIT", - "PublicDescription": "Counts retired load instructions with at least one uop that hit in the L3 cache.", + "PublicDescription": "Counts retired load instructions with at least one uop that hit in the L3 cache. Available PDIST counters: 0", "SampleAfterValue": "100021", "UMask": "0x4", "Unit": "cpu_core" @@ -663,7 +790,7 @@ "Data_LA": "1", "EventCode": "0xd1", "EventName": "MEM_LOAD_RETIRED.L3_MISS", - "PublicDescription": "Counts retired load instructions with at least one uop that missed in the L3 cache.", + "PublicDescription": "Counts retired load instructions with at least one uop that missed in the L3 cache. Available PDIST counters: 0", "SampleAfterValue": "50021", "UMask": "0x20", "Unit": "cpu_core" @@ -1246,12 +1373,25 @@ "Unit": "cpu_core" }, { + "BriefDescription": "Counts demand data reads that have any type of response.", + "Counter": "0,1,2,3", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.DEMAND_DATA_RD.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x10001", + "PublicDescription": "Counts demand data reads that have any type of response. Available PDIST counters: 0", + "SampleAfterValue": "100003", + "UMask": "0x1", + "Unit": "cpu_core" + }, + { "BriefDescription": "Counts demand data reads that were supplied by the L3 cache where a snoop hit in another cores caches, data forwarding is required as the data is modified.", "Counter": "0,1,2,3", "EventCode": "0x2A,0x2B", "EventName": "OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x40001E00001", + "PublicDescription": "Counts demand data reads that were supplied by the L3 cache where a snoop hit in another cores caches, data forwarding is required as the data is modified. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1", "Unit": "cpu_core" @@ -1263,6 +1403,19 @@ "EventName": "OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x20001E00001", + "PublicDescription": "Counts demand data reads that were supplied by the L3 cache where a snoop hit in another cores caches which forwarded the unmodified data to the requesting core. Available PDIST counters: 0", + "SampleAfterValue": "100003", + "UMask": "0x1", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts demand read for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that have any type of response.", + "Counter": "0,1,2,3", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.DEMAND_RFO.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x10002", + "PublicDescription": "Counts demand read for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that have any type of response. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1", "Unit": "cpu_core" @@ -1274,6 +1427,7 @@ "EventName": "OCR.DEMAND_RFO.L3_HIT.SNOOP_HITM", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x40001E00002", + "PublicDescription": "Counts demand read for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that were supplied by the L3 cache where a snoop hit in another cores caches, data forwarding is required as the data is modified. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1", "Unit": "cpu_core" diff --git a/tools/perf/pmu-events/arch/x86/arrowlake/frontend.json b/tools/perf/pmu-events/arch/x86/arrowlake/frontend.json index fc5f4dd50fe6..67cc83de18d3 100644 --- a/tools/perf/pmu-events/arch/x86/arrowlake/frontend.json +++ b/tools/perf/pmu-events/arch/x86/arrowlake/frontend.json @@ -65,7 +65,7 @@ "EventName": "FRONTEND_RETIRED.ANY_ANT", "MSRIndex": "0x3F7", "MSRValue": "0x9", - "PublicDescription": "Always Not Taken (ANT) conditional retired branches (no BTB entry and not mispredicted)", + "PublicDescription": "Always Not Taken (ANT) conditional retired branches (no BTB entry and not mispredicted) Available PDIST counters: 0", "SampleAfterValue": "100007", "UMask": "0x3", "Unit": "cpu_core" @@ -77,7 +77,7 @@ "EventName": "FRONTEND_RETIRED.ANY_DSB_MISS", "MSRIndex": "0x3F7", "MSRValue": "0x1", - "PublicDescription": "Counts retired Instructions that experienced DSB (Decode stream buffer i.e. the decoded instruction-cache) miss.", + "PublicDescription": "Counts retired Instructions that experienced DSB (Decode stream buffer i.e. the decoded instruction-cache) miss. Available PDIST counters: 0", "SampleAfterValue": "100007", "UMask": "0x3", "Unit": "cpu_core" @@ -89,7 +89,7 @@ "EventName": "FRONTEND_RETIRED.DSB_MISS", "MSRIndex": "0x3F7", "MSRValue": "0x11", - "PublicDescription": "Number of retired Instructions that experienced a critical DSB (Decode stream buffer i.e. the decoded instruction-cache) miss. Critical means stalls were exposed to the back-end as a result of the DSB miss.", + "PublicDescription": "Number of retired Instructions that experienced a critical DSB (Decode stream buffer i.e. the decoded instruction-cache) miss. Critical means stalls were exposed to the back-end as a result of the DSB miss. Available PDIST counters: 0", "SampleAfterValue": "100007", "UMask": "0x3", "Unit": "cpu_core" @@ -119,7 +119,7 @@ "EventName": "FRONTEND_RETIRED.ITLB_MISS", "MSRIndex": "0x3F7", "MSRValue": "0x14", - "PublicDescription": "Counts retired Instructions that experienced iTLB (Instruction TLB) true miss.", + "PublicDescription": "Counts retired Instructions that experienced iTLB (Instruction TLB) true miss. Available PDIST counters: 0", "SampleAfterValue": "100007", "UMask": "0x3", "Unit": "cpu_core" @@ -140,7 +140,7 @@ "EventName": "FRONTEND_RETIRED.L1I_MISS", "MSRIndex": "0x3F7", "MSRValue": "0x12", - "PublicDescription": "Counts retired Instructions who experienced Instruction L1 Cache true miss.", + "PublicDescription": "Counts retired Instructions who experienced Instruction L1 Cache true miss. Available PDIST counters: 0", "SampleAfterValue": "100007", "UMask": "0x3", "Unit": "cpu_core" @@ -152,7 +152,7 @@ "EventName": "FRONTEND_RETIRED.L2_MISS", "MSRIndex": "0x3F7", "MSRValue": "0x13", - "PublicDescription": "Counts retired Instructions who experienced Instruction L2 Cache true miss.", + "PublicDescription": "Counts retired Instructions who experienced Instruction L2 Cache true miss. Available PDIST counters: 0", "SampleAfterValue": "100007", "UMask": "0x3", "Unit": "cpu_core" @@ -164,7 +164,7 @@ "EventName": "FRONTEND_RETIRED.LATENCY_GE_128", "MSRIndex": "0x3F7", "MSRValue": "0x608006", - "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 128 cycles which was not interrupted by a back-end stall.", + "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 128 cycles which was not interrupted by a back-end stall. Available PDIST counters: 0", "SampleAfterValue": "100007", "UMask": "0x3", "Unit": "cpu_core" @@ -176,7 +176,7 @@ "EventName": "FRONTEND_RETIRED.LATENCY_GE_16", "MSRIndex": "0x3F7", "MSRValue": "0x601006", - "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 16 cycles. During this period the front-end delivered no uops.", + "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 16 cycles. During this period the front-end delivered no uops. Available PDIST counters: 0", "SampleAfterValue": "100007", "UMask": "0x3", "Unit": "cpu_core" @@ -188,7 +188,7 @@ "EventName": "FRONTEND_RETIRED.LATENCY_GE_2", "MSRIndex": "0x3F7", "MSRValue": "0x600206", - "PublicDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of at least 2 cycles which was not interrupted by a back-end stall.", + "PublicDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of at least 2 cycles which was not interrupted by a back-end stall. Available PDIST counters: 0", "SampleAfterValue": "100007", "UMask": "0x3", "Unit": "cpu_core" @@ -200,7 +200,7 @@ "EventName": "FRONTEND_RETIRED.LATENCY_GE_256", "MSRIndex": "0x3F7", "MSRValue": "0x610006", - "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 256 cycles which was not interrupted by a back-end stall.", + "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 256 cycles which was not interrupted by a back-end stall. Available PDIST counters: 0", "SampleAfterValue": "100007", "UMask": "0x3", "Unit": "cpu_core" @@ -212,7 +212,7 @@ "EventName": "FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1", "MSRIndex": "0x3F7", "MSRValue": "0x100206", - "PublicDescription": "Counts retired instructions that are delivered to the back-end after the front-end had at least 1 bubble-slot for a period of 2 cycles. A bubble-slot is an empty issue-pipeline slot while there was no RAT stall.", + "PublicDescription": "Counts retired instructions that are delivered to the back-end after the front-end had at least 1 bubble-slot for a period of 2 cycles. A bubble-slot is an empty issue-pipeline slot while there was no RAT stall. Available PDIST counters: 0", "SampleAfterValue": "100007", "UMask": "0x3", "Unit": "cpu_core" @@ -224,7 +224,7 @@ "EventName": "FRONTEND_RETIRED.LATENCY_GE_32", "MSRIndex": "0x3F7", "MSRValue": "0x602006", - "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 32 cycles. During this period the front-end delivered no uops.", + "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 32 cycles. During this period the front-end delivered no uops. Available PDIST counters: 0", "SampleAfterValue": "100007", "UMask": "0x3", "Unit": "cpu_core" @@ -236,7 +236,7 @@ "EventName": "FRONTEND_RETIRED.LATENCY_GE_4", "MSRIndex": "0x3F7", "MSRValue": "0x600406", - "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 4 cycles which was not interrupted by a back-end stall.", + "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 4 cycles which was not interrupted by a back-end stall. Available PDIST counters: 0", "SampleAfterValue": "100007", "UMask": "0x3", "Unit": "cpu_core" @@ -248,7 +248,7 @@ "EventName": "FRONTEND_RETIRED.LATENCY_GE_512", "MSRIndex": "0x3F7", "MSRValue": "0x620006", - "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 512 cycles which was not interrupted by a back-end stall.", + "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 512 cycles which was not interrupted by a back-end stall. Available PDIST counters: 0", "SampleAfterValue": "100007", "UMask": "0x3", "Unit": "cpu_core" @@ -260,7 +260,7 @@ "EventName": "FRONTEND_RETIRED.LATENCY_GE_64", "MSRIndex": "0x3F7", "MSRValue": "0x604006", - "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 64 cycles which was not interrupted by a back-end stall.", + "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 64 cycles which was not interrupted by a back-end stall. Available PDIST counters: 0", "SampleAfterValue": "100007", "UMask": "0x3", "Unit": "cpu_core" @@ -272,7 +272,7 @@ "EventName": "FRONTEND_RETIRED.LATENCY_GE_8", "MSRIndex": "0x3F7", "MSRValue": "0x600806", - "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 8 cycles. During this period the front-end delivered no uops.", + "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 8 cycles. During this period the front-end delivered no uops. Available PDIST counters: 0", "SampleAfterValue": "100007", "UMask": "0x3", "Unit": "cpu_core" @@ -284,7 +284,7 @@ "EventName": "FRONTEND_RETIRED.MISP_ANT", "MSRIndex": "0x3F7", "MSRValue": "0x9", - "PublicDescription": "ANT retired branches that got just mispredicted", + "PublicDescription": "ANT retired branches that got just mispredicted Available PDIST counters: 0", "SampleAfterValue": "100007", "UMask": "0x2", "Unit": "cpu_core" @@ -296,6 +296,7 @@ "EventName": "FRONTEND_RETIRED.MS_FLOWS", "MSRIndex": "0x3F7", "MSRValue": "0x8", + "PublicDescription": "Counts flows delivered by the Microcode Sequencer Available PDIST counters: 0", "SampleAfterValue": "100007", "UMask": "0x3", "Unit": "cpu_core" @@ -307,7 +308,7 @@ "EventName": "FRONTEND_RETIRED.STLB_MISS", "MSRIndex": "0x3F7", "MSRValue": "0x15", - "PublicDescription": "Counts retired Instructions that experienced STLB (2nd level TLB) true miss.", + "PublicDescription": "Counts retired Instructions that experienced STLB (2nd level TLB) true miss. Available PDIST counters: 0", "SampleAfterValue": "100007", "UMask": "0x3", "Unit": "cpu_core" @@ -319,7 +320,7 @@ "EventName": "FRONTEND_RETIRED.UNKNOWN_BRANCH", "MSRIndex": "0x3F7", "MSRValue": "0x17", - "PublicDescription": "Number retired branch instructions that caused the front-end to be resteered when it finds the instruction in a fetch line. This is called Unknown Branch which occurs for the first time a branch instruction is fetched or when the branch is not tracked by the BPU (Branch Prediction Unit) anymore.", + "PublicDescription": "Number retired branch instructions that caused the front-end to be resteered when it finds the instruction in a fetch line. This is called Unknown Branch which occurs for the first time a branch instruction is fetched or when the branch is not tracked by the BPU (Branch Prediction Unit) anymore. Available PDIST counters: 0", "SampleAfterValue": "100007", "UMask": "0x3", "Unit": "cpu_core" diff --git a/tools/perf/pmu-events/arch/x86/arrowlake/memory.json b/tools/perf/pmu-events/arch/x86/arrowlake/memory.json index 08f01fc66fef..fb8d4ac69bda 100644 --- a/tools/perf/pmu-events/arch/x86/arrowlake/memory.json +++ b/tools/perf/pmu-events/arch/x86/arrowlake/memory.json @@ -163,7 +163,7 @@ "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_1024", "MSRIndex": "0x3F6", "MSRValue": "0x400", - "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 1024 cycles. Reported latency may be longer than just the memory latency.", + "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 1024 cycles. Reported latency may be longer than just the memory latency. Available PDIST counters: 0", "SampleAfterValue": "53", "UMask": "0x1", "Unit": "cpu_core" @@ -176,7 +176,7 @@ "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_128", "MSRIndex": "0x3F6", "MSRValue": "0x80", - "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 128 cycles. Reported latency may be longer than just the memory latency.", + "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 128 cycles. Reported latency may be longer than just the memory latency. Available PDIST counters: 0", "SampleAfterValue": "1009", "UMask": "0x1", "Unit": "cpu_core" @@ -189,7 +189,7 @@ "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_16", "MSRIndex": "0x3F6", "MSRValue": "0x10", - "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 16 cycles. Reported latency may be longer than just the memory latency.", + "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 16 cycles. Reported latency may be longer than just the memory latency. Available PDIST counters: 0", "SampleAfterValue": "20011", "UMask": "0x1", "Unit": "cpu_core" @@ -202,7 +202,7 @@ "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_2048", "MSRIndex": "0x3F6", "MSRValue": "0x800", - "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 2048 cycles. Reported latency may be longer than just the memory latency.", + "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 2048 cycles. Reported latency may be longer than just the memory latency. Available PDIST counters: 0", "SampleAfterValue": "23", "UMask": "0x1", "Unit": "cpu_core" @@ -215,7 +215,7 @@ "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_256", "MSRIndex": "0x3F6", "MSRValue": "0x100", - "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 256 cycles. Reported latency may be longer than just the memory latency.", + "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 256 cycles. Reported latency may be longer than just the memory latency. Available PDIST counters: 0", "SampleAfterValue": "503", "UMask": "0x1", "Unit": "cpu_core" @@ -228,7 +228,7 @@ "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_32", "MSRIndex": "0x3F6", "MSRValue": "0x20", - "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 32 cycles. Reported latency may be longer than just the memory latency.", + "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 32 cycles. Reported latency may be longer than just the memory latency. Available PDIST counters: 0", "SampleAfterValue": "100007", "UMask": "0x1", "Unit": "cpu_core" @@ -241,7 +241,7 @@ "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_4", "MSRIndex": "0x3F6", "MSRValue": "0x4", - "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 4 cycles. Reported latency may be longer than just the memory latency.", + "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 4 cycles. Reported latency may be longer than just the memory latency. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1", "Unit": "cpu_core" @@ -254,7 +254,7 @@ "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_512", "MSRIndex": "0x3F6", "MSRValue": "0x200", - "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 512 cycles. Reported latency may be longer than just the memory latency.", + "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 512 cycles. Reported latency may be longer than just the memory latency. Available PDIST counters: 0", "SampleAfterValue": "101", "UMask": "0x1", "Unit": "cpu_core" @@ -267,7 +267,7 @@ "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_64", "MSRIndex": "0x3F6", "MSRValue": "0x40", - "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 64 cycles. Reported latency may be longer than just the memory latency.", + "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 64 cycles. Reported latency may be longer than just the memory latency. Available PDIST counters: 0", "SampleAfterValue": "2003", "UMask": "0x1", "Unit": "cpu_core" @@ -280,7 +280,7 @@ "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_8", "MSRIndex": "0x3F6", "MSRValue": "0x8", - "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 8 cycles. Reported latency may be longer than just the memory latency.", + "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 8 cycles. Reported latency may be longer than just the memory latency. Available PDIST counters: 0", "SampleAfterValue": "50021", "UMask": "0x1", "Unit": "cpu_core" @@ -291,7 +291,7 @@ "Data_LA": "1", "EventCode": "0xcd", "EventName": "MEM_TRANS_RETIRED.STORE_SAMPLE", - "PublicDescription": "Counts Retired memory accesses with at least 1 store operation. This PEBS event is the precisely-distributed (PDist) trigger covering all stores uops for sampling by the PEBS Store Latency Facility. The facility is described in Intel SDM Volume 3 section 19.9.8", + "PublicDescription": "Counts Retired memory accesses with at least 1 store operation. This PEBS event is the precisely-distributed (PDist) trigger covering all stores uops for sampling by the PEBS Store Latency Facility. The facility is described in Intel SDM Volume 3 section 19.9.8 Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x2", "Unit": "cpu_core" @@ -333,12 +333,25 @@ "Unit": "cpu_lowpower" }, { + "BriefDescription": "Counts demand data reads that were supplied by DRAM.", + "Counter": "0,1,2,3", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.DEMAND_DATA_RD.DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x1E780000001", + "PublicDescription": "Counts demand data reads that were supplied by DRAM. Available PDIST counters: 0", + "SampleAfterValue": "100003", + "UMask": "0x1", + "Unit": "cpu_core" + }, + { "BriefDescription": "Counts demand data reads that were not supplied by the L3 cache.", "Counter": "0,1,2,3", "EventCode": "0x2A,0x2B", "EventName": "OCR.DEMAND_DATA_RD.L3_MISS", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0xFE7F8000001", + "PublicDescription": "Counts demand data reads that were not supplied by the L3 cache. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1", "Unit": "cpu_core" @@ -350,6 +363,7 @@ "EventName": "OCR.DEMAND_RFO.L3_MISS", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0xFE7F8000002", + "PublicDescription": "Counts demand read for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that were not supplied by the L3 cache. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1", "Unit": "cpu_core" diff --git a/tools/perf/pmu-events/arch/x86/arrowlake/other.json b/tools/perf/pmu-events/arch/x86/arrowlake/other.json index 0175b2193201..51bc763a5887 100644 --- a/tools/perf/pmu-events/arch/x86/arrowlake/other.json +++ b/tools/perf/pmu-events/arch/x86/arrowlake/other.json @@ -19,71 +19,6 @@ "Unit": "cpu_core" }, { - "BriefDescription": "Counts cycles where the pipeline is stalled due to serializing operations.", - "Counter": "0,1,2,3,4,5,6,7,8,9", - "EventCode": "0xa2", - "EventName": "BE_STALLS.SCOREBOARD", - "SampleAfterValue": "100003", - "UMask": "0x2", - "Unit": "cpu_core" - }, - { - "BriefDescription": "Count number of times a load is depending on another load that had just write back its data or in previous or 2 cycles back. This event supports in-direct dependency through a single uop.", - "Counter": "0,1,2,3,4,5,6,7,8,9", - "EventCode": "0x02", - "EventName": "DEPENDENT_LOADS.ANY", - "SampleAfterValue": "1000003", - "UMask": "0x7", - "Unit": "cpu_core" - }, - { - "BriefDescription": "Counts the number of uops executed on secondary integer ports 0,1,2,3.", - "Counter": "0,1,2,3,4,5,6,7", - "EventCode": "0xb3", - "EventName": "INT_UOPS_EXECUTED.2ND", - "SampleAfterValue": "1000003", - "UMask": "0x80", - "Unit": "cpu_atom" - }, - { - "BriefDescription": "Counts the number of uops executed on a load port.", - "Counter": "0,1,2,3,4,5,6,7", - "EventCode": "0xb3", - "EventName": "INT_UOPS_EXECUTED.LD", - "PublicDescription": "Counts the number of uops executed on a load port. This event counts for integer uops even if the destination is FP/vector", - "SampleAfterValue": "1000003", - "UMask": "0x1", - "Unit": "cpu_atom" - }, - { - "BriefDescription": "Counts the number of uops executed on integer port 0,1, 2, 3.", - "Counter": "0,1,2,3,4,5,6,7", - "EventCode": "0xb3", - "EventName": "INT_UOPS_EXECUTED.PRIMARY", - "SampleAfterValue": "1000003", - "UMask": "0x78", - "Unit": "cpu_atom" - }, - { - "BriefDescription": "Counts the number of uops executed on a Store address port.", - "Counter": "0,1,2,3,4,5,6,7", - "EventCode": "0xb3", - "EventName": "INT_UOPS_EXECUTED.STA", - "PublicDescription": "Counts the number of uops executed on a Store address port. This event counts integer uops even if the data source is FP/vector", - "SampleAfterValue": "1000003", - "UMask": "0x2", - "Unit": "cpu_atom" - }, - { - "BriefDescription": "Counts the number of uops executed on an integer store data and jump port.", - "Counter": "0,1,2,3,4,5,6,7", - "EventCode": "0xb3", - "EventName": "INT_UOPS_EXECUTED.STD_JMP", - "SampleAfterValue": "1000003", - "UMask": "0x4", - "Unit": "cpu_atom" - }, - { "BriefDescription": "This event is deprecated. [This event is alias to MISC_RETIRED.LBR_INSERTS]", "Counter": "0,1,2,3,4,5,6,7", "Deprecated": "1", @@ -94,81 +29,13 @@ "Unit": "cpu_lowpower" }, { - "BriefDescription": "Counts cycles where no execution is happening due to loads waiting for L1 cache (that is: no execution & load in flight & no load missed L1 cache)", - "Counter": "0,1,2,3,4,5,6,7,8,9", - "EventCode": "0x46", - "EventName": "MEMORY_STALLS.L1", - "SampleAfterValue": "1000003", - "UMask": "0x1", - "Unit": "cpu_core" - }, - { - "BriefDescription": "Counts cycles where no execution is happening due to loads waiting for L2 cache (that is: no execution & load in flight & load missed L1 & no load missed L2 cache)", - "Counter": "0,1,2,3,4,5,6,7,8,9", - "EventCode": "0x46", - "EventName": "MEMORY_STALLS.L2", - "SampleAfterValue": "1000003", - "UMask": "0x2", - "Unit": "cpu_core" - }, - { - "BriefDescription": "Counts cycles where no execution is happening due to loads waiting for L3 cache (that is: no execution & load in flight & load missed L1 & load missed L2 cache & no load missed L3 Cache)", - "Counter": "0,1,2,3,4,5,6,7,8,9", - "EventCode": "0x46", - "EventName": "MEMORY_STALLS.L3", - "SampleAfterValue": "1000003", - "UMask": "0x4", - "Unit": "cpu_core" - }, - { - "BriefDescription": "Counts cycles where no execution is happening due to loads waiting for Memory (that is: no execution & load in flight & a load missed L3 cache)", - "Counter": "0,1,2,3,4,5,6,7,8,9", - "EventCode": "0x46", - "EventName": "MEMORY_STALLS.MEM", - "SampleAfterValue": "1000003", - "UMask": "0x8", - "Unit": "cpu_core" - }, - { - "BriefDescription": "Counts demand data reads that have any type of response.", - "Counter": "0,1,2,3", - "EventCode": "0x2A,0x2B", - "EventName": "OCR.DEMAND_DATA_RD.ANY_RESPONSE", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x10001", - "SampleAfterValue": "100003", - "UMask": "0x1", - "Unit": "cpu_core" - }, - { - "BriefDescription": "Counts demand data reads that were supplied by DRAM.", - "Counter": "0,1,2,3", - "EventCode": "0x2A,0x2B", - "EventName": "OCR.DEMAND_DATA_RD.DRAM", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x1E780000001", - "SampleAfterValue": "100003", - "UMask": "0x1", - "Unit": "cpu_core" - }, - { - "BriefDescription": "Counts demand read for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that have any type of response.", - "Counter": "0,1,2,3", - "EventCode": "0x2A,0x2B", - "EventName": "OCR.DEMAND_RFO.ANY_RESPONSE", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x10002", - "SampleAfterValue": "100003", - "UMask": "0x1", - "Unit": "cpu_core" - }, - { "BriefDescription": "Counts streaming stores which modify a full 64 byte cacheline that have any type of response.", "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xB7", "EventName": "OCR.FULL_STREAMING_WR.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x800000010000", + "PublicDescription": "Counts streaming stores which modify a full 64 byte cacheline that have any type of response. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1", "Unit": "cpu_atom" @@ -180,6 +47,7 @@ "EventName": "OCR.PARTIAL_STREAMING_WR.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x400000010000", + "PublicDescription": "Counts streaming stores which modify only part of a 64 byte cacheline that have any type of response. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1", "Unit": "cpu_atom" @@ -191,6 +59,7 @@ "EventName": "OCR.STREAMING_WR.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x10800", + "PublicDescription": "Counts streaming stores that have any type of response. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1", "Unit": "cpu_atom" @@ -202,70 +71,12 @@ "EventName": "OCR.STREAMING_WR.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x10800", + "PublicDescription": "Counts streaming stores that have any type of response. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1", "Unit": "cpu_core" }, { - "BriefDescription": "Cycles when Reservation Station (RS) is empty for the thread.", - "Counter": "0,1,2,3,4,5,6,7,8,9", - "EventCode": "0xa5", - "EventName": "RS.EMPTY", - "PublicDescription": "Counts cycles during which the reservation station (RS) is empty for this logical processor. This is usually caused when the front-end pipeline runs into starvation periods (e.g. branch mispredictions or i-cache misses)", - "SampleAfterValue": "1000003", - "UMask": "0x7", - "Unit": "cpu_core" - }, - { - "BriefDescription": "Counts end of periods where the Reservation Station (RS) was empty.", - "Counter": "0,1,2,3,4,5,6,7,8,9", - "CounterMask": "1", - "EdgeDetect": "1", - "EventCode": "0xa5", - "EventName": "RS.EMPTY_COUNT", - "Invert": "1", - "PublicDescription": "Counts end of periods where the Reservation Station (RS) was empty. Could be useful to closely sample on front-end latency issues (see the FRONTEND_RETIRED event of designated precise events)", - "SampleAfterValue": "100003", - "UMask": "0x7", - "Unit": "cpu_core" - }, - { - "BriefDescription": "Cycles when RS was empty and a resource allocation stall is asserted", - "Counter": "0,1,2,3,4,5,6,7,8,9", - "EventCode": "0xa5", - "EventName": "RS.EMPTY_RESOURCE", - "SampleAfterValue": "1000003", - "UMask": "0x1", - "Unit": "cpu_core" - }, - { - "BriefDescription": "Counts the number of issue slots in a UMWAIT or TPAUSE instruction where no uop issues due to the instruction putting the CPU into the C0.1 activity state.", - "Counter": "0,1,2,3,4,5,6,7", - "EventCode": "0x75", - "EventName": "SERIALIZATION.C01_MS_SCB", - "SampleAfterValue": "1000003", - "UMask": "0x4", - "Unit": "cpu_atom" - }, - { - "BriefDescription": "Counts the number of issue slots in a UMWAIT or TPAUSE instruction where no uop issues due to the instruction putting the CPU into the C0.1 activity state.", - "Counter": "0,1,2,3,4,5,6,7", - "EventCode": "0x75", - "EventName": "SERIALIZATION.C01_MS_SCB", - "SampleAfterValue": "200003", - "UMask": "0x4", - "Unit": "cpu_lowpower" - }, - { - "BriefDescription": "Counts the number of issue slots where no uop could issue due to an IQ scoreboard that stalls allocation until a specified older uop retires or (in the case of jump scoreboard) executes. Commonly executed instructions with IQ scoreboards include LFENCE and MFENCE.", - "Counter": "0,1,2,3,4,5,6,7", - "EventCode": "0x75", - "EventName": "SERIALIZATION.IQ_JEU_SCB", - "SampleAfterValue": "1000003", - "UMask": "0x1", - "Unit": "cpu_atom" - }, - { "BriefDescription": "Cycles the uncore cannot take further requests", "Counter": "0,1,2,3,4,5,6,7,8,9", "CounterMask": "1", diff --git a/tools/perf/pmu-events/arch/x86/arrowlake/pipeline.json b/tools/perf/pmu-events/arch/x86/arrowlake/pipeline.json index 6dbde51e7ead..18a22368b99b 100644 --- a/tools/perf/pmu-events/arch/x86/arrowlake/pipeline.json +++ b/tools/perf/pmu-events/arch/x86/arrowlake/pipeline.json @@ -52,6 +52,15 @@ "Unit": "cpu_core" }, { + "BriefDescription": "Counts cycles where the pipeline is stalled due to serializing operations.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xa2", + "EventName": "BE_STALLS.SCOREBOARD", + "SampleAfterValue": "100003", + "UMask": "0x2", + "Unit": "cpu_core" + }, + { "BriefDescription": "Counts the total number of branch instructions retired for all branch types.", "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc4", @@ -65,7 +74,7 @@ "Counter": "0,1,2,3,4,5,6,7,8,9", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.ALL_BRANCHES", - "PublicDescription": "Counts all branch instructions retired.", + "PublicDescription": "Counts all branch instructions retired. Available PDIST counters: 0", "SampleAfterValue": "400009", "Unit": "cpu_core" }, @@ -92,7 +101,7 @@ "Counter": "0,1,2,3,4,5,6,7,8,9", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.COND", - "PublicDescription": "Counts conditional branch instructions retired.", + "PublicDescription": "Counts conditional branch instructions retired. Available PDIST counters: 0", "SampleAfterValue": "400009", "UMask": "0x111", "Unit": "cpu_core" @@ -111,7 +120,7 @@ "Counter": "0,1,2,3,4,5,6,7,8,9", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.COND_NTAKEN", - "PublicDescription": "Counts not taken branch instructions retired.", + "PublicDescription": "Counts not taken branch instructions retired. Available PDIST counters: 0", "SampleAfterValue": "400009", "UMask": "0x10", "Unit": "cpu_core" @@ -130,7 +139,7 @@ "Counter": "0,1,2,3,4,5,6,7,8,9", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.COND_TAKEN", - "PublicDescription": "Counts taken conditional branch instructions retired.", + "PublicDescription": "Counts taken conditional branch instructions retired. Available PDIST counters: 0", "SampleAfterValue": "400009", "UMask": "0x101", "Unit": "cpu_core" @@ -149,7 +158,7 @@ "Counter": "0,1,2,3,4,5,6,7,8,9", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.COND_TAKEN_BWD", - "PublicDescription": "Counts taken backward conditional branch instructions retired.", + "PublicDescription": "Counts taken backward conditional branch instructions retired. Available PDIST counters: 0", "SampleAfterValue": "400009", "UMask": "0x1", "Unit": "cpu_core" @@ -159,7 +168,7 @@ "Counter": "0,1,2,3,4,5,6,7,8,9", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.COND_TAKEN_FWD", - "PublicDescription": "Counts taken forward conditional branch instructions retired.", + "PublicDescription": "Counts taken forward conditional branch instructions retired. Available PDIST counters: 0", "SampleAfterValue": "400009", "UMask": "0x102", "Unit": "cpu_core" @@ -178,7 +187,7 @@ "Counter": "0,1,2,3,4,5,6,7,8,9", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.FAR_BRANCH", - "PublicDescription": "Counts far branch instructions retired.", + "PublicDescription": "Counts far branch instructions retired. Available PDIST counters: 0", "SampleAfterValue": "100007", "UMask": "0x40", "Unit": "cpu_core" @@ -206,7 +215,7 @@ "Counter": "0,1,2,3,4,5,6,7,8,9", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.INDIRECT", - "PublicDescription": "Counts near indirect branch instructions retired excluding returns. TSX abort is an indirect branch.", + "PublicDescription": "Counts near indirect branch instructions retired excluding returns. TSX abort is an indirect branch. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x80", "Unit": "cpu_core" @@ -261,7 +270,7 @@ "Counter": "0,1,2,3,4,5,6,7,8,9", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.NEAR_CALL", - "PublicDescription": "Counts both direct and indirect near call instructions retired.", + "PublicDescription": "Counts both direct and indirect near call instructions retired. Available PDIST counters: 0", "SampleAfterValue": "100007", "UMask": "0x2", "Unit": "cpu_core" @@ -289,7 +298,7 @@ "Counter": "0,1,2,3,4,5,6,7,8,9", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.NEAR_RETURN", - "PublicDescription": "Counts return instructions retired.", + "PublicDescription": "Counts return instructions retired. Available PDIST counters: 0", "SampleAfterValue": "100007", "UMask": "0x8", "Unit": "cpu_core" @@ -308,7 +317,7 @@ "Counter": "0,1,2,3,4,5,6,7,8,9", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.NEAR_TAKEN", - "PublicDescription": "Counts taken branch instructions retired.", + "PublicDescription": "Counts taken branch instructions retired. Available PDIST counters: 0", "SampleAfterValue": "400009", "UMask": "0x20", "Unit": "cpu_core" @@ -363,7 +372,7 @@ "Counter": "0,1,2,3,4,5,6,7,8,9", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.ALL_BRANCHES", - "PublicDescription": "Counts all the retired branch instructions that were mispredicted by the processor. A branch misprediction occurs when the processor incorrectly predicts the destination of the branch. When the misprediction is discovered at execution, all the instructions executed in the wrong (speculative) path must be discarded, and the processor must start fetching from the correct path.", + "PublicDescription": "Counts all the retired branch instructions that were mispredicted by the processor. A branch misprediction occurs when the processor incorrectly predicts the destination of the branch. When the misprediction is discovered at execution, all the instructions executed in the wrong (speculative) path must be discarded, and the processor must start fetching from the correct path. Available PDIST counters: 0", "SampleAfterValue": "400009", "Unit": "cpu_core" }, @@ -381,6 +390,7 @@ "Counter": "0,1,2,3,4,5,6,7,8,9", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.ALL_BRANCHES_COST", + "PublicDescription": "All mispredicted branch instructions retired. This precise event may be used to get the misprediction cost via the Retire_Latency field of PEBS. It fires on the instruction that immediately follows the mispredicted branch. Available PDIST counters: 0", "SampleAfterValue": "400009", "UMask": "0x44", "Unit": "cpu_core" @@ -399,7 +409,7 @@ "Counter": "0,1,2,3,4,5,6,7,8,9", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.COND", - "PublicDescription": "Counts mispredicted conditional branch instructions retired.", + "PublicDescription": "Counts mispredicted conditional branch instructions retired. Available PDIST counters: 0", "SampleAfterValue": "400009", "UMask": "0x111", "Unit": "cpu_core" @@ -418,6 +428,7 @@ "Counter": "0,1,2,3,4,5,6,7,8,9", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.COND_COST", + "PublicDescription": "Mispredicted conditional branch instructions retired. This precise event may be used to get the misprediction cost via the Retire_Latency field of PEBS. It fires on the instruction that immediately follows the mispredicted branch. Available PDIST counters: 0", "SampleAfterValue": "400009", "UMask": "0x151", "Unit": "cpu_core" @@ -427,7 +438,7 @@ "Counter": "0,1,2,3,4,5,6,7,8,9", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.COND_NTAKEN", - "PublicDescription": "Counts the number of conditional branch instructions retired that were mispredicted and the branch direction was not taken.", + "PublicDescription": "Counts the number of conditional branch instructions retired that were mispredicted and the branch direction was not taken. Available PDIST counters: 0", "SampleAfterValue": "400009", "UMask": "0x10", "Unit": "cpu_core" @@ -437,6 +448,7 @@ "Counter": "0,1,2,3,4,5,6,7,8,9", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.COND_NTAKEN_COST", + "PublicDescription": "Mispredicted non-taken conditional branch instructions retired. This precise event may be used to get the misprediction cost via the Retire_Latency field of PEBS. It fires on the instruction that immediately follows the mispredicted branch. Available PDIST counters: 0", "SampleAfterValue": "400009", "UMask": "0x50", "Unit": "cpu_core" @@ -455,7 +467,7 @@ "Counter": "0,1,2,3,4,5,6,7,8,9", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.COND_TAKEN", - "PublicDescription": "Counts taken conditional mispredicted branch instructions retired.", + "PublicDescription": "Counts taken conditional mispredicted branch instructions retired. Available PDIST counters: 0", "SampleAfterValue": "400009", "UMask": "0x101", "Unit": "cpu_core" @@ -474,7 +486,7 @@ "Counter": "0,1,2,3,4,5,6,7,8,9", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.COND_TAKEN_BWD", - "PublicDescription": "Counts taken backward conditional mispredicted branch instructions retired.", + "PublicDescription": "Counts taken backward conditional mispredicted branch instructions retired. Available PDIST counters: 0", "SampleAfterValue": "400009", "UMask": "0x1", "Unit": "cpu_core" @@ -484,6 +496,7 @@ "Counter": "0,1,2,3,4,5,6,7,8,9", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.COND_TAKEN_BWD_COST", + "PublicDescription": "number of branch instructions retired that were mispredicted and taken backward. This precise event may be used to get the misprediction cost via the Retire_Latency field of PEBS. It fires on the instruction that immediately follows the mispredicted branch. Available PDIST counters: 0", "SampleAfterValue": "400009", "UMask": "0x8001", "Unit": "cpu_core" @@ -493,6 +506,7 @@ "Counter": "0,1,2,3,4,5,6,7,8,9", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.COND_TAKEN_COST", + "PublicDescription": "Mispredicted taken conditional branch instructions retired. This precise event may be used to get the misprediction cost via the Retire_Latency field of PEBS. It fires on the instruction that immediately follows the mispredicted branch. Available PDIST counters: 0", "SampleAfterValue": "400009", "UMask": "0x141", "Unit": "cpu_core" @@ -502,7 +516,7 @@ "Counter": "0,1,2,3,4,5,6,7,8,9", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.COND_TAKEN_FWD", - "PublicDescription": "Counts taken forward conditional mispredicted branch instructions retired.", + "PublicDescription": "Counts taken forward conditional mispredicted branch instructions retired. Available PDIST counters: 0", "SampleAfterValue": "400009", "Unit": "cpu_core" }, @@ -511,6 +525,7 @@ "Counter": "0,1,2,3,4,5,6,7,8,9", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.COND_TAKEN_FWD_COST", + "PublicDescription": "number of branch instructions retired that were mispredicted and taken forward. This precise event may be used to get the misprediction cost via the Retire_Latency field of PEBS. It fires on the instruction that immediately follows the mispredicted branch. Available PDIST counters: 0", "SampleAfterValue": "400009", "UMask": "0x8002", "Unit": "cpu_core" @@ -529,7 +544,7 @@ "Counter": "0,1,2,3,4,5,6,7,8,9", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.INDIRECT", - "PublicDescription": "Counts miss-predicted near indirect branch instructions retired excluding returns. TSX abort is an indirect branch.", + "PublicDescription": "Counts miss-predicted near indirect branch instructions retired excluding returns. TSX abort is an indirect branch. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x80", "Unit": "cpu_core" @@ -557,7 +572,7 @@ "Counter": "0,1,2,3,4,5,6,7,8,9", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.INDIRECT_CALL", - "PublicDescription": "Counts retired mispredicted indirect (near taken) CALL instructions, including both register and memory indirect.", + "PublicDescription": "Counts retired mispredicted indirect (near taken) CALL instructions, including both register and memory indirect. Available PDIST counters: 0", "SampleAfterValue": "400009", "UMask": "0x2", "Unit": "cpu_core" @@ -576,6 +591,7 @@ "Counter": "0,1,2,3,4,5,6,7,8,9", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.INDIRECT_CALL_COST", + "PublicDescription": "Mispredicted indirect CALL retired. This precise event may be used to get the misprediction cost via the Retire_Latency field of PEBS. It fires on the instruction that immediately follows the mispredicted branch. Available PDIST counters: 0", "SampleAfterValue": "400009", "UMask": "0x42", "Unit": "cpu_core" @@ -585,6 +601,7 @@ "Counter": "0,1,2,3,4,5,6,7,8,9", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.INDIRECT_COST", + "PublicDescription": "Mispredicted near indirect branch instructions retired (excluding returns). This precise event may be used to get the misprediction cost via the Retire_Latency field of PEBS. It fires on the instruction that immediately follows the mispredicted branch. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0xc0", "Unit": "cpu_core" @@ -603,7 +620,7 @@ "Counter": "0,1,2,3,4,5,6,7,8,9", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.NEAR_TAKEN", - "PublicDescription": "Counts number of near branch instructions retired that were mispredicted and taken.", + "PublicDescription": "Counts number of near branch instructions retired that were mispredicted and taken. Available PDIST counters: 0", "SampleAfterValue": "400009", "UMask": "0x20", "Unit": "cpu_core" @@ -622,6 +639,7 @@ "Counter": "0,1,2,3,4,5,6,7,8,9", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.NEAR_TAKEN_COST", + "PublicDescription": "Mispredicted taken near branch instructions retired. This precise event may be used to get the misprediction cost via the Retire_Latency field of PEBS. It fires on the instruction that immediately follows the mispredicted branch. Available PDIST counters: 0", "SampleAfterValue": "400009", "UMask": "0x60", "Unit": "cpu_core" @@ -631,7 +649,7 @@ "Counter": "0,1,2,3,4,5,6,7,8,9", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.RET", - "PublicDescription": "This is a non-precise version (that is, does not use PEBS) of the event that counts mispredicted return instructions retired.", + "PublicDescription": "This is a non-precise version (that is, does not use PEBS) of the event that counts mispredicted return instructions retired. Available PDIST counters: 0", "SampleAfterValue": "100007", "UMask": "0x8", "Unit": "cpu_core" @@ -659,6 +677,7 @@ "Counter": "0,1,2,3,4,5,6,7,8,9", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.RET_COST", + "PublicDescription": "Mispredicted ret instructions retired. This precise event may be used to get the misprediction cost via the Retire_Latency field of PEBS. It fires on the instruction that immediately follows the mispredicted branch. Available PDIST counters: 0", "SampleAfterValue": "100007", "UMask": "0x48", "Unit": "cpu_core" @@ -889,6 +908,15 @@ "Unit": "cpu_core" }, { + "BriefDescription": "Count number of times a load is depending on another load that had just write back its data or in previous or 2 cycles back. This event supports in-direct dependency through a single uop.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0x02", + "EventName": "DEPENDENT_LOADS.ANY", + "SampleAfterValue": "1000003", + "UMask": "0x7", + "Unit": "cpu_core" + }, + { "BriefDescription": "Cycles total of 1 uop is executed on all ports and Reservation Station was not empty.", "Counter": "0,1,2,3,4,5,6,7,8,9", "EventCode": "0xa6", @@ -982,6 +1010,7 @@ "BriefDescription": "Fixed Counter: Counts the number of instructions retired.", "Counter": "Fixed counter 0", "EventName": "INST_RETIRED.ANY", + "PublicDescription": "Fixed Counter: Counts the number of instructions retired. Available PDIST counters: 32", "SampleAfterValue": "2000003", "UMask": "0x1", "Unit": "cpu_atom" @@ -990,7 +1019,7 @@ "BriefDescription": "Number of instructions retired. Fixed Counter - architectural event", "Counter": "Fixed counter 0", "EventName": "INST_RETIRED.ANY", - "PublicDescription": "Counts the number of X86 instructions retired - an Architectural PerfMon event. Counting continues during hardware interrupts, traps, and inside interrupt handlers. Notes: INST_RETIRED.ANY is counted by a designated fixed counter freeing up programmable counters to count other events. INST_RETIRED.ANY_P is counted by a programmable counter.", + "PublicDescription": "Counts the number of X86 instructions retired - an Architectural PerfMon event. Counting continues during hardware interrupts, traps, and inside interrupt handlers. Notes: INST_RETIRED.ANY is counted by a designated fixed counter freeing up programmable counters to count other events. INST_RETIRED.ANY_P is counted by a programmable counter. Available PDIST counters: 32", "SampleAfterValue": "2000003", "UMask": "0x1", "Unit": "cpu_core" @@ -999,6 +1028,7 @@ "BriefDescription": "Fixed Counter: Counts the number of instructions retired", "Counter": "Fixed counter 0", "EventName": "INST_RETIRED.ANY", + "PublicDescription": "Fixed Counter: Counts the number of instructions retired Available PDIST counters: 32", "SampleAfterValue": "2000003", "UMask": "0x1", "Unit": "cpu_lowpower" @@ -1016,7 +1046,7 @@ "Counter": "0,1,2,3,4,5,6,7,8,9", "EventCode": "0xc0", "EventName": "INST_RETIRED.ANY_P", - "PublicDescription": "Counts the number of X86 instructions retired - an Architectural PerfMon event. Counting continues during hardware interrupts, traps, and inside interrupt handlers. Notes: INST_RETIRED.ANY is counted by a designated fixed counter freeing up programmable counters to count other events. INST_RETIRED.ANY_P is counted by a programmable counter.", + "PublicDescription": "Counts the number of X86 instructions retired - an Architectural PerfMon event. Counting continues during hardware interrupts, traps, and inside interrupt handlers. Notes: INST_RETIRED.ANY is counted by a designated fixed counter freeing up programmable counters to count other events. INST_RETIRED.ANY_P is counted by a programmable counter. Available PDIST counters: 0", "SampleAfterValue": "2000003", "Unit": "cpu_core" }, @@ -1033,6 +1063,7 @@ "Counter": "0,1,2,3,4,5,6,7,8,9", "EventCode": "0xc0", "EventName": "INST_RETIRED.BR_FUSED", + "PublicDescription": "retired macro-fused uops when there is a branch in the macro-fused pair (the two instructions that got macro-fused count once in this pmon) Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x10", "Unit": "cpu_core" @@ -1042,6 +1073,7 @@ "Counter": "0,1,2,3,4,5,6,7,8,9", "EventCode": "0xc0", "EventName": "INST_RETIRED.MACRO_FUSED", + "PublicDescription": "INST_RETIRED.MACRO_FUSED Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x30", "Unit": "cpu_core" @@ -1051,7 +1083,7 @@ "Counter": "0,1,2,3,4,5,6,7,8,9", "EventCode": "0xc0", "EventName": "INST_RETIRED.NOP", - "PublicDescription": "Counts all retired NOP or ENDBR32/64 or PREFETCHIT0/1 instructions", + "PublicDescription": "Counts all retired NOP or ENDBR32/64 or PREFETCHIT0/1 instructions Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x2", "Unit": "cpu_core" @@ -1060,7 +1092,7 @@ "BriefDescription": "Precise instruction retired with PEBS precise-distribution", "Counter": "Fixed counter 0", "EventName": "INST_RETIRED.PREC_DIST", - "PublicDescription": "A version of INST_RETIRED that allows for a precise distribution of samples across instructions retired. It utilizes the Precise Distribution of Instructions Retired (PDIR++) feature to fix bias in how retired instructions get sampled. Use on Fixed Counter 0.", + "PublicDescription": "A version of INST_RETIRED that allows for a precise distribution of samples across instructions retired. It utilizes the Precise Distribution of Instructions Retired (PDIR++) feature to fix bias in how retired instructions get sampled. Use on Fixed Counter 0. Available PDIST counters: 32", "SampleAfterValue": "2000003", "UMask": "0x1", "Unit": "cpu_core" @@ -1070,7 +1102,7 @@ "Counter": "0,1,2,3,4,5,6,7,8,9", "EventCode": "0xc0", "EventName": "INST_RETIRED.REP_ITERATION", - "PublicDescription": "Number of iterations of Repeat (REP) string retired instructions such as MOVS, CMPS, and SCAS. Each has a byte, word, and doubleword version and string instructions can be repeated using a repetition prefix, REP, that allows their architectural execution to be repeated a number of times as specified by the RCX register. Note the number of iterations is implementation-dependent.", + "PublicDescription": "Number of iterations of Repeat (REP) string retired instructions such as MOVS, CMPS, and SCAS. Each has a byte, word, and doubleword version and string instructions can be repeated using a repetition prefix, REP, that allows their architectural execution to be repeated a number of times as specified by the RCX register. Note the number of iterations is implementation-dependent. Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x8", "Unit": "cpu_core" @@ -1140,6 +1172,53 @@ "Unit": "cpu_core" }, { + "BriefDescription": "Counts the number of uops executed on secondary integer ports 0,1,2,3.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xb3", + "EventName": "INT_UOPS_EXECUTED.2ND", + "SampleAfterValue": "1000003", + "UMask": "0x80", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of uops executed on a load port.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xb3", + "EventName": "INT_UOPS_EXECUTED.LD", + "PublicDescription": "Counts the number of uops executed on a load port. This event counts for integer uops even if the destination is FP/vector", + "SampleAfterValue": "1000003", + "UMask": "0x1", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of uops executed on integer port 0,1, 2, 3.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xb3", + "EventName": "INT_UOPS_EXECUTED.PRIMARY", + "SampleAfterValue": "1000003", + "UMask": "0x78", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of uops executed on a Store address port.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xb3", + "EventName": "INT_UOPS_EXECUTED.STA", + "PublicDescription": "Counts the number of uops executed on a Store address port. This event counts integer uops even if the data source is FP/vector", + "SampleAfterValue": "1000003", + "UMask": "0x2", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of uops executed on an integer store data and jump port.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xb3", + "EventName": "INT_UOPS_EXECUTED.STD_JMP", + "SampleAfterValue": "1000003", + "UMask": "0x4", + "Unit": "cpu_atom" + }, + { "BriefDescription": "Number of vector integer instructions retired of 128-bit vector-width.", "Counter": "0,1,2,3,4,5,6,7,8,9", "EventCode": "0xe7", @@ -1405,8 +1484,9 @@ "Unit": "cpu_atom" }, { - "BriefDescription": "Counts the number of machine clears that flush the pipeline and restart the machine with the use of microcode due to SMC, MEMORY_ORDERING, FP_ASSISTS, PAGE_FAULT, DISAMBIGUATION, and FPC_VIRTUAL_TRAP.", + "BriefDescription": "This event is deprecated.", "Counter": "0,1,2,3,4,5,6,7", + "Deprecated": "1", "EventCode": "0xc3", "EventName": "MACHINE_CLEARS.SLOW", "SampleAfterValue": "20003", @@ -1433,6 +1513,42 @@ "Unit": "cpu_lowpower" }, { + "BriefDescription": "Counts cycles where no execution is happening due to loads waiting for L1 cache (that is: no execution & load in flight & no load missed L1 cache)", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0x46", + "EventName": "MEMORY_STALLS.L1", + "SampleAfterValue": "1000003", + "UMask": "0x1", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts cycles where no execution is happening due to loads waiting for L2 cache (that is: no execution & load in flight & load missed L1 & no load missed L2 cache)", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0x46", + "EventName": "MEMORY_STALLS.L2", + "SampleAfterValue": "1000003", + "UMask": "0x2", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts cycles where no execution is happening due to loads waiting for L3 cache (that is: no execution & load in flight & load missed L1 & load missed L2 cache & no load missed L3 Cache)", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0x46", + "EventName": "MEMORY_STALLS.L3", + "SampleAfterValue": "1000003", + "UMask": "0x4", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts cycles where no execution is happening due to loads waiting for Memory (that is: no execution & load in flight & a load missed L3 cache)", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0x46", + "EventName": "MEMORY_STALLS.MEM", + "SampleAfterValue": "1000003", + "UMask": "0x8", + "Unit": "cpu_core" + }, + { "BriefDescription": "LFENCE instructions retired", "Counter": "0,1,2,3,4,5,6,7,8,9", "EventCode": "0xe0", @@ -1447,6 +1563,7 @@ "Counter": "0,1,2,3,4,5,6,7,8,9", "EventCode": "0xe4", "EventName": "MISC_RETIRED.LBR_INSERTS", + "PublicDescription": "LBR record is inserted Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x1", "Unit": "cpu_core" @@ -1461,6 +1578,65 @@ "Unit": "cpu_lowpower" }, { + "BriefDescription": "Cycles when Reservation Station (RS) is empty for the thread.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xa5", + "EventName": "RS.EMPTY", + "PublicDescription": "Counts cycles during which the reservation station (RS) is empty for this logical processor. This is usually caused when the front-end pipeline runs into starvation periods (e.g. branch mispredictions or i-cache misses)", + "SampleAfterValue": "1000003", + "UMask": "0x7", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts end of periods where the Reservation Station (RS) was empty.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "CounterMask": "1", + "EdgeDetect": "1", + "EventCode": "0xa5", + "EventName": "RS.EMPTY_COUNT", + "Invert": "1", + "PublicDescription": "Counts end of periods where the Reservation Station (RS) was empty. Could be useful to closely sample on front-end latency issues (see the FRONTEND_RETIRED event of designated precise events)", + "SampleAfterValue": "100003", + "UMask": "0x7", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Cycles when RS was empty and a resource allocation stall is asserted", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xa5", + "EventName": "RS.EMPTY_RESOURCE", + "SampleAfterValue": "1000003", + "UMask": "0x1", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts the number of issue slots in a UMWAIT or TPAUSE instruction where no uop issues due to the instruction putting the CPU into the C0.1 activity state.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x75", + "EventName": "SERIALIZATION.C01_MS_SCB", + "SampleAfterValue": "1000003", + "UMask": "0x4", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of issue slots in a UMWAIT or TPAUSE instruction where no uop issues due to the instruction putting the CPU into the C0.1 activity state.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x75", + "EventName": "SERIALIZATION.C01_MS_SCB", + "SampleAfterValue": "200003", + "UMask": "0x4", + "Unit": "cpu_lowpower" + }, + { + "BriefDescription": "Counts the number of issue slots where no uop could issue due to an IQ scoreboard that stalls allocation until a specified older uop retires or (in the case of jump scoreboard) executes. Commonly executed instructions with IQ scoreboards include LFENCE and MFENCE.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x75", + "EventName": "SERIALIZATION.IQ_JEU_SCB", + "SampleAfterValue": "1000003", + "UMask": "0x1", + "Unit": "cpu_atom" + }, + { "BriefDescription": "Counts the number of issue slots not consumed by the backend due to a micro-sequencer (MS) scoreboard, which stalls the front-end from issuing from the UROM until a specified older uop retires.", "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0x75", diff --git a/tools/perf/pmu-events/arch/x86/bonnell/other.json b/tools/perf/pmu-events/arch/x86/bonnell/other.json index 3a55c101fbf7..6e6f64b96834 100644 --- a/tools/perf/pmu-events/arch/x86/bonnell/other.json +++ b/tools/perf/pmu-events/arch/x86/bonnell/other.json @@ -324,14 +324,6 @@ "UMask": "0x2" }, { - "BriefDescription": "Memory cluster signals to block micro-op dispatch for any reason", - "Counter": "0,1", - "EventCode": "0x9", - "EventName": "DISPATCH_BLOCKED.ANY", - "SampleAfterValue": "200000", - "UMask": "0x20" - }, - { "BriefDescription": "Number of Enhanced Intel SpeedStep(R) Technology (EIST) transitions", "Counter": "0,1", "EventCode": "0x3A", diff --git a/tools/perf/pmu-events/arch/x86/bonnell/pipeline.json b/tools/perf/pmu-events/arch/x86/bonnell/pipeline.json index 9ff032ab11e2..48d3d053a369 100644 --- a/tools/perf/pmu-events/arch/x86/bonnell/pipeline.json +++ b/tools/perf/pmu-events/arch/x86/bonnell/pipeline.json @@ -212,6 +212,14 @@ "UMask": "0x1" }, { + "BriefDescription": "Memory cluster signals to block micro-op dispatch for any reason", + "Counter": "0,1", + "EventCode": "0x9", + "EventName": "DISPATCH_BLOCKED.ANY", + "SampleAfterValue": "200000", + "UMask": "0x20" + }, + { "BriefDescription": "Divide operations retired", "Counter": "0,1", "EventCode": "0x13", diff --git a/tools/perf/pmu-events/arch/x86/broadwell/bdw-metrics.json b/tools/perf/pmu-events/arch/x86/broadwell/bdw-metrics.json index 40970fa5566c..89750117a7f6 100644 --- a/tools/perf/pmu-events/arch/x86/broadwell/bdw-metrics.json +++ b/tools/perf/pmu-events/arch/x86/broadwell/bdw-metrics.json @@ -74,12 +74,12 @@ "MetricExpr": "LD_BLOCKS_PARTIAL.ADDRESS_ALIAS / tma_info_thread_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group", "MetricName": "tma_4k_aliasing", - "MetricThreshold": "tma_4k_aliasing > 0.2 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", - "PublicDescription": "This metric estimates how often memory load accesses were aliased by preceding stores (in program order) with a 4K address offset. False match is possible; which incur a few cycles load re-issue. However; the short re-issue duration is often hidden by the out-of-order core and HW optimizations; hence a user may safely ignore a high value of this metric unless it manages to propagate up into parent nodes of the hierarchy (e.g. to L1_Bound)", + "MetricThreshold": "tma_4k_aliasing > 0.2 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric estimates how often memory load accesses were aliased by preceding stores (in program order) with a 4K address offset. False match is possible; which incur a few cycles load re-issue. However; the short re-issue duration is often hidden by the out-of-order core and HW optimizations; hence a user may safely ignore a high value of this metric unless it manages to propagate up into parent nodes of the hierarchy (e.g. to L1_Bound).", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution ports for ALU operations", + "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution ports for ALU operations.", "MetricConstraint": "NO_GROUP_EVENTS_NMI", "MetricExpr": "(UOPS_DISPATCHED_PORT.PORT_0 + UOPS_DISPATCHED_PORT.PORT_1 + UOPS_DISPATCHED_PORT.PORT_5 + UOPS_DISPATCHED_PORT.PORT_6) / tma_info_thread_slots", "MetricGroup": "TopdownL5;tma_L5_group;tma_ports_utilized_3m_group", @@ -92,8 +92,8 @@ "MetricExpr": "66 * OTHER_ASSISTS.ANY_WB_ASSIST / tma_info_thread_slots", "MetricGroup": "BvIO;TopdownL4;tma_L4_group;tma_microcode_sequencer_group", "MetricName": "tma_assists", - "MetricThreshold": "tma_assists > 0.1 & tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1", - "PublicDescription": "This metric estimates fraction of slots the CPU retired uops delivered by the Microcode_Sequencer as a result of Assists. Assists are long sequences of uops that are required in certain corner-cases for operations that cannot be handled natively by the execution pipeline. For example; when working with very small floating point values (so-called Denormals); the FP units are not set up to perform these operations natively. Instead; a sequence of instructions to perform the computation on the Denormals is injected into the pipeline. Since these microcode sequences might be dozens of uops long; Assists can be extremely deleterious to performance and they can be avoided in many cases. Sample with: OTHER_ASSISTS.ANY_WB_ASSIST", + "MetricThreshold": "tma_assists > 0.1 & (tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1)", + "PublicDescription": "This metric estimates fraction of slots the CPU retired uops delivered by the Microcode_Sequencer as a result of Assists. Assists are long sequences of uops that are required in certain corner-cases for operations that cannot be handled natively by the execution pipeline. For example; when working with very small floating point values (so-called Denormals); the FP units are not set up to perform these operations natively. Instead; a sequence of instructions to perform the computation on the Denormals is injected into the pipeline. Since these microcode sequences might be dozens of uops long; Assists can be extremely deleterious to performance and they can be avoided in many cases. Sample with: OTHER_ASSISTS.ANY", "ScaleUnit": "100%" }, { @@ -104,7 +104,7 @@ "MetricName": "tma_backend_bound", "MetricThreshold": "tma_backend_bound > 0.2", "MetricgroupNoGroup": "TopdownL1", - "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound", + "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound.", "ScaleUnit": "100%" }, { @@ -114,7 +114,7 @@ "MetricName": "tma_bad_speculation", "MetricThreshold": "tma_bad_speculation > 0.15", "MetricgroupNoGroup": "TopdownL1", - "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example", + "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.", "ScaleUnit": "100%" }, { @@ -125,7 +125,7 @@ "MetricName": "tma_branch_mispredicts", "MetricThreshold": "tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", "MetricgroupNoGroup": "TopdownL2", - "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction. These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_mispredicts_resteers", + "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction. These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_info_bad_spec_branch_misprediction_cost, tma_mispredicts_resteers", "ScaleUnit": "100%" }, { @@ -133,8 +133,8 @@ "MetricExpr": "12 * (BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT + BACLEARS.ANY) / tma_info_thread_clks", "MetricGroup": "FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group", "MetricName": "tma_branch_resteers", - "MetricThreshold": "tma_branch_resteers > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", - "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers. Branch Resteers estimates the Frontend delay in fetching operations from corrected path; following all sorts of miss-predicted branches. For example; branchy code with lots of miss-predictions might get categorized under Branch Resteers. Note the value of this node may overlap with its siblings. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_l3_hit_latency, tma_store_latency", + "MetricThreshold": "tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers. Branch Resteers estimates the Frontend delay in fetching operations from corrected path; following all sorts of miss-predicted branches. For example; branchy code with lots of miss-predictions might get categorized under Branch Resteers. Note the value of this node may overlap with its siblings. Sample with: BR_MISP_RETIRED.ALL_BRANCHES", "ScaleUnit": "100%" }, { @@ -143,8 +143,8 @@ "MetricExpr": "max(0, tma_microcode_sequencer - tma_assists)", "MetricGroup": "TopdownL4;tma_L4_group;tma_microcode_sequencer_group", "MetricName": "tma_cisc", - "MetricThreshold": "tma_cisc > 0.1 & tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1", - "PublicDescription": "This metric estimates fraction of cycles the CPU retired uops originated from CISC (complex instruction set computer) instruction. A CISC instruction has multiple uops that are required to perform the instruction's functionality as in the case of read-modify-write as an example. Since these instructions require multiple uops they may or may not imply sub-optimal use of machine resources", + "MetricThreshold": "tma_cisc > 0.1 & (tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1)", + "PublicDescription": "This metric estimates fraction of cycles the CPU retired uops originated from CISC (complex instruction set computer) instruction. A CISC instruction has multiple uops that are required to perform the instruction's functionality as in the case of read-modify-write as an example. Since these instructions require multiple uops they may or may not imply sub-optimal use of machine resources.", "ScaleUnit": "100%" }, { @@ -152,7 +152,7 @@ "MetricExpr": "MACHINE_CLEARS.COUNT * tma_branch_resteers / (BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT + BACLEARS.ANY)", "MetricGroup": "BadSpec;MachineClears;TopdownL4;tma_L4_group;tma_branch_resteers_group;tma_issueMC", "MetricName": "tma_clears_resteers", - "MetricThreshold": "tma_clears_resteers > 0.05 & tma_branch_resteers > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricThreshold": "tma_clears_resteers > 0.05 & (tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))", "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Machine Clears. Related metrics: tma_l1_bound, tma_machine_clears, tma_microcode_sequencer, tma_ms_switches", "ScaleUnit": "100%" }, @@ -162,8 +162,8 @@ "MetricExpr": "(60 * (MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.L3_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_RETIRED.L3_MISS))) + 43 * (MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.L3_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_RETIRED.L3_MISS)))) / tma_info_thread_clks", "MetricGroup": "BvMS;DataSharing;LockCont;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group", "MetricName": "tma_contested_accesses", - "MetricThreshold": "tma_contested_accesses > 0.05 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", - "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses. Contested accesses occur when data written by one Logical Processor are read by another Logical Processor on a different Physical Core. Examples of contested accesses include synchronizations such as locks; true data sharing such as modified locked variables; and false sharing. Sample with: MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM, MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS. Related metrics: tma_data_sharing, tma_false_sharing, tma_machine_clears", + "MetricThreshold": "tma_contested_accesses > 0.05 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses. Contested accesses occur when data written by one Logical Processor are read by another Logical Processor on a different Physical Core. Examples of contested accesses include synchronizations such as locks; true data sharing such as modified locked variables; and false sharing. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM_PS;MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS_PS. Related metrics: tma_data_sharing, tma_false_sharing, tma_machine_clears, tma_remote_cache", "ScaleUnit": "100%" }, { @@ -174,7 +174,7 @@ "MetricName": "tma_core_bound", "MetricThreshold": "tma_core_bound > 0.1 & tma_backend_bound > 0.2", "MetricgroupNoGroup": "TopdownL2", - "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck. Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations)", + "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck. Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations).", "ScaleUnit": "100%" }, { @@ -183,8 +183,8 @@ "MetricExpr": "43 * (MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.L3_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_RETIRED.L3_MISS))) / tma_info_thread_clks", "MetricGroup": "BvMS;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group", "MetricName": "tma_data_sharing", - "MetricThreshold": "tma_data_sharing > 0.05 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", - "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses. Data shared by multiple Logical Processors (even just read shared) may cause increased access latency due to cache coherency. Excessive data sharing can drastically harm multithreaded performance. Sample with: MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT. Related metrics: tma_contested_accesses, tma_false_sharing, tma_machine_clears", + "MetricThreshold": "tma_data_sharing > 0.05 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses. Data shared by multiple Logical Processors (even just read shared) may cause increased access latency due to cache coherency. Excessive data sharing can drastically harm multithreaded performance. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_HIT_PS. Related metrics: tma_contested_accesses, tma_false_sharing, tma_machine_clears, tma_remote_cache", "ScaleUnit": "100%" }, { @@ -192,8 +192,8 @@ "MetricExpr": "ARITH.FPU_DIV_ACTIVE / tma_info_core_core_clks", "MetricGroup": "BvCB;TopdownL3;tma_L3_group;tma_core_bound_group", "MetricName": "tma_divider", - "MetricThreshold": "tma_divider > 0.2 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", - "PublicDescription": "This metric represents fraction of cycles where the Divider unit was active. Divide and square root instructions are performed by the Divider unit and can take considerably longer latency than integer or Floating Point addition; subtraction; or multiplication. Sample with: ARITH.FPU_DIV_ACTIVE", + "MetricThreshold": "tma_divider > 0.2 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)", + "PublicDescription": "This metric represents fraction of cycles where the Divider unit was active. Divide and square root instructions are performed by the Divider unit and can take considerably longer latency than integer or Floating Point addition; subtraction; or multiplication. Sample with: ARITH.DIVIDER_ACTIVE", "ScaleUnit": "100%" }, { @@ -202,8 +202,8 @@ "MetricExpr": "(1 - MEM_LOAD_UOPS_RETIRED.L3_HIT / (MEM_LOAD_UOPS_RETIRED.L3_HIT + 7 * MEM_LOAD_UOPS_RETIRED.L3_MISS)) * CYCLE_ACTIVITY.STALLS_L2_MISS / tma_info_thread_clks", "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_dram_bound", - "MetricThreshold": "tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", - "PublicDescription": "This metric estimates how often the CPU was stalled on accesses to external memory (DRAM) by loads. Better caching can improve the latency and increase performance. Sample with: MEM_LOAD_UOPS_RETIRED.L3_MISS", + "MetricThreshold": "tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", + "PublicDescription": "This metric estimates how often the CPU was stalled on accesses to external memory (DRAM) by loads. Better caching can improve the latency and increase performance. Sample with: MEM_LOAD_UOPS_RETIRED.L3_MISS_PS", "ScaleUnit": "100%" }, { @@ -212,7 +212,7 @@ "MetricGroup": "DSB;FetchBW;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group", "MetricName": "tma_dsb", "MetricThreshold": "tma_dsb > 0.15 & tma_fetch_bandwidth > 0.2", - "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to DSB (decoded uop cache) fetch pipeline. For example; inefficient utilization of the DSB cache structure or bank conflict when reading from it; are categorized here", + "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to DSB (decoded uop cache) fetch pipeline. For example; inefficient utilization of the DSB cache structure or bank conflict when reading from it; are categorized here.", "ScaleUnit": "100%" }, { @@ -220,26 +220,26 @@ "MetricExpr": "DSB2MITE_SWITCHES.PENALTY_CYCLES / tma_info_thread_clks", "MetricGroup": "DSBmiss;FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueFB", "MetricName": "tma_dsb_switches", - "MetricThreshold": "tma_dsb_switches > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricThreshold": "tma_dsb_switches > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines. The DSB (decoded i-cache) is a Uop Cache where the front-end directly delivers Uops (micro operations) avoiding heavy x86 decoding. The DSB pipeline has shorter latency and delivered higher bandwidth than the MITE (legacy instruction decode pipeline). Switching between the two pipelines can cause penalties hence this metric measures the exposed penalty. Related metrics: tma_fetch_bandwidth, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp", "ScaleUnit": "100%" }, { "BriefDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses", - "MetricExpr": "(8 * DTLB_LOAD_MISSES.STLB_HIT + cpu@DTLB_LOAD_MISSES.WALK_DURATION\\,cmask\\=0x1@ + 7 * DTLB_LOAD_MISSES.WALK_COMPLETED) / tma_info_thread_clks", + "MetricExpr": "(8 * DTLB_LOAD_MISSES.STLB_HIT + cpu@DTLB_LOAD_MISSES.WALK_DURATION\\,cmask\\=1@ + 7 * DTLB_LOAD_MISSES.WALK_COMPLETED) / tma_info_thread_clks", "MetricGroup": "BvMT;MemoryTLB;TopdownL4;tma_L4_group;tma_issueTLB;tma_l1_bound_group", "MetricName": "tma_dtlb_load", - "MetricThreshold": "tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", - "PublicDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses. TLBs (Translation Look-aside Buffers) are processor caches for recently used entries out of the Page Tables that are used to map virtual- to physical-addresses by the operating system. This metric approximates the potential delay of demand loads missing the first-level data TLB (assuming worst case scenario with back to back misses to different pages). This includes hitting in the second-level TLB (STLB) as well as performing a hardware page walk on an STLB miss. Sample with: MEM_UOPS_RETIRED.STLB_MISS_LOADS. Related metrics: tma_dtlb_store", + "MetricThreshold": "tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses. TLBs (Translation Look-aside Buffers) are processor caches for recently used entries out of the Page Tables that are used to map virtual- to physical-addresses by the operating system. This metric approximates the potential delay of demand loads missing the first-level data TLB (assuming worst case scenario with back to back misses to different pages). This includes hitting in the second-level TLB (STLB) as well as performing a hardware page walk on an STLB miss. Sample with: MEM_UOPS_RETIRED.STLB_MISS_LOADS_PS. Related metrics: tma_dtlb_store", "ScaleUnit": "100%" }, { "BriefDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses", - "MetricExpr": "(8 * DTLB_STORE_MISSES.STLB_HIT + cpu@DTLB_STORE_MISSES.WALK_DURATION\\,cmask\\=0x1@ + 7 * DTLB_STORE_MISSES.WALK_COMPLETED) / tma_info_thread_clks", + "MetricExpr": "(8 * DTLB_STORE_MISSES.STLB_HIT + cpu@DTLB_STORE_MISSES.WALK_DURATION\\,cmask\\=1@ + 7 * DTLB_STORE_MISSES.WALK_COMPLETED) / tma_info_thread_clks", "MetricGroup": "BvMT;MemoryTLB;TopdownL4;tma_L4_group;tma_issueTLB;tma_store_bound_group", "MetricName": "tma_dtlb_store", - "MetricThreshold": "tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", - "PublicDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses. As with ordinary data caching; focus on improving data locality and reducing working-set size to reduce DTLB overhead. Additionally; consider using profile-guided optimization (PGO) to collocate frequently-used data on the same page. Try using larger page sizes for large amounts of frequently-used data. Sample with: MEM_UOPS_RETIRED.STLB_MISS_STORES. Related metrics: tma_dtlb_load", + "MetricThreshold": "tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses. As with ordinary data caching; focus on improving data locality and reducing working-set size to reduce DTLB overhead. Additionally; consider using profile-guided optimization (PGO) to collocate frequently-used data on the same page. Try using larger page sizes for large amounts of frequently-used data. Sample with: MEM_UOPS_RETIRED.STLB_MISS_STORES_PS. Related metrics: tma_dtlb_load", "ScaleUnit": "100%" }, { @@ -247,18 +247,18 @@ "MetricExpr": "60 * OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.SNOOP_HITM / tma_info_thread_clks", "MetricGroup": "BvMS;DataSharing;LockCont;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_store_bound_group", "MetricName": "tma_false_sharing", - "MetricThreshold": "tma_false_sharing > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", - "PublicDescription": "This metric roughly estimates how often CPU was handling synchronizations due to False Sharing. False Sharing is a multithreading hiccup; where multiple Logical Processors contend on different data-elements mapped into the same cache line. Sample with: MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM, OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.SNOOP_HITM. Related metrics: tma_contested_accesses, tma_data_sharing, tma_machine_clears", + "MetricThreshold": "tma_false_sharing > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric roughly estimates how often CPU was handling synchronizations due to False Sharing. False Sharing is a multithreading hiccup; where multiple Logical Processors contend on different data-elements mapped into the same cache line. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM_PS;OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.SNOOP_HITM. Related metrics: tma_contested_accesses, tma_data_sharing, tma_machine_clears, tma_remote_cache", "ScaleUnit": "100%" }, { "BriefDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed", "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "tma_info_memory_load_miss_real_latency * cpu@L1D_PEND_MISS.FB_FULL\\,cmask\\=0x1@ / tma_info_thread_clks", + "MetricExpr": "tma_info_memory_load_miss_real_latency * cpu@L1D_PEND_MISS.FB_FULL\\,cmask\\=1@ / tma_info_thread_clks", "MetricGroup": "BvMB;MemoryBW;TopdownL4;tma_L4_group;tma_issueBW;tma_issueSL;tma_issueSmSt;tma_l1_bound_group", "MetricName": "tma_fb_full", "MetricThreshold": "tma_fb_full > 0.3", - "PublicDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed. The higher the metric value; the deeper the memory hierarchy level the misses are satisfied from (metric values >1 are valid). Often it hints on approaching bandwidth limits (to L2 cache; L3 cache or external memory). Related metrics: tma_info_system_dram_bw_use, tma_mem_bandwidth, tma_sq_full, tma_store_latency", + "PublicDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed. The higher the metric value; the deeper the memory hierarchy level the misses are satisfied from (metric values >1 are valid). Often it hints on approaching bandwidth limits (to L2 cache; L3 cache or external memory). Related metrics: tma_info_system_dram_bw_use, tma_mem_bandwidth, tma_sq_full, tma_store_latency, tma_streaming_stores", "ScaleUnit": "100%" }, { @@ -287,7 +287,7 @@ "MetricGroup": "HPC;TopdownL3;tma_L3_group;tma_light_operations_group", "MetricName": "tma_fp_arith", "MetricThreshold": "tma_fp_arith > 0.2 & tma_light_operations > 0.6", - "PublicDescription": "This metric represents overall arithmetic floating-point (FP) operations fraction the CPU has executed (retired). Note this metric's value may exceed its parent due to use of \"Uops\" CountDomain and FMA double-counting", + "PublicDescription": "This metric represents overall arithmetic floating-point (FP) operations fraction the CPU has executed (retired). Note this metric's value may exceed its parent due to use of \"Uops\" CountDomain and FMA double-counting.", "ScaleUnit": "100%" }, { @@ -295,8 +295,8 @@ "MetricExpr": "FP_ARITH_INST_RETIRED.SCALAR / UOPS_RETIRED.RETIRE_SLOTS", "MetricGroup": "Compute;Flops;TopdownL4;tma_L4_group;tma_fp_arith_group;tma_issue2P", "MetricName": "tma_fp_scalar", - "MetricThreshold": "tma_fp_scalar > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6", - "PublicDescription": "This metric approximates arithmetic floating-point (FP) scalar uops fraction the CPU has retired. May overcount due to FMA double counting. Related metrics: tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", + "MetricThreshold": "tma_fp_scalar > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6)", + "PublicDescription": "This metric approximates arithmetic floating-point (FP) scalar uops fraction the CPU has retired. May overcount due to FMA double counting. Related metrics: tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%" }, { @@ -304,8 +304,8 @@ "MetricExpr": "FP_ARITH_INST_RETIRED.VECTOR / UOPS_RETIRED.RETIRE_SLOTS", "MetricGroup": "Compute;Flops;TopdownL4;tma_L4_group;tma_fp_arith_group;tma_issue2P", "MetricName": "tma_fp_vector", - "MetricThreshold": "tma_fp_vector > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6", - "PublicDescription": "This metric approximates arithmetic floating-point (FP) vector uops fraction the CPU has retired aggregated across all vector widths. May overcount due to FMA double counting. Related metrics: tma_fp_scalar, tma_fp_vector_128b, tma_fp_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", + "MetricThreshold": "tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6)", + "PublicDescription": "This metric approximates arithmetic floating-point (FP) vector uops fraction the CPU has retired aggregated across all vector widths. May overcount due to FMA double counting. Related metrics: tma_fp_scalar, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%" }, { @@ -313,8 +313,8 @@ "MetricExpr": "(FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE) / UOPS_RETIRED.RETIRE_SLOTS", "MetricGroup": "Compute;Flops;TopdownL5;tma_L5_group;tma_fp_vector_group;tma_issue2P", "MetricName": "tma_fp_vector_128b", - "MetricThreshold": "tma_fp_vector_128b > 0.1 & tma_fp_vector > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6", - "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 128-bit wide vectors. May overcount due to FMA double counting prior to LNL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", + "MetricThreshold": "tma_fp_vector_128b > 0.1 & (tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6))", + "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 128-bit wide vectors. May overcount due to FMA double counting prior to LNL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%" }, { @@ -322,8 +322,8 @@ "MetricExpr": "(FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE) / UOPS_RETIRED.RETIRE_SLOTS", "MetricGroup": "Compute;Flops;TopdownL5;tma_L5_group;tma_fp_vector_group;tma_issue2P", "MetricName": "tma_fp_vector_256b", - "MetricThreshold": "tma_fp_vector_256b > 0.1 & tma_fp_vector > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6", - "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 256-bit wide vectors. May overcount due to FMA double counting prior to LNL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", + "MetricThreshold": "tma_fp_vector_256b > 0.1 & (tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6))", + "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 256-bit wide vectors. May overcount due to FMA double counting prior to LNL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%" }, { @@ -333,33 +333,33 @@ "MetricName": "tma_frontend_bound", "MetricThreshold": "tma_frontend_bound > 0.15", "MetricgroupNoGroup": "TopdownL1", - "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound", + "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound.", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations , instructions that require two or more uops or micro-coded sequences", + "BriefDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences", "MetricExpr": "tma_microcode_sequencer", "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_heavy_operations", "MetricThreshold": "tma_heavy_operations > 0.1", "MetricgroupNoGroup": "TopdownL2", - "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations , instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences.([ICL+] Note this may overcount due to approximation using indirect events; [ADL+])", + "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences.([ICL+] Note this may overcount due to approximation using indirect events; [ADL+])", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to instruction cache misses", + "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to instruction cache misses.", "MetricExpr": "ICACHE.IFDATA_STALL / tma_info_thread_clks", "MetricGroup": "BigFootprint;BvBC;FetchLat;IcMiss;TopdownL3;tma_L3_group;tma_fetch_latency_group", "MetricName": "tma_icache_misses", - "MetricThreshold": "tma_icache_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricThreshold": "tma_icache_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", "ScaleUnit": "100%" }, { - "BriefDescription": "Instructions per retired Mispredicts for indirect CALL or JMP branches (lower number means higher occurrence rate)", + "BriefDescription": "Instructions per retired Mispredicts for indirect CALL or JMP branches (lower number means higher occurrence rate).", "MetricExpr": "tma_info_inst_mix_instructions / (UOPS_RETIRED.RETIRE_SLOTS / UOPS_ISSUED.ANY * BR_MISP_EXEC.INDIRECT)", "MetricGroup": "Bad;BrMispredicts", "MetricName": "tma_info_bad_spec_ipmisp_indirect", - "MetricThreshold": "tma_info_bad_spec_ipmisp_indirect < 1000" + "MetricThreshold": "tma_info_bad_spec_ipmisp_indirect < 1e3" }, { "BriefDescription": "Number of Instructions per non-speculative Branch Misprediction (JEClear) (lower number means higher occurrence rate)", @@ -370,7 +370,7 @@ }, { "BriefDescription": "Core actual clocks when any Logical Processor is active on the Physical Core", - "MetricExpr": "(CPU_CLK_UNHALTED.THREAD_ANY / 2 if #SMT_on else tma_info_thread_clks)", + "MetricExpr": "(CPU_CLK_UNHALTED.THREAD / 2 * (1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK) if #core_wide < 1 else (CPU_CLK_UNHALTED.THREAD_ANY / 2 if #SMT_on else tma_info_thread_clks))", "MetricGroup": "SMT", "MetricName": "tma_info_core_core_clks" }, @@ -391,11 +391,11 @@ "MetricExpr": "(FP_ARITH_INST_RETIRED.SCALAR + FP_ARITH_INST_RETIRED.VECTOR) / (2 * tma_info_core_core_clks)", "MetricGroup": "Cor;Flops;HPC", "MetricName": "tma_info_core_fp_arith_utilization", - "PublicDescription": "Actual per-core usage of the Floating Point non-X87 execution units (regardless of precision or vector-width). Values > 1 are possible due to ([BDW+] Fused-Multiply Add (FMA) counting - common; [ADL+] use all of ADD/MUL/FMA in Scalar or 128/256-bit vectors - less common)" + "PublicDescription": "Actual per-core usage of the Floating Point non-X87 execution units (regardless of precision or vector-width). Values > 1 are possible due to ([BDW+] Fused-Multiply Add (FMA) counting - common; [ADL+] use all of ADD/MUL/FMA in Scalar or 128/256-bit vectors - less common)." }, { "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is execution) per thread (logical-processor)", - "MetricExpr": "UOPS_EXECUTED.THREAD / cpu@UOPS_EXECUTED.THREAD\\,cmask\\=0x1@", + "MetricExpr": "UOPS_EXECUTED.THREAD / cpu@UOPS_EXECUTED.THREAD\\,cmask\\=1@", "MetricGroup": "Backend;Cor;Pipeline;PortsUtil", "MetricName": "tma_info_core_ilp" }, @@ -420,7 +420,7 @@ "MetricName": "tma_info_frontend_tbpc" }, { - "BriefDescription": "Branch instructions per taken branch", + "BriefDescription": "Branch instructions per taken branch.", "MetricExpr": "BR_INST_RETIRED.ALL_BRANCHES / BR_INST_RETIRED.NEAR_TAKEN", "MetricGroup": "Branches;Fed;PGO", "MetricName": "tma_info_inst_mix_bptkbranch" @@ -438,7 +438,7 @@ "MetricGroup": "Flops;InsType", "MetricName": "tma_info_inst_mix_iparith", "MetricThreshold": "tma_info_inst_mix_iparith < 10", - "PublicDescription": "Instructions per FP Arithmetic instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting. Approximated prior to BDW" + "PublicDescription": "Instructions per FP Arithmetic instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting. Approximated prior to BDW." }, { "BriefDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number means higher occurrence rate)", @@ -446,7 +446,7 @@ "MetricGroup": "Flops;FpVector;InsType", "MetricName": "tma_info_inst_mix_iparith_avx128", "MetricThreshold": "tma_info_inst_mix_iparith_avx128 < 10", - "PublicDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting" + "PublicDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting." }, { "BriefDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means higher occurrence rate)", @@ -454,7 +454,7 @@ "MetricGroup": "Flops;FpVector;InsType", "MetricName": "tma_info_inst_mix_iparith_avx256", "MetricThreshold": "tma_info_inst_mix_iparith_avx256 < 10", - "PublicDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting" + "PublicDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting." }, { "BriefDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction (lower number means higher occurrence rate)", @@ -462,7 +462,7 @@ "MetricGroup": "Flops;FpScalar;InsType", "MetricName": "tma_info_inst_mix_iparith_scalar_dp", "MetricThreshold": "tma_info_inst_mix_iparith_scalar_dp < 10", - "PublicDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting" + "PublicDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting." }, { "BriefDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction (lower number means higher occurrence rate)", @@ -470,7 +470,7 @@ "MetricGroup": "Flops;FpScalar;InsType", "MetricName": "tma_info_inst_mix_iparith_scalar_sp", "MetricThreshold": "tma_info_inst_mix_iparith_scalar_sp < 10", - "PublicDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting" + "PublicDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting." }, { "BriefDescription": "Instructions per Branch (lower number means higher occurrence rate)", @@ -512,7 +512,7 @@ "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_TAKEN", "MetricGroup": "Branches;Fed;FetchBW;Frontend;PGO;tma_issueFB", "MetricName": "tma_info_inst_mix_iptb", - "MetricThreshold": "tma_info_inst_mix_iptb < 4 * 2 + 1", + "MetricThreshold": "tma_info_inst_mix_iptb < 9", "PublicDescription": "Instructions per taken branch. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_frontend_dsb_coverage, tma_lcp" }, { @@ -634,20 +634,20 @@ }, { "BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses", - "MetricExpr": "(cpu@ITLB_MISSES.WALK_DURATION\\,cmask\\=0x1@ + cpu@DTLB_LOAD_MISSES.WALK_DURATION\\,cmask\\=0x1@ + cpu@DTLB_STORE_MISSES.WALK_DURATION\\,cmask\\=0x1@ + 7 * (DTLB_STORE_MISSES.WALK_COMPLETED + DTLB_LOAD_MISSES.WALK_COMPLETED + ITLB_MISSES.WALK_COMPLETED)) / tma_info_core_core_clks", + "MetricExpr": "(cpu@ITLB_MISSES.WALK_DURATION\\,cmask\\=1@ + cpu@DTLB_LOAD_MISSES.WALK_DURATION\\,cmask\\=1@ + cpu@DTLB_STORE_MISSES.WALK_DURATION\\,cmask\\=1@ + 7 * (DTLB_STORE_MISSES.WALK_COMPLETED + DTLB_LOAD_MISSES.WALK_COMPLETED + ITLB_MISSES.WALK_COMPLETED)) / tma_info_core_core_clks", "MetricGroup": "Mem;MemoryTLB", "MetricName": "tma_info_memory_tlb_page_walks_utilization", "MetricThreshold": "tma_info_memory_tlb_page_walks_utilization > 0.5" }, { - "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is execution) per core", - "MetricExpr": "UOPS_EXECUTED.THREAD / (cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x1@ / 2 if #SMT_on else UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC)", + "BriefDescription": "", + "MetricExpr": "UOPS_EXECUTED.THREAD / (cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ / 2 if #SMT_on else UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC)", "MetricGroup": "Cor;Pipeline;PortsUtil;SMT", "MetricName": "tma_info_pipeline_execute" }, { - "BriefDescription": "Average number of Uops retired in cycles where at least one uop has retired", - "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / cpu@UOPS_RETIRED.RETIRE_SLOTS\\,cmask\\=0x1@", + "BriefDescription": "Average number of Uops retired in cycles where at least one uop has retired.", + "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / cpu@UOPS_RETIRED.RETIRE_SLOTS\\,cmask\\=1@", "MetricGroup": "Pipeline;Ret", "MetricName": "tma_info_pipeline_retire" }, @@ -688,14 +688,13 @@ "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.FAR_BRANCH:u", "MetricGroup": "Branches;OS", "MetricName": "tma_info_system_ipfarbranch", - "MetricThreshold": "tma_info_system_ipfarbranch < 1000000" + "MetricThreshold": "tma_info_system_ipfarbranch < 1e6" }, { "BriefDescription": "Cycles Per Instruction for the Operating System (OS) Kernel mode", "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P:k / INST_RETIRED.ANY_P:k", "MetricGroup": "OS", - "MetricName": "tma_info_system_kernel_cpi", - "ScaleUnit": "1per_instr" + "MetricName": "tma_info_system_kernel_cpi" }, { "BriefDescription": "Fraction of cycles spent in the Operating System (OS) Kernel mode", @@ -743,7 +742,7 @@ "MetricName": "tma_info_system_turbo_utilization" }, { - "BriefDescription": "Per-Logical Processor actual clocks when the Logical Processor is active", + "BriefDescription": "Per-Logical Processor actual clocks when the Logical Processor is active.", "MetricExpr": "CPU_CLK_UNHALTED.THREAD", "MetricGroup": "Pipeline", "MetricName": "tma_info_thread_clks" @@ -752,15 +751,14 @@ "BriefDescription": "Cycles Per Instruction (per Logical Processor)", "MetricExpr": "1 / tma_info_thread_ipc", "MetricGroup": "Mem;Pipeline", - "MetricName": "tma_info_thread_cpi", - "ScaleUnit": "1per_instr" + "MetricName": "tma_info_thread_cpi" }, { "BriefDescription": "The ratio of Executed- by Issued-Uops", "MetricExpr": "UOPS_EXECUTED.THREAD / UOPS_ISSUED.ANY", "MetricGroup": "Cor;Pipeline", "MetricName": "tma_info_thread_execute_per_issue", - "PublicDescription": "The ratio of Executed- by Issued-Uops. Ratio > 1 suggests high rate of uop micro-fusions. Ratio < 1 suggest high rate of \"execute\" at rename stage" + "PublicDescription": "The ratio of Executed- by Issued-Uops. Ratio > 1 suggests high rate of uop micro-fusions. Ratio < 1 suggest high rate of \"execute\" at rename stage." }, { "BriefDescription": "Instructions Per Cycle (per Logical Processor)", @@ -786,14 +784,14 @@ "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / BR_INST_RETIRED.NEAR_TAKEN", "MetricGroup": "Branches;Fed;FetchBW", "MetricName": "tma_info_thread_uptb", - "MetricThreshold": "tma_info_thread_uptb < 4 * 1.5" + "MetricThreshold": "tma_info_thread_uptb < 6" }, { "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to Instruction TLB (ITLB) misses", - "MetricExpr": "(14 * ITLB_MISSES.STLB_HIT + cpu@ITLB_MISSES.WALK_DURATION\\,cmask\\=0x1@ + 7 * ITLB_MISSES.WALK_COMPLETED) / tma_info_thread_clks", + "MetricExpr": "(14 * ITLB_MISSES.STLB_HIT + cpu@ITLB_MISSES.WALK_DURATION\\,cmask\\=1@ + 7 * ITLB_MISSES.WALK_COMPLETED) / tma_info_thread_clks", "MetricGroup": "BigFootprint;BvBC;FetchLat;MemoryTLB;TopdownL3;tma_L3_group;tma_fetch_latency_group", "MetricName": "tma_itlb_misses", - "MetricThreshold": "tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricThreshold": "tma_itlb_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Instruction TLB (ITLB) misses. Sample with: ITLB_MISSES.WALK_COMPLETED", "ScaleUnit": "100%" }, @@ -802,8 +800,8 @@ "MetricExpr": "max((CYCLE_ACTIVITY.STALLS_MEM_ANY - CYCLE_ACTIVITY.STALLS_L1D_MISS) / tma_info_thread_clks, 0)", "MetricGroup": "CacheHits;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_issueL1;tma_issueMC;tma_memory_bound_group", "MetricName": "tma_l1_bound", - "MetricThreshold": "tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", - "PublicDescription": "This metric estimates how often the CPU was stalled without loads missing the L1 Data (L1D) cache. The L1D cache typically has the shortest latency. However; in certain cases like loads blocked on older stores; a load might suffer due to high latency even though it is being satisfied by the L1D. Another example is loads who miss in the TLB. These cases are characterized by execution unit stalls; while some non-completed demand load lives in the machine without having that demand load missing the L1 cache. Sample with: MEM_LOAD_UOPS_RETIRED.L1_HIT. Related metrics: tma_clears_resteers, tma_machine_clears, tma_microcode_sequencer, tma_ms_switches, tma_ports_utilized_1", + "MetricThreshold": "tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", + "PublicDescription": "This metric estimates how often the CPU was stalled without loads missing the L1 Data (L1D) cache. The L1D cache typically has the shortest latency. However; in certain cases like loads blocked on older stores; a load might suffer due to high latency even though it is being satisfied by the L1D. Another example is loads who miss in the TLB. These cases are characterized by execution unit stalls; while some non-completed demand load lives in the machine without having that demand load missing the L1 cache. Sample with: MEM_LOAD_UOPS_RETIRED.L1_HIT_PS. Related metrics: tma_clears_resteers, tma_machine_clears, tma_microcode_sequencer, tma_ms_switches, tma_ports_utilized_1", "ScaleUnit": "100%" }, { @@ -811,8 +809,8 @@ "MetricExpr": "(CYCLE_ACTIVITY.STALLS_L1D_MISS - CYCLE_ACTIVITY.STALLS_L2_MISS) / tma_info_thread_clks", "MetricGroup": "BvML;CacheHits;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_l2_bound", - "MetricThreshold": "tma_l2_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", - "PublicDescription": "This metric estimates how often the CPU was stalled due to L2 cache accesses by loads. Avoiding cache misses (i.e. L1 misses/L2 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_UOPS_RETIRED.L2_HIT", + "MetricThreshold": "tma_l2_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", + "PublicDescription": "This metric estimates how often the CPU was stalled due to L2 cache accesses by loads. Avoiding cache misses (i.e. L1 misses/L2 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_UOPS_RETIRED.L2_HIT_PS", "ScaleUnit": "100%" }, { @@ -821,8 +819,8 @@ "MetricExpr": "MEM_LOAD_UOPS_RETIRED.L3_HIT / (MEM_LOAD_UOPS_RETIRED.L3_HIT + 7 * MEM_LOAD_UOPS_RETIRED.L3_MISS) * CYCLE_ACTIVITY.STALLS_L2_MISS / tma_info_thread_clks", "MetricGroup": "CacheHits;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_l3_bound", - "MetricThreshold": "tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", - "PublicDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core. Avoiding cache misses (i.e. L2 misses/L3 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_UOPS_RETIRED.L3_HIT", + "MetricThreshold": "tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", + "PublicDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core. Avoiding cache misses (i.e. L2 misses/L3 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_UOPS_RETIRED.L3_HIT_PS", "ScaleUnit": "100%" }, { @@ -831,8 +829,8 @@ "MetricExpr": "29 * (MEM_LOAD_UOPS_RETIRED.L3_HIT * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.L3_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_RETIRED.L3_MISS))) / tma_info_thread_clks", "MetricGroup": "BvML;MemoryLat;TopdownL4;tma_L4_group;tma_issueLat;tma_l3_bound_group", "MetricName": "tma_l3_hit_latency", - "MetricThreshold": "tma_l3_hit_latency > 0.1 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", - "PublicDescription": "This metric estimates fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited). Avoiding private cache misses (i.e. L2 misses/L3 hits) will improve the latency; reduce contention with sibling physical cores and increase performance. Note the value of this node may overlap with its siblings. Sample with: MEM_LOAD_UOPS_RETIRED.L3_HIT. Related metrics: tma_branch_resteers, tma_mem_latency, tma_store_latency", + "MetricThreshold": "tma_l3_hit_latency > 0.1 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric estimates fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited). Avoiding private cache misses (i.e. L2 misses/L3 hits) will improve the latency; reduce contention with sibling physical cores and increase performance. Note the value of this node may overlap with its siblings. Sample with: MEM_LOAD_UOPS_RETIRED.L3_HIT_PS. Related metrics: tma_mem_latency", "ScaleUnit": "100%" }, { @@ -840,18 +838,18 @@ "MetricExpr": "ILD_STALL.LCP / tma_info_thread_clks", "MetricGroup": "FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueFB", "MetricName": "tma_lcp", - "MetricThreshold": "tma_lcp > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", - "PublicDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs). Using proper compiler flags or Intel Compiler by default will certainly avoid this. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb", + "MetricThreshold": "tma_lcp > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", + "PublicDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs). Using proper compiler flags or Intel Compiler by default will certainly avoid this. #Link: Optimization Guide about LCP BKMs. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations , instructions that require no more than one uop (micro-operation)", + "BriefDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation)", "MetricExpr": "tma_retiring - tma_heavy_operations", "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_light_operations", "MetricThreshold": "tma_light_operations > 0.6", "MetricgroupNoGroup": "TopdownL2", - "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations , instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized code running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. ([ICL+] Note this may undercount due to approximation using indirect events; [ADL+] .). Sample with: INST_RETIRED.PREC_DIST", + "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized code running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. ([ICL+] Note this may undercount due to approximation using indirect events; [ADL+] .). Sample with: INST_RETIRED.PREC_DIST", "ScaleUnit": "100%" }, { @@ -870,8 +868,8 @@ "MetricExpr": "MEM_UOPS_RETIRED.LOCK_LOADS / MEM_UOPS_RETIRED.ALL_STORES * min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO) / tma_info_thread_clks", "MetricGroup": "LockCont;Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_l1_bound_group", "MetricName": "tma_lock_latency", - "MetricThreshold": "tma_lock_latency > 0.2 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", - "PublicDescription": "This metric represents fraction of cycles the CPU spent handling cache misses due to lock operations. Due to the microarchitecture handling of locks; they are classified as L1_Bound regardless of what memory source satisfied them. Sample with: MEM_UOPS_RETIRED.LOCK_LOADS. Related metrics: tma_store_latency", + "MetricThreshold": "tma_lock_latency > 0.2 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric represents fraction of cycles the CPU spent handling cache misses due to lock operations. Due to the microarchitecture handling of locks; they are classified as L1_Bound regardless of what memory source satisfied them. Sample with: MEM_UOPS_RETIRED.LOCK_LOADS_PS. Related metrics: tma_store_latency", "ScaleUnit": "100%" }, { @@ -882,15 +880,15 @@ "MetricName": "tma_machine_clears", "MetricThreshold": "tma_machine_clears > 0.1 & tma_bad_speculation > 0.15", "MetricgroupNoGroup": "TopdownL2", - "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears. These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT. Related metrics: tma_clears_resteers, tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_l1_bound, tma_microcode_sequencer, tma_ms_switches", + "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears. These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT. Related metrics: tma_clears_resteers, tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_l1_bound, tma_microcode_sequencer, tma_ms_switches, tma_remote_cache", "ScaleUnit": "100%" }, { "BriefDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory - DRAM ([SPR-HBM] and/or HBM)", - "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, cpu@OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD\\,cmask\\=0x4@) / tma_info_thread_clks", + "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, cpu@OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD\\,cmask\\=4@) / tma_info_thread_clks", "MetricGroup": "BvMB;MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueBW", "MetricName": "tma_mem_bandwidth", - "MetricThreshold": "tma_mem_bandwidth > 0.2 & tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_mem_bandwidth > 0.2 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", "PublicDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory - DRAM ([SPR-HBM] and/or HBM). The underlying heuristic assumes that a similar off-core traffic is generated by all IA cores. This metric does not aggregate non-data-read requests by this logical processor; requests from other IA Logical Processors/Physical Cores/sockets; or other non-IA devices like GPU; hence the maximum external memory bandwidth limits may or may not be approached when this metric is flagged (see Uncore counters for that). Related metrics: tma_fb_full, tma_info_system_dram_bw_use, tma_sq_full", "ScaleUnit": "100%" }, @@ -899,7 +897,7 @@ "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD) / tma_info_thread_clks - tma_mem_bandwidth", "MetricGroup": "BvML;MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueLat", "MetricName": "tma_mem_latency", - "MetricThreshold": "tma_mem_latency > 0.1 & tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_mem_latency > 0.1 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", "PublicDescription": "This metric estimates fraction of cycles where the performance was likely hurt due to latency from external memory - DRAM ([SPR-HBM] and/or HBM). This metric does not aggregate requests from other Logical Processors/Physical Cores/sockets (see Uncore counters for that). Related metrics: tma_l3_hit_latency", "ScaleUnit": "100%" }, @@ -911,7 +909,7 @@ "MetricName": "tma_memory_bound", "MetricThreshold": "tma_memory_bound > 0.2 & tma_backend_bound > 0.2", "MetricgroupNoGroup": "TopdownL2", - "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck. Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two)", + "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck. Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two).", "ScaleUnit": "100%" }, { @@ -928,8 +926,8 @@ "MetricExpr": "BR_MISP_RETIRED.ALL_BRANCHES * tma_branch_resteers / (BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT + BACLEARS.ANY)", "MetricGroup": "BadSpec;BrMispredicts;BvMP;TopdownL4;tma_L4_group;tma_branch_resteers_group;tma_issueBM", "MetricName": "tma_mispredicts_resteers", - "MetricThreshold": "tma_mispredicts_resteers > 0.05 & tma_branch_resteers > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", - "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Branch Misprediction at execution stage. Related metrics: tma_branch_mispredicts", + "MetricThreshold": "tma_mispredicts_resteers > 0.05 & (tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Branch Misprediction at execution stage. Related metrics: tma_branch_mispredicts, tma_info_bad_spec_branch_misprediction_cost", "ScaleUnit": "100%" }, { @@ -938,7 +936,7 @@ "MetricGroup": "DSBmiss;FetchBW;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group", "MetricName": "tma_mite", "MetricThreshold": "tma_mite > 0.1 & tma_fetch_bandwidth > 0.2", - "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to the MITE pipeline (the legacy decode pipeline). This pipeline is used for code that was not pre-cached in the DSB or LSD. For example; inefficiencies due to asymmetric decoders; use of long immediate or LCP can manifest as MITE fetch bandwidth bottleneck", + "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to the MITE pipeline (the legacy decode pipeline). This pipeline is used for code that was not pre-cached in the DSB or LSD. For example; inefficiencies due to asymmetric decoders; use of long immediate or LCP can manifest as MITE fetch bandwidth bottleneck.", "ScaleUnit": "100%" }, { @@ -946,8 +944,8 @@ "MetricExpr": "2 * IDQ.MS_SWITCHES / tma_info_thread_clks", "MetricGroup": "FetchLat;MicroSeq;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueMC;tma_issueMS;tma_issueMV;tma_issueSO", "MetricName": "tma_ms_switches", - "MetricThreshold": "tma_ms_switches > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", - "PublicDescription": "This metric estimates the fraction of cycles when the CPU was stalled due to switches of uop delivery to the Microcode Sequencer (MS). Commonly used instructions are optimized for delivery by the DSB (decoded i-cache) or MITE (legacy instruction decode) pipelines. Certain operations cannot be handled natively by the execution pipeline; and must be performed by microcode (small programs injected into the execution stream). Switching to the MS too often can negatively impact performance. The MS is designated to deliver long uop flows required by CISC instructions like CPUID; or uncommon conditions like Floating Point Assists when dealing with Denormals. Sample with: IDQ.MS_SWITCHES. Related metrics: tma_clears_resteers, tma_l1_bound, tma_machine_clears, tma_microcode_sequencer", + "MetricThreshold": "tma_ms_switches > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", + "PublicDescription": "This metric estimates the fraction of cycles when the CPU was stalled due to switches of uop delivery to the Microcode Sequencer (MS). Commonly used instructions are optimized for delivery by the DSB (decoded i-cache) or MITE (legacy instruction decode) pipelines. Certain operations cannot be handled natively by the execution pipeline; and must be performed by microcode (small programs injected into the execution stream). Switching to the MS too often can negatively impact performance. The MS is designated to deliver long uop flows required by CISC instructions like CPUID; or uncommon conditions like Floating Point Assists when dealing with Denormals. Sample with: IDQ.MS_SWITCHES. Related metrics: tma_clears_resteers, tma_l1_bound, tma_machine_clears, tma_microcode_sequencer, tma_mixing_vectors, tma_serializing_operation", "ScaleUnit": "100%" }, { @@ -956,7 +954,7 @@ "MetricGroup": "Compute;TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P", "MetricName": "tma_port_0", "MetricThreshold": "tma_port_0 > 0.6", - "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 0 ([SNB+] ALU; [HSW+] ALU and 2nd branch). Sample with: UOPS_DISPATCHED_PORT.PORT_0. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", + "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 0 ([SNB+] ALU; [HSW+] ALU and 2nd branch). Sample with: UOPS_DISPATCHED.PORT_0. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%" }, { @@ -965,7 +963,7 @@ "MetricGroup": "TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P", "MetricName": "tma_port_1", "MetricThreshold": "tma_port_1 > 0.6", - "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 1 (ALU). Sample with: UOPS_DISPATCHED_PORT.PORT_1. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_port_0, tma_port_5, tma_port_6, tma_ports_utilized_2", + "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 1 (ALU). Sample with: UOPS_DISPATCHED.PORT_1. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_5, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%" }, { @@ -1001,7 +999,7 @@ "MetricGroup": "TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P", "MetricName": "tma_port_5", "MetricThreshold": "tma_port_5 > 0.6", - "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 5 ([SNB+] Branches and ALU; [HSW+] ALU). Sample with: UOPS_DISPATCHED_PORT.PORT_5. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_port_0, tma_port_1, tma_port_6, tma_ports_utilized_2", + "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 5 ([SNB+] Branches and ALU; [HSW+] ALU). Sample with: UOPS_DISPATCHED.PORT_5. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%" }, { @@ -1010,7 +1008,7 @@ "MetricGroup": "TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P", "MetricName": "tma_port_6", "MetricThreshold": "tma_port_6 > 0.6", - "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 6 ([HSW+] Primary Branch and simple ALU). Sample with: UOPS_DISPATCHED_PORT.PORT_1. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_ports_utilized_2", + "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 6 ([HSW+] Primary Branch and simple ALU). Sample with: UOPS_DISPATCHED.PORT_1. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_ports_utilized_2", "ScaleUnit": "100%" }, { @@ -1028,43 +1026,43 @@ "MetricExpr": "(CYCLE_ACTIVITY.STALLS_TOTAL + UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC - (UOPS_EXECUTED.CYCLES_GE_3_UOPS_EXEC if tma_info_thread_ipc > 1.8 else UOPS_EXECUTED.CYCLES_GE_2_UOPS_EXEC) - (RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else 0) + RESOURCE_STALLS.SB - RESOURCE_STALLS.SB - CYCLE_ACTIVITY.STALLS_MEM_ANY) / tma_info_thread_clks", "MetricGroup": "PortsUtil;TopdownL3;tma_L3_group;tma_core_bound_group", "MetricName": "tma_ports_utilization", - "MetricThreshold": "tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", - "PublicDescription": "This metric estimates fraction of cycles the CPU performance was potentially limited due to Core computation issues (non divider-related). Two distinct categories can be attributed into this metric: (1) heavy data-dependency among contiguous instructions would manifest in this metric - such cases are often referred to as low Instruction Level Parallelism (ILP). (2) Contention on some hardware execution unit other than Divider. For example; when there are too many multiply operations", + "MetricThreshold": "tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)", + "PublicDescription": "This metric estimates fraction of cycles the CPU performance was potentially limited due to Core computation issues (non divider-related). Two distinct categories can be attributed into this metric: (1) heavy data-dependency among contiguous instructions would manifest in this metric - such cases are often referred to as low Instruction Level Parallelism (ILP). (2) Contention on some hardware execution unit other than Divider. For example; when there are too many multiply operations.", "ScaleUnit": "100%" }, { "BriefDescription": "This metric represents fraction of cycles CPU executed no uops on any execution port (Logical Processor cycles since ICL, Physical Core cycles otherwise)", - "MetricExpr": "(cpu@UOPS_EXECUTED.CORE\\,inv\\=0x1\\,cmask\\=0x1@ / 2 if #SMT_on else CYCLE_ACTIVITY.STALLS_TOTAL - (RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else 0)) / tma_info_core_core_clks", + "MetricExpr": "(cpu@UOPS_EXECUTED.CORE\\,inv\\,cmask\\=1@ / 2 if #SMT_on else (CYCLE_ACTIVITY.STALLS_TOTAL - (RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else 0)) / tma_info_core_core_clks)", "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group", "MetricName": "tma_ports_utilized_0", - "MetricThreshold": "tma_ports_utilized_0 > 0.2 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", - "PublicDescription": "This metric represents fraction of cycles CPU executed no uops on any execution port (Logical Processor cycles since ICL, Physical Core cycles otherwise). Long-latency instructions like divides may contribute to this metric", + "MetricThreshold": "tma_ports_utilized_0 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric represents fraction of cycles CPU executed no uops on any execution port (Logical Processor cycles since ICL, Physical Core cycles otherwise). Long-latency instructions like divides may contribute to this metric.", "ScaleUnit": "100%" }, { "BriefDescription": "This metric represents fraction of cycles where the CPU executed total of 1 uop per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise)", - "MetricExpr": "((cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x1@ - cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x2@) / 2 if #SMT_on else UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC - UOPS_EXECUTED.CYCLES_GE_2_UOPS_EXEC) / tma_info_core_core_clks", + "MetricExpr": "((cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ - cpu@UOPS_EXECUTED.CORE\\,cmask\\=2@) / 2 if #SMT_on else (UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC - UOPS_EXECUTED.CYCLES_GE_2_UOPS_EXEC) / tma_info_core_core_clks)", "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_issueL1;tma_ports_utilization_group", "MetricName": "tma_ports_utilized_1", - "MetricThreshold": "tma_ports_utilized_1 > 0.2 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_ports_utilized_1 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", "PublicDescription": "This metric represents fraction of cycles where the CPU executed total of 1 uop per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise). This can be due to heavy data-dependency among software instructions; or over oversubscribing a particular hardware resource. In some other cases with high 1_Port_Utilized and L1_Bound; this metric can point to L1 data-cache latency bottleneck that may not necessarily manifest with complete execution starvation (due to the short L1 latency e.g. walking a linked list) - looking at the assembly can be helpful. Related metrics: tma_l1_bound", "ScaleUnit": "100%" }, { "BriefDescription": "This metric represents fraction of cycles CPU executed total of 2 uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise)", - "MetricExpr": "((cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x2@ - cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x3@) / 2 if #SMT_on else UOPS_EXECUTED.CYCLES_GE_2_UOPS_EXEC - UOPS_EXECUTED.CYCLES_GE_3_UOPS_EXEC) / tma_info_core_core_clks", + "MetricExpr": "((cpu@UOPS_EXECUTED.CORE\\,cmask\\=2@ - cpu@UOPS_EXECUTED.CORE\\,cmask\\=3@) / 2 if #SMT_on else (UOPS_EXECUTED.CYCLES_GE_2_UOPS_EXEC - UOPS_EXECUTED.CYCLES_GE_3_UOPS_EXEC) / tma_info_core_core_clks)", "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_issue2P;tma_ports_utilization_group", "MetricName": "tma_ports_utilized_2", - "MetricThreshold": "tma_ports_utilized_2 > 0.15 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", - "PublicDescription": "This metric represents fraction of cycles CPU executed total of 2 uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise). Loop Vectorization -most compilers feature auto-Vectorization options today- reduces pressure on the execution ports as multiple elements are calculated with same uop. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_port_6", + "MetricThreshold": "tma_ports_utilized_2 > 0.15 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric represents fraction of cycles CPU executed total of 2 uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise). Loop Vectorization -most compilers feature auto-Vectorization options today- reduces pressure on the execution ports as multiple elements are calculated with same uop. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of cycles CPU executed total of 3 or more uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise)", - "MetricExpr": "(cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x3@ / 2 if #SMT_on else UOPS_EXECUTED.CYCLES_GE_3_UOPS_EXEC) / tma_info_core_core_clks", + "BriefDescription": "This metric represents fraction of cycles CPU executed total of 3 or more uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise).", + "MetricExpr": "(cpu@UOPS_EXECUTED.CORE\\,cmask\\=3@ / 2 if #SMT_on else UOPS_EXECUTED.CYCLES_GE_3_UOPS_EXEC) / tma_info_core_core_clks", "MetricGroup": "BvCB;PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group", "MetricName": "tma_ports_utilized_3m", - "MetricThreshold": "tma_ports_utilized_3m > 0.4 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_ports_utilized_3m > 0.4 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", "ScaleUnit": "100%" }, { @@ -1084,7 +1082,7 @@ "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group", "MetricName": "tma_split_loads", "MetricThreshold": "tma_split_loads > 0.3", - "PublicDescription": "This metric estimates fraction of cycles handling memory load split accesses - load that cross 64-byte cache line boundary. Sample with: MEM_UOPS_RETIRED.SPLIT_LOADS", + "PublicDescription": "This metric estimates fraction of cycles handling memory load split accesses - load that cross 64-byte cache line boundary. Sample with: MEM_UOPS_RETIRED.SPLIT_LOADS_PS", "ScaleUnit": "100%" }, { @@ -1092,8 +1090,8 @@ "MetricExpr": "2 * MEM_UOPS_RETIRED.SPLIT_STORES / tma_info_core_core_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_issueSpSt;tma_store_bound_group", "MetricName": "tma_split_stores", - "MetricThreshold": "tma_split_stores > 0.2 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", - "PublicDescription": "This metric represents rate of split store accesses. Consider aligning your data to the 64-byte cache line granularity. Sample with: MEM_UOPS_RETIRED.SPLIT_STORES. Related metrics: tma_port_4", + "MetricThreshold": "tma_split_stores > 0.2 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric represents rate of split store accesses. Consider aligning your data to the 64-byte cache line granularity. Sample with: MEM_UOPS_RETIRED.SPLIT_STORES_PS. Related metrics: tma_port_4", "ScaleUnit": "100%" }, { @@ -1101,7 +1099,7 @@ "MetricExpr": "(OFFCORE_REQUESTS_BUFFER.SQ_FULL / 2 if #SMT_on else OFFCORE_REQUESTS_BUFFER.SQ_FULL) / tma_info_core_core_clks", "MetricGroup": "BvMB;MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_issueBW;tma_l3_bound_group", "MetricName": "tma_sq_full", - "MetricThreshold": "tma_sq_full > 0.3 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_sq_full > 0.3 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", "PublicDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors). Related metrics: tma_fb_full, tma_info_system_dram_bw_use, tma_mem_bandwidth", "ScaleUnit": "100%" }, @@ -1110,8 +1108,8 @@ "MetricExpr": "RESOURCE_STALLS.SB / tma_info_thread_clks", "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_store_bound", - "MetricThreshold": "tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", - "PublicDescription": "This metric estimates how often CPU was stalled due to RFO store memory accesses; RFO store issue a read-for-ownership request before the write. Even though store accesses do not typically stall out-of-order CPUs; there are few cases where stores can lead to actual stalls. This metric will be flagged should RFO stores be a bottleneck. Sample with: MEM_UOPS_RETIRED.ALL_STORES", + "MetricThreshold": "tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", + "PublicDescription": "This metric estimates how often CPU was stalled due to RFO store memory accesses; RFO store issue a read-for-ownership request before the write. Even though store accesses do not typically stall out-of-order CPUs; there are few cases where stores can lead to actual stalls. This metric will be flagged should RFO stores be a bottleneck. Sample with: MEM_UOPS_RETIRED.ALL_STORES_PS", "ScaleUnit": "100%" }, { @@ -1119,8 +1117,8 @@ "MetricExpr": "13 * LD_BLOCKS.STORE_FORWARD / tma_info_thread_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group", "MetricName": "tma_store_fwd_blk", - "MetricThreshold": "tma_store_fwd_blk > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", - "PublicDescription": "This metric roughly estimates fraction of cycles when the memory subsystem had loads blocked since they could not forward data from earlier (in program order) overlapping stores. To streamline memory operations in the pipeline; a load can avoid waiting for memory if a prior in-flight store is writing the data that the load wants to read (store forwarding process). However; in some cases the load may be blocked for a significant time pending the store forward. For example; when the prior store is writing a smaller region than the load is reading", + "MetricThreshold": "tma_store_fwd_blk > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric roughly estimates fraction of cycles when the memory subsystem had loads blocked since they could not forward data from earlier (in program order) overlapping stores. To streamline memory operations in the pipeline; a load can avoid waiting for memory if a prior in-flight store is writing the data that the load wants to read (store forwarding process). However; in some cases the load may be blocked for a significant time pending the store forward. For example; when the prior store is writing a smaller region than the load is reading.", "ScaleUnit": "100%" }, { @@ -1129,8 +1127,8 @@ "MetricExpr": "(L2_RQSTS.RFO_HIT * 9 * (1 - MEM_UOPS_RETIRED.LOCK_LOADS / MEM_UOPS_RETIRED.ALL_STORES) + (1 - MEM_UOPS_RETIRED.LOCK_LOADS / MEM_UOPS_RETIRED.ALL_STORES) * min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO)) / tma_info_thread_clks", "MetricGroup": "BvML;LockCont;MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_issueSL;tma_store_bound_group", "MetricName": "tma_store_latency", - "MetricThreshold": "tma_store_latency > 0.1 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", - "PublicDescription": "This metric estimates fraction of cycles the CPU spent handling L1D store misses. Store accesses usually less impact out-of-order core performance; however; holding resources for longer time can lead into undesired implications (e.g. contention on L1D fill-buffer entries - see FB_Full). Related metrics: tma_branch_resteers, tma_fb_full, tma_l3_hit_latency, tma_lock_latency", + "MetricThreshold": "tma_store_latency > 0.1 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric estimates fraction of cycles the CPU spent handling L1D store misses. Store accesses usually less impact out-of-order core performance; however; holding resources for longer time can lead into undesired implications (e.g. contention on L1D fill-buffer entries - see FB_Full). Related metrics: tma_fb_full, tma_lock_latency", "ScaleUnit": "100%" }, { @@ -1146,7 +1144,7 @@ "MetricExpr": "tma_branch_resteers - tma_mispredicts_resteers - tma_clears_resteers", "MetricGroup": "BigFootprint;BvBC;FetchLat;TopdownL4;tma_L4_group;tma_branch_resteers_group", "MetricName": "tma_unknown_branches", - "MetricThreshold": "tma_unknown_branches > 0.05 & tma_branch_resteers > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricThreshold": "tma_unknown_branches > 0.05 & (tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))", "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to new branch address clears. These are fetched branches the Branch Prediction Unit was unable to recognize (e.g. first time the branch is fetched or hitting BTB capacity limit) hence called Unknown Branches. Sample with: BACLEARS.ANY", "ScaleUnit": "100%" }, @@ -1155,8 +1153,8 @@ "MetricExpr": "INST_RETIRED.X87 * tma_info_thread_uoppi / UOPS_RETIRED.RETIRE_SLOTS", "MetricGroup": "Compute;TopdownL4;tma_L4_group;tma_fp_arith_group", "MetricName": "tma_x87_use", - "MetricThreshold": "tma_x87_use > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6", - "PublicDescription": "This metric serves as an approximation of legacy x87 usage. It accounts for instructions beyond X87 FP arithmetic operations; hence may be used as a thermometer to avoid X87 high usage and preferably upgrade to modern ISA. See Tip under Tuning Hint", + "MetricThreshold": "tma_x87_use > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6)", + "PublicDescription": "This metric serves as an approximation of legacy x87 usage. It accounts for instructions beyond X87 FP arithmetic operations; hence may be used as a thermometer to avoid X87 high usage and preferably upgrade to modern ISA. See Tip under Tuning Hint.", "ScaleUnit": "100%" } ] diff --git a/tools/perf/pmu-events/arch/x86/broadwellde/bdwde-metrics.json b/tools/perf/pmu-events/arch/x86/broadwellde/bdwde-metrics.json index b03a5f2bcd82..81175f0f2603 100644 --- a/tools/perf/pmu-events/arch/x86/broadwellde/bdwde-metrics.json +++ b/tools/perf/pmu-events/arch/x86/broadwellde/bdwde-metrics.json @@ -74,7 +74,7 @@ "MetricExpr": "LD_BLOCKS_PARTIAL.ADDRESS_ALIAS / tma_info_thread_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group", "MetricName": "tma_4k_aliasing", - "MetricThreshold": "(tma_4k_aliasing > 0.2) & ((tma_l1_bound > 0.1) & ((tma_memory_bound > 0.2) & ((tma_backend_bound > 0.2))))", + "MetricThreshold": "tma_4k_aliasing > 0.2 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", "PublicDescription": "This metric estimates how often memory load accesses were aliased by preceding stores (in program order) with a 4K address offset. False match is possible; which incur a few cycles load re-issue. However; the short re-issue duration is often hidden by the out-of-order core and HW optimizations; hence a user may safely ignore a high value of this metric unless it manages to propagate up into parent nodes of the hierarchy (e.g. to L1_Bound).", "ScaleUnit": "100%" }, @@ -84,7 +84,7 @@ "MetricExpr": "(UOPS_DISPATCHED_PORT.PORT_0 + UOPS_DISPATCHED_PORT.PORT_1 + UOPS_DISPATCHED_PORT.PORT_5 + UOPS_DISPATCHED_PORT.PORT_6) / tma_info_thread_slots", "MetricGroup": "TopdownL5;tma_L5_group;tma_ports_utilized_3m_group", "MetricName": "tma_alu_op_utilization", - "MetricThreshold": "(tma_alu_op_utilization > 0.4)", + "MetricThreshold": "tma_alu_op_utilization > 0.4", "ScaleUnit": "100%" }, { @@ -92,7 +92,7 @@ "MetricExpr": "66 * OTHER_ASSISTS.ANY_WB_ASSIST / tma_info_thread_slots", "MetricGroup": "BvIO;TopdownL4;tma_L4_group;tma_microcode_sequencer_group", "MetricName": "tma_assists", - "MetricThreshold": "(tma_assists > 0.1) & ((tma_microcode_sequencer > 0.05) & ((tma_heavy_operations > 0.1)))", + "MetricThreshold": "tma_assists > 0.1 & (tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1)", "PublicDescription": "This metric estimates fraction of slots the CPU retired uops delivered by the Microcode_Sequencer as a result of Assists. Assists are long sequences of uops that are required in certain corner-cases for operations that cannot be handled natively by the execution pipeline. For example; when working with very small floating point values (so-called Denormals); the FP units are not set up to perform these operations natively. Instead; a sequence of instructions to perform the computation on the Denormals is injected into the pipeline. Since these microcode sequences might be dozens of uops long; Assists can be extremely deleterious to performance and they can be avoided in many cases. Sample with: ASSISTS.ANY", "ScaleUnit": "100%" }, @@ -102,7 +102,7 @@ "MetricExpr": "1 - (tma_frontend_bound + tma_bad_speculation + tma_retiring)", "MetricGroup": "BvOB;TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_backend_bound", - "MetricThreshold": "(tma_backend_bound > 0.2)", + "MetricThreshold": "tma_backend_bound > 0.2", "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound. Sample with: TOPDOWN.BACKEND_BOUND_SLOTS", "ScaleUnit": "100%" @@ -112,7 +112,7 @@ "MetricExpr": "(UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * (INT_MISC.RECOVERY_CYCLES_ANY / 2 if #SMT_on else INT_MISC.RECOVERY_CYCLES)) / tma_info_thread_slots", "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_bad_speculation", - "MetricThreshold": "(tma_bad_speculation > 0.15)", + "MetricThreshold": "tma_bad_speculation > 0.15", "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.", "ScaleUnit": "100%" @@ -123,7 +123,7 @@ "MetricExpr": "BR_MISP_RETIRED.ALL_BRANCHES / (BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT) * tma_bad_speculation", "MetricGroup": "BadSpec;BrMispredicts;BvMP;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueBM", "MetricName": "tma_branch_mispredicts", - "MetricThreshold": "(tma_branch_mispredicts > 0.1) & ((tma_bad_speculation > 0.15))", + "MetricThreshold": "tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction. These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: TOPDOWN.BR_MISPREDICT_SLOTS. Related metrics: tma_info_bad_spec_branch_misprediction_cost, tma_mispredicts_resteers", "ScaleUnit": "100%" @@ -133,7 +133,7 @@ "MetricExpr": "12 * (BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT + BACLEARS.ANY) / tma_info_thread_clks", "MetricGroup": "FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group", "MetricName": "tma_branch_resteers", - "MetricThreshold": "(tma_branch_resteers > 0.05) & ((tma_fetch_latency > 0.1) & ((tma_frontend_bound > 0.15)))", + "MetricThreshold": "tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers. Branch Resteers estimates the Frontend delay in fetching operations from corrected path; following all sorts of miss-predicted branches. For example; branchy code with lots of miss-predictions might get categorized under Branch Resteers. Note the value of this node may overlap with its siblings. Sample with: BR_MISP_RETIRED.ALL_BRANCHES", "ScaleUnit": "100%" }, @@ -143,7 +143,7 @@ "MetricExpr": "max(0, tma_microcode_sequencer - tma_assists)", "MetricGroup": "TopdownL4;tma_L4_group;tma_microcode_sequencer_group", "MetricName": "tma_cisc", - "MetricThreshold": "(tma_cisc > 0.1) & ((tma_microcode_sequencer > 0.05) & ((tma_heavy_operations > 0.1)))", + "MetricThreshold": "tma_cisc > 0.1 & (tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1)", "PublicDescription": "This metric estimates fraction of cycles the CPU retired uops originated from CISC (complex instruction set computer) instruction. A CISC instruction has multiple uops that are required to perform the instruction's functionality as in the case of read-modify-write as an example. Since these instructions require multiple uops they may or may not imply sub-optimal use of machine resources.", "ScaleUnit": "100%" }, @@ -152,7 +152,7 @@ "MetricExpr": "MACHINE_CLEARS.COUNT * tma_branch_resteers / (BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT + BACLEARS.ANY)", "MetricGroup": "BadSpec;MachineClears;TopdownL4;tma_L4_group;tma_branch_resteers_group;tma_issueMC", "MetricName": "tma_clears_resteers", - "MetricThreshold": "(tma_clears_resteers > 0.05) & ((tma_branch_resteers > 0.05) & ((tma_fetch_latency > 0.1) & ((tma_frontend_bound > 0.15))))", + "MetricThreshold": "tma_clears_resteers > 0.05 & (tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))", "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Machine Clears. Sample with: INT_MISC.CLEAR_RESTEER_CYCLES. Related metrics: tma_l1_bound, tma_machine_clears, tma_microcode_sequencer, tma_ms_switches", "ScaleUnit": "100%" }, @@ -162,7 +162,7 @@ "MetricExpr": "(60 * (MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.L3_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_RETIRED.L3_MISS))) + 43 * (MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.L3_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_RETIRED.L3_MISS)))) / tma_info_thread_clks", "MetricGroup": "BvMS;DataSharing;LockCont;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group", "MetricName": "tma_contested_accesses", - "MetricThreshold": "(tma_contested_accesses > 0.05) & ((tma_l3_bound > 0.05) & ((tma_memory_bound > 0.2) & ((tma_backend_bound > 0.2))))", + "MetricThreshold": "tma_contested_accesses > 0.05 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses. Contested accesses occur when data written by one Logical Processor are read by another Logical Processor on a different Physical Core. Examples of contested accesses include synchronizations such as locks; true data sharing such as modified locked variables; and false sharing. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD;MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS. Related metrics: tma_data_sharing, tma_false_sharing, tma_machine_clears, tma_remote_cache", "ScaleUnit": "100%" }, @@ -172,7 +172,7 @@ "MetricExpr": "tma_backend_bound - tma_memory_bound", "MetricGroup": "Backend;Compute;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_core_bound", - "MetricThreshold": "(tma_core_bound > 0.1) & ((tma_backend_bound > 0.2))", + "MetricThreshold": "tma_core_bound > 0.1 & tma_backend_bound > 0.2", "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck. Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations).", "ScaleUnit": "100%" @@ -183,7 +183,7 @@ "MetricExpr": "43 * (MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.L3_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_RETIRED.L3_MISS))) / tma_info_thread_clks", "MetricGroup": "BvMS;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group", "MetricName": "tma_data_sharing", - "MetricThreshold": "(tma_data_sharing > 0.05) & ((tma_l3_bound > 0.05) & ((tma_memory_bound > 0.2) & ((tma_backend_bound > 0.2))))", + "MetricThreshold": "tma_data_sharing > 0.05 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses. Data shared by multiple Logical Processors (even just read shared) may cause increased access latency due to cache coherency. Excessive data sharing can drastically harm multithreaded performance. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_NO_FWD. Related metrics: tma_contested_accesses, tma_false_sharing, tma_machine_clears, tma_remote_cache", "ScaleUnit": "100%" }, @@ -192,7 +192,7 @@ "MetricExpr": "ARITH.FPU_DIV_ACTIVE / tma_info_core_core_clks", "MetricGroup": "BvCB;TopdownL3;tma_L3_group;tma_core_bound_group", "MetricName": "tma_divider", - "MetricThreshold": "(tma_divider > 0.2) & ((tma_core_bound > 0.1) & ((tma_backend_bound > 0.2)))", + "MetricThreshold": "tma_divider > 0.2 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)", "PublicDescription": "This metric represents fraction of cycles where the Divider unit was active. Divide and square root instructions are performed by the Divider unit and can take considerably longer latency than integer or Floating Point addition; subtraction; or multiplication. Sample with: ARITH.DIV_ACTIVE", "ScaleUnit": "100%" }, @@ -202,7 +202,7 @@ "MetricExpr": "(1 - MEM_LOAD_UOPS_RETIRED.L3_HIT / (MEM_LOAD_UOPS_RETIRED.L3_HIT + 7 * MEM_LOAD_UOPS_RETIRED.L3_MISS)) * CYCLE_ACTIVITY.STALLS_L2_MISS / tma_info_thread_clks", "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_dram_bound", - "MetricThreshold": "(tma_dram_bound > 0.1) & ((tma_memory_bound > 0.2) & ((tma_backend_bound > 0.2)))", + "MetricThreshold": "tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", "PublicDescription": "This metric estimates how often the CPU was stalled on accesses to external memory (DRAM) by loads. Better caching can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L3_MISS", "ScaleUnit": "100%" }, @@ -211,7 +211,7 @@ "MetricExpr": "(IDQ.ALL_DSB_CYCLES_ANY_UOPS - IDQ.ALL_DSB_CYCLES_4_UOPS) / tma_info_core_core_clks / 2", "MetricGroup": "DSB;FetchBW;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group", "MetricName": "tma_dsb", - "MetricThreshold": "(tma_dsb > 0.15) & ((tma_fetch_bandwidth > 0.2))", + "MetricThreshold": "tma_dsb > 0.15 & tma_fetch_bandwidth > 0.2", "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to DSB (decoded uop cache) fetch pipeline. For example; inefficient utilization of the DSB cache structure or bank conflict when reading from it; are categorized here.", "ScaleUnit": "100%" }, @@ -220,7 +220,7 @@ "MetricExpr": "DSB2MITE_SWITCHES.PENALTY_CYCLES / tma_info_thread_clks", "MetricGroup": "DSBmiss;FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueFB", "MetricName": "tma_dsb_switches", - "MetricThreshold": "(tma_dsb_switches > 0.05) & ((tma_fetch_latency > 0.1) & ((tma_frontend_bound > 0.15)))", + "MetricThreshold": "tma_dsb_switches > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines. The DSB (decoded i-cache) is a Uop Cache where the front-end directly delivers Uops (micro operations) avoiding heavy x86 decoding. The DSB pipeline has shorter latency and delivered higher bandwidth than the MITE (legacy instruction decode pipeline). Switching between the two pipelines can cause penalties hence this metric measures the exposed penalty. Sample with: FRONTEND_RETIRED.DSB_MISS_PS. Related metrics: tma_fetch_bandwidth, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp", "ScaleUnit": "100%" }, @@ -229,7 +229,7 @@ "MetricExpr": "(8 * DTLB_LOAD_MISSES.STLB_HIT + cpu@DTLB_LOAD_MISSES.WALK_DURATION\\,cmask\\=1@ + 7 * DTLB_LOAD_MISSES.WALK_COMPLETED) / tma_info_thread_clks", "MetricGroup": "BvMT;MemoryTLB;TopdownL4;tma_L4_group;tma_issueTLB;tma_l1_bound_group", "MetricName": "tma_dtlb_load", - "MetricThreshold": "(tma_dtlb_load > 0.1) & ((tma_l1_bound > 0.1) & ((tma_memory_bound > 0.2) & ((tma_backend_bound > 0.2))))", + "MetricThreshold": "tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", "PublicDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses. TLBs (Translation Look-aside Buffers) are processor caches for recently used entries out of the Page Tables that are used to map virtual- to physical-addresses by the operating system. This metric approximates the potential delay of demand loads missing the first-level data TLB (assuming worst case scenario with back to back misses to different pages). This includes hitting in the second-level TLB (STLB) as well as performing a hardware page walk on an STLB miss. Sample with: MEM_INST_RETIRED.STLB_MISS_LOADS_PS. Related metrics: tma_dtlb_store", "ScaleUnit": "100%" }, @@ -238,7 +238,7 @@ "MetricExpr": "(8 * DTLB_STORE_MISSES.STLB_HIT + cpu@DTLB_STORE_MISSES.WALK_DURATION\\,cmask\\=1@ + 7 * DTLB_STORE_MISSES.WALK_COMPLETED) / tma_info_thread_clks", "MetricGroup": "BvMT;MemoryTLB;TopdownL4;tma_L4_group;tma_issueTLB;tma_store_bound_group", "MetricName": "tma_dtlb_store", - "MetricThreshold": "(tma_dtlb_store > 0.05) & ((tma_store_bound > 0.2) & ((tma_memory_bound > 0.2) & ((tma_backend_bound > 0.2))))", + "MetricThreshold": "tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", "PublicDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses. As with ordinary data caching; focus on improving data locality and reducing working-set size to reduce DTLB overhead. Additionally; consider using profile-guided optimization (PGO) to collocate frequently-used data on the same page. Try using larger page sizes for large amounts of frequently-used data. Sample with: MEM_INST_RETIRED.STLB_MISS_STORES_PS. Related metrics: tma_dtlb_load", "ScaleUnit": "100%" }, @@ -248,7 +248,7 @@ "MetricExpr": "tma_info_memory_load_miss_real_latency * cpu@L1D_PEND_MISS.FB_FULL\\,cmask\\=1@ / tma_info_thread_clks", "MetricGroup": "BvMB;MemoryBW;TopdownL4;tma_L4_group;tma_issueBW;tma_issueSL;tma_issueSmSt;tma_l1_bound_group", "MetricName": "tma_fb_full", - "MetricThreshold": "(tma_fb_full > 0.3)", + "MetricThreshold": "tma_fb_full > 0.3", "PublicDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed. The higher the metric value; the deeper the memory hierarchy level the misses are satisfied from (metric values >1 are valid). Often it hints on approaching bandwidth limits (to L2 cache; L3 cache or external memory). Related metrics: tma_info_system_dram_bw_use, tma_mem_bandwidth, tma_sq_full, tma_store_latency, tma_streaming_stores", "ScaleUnit": "100%" }, @@ -257,7 +257,7 @@ "MetricExpr": "tma_frontend_bound - tma_fetch_latency", "MetricGroup": "FetchBW;Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group;tma_issueFB", "MetricName": "tma_fetch_bandwidth", - "MetricThreshold": "(tma_fetch_bandwidth > 0.2)", + "MetricThreshold": "tma_fetch_bandwidth > 0.2", "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues. For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Sample with: FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1;FRONTEND_RETIRED.LATENCY_GE_1;FRONTEND_RETIRED.LATENCY_GE_2. Related metrics: tma_dsb_switches, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp", "ScaleUnit": "100%" @@ -267,7 +267,7 @@ "MetricExpr": "4 * IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE / tma_info_thread_slots", "MetricGroup": "Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group", "MetricName": "tma_fetch_latency", - "MetricThreshold": "(tma_fetch_latency > 0.1) & ((tma_frontend_bound > 0.15))", + "MetricThreshold": "tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues. For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: FRONTEND_RETIRED.LATENCY_GE_16_PS;FRONTEND_RETIRED.LATENCY_GE_8_PS", "ScaleUnit": "100%" @@ -277,7 +277,7 @@ "MetricExpr": "tma_x87_use + tma_fp_scalar + tma_fp_vector", "MetricGroup": "HPC;TopdownL3;tma_L3_group;tma_light_operations_group", "MetricName": "tma_fp_arith", - "MetricThreshold": "(tma_fp_arith > 0.2) & ((tma_light_operations > 0.6))", + "MetricThreshold": "tma_fp_arith > 0.2 & tma_light_operations > 0.6", "PublicDescription": "This metric represents overall arithmetic floating-point (FP) operations fraction the CPU has executed (retired). Note this metric's value may exceed its parent due to use of \"Uops\" CountDomain and FMA double-counting.", "ScaleUnit": "100%" }, @@ -286,7 +286,7 @@ "MetricExpr": "FP_ARITH_INST_RETIRED.SCALAR / UOPS_RETIRED.RETIRE_SLOTS", "MetricGroup": "Compute;Flops;TopdownL4;tma_L4_group;tma_fp_arith_group;tma_issue2P", "MetricName": "tma_fp_scalar", - "MetricThreshold": "(tma_fp_scalar > 0.1) & ((tma_fp_arith > 0.2) & ((tma_light_operations > 0.6)))", + "MetricThreshold": "tma_fp_scalar > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6)", "PublicDescription": "This metric approximates arithmetic floating-point (FP) scalar uops fraction the CPU has retired. May overcount due to FMA double counting. Related metrics: tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%" }, @@ -295,7 +295,7 @@ "MetricExpr": "FP_ARITH_INST_RETIRED.VECTOR / UOPS_RETIRED.RETIRE_SLOTS", "MetricGroup": "Compute;Flops;TopdownL4;tma_L4_group;tma_fp_arith_group;tma_issue2P", "MetricName": "tma_fp_vector", - "MetricThreshold": "(tma_fp_vector > 0.1) & ((tma_fp_arith > 0.2) & ((tma_light_operations > 0.6)))", + "MetricThreshold": "tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6)", "PublicDescription": "This metric approximates arithmetic floating-point (FP) vector uops fraction the CPU has retired aggregated across all vector widths. May overcount due to FMA double counting. Related metrics: tma_fp_scalar, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%" }, @@ -304,7 +304,7 @@ "MetricExpr": "(FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE) / UOPS_RETIRED.RETIRE_SLOTS", "MetricGroup": "Compute;Flops;TopdownL5;tma_L5_group;tma_fp_vector_group;tma_issue2P", "MetricName": "tma_fp_vector_128b", - "MetricThreshold": "(tma_fp_vector_128b > 0.1) & ((tma_fp_vector > 0.1) & ((tma_fp_arith > 0.2) & ((tma_light_operations > 0.6))))", + "MetricThreshold": "tma_fp_vector_128b > 0.1 & (tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6))", "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 128-bit wide vectors. May overcount due to FMA double counting prior to LNL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%" }, @@ -313,7 +313,7 @@ "MetricExpr": "(FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE) / UOPS_RETIRED.RETIRE_SLOTS", "MetricGroup": "Compute;Flops;TopdownL5;tma_L5_group;tma_fp_vector_group;tma_issue2P", "MetricName": "tma_fp_vector_256b", - "MetricThreshold": "(tma_fp_vector_256b > 0.1) & ((tma_fp_vector > 0.1) & ((tma_fp_arith > 0.2) & ((tma_light_operations > 0.6))))", + "MetricThreshold": "tma_fp_vector_256b > 0.1 & (tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6))", "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 256-bit wide vectors. May overcount due to FMA double counting prior to LNL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%" }, @@ -322,7 +322,7 @@ "MetricExpr": "IDQ_UOPS_NOT_DELIVERED.CORE / tma_info_thread_slots", "MetricGroup": "BvFB;BvIO;PGO;TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_frontend_bound", - "MetricThreshold": "(tma_frontend_bound > 0.15)", + "MetricThreshold": "tma_frontend_bound > 0.15", "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound. Sample with: FRONTEND_RETIRED.LATENCY_GE_4_PS", "ScaleUnit": "100%" @@ -332,7 +332,7 @@ "MetricExpr": "tma_microcode_sequencer", "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_heavy_operations", - "MetricThreshold": "(tma_heavy_operations > 0.1)", + "MetricThreshold": "tma_heavy_operations > 0.1", "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences.([ICL+] Note this may overcount due to approximation using indirect events; [ADL+]). Sample with: UOPS_RETIRED.HEAVY", "ScaleUnit": "100%" @@ -342,7 +342,7 @@ "MetricExpr": "ICACHE.IFDATA_STALL / tma_info_thread_clks", "MetricGroup": "BigFootprint;BvBC;FetchLat;IcMiss;TopdownL3;tma_L3_group;tma_fetch_latency_group", "MetricName": "tma_icache_misses", - "MetricThreshold": "(tma_icache_misses > 0.05) & ((tma_fetch_latency > 0.1) & ((tma_frontend_bound > 0.15)))", + "MetricThreshold": "tma_icache_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to instruction cache misses. Sample with: FRONTEND_RETIRED.L2_MISS_PS;FRONTEND_RETIRED.L1I_MISS_PS", "ScaleUnit": "100%" }, @@ -351,14 +351,14 @@ "MetricExpr": "tma_info_inst_mix_instructions / (UOPS_RETIRED.RETIRE_SLOTS / UOPS_ISSUED.ANY * BR_MISP_EXEC.INDIRECT)", "MetricGroup": "Bad;BrMispredicts", "MetricName": "tma_info_bad_spec_ipmisp_indirect", - "MetricThreshold": "(tma_info_bad_spec_ipmisp_indirect < 1000)" + "MetricThreshold": "tma_info_bad_spec_ipmisp_indirect < 1e3" }, { "BriefDescription": "Number of Instructions per non-speculative Branch Misprediction (JEClear) (lower number means higher occurrence rate)", "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.ALL_BRANCHES", "MetricGroup": "Bad;BadSpec;BrMispredicts", "MetricName": "tma_info_bad_spec_ipmispredict", - "MetricThreshold": "(tma_info_bad_spec_ipmispredict < 200)" + "MetricThreshold": "tma_info_bad_spec_ipmispredict < 200" }, { "BriefDescription": "Core actual clocks when any Logical Processor is active on the Physical Core", @@ -396,7 +396,7 @@ "MetricExpr": "IDQ.DSB_UOPS / (IDQ.DSB_UOPS + LSD.UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS)", "MetricGroup": "DSB;Fed;FetchBW;tma_issueFB", "MetricName": "tma_info_frontend_dsb_coverage", - "MetricThreshold": "(tma_info_frontend_dsb_coverage < 0.7) & ((tma_info_thread_ipc / 4) > 0.35)", + "MetricThreshold": "tma_info_frontend_dsb_coverage < 0.7 & tma_info_thread_ipc / 4 > 0.35", "PublicDescription": "Fraction of Uops delivered by the DSB (aka Decoded ICache; or Uop Cache). Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_inst_mix_iptb, tma_lcp" }, { @@ -429,7 +429,7 @@ "MetricExpr": "INST_RETIRED.ANY / (FP_ARITH_INST_RETIRED.SCALAR + FP_ARITH_INST_RETIRED.VECTOR)", "MetricGroup": "Flops;InsType", "MetricName": "tma_info_inst_mix_iparith", - "MetricThreshold": "(tma_info_inst_mix_iparith < 10)", + "MetricThreshold": "tma_info_inst_mix_iparith < 10", "PublicDescription": "Instructions per FP Arithmetic instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting. Approximated prior to BDW." }, { @@ -437,7 +437,7 @@ "MetricExpr": "INST_RETIRED.ANY / (FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE)", "MetricGroup": "Flops;FpVector;InsType", "MetricName": "tma_info_inst_mix_iparith_avx128", - "MetricThreshold": "(tma_info_inst_mix_iparith_avx128 < 10)", + "MetricThreshold": "tma_info_inst_mix_iparith_avx128 < 10", "PublicDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting." }, { @@ -445,7 +445,7 @@ "MetricExpr": "INST_RETIRED.ANY / (FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE)", "MetricGroup": "Flops;FpVector;InsType", "MetricName": "tma_info_inst_mix_iparith_avx256", - "MetricThreshold": "(tma_info_inst_mix_iparith_avx256 < 10)", + "MetricThreshold": "tma_info_inst_mix_iparith_avx256 < 10", "PublicDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting." }, { @@ -453,7 +453,7 @@ "MetricExpr": "INST_RETIRED.ANY / FP_ARITH_INST_RETIRED.SCALAR_DOUBLE", "MetricGroup": "Flops;FpScalar;InsType", "MetricName": "tma_info_inst_mix_iparith_scalar_dp", - "MetricThreshold": "(tma_info_inst_mix_iparith_scalar_dp < 10)", + "MetricThreshold": "tma_info_inst_mix_iparith_scalar_dp < 10", "PublicDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting." }, { @@ -461,7 +461,7 @@ "MetricExpr": "INST_RETIRED.ANY / FP_ARITH_INST_RETIRED.SCALAR_SINGLE", "MetricGroup": "Flops;FpScalar;InsType", "MetricName": "tma_info_inst_mix_iparith_scalar_sp", - "MetricThreshold": "(tma_info_inst_mix_iparith_scalar_sp < 10)", + "MetricThreshold": "tma_info_inst_mix_iparith_scalar_sp < 10", "PublicDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting." }, { @@ -469,42 +469,42 @@ "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.ALL_BRANCHES", "MetricGroup": "Branches;Fed;InsType", "MetricName": "tma_info_inst_mix_ipbranch", - "MetricThreshold": "(tma_info_inst_mix_ipbranch < 8)" + "MetricThreshold": "tma_info_inst_mix_ipbranch < 8" }, { "BriefDescription": "Instructions per (near) call (lower number means higher occurrence rate)", "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_CALL", "MetricGroup": "Branches;Fed;PGO", "MetricName": "tma_info_inst_mix_ipcall", - "MetricThreshold": "(tma_info_inst_mix_ipcall < 200)" + "MetricThreshold": "tma_info_inst_mix_ipcall < 200" }, { "BriefDescription": "Instructions per Floating Point (FP) Operation (lower number means higher occurrence rate)", "MetricExpr": "INST_RETIRED.ANY / (FP_ARITH_INST_RETIRED.SCALAR + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * FP_ARITH_INST_RETIRED.4_FLOPS + 8 * FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE)", "MetricGroup": "Flops;InsType", "MetricName": "tma_info_inst_mix_ipflop", - "MetricThreshold": "(tma_info_inst_mix_ipflop < 10)" + "MetricThreshold": "tma_info_inst_mix_ipflop < 10" }, { "BriefDescription": "Instructions per Load (lower number means higher occurrence rate)", "MetricExpr": "INST_RETIRED.ANY / MEM_UOPS_RETIRED.ALL_LOADS", "MetricGroup": "InsType", "MetricName": "tma_info_inst_mix_ipload", - "MetricThreshold": "(tma_info_inst_mix_ipload < 3)" + "MetricThreshold": "tma_info_inst_mix_ipload < 3" }, { "BriefDescription": "Instructions per Store (lower number means higher occurrence rate)", "MetricExpr": "INST_RETIRED.ANY / MEM_UOPS_RETIRED.ALL_STORES", "MetricGroup": "InsType", "MetricName": "tma_info_inst_mix_ipstore", - "MetricThreshold": "(tma_info_inst_mix_ipstore < 8)" + "MetricThreshold": "tma_info_inst_mix_ipstore < 8" }, { "BriefDescription": "Instructions per taken branch", "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_TAKEN", "MetricGroup": "Branches;Fed;FetchBW;Frontend;PGO;tma_issueFB", "MetricName": "tma_info_inst_mix_iptb", - "MetricThreshold": "(tma_info_inst_mix_iptb < 4 * 2 + 1)", + "MetricThreshold": "tma_info_inst_mix_iptb < 9", "PublicDescription": "Instructions per taken branch. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_frontend_dsb_coverage, tma_lcp" }, { @@ -629,7 +629,7 @@ "MetricExpr": "(cpu@ITLB_MISSES.WALK_DURATION\\,cmask\\=1@ + cpu@DTLB_LOAD_MISSES.WALK_DURATION\\,cmask\\=1@ + cpu@DTLB_STORE_MISSES.WALK_DURATION\\,cmask\\=1@ + 7 * (DTLB_STORE_MISSES.WALK_COMPLETED + DTLB_LOAD_MISSES.WALK_COMPLETED + ITLB_MISSES.WALK_COMPLETED)) / tma_info_core_core_clks", "MetricGroup": "Mem;MemoryTLB", "MetricName": "tma_info_memory_tlb_page_walks_utilization", - "MetricThreshold": "(tma_info_memory_tlb_page_walks_utilization > 0.5)" + "MetricThreshold": "tma_info_memory_tlb_page_walks_utilization > 0.5" }, { "BriefDescription": "", @@ -680,7 +680,7 @@ "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.FAR_BRANCH:u", "MetricGroup": "Branches;OS", "MetricName": "tma_info_system_ipfarbranch", - "MetricThreshold": "(tma_info_system_ipfarbranch < 1000000)" + "MetricThreshold": "tma_info_system_ipfarbranch < 1e6" }, { "BriefDescription": "Cycles Per Instruction for the Operating System (OS) Kernel mode", @@ -693,14 +693,14 @@ "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P:k / CPU_CLK_UNHALTED.THREAD", "MetricGroup": "OS", "MetricName": "tma_info_system_kernel_utilization", - "MetricThreshold": "(tma_info_system_kernel_utilization > 0.05)" + "MetricThreshold": "tma_info_system_kernel_utilization > 0.05" }, { "BriefDescription": "PerfMon Event Multiplexing accuracy indicator", "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P / CPU_CLK_UNHALTED.THREAD", "MetricGroup": "Summary", "MetricName": "tma_info_system_mux", - "MetricThreshold": "((tma_info_system_mux > 1.1)|(tma_info_system_mux < 0.9))" + "MetricThreshold": "tma_info_system_mux > 1.1 | tma_info_system_mux < 0.9" }, { "BriefDescription": "Total package Power in Watts", @@ -725,7 +725,7 @@ "MetricExpr": "duration_time", "MetricGroup": "Summary", "MetricName": "tma_info_system_time", - "MetricThreshold": "(tma_info_system_time < 1)" + "MetricThreshold": "tma_info_system_time < 1" }, { "BriefDescription": "Average Frequency Utilization relative nominal frequency", @@ -769,21 +769,21 @@ "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY", "MetricGroup": "Pipeline;Ret;Retire", "MetricName": "tma_info_thread_uoppi", - "MetricThreshold": "(tma_info_thread_uoppi > 1.05)" + "MetricThreshold": "tma_info_thread_uoppi > 1.05" }, { "BriefDescription": "Uops per taken branch", "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / BR_INST_RETIRED.NEAR_TAKEN", "MetricGroup": "Branches;Fed;FetchBW", "MetricName": "tma_info_thread_uptb", - "MetricThreshold": "(tma_info_thread_uptb < 4 * 1.5)" + "MetricThreshold": "tma_info_thread_uptb < 6" }, { "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to Instruction TLB (ITLB) misses", "MetricExpr": "(14 * ITLB_MISSES.STLB_HIT + cpu@ITLB_MISSES.WALK_DURATION\\,cmask\\=1@ + 7 * ITLB_MISSES.WALK_COMPLETED) / tma_info_thread_clks", "MetricGroup": "BigFootprint;BvBC;FetchLat;MemoryTLB;TopdownL3;tma_L3_group;tma_fetch_latency_group", "MetricName": "tma_itlb_misses", - "MetricThreshold": "(tma_itlb_misses > 0.05) & ((tma_fetch_latency > 0.1) & ((tma_frontend_bound > 0.15)))", + "MetricThreshold": "tma_itlb_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Instruction TLB (ITLB) misses. Sample with: FRONTEND_RETIRED.STLB_MISS_PS;FRONTEND_RETIRED.ITLB_MISS_PS", "ScaleUnit": "100%" }, @@ -792,7 +792,7 @@ "MetricExpr": "max((CYCLE_ACTIVITY.STALLS_MEM_ANY - CYCLE_ACTIVITY.STALLS_L1D_MISS) / tma_info_thread_clks, 0)", "MetricGroup": "CacheHits;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_issueL1;tma_issueMC;tma_memory_bound_group", "MetricName": "tma_l1_bound", - "MetricThreshold": "(tma_l1_bound > 0.1) & ((tma_memory_bound > 0.2) & ((tma_backend_bound > 0.2)))", + "MetricThreshold": "tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", "PublicDescription": "This metric estimates how often the CPU was stalled without loads missing the L1 Data (L1D) cache. The L1D cache typically has the shortest latency. However; in certain cases like loads blocked on older stores; a load might suffer due to high latency even though it is being satisfied by the L1D. Another example is loads who miss in the TLB. These cases are characterized by execution unit stalls; while some non-completed demand load lives in the machine without having that demand load missing the L1 cache. Sample with: MEM_LOAD_RETIRED.L1_HIT. Related metrics: tma_clears_resteers, tma_machine_clears, tma_microcode_sequencer, tma_ms_switches, tma_ports_utilized_1", "ScaleUnit": "100%" }, @@ -801,7 +801,7 @@ "MetricExpr": "(CYCLE_ACTIVITY.STALLS_L1D_MISS - CYCLE_ACTIVITY.STALLS_L2_MISS) / tma_info_thread_clks", "MetricGroup": "BvML;CacheHits;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_l2_bound", - "MetricThreshold": "(tma_l2_bound > 0.05) & ((tma_memory_bound > 0.2) & ((tma_backend_bound > 0.2)))", + "MetricThreshold": "tma_l2_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", "PublicDescription": "This metric estimates how often the CPU was stalled due to L2 cache accesses by loads. Avoiding cache misses (i.e. L1 misses/L2 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L2_HIT", "ScaleUnit": "100%" }, @@ -811,7 +811,7 @@ "MetricExpr": "MEM_LOAD_UOPS_RETIRED.L3_HIT / (MEM_LOAD_UOPS_RETIRED.L3_HIT + 7 * MEM_LOAD_UOPS_RETIRED.L3_MISS) * CYCLE_ACTIVITY.STALLS_L2_MISS / tma_info_thread_clks", "MetricGroup": "CacheHits;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_l3_bound", - "MetricThreshold": "(tma_l3_bound > 0.05) & ((tma_memory_bound > 0.2) & ((tma_backend_bound > 0.2)))", + "MetricThreshold": "tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", "PublicDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core. Avoiding cache misses (i.e. L2 misses/L3 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L3_HIT_PS", "ScaleUnit": "100%" }, @@ -821,7 +821,7 @@ "MetricExpr": "29 * (MEM_LOAD_UOPS_RETIRED.L3_HIT * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.L3_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_RETIRED.L3_MISS))) / tma_info_thread_clks", "MetricGroup": "BvML;MemoryLat;TopdownL4;tma_L4_group;tma_issueLat;tma_l3_bound_group", "MetricName": "tma_l3_hit_latency", - "MetricThreshold": "(tma_l3_hit_latency > 0.1) & ((tma_l3_bound > 0.05) & ((tma_memory_bound > 0.2) & ((tma_backend_bound > 0.2))))", + "MetricThreshold": "tma_l3_hit_latency > 0.1 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", "PublicDescription": "This metric estimates fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited). Avoiding private cache misses (i.e. L2 misses/L3 hits) will improve the latency; reduce contention with sibling physical cores and increase performance. Note the value of this node may overlap with its siblings. Sample with: MEM_LOAD_RETIRED.L3_HIT_PS. Related metrics: tma_mem_latency", "ScaleUnit": "100%" }, @@ -830,7 +830,7 @@ "MetricExpr": "ILD_STALL.LCP / tma_info_thread_clks", "MetricGroup": "FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueFB", "MetricName": "tma_lcp", - "MetricThreshold": "(tma_lcp > 0.05) & ((tma_fetch_latency > 0.1) & ((tma_frontend_bound > 0.15)))", + "MetricThreshold": "tma_lcp > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", "PublicDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs). Using proper compiler flags or Intel Compiler by default will certainly avoid this. #Link: Optimization Guide about LCP BKMs. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb", "ScaleUnit": "100%" }, @@ -839,7 +839,7 @@ "MetricExpr": "tma_retiring - tma_heavy_operations", "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_light_operations", - "MetricThreshold": "(tma_light_operations > 0.6)", + "MetricThreshold": "tma_light_operations > 0.6", "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized code running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. ([ICL+] Note this may undercount due to approximation using indirect events; [ADL+] .). Sample with: INST_RETIRED.PREC_DIST", "ScaleUnit": "100%" @@ -850,7 +850,7 @@ "MetricExpr": "(UOPS_DISPATCHED_PORT.PORT_2 + UOPS_DISPATCHED_PORT.PORT_3 + UOPS_DISPATCHED_PORT.PORT_7 - UOPS_DISPATCHED_PORT.PORT_4) / (2 * tma_info_core_core_clks)", "MetricGroup": "TopdownL5;tma_L5_group;tma_ports_utilized_3m_group", "MetricName": "tma_load_op_utilization", - "MetricThreshold": "(tma_load_op_utilization > 0.6)", + "MetricThreshold": "tma_load_op_utilization > 0.6", "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port for Load operations. Sample with: UOPS_DISPATCHED.PORT_2_3_10", "ScaleUnit": "100%" }, @@ -860,7 +860,7 @@ "MetricExpr": "MEM_UOPS_RETIRED.LOCK_LOADS / MEM_UOPS_RETIRED.ALL_STORES * min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO) / tma_info_thread_clks", "MetricGroup": "LockCont;Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_l1_bound_group", "MetricName": "tma_lock_latency", - "MetricThreshold": "(tma_lock_latency > 0.2) & ((tma_l1_bound > 0.1) & ((tma_memory_bound > 0.2) & ((tma_backend_bound > 0.2))))", + "MetricThreshold": "tma_lock_latency > 0.2 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", "PublicDescription": "This metric represents fraction of cycles the CPU spent handling cache misses due to lock operations. Due to the microarchitecture handling of locks; they are classified as L1_Bound regardless of what memory source satisfied them. Sample with: MEM_INST_RETIRED.LOCK_LOADS. Related metrics: tma_store_latency", "ScaleUnit": "100%" }, @@ -870,7 +870,7 @@ "MetricExpr": "tma_bad_speculation - tma_branch_mispredicts", "MetricGroup": "BadSpec;BvMS;MachineClears;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueMC;tma_issueSyncxn", "MetricName": "tma_machine_clears", - "MetricThreshold": "(tma_machine_clears > 0.1) & ((tma_bad_speculation > 0.15))", + "MetricThreshold": "tma_machine_clears > 0.1 & tma_bad_speculation > 0.15", "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears. These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT. Related metrics: tma_clears_resteers, tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_l1_bound, tma_microcode_sequencer, tma_ms_switches, tma_remote_cache", "ScaleUnit": "100%" @@ -880,7 +880,7 @@ "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, cpu@OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD\\,cmask\\=4@) / tma_info_thread_clks", "MetricGroup": "BvMB;MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueBW", "MetricName": "tma_mem_bandwidth", - "MetricThreshold": "(tma_mem_bandwidth > 0.2) & ((tma_dram_bound > 0.1) & ((tma_memory_bound > 0.2) & ((tma_backend_bound > 0.2))))", + "MetricThreshold": "tma_mem_bandwidth > 0.2 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", "PublicDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory - DRAM ([SPR-HBM] and/or HBM). The underlying heuristic assumes that a similar off-core traffic is generated by all IA cores. This metric does not aggregate non-data-read requests by this logical processor; requests from other IA Logical Processors/Physical Cores/sockets; or other non-IA devices like GPU; hence the maximum external memory bandwidth limits may or may not be approached when this metric is flagged (see Uncore counters for that). Related metrics: tma_fb_full, tma_info_system_dram_bw_use, tma_sq_full", "ScaleUnit": "100%" }, @@ -889,7 +889,7 @@ "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD) / tma_info_thread_clks - tma_mem_bandwidth", "MetricGroup": "BvML;MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueLat", "MetricName": "tma_mem_latency", - "MetricThreshold": "(tma_mem_latency > 0.1) & ((tma_dram_bound > 0.1) & ((tma_memory_bound > 0.2) & ((tma_backend_bound > 0.2))))", + "MetricThreshold": "tma_mem_latency > 0.1 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", "PublicDescription": "This metric estimates fraction of cycles where the performance was likely hurt due to latency from external memory - DRAM ([SPR-HBM] and/or HBM). This metric does not aggregate requests from other Logical Processors/Physical Cores/sockets (see Uncore counters for that). Related metrics: tma_l3_hit_latency", "ScaleUnit": "100%" }, @@ -899,7 +899,7 @@ "MetricExpr": "(CYCLE_ACTIVITY.STALLS_MEM_ANY + RESOURCE_STALLS.SB) / (CYCLE_ACTIVITY.STALLS_TOTAL + UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC - (UOPS_EXECUTED.CYCLES_GE_3_UOPS_EXEC if tma_info_thread_ipc > 1.8 else UOPS_EXECUTED.CYCLES_GE_2_UOPS_EXEC) - (RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else 0) + RESOURCE_STALLS.SB) * tma_backend_bound", "MetricGroup": "Backend;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_memory_bound", - "MetricThreshold": "(tma_memory_bound > 0.2) & ((tma_backend_bound > 0.2))", + "MetricThreshold": "tma_memory_bound > 0.2 & tma_backend_bound > 0.2", "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck. Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two).", "ScaleUnit": "100%" @@ -909,7 +909,7 @@ "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / UOPS_ISSUED.ANY * IDQ.MS_UOPS / tma_info_thread_slots", "MetricGroup": "MicroSeq;TopdownL3;tma_L3_group;tma_heavy_operations_group;tma_issueMC;tma_issueMS", "MetricName": "tma_microcode_sequencer", - "MetricThreshold": "(tma_microcode_sequencer > 0.05) & ((tma_heavy_operations > 0.1))", + "MetricThreshold": "tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1", "PublicDescription": "This metric represents fraction of slots the CPU was retiring uops fetched by the Microcode Sequencer (MS) unit. The MS is used for CISC instructions not supported by the default decoders (like repeat move strings; or CPUID); or by microcode assists used to address some operation modes (like in Floating Point assists). These cases can often be avoided. Sample with: UOPS_RETIRED.MS. Related metrics: tma_clears_resteers, tma_l1_bound, tma_machine_clears, tma_ms_switches", "ScaleUnit": "100%" }, @@ -918,7 +918,7 @@ "MetricExpr": "BR_MISP_RETIRED.ALL_BRANCHES * tma_branch_resteers / (BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT + BACLEARS.ANY)", "MetricGroup": "BadSpec;BrMispredicts;BvMP;TopdownL4;tma_L4_group;tma_branch_resteers_group;tma_issueBM", "MetricName": "tma_mispredicts_resteers", - "MetricThreshold": "(tma_mispredicts_resteers > 0.05) & ((tma_branch_resteers > 0.05) & ((tma_fetch_latency > 0.1) & ((tma_frontend_bound > 0.15))))", + "MetricThreshold": "tma_mispredicts_resteers > 0.05 & (tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))", "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Branch Misprediction at execution stage. Sample with: INT_MISC.CLEAR_RESTEER_CYCLES. Related metrics: tma_branch_mispredicts, tma_info_bad_spec_branch_misprediction_cost", "ScaleUnit": "100%" }, @@ -927,7 +927,7 @@ "MetricExpr": "(IDQ.ALL_MITE_CYCLES_ANY_UOPS - IDQ.ALL_MITE_CYCLES_4_UOPS) / tma_info_core_core_clks / 2", "MetricGroup": "DSBmiss;FetchBW;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group", "MetricName": "tma_mite", - "MetricThreshold": "(tma_mite > 0.1) & ((tma_fetch_bandwidth > 0.2))", + "MetricThreshold": "tma_mite > 0.1 & tma_fetch_bandwidth > 0.2", "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to the MITE pipeline (the legacy decode pipeline). This pipeline is used for code that was not pre-cached in the DSB or LSD. For example; inefficiencies due to asymmetric decoders; use of long immediate or LCP can manifest as MITE fetch bandwidth bottleneck. Sample with: FRONTEND_RETIRED.ANY_DSB_MISS", "ScaleUnit": "100%" }, @@ -936,7 +936,7 @@ "MetricExpr": "2 * IDQ.MS_SWITCHES / tma_info_thread_clks", "MetricGroup": "FetchLat;MicroSeq;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueMC;tma_issueMS;tma_issueMV;tma_issueSO", "MetricName": "tma_ms_switches", - "MetricThreshold": "(tma_ms_switches > 0.05) & ((tma_fetch_latency > 0.1) & ((tma_frontend_bound > 0.15)))", + "MetricThreshold": "tma_ms_switches > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", "PublicDescription": "This metric estimates the fraction of cycles when the CPU was stalled due to switches of uop delivery to the Microcode Sequencer (MS). Commonly used instructions are optimized for delivery by the DSB (decoded i-cache) or MITE (legacy instruction decode) pipelines. Certain operations cannot be handled natively by the execution pipeline; and must be performed by microcode (small programs injected into the execution stream). Switching to the MS too often can negatively impact performance. The MS is designated to deliver long uop flows required by CISC instructions like CPUID; or uncommon conditions like Floating Point Assists when dealing with Denormals. Sample with: IDQ.MS_SWITCHES. Related metrics: tma_clears_resteers, tma_l1_bound, tma_machine_clears, tma_microcode_sequencer, tma_mixing_vectors, tma_serializing_operation", "ScaleUnit": "100%" }, @@ -945,7 +945,7 @@ "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_0 / tma_info_core_core_clks", "MetricGroup": "Compute;TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P", "MetricName": "tma_port_0", - "MetricThreshold": "(tma_port_0 > 0.6)", + "MetricThreshold": "tma_port_0 > 0.6", "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 0 ([SNB+] ALU; [HSW+] ALU and 2nd branch). Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%" }, @@ -954,7 +954,7 @@ "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_1 / tma_info_core_core_clks", "MetricGroup": "TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P", "MetricName": "tma_port_1", - "MetricThreshold": "(tma_port_1 > 0.6)", + "MetricThreshold": "tma_port_1 > 0.6", "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 1 (ALU). Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_5, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%" }, @@ -963,7 +963,7 @@ "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_2 / tma_info_core_core_clks", "MetricGroup": "TopdownL6;tma_L6_group;tma_load_op_utilization_group", "MetricName": "tma_port_2", - "MetricThreshold": "(tma_port_2 > 0.6)", + "MetricThreshold": "tma_port_2 > 0.6", "ScaleUnit": "100%" }, { @@ -971,7 +971,7 @@ "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_3 / tma_info_core_core_clks", "MetricGroup": "TopdownL6;tma_L6_group;tma_load_op_utilization_group", "MetricName": "tma_port_3", - "MetricThreshold": "(tma_port_3 > 0.6)", + "MetricThreshold": "tma_port_3 > 0.6", "ScaleUnit": "100%" }, { @@ -979,7 +979,7 @@ "MetricExpr": "tma_store_op_utilization", "MetricGroup": "TopdownL6;tma_L6_group;tma_issueSpSt;tma_store_op_utilization_group", "MetricName": "tma_port_4", - "MetricThreshold": "(tma_port_4 > 0.6)", + "MetricThreshold": "tma_port_4 > 0.6", "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 4 (Store-data). Related metrics: tma_split_stores", "ScaleUnit": "100%" }, @@ -988,7 +988,7 @@ "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_5 / tma_info_core_core_clks", "MetricGroup": "TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P", "MetricName": "tma_port_5", - "MetricThreshold": "(tma_port_5 > 0.6)", + "MetricThreshold": "tma_port_5 > 0.6", "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 5 ([SNB+] Branches and ALU; [HSW+] ALU). Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%" }, @@ -997,7 +997,7 @@ "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_6 / tma_info_core_core_clks", "MetricGroup": "TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P", "MetricName": "tma_port_6", - "MetricThreshold": "(tma_port_6 > 0.6)", + "MetricThreshold": "tma_port_6 > 0.6", "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 6 ([HSW+] Primary Branch and simple ALU). Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_ports_utilized_2", "ScaleUnit": "100%" }, @@ -1006,7 +1006,7 @@ "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_7 / tma_info_core_core_clks", "MetricGroup": "TopdownL6;tma_L6_group;tma_store_op_utilization_group", "MetricName": "tma_port_7", - "MetricThreshold": "(tma_port_7 > 0.6)", + "MetricThreshold": "tma_port_7 > 0.6", "ScaleUnit": "100%" }, { @@ -1015,7 +1015,7 @@ "MetricExpr": "(CYCLE_ACTIVITY.STALLS_TOTAL + UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC - (UOPS_EXECUTED.CYCLES_GE_3_UOPS_EXEC if tma_info_thread_ipc > 1.8 else UOPS_EXECUTED.CYCLES_GE_2_UOPS_EXEC) - (RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else 0) + RESOURCE_STALLS.SB - RESOURCE_STALLS.SB - CYCLE_ACTIVITY.STALLS_MEM_ANY) / tma_info_thread_clks", "MetricGroup": "PortsUtil;TopdownL3;tma_L3_group;tma_core_bound_group", "MetricName": "tma_ports_utilization", - "MetricThreshold": "(tma_ports_utilization > 0.15) & ((tma_core_bound > 0.1) & ((tma_backend_bound > 0.2)))", + "MetricThreshold": "tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)", "PublicDescription": "This metric estimates fraction of cycles the CPU performance was potentially limited due to Core computation issues (non divider-related). Two distinct categories can be attributed into this metric: (1) heavy data-dependency among contiguous instructions would manifest in this metric - such cases are often referred to as low Instruction Level Parallelism (ILP). (2) Contention on some hardware execution unit other than Divider. For example; when there are too many multiply operations.", "ScaleUnit": "100%" }, @@ -1024,7 +1024,7 @@ "MetricExpr": "(cpu@UOPS_EXECUTED.CORE\\,inv\\,cmask\\=1@ / 2 if #SMT_on else (CYCLE_ACTIVITY.STALLS_TOTAL - (RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else 0)) / tma_info_core_core_clks)", "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group", "MetricName": "tma_ports_utilized_0", - "MetricThreshold": "(tma_ports_utilized_0 > 0.2) & ((tma_ports_utilization > 0.15) & ((tma_core_bound > 0.1) & ((tma_backend_bound > 0.2))))", + "MetricThreshold": "tma_ports_utilized_0 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", "PublicDescription": "This metric represents fraction of cycles CPU executed no uops on any execution port (Logical Processor cycles since ICL, Physical Core cycles otherwise). Long-latency instructions like divides may contribute to this metric.", "ScaleUnit": "100%" }, @@ -1033,7 +1033,7 @@ "MetricExpr": "((cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ - cpu@UOPS_EXECUTED.CORE\\,cmask\\=2@) / 2 if #SMT_on else (UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC - UOPS_EXECUTED.CYCLES_GE_2_UOPS_EXEC) / tma_info_core_core_clks)", "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_issueL1;tma_ports_utilization_group", "MetricName": "tma_ports_utilized_1", - "MetricThreshold": "(tma_ports_utilized_1 > 0.2) & ((tma_ports_utilization > 0.15) & ((tma_core_bound > 0.1) & ((tma_backend_bound > 0.2))))", + "MetricThreshold": "tma_ports_utilized_1 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", "PublicDescription": "This metric represents fraction of cycles where the CPU executed total of 1 uop per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise). This can be due to heavy data-dependency among software instructions; or over oversubscribing a particular hardware resource. In some other cases with high 1_Port_Utilized and L1_Bound; this metric can point to L1 data-cache latency bottleneck that may not necessarily manifest with complete execution starvation (due to the short L1 latency e.g. walking a linked list) - looking at the assembly can be helpful. Sample with: EXE_ACTIVITY.1_PORTS_UTIL. Related metrics: tma_l1_bound", "ScaleUnit": "100%" }, @@ -1042,7 +1042,7 @@ "MetricExpr": "((cpu@UOPS_EXECUTED.CORE\\,cmask\\=2@ - cpu@UOPS_EXECUTED.CORE\\,cmask\\=3@) / 2 if #SMT_on else (UOPS_EXECUTED.CYCLES_GE_2_UOPS_EXEC - UOPS_EXECUTED.CYCLES_GE_3_UOPS_EXEC) / tma_info_core_core_clks)", "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_issue2P;tma_ports_utilization_group", "MetricName": "tma_ports_utilized_2", - "MetricThreshold": "(tma_ports_utilized_2 > 0.15) & ((tma_ports_utilization > 0.15) & ((tma_core_bound > 0.1) & ((tma_backend_bound > 0.2))))", + "MetricThreshold": "tma_ports_utilized_2 > 0.15 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", "PublicDescription": "This metric represents fraction of cycles CPU executed total of 2 uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise). Loop Vectorization -most compilers feature auto-Vectorization options today- reduces pressure on the execution ports as multiple elements are calculated with same uop. Sample with: EXE_ACTIVITY.2_PORTS_UTIL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6", "ScaleUnit": "100%" }, @@ -1051,7 +1051,7 @@ "MetricExpr": "(cpu@UOPS_EXECUTED.CORE\\,cmask\\=3@ / 2 if #SMT_on else UOPS_EXECUTED.CYCLES_GE_3_UOPS_EXEC) / tma_info_core_core_clks", "MetricGroup": "BvCB;PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group", "MetricName": "tma_ports_utilized_3m", - "MetricThreshold": "(tma_ports_utilized_3m > 0.4) & ((tma_ports_utilization > 0.15) & ((tma_core_bound > 0.1) & ((tma_backend_bound > 0.2))))", + "MetricThreshold": "tma_ports_utilized_3m > 0.4 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", "PublicDescription": "This metric represents fraction of cycles CPU executed total of 3 or more uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise). Sample with: UOPS_EXECUTED.CYCLES_GE_3", "ScaleUnit": "100%" }, @@ -1060,7 +1060,7 @@ "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / tma_info_thread_slots", "MetricGroup": "BvUW;TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_retiring", - "MetricThreshold": "((tma_retiring > 0.7)|(tma_heavy_operations > 0.1))", + "MetricThreshold": "tma_retiring > 0.7 | tma_heavy_operations > 0.1", "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum Pipeline_Width throughput was achieved. Maximizing Retiring typically increases the Instructions-per-cycle (see IPC metric). Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Heavy-operations or Microcode Assists are categorized under Retiring. They often indicate suboptimal performance and can often be optimized or avoided. Sample with: UOPS_RETIRED.SLOTS", "ScaleUnit": "100%" @@ -1071,7 +1071,7 @@ "MetricExpr": "tma_info_memory_load_miss_real_latency * LD_BLOCKS.NO_SR / tma_info_thread_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group", "MetricName": "tma_split_loads", - "MetricThreshold": "(tma_split_loads > 0.3)", + "MetricThreshold": "tma_split_loads > 0.3", "PublicDescription": "This metric estimates fraction of cycles handling memory load split accesses - load that cross 64-byte cache line boundary. Sample with: MEM_INST_RETIRED.SPLIT_LOADS_PS", "ScaleUnit": "100%" }, @@ -1080,7 +1080,7 @@ "MetricExpr": "2 * MEM_UOPS_RETIRED.SPLIT_STORES / tma_info_core_core_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_issueSpSt;tma_store_bound_group", "MetricName": "tma_split_stores", - "MetricThreshold": "(tma_split_stores > 0.2) & ((tma_store_bound > 0.2) & ((tma_memory_bound > 0.2) & ((tma_backend_bound > 0.2))))", + "MetricThreshold": "tma_split_stores > 0.2 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", "PublicDescription": "This metric represents rate of split store accesses. Consider aligning your data to the 64-byte cache line granularity. Sample with: MEM_INST_RETIRED.SPLIT_STORES_PS. Related metrics: tma_port_4", "ScaleUnit": "100%" }, @@ -1089,7 +1089,7 @@ "MetricExpr": "(OFFCORE_REQUESTS_BUFFER.SQ_FULL / 2 if #SMT_on else OFFCORE_REQUESTS_BUFFER.SQ_FULL) / tma_info_core_core_clks", "MetricGroup": "BvMB;MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_issueBW;tma_l3_bound_group", "MetricName": "tma_sq_full", - "MetricThreshold": "(tma_sq_full > 0.3) & ((tma_l3_bound > 0.05) & ((tma_memory_bound > 0.2) & ((tma_backend_bound > 0.2))))", + "MetricThreshold": "tma_sq_full > 0.3 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", "PublicDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors). Related metrics: tma_fb_full, tma_info_system_dram_bw_use, tma_mem_bandwidth", "ScaleUnit": "100%" }, @@ -1098,7 +1098,7 @@ "MetricExpr": "RESOURCE_STALLS.SB / tma_info_thread_clks", "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_store_bound", - "MetricThreshold": "(tma_store_bound > 0.2) & ((tma_memory_bound > 0.2) & ((tma_backend_bound > 0.2)))", + "MetricThreshold": "tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", "PublicDescription": "This metric estimates how often CPU was stalled due to RFO store memory accesses; RFO store issue a read-for-ownership request before the write. Even though store accesses do not typically stall out-of-order CPUs; there are few cases where stores can lead to actual stalls. This metric will be flagged should RFO stores be a bottleneck. Sample with: MEM_INST_RETIRED.ALL_STORES_PS", "ScaleUnit": "100%" }, @@ -1107,7 +1107,7 @@ "MetricExpr": "13 * LD_BLOCKS.STORE_FORWARD / tma_info_thread_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group", "MetricName": "tma_store_fwd_blk", - "MetricThreshold": "(tma_store_fwd_blk > 0.1) & ((tma_l1_bound > 0.1) & ((tma_memory_bound > 0.2) & ((tma_backend_bound > 0.2))))", + "MetricThreshold": "tma_store_fwd_blk > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", "PublicDescription": "This metric roughly estimates fraction of cycles when the memory subsystem had loads blocked since they could not forward data from earlier (in program order) overlapping stores. To streamline memory operations in the pipeline; a load can avoid waiting for memory if a prior in-flight store is writing the data that the load wants to read (store forwarding process). However; in some cases the load may be blocked for a significant time pending the store forward. For example; when the prior store is writing a smaller region than the load is reading.", "ScaleUnit": "100%" }, @@ -1117,7 +1117,7 @@ "MetricExpr": "(L2_RQSTS.RFO_HIT * 9 * (1 - MEM_UOPS_RETIRED.LOCK_LOADS / MEM_UOPS_RETIRED.ALL_STORES) + (1 - MEM_UOPS_RETIRED.LOCK_LOADS / MEM_UOPS_RETIRED.ALL_STORES) * min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO)) / tma_info_thread_clks", "MetricGroup": "BvML;LockCont;MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_issueSL;tma_store_bound_group", "MetricName": "tma_store_latency", - "MetricThreshold": "(tma_store_latency > 0.1) & ((tma_store_bound > 0.2) & ((tma_memory_bound > 0.2) & ((tma_backend_bound > 0.2))))", + "MetricThreshold": "tma_store_latency > 0.1 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", "PublicDescription": "This metric estimates fraction of cycles the CPU spent handling L1D store misses. Store accesses usually less impact out-of-order core performance; however; holding resources for longer time can lead into undesired implications (e.g. contention on L1D fill-buffer entries - see FB_Full). Related metrics: tma_fb_full, tma_lock_latency", "ScaleUnit": "100%" }, @@ -1126,7 +1126,7 @@ "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_4 / tma_info_core_core_clks", "MetricGroup": "TopdownL5;tma_L5_group;tma_ports_utilized_3m_group", "MetricName": "tma_store_op_utilization", - "MetricThreshold": "(tma_store_op_utilization > 0.6)", + "MetricThreshold": "tma_store_op_utilization > 0.6", "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port for Store operations. Sample with: UOPS_DISPATCHED.PORT_7_8", "ScaleUnit": "100%" }, @@ -1135,7 +1135,7 @@ "MetricExpr": "tma_branch_resteers - tma_mispredicts_resteers - tma_clears_resteers", "MetricGroup": "BigFootprint;BvBC;FetchLat;TopdownL4;tma_L4_group;tma_branch_resteers_group", "MetricName": "tma_unknown_branches", - "MetricThreshold": "(tma_unknown_branches > 0.05) & ((tma_branch_resteers > 0.05) & ((tma_fetch_latency > 0.1) & ((tma_frontend_bound > 0.15))))", + "MetricThreshold": "tma_unknown_branches > 0.05 & (tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))", "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to new branch address clears. These are fetched branches the Branch Prediction Unit was unable to recognize (e.g. first time the branch is fetched or hitting BTB capacity limit) hence called Unknown Branches. Sample with: FRONTEND_RETIRED.UNKNOWN_BRANCH", "ScaleUnit": "100%" }, @@ -1144,7 +1144,7 @@ "MetricExpr": "INST_RETIRED.X87 * tma_info_thread_uoppi / UOPS_RETIRED.RETIRE_SLOTS", "MetricGroup": "Compute;TopdownL4;tma_L4_group;tma_fp_arith_group", "MetricName": "tma_x87_use", - "MetricThreshold": "(tma_x87_use > 0.1) & ((tma_fp_arith > 0.2) & ((tma_light_operations > 0.6)))", + "MetricThreshold": "tma_x87_use > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6)", "PublicDescription": "This metric serves as an approximation of legacy x87 usage. It accounts for instructions beyond X87 FP arithmetic operations; hence may be used as a thermometer to avoid X87 high usage and preferably upgrade to modern ISA. See Tip under Tuning Hint.", "ScaleUnit": "100%" } diff --git a/tools/perf/pmu-events/arch/x86/broadwellx/bdx-metrics.json b/tools/perf/pmu-events/arch/x86/broadwellx/bdx-metrics.json index 8016202bad1f..5d06a3f72be2 100644 --- a/tools/perf/pmu-events/arch/x86/broadwellx/bdx-metrics.json +++ b/tools/perf/pmu-events/arch/x86/broadwellx/bdx-metrics.json @@ -276,12 +276,12 @@ "MetricExpr": "LD_BLOCKS_PARTIAL.ADDRESS_ALIAS / tma_info_thread_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group", "MetricName": "tma_4k_aliasing", - "MetricThreshold": "tma_4k_aliasing > 0.2 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", - "PublicDescription": "This metric estimates how often memory load accesses were aliased by preceding stores (in program order) with a 4K address offset. False match is possible; which incur a few cycles load re-issue. However; the short re-issue duration is often hidden by the out-of-order core and HW optimizations; hence a user may safely ignore a high value of this metric unless it manages to propagate up into parent nodes of the hierarchy (e.g. to L1_Bound)", + "MetricThreshold": "tma_4k_aliasing > 0.2 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric estimates how often memory load accesses were aliased by preceding stores (in program order) with a 4K address offset. False match is possible; which incur a few cycles load re-issue. However; the short re-issue duration is often hidden by the out-of-order core and HW optimizations; hence a user may safely ignore a high value of this metric unless it manages to propagate up into parent nodes of the hierarchy (e.g. to L1_Bound).", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution ports for ALU operations", + "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution ports for ALU operations.", "MetricConstraint": "NO_GROUP_EVENTS_NMI", "MetricExpr": "(UOPS_DISPATCHED_PORT.PORT_0 + UOPS_DISPATCHED_PORT.PORT_1 + UOPS_DISPATCHED_PORT.PORT_5 + UOPS_DISPATCHED_PORT.PORT_6) / tma_info_thread_slots", "MetricGroup": "TopdownL5;tma_L5_group;tma_ports_utilized_3m_group", @@ -294,8 +294,8 @@ "MetricExpr": "66 * OTHER_ASSISTS.ANY_WB_ASSIST / tma_info_thread_slots", "MetricGroup": "BvIO;TopdownL4;tma_L4_group;tma_microcode_sequencer_group", "MetricName": "tma_assists", - "MetricThreshold": "tma_assists > 0.1 & tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1", - "PublicDescription": "This metric estimates fraction of slots the CPU retired uops delivered by the Microcode_Sequencer as a result of Assists. Assists are long sequences of uops that are required in certain corner-cases for operations that cannot be handled natively by the execution pipeline. For example; when working with very small floating point values (so-called Denormals); the FP units are not set up to perform these operations natively. Instead; a sequence of instructions to perform the computation on the Denormals is injected into the pipeline. Since these microcode sequences might be dozens of uops long; Assists can be extremely deleterious to performance and they can be avoided in many cases. Sample with: OTHER_ASSISTS.ANY_WB_ASSIST", + "MetricThreshold": "tma_assists > 0.1 & (tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1)", + "PublicDescription": "This metric estimates fraction of slots the CPU retired uops delivered by the Microcode_Sequencer as a result of Assists. Assists are long sequences of uops that are required in certain corner-cases for operations that cannot be handled natively by the execution pipeline. For example; when working with very small floating point values (so-called Denormals); the FP units are not set up to perform these operations natively. Instead; a sequence of instructions to perform the computation on the Denormals is injected into the pipeline. Since these microcode sequences might be dozens of uops long; Assists can be extremely deleterious to performance and they can be avoided in many cases. Sample with: OTHER_ASSISTS.ANY", "ScaleUnit": "100%" }, { @@ -306,7 +306,7 @@ "MetricName": "tma_backend_bound", "MetricThreshold": "tma_backend_bound > 0.2", "MetricgroupNoGroup": "TopdownL1", - "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound", + "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound.", "ScaleUnit": "100%" }, { @@ -316,7 +316,7 @@ "MetricName": "tma_bad_speculation", "MetricThreshold": "tma_bad_speculation > 0.15", "MetricgroupNoGroup": "TopdownL1", - "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example", + "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.", "ScaleUnit": "100%" }, { @@ -327,7 +327,7 @@ "MetricName": "tma_branch_mispredicts", "MetricThreshold": "tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", "MetricgroupNoGroup": "TopdownL2", - "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction. These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_mispredicts_resteers", + "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction. These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_info_bad_spec_branch_misprediction_cost, tma_mispredicts_resteers", "ScaleUnit": "100%" }, { @@ -335,8 +335,8 @@ "MetricExpr": "12 * (BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT + BACLEARS.ANY) / tma_info_thread_clks", "MetricGroup": "FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group", "MetricName": "tma_branch_resteers", - "MetricThreshold": "tma_branch_resteers > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", - "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers. Branch Resteers estimates the Frontend delay in fetching operations from corrected path; following all sorts of miss-predicted branches. For example; branchy code with lots of miss-predictions might get categorized under Branch Resteers. Note the value of this node may overlap with its siblings. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_l3_hit_latency, tma_store_latency", + "MetricThreshold": "tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers. Branch Resteers estimates the Frontend delay in fetching operations from corrected path; following all sorts of miss-predicted branches. For example; branchy code with lots of miss-predictions might get categorized under Branch Resteers. Note the value of this node may overlap with its siblings. Sample with: BR_MISP_RETIRED.ALL_BRANCHES", "ScaleUnit": "100%" }, { @@ -345,8 +345,8 @@ "MetricExpr": "max(0, tma_microcode_sequencer - tma_assists)", "MetricGroup": "TopdownL4;tma_L4_group;tma_microcode_sequencer_group", "MetricName": "tma_cisc", - "MetricThreshold": "tma_cisc > 0.1 & tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1", - "PublicDescription": "This metric estimates fraction of cycles the CPU retired uops originated from CISC (complex instruction set computer) instruction. A CISC instruction has multiple uops that are required to perform the instruction's functionality as in the case of read-modify-write as an example. Since these instructions require multiple uops they may or may not imply sub-optimal use of machine resources", + "MetricThreshold": "tma_cisc > 0.1 & (tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1)", + "PublicDescription": "This metric estimates fraction of cycles the CPU retired uops originated from CISC (complex instruction set computer) instruction. A CISC instruction has multiple uops that are required to perform the instruction's functionality as in the case of read-modify-write as an example. Since these instructions require multiple uops they may or may not imply sub-optimal use of machine resources.", "ScaleUnit": "100%" }, { @@ -354,7 +354,7 @@ "MetricExpr": "MACHINE_CLEARS.COUNT * tma_branch_resteers / (BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT + BACLEARS.ANY)", "MetricGroup": "BadSpec;MachineClears;TopdownL4;tma_L4_group;tma_branch_resteers_group;tma_issueMC", "MetricName": "tma_clears_resteers", - "MetricThreshold": "tma_clears_resteers > 0.05 & tma_branch_resteers > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricThreshold": "tma_clears_resteers > 0.05 & (tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))", "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Machine Clears. Related metrics: tma_l1_bound, tma_machine_clears, tma_microcode_sequencer, tma_ms_switches", "ScaleUnit": "100%" }, @@ -364,8 +364,8 @@ "MetricExpr": "(60 * (MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.L3_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_L3_MISS_RETIRED.LOCAL_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_HITM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_FWD))) + 43 * (MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.L3_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_L3_MISS_RETIRED.LOCAL_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_HITM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_FWD)))) / tma_info_thread_clks", "MetricGroup": "BvMS;DataSharing;LockCont;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group", "MetricName": "tma_contested_accesses", - "MetricThreshold": "tma_contested_accesses > 0.05 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", - "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses. Contested accesses occur when data written by one Logical Processor are read by another Logical Processor on a different Physical Core. Examples of contested accesses include synchronizations such as locks; true data sharing such as modified locked variables; and false sharing. Sample with: MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM, MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS. Related metrics: tma_data_sharing, tma_false_sharing, tma_machine_clears, tma_remote_cache", + "MetricThreshold": "tma_contested_accesses > 0.05 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses. Contested accesses occur when data written by one Logical Processor are read by another Logical Processor on a different Physical Core. Examples of contested accesses include synchronizations such as locks; true data sharing such as modified locked variables; and false sharing. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM_PS;MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS_PS. Related metrics: tma_data_sharing, tma_false_sharing, tma_machine_clears, tma_remote_cache", "ScaleUnit": "100%" }, { @@ -376,7 +376,7 @@ "MetricName": "tma_core_bound", "MetricThreshold": "tma_core_bound > 0.1 & tma_backend_bound > 0.2", "MetricgroupNoGroup": "TopdownL2", - "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck. Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations)", + "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck. Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations).", "ScaleUnit": "100%" }, { @@ -385,8 +385,8 @@ "MetricExpr": "43 * (MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.L3_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_L3_MISS_RETIRED.LOCAL_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_HITM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_FWD))) / tma_info_thread_clks", "MetricGroup": "BvMS;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group", "MetricName": "tma_data_sharing", - "MetricThreshold": "tma_data_sharing > 0.05 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", - "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses. Data shared by multiple Logical Processors (even just read shared) may cause increased access latency due to cache coherency. Excessive data sharing can drastically harm multithreaded performance. Sample with: MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT. Related metrics: tma_contested_accesses, tma_false_sharing, tma_machine_clears, tma_remote_cache", + "MetricThreshold": "tma_data_sharing > 0.05 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses. Data shared by multiple Logical Processors (even just read shared) may cause increased access latency due to cache coherency. Excessive data sharing can drastically harm multithreaded performance. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_HIT_PS. Related metrics: tma_contested_accesses, tma_false_sharing, tma_machine_clears, tma_remote_cache", "ScaleUnit": "100%" }, { @@ -394,8 +394,8 @@ "MetricExpr": "ARITH.FPU_DIV_ACTIVE / tma_info_core_core_clks", "MetricGroup": "BvCB;TopdownL3;tma_L3_group;tma_core_bound_group", "MetricName": "tma_divider", - "MetricThreshold": "tma_divider > 0.2 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", - "PublicDescription": "This metric represents fraction of cycles where the Divider unit was active. Divide and square root instructions are performed by the Divider unit and can take considerably longer latency than integer or Floating Point addition; subtraction; or multiplication. Sample with: ARITH.FPU_DIV_ACTIVE", + "MetricThreshold": "tma_divider > 0.2 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)", + "PublicDescription": "This metric represents fraction of cycles where the Divider unit was active. Divide and square root instructions are performed by the Divider unit and can take considerably longer latency than integer or Floating Point addition; subtraction; or multiplication. Sample with: ARITH.DIVIDER_ACTIVE", "ScaleUnit": "100%" }, { @@ -404,8 +404,8 @@ "MetricExpr": "(1 - MEM_LOAD_UOPS_RETIRED.L3_HIT / (MEM_LOAD_UOPS_RETIRED.L3_HIT + 7 * MEM_LOAD_UOPS_RETIRED.L3_MISS)) * CYCLE_ACTIVITY.STALLS_L2_MISS / tma_info_thread_clks", "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_dram_bound", - "MetricThreshold": "tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", - "PublicDescription": "This metric estimates how often the CPU was stalled on accesses to external memory (DRAM) by loads. Better caching can improve the latency and increase performance. Sample with: MEM_LOAD_UOPS_RETIRED.L3_MISS", + "MetricThreshold": "tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", + "PublicDescription": "This metric estimates how often the CPU was stalled on accesses to external memory (DRAM) by loads. Better caching can improve the latency and increase performance. Sample with: MEM_LOAD_UOPS_RETIRED.L3_MISS_PS", "ScaleUnit": "100%" }, { @@ -414,7 +414,7 @@ "MetricGroup": "DSB;FetchBW;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group", "MetricName": "tma_dsb", "MetricThreshold": "tma_dsb > 0.15 & tma_fetch_bandwidth > 0.2", - "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to DSB (decoded uop cache) fetch pipeline. For example; inefficient utilization of the DSB cache structure or bank conflict when reading from it; are categorized here", + "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to DSB (decoded uop cache) fetch pipeline. For example; inefficient utilization of the DSB cache structure or bank conflict when reading from it; are categorized here.", "ScaleUnit": "100%" }, { @@ -422,26 +422,26 @@ "MetricExpr": "DSB2MITE_SWITCHES.PENALTY_CYCLES / tma_info_thread_clks", "MetricGroup": "DSBmiss;FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueFB", "MetricName": "tma_dsb_switches", - "MetricThreshold": "tma_dsb_switches > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricThreshold": "tma_dsb_switches > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines. The DSB (decoded i-cache) is a Uop Cache where the front-end directly delivers Uops (micro operations) avoiding heavy x86 decoding. The DSB pipeline has shorter latency and delivered higher bandwidth than the MITE (legacy instruction decode pipeline). Switching between the two pipelines can cause penalties hence this metric measures the exposed penalty. Related metrics: tma_fetch_bandwidth, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp", "ScaleUnit": "100%" }, { "BriefDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses", - "MetricExpr": "(8 * DTLB_LOAD_MISSES.STLB_HIT + cpu@DTLB_LOAD_MISSES.WALK_DURATION\\,cmask\\=0x1@ + 7 * DTLB_LOAD_MISSES.WALK_COMPLETED) / tma_info_thread_clks", + "MetricExpr": "(8 * DTLB_LOAD_MISSES.STLB_HIT + cpu@DTLB_LOAD_MISSES.WALK_DURATION\\,cmask\\=1@ + 7 * DTLB_LOAD_MISSES.WALK_COMPLETED) / tma_info_thread_clks", "MetricGroup": "BvMT;MemoryTLB;TopdownL4;tma_L4_group;tma_issueTLB;tma_l1_bound_group", "MetricName": "tma_dtlb_load", - "MetricThreshold": "tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", - "PublicDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses. TLBs (Translation Look-aside Buffers) are processor caches for recently used entries out of the Page Tables that are used to map virtual- to physical-addresses by the operating system. This metric approximates the potential delay of demand loads missing the first-level data TLB (assuming worst case scenario with back to back misses to different pages). This includes hitting in the second-level TLB (STLB) as well as performing a hardware page walk on an STLB miss. Sample with: MEM_UOPS_RETIRED.STLB_MISS_LOADS. Related metrics: tma_dtlb_store", + "MetricThreshold": "tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses. TLBs (Translation Look-aside Buffers) are processor caches for recently used entries out of the Page Tables that are used to map virtual- to physical-addresses by the operating system. This metric approximates the potential delay of demand loads missing the first-level data TLB (assuming worst case scenario with back to back misses to different pages). This includes hitting in the second-level TLB (STLB) as well as performing a hardware page walk on an STLB miss. Sample with: MEM_UOPS_RETIRED.STLB_MISS_LOADS_PS. Related metrics: tma_dtlb_store", "ScaleUnit": "100%" }, { "BriefDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses", - "MetricExpr": "(8 * DTLB_STORE_MISSES.STLB_HIT + cpu@DTLB_STORE_MISSES.WALK_DURATION\\,cmask\\=0x1@ + 7 * DTLB_STORE_MISSES.WALK_COMPLETED) / tma_info_thread_clks", + "MetricExpr": "(8 * DTLB_STORE_MISSES.STLB_HIT + cpu@DTLB_STORE_MISSES.WALK_DURATION\\,cmask\\=1@ + 7 * DTLB_STORE_MISSES.WALK_COMPLETED) / tma_info_thread_clks", "MetricGroup": "BvMT;MemoryTLB;TopdownL4;tma_L4_group;tma_issueTLB;tma_store_bound_group", "MetricName": "tma_dtlb_store", - "MetricThreshold": "tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", - "PublicDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses. As with ordinary data caching; focus on improving data locality and reducing working-set size to reduce DTLB overhead. Additionally; consider using profile-guided optimization (PGO) to collocate frequently-used data on the same page. Try using larger page sizes for large amounts of frequently-used data. Sample with: MEM_UOPS_RETIRED.STLB_MISS_STORES. Related metrics: tma_dtlb_load", + "MetricThreshold": "tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses. As with ordinary data caching; focus on improving data locality and reducing working-set size to reduce DTLB overhead. Additionally; consider using profile-guided optimization (PGO) to collocate frequently-used data on the same page. Try using larger page sizes for large amounts of frequently-used data. Sample with: MEM_UOPS_RETIRED.STLB_MISS_STORES_PS. Related metrics: tma_dtlb_load", "ScaleUnit": "100%" }, { @@ -449,18 +449,18 @@ "MetricExpr": "(200 * OFFCORE_RESPONSE.DEMAND_RFO.LLC_MISS.REMOTE_HITM + 60 * OFFCORE_RESPONSE.DEMAND_RFO.LLC_HIT.HITM_OTHER_CORE) / tma_info_thread_clks", "MetricGroup": "BvMS;DataSharing;LockCont;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_store_bound_group", "MetricName": "tma_false_sharing", - "MetricThreshold": "tma_false_sharing > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", - "PublicDescription": "This metric roughly estimates how often CPU was handling synchronizations due to False Sharing. False Sharing is a multithreading hiccup; where multiple Logical Processors contend on different data-elements mapped into the same cache line. Sample with: MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM, MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_HITM, OFFCORE_RESPONSE.DEMAND_RFO.LLC_HIT.HITM_OTHER_CORE, OFFCORE_RESPONSE.DEMAND_RFO.LLC_MISS.REMOTE_HITM. Related metrics: tma_contested_accesses, tma_data_sharing, tma_machine_clears, tma_remote_cache", + "MetricThreshold": "tma_false_sharing > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric roughly estimates how often CPU was handling synchronizations due to False Sharing. False Sharing is a multithreading hiccup; where multiple Logical Processors contend on different data-elements mapped into the same cache line. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM_PS;OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.SNOOP_HITM. Related metrics: tma_contested_accesses, tma_data_sharing, tma_machine_clears, tma_remote_cache", "ScaleUnit": "100%" }, { "BriefDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed", "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "tma_info_memory_load_miss_real_latency * cpu@L1D_PEND_MISS.FB_FULL\\,cmask\\=0x1@ / tma_info_thread_clks", + "MetricExpr": "tma_info_memory_load_miss_real_latency * cpu@L1D_PEND_MISS.FB_FULL\\,cmask\\=1@ / tma_info_thread_clks", "MetricGroup": "BvMB;MemoryBW;TopdownL4;tma_L4_group;tma_issueBW;tma_issueSL;tma_issueSmSt;tma_l1_bound_group", "MetricName": "tma_fb_full", "MetricThreshold": "tma_fb_full > 0.3", - "PublicDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed. The higher the metric value; the deeper the memory hierarchy level the misses are satisfied from (metric values >1 are valid). Often it hints on approaching bandwidth limits (to L2 cache; L3 cache or external memory). Related metrics: tma_info_system_dram_bw_use, tma_mem_bandwidth, tma_sq_full, tma_store_latency", + "PublicDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed. The higher the metric value; the deeper the memory hierarchy level the misses are satisfied from (metric values >1 are valid). Often it hints on approaching bandwidth limits (to L2 cache; L3 cache or external memory). Related metrics: tma_info_system_dram_bw_use, tma_mem_bandwidth, tma_sq_full, tma_store_latency, tma_streaming_stores", "ScaleUnit": "100%" }, { @@ -489,7 +489,7 @@ "MetricGroup": "HPC;TopdownL3;tma_L3_group;tma_light_operations_group", "MetricName": "tma_fp_arith", "MetricThreshold": "tma_fp_arith > 0.2 & tma_light_operations > 0.6", - "PublicDescription": "This metric represents overall arithmetic floating-point (FP) operations fraction the CPU has executed (retired). Note this metric's value may exceed its parent due to use of \"Uops\" CountDomain and FMA double-counting", + "PublicDescription": "This metric represents overall arithmetic floating-point (FP) operations fraction the CPU has executed (retired). Note this metric's value may exceed its parent due to use of \"Uops\" CountDomain and FMA double-counting.", "ScaleUnit": "100%" }, { @@ -497,8 +497,8 @@ "MetricExpr": "FP_ARITH_INST_RETIRED.SCALAR / UOPS_RETIRED.RETIRE_SLOTS", "MetricGroup": "Compute;Flops;TopdownL4;tma_L4_group;tma_fp_arith_group;tma_issue2P", "MetricName": "tma_fp_scalar", - "MetricThreshold": "tma_fp_scalar > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6", - "PublicDescription": "This metric approximates arithmetic floating-point (FP) scalar uops fraction the CPU has retired. May overcount due to FMA double counting. Related metrics: tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", + "MetricThreshold": "tma_fp_scalar > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6)", + "PublicDescription": "This metric approximates arithmetic floating-point (FP) scalar uops fraction the CPU has retired. May overcount due to FMA double counting. Related metrics: tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%" }, { @@ -506,8 +506,8 @@ "MetricExpr": "FP_ARITH_INST_RETIRED.VECTOR / UOPS_RETIRED.RETIRE_SLOTS", "MetricGroup": "Compute;Flops;TopdownL4;tma_L4_group;tma_fp_arith_group;tma_issue2P", "MetricName": "tma_fp_vector", - "MetricThreshold": "tma_fp_vector > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6", - "PublicDescription": "This metric approximates arithmetic floating-point (FP) vector uops fraction the CPU has retired aggregated across all vector widths. May overcount due to FMA double counting. Related metrics: tma_fp_scalar, tma_fp_vector_128b, tma_fp_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", + "MetricThreshold": "tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6)", + "PublicDescription": "This metric approximates arithmetic floating-point (FP) vector uops fraction the CPU has retired aggregated across all vector widths. May overcount due to FMA double counting. Related metrics: tma_fp_scalar, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%" }, { @@ -515,8 +515,8 @@ "MetricExpr": "(FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE) / UOPS_RETIRED.RETIRE_SLOTS", "MetricGroup": "Compute;Flops;TopdownL5;tma_L5_group;tma_fp_vector_group;tma_issue2P", "MetricName": "tma_fp_vector_128b", - "MetricThreshold": "tma_fp_vector_128b > 0.1 & tma_fp_vector > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6", - "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 128-bit wide vectors. May overcount due to FMA double counting prior to LNL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", + "MetricThreshold": "tma_fp_vector_128b > 0.1 & (tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6))", + "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 128-bit wide vectors. May overcount due to FMA double counting prior to LNL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%" }, { @@ -524,8 +524,8 @@ "MetricExpr": "(FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE) / UOPS_RETIRED.RETIRE_SLOTS", "MetricGroup": "Compute;Flops;TopdownL5;tma_L5_group;tma_fp_vector_group;tma_issue2P", "MetricName": "tma_fp_vector_256b", - "MetricThreshold": "tma_fp_vector_256b > 0.1 & tma_fp_vector > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6", - "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 256-bit wide vectors. May overcount due to FMA double counting prior to LNL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", + "MetricThreshold": "tma_fp_vector_256b > 0.1 & (tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6))", + "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 256-bit wide vectors. May overcount due to FMA double counting prior to LNL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%" }, { @@ -535,33 +535,33 @@ "MetricName": "tma_frontend_bound", "MetricThreshold": "tma_frontend_bound > 0.15", "MetricgroupNoGroup": "TopdownL1", - "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound", + "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound.", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations , instructions that require two or more uops or micro-coded sequences", + "BriefDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences", "MetricExpr": "tma_microcode_sequencer", "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_heavy_operations", "MetricThreshold": "tma_heavy_operations > 0.1", "MetricgroupNoGroup": "TopdownL2", - "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations , instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences.([ICL+] Note this may overcount due to approximation using indirect events; [ADL+])", + "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences.([ICL+] Note this may overcount due to approximation using indirect events; [ADL+])", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to instruction cache misses", + "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to instruction cache misses.", "MetricExpr": "ICACHE.IFDATA_STALL / tma_info_thread_clks", "MetricGroup": "BigFootprint;BvBC;FetchLat;IcMiss;TopdownL3;tma_L3_group;tma_fetch_latency_group", "MetricName": "tma_icache_misses", - "MetricThreshold": "tma_icache_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricThreshold": "tma_icache_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", "ScaleUnit": "100%" }, { - "BriefDescription": "Instructions per retired Mispredicts for indirect CALL or JMP branches (lower number means higher occurrence rate)", + "BriefDescription": "Instructions per retired Mispredicts for indirect CALL or JMP branches (lower number means higher occurrence rate).", "MetricExpr": "tma_info_inst_mix_instructions / (UOPS_RETIRED.RETIRE_SLOTS / UOPS_ISSUED.ANY * BR_MISP_EXEC.INDIRECT)", "MetricGroup": "Bad;BrMispredicts", "MetricName": "tma_info_bad_spec_ipmisp_indirect", - "MetricThreshold": "tma_info_bad_spec_ipmisp_indirect < 1000" + "MetricThreshold": "tma_info_bad_spec_ipmisp_indirect < 1e3" }, { "BriefDescription": "Number of Instructions per non-speculative Branch Misprediction (JEClear) (lower number means higher occurrence rate)", @@ -572,7 +572,7 @@ }, { "BriefDescription": "Core actual clocks when any Logical Processor is active on the Physical Core", - "MetricExpr": "(CPU_CLK_UNHALTED.THREAD_ANY / 2 if #SMT_on else tma_info_thread_clks)", + "MetricExpr": "(CPU_CLK_UNHALTED.THREAD / 2 * (1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK) if #core_wide < 1 else (CPU_CLK_UNHALTED.THREAD_ANY / 2 if #SMT_on else tma_info_thread_clks))", "MetricGroup": "SMT", "MetricName": "tma_info_core_core_clks" }, @@ -593,11 +593,11 @@ "MetricExpr": "(FP_ARITH_INST_RETIRED.SCALAR + FP_ARITH_INST_RETIRED.VECTOR) / (2 * tma_info_core_core_clks)", "MetricGroup": "Cor;Flops;HPC", "MetricName": "tma_info_core_fp_arith_utilization", - "PublicDescription": "Actual per-core usage of the Floating Point non-X87 execution units (regardless of precision or vector-width). Values > 1 are possible due to ([BDW+] Fused-Multiply Add (FMA) counting - common; [ADL+] use all of ADD/MUL/FMA in Scalar or 128/256-bit vectors - less common)" + "PublicDescription": "Actual per-core usage of the Floating Point non-X87 execution units (regardless of precision or vector-width). Values > 1 are possible due to ([BDW+] Fused-Multiply Add (FMA) counting - common; [ADL+] use all of ADD/MUL/FMA in Scalar or 128/256-bit vectors - less common)." }, { "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is execution) per thread (logical-processor)", - "MetricExpr": "UOPS_EXECUTED.THREAD / cpu@UOPS_EXECUTED.THREAD\\,cmask\\=0x1@", + "MetricExpr": "UOPS_EXECUTED.THREAD / cpu@UOPS_EXECUTED.THREAD\\,cmask\\=1@", "MetricGroup": "Backend;Cor;Pipeline;PortsUtil", "MetricName": "tma_info_core_ilp" }, @@ -622,7 +622,7 @@ "MetricName": "tma_info_frontend_tbpc" }, { - "BriefDescription": "Branch instructions per taken branch", + "BriefDescription": "Branch instructions per taken branch.", "MetricExpr": "BR_INST_RETIRED.ALL_BRANCHES / BR_INST_RETIRED.NEAR_TAKEN", "MetricGroup": "Branches;Fed;PGO", "MetricName": "tma_info_inst_mix_bptkbranch" @@ -640,7 +640,7 @@ "MetricGroup": "Flops;InsType", "MetricName": "tma_info_inst_mix_iparith", "MetricThreshold": "tma_info_inst_mix_iparith < 10", - "PublicDescription": "Instructions per FP Arithmetic instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting. Approximated prior to BDW" + "PublicDescription": "Instructions per FP Arithmetic instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting. Approximated prior to BDW." }, { "BriefDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number means higher occurrence rate)", @@ -648,7 +648,7 @@ "MetricGroup": "Flops;FpVector;InsType", "MetricName": "tma_info_inst_mix_iparith_avx128", "MetricThreshold": "tma_info_inst_mix_iparith_avx128 < 10", - "PublicDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting" + "PublicDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting." }, { "BriefDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means higher occurrence rate)", @@ -656,7 +656,7 @@ "MetricGroup": "Flops;FpVector;InsType", "MetricName": "tma_info_inst_mix_iparith_avx256", "MetricThreshold": "tma_info_inst_mix_iparith_avx256 < 10", - "PublicDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting" + "PublicDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting." }, { "BriefDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction (lower number means higher occurrence rate)", @@ -664,7 +664,7 @@ "MetricGroup": "Flops;FpScalar;InsType", "MetricName": "tma_info_inst_mix_iparith_scalar_dp", "MetricThreshold": "tma_info_inst_mix_iparith_scalar_dp < 10", - "PublicDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting" + "PublicDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting." }, { "BriefDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction (lower number means higher occurrence rate)", @@ -672,7 +672,7 @@ "MetricGroup": "Flops;FpScalar;InsType", "MetricName": "tma_info_inst_mix_iparith_scalar_sp", "MetricThreshold": "tma_info_inst_mix_iparith_scalar_sp < 10", - "PublicDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting" + "PublicDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting." }, { "BriefDescription": "Instructions per Branch (lower number means higher occurrence rate)", @@ -714,7 +714,7 @@ "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_TAKEN", "MetricGroup": "Branches;Fed;FetchBW;Frontend;PGO;tma_issueFB", "MetricName": "tma_info_inst_mix_iptb", - "MetricThreshold": "tma_info_inst_mix_iptb < 4 * 2 + 1", + "MetricThreshold": "tma_info_inst_mix_iptb < 9", "PublicDescription": "Instructions per taken branch. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_frontend_dsb_coverage, tma_lcp" }, { @@ -842,14 +842,14 @@ "MetricThreshold": "tma_info_memory_tlb_page_walks_utilization > 0.5" }, { - "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is execution) per core", - "MetricExpr": "UOPS_EXECUTED.THREAD / (cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x1@ / 2 if #SMT_on else UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC)", + "BriefDescription": "", + "MetricExpr": "UOPS_EXECUTED.THREAD / (cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ / 2 if #SMT_on else UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC)", "MetricGroup": "Cor;Pipeline;PortsUtil;SMT", "MetricName": "tma_info_pipeline_execute" }, { - "BriefDescription": "Average number of Uops retired in cycles where at least one uop has retired", - "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / cpu@UOPS_RETIRED.RETIRE_SLOTS\\,cmask\\=0x1@", + "BriefDescription": "Average number of Uops retired in cycles where at least one uop has retired.", + "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / cpu@UOPS_RETIRED.RETIRE_SLOTS\\,cmask\\=1@", "MetricGroup": "Pipeline;Ret", "MetricName": "tma_info_pipeline_retire" }, @@ -890,14 +890,13 @@ "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.FAR_BRANCH:u", "MetricGroup": "Branches;OS", "MetricName": "tma_info_system_ipfarbranch", - "MetricThreshold": "tma_info_system_ipfarbranch < 1000000" + "MetricThreshold": "tma_info_system_ipfarbranch < 1e6" }, { "BriefDescription": "Cycles Per Instruction for the Operating System (OS) Kernel mode", "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P:k / INST_RETIRED.ANY_P:k", "MetricGroup": "OS", - "MetricName": "tma_info_system_kernel_cpi", - "ScaleUnit": "1per_instr" + "MetricName": "tma_info_system_kernel_cpi" }, { "BriefDescription": "Fraction of cycles spent in the Operating System (OS) Kernel mode", @@ -908,14 +907,14 @@ }, { "BriefDescription": "Average number of parallel data read requests to external memory", - "MetricExpr": "cbox@UNC_C_TOR_OCCUPANCY.MISS_OPCODE\\,filter_opc\\=0x182@ / cbox@UNC_C_TOR_OCCUPANCY.MISS_OPCODE\\,filter_opc\\=0x182@", + "MetricExpr": "UNC_C_TOR_OCCUPANCY.MISS_OPCODE@filter_opc\\=0x182@ / UNC_C_TOR_OCCUPANCY.MISS_OPCODE@filter_opc\\=0x182\\,thresh\\=1@", "MetricGroup": "Mem;MemoryBW;SoC", "MetricName": "tma_info_system_mem_parallel_reads", "PublicDescription": "Average number of parallel data read requests to external memory. Accounts for demand loads and L1/L2 prefetches" }, { "BriefDescription": "Average latency of data read request to external memory (in nanoseconds)", - "MetricExpr": "1e9 * (cbox@UNC_C_TOR_OCCUPANCY.MISS_OPCODE\\,filter_opc\\=0x182@ / cbox@UNC_C_TOR_INSERTS.MISS_OPCODE\\,filter_opc\\=0x182@) / (tma_info_system_socket_clks / tma_info_system_time)", + "MetricExpr": "1e9 * (UNC_C_TOR_OCCUPANCY.MISS_OPCODE@filter_opc\\=0x182@ / UNC_C_TOR_INSERTS.MISS_OPCODE@filter_opc\\=0x182@) / (tma_info_system_socket_clks / tma_info_system_time)", "MetricGroup": "Mem;MemoryLat;SoC", "MetricName": "tma_info_system_mem_read_latency", "PublicDescription": "Average latency of data read request to external memory (in nanoseconds). Accounts for demand loads and L1/L2 prefetches. ([RKL+]memory-controller only)" @@ -965,7 +964,7 @@ "MetricName": "tma_info_system_uncore_frequency" }, { - "BriefDescription": "Per-Logical Processor actual clocks when the Logical Processor is active", + "BriefDescription": "Per-Logical Processor actual clocks when the Logical Processor is active.", "MetricExpr": "CPU_CLK_UNHALTED.THREAD", "MetricGroup": "Pipeline", "MetricName": "tma_info_thread_clks" @@ -974,15 +973,14 @@ "BriefDescription": "Cycles Per Instruction (per Logical Processor)", "MetricExpr": "1 / tma_info_thread_ipc", "MetricGroup": "Mem;Pipeline", - "MetricName": "tma_info_thread_cpi", - "ScaleUnit": "1per_instr" + "MetricName": "tma_info_thread_cpi" }, { "BriefDescription": "The ratio of Executed- by Issued-Uops", "MetricExpr": "UOPS_EXECUTED.THREAD / UOPS_ISSUED.ANY", "MetricGroup": "Cor;Pipeline", "MetricName": "tma_info_thread_execute_per_issue", - "PublicDescription": "The ratio of Executed- by Issued-Uops. Ratio > 1 suggests high rate of uop micro-fusions. Ratio < 1 suggest high rate of \"execute\" at rename stage" + "PublicDescription": "The ratio of Executed- by Issued-Uops. Ratio > 1 suggests high rate of uop micro-fusions. Ratio < 1 suggest high rate of \"execute\" at rename stage." }, { "BriefDescription": "Instructions Per Cycle (per Logical Processor)", @@ -1008,14 +1006,14 @@ "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / BR_INST_RETIRED.NEAR_TAKEN", "MetricGroup": "Branches;Fed;FetchBW", "MetricName": "tma_info_thread_uptb", - "MetricThreshold": "tma_info_thread_uptb < 4 * 1.5" + "MetricThreshold": "tma_info_thread_uptb < 6" }, { "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to Instruction TLB (ITLB) misses", - "MetricExpr": "(14 * ITLB_MISSES.STLB_HIT + cpu@ITLB_MISSES.WALK_DURATION\\,cmask\\=0x1@ + 7 * ITLB_MISSES.WALK_COMPLETED) / tma_info_thread_clks", + "MetricExpr": "(14 * ITLB_MISSES.STLB_HIT + cpu@ITLB_MISSES.WALK_DURATION\\,cmask\\=1@ + 7 * ITLB_MISSES.WALK_COMPLETED) / tma_info_thread_clks", "MetricGroup": "BigFootprint;BvBC;FetchLat;MemoryTLB;TopdownL3;tma_L3_group;tma_fetch_latency_group", "MetricName": "tma_itlb_misses", - "MetricThreshold": "tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricThreshold": "tma_itlb_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Instruction TLB (ITLB) misses. Sample with: ITLB_MISSES.WALK_COMPLETED", "ScaleUnit": "100%" }, @@ -1024,8 +1022,8 @@ "MetricExpr": "max((CYCLE_ACTIVITY.STALLS_MEM_ANY - CYCLE_ACTIVITY.STALLS_L1D_MISS) / tma_info_thread_clks, 0)", "MetricGroup": "CacheHits;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_issueL1;tma_issueMC;tma_memory_bound_group", "MetricName": "tma_l1_bound", - "MetricThreshold": "tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", - "PublicDescription": "This metric estimates how often the CPU was stalled without loads missing the L1 Data (L1D) cache. The L1D cache typically has the shortest latency. However; in certain cases like loads blocked on older stores; a load might suffer due to high latency even though it is being satisfied by the L1D. Another example is loads who miss in the TLB. These cases are characterized by execution unit stalls; while some non-completed demand load lives in the machine without having that demand load missing the L1 cache. Sample with: MEM_LOAD_UOPS_RETIRED.L1_HIT. Related metrics: tma_clears_resteers, tma_machine_clears, tma_microcode_sequencer, tma_ms_switches, tma_ports_utilized_1", + "MetricThreshold": "tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", + "PublicDescription": "This metric estimates how often the CPU was stalled without loads missing the L1 Data (L1D) cache. The L1D cache typically has the shortest latency. However; in certain cases like loads blocked on older stores; a load might suffer due to high latency even though it is being satisfied by the L1D. Another example is loads who miss in the TLB. These cases are characterized by execution unit stalls; while some non-completed demand load lives in the machine without having that demand load missing the L1 cache. Sample with: MEM_LOAD_UOPS_RETIRED.L1_HIT_PS. Related metrics: tma_clears_resteers, tma_machine_clears, tma_microcode_sequencer, tma_ms_switches, tma_ports_utilized_1", "ScaleUnit": "100%" }, { @@ -1033,8 +1031,8 @@ "MetricExpr": "(CYCLE_ACTIVITY.STALLS_L1D_MISS - CYCLE_ACTIVITY.STALLS_L2_MISS) / tma_info_thread_clks", "MetricGroup": "BvML;CacheHits;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_l2_bound", - "MetricThreshold": "tma_l2_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", - "PublicDescription": "This metric estimates how often the CPU was stalled due to L2 cache accesses by loads. Avoiding cache misses (i.e. L1 misses/L2 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_UOPS_RETIRED.L2_HIT", + "MetricThreshold": "tma_l2_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", + "PublicDescription": "This metric estimates how often the CPU was stalled due to L2 cache accesses by loads. Avoiding cache misses (i.e. L1 misses/L2 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_UOPS_RETIRED.L2_HIT_PS", "ScaleUnit": "100%" }, { @@ -1043,8 +1041,8 @@ "MetricExpr": "MEM_LOAD_UOPS_RETIRED.L3_HIT / (MEM_LOAD_UOPS_RETIRED.L3_HIT + 7 * MEM_LOAD_UOPS_RETIRED.L3_MISS) * CYCLE_ACTIVITY.STALLS_L2_MISS / tma_info_thread_clks", "MetricGroup": "CacheHits;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_l3_bound", - "MetricThreshold": "tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", - "PublicDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core. Avoiding cache misses (i.e. L2 misses/L3 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_UOPS_RETIRED.L3_HIT", + "MetricThreshold": "tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", + "PublicDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core. Avoiding cache misses (i.e. L2 misses/L3 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_UOPS_RETIRED.L3_HIT_PS", "ScaleUnit": "100%" }, { @@ -1053,8 +1051,8 @@ "MetricExpr": "41 * (MEM_LOAD_UOPS_RETIRED.L3_HIT * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.L3_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_L3_MISS_RETIRED.LOCAL_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_HITM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_FWD))) / tma_info_thread_clks", "MetricGroup": "BvML;MemoryLat;TopdownL4;tma_L4_group;tma_issueLat;tma_l3_bound_group", "MetricName": "tma_l3_hit_latency", - "MetricThreshold": "tma_l3_hit_latency > 0.1 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", - "PublicDescription": "This metric estimates fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited). Avoiding private cache misses (i.e. L2 misses/L3 hits) will improve the latency; reduce contention with sibling physical cores and increase performance. Note the value of this node may overlap with its siblings. Sample with: MEM_LOAD_UOPS_RETIRED.L3_HIT. Related metrics: tma_branch_resteers, tma_mem_latency, tma_store_latency", + "MetricThreshold": "tma_l3_hit_latency > 0.1 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric estimates fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited). Avoiding private cache misses (i.e. L2 misses/L3 hits) will improve the latency; reduce contention with sibling physical cores and increase performance. Note the value of this node may overlap with its siblings. Sample with: MEM_LOAD_UOPS_RETIRED.L3_HIT_PS. Related metrics: tma_mem_latency", "ScaleUnit": "100%" }, { @@ -1062,18 +1060,18 @@ "MetricExpr": "ILD_STALL.LCP / tma_info_thread_clks", "MetricGroup": "FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueFB", "MetricName": "tma_lcp", - "MetricThreshold": "tma_lcp > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", - "PublicDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs). Using proper compiler flags or Intel Compiler by default will certainly avoid this. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb", + "MetricThreshold": "tma_lcp > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", + "PublicDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs). Using proper compiler flags or Intel Compiler by default will certainly avoid this. #Link: Optimization Guide about LCP BKMs. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations , instructions that require no more than one uop (micro-operation)", + "BriefDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation)", "MetricExpr": "tma_retiring - tma_heavy_operations", "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_light_operations", "MetricThreshold": "tma_light_operations > 0.6", "MetricgroupNoGroup": "TopdownL2", - "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations , instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized code running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. ([ICL+] Note this may undercount due to approximation using indirect events; [ADL+] .). Sample with: INST_RETIRED.PREC_DIST", + "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized code running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. ([ICL+] Note this may undercount due to approximation using indirect events; [ADL+] .). Sample with: INST_RETIRED.PREC_DIST", "ScaleUnit": "100%" }, { @@ -1091,8 +1089,8 @@ "MetricExpr": "200 * (MEM_LOAD_UOPS_L3_MISS_RETIRED.LOCAL_DRAM * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.L3_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_L3_MISS_RETIRED.LOCAL_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_HITM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_FWD))) / tma_info_thread_clks", "MetricGroup": "Server;TopdownL5;tma_L5_group;tma_mem_latency_group", "MetricName": "tma_local_mem", - "MetricThreshold": "tma_local_mem > 0.1 & tma_mem_latency > 0.1 & tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", - "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from local memory. Caching will improve the latency and increase performance. Sample with: MEM_LOAD_UOPS_L3_MISS_RETIRED.LOCAL_DRAM", + "MetricThreshold": "tma_local_mem > 0.1 & (tma_mem_latency > 0.1 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))", + "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from local memory. Caching will improve the latency and increase performance. Sample with: MEM_LOAD_UOPS_L3_MISS_RETIRED.LOCAL_DRAM_PS", "ScaleUnit": "100%" }, { @@ -1101,8 +1099,8 @@ "MetricExpr": "MEM_UOPS_RETIRED.LOCK_LOADS / MEM_UOPS_RETIRED.ALL_STORES * min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO) / tma_info_thread_clks", "MetricGroup": "LockCont;Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_l1_bound_group", "MetricName": "tma_lock_latency", - "MetricThreshold": "tma_lock_latency > 0.2 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", - "PublicDescription": "This metric represents fraction of cycles the CPU spent handling cache misses due to lock operations. Due to the microarchitecture handling of locks; they are classified as L1_Bound regardless of what memory source satisfied them. Sample with: MEM_UOPS_RETIRED.LOCK_LOADS. Related metrics: tma_store_latency", + "MetricThreshold": "tma_lock_latency > 0.2 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric represents fraction of cycles the CPU spent handling cache misses due to lock operations. Due to the microarchitecture handling of locks; they are classified as L1_Bound regardless of what memory source satisfied them. Sample with: MEM_UOPS_RETIRED.LOCK_LOADS_PS. Related metrics: tma_store_latency", "ScaleUnit": "100%" }, { @@ -1118,10 +1116,10 @@ }, { "BriefDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory - DRAM ([SPR-HBM] and/or HBM)", - "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, cpu@OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD\\,cmask\\=0x4@) / tma_info_thread_clks", + "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, cpu@OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD\\,cmask\\=4@) / tma_info_thread_clks", "MetricGroup": "BvMB;MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueBW", "MetricName": "tma_mem_bandwidth", - "MetricThreshold": "tma_mem_bandwidth > 0.2 & tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_mem_bandwidth > 0.2 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", "PublicDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory - DRAM ([SPR-HBM] and/or HBM). The underlying heuristic assumes that a similar off-core traffic is generated by all IA cores. This metric does not aggregate non-data-read requests by this logical processor; requests from other IA Logical Processors/Physical Cores/sockets; or other non-IA devices like GPU; hence the maximum external memory bandwidth limits may or may not be approached when this metric is flagged (see Uncore counters for that). Related metrics: tma_fb_full, tma_info_system_dram_bw_use, tma_sq_full", "ScaleUnit": "100%" }, @@ -1130,7 +1128,7 @@ "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD) / tma_info_thread_clks - tma_mem_bandwidth", "MetricGroup": "BvML;MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueLat", "MetricName": "tma_mem_latency", - "MetricThreshold": "tma_mem_latency > 0.1 & tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_mem_latency > 0.1 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", "PublicDescription": "This metric estimates fraction of cycles where the performance was likely hurt due to latency from external memory - DRAM ([SPR-HBM] and/or HBM). This metric does not aggregate requests from other Logical Processors/Physical Cores/sockets (see Uncore counters for that). Related metrics: tma_l3_hit_latency", "ScaleUnit": "100%" }, @@ -1142,7 +1140,7 @@ "MetricName": "tma_memory_bound", "MetricThreshold": "tma_memory_bound > 0.2 & tma_backend_bound > 0.2", "MetricgroupNoGroup": "TopdownL2", - "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck. Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two)", + "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck. Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two).", "ScaleUnit": "100%" }, { @@ -1159,8 +1157,8 @@ "MetricExpr": "BR_MISP_RETIRED.ALL_BRANCHES * tma_branch_resteers / (BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT + BACLEARS.ANY)", "MetricGroup": "BadSpec;BrMispredicts;BvMP;TopdownL4;tma_L4_group;tma_branch_resteers_group;tma_issueBM", "MetricName": "tma_mispredicts_resteers", - "MetricThreshold": "tma_mispredicts_resteers > 0.05 & tma_branch_resteers > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", - "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Branch Misprediction at execution stage. Related metrics: tma_branch_mispredicts", + "MetricThreshold": "tma_mispredicts_resteers > 0.05 & (tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Branch Misprediction at execution stage. Related metrics: tma_branch_mispredicts, tma_info_bad_spec_branch_misprediction_cost", "ScaleUnit": "100%" }, { @@ -1169,7 +1167,7 @@ "MetricGroup": "DSBmiss;FetchBW;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group", "MetricName": "tma_mite", "MetricThreshold": "tma_mite > 0.1 & tma_fetch_bandwidth > 0.2", - "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to the MITE pipeline (the legacy decode pipeline). This pipeline is used for code that was not pre-cached in the DSB or LSD. For example; inefficiencies due to asymmetric decoders; use of long immediate or LCP can manifest as MITE fetch bandwidth bottleneck", + "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to the MITE pipeline (the legacy decode pipeline). This pipeline is used for code that was not pre-cached in the DSB or LSD. For example; inefficiencies due to asymmetric decoders; use of long immediate or LCP can manifest as MITE fetch bandwidth bottleneck.", "ScaleUnit": "100%" }, { @@ -1177,8 +1175,8 @@ "MetricExpr": "2 * IDQ.MS_SWITCHES / tma_info_thread_clks", "MetricGroup": "FetchLat;MicroSeq;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueMC;tma_issueMS;tma_issueMV;tma_issueSO", "MetricName": "tma_ms_switches", - "MetricThreshold": "tma_ms_switches > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", - "PublicDescription": "This metric estimates the fraction of cycles when the CPU was stalled due to switches of uop delivery to the Microcode Sequencer (MS). Commonly used instructions are optimized for delivery by the DSB (decoded i-cache) or MITE (legacy instruction decode) pipelines. Certain operations cannot be handled natively by the execution pipeline; and must be performed by microcode (small programs injected into the execution stream). Switching to the MS too often can negatively impact performance. The MS is designated to deliver long uop flows required by CISC instructions like CPUID; or uncommon conditions like Floating Point Assists when dealing with Denormals. Sample with: IDQ.MS_SWITCHES. Related metrics: tma_clears_resteers, tma_l1_bound, tma_machine_clears, tma_microcode_sequencer", + "MetricThreshold": "tma_ms_switches > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", + "PublicDescription": "This metric estimates the fraction of cycles when the CPU was stalled due to switches of uop delivery to the Microcode Sequencer (MS). Commonly used instructions are optimized for delivery by the DSB (decoded i-cache) or MITE (legacy instruction decode) pipelines. Certain operations cannot be handled natively by the execution pipeline; and must be performed by microcode (small programs injected into the execution stream). Switching to the MS too often can negatively impact performance. The MS is designated to deliver long uop flows required by CISC instructions like CPUID; or uncommon conditions like Floating Point Assists when dealing with Denormals. Sample with: IDQ.MS_SWITCHES. Related metrics: tma_clears_resteers, tma_l1_bound, tma_machine_clears, tma_microcode_sequencer, tma_mixing_vectors, tma_serializing_operation", "ScaleUnit": "100%" }, { @@ -1187,7 +1185,7 @@ "MetricGroup": "Compute;TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P", "MetricName": "tma_port_0", "MetricThreshold": "tma_port_0 > 0.6", - "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 0 ([SNB+] ALU; [HSW+] ALU and 2nd branch). Sample with: UOPS_DISPATCHED_PORT.PORT_0. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", + "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 0 ([SNB+] ALU; [HSW+] ALU and 2nd branch). Sample with: UOPS_DISPATCHED.PORT_0. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%" }, { @@ -1196,7 +1194,7 @@ "MetricGroup": "TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P", "MetricName": "tma_port_1", "MetricThreshold": "tma_port_1 > 0.6", - "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 1 (ALU). Sample with: UOPS_DISPATCHED_PORT.PORT_1. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_port_0, tma_port_5, tma_port_6, tma_ports_utilized_2", + "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 1 (ALU). Sample with: UOPS_DISPATCHED.PORT_1. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_5, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%" }, { @@ -1232,7 +1230,7 @@ "MetricGroup": "TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P", "MetricName": "tma_port_5", "MetricThreshold": "tma_port_5 > 0.6", - "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 5 ([SNB+] Branches and ALU; [HSW+] ALU). Sample with: UOPS_DISPATCHED_PORT.PORT_5. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_port_0, tma_port_1, tma_port_6, tma_ports_utilized_2", + "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 5 ([SNB+] Branches and ALU; [HSW+] ALU). Sample with: UOPS_DISPATCHED.PORT_5. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%" }, { @@ -1241,7 +1239,7 @@ "MetricGroup": "TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P", "MetricName": "tma_port_6", "MetricThreshold": "tma_port_6 > 0.6", - "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 6 ([HSW+] Primary Branch and simple ALU). Sample with: UOPS_DISPATCHED_PORT.PORT_1. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_ports_utilized_2", + "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 6 ([HSW+] Primary Branch and simple ALU). Sample with: UOPS_DISPATCHED.PORT_1. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_ports_utilized_2", "ScaleUnit": "100%" }, { @@ -1259,43 +1257,43 @@ "MetricExpr": "(CYCLE_ACTIVITY.STALLS_TOTAL + UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC - (UOPS_EXECUTED.CYCLES_GE_3_UOPS_EXEC if tma_info_thread_ipc > 1.8 else UOPS_EXECUTED.CYCLES_GE_2_UOPS_EXEC) - (RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else 0) + RESOURCE_STALLS.SB - RESOURCE_STALLS.SB - CYCLE_ACTIVITY.STALLS_MEM_ANY) / tma_info_thread_clks", "MetricGroup": "PortsUtil;TopdownL3;tma_L3_group;tma_core_bound_group", "MetricName": "tma_ports_utilization", - "MetricThreshold": "tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", - "PublicDescription": "This metric estimates fraction of cycles the CPU performance was potentially limited due to Core computation issues (non divider-related). Two distinct categories can be attributed into this metric: (1) heavy data-dependency among contiguous instructions would manifest in this metric - such cases are often referred to as low Instruction Level Parallelism (ILP). (2) Contention on some hardware execution unit other than Divider. For example; when there are too many multiply operations", + "MetricThreshold": "tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)", + "PublicDescription": "This metric estimates fraction of cycles the CPU performance was potentially limited due to Core computation issues (non divider-related). Two distinct categories can be attributed into this metric: (1) heavy data-dependency among contiguous instructions would manifest in this metric - such cases are often referred to as low Instruction Level Parallelism (ILP). (2) Contention on some hardware execution unit other than Divider. For example; when there are too many multiply operations.", "ScaleUnit": "100%" }, { "BriefDescription": "This metric represents fraction of cycles CPU executed no uops on any execution port (Logical Processor cycles since ICL, Physical Core cycles otherwise)", - "MetricExpr": "(cpu@UOPS_EXECUTED.CORE\\,inv\\=0x1\\,cmask\\=0x1@ / 2 if #SMT_on else CYCLE_ACTIVITY.STALLS_TOTAL - (RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else 0)) / tma_info_core_core_clks", + "MetricExpr": "(cpu@UOPS_EXECUTED.CORE\\,inv\\,cmask\\=1@ / 2 if #SMT_on else (CYCLE_ACTIVITY.STALLS_TOTAL - (RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else 0)) / tma_info_core_core_clks)", "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group", "MetricName": "tma_ports_utilized_0", - "MetricThreshold": "tma_ports_utilized_0 > 0.2 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", - "PublicDescription": "This metric represents fraction of cycles CPU executed no uops on any execution port (Logical Processor cycles since ICL, Physical Core cycles otherwise). Long-latency instructions like divides may contribute to this metric", + "MetricThreshold": "tma_ports_utilized_0 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric represents fraction of cycles CPU executed no uops on any execution port (Logical Processor cycles since ICL, Physical Core cycles otherwise). Long-latency instructions like divides may contribute to this metric.", "ScaleUnit": "100%" }, { "BriefDescription": "This metric represents fraction of cycles where the CPU executed total of 1 uop per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise)", - "MetricExpr": "((cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x1@ - cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x2@) / 2 if #SMT_on else UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC - UOPS_EXECUTED.CYCLES_GE_2_UOPS_EXEC) / tma_info_core_core_clks", + "MetricExpr": "((cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ - cpu@UOPS_EXECUTED.CORE\\,cmask\\=2@) / 2 if #SMT_on else (UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC - UOPS_EXECUTED.CYCLES_GE_2_UOPS_EXEC) / tma_info_core_core_clks)", "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_issueL1;tma_ports_utilization_group", "MetricName": "tma_ports_utilized_1", - "MetricThreshold": "tma_ports_utilized_1 > 0.2 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_ports_utilized_1 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", "PublicDescription": "This metric represents fraction of cycles where the CPU executed total of 1 uop per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise). This can be due to heavy data-dependency among software instructions; or over oversubscribing a particular hardware resource. In some other cases with high 1_Port_Utilized and L1_Bound; this metric can point to L1 data-cache latency bottleneck that may not necessarily manifest with complete execution starvation (due to the short L1 latency e.g. walking a linked list) - looking at the assembly can be helpful. Related metrics: tma_l1_bound", "ScaleUnit": "100%" }, { "BriefDescription": "This metric represents fraction of cycles CPU executed total of 2 uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise)", - "MetricExpr": "((cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x2@ - cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x3@) / 2 if #SMT_on else UOPS_EXECUTED.CYCLES_GE_2_UOPS_EXEC - UOPS_EXECUTED.CYCLES_GE_3_UOPS_EXEC) / tma_info_core_core_clks", + "MetricExpr": "((cpu@UOPS_EXECUTED.CORE\\,cmask\\=2@ - cpu@UOPS_EXECUTED.CORE\\,cmask\\=3@) / 2 if #SMT_on else (UOPS_EXECUTED.CYCLES_GE_2_UOPS_EXEC - UOPS_EXECUTED.CYCLES_GE_3_UOPS_EXEC) / tma_info_core_core_clks)", "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_issue2P;tma_ports_utilization_group", "MetricName": "tma_ports_utilized_2", - "MetricThreshold": "tma_ports_utilized_2 > 0.15 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", - "PublicDescription": "This metric represents fraction of cycles CPU executed total of 2 uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise). Loop Vectorization -most compilers feature auto-Vectorization options today- reduces pressure on the execution ports as multiple elements are calculated with same uop. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_port_6", + "MetricThreshold": "tma_ports_utilized_2 > 0.15 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric represents fraction of cycles CPU executed total of 2 uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise). Loop Vectorization -most compilers feature auto-Vectorization options today- reduces pressure on the execution ports as multiple elements are calculated with same uop. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of cycles CPU executed total of 3 or more uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise)", - "MetricExpr": "(cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x3@ / 2 if #SMT_on else UOPS_EXECUTED.CYCLES_GE_3_UOPS_EXEC) / tma_info_core_core_clks", + "BriefDescription": "This metric represents fraction of cycles CPU executed total of 3 or more uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise).", + "MetricExpr": "(cpu@UOPS_EXECUTED.CORE\\,cmask\\=3@ / 2 if #SMT_on else UOPS_EXECUTED.CYCLES_GE_3_UOPS_EXEC) / tma_info_core_core_clks", "MetricGroup": "BvCB;PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group", "MetricName": "tma_ports_utilized_3m", - "MetricThreshold": "tma_ports_utilized_3m > 0.4 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_ports_utilized_3m > 0.4 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", "ScaleUnit": "100%" }, { @@ -1304,8 +1302,8 @@ "MetricExpr": "(200 * (MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_HITM * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.L3_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_L3_MISS_RETIRED.LOCAL_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_HITM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_FWD))) + 180 * (MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_FWD * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.L3_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_L3_MISS_RETIRED.LOCAL_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_HITM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_FWD)))) / tma_info_thread_clks", "MetricGroup": "Offcore;Server;Snoop;TopdownL5;tma_L5_group;tma_issueSyncxn;tma_mem_latency_group", "MetricName": "tma_remote_cache", - "MetricThreshold": "tma_remote_cache > 0.05 & tma_mem_latency > 0.1 & tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", - "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from remote cache in other sockets including synchronizations issues. This is caused often due to non-optimal NUMA allocations. Sample with: MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_HITM, MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_FWD. Related metrics: tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_machine_clears", + "MetricThreshold": "tma_remote_cache > 0.05 & (tma_mem_latency > 0.1 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))", + "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from remote cache in other sockets including synchronizations issues. This is caused often due to non-optimal NUMA allocations. #link to NUMA article. Sample with: MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_HITM_PS;MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_FWD_PS. Related metrics: tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_machine_clears", "ScaleUnit": "100%" }, { @@ -1313,8 +1311,8 @@ "MetricExpr": "310 * (MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_DRAM * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.L3_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_L3_MISS_RETIRED.LOCAL_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_HITM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_FWD))) / tma_info_thread_clks", "MetricGroup": "Server;Snoop;TopdownL5;tma_L5_group;tma_mem_latency_group", "MetricName": "tma_remote_mem", - "MetricThreshold": "tma_remote_mem > 0.1 & tma_mem_latency > 0.1 & tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", - "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from remote memory. This is caused often due to non-optimal NUMA allocations. Sample with: MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_DRAM", + "MetricThreshold": "tma_remote_mem > 0.1 & (tma_mem_latency > 0.1 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))", + "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from remote memory. This is caused often due to non-optimal NUMA allocations. #link to NUMA article. Sample with: MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_DRAM_PS", "ScaleUnit": "100%" }, { @@ -1334,7 +1332,7 @@ "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group", "MetricName": "tma_split_loads", "MetricThreshold": "tma_split_loads > 0.3", - "PublicDescription": "This metric estimates fraction of cycles handling memory load split accesses - load that cross 64-byte cache line boundary. Sample with: MEM_UOPS_RETIRED.SPLIT_LOADS", + "PublicDescription": "This metric estimates fraction of cycles handling memory load split accesses - load that cross 64-byte cache line boundary. Sample with: MEM_UOPS_RETIRED.SPLIT_LOADS_PS", "ScaleUnit": "100%" }, { @@ -1342,8 +1340,8 @@ "MetricExpr": "2 * MEM_UOPS_RETIRED.SPLIT_STORES / tma_info_core_core_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_issueSpSt;tma_store_bound_group", "MetricName": "tma_split_stores", - "MetricThreshold": "tma_split_stores > 0.2 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", - "PublicDescription": "This metric represents rate of split store accesses. Consider aligning your data to the 64-byte cache line granularity. Sample with: MEM_UOPS_RETIRED.SPLIT_STORES. Related metrics: tma_port_4", + "MetricThreshold": "tma_split_stores > 0.2 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric represents rate of split store accesses. Consider aligning your data to the 64-byte cache line granularity. Sample with: MEM_UOPS_RETIRED.SPLIT_STORES_PS. Related metrics: tma_port_4", "ScaleUnit": "100%" }, { @@ -1351,7 +1349,7 @@ "MetricExpr": "(OFFCORE_REQUESTS_BUFFER.SQ_FULL / 2 if #SMT_on else OFFCORE_REQUESTS_BUFFER.SQ_FULL) / tma_info_core_core_clks", "MetricGroup": "BvMB;MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_issueBW;tma_l3_bound_group", "MetricName": "tma_sq_full", - "MetricThreshold": "tma_sq_full > 0.3 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_sq_full > 0.3 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", "PublicDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors). Related metrics: tma_fb_full, tma_info_system_dram_bw_use, tma_mem_bandwidth", "ScaleUnit": "100%" }, @@ -1360,8 +1358,8 @@ "MetricExpr": "RESOURCE_STALLS.SB / tma_info_thread_clks", "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_store_bound", - "MetricThreshold": "tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", - "PublicDescription": "This metric estimates how often CPU was stalled due to RFO store memory accesses; RFO store issue a read-for-ownership request before the write. Even though store accesses do not typically stall out-of-order CPUs; there are few cases where stores can lead to actual stalls. This metric will be flagged should RFO stores be a bottleneck. Sample with: MEM_UOPS_RETIRED.ALL_STORES", + "MetricThreshold": "tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", + "PublicDescription": "This metric estimates how often CPU was stalled due to RFO store memory accesses; RFO store issue a read-for-ownership request before the write. Even though store accesses do not typically stall out-of-order CPUs; there are few cases where stores can lead to actual stalls. This metric will be flagged should RFO stores be a bottleneck. Sample with: MEM_UOPS_RETIRED.ALL_STORES_PS", "ScaleUnit": "100%" }, { @@ -1369,8 +1367,8 @@ "MetricExpr": "13 * LD_BLOCKS.STORE_FORWARD / tma_info_thread_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group", "MetricName": "tma_store_fwd_blk", - "MetricThreshold": "tma_store_fwd_blk > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", - "PublicDescription": "This metric roughly estimates fraction of cycles when the memory subsystem had loads blocked since they could not forward data from earlier (in program order) overlapping stores. To streamline memory operations in the pipeline; a load can avoid waiting for memory if a prior in-flight store is writing the data that the load wants to read (store forwarding process). However; in some cases the load may be blocked for a significant time pending the store forward. For example; when the prior store is writing a smaller region than the load is reading", + "MetricThreshold": "tma_store_fwd_blk > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric roughly estimates fraction of cycles when the memory subsystem had loads blocked since they could not forward data from earlier (in program order) overlapping stores. To streamline memory operations in the pipeline; a load can avoid waiting for memory if a prior in-flight store is writing the data that the load wants to read (store forwarding process). However; in some cases the load may be blocked for a significant time pending the store forward. For example; when the prior store is writing a smaller region than the load is reading.", "ScaleUnit": "100%" }, { @@ -1379,8 +1377,8 @@ "MetricExpr": "(L2_RQSTS.RFO_HIT * 9 * (1 - MEM_UOPS_RETIRED.LOCK_LOADS / MEM_UOPS_RETIRED.ALL_STORES) + (1 - MEM_UOPS_RETIRED.LOCK_LOADS / MEM_UOPS_RETIRED.ALL_STORES) * min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO)) / tma_info_thread_clks", "MetricGroup": "BvML;LockCont;MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_issueSL;tma_store_bound_group", "MetricName": "tma_store_latency", - "MetricThreshold": "tma_store_latency > 0.1 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", - "PublicDescription": "This metric estimates fraction of cycles the CPU spent handling L1D store misses. Store accesses usually less impact out-of-order core performance; however; holding resources for longer time can lead into undesired implications (e.g. contention on L1D fill-buffer entries - see FB_Full). Related metrics: tma_branch_resteers, tma_fb_full, tma_l3_hit_latency, tma_lock_latency", + "MetricThreshold": "tma_store_latency > 0.1 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric estimates fraction of cycles the CPU spent handling L1D store misses. Store accesses usually less impact out-of-order core performance; however; holding resources for longer time can lead into undesired implications (e.g. contention on L1D fill-buffer entries - see FB_Full). Related metrics: tma_fb_full, tma_lock_latency", "ScaleUnit": "100%" }, { @@ -1396,7 +1394,7 @@ "MetricExpr": "tma_branch_resteers - tma_mispredicts_resteers - tma_clears_resteers", "MetricGroup": "BigFootprint;BvBC;FetchLat;TopdownL4;tma_L4_group;tma_branch_resteers_group", "MetricName": "tma_unknown_branches", - "MetricThreshold": "tma_unknown_branches > 0.05 & tma_branch_resteers > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricThreshold": "tma_unknown_branches > 0.05 & (tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))", "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to new branch address clears. These are fetched branches the Branch Prediction Unit was unable to recognize (e.g. first time the branch is fetched or hitting BTB capacity limit) hence called Unknown Branches. Sample with: BACLEARS.ANY", "ScaleUnit": "100%" }, @@ -1405,8 +1403,8 @@ "MetricExpr": "INST_RETIRED.X87 * tma_info_thread_uoppi / UOPS_RETIRED.RETIRE_SLOTS", "MetricGroup": "Compute;TopdownL4;tma_L4_group;tma_fp_arith_group", "MetricName": "tma_x87_use", - "MetricThreshold": "tma_x87_use > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6", - "PublicDescription": "This metric serves as an approximation of legacy x87 usage. It accounts for instructions beyond X87 FP arithmetic operations; hence may be used as a thermometer to avoid X87 high usage and preferably upgrade to modern ISA. See Tip under Tuning Hint", + "MetricThreshold": "tma_x87_use > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6)", + "PublicDescription": "This metric serves as an approximation of legacy x87 usage. It accounts for instructions beyond X87 FP arithmetic operations; hence may be used as a thermometer to avoid X87 high usage and preferably upgrade to modern ISA. See Tip under Tuning Hint.", "ScaleUnit": "100%" }, { diff --git a/tools/perf/pmu-events/arch/x86/cascadelakex/cache.json b/tools/perf/pmu-events/arch/x86/cascadelakex/cache.json index 8bad700ff8ea..d113c14aa7c9 100644 --- a/tools/perf/pmu-events/arch/x86/cascadelakex/cache.json +++ b/tools/perf/pmu-events/arch/x86/cascadelakex/cache.json @@ -1,5 +1,79 @@ [ { + "BriefDescription": "CORE_SNOOP_RESPONSE.RSP_IFWDFE", + "Counter": "0,1,2,3", + "EventCode": "0xEF", + "EventName": "CORE_SNOOP_RESPONSE.RSP_IFWDFE", + "SampleAfterValue": "2000003", + "UMask": "0x20" + }, + { + "BriefDescription": "CORE_SNOOP_RESPONSE.RSP_IFWDM", + "Counter": "0,1,2,3", + "EventCode": "0xEF", + "EventName": "CORE_SNOOP_RESPONSE.RSP_IFWDM", + "SampleAfterValue": "2000003", + "UMask": "0x10" + }, + { + "BriefDescription": "CORE_SNOOP_RESPONSE.RSP_IHITFSE", + "Counter": "0,1,2,3", + "EventCode": "0xEF", + "EventName": "CORE_SNOOP_RESPONSE.RSP_IHITFSE", + "SampleAfterValue": "2000003", + "UMask": "0x2" + }, + { + "BriefDescription": "CORE_SNOOP_RESPONSE.RSP_IHITI", + "Counter": "0,1,2,3", + "EventCode": "0xEF", + "EventName": "CORE_SNOOP_RESPONSE.RSP_IHITI", + "SampleAfterValue": "2000003", + "UMask": "0x1" + }, + { + "BriefDescription": "CORE_SNOOP_RESPONSE.RSP_SFWDFE", + "Counter": "0,1,2,3", + "EventCode": "0xEF", + "EventName": "CORE_SNOOP_RESPONSE.RSP_SFWDFE", + "SampleAfterValue": "2000003", + "UMask": "0x40" + }, + { + "BriefDescription": "CORE_SNOOP_RESPONSE.RSP_SFWDM", + "Counter": "0,1,2,3", + "EventCode": "0xEF", + "EventName": "CORE_SNOOP_RESPONSE.RSP_SFWDM", + "SampleAfterValue": "2000003", + "UMask": "0x8" + }, + { + "BriefDescription": "CORE_SNOOP_RESPONSE.RSP_SHITFSE", + "Counter": "0,1,2,3", + "EventCode": "0xEF", + "EventName": "CORE_SNOOP_RESPONSE.RSP_SHITFSE", + "SampleAfterValue": "2000003", + "UMask": "0x4" + }, + { + "BriefDescription": "Counts number of cache lines that are dropped and not written back to L3 as they are deemed to be less likely to be reused shortly", + "Counter": "0,1,2,3", + "EventCode": "0xFE", + "EventName": "IDI_MISC.WB_DOWNGRADE", + "PublicDescription": "Counts number of cache lines that are dropped and not written back to L3 as they are deemed to be less likely to be reused shortly.", + "SampleAfterValue": "100003", + "UMask": "0x4" + }, + { + "BriefDescription": "Counts number of cache lines that are allocated and written back to L3 with the intention that they are more likely to be reused shortly", + "Counter": "0,1,2,3", + "EventCode": "0xFE", + "EventName": "IDI_MISC.WB_UPGRADE", + "PublicDescription": "Counts number of cache lines that are allocated and written back to L3 with the intention that they are more likely to be reused shortly.", + "SampleAfterValue": "100003", + "UMask": "0x2" + }, + { "BriefDescription": "L1D data line replacements", "Counter": "0,1,2,3", "EventCode": "0x51", @@ -2344,6 +2418,16 @@ "UMask": "0x1" }, { + "BriefDescription": "Counts all demand code reads have any response type.", + "Counter": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OCR.DEMAND_CODE_RD.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x10004", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { "BriefDescription": "Counts all demand code reads OCR.DEMAND_CODE_RD.L3_HIT.ANY_SNOOP OCR.DEMAND_CODE_RD.L3_HIT.ANY_SNOOP", "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -2704,6 +2788,116 @@ "UMask": "0x1" }, { + "BriefDescription": "Counts all demand code reads OCR.DEMAND_CODE_RD.PMM_HIT_LOCAL_PMM.ANY_SNOOP", + "Counter": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OCR.DEMAND_CODE_RD.PMM_HIT_LOCAL_PMM.ANY_SNOOP", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x3F80400004", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts all demand code reads OCR.DEMAND_CODE_RD.PMM_HIT_LOCAL_PMM.SNOOP_NONE", + "Counter": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OCR.DEMAND_CODE_RD.PMM_HIT_LOCAL_PMM.SNOOP_NONE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x80400004", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts all demand code reads OCR.DEMAND_CODE_RD.PMM_HIT_LOCAL_PMM.SNOOP_NOT_NEEDED", + "Counter": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OCR.DEMAND_CODE_RD.PMM_HIT_LOCAL_PMM.SNOOP_NOT_NEEDED", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x100400004", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts all demand code reads OCR.DEMAND_CODE_RD.SUPPLIER_NONE.ANY_SNOOP", + "Counter": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OCR.DEMAND_CODE_RD.SUPPLIER_NONE.ANY_SNOOP", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x3F80020004", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts all demand code reads OCR.DEMAND_CODE_RD.SUPPLIER_NONE.HITM_OTHER_CORE", + "Counter": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OCR.DEMAND_CODE_RD.SUPPLIER_NONE.HITM_OTHER_CORE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x1000020004", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts all demand code reads OCR.DEMAND_CODE_RD.SUPPLIER_NONE.HIT_OTHER_CORE_FWD", + "Counter": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OCR.DEMAND_CODE_RD.SUPPLIER_NONE.HIT_OTHER_CORE_FWD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x800020004", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts all demand code reads OCR.DEMAND_CODE_RD.SUPPLIER_NONE.HIT_OTHER_CORE_NO_FWD", + "Counter": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OCR.DEMAND_CODE_RD.SUPPLIER_NONE.HIT_OTHER_CORE_NO_FWD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x400020004", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts all demand code reads OCR.DEMAND_CODE_RD.SUPPLIER_NONE.NO_SNOOP_NEEDED", + "Counter": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OCR.DEMAND_CODE_RD.SUPPLIER_NONE.NO_SNOOP_NEEDED", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x100020004", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts all demand code reads", + "Counter": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OCR.DEMAND_CODE_RD.SUPPLIER_NONE.SNOOP_MISS", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x200020004", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts all demand code reads", + "Counter": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OCR.DEMAND_CODE_RD.SUPPLIER_NONE.SNOOP_NONE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x80020004", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts demand data reads have any response type.", + "Counter": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OCR.DEMAND_DATA_RD.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x10001", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { "BriefDescription": "Counts demand data reads OCR.DEMAND_DATA_RD.L3_HIT.ANY_SNOOP OCR.DEMAND_DATA_RD.L3_HIT.ANY_SNOOP", "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -3064,6 +3258,116 @@ "UMask": "0x1" }, { + "BriefDescription": "Counts demand data reads OCR.DEMAND_DATA_RD.PMM_HIT_LOCAL_PMM.ANY_SNOOP", + "Counter": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OCR.DEMAND_DATA_RD.PMM_HIT_LOCAL_PMM.ANY_SNOOP", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x3F80400001", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts demand data reads OCR.DEMAND_DATA_RD.PMM_HIT_LOCAL_PMM.SNOOP_NONE", + "Counter": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OCR.DEMAND_DATA_RD.PMM_HIT_LOCAL_PMM.SNOOP_NONE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x80400001", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts demand data reads OCR.DEMAND_DATA_RD.PMM_HIT_LOCAL_PMM.SNOOP_NOT_NEEDED", + "Counter": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OCR.DEMAND_DATA_RD.PMM_HIT_LOCAL_PMM.SNOOP_NOT_NEEDED", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x100400001", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts demand data reads OCR.DEMAND_DATA_RD.SUPPLIER_NONE.ANY_SNOOP", + "Counter": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OCR.DEMAND_DATA_RD.SUPPLIER_NONE.ANY_SNOOP", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x3F80020001", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts demand data reads OCR.DEMAND_DATA_RD.SUPPLIER_NONE.HITM_OTHER_CORE", + "Counter": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OCR.DEMAND_DATA_RD.SUPPLIER_NONE.HITM_OTHER_CORE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x1000020001", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts demand data reads OCR.DEMAND_DATA_RD.SUPPLIER_NONE.HIT_OTHER_CORE_FWD", + "Counter": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OCR.DEMAND_DATA_RD.SUPPLIER_NONE.HIT_OTHER_CORE_FWD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x800020001", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts demand data reads OCR.DEMAND_DATA_RD.SUPPLIER_NONE.HIT_OTHER_CORE_NO_FWD", + "Counter": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OCR.DEMAND_DATA_RD.SUPPLIER_NONE.HIT_OTHER_CORE_NO_FWD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x400020001", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts demand data reads OCR.DEMAND_DATA_RD.SUPPLIER_NONE.NO_SNOOP_NEEDED", + "Counter": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OCR.DEMAND_DATA_RD.SUPPLIER_NONE.NO_SNOOP_NEEDED", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x100020001", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts demand data reads", + "Counter": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OCR.DEMAND_DATA_RD.SUPPLIER_NONE.SNOOP_MISS", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x200020001", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts demand data reads", + "Counter": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OCR.DEMAND_DATA_RD.SUPPLIER_NONE.SNOOP_NONE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x80020001", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts all demand data writes (RFOs) have any response type.", + "Counter": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OCR.DEMAND_RFO.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x10002", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { "BriefDescription": "Counts all demand data writes (RFOs) OCR.DEMAND_RFO.L3_HIT.ANY_SNOOP OCR.DEMAND_RFO.L3_HIT.ANY_SNOOP", "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -3424,6 +3728,106 @@ "UMask": "0x1" }, { + "BriefDescription": "Counts all demand data writes (RFOs) OCR.DEMAND_RFO.PMM_HIT_LOCAL_PMM.ANY_SNOOP", + "Counter": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OCR.DEMAND_RFO.PMM_HIT_LOCAL_PMM.ANY_SNOOP", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x3F80400002", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts all demand data writes (RFOs) OCR.DEMAND_RFO.PMM_HIT_LOCAL_PMM.SNOOP_NONE", + "Counter": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OCR.DEMAND_RFO.PMM_HIT_LOCAL_PMM.SNOOP_NONE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x80400002", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts all demand data writes (RFOs) OCR.DEMAND_RFO.PMM_HIT_LOCAL_PMM.SNOOP_NOT_NEEDED", + "Counter": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OCR.DEMAND_RFO.PMM_HIT_LOCAL_PMM.SNOOP_NOT_NEEDED", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x100400002", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts all demand data writes (RFOs) OCR.DEMAND_RFO.SUPPLIER_NONE.ANY_SNOOP", + "Counter": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OCR.DEMAND_RFO.SUPPLIER_NONE.ANY_SNOOP", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x3F80020002", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts all demand data writes (RFOs) OCR.DEMAND_RFO.SUPPLIER_NONE.HITM_OTHER_CORE", + "Counter": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OCR.DEMAND_RFO.SUPPLIER_NONE.HITM_OTHER_CORE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x1000020002", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts all demand data writes (RFOs) OCR.DEMAND_RFO.SUPPLIER_NONE.HIT_OTHER_CORE_FWD", + "Counter": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OCR.DEMAND_RFO.SUPPLIER_NONE.HIT_OTHER_CORE_FWD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x800020002", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts all demand data writes (RFOs) OCR.DEMAND_RFO.SUPPLIER_NONE.HIT_OTHER_CORE_NO_FWD", + "Counter": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OCR.DEMAND_RFO.SUPPLIER_NONE.HIT_OTHER_CORE_NO_FWD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x400020002", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts all demand data writes (RFOs) OCR.DEMAND_RFO.SUPPLIER_NONE.NO_SNOOP_NEEDED", + "Counter": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OCR.DEMAND_RFO.SUPPLIER_NONE.NO_SNOOP_NEEDED", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x100020002", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts all demand data writes (RFOs)", + "Counter": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OCR.DEMAND_RFO.SUPPLIER_NONE.SNOOP_MISS", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x200020002", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts all demand data writes (RFOs)", + "Counter": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OCR.DEMAND_RFO.SUPPLIER_NONE.SNOOP_NONE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x80020002", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { "BriefDescription": "Counts any other requests OCR.OTHER.L3_HIT.ANY_SNOOP OCR.OTHER.L3_HIT.ANY_SNOOP", "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", diff --git a/tools/perf/pmu-events/arch/x86/cascadelakex/clx-metrics.json b/tools/perf/pmu-events/arch/x86/cascadelakex/clx-metrics.json index 5729b93a9c68..6485b565acbc 100644 --- a/tools/perf/pmu-events/arch/x86/cascadelakex/clx-metrics.json +++ b/tools/perf/pmu-events/arch/x86/cascadelakex/clx-metrics.json @@ -313,12 +313,12 @@ "MetricExpr": "LD_BLOCKS_PARTIAL.ADDRESS_ALIAS / tma_info_thread_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group", "MetricName": "tma_4k_aliasing", - "MetricThreshold": "tma_4k_aliasing > 0.2 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", - "PublicDescription": "This metric estimates how often memory load accesses were aliased by preceding stores (in program order) with a 4K address offset. False match is possible; which incur a few cycles load re-issue. However; the short re-issue duration is often hidden by the out-of-order core and HW optimizations; hence a user may safely ignore a high value of this metric unless it manages to propagate up into parent nodes of the hierarchy (e.g. to L1_Bound)", + "MetricThreshold": "tma_4k_aliasing > 0.2 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric estimates how often memory load accesses were aliased by preceding stores (in program order) with a 4K address offset. False match is possible; which incur a few cycles load re-issue. However; the short re-issue duration is often hidden by the out-of-order core and HW optimizations; hence a user may safely ignore a high value of this metric unless it manages to propagate up into parent nodes of the hierarchy (e.g. to L1_Bound).", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution ports for ALU operations", + "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution ports for ALU operations.", "MetricExpr": "(UOPS_DISPATCHED_PORT.PORT_0 + UOPS_DISPATCHED_PORT.PORT_1 + UOPS_DISPATCHED_PORT.PORT_5 + UOPS_DISPATCHED_PORT.PORT_6) / tma_info_thread_slots", "MetricGroup": "TopdownL5;tma_L5_group;tma_ports_utilized_3m_group", "MetricName": "tma_alu_op_utilization", @@ -330,7 +330,7 @@ "MetricExpr": "34 * (FP_ASSIST.ANY + OTHER_ASSISTS.ANY) / tma_info_thread_slots", "MetricGroup": "BvIO;TopdownL4;tma_L4_group;tma_microcode_sequencer_group", "MetricName": "tma_assists", - "MetricThreshold": "tma_assists > 0.1 & tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1", + "MetricThreshold": "tma_assists > 0.1 & (tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1)", "PublicDescription": "This metric estimates fraction of slots the CPU retired uops delivered by the Microcode_Sequencer as a result of Assists. Assists are long sequences of uops that are required in certain corner-cases for operations that cannot be handled natively by the execution pipeline. For example; when working with very small floating point values (so-called Denormals); the FP units are not set up to perform these operations natively. Instead; a sequence of instructions to perform the computation on the Denormals is injected into the pipeline. Since these microcode sequences might be dozens of uops long; Assists can be extremely deleterious to performance and they can be avoided in many cases. Sample with: OTHER_ASSISTS.ANY", "ScaleUnit": "100%" }, @@ -341,7 +341,7 @@ "MetricName": "tma_backend_bound", "MetricThreshold": "tma_backend_bound > 0.2", "MetricgroupNoGroup": "TopdownL1", - "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound", + "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound.", "ScaleUnit": "100%" }, { @@ -351,12 +351,12 @@ "MetricName": "tma_bad_speculation", "MetricThreshold": "tma_bad_speculation > 0.15", "MetricgroupNoGroup": "TopdownL1", - "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example", + "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.", "ScaleUnit": "100%" }, { "BriefDescription": "Total pipeline cost of instruction fetch related bottlenecks by large code footprint programs (i-side cache; TLB and BTB misses)", - "MetricExpr": "100 * tma_fetch_latency * (tma_itlb_misses + tma_icache_misses + tma_unknown_branches) / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches)", + "MetricExpr": "100 * tma_fetch_latency * (tma_itlb_misses + tma_icache_misses + tma_unknown_branches) / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches)", "MetricGroup": "BigFootprint;BvBC;Fed;Frontend;IcMiss;MemoryTLB", "MetricName": "tma_bottleneck_big_code", "MetricThreshold": "tma_bottleneck_big_code > 20" @@ -371,7 +371,7 @@ }, { "BriefDescription": "Total pipeline cost of external Memory- or Cache-Bandwidth related bottlenecks", - "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_mem_bandwidth / (tma_mem_bandwidth + tma_mem_latency)) + tma_memory_bound * (tma_l3_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_sq_full / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_memory_bound * (tma_l1_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_fb_full / (tma_dtlb_load + tma_store_fwd_blk + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_4k_aliasing + tma_fb_full)))", + "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_mem_bandwidth / (tma_mem_bandwidth + tma_mem_latency)) + tma_memory_bound * (tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_sq_full / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_fb_full / (tma_4k_aliasing + tma_dtlb_load + tma_fb_full + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)))", "MetricGroup": "BvMB;Mem;MemoryBW;Offcore;tma_issueBW", "MetricName": "tma_bottleneck_cache_memory_bandwidth", "MetricThreshold": "tma_bottleneck_cache_memory_bandwidth > 20", @@ -379,7 +379,7 @@ }, { "BriefDescription": "Total pipeline cost of external Memory- or Cache-Latency related bottlenecks", - "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_mem_latency / (tma_mem_bandwidth + tma_mem_latency)) + tma_memory_bound * (tma_l3_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_l3_hit_latency / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_memory_bound * tma_l2_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound) + tma_memory_bound * (tma_l1_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_l1_latency_dependency / (tma_dtlb_load + tma_store_fwd_blk + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_4k_aliasing + tma_fb_full)) + tma_memory_bound * (tma_l1_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_lock_latency / (tma_dtlb_load + tma_store_fwd_blk + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_4k_aliasing + tma_fb_full)) + tma_memory_bound * (tma_l1_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_split_loads / (tma_dtlb_load + tma_store_fwd_blk + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_4k_aliasing + tma_fb_full)) + tma_memory_bound * (tma_store_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_split_stores / (tma_store_latency + tma_false_sharing + tma_split_stores + tma_dtlb_store)) + tma_memory_bound * (tma_store_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_store_latency / (tma_store_latency + tma_false_sharing + tma_split_stores + tma_dtlb_store)))", + "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_mem_latency / (tma_mem_bandwidth + tma_mem_latency)) + tma_memory_bound * (tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_l3_hit_latency / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_memory_bound * tma_l2_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) + tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_l1_latency_dependency / (tma_4k_aliasing + tma_dtlb_load + tma_fb_full + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_lock_latency / (tma_4k_aliasing + tma_dtlb_load + tma_fb_full + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_split_loads / (tma_4k_aliasing + tma_dtlb_load + tma_fb_full + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_memory_bound * (tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_split_stores / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency)) + tma_memory_bound * (tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_store_latency / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency)))", "MetricGroup": "BvML;Mem;MemoryLat;Offcore;tma_issueLat", "MetricName": "tma_bottleneck_cache_memory_latency", "MetricThreshold": "tma_bottleneck_cache_memory_latency > 20", @@ -387,22 +387,22 @@ }, { "BriefDescription": "Total pipeline cost when the execution is compute-bound - an estimation", - "MetricExpr": "100 * (tma_core_bound * tma_divider / (tma_divider + tma_serializing_operation + tma_ports_utilization) + tma_core_bound * (tma_ports_utilization / (tma_divider + tma_serializing_operation + tma_ports_utilization)) * (tma_ports_utilized_3m / (tma_ports_utilized_0 + tma_ports_utilized_1 + tma_ports_utilized_2 + tma_ports_utilized_3m)))", + "MetricExpr": "100 * (tma_core_bound * tma_divider / (tma_divider + tma_ports_utilization + tma_serializing_operation) + tma_core_bound * (tma_ports_utilization / (tma_divider + tma_ports_utilization + tma_serializing_operation)) * (tma_ports_utilized_3m / (tma_ports_utilized_0 + tma_ports_utilized_1 + tma_ports_utilized_2 + tma_ports_utilized_3m)))", "MetricGroup": "BvCB;Cor;tma_issueComp", "MetricName": "tma_bottleneck_compute_bound_est", "MetricThreshold": "tma_bottleneck_compute_bound_est > 20", - "PublicDescription": "Total pipeline cost when the execution is compute-bound - an estimation. Covers Core Bound when High ILP as well as when long-latency execution units are busy" + "PublicDescription": "Total pipeline cost when the execution is compute-bound - an estimation. Covers Core Bound when High ILP as well as when long-latency execution units are busy. Related metrics: " }, { "BriefDescription": "Total pipeline cost of instruction fetch bandwidth related bottlenecks (when the front-end could not sustain operations delivery to the back-end)", - "MetricExpr": "100 * (tma_frontend_bound - (1 - 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts) * tma_fetch_latency * tma_mispredicts_resteers / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches) - tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * tma_fetch_latency * (tma_ms_switches + tma_branch_resteers * (tma_clears_resteers + tma_mispredicts_resteers * (10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts)) / (tma_mispredicts_resteers + tma_clears_resteers + tma_unknown_branches)) / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches)) - tma_bottleneck_big_code", + "MetricExpr": "100 * (tma_frontend_bound - (1 - 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts) * tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) - tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * tma_fetch_latency * (tma_ms_switches + tma_branch_resteers * (tma_clears_resteers + tma_mispredicts_resteers * (10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts)) / (tma_clears_resteers + tma_mispredicts_resteers + tma_unknown_branches)) / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches)) - tma_bottleneck_big_code", "MetricGroup": "BvFB;Fed;FetchBW;Frontend", "MetricName": "tma_bottleneck_instruction_fetch_bw", "MetricThreshold": "tma_bottleneck_instruction_fetch_bw > 20" }, { "BriefDescription": "Total pipeline cost of irregular execution (e.g", - "MetricExpr": "100 * (tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * tma_fetch_latency * (tma_ms_switches + tma_branch_resteers * (tma_clears_resteers + tma_mispredicts_resteers * (10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts)) / (tma_mispredicts_resteers + tma_clears_resteers + tma_unknown_branches)) / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches) + 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts * tma_branch_mispredicts + tma_machine_clears * tma_other_nukes / tma_other_nukes + tma_core_bound * (tma_serializing_operation + tma_core_bound * RS_EVENTS.EMPTY_CYCLES / tma_info_thread_clks * tma_ports_utilized_0) / (tma_divider + tma_serializing_operation + tma_ports_utilization) + tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * tma_heavy_operations)", + "MetricExpr": "100 * (tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * tma_fetch_latency * (tma_ms_switches + tma_branch_resteers * (tma_clears_resteers + tma_mispredicts_resteers * (10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts)) / (tma_clears_resteers + tma_mispredicts_resteers + tma_unknown_branches)) / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) + 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts * tma_branch_mispredicts + tma_machine_clears * tma_other_nukes / tma_other_nukes + tma_core_bound * (tma_serializing_operation + tma_core_bound * RS_EVENTS.EMPTY_CYCLES / tma_info_thread_clks * tma_ports_utilized_0) / (tma_divider + tma_ports_utilization + tma_serializing_operation) + tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * tma_heavy_operations)", "MetricGroup": "Bad;BvIO;Cor;Ret;tma_issueMS", "MetricName": "tma_bottleneck_irregular_overhead", "MetricThreshold": "tma_bottleneck_irregular_overhead > 10", @@ -410,7 +410,7 @@ }, { "BriefDescription": "Total pipeline cost of Memory Address Translation related bottlenecks (data-side TLBs)", - "MetricExpr": "100 * (tma_memory_bound * (tma_l1_bound / max(tma_memory_bound, tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_dtlb_load / max(tma_l1_bound, tma_dtlb_load + tma_store_fwd_blk + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_4k_aliasing + tma_fb_full)) + tma_memory_bound * (tma_store_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_dtlb_store / (tma_store_latency + tma_false_sharing + tma_split_stores + tma_dtlb_store)))", + "MetricExpr": "100 * (tma_memory_bound * (tma_l1_bound / max(tma_memory_bound, tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_dtlb_load / max(tma_l1_bound, tma_4k_aliasing + tma_dtlb_load + tma_fb_full + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_memory_bound * (tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_dtlb_store / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency)))", "MetricGroup": "BvMT;Mem;MemoryTLB;Offcore;tma_issueTLB", "MetricName": "tma_bottleneck_memory_data_tlbs", "MetricThreshold": "tma_bottleneck_memory_data_tlbs > 20", @@ -418,7 +418,7 @@ }, { "BriefDescription": "Total pipeline cost of Memory Synchronization related bottlenecks (data transfers and coherency updates across processors)", - "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound) * (tma_mem_latency / (tma_mem_bandwidth + tma_mem_latency)) * tma_remote_cache / (tma_local_mem + tma_remote_mem + tma_remote_cache) + tma_l3_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound) * (tma_contested_accesses + tma_data_sharing) / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full) + tma_store_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound) * tma_false_sharing / (tma_store_latency + tma_false_sharing + tma_split_stores + tma_dtlb_store - tma_store_latency)) + tma_machine_clears * (1 - tma_other_nukes / tma_other_nukes))", + "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_mem_latency / (tma_mem_bandwidth + tma_mem_latency)) * tma_remote_cache / (tma_local_mem + tma_remote_cache + tma_remote_mem) + tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_contested_accesses + tma_data_sharing) / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full) + tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * tma_false_sharing / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency - tma_store_latency)) + tma_machine_clears * (1 - tma_other_nukes / tma_other_nukes))", "MetricGroup": "BvMS;LockCont;Mem;Offcore;tma_issueSyncxn", "MetricName": "tma_bottleneck_memory_synchronization", "MetricThreshold": "tma_bottleneck_memory_synchronization > 10", @@ -426,7 +426,7 @@ }, { "BriefDescription": "Total pipeline cost of Branch Misprediction related bottlenecks", - "MetricExpr": "100 * (1 - 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts) * (tma_branch_mispredicts + tma_fetch_latency * tma_mispredicts_resteers / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches))", + "MetricExpr": "100 * (1 - 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts) * (tma_branch_mispredicts + tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches))", "MetricGroup": "Bad;BadSpec;BrMispredicts;BvMP;tma_issueBM", "MetricName": "tma_bottleneck_mispredictions", "MetricThreshold": "tma_bottleneck_mispredictions > 20", @@ -438,10 +438,10 @@ "MetricGroup": "BvOB;Cor;Offcore", "MetricName": "tma_bottleneck_other_bottlenecks", "MetricThreshold": "tma_bottleneck_other_bottlenecks > 20", - "PublicDescription": "Total pipeline cost of remaining bottlenecks in the back-end. Examples include data-dependencies (Core Bound when Low ILP) and other unlisted memory-related stalls" + "PublicDescription": "Total pipeline cost of remaining bottlenecks in the back-end. Examples include data-dependencies (Core Bound when Low ILP) and other unlisted memory-related stalls." }, { - "BriefDescription": "Total pipeline cost of \"useful operations\" - the portion of Retiring category not covered by Branching_Overhead nor Irregular_Overhead", + "BriefDescription": "Total pipeline cost of \"useful operations\" - the portion of Retiring category not covered by Branching_Overhead nor Irregular_Overhead.", "MetricExpr": "100 * (tma_retiring - (BR_INST_RETIRED.ALL_BRANCHES + 2 * BR_INST_RETIRED.NEAR_CALL + INST_RETIRED.NOP) / tma_info_thread_slots - tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * tma_heavy_operations)", "MetricGroup": "BvUW;Ret", "MetricName": "tma_bottleneck_useful_work", @@ -463,8 +463,8 @@ "MetricExpr": "INT_MISC.CLEAR_RESTEER_CYCLES / tma_info_thread_clks + tma_unknown_branches", "MetricGroup": "FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group", "MetricName": "tma_branch_resteers", - "MetricThreshold": "tma_branch_resteers > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", - "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers. Branch Resteers estimates the Frontend delay in fetching operations from corrected path; following all sorts of miss-predicted branches. For example; branchy code with lots of miss-predictions might get categorized under Branch Resteers. Note the value of this node may overlap with its siblings. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_l3_hit_latency, tma_store_latency", + "MetricThreshold": "tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers. Branch Resteers estimates the Frontend delay in fetching operations from corrected path; following all sorts of miss-predicted branches. For example; branchy code with lots of miss-predictions might get categorized under Branch Resteers. Note the value of this node may overlap with its siblings. Sample with: BR_MISP_RETIRED.ALL_BRANCHES", "ScaleUnit": "100%" }, { @@ -472,8 +472,8 @@ "MetricExpr": "max(0, tma_microcode_sequencer - tma_assists)", "MetricGroup": "TopdownL4;tma_L4_group;tma_microcode_sequencer_group", "MetricName": "tma_cisc", - "MetricThreshold": "tma_cisc > 0.1 & tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1", - "PublicDescription": "This metric estimates fraction of cycles the CPU retired uops originated from CISC (complex instruction set computer) instruction. A CISC instruction has multiple uops that are required to perform the instruction's functionality as in the case of read-modify-write as an example. Since these instructions require multiple uops they may or may not imply sub-optimal use of machine resources", + "MetricThreshold": "tma_cisc > 0.1 & (tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1)", + "PublicDescription": "This metric estimates fraction of cycles the CPU retired uops originated from CISC (complex instruction set computer) instruction. A CISC instruction has multiple uops that are required to perform the instruction's functionality as in the case of read-modify-write as an example. Since these instructions require multiple uops they may or may not imply sub-optimal use of machine resources.", "ScaleUnit": "100%" }, { @@ -481,7 +481,7 @@ "MetricExpr": "(1 - BR_MISP_RETIRED.ALL_BRANCHES / (BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT)) * INT_MISC.CLEAR_RESTEER_CYCLES / tma_info_thread_clks", "MetricGroup": "BadSpec;MachineClears;TopdownL4;tma_L4_group;tma_branch_resteers_group;tma_issueMC", "MetricName": "tma_clears_resteers", - "MetricThreshold": "tma_clears_resteers > 0.05 & tma_branch_resteers > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricThreshold": "tma_clears_resteers > 0.05 & (tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))", "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Machine Clears. Sample with: INT_MISC.CLEAR_RESTEER_CYCLES. Related metrics: tma_l1_bound, tma_machine_clears, tma_microcode_sequencer, tma_ms_switches", "ScaleUnit": "100%" }, @@ -490,7 +490,7 @@ "MetricExpr": "max(0, tma_itlb_misses - tma_code_stlb_miss)", "MetricGroup": "FetchLat;MemoryTLB;TopdownL4;tma_L4_group;tma_itlb_misses_group", "MetricName": "tma_code_stlb_hit", - "MetricThreshold": "tma_code_stlb_hit > 0.05 & tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricThreshold": "tma_code_stlb_hit > 0.05 & (tma_itlb_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))", "ScaleUnit": "100%" }, { @@ -498,33 +498,33 @@ "MetricExpr": "ITLB_MISSES.WALK_ACTIVE / tma_info_thread_clks", "MetricGroup": "FetchLat;MemoryTLB;TopdownL4;tma_L4_group;tma_itlb_misses_group", "MetricName": "tma_code_stlb_miss", - "MetricThreshold": "tma_code_stlb_miss > 0.05 & tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricThreshold": "tma_code_stlb_miss > 0.05 & (tma_itlb_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 2 or 4 MB pages for (instruction) code accesses", + "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 2 or 4 MB pages for (instruction) code accesses.", "MetricExpr": "tma_code_stlb_miss * ITLB_MISSES.WALK_COMPLETED_2M_4M / (ITLB_MISSES.WALK_COMPLETED_4K + ITLB_MISSES.WALK_COMPLETED_2M_4M)", "MetricGroup": "FetchLat;MemoryTLB;TopdownL5;tma_L5_group;tma_code_stlb_miss_group", "MetricName": "tma_code_stlb_miss_2m", - "MetricThreshold": "tma_code_stlb_miss_2m > 0.05 & tma_code_stlb_miss > 0.05 & tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricThreshold": "tma_code_stlb_miss_2m > 0.05 & (tma_code_stlb_miss > 0.05 & (tma_itlb_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)))", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 4 KB pages for (instruction) code accesses", + "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 4 KB pages for (instruction) code accesses.", "MetricExpr": "tma_code_stlb_miss * ITLB_MISSES.WALK_COMPLETED_4K / (ITLB_MISSES.WALK_COMPLETED_4K + ITLB_MISSES.WALK_COMPLETED_2M_4M)", "MetricGroup": "FetchLat;MemoryTLB;TopdownL5;tma_L5_group;tma_code_stlb_miss_group", "MetricName": "tma_code_stlb_miss_4k", - "MetricThreshold": "tma_code_stlb_miss_4k > 0.05 & tma_code_stlb_miss > 0.05 & tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricThreshold": "tma_code_stlb_miss_4k > 0.05 & (tma_code_stlb_miss > 0.05 & (tma_itlb_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)))", "ScaleUnit": "100%" }, { "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses", "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "((47.5 * tma_info_system_core_frequency - 3.5 * tma_info_system_core_frequency) * (MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM * (OCR.DEMAND_DATA_RD.L3_HIT.HITM_OTHER_CORE / (OCR.DEMAND_DATA_RD.L3_HIT.HITM_OTHER_CORE + OCR.DEMAND_DATA_RD.L3_HIT.HIT_OTHER_CORE_FWD))) + (47.5 * tma_info_system_core_frequency - 3.5 * tma_info_system_core_frequency) * MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks", + "MetricExpr": "(44 * tma_info_system_core_frequency * (MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM * (OCR.DEMAND_DATA_RD.L3_HIT.HITM_OTHER_CORE / (OCR.DEMAND_DATA_RD.L3_HIT.HITM_OTHER_CORE + OCR.DEMAND_DATA_RD.L3_HIT.HIT_OTHER_CORE_FWD))) + 44 * tma_info_system_core_frequency * MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks", "MetricGroup": "BvMS;DataSharing;LockCont;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group", "MetricName": "tma_contested_accesses", - "MetricThreshold": "tma_contested_accesses > 0.05 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", - "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses. Contested accesses occur when data written by one Logical Processor are read by another Logical Processor on a different Physical Core. Examples of contested accesses include synchronizations such as locks; true data sharing such as modified locked variables; and false sharing. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM, MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS. Related metrics: tma_bottleneck_memory_synchronization, tma_data_sharing, tma_false_sharing, tma_machine_clears, tma_remote_cache", + "MetricThreshold": "tma_contested_accesses > 0.05 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses. Contested accesses occur when data written by one Logical Processor are read by another Logical Processor on a different Physical Core. Examples of contested accesses include synchronizations such as locks; true data sharing such as modified locked variables; and false sharing. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM_PS;MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS_PS. Related metrics: tma_bottleneck_memory_synchronization, tma_data_sharing, tma_false_sharing, tma_machine_clears, tma_remote_cache", "ScaleUnit": "100%" }, { @@ -535,25 +535,25 @@ "MetricName": "tma_core_bound", "MetricThreshold": "tma_core_bound > 0.1 & tma_backend_bound > 0.2", "MetricgroupNoGroup": "TopdownL2", - "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck. Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations)", + "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck. Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations).", "ScaleUnit": "100%" }, { "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses", "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "(47.5 * tma_info_system_core_frequency - 3.5 * tma_info_system_core_frequency) * (MEM_LOAD_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM * (1 - OCR.DEMAND_DATA_RD.L3_HIT.HITM_OTHER_CORE / (OCR.DEMAND_DATA_RD.L3_HIT.HITM_OTHER_CORE + OCR.DEMAND_DATA_RD.L3_HIT.HIT_OTHER_CORE_FWD))) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks", + "MetricExpr": "44 * tma_info_system_core_frequency * (MEM_LOAD_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM * (1 - OCR.DEMAND_DATA_RD.L3_HIT.HITM_OTHER_CORE / (OCR.DEMAND_DATA_RD.L3_HIT.HITM_OTHER_CORE + OCR.DEMAND_DATA_RD.L3_HIT.HIT_OTHER_CORE_FWD))) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks", "MetricGroup": "BvMS;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group", "MetricName": "tma_data_sharing", - "MetricThreshold": "tma_data_sharing > 0.05 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", - "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses. Data shared by multiple Logical Processors (even just read shared) may cause increased access latency due to cache coherency. Excessive data sharing can drastically harm multithreaded performance. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_HIT. Related metrics: tma_bottleneck_memory_synchronization, tma_contested_accesses, tma_false_sharing, tma_machine_clears, tma_remote_cache", + "MetricThreshold": "tma_data_sharing > 0.05 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses. Data shared by multiple Logical Processors (even just read shared) may cause increased access latency due to cache coherency. Excessive data sharing can drastically harm multithreaded performance. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_HIT_PS. Related metrics: tma_bottleneck_memory_synchronization, tma_contested_accesses, tma_false_sharing, tma_machine_clears, tma_remote_cache", "ScaleUnit": "100%" }, { "BriefDescription": "This metric represents fraction of cycles where decoder-0 was the only active decoder", - "MetricExpr": "(cpu@INST_DECODED.DECODERS\\,cmask\\=0x1@ - cpu@INST_DECODED.DECODERS\\,cmask\\=0x2@) / tma_info_core_core_clks / 2", + "MetricExpr": "(cpu@INST_DECODED.DECODERS\\,cmask\\=1@ - cpu@INST_DECODED.DECODERS\\,cmask\\=2@) / tma_info_core_core_clks / 2", "MetricGroup": "DSBmiss;FetchBW;TopdownL4;tma_L4_group;tma_issueD0;tma_mite_group", "MetricName": "tma_decoder0_alone", - "MetricThreshold": "tma_decoder0_alone > 0.1 & tma_mite > 0.1 & tma_fetch_bandwidth > 0.2", + "MetricThreshold": "tma_decoder0_alone > 0.1 & (tma_mite > 0.1 & tma_fetch_bandwidth > 0.2)", "PublicDescription": "This metric represents fraction of cycles where decoder-0 was the only active decoder. Related metrics: tma_few_uops_instructions", "ScaleUnit": "100%" }, @@ -562,7 +562,7 @@ "MetricExpr": "ARITH.DIVIDER_ACTIVE / tma_info_thread_clks", "MetricGroup": "BvCB;TopdownL3;tma_L3_group;tma_core_bound_group", "MetricName": "tma_divider", - "MetricThreshold": "tma_divider > 0.2 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_divider > 0.2 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)", "PublicDescription": "This metric represents fraction of cycles where the Divider unit was active. Divide and square root instructions are performed by the Divider unit and can take considerably longer latency than integer or Floating Point addition; subtraction; or multiplication. Sample with: ARITH.DIVIDER_ACTIVE", "ScaleUnit": "100%" }, @@ -572,7 +572,7 @@ "MetricExpr": "CYCLE_ACTIVITY.STALLS_L3_MISS / tma_info_thread_clks + (CYCLE_ACTIVITY.STALLS_L1D_MISS - CYCLE_ACTIVITY.STALLS_L2_MISS) / tma_info_thread_clks - tma_l2_bound", "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_dram_bound", - "MetricThreshold": "tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", "PublicDescription": "This metric estimates how often the CPU was stalled on accesses to external memory (DRAM) by loads. Better caching can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L3_MISS", "ScaleUnit": "100%" }, @@ -582,7 +582,7 @@ "MetricGroup": "DSB;FetchBW;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group", "MetricName": "tma_dsb", "MetricThreshold": "tma_dsb > 0.15 & tma_fetch_bandwidth > 0.2", - "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to DSB (decoded uop cache) fetch pipeline. For example; inefficient utilization of the DSB cache structure or bank conflict when reading from it; are categorized here", + "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to DSB (decoded uop cache) fetch pipeline. For example; inefficient utilization of the DSB cache structure or bank conflict when reading from it; are categorized here.", "ScaleUnit": "100%" }, { @@ -590,27 +590,27 @@ "MetricExpr": "DSB2MITE_SWITCHES.PENALTY_CYCLES / tma_info_thread_clks", "MetricGroup": "DSBmiss;FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueFB", "MetricName": "tma_dsb_switches", - "MetricThreshold": "tma_dsb_switches > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", - "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines. The DSB (decoded i-cache) is a Uop Cache where the front-end directly delivers Uops (micro operations) avoiding heavy x86 decoding. The DSB pipeline has shorter latency and delivered higher bandwidth than the MITE (legacy instruction decode pipeline). Switching between the two pipelines can cause penalties hence this metric measures the exposed penalty. Sample with: FRONTEND_RETIRED.DSB_MISS. Related metrics: tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp", + "MetricThreshold": "tma_dsb_switches > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines. The DSB (decoded i-cache) is a Uop Cache where the front-end directly delivers Uops (micro operations) avoiding heavy x86 decoding. The DSB pipeline has shorter latency and delivered higher bandwidth than the MITE (legacy instruction decode pipeline). Switching between the two pipelines can cause penalties hence this metric measures the exposed penalty. Sample with: FRONTEND_RETIRED.DSB_MISS_PS. Related metrics: tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp", "ScaleUnit": "100%" }, { "BriefDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses", "MetricConstraint": "NO_GROUP_EVENTS_NMI", - "MetricExpr": "min(9 * cpu@DTLB_LOAD_MISSES.STLB_HIT\\,cmask\\=0x1@ + DTLB_LOAD_MISSES.WALK_ACTIVE, max(CYCLE_ACTIVITY.CYCLES_MEM_ANY - CYCLE_ACTIVITY.CYCLES_L1D_MISS, 0)) / tma_info_thread_clks", + "MetricExpr": "min(9 * cpu@DTLB_LOAD_MISSES.STLB_HIT\\,cmask\\=1@ + DTLB_LOAD_MISSES.WALK_ACTIVE, max(CYCLE_ACTIVITY.CYCLES_MEM_ANY - CYCLE_ACTIVITY.CYCLES_L1D_MISS, 0)) / tma_info_thread_clks", "MetricGroup": "BvMT;MemoryTLB;TopdownL4;tma_L4_group;tma_issueTLB;tma_l1_bound_group", "MetricName": "tma_dtlb_load", - "MetricThreshold": "tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", - "PublicDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses. TLBs (Translation Look-aside Buffers) are processor caches for recently used entries out of the Page Tables that are used to map virtual- to physical-addresses by the operating system. This metric approximates the potential delay of demand loads missing the first-level data TLB (assuming worst case scenario with back to back misses to different pages). This includes hitting in the second-level TLB (STLB) as well as performing a hardware page walk on an STLB miss. Sample with: MEM_INST_RETIRED.STLB_MISS_LOADS. Related metrics: tma_bottleneck_memory_data_tlbs, tma_dtlb_store", + "MetricThreshold": "tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses. TLBs (Translation Look-aside Buffers) are processor caches for recently used entries out of the Page Tables that are used to map virtual- to physical-addresses by the operating system. This metric approximates the potential delay of demand loads missing the first-level data TLB (assuming worst case scenario with back to back misses to different pages). This includes hitting in the second-level TLB (STLB) as well as performing a hardware page walk on an STLB miss. Sample with: MEM_INST_RETIRED.STLB_MISS_LOADS_PS. Related metrics: tma_bottleneck_memory_data_tlbs, tma_dtlb_store", "ScaleUnit": "100%" }, { "BriefDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses", - "MetricExpr": "(9 * cpu@DTLB_STORE_MISSES.STLB_HIT\\,cmask\\=0x1@ + DTLB_STORE_MISSES.WALK_ACTIVE) / tma_info_core_core_clks", + "MetricExpr": "(9 * cpu@DTLB_STORE_MISSES.STLB_HIT\\,cmask\\=1@ + DTLB_STORE_MISSES.WALK_ACTIVE) / tma_info_core_core_clks", "MetricGroup": "BvMT;MemoryTLB;TopdownL4;tma_L4_group;tma_issueTLB;tma_store_bound_group", "MetricName": "tma_dtlb_store", - "MetricThreshold": "tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", - "PublicDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses. As with ordinary data caching; focus on improving data locality and reducing working-set size to reduce DTLB overhead. Additionally; consider using profile-guided optimization (PGO) to collocate frequently-used data on the same page. Try using larger page sizes for large amounts of frequently-used data. Sample with: MEM_INST_RETIRED.STLB_MISS_STORES. Related metrics: tma_bottleneck_memory_data_tlbs, tma_dtlb_load", + "MetricThreshold": "tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses. As with ordinary data caching; focus on improving data locality and reducing working-set size to reduce DTLB overhead. Additionally; consider using profile-guided optimization (PGO) to collocate frequently-used data on the same page. Try using larger page sizes for large amounts of frequently-used data. Sample with: MEM_INST_RETIRED.STLB_MISS_STORES_PS. Related metrics: tma_bottleneck_memory_data_tlbs, tma_dtlb_load", "ScaleUnit": "100%" }, { @@ -619,18 +619,18 @@ "MetricExpr": "(110 * tma_info_system_core_frequency * (OCR.DEMAND_RFO.L3_MISS.REMOTE_HITM + OCR.PF_L2_RFO.L3_MISS.REMOTE_HITM) + 47.5 * tma_info_system_core_frequency * (OCR.DEMAND_RFO.L3_HIT.HITM_OTHER_CORE + OCR.PF_L2_RFO.L3_HIT.HITM_OTHER_CORE)) / tma_info_thread_clks", "MetricGroup": "BvMS;DataSharing;LockCont;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_store_bound_group", "MetricName": "tma_false_sharing", - "MetricThreshold": "tma_false_sharing > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", - "PublicDescription": "This metric roughly estimates how often CPU was handling synchronizations due to False Sharing. False Sharing is a multithreading hiccup; where multiple Logical Processors contend on different data-elements mapped into the same cache line. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM, OCR.DEMAND_RFO.L3_HIT.HITM_OTHER_CORE. Related metrics: tma_bottleneck_memory_synchronization, tma_contested_accesses, tma_data_sharing, tma_machine_clears, tma_remote_cache", + "MetricThreshold": "tma_false_sharing > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric roughly estimates how often CPU was handling synchronizations due to False Sharing. False Sharing is a multithreading hiccup; where multiple Logical Processors contend on different data-elements mapped into the same cache line. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM_PS;OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.SNOOP_HITM. Related metrics: tma_bottleneck_memory_synchronization, tma_contested_accesses, tma_data_sharing, tma_machine_clears, tma_remote_cache", "ScaleUnit": "100%" }, { "BriefDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed", "MetricConstraint": "NO_GROUP_EVENTS_NMI", - "MetricExpr": "tma_info_memory_load_miss_real_latency * cpu@L1D_PEND_MISS.FB_FULL\\,cmask\\=0x1@ / tma_info_thread_clks", + "MetricExpr": "tma_info_memory_load_miss_real_latency * cpu@L1D_PEND_MISS.FB_FULL\\,cmask\\=1@ / tma_info_thread_clks", "MetricGroup": "BvMB;MemoryBW;TopdownL4;tma_L4_group;tma_issueBW;tma_issueSL;tma_issueSmSt;tma_l1_bound_group", "MetricName": "tma_fb_full", "MetricThreshold": "tma_fb_full > 0.3", - "PublicDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed. The higher the metric value; the deeper the memory hierarchy level the misses are satisfied from (metric values >1 are valid). Often it hints on approaching bandwidth limits (to L2 cache; L3 cache or external memory). Related metrics: tma_bottleneck_cache_memory_bandwidth, tma_info_system_dram_bw_use, tma_mem_bandwidth, tma_sq_full, tma_store_latency", + "PublicDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed. The higher the metric value; the deeper the memory hierarchy level the misses are satisfied from (metric values >1 are valid). Often it hints on approaching bandwidth limits (to L2 cache; L3 cache or external memory). Related metrics: tma_bottleneck_cache_memory_bandwidth, tma_info_system_dram_bw_use, tma_mem_bandwidth, tma_sq_full, tma_store_latency, tma_streaming_stores", "ScaleUnit": "100%" }, { @@ -640,7 +640,7 @@ "MetricName": "tma_fetch_bandwidth", "MetricThreshold": "tma_fetch_bandwidth > 0.2", "MetricgroupNoGroup": "TopdownL2", - "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues. For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Sample with: FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1, FRONTEND_RETIRED.LATENCY_GE_1, FRONTEND_RETIRED.LATENCY_GE_2. Related metrics: tma_dsb_switches, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp", + "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues. For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Sample with: FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1;FRONTEND_RETIRED.LATENCY_GE_1;FRONTEND_RETIRED.LATENCY_GE_2. Related metrics: tma_dsb_switches, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp", "ScaleUnit": "100%" }, { @@ -650,7 +650,7 @@ "MetricName": "tma_fetch_latency", "MetricThreshold": "tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", "MetricgroupNoGroup": "TopdownL2", - "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues. For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: FRONTEND_RETIRED.LATENCY_GE_16, FRONTEND_RETIRED.LATENCY_GE_8", + "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues. For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: FRONTEND_RETIRED.LATENCY_GE_16_PS;FRONTEND_RETIRED.LATENCY_GE_8_PS", "ScaleUnit": "100%" }, { @@ -670,7 +670,7 @@ "MetricGroup": "HPC;TopdownL3;tma_L3_group;tma_light_operations_group", "MetricName": "tma_fp_arith", "MetricThreshold": "tma_fp_arith > 0.2 & tma_light_operations > 0.6", - "PublicDescription": "This metric represents overall arithmetic floating-point (FP) operations fraction the CPU has executed (retired). Note this metric's value may exceed its parent due to use of \"Uops\" CountDomain and FMA double-counting", + "PublicDescription": "This metric represents overall arithmetic floating-point (FP) operations fraction the CPU has executed (retired). Note this metric's value may exceed its parent due to use of \"Uops\" CountDomain and FMA double-counting.", "ScaleUnit": "100%" }, { @@ -679,7 +679,7 @@ "MetricGroup": "HPC;TopdownL5;tma_L5_group;tma_assists_group", "MetricName": "tma_fp_assists", "MetricThreshold": "tma_fp_assists > 0.1", - "PublicDescription": "This metric roughly estimates fraction of slots the CPU retired uops as a result of handing Floating Point (FP) Assists. FP Assist may apply when working with very small floating point values (so-called Denormals)", + "PublicDescription": "This metric roughly estimates fraction of slots the CPU retired uops as a result of handing Floating Point (FP) Assists. FP Assist may apply when working with very small floating point values (so-called Denormals).", "ScaleUnit": "100%" }, { @@ -687,17 +687,17 @@ "MetricExpr": "FP_ARITH_INST_RETIRED.SCALAR / UOPS_RETIRED.RETIRE_SLOTS", "MetricGroup": "Compute;Flops;TopdownL4;tma_L4_group;tma_fp_arith_group;tma_issue2P", "MetricName": "tma_fp_scalar", - "MetricThreshold": "tma_fp_scalar > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6", + "MetricThreshold": "tma_fp_scalar > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6)", "PublicDescription": "This metric approximates arithmetic floating-point (FP) scalar uops fraction the CPU has retired. May overcount due to FMA double counting. Related metrics: tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%" }, { "BriefDescription": "This metric approximates arithmetic floating-point (FP) vector uops fraction the CPU has retired aggregated across all vector widths", "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "cpu@FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE\\,umask\\=0xFC@ / UOPS_RETIRED.RETIRE_SLOTS", + "MetricExpr": "cpu@FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE\\,umask\\=0xfc@ / UOPS_RETIRED.RETIRE_SLOTS", "MetricGroup": "Compute;Flops;TopdownL4;tma_L4_group;tma_fp_arith_group;tma_issue2P", "MetricName": "tma_fp_vector", - "MetricThreshold": "tma_fp_vector > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6", + "MetricThreshold": "tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6)", "PublicDescription": "This metric approximates arithmetic floating-point (FP) vector uops fraction the CPU has retired aggregated across all vector widths. May overcount due to FMA double counting. Related metrics: tma_fp_scalar, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%" }, @@ -706,7 +706,7 @@ "MetricExpr": "(FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE) / UOPS_RETIRED.RETIRE_SLOTS", "MetricGroup": "Compute;Flops;TopdownL5;tma_L5_group;tma_fp_vector_group;tma_issue2P", "MetricName": "tma_fp_vector_128b", - "MetricThreshold": "tma_fp_vector_128b > 0.1 & tma_fp_vector > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6", + "MetricThreshold": "tma_fp_vector_128b > 0.1 & (tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6))", "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 128-bit wide vectors. May overcount due to FMA double counting prior to LNL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%" }, @@ -715,7 +715,7 @@ "MetricExpr": "(FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE) / UOPS_RETIRED.RETIRE_SLOTS", "MetricGroup": "Compute;Flops;TopdownL5;tma_L5_group;tma_fp_vector_group;tma_issue2P", "MetricName": "tma_fp_vector_256b", - "MetricThreshold": "tma_fp_vector_256b > 0.1 & tma_fp_vector > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6", + "MetricThreshold": "tma_fp_vector_256b > 0.1 & (tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6))", "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 256-bit wide vectors. May overcount due to FMA double counting prior to LNL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%" }, @@ -724,7 +724,7 @@ "MetricExpr": "(FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE) / UOPS_RETIRED.RETIRE_SLOTS", "MetricGroup": "Compute;Flops;TopdownL5;tma_L5_group;tma_fp_vector_group;tma_issue2P", "MetricName": "tma_fp_vector_512b", - "MetricThreshold": "tma_fp_vector_512b > 0.1 & tma_fp_vector > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6", + "MetricThreshold": "tma_fp_vector_512b > 0.1 & (tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6))", "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 512-bit wide vectors. May overcount due to FMA double counting. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%" }, @@ -735,35 +735,35 @@ "MetricName": "tma_frontend_bound", "MetricThreshold": "tma_frontend_bound > 0.15", "MetricgroupNoGroup": "TopdownL1", - "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound. Sample with: FRONTEND_RETIRED.LATENCY_GE_4", + "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound. Sample with: FRONTEND_RETIRED.LATENCY_GE_4_PS", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of slots where the CPU was retiring fused instructions , where one uop can represent multiple contiguous instructions", + "BriefDescription": "This metric represents fraction of slots where the CPU was retiring fused instructions -- where one uop can represent multiple contiguous instructions", "MetricExpr": "tma_light_operations * UOPS_RETIRED.MACRO_FUSED / UOPS_RETIRED.RETIRE_SLOTS", "MetricGroup": "Branches;BvBO;Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group", "MetricName": "tma_fused_instructions", "MetricThreshold": "tma_fused_instructions > 0.1 & tma_light_operations > 0.6", - "PublicDescription": "This metric represents fraction of slots where the CPU was retiring fused instructions , where one uop can represent multiple contiguous instructions. CMP+JCC or DEC+JCC are common examples of legacy fusions. {([MTL] Note new MOV+OP and Load+OP fusions appear under Other_Light_Ops in MTL!)}", + "PublicDescription": "This metric represents fraction of slots where the CPU was retiring fused instructions -- where one uop can represent multiple contiguous instructions. CMP+JCC or DEC+JCC are common examples of legacy fusions. {([MTL] Note new MOV+OP and Load+OP fusions appear under Other_Light_Ops in MTL!)}", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations , instructions that require two or more uops or micro-coded sequences", + "BriefDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences", "MetricExpr": "(UOPS_RETIRED.RETIRE_SLOTS + UOPS_RETIRED.MACRO_FUSED - INST_RETIRED.ANY) / tma_info_thread_slots", "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_heavy_operations", "MetricThreshold": "tma_heavy_operations > 0.1", "MetricgroupNoGroup": "TopdownL2", - "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations , instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences.([ICL+] Note this may overcount due to approximation using indirect events; [ADL+])", + "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences.([ICL+] Note this may overcount due to approximation using indirect events; [ADL+])", "ScaleUnit": "100%" }, { "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to instruction cache misses", - "MetricExpr": "(ICACHE_16B.IFDATA_STALL + 2 * cpu@ICACHE_16B.IFDATA_STALL\\,cmask\\=0x1\\,edge\\=0x1@) / tma_info_thread_clks", + "MetricExpr": "(ICACHE_16B.IFDATA_STALL + 2 * cpu@ICACHE_16B.IFDATA_STALL\\,cmask\\=1\\,edge@) / tma_info_thread_clks", "MetricGroup": "BigFootprint;BvBC;FetchLat;IcMiss;TopdownL3;tma_L3_group;tma_fetch_latency_group", "MetricName": "tma_icache_misses", - "MetricThreshold": "tma_icache_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", - "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to instruction cache misses. Sample with: FRONTEND_RETIRED.L2_MISS, FRONTEND_RETIRED.L1I_MISS", + "MetricThreshold": "tma_icache_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to instruction cache misses. Sample with: FRONTEND_RETIRED.L2_MISS_PS;FRONTEND_RETIRED.L1I_MISS_PS", "ScaleUnit": "100%" }, { @@ -774,11 +774,11 @@ "PublicDescription": "Branch Misprediction Cost: Cycles representing fraction of TMA slots wasted per non-speculative branch misprediction (retired JEClear). Related metrics: tma_bottleneck_mispredictions, tma_branch_mispredicts, tma_mispredicts_resteers" }, { - "BriefDescription": "Instructions per retired Mispredicts for indirect CALL or JMP branches (lower number means higher occurrence rate)", + "BriefDescription": "Instructions per retired Mispredicts for indirect CALL or JMP branches (lower number means higher occurrence rate).", "MetricExpr": "tma_info_inst_mix_instructions / (UOPS_RETIRED.RETIRE_SLOTS / UOPS_ISSUED.ANY * BR_MISP_EXEC.INDIRECT)", "MetricGroup": "Bad;BrMispredicts", "MetricName": "tma_info_bad_spec_ipmisp_indirect", - "MetricThreshold": "tma_info_bad_spec_ipmisp_indirect < 1000" + "MetricThreshold": "tma_info_bad_spec_ipmisp_indirect < 1e3" }, { "BriefDescription": "Number of Instructions per non-speculative Branch Misprediction (JEClear) (lower number means higher occurrence rate)", @@ -803,7 +803,7 @@ }, { "BriefDescription": "Total pipeline cost of DSB (uop cache) hits - subset of the Instruction_Fetch_BW Bottleneck", - "MetricExpr": "100 * (tma_frontend_bound * (tma_fetch_bandwidth / (tma_fetch_latency + tma_fetch_bandwidth)) * (tma_dsb / (tma_mite + tma_dsb)))", + "MetricExpr": "100 * (tma_frontend_bound * (tma_fetch_bandwidth / (tma_fetch_bandwidth + tma_fetch_latency)) * (tma_dsb / (tma_dsb + tma_mite)))", "MetricGroup": "DSB;Fed;FetchBW;tma_issueFB", "MetricName": "tma_info_botlnk_l2_dsb_bandwidth", "MetricThreshold": "tma_info_botlnk_l2_dsb_bandwidth > 10", @@ -812,7 +812,7 @@ { "BriefDescription": "Total pipeline cost of DSB (uop cache) misses - subset of the Instruction_Fetch_BW Bottleneck", "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "100 * (tma_fetch_latency * tma_dsb_switches / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches) + tma_fetch_bandwidth * tma_mite / (tma_mite + tma_dsb))", + "MetricExpr": "100 * (tma_fetch_latency * tma_dsb_switches / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) + tma_fetch_bandwidth * tma_mite / (tma_dsb + tma_mite))", "MetricGroup": "DSBmiss;Fed;tma_issueFB", "MetricName": "tma_info_botlnk_l2_dsb_misses", "MetricThreshold": "tma_info_botlnk_l2_dsb_misses > 10", @@ -820,10 +820,11 @@ }, { "BriefDescription": "Total pipeline cost of Instruction Cache misses - subset of the Big_Code Bottleneck", - "MetricExpr": "100 * (tma_fetch_latency * tma_icache_misses / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches))", + "MetricExpr": "100 * (tma_fetch_latency * tma_icache_misses / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches))", "MetricGroup": "Fed;FetchLat;IcMiss;tma_issueFL", "MetricName": "tma_info_botlnk_l2_ic_misses", - "MetricThreshold": "tma_info_botlnk_l2_ic_misses > 5" + "MetricThreshold": "tma_info_botlnk_l2_ic_misses > 5", + "PublicDescription": "Total pipeline cost of Instruction Cache misses - subset of the Big_Code Bottleneck. Related metrics: " }, { "BriefDescription": "Fraction of branches that are CALL or RET", @@ -852,7 +853,7 @@ }, { "BriefDescription": "Core actual clocks when any Logical Processor is active on the Physical Core", - "MetricExpr": "(CPU_CLK_UNHALTED.THREAD_ANY / 2 if #SMT_on else tma_info_thread_clks)", + "MetricExpr": "(CPU_CLK_UNHALTED.THREAD / 2 * (1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK) if #core_wide < 1 else (CPU_CLK_UNHALTED.THREAD_ANY / 2 if #SMT_on else tma_info_thread_clks))", "MetricGroup": "SMT", "MetricName": "tma_info_core_core_clks" }, @@ -877,14 +878,14 @@ }, { "BriefDescription": "Actual per-core usage of the Floating Point non-X87 execution units (regardless of precision or vector-width)", - "MetricExpr": "(FP_ARITH_INST_RETIRED.SCALAR + cpu@FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE\\,umask\\=0xFC@) / (2 * tma_info_core_core_clks)", + "MetricExpr": "(FP_ARITH_INST_RETIRED.SCALAR + cpu@FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE\\,umask\\=0xfc@) / (2 * tma_info_core_core_clks)", "MetricGroup": "Cor;Flops;HPC", "MetricName": "tma_info_core_fp_arith_utilization", - "PublicDescription": "Actual per-core usage of the Floating Point non-X87 execution units (regardless of precision or vector-width). Values > 1 are possible due to ([BDW+] Fused-Multiply Add (FMA) counting - common; [ADL+] use all of ADD/MUL/FMA in Scalar or 128/256-bit vectors - less common)" + "PublicDescription": "Actual per-core usage of the Floating Point non-X87 execution units (regardless of precision or vector-width). Values > 1 are possible due to ([BDW+] Fused-Multiply Add (FMA) counting - common; [ADL+] use all of ADD/MUL/FMA in Scalar or 128/256-bit vectors - less common)." }, { "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is execution) per thread (logical-processor)", - "MetricExpr": "UOPS_EXECUTED.THREAD / cpu@UOPS_EXECUTED.THREAD\\,cmask\\=0x1@", + "MetricExpr": "UOPS_EXECUTED.THREAD / cpu@UOPS_EXECUTED.THREAD\\,cmask\\=1@", "MetricGroup": "Backend;Cor;Pipeline;PortsUtil", "MetricName": "tma_info_core_ilp" }, @@ -897,20 +898,20 @@ "PublicDescription": "Fraction of Uops delivered by the DSB (aka Decoded ICache; or Uop Cache). Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_inst_mix_iptb, tma_lcp" }, { - "BriefDescription": "Average number of cycles of a switch from the DSB fetch-unit to MITE fetch unit - see DSB_Switches tree node for details", + "BriefDescription": "Average number of cycles of a switch from the DSB fetch-unit to MITE fetch unit - see DSB_Switches tree node for details.", "MetricExpr": "DSB2MITE_SWITCHES.PENALTY_CYCLES / DSB2MITE_SWITCHES.COUNT", "MetricGroup": "DSBmiss", "MetricName": "tma_info_frontend_dsb_switch_cost" }, { "BriefDescription": "Average number of Uops issued by front-end when it issued something", - "MetricExpr": "UOPS_ISSUED.ANY / cpu@UOPS_ISSUED.ANY\\,cmask\\=0x1@", + "MetricExpr": "UOPS_ISSUED.ANY / cpu@UOPS_ISSUED.ANY\\,cmask\\=1@", "MetricGroup": "Fed;FetchBW", "MetricName": "tma_info_frontend_fetch_upc" }, { "BriefDescription": "Average Latency for L1 instruction cache misses", - "MetricExpr": "ICACHE_16B.IFDATA_STALL / cpu@ICACHE_16B.IFDATA_STALL\\,cmask\\=0x1\\,edge\\=0x1@ + 2", + "MetricExpr": "ICACHE_16B.IFDATA_STALL / cpu@ICACHE_16B.IFDATA_STALL\\,cmask\\=1\\,edge@ + 2", "MetricGroup": "Fed;FetchLat;IcMiss", "MetricName": "tma_info_frontend_icache_miss_latency" }, @@ -946,7 +947,7 @@ "MetricName": "tma_info_frontend_tbpc" }, { - "BriefDescription": "Branch instructions per taken branch", + "BriefDescription": "Branch instructions per taken branch.", "MetricExpr": "BR_INST_RETIRED.ALL_BRANCHES / BR_INST_RETIRED.NEAR_TAKEN", "MetricGroup": "Branches;Fed;PGO", "MetricName": "tma_info_inst_mix_bptkbranch" @@ -961,11 +962,11 @@ { "BriefDescription": "Instructions per FP Arithmetic instruction (lower number means higher occurrence rate)", "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "INST_RETIRED.ANY / (FP_ARITH_INST_RETIRED.SCALAR + cpu@FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE\\,umask\\=0xFC@)", + "MetricExpr": "INST_RETIRED.ANY / (FP_ARITH_INST_RETIRED.SCALAR + cpu@FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE\\,umask\\=0xfc@)", "MetricGroup": "Flops;InsType", "MetricName": "tma_info_inst_mix_iparith", "MetricThreshold": "tma_info_inst_mix_iparith < 10", - "PublicDescription": "Instructions per FP Arithmetic instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting. Approximated prior to BDW" + "PublicDescription": "Instructions per FP Arithmetic instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting. Approximated prior to BDW." }, { "BriefDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number means higher occurrence rate)", @@ -973,7 +974,7 @@ "MetricGroup": "Flops;FpVector;InsType", "MetricName": "tma_info_inst_mix_iparith_avx128", "MetricThreshold": "tma_info_inst_mix_iparith_avx128 < 10", - "PublicDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting" + "PublicDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting." }, { "BriefDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means higher occurrence rate)", @@ -981,7 +982,7 @@ "MetricGroup": "Flops;FpVector;InsType", "MetricName": "tma_info_inst_mix_iparith_avx256", "MetricThreshold": "tma_info_inst_mix_iparith_avx256 < 10", - "PublicDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting" + "PublicDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting." }, { "BriefDescription": "Instructions per FP Arithmetic AVX 512-bit instruction (lower number means higher occurrence rate)", @@ -989,7 +990,7 @@ "MetricGroup": "Flops;FpVector;InsType", "MetricName": "tma_info_inst_mix_iparith_avx512", "MetricThreshold": "tma_info_inst_mix_iparith_avx512 < 10", - "PublicDescription": "Instructions per FP Arithmetic AVX 512-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting" + "PublicDescription": "Instructions per FP Arithmetic AVX 512-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting." }, { "BriefDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction (lower number means higher occurrence rate)", @@ -997,7 +998,7 @@ "MetricGroup": "Flops;FpScalar;InsType", "MetricName": "tma_info_inst_mix_iparith_scalar_dp", "MetricThreshold": "tma_info_inst_mix_iparith_scalar_dp < 10", - "PublicDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting" + "PublicDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting." }, { "BriefDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction (lower number means higher occurrence rate)", @@ -1005,7 +1006,7 @@ "MetricGroup": "Flops;FpScalar;InsType", "MetricName": "tma_info_inst_mix_iparith_scalar_sp", "MetricThreshold": "tma_info_inst_mix_iparith_scalar_sp < 10", - "PublicDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting" + "PublicDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting." }, { "BriefDescription": "Instructions per Branch (lower number means higher occurrence rate)", @@ -1061,7 +1062,7 @@ "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_TAKEN", "MetricGroup": "Branches;Fed;FetchBW;Frontend;PGO;tma_issueFB", "MetricName": "tma_info_inst_mix_iptb", - "MetricThreshold": "tma_info_inst_mix_iptb < 4 * 2 + 1", + "MetricThreshold": "tma_info_inst_mix_iptb < 9", "PublicDescription": "Instructions per taken branch. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_lcp" }, { @@ -1248,8 +1249,8 @@ "MetricName": "tma_info_memory_tlb_store_stlb_mpki" }, { - "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is execution) per core", - "MetricExpr": "UOPS_EXECUTED.THREAD / (UOPS_EXECUTED.CORE_CYCLES_GE_1 / 2 if #SMT_on else cpu@UOPS_EXECUTED.THREAD\\,cmask\\=0x1@)", + "BriefDescription": "", + "MetricExpr": "UOPS_EXECUTED.THREAD / (UOPS_EXECUTED.CORE_CYCLES_GE_1 / 2 if #SMT_on else cpu@UOPS_EXECUTED.THREAD\\,cmask\\=1@)", "MetricGroup": "Cor;Pipeline;PortsUtil;SMT", "MetricName": "tma_info_pipeline_execute" }, @@ -1270,12 +1271,12 @@ "MetricExpr": "INST_RETIRED.ANY / (FP_ASSIST.ANY + OTHER_ASSISTS.ANY)", "MetricGroup": "MicroSeq;Pipeline;Ret;Retire", "MetricName": "tma_info_pipeline_ipassist", - "MetricThreshold": "tma_info_pipeline_ipassist < 100000", + "MetricThreshold": "tma_info_pipeline_ipassist < 100e3", "PublicDescription": "Instructions per a microcode Assist invocation. See Assists tree node for details (lower number means higher occurrence rate)" }, { - "BriefDescription": "Average number of Uops retired in cycles where at least one uop has retired", - "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / cpu@UOPS_RETIRED.RETIRE_SLOTS\\,cmask\\=0x1@", + "BriefDescription": "Average number of Uops retired in cycles where at least one uop has retired.", + "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / cpu@UOPS_RETIRED.RETIRE_SLOTS\\,cmask\\=1@", "MetricGroup": "Pipeline;Ret", "MetricName": "tma_info_pipeline_retire" }, @@ -1331,14 +1332,13 @@ "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.FAR_BRANCH:u", "MetricGroup": "Branches;OS", "MetricName": "tma_info_system_ipfarbranch", - "MetricThreshold": "tma_info_system_ipfarbranch < 1000000" + "MetricThreshold": "tma_info_system_ipfarbranch < 1e6" }, { "BriefDescription": "Cycles Per Instruction for the Operating System (OS) Kernel mode", "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P:k / INST_RETIRED.ANY_P:k", "MetricGroup": "OS", - "MetricName": "tma_info_system_kernel_cpi", - "ScaleUnit": "1per_instr" + "MetricName": "tma_info_system_kernel_cpi" }, { "BriefDescription": "Fraction of cycles spent in the Operating System (OS) Kernel mode", @@ -1356,7 +1356,7 @@ }, { "BriefDescription": "Average number of parallel data read requests to external memory", - "MetricExpr": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD / cha@UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD\\,thresh\\=0x1@", + "MetricExpr": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD / UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD@thresh\\=1@", "MetricGroup": "Mem;MemoryBW;SoC", "MetricName": "tma_info_system_mem_parallel_reads", "PublicDescription": "Average number of parallel data read requests to external memory. Accounts for demand loads and L1/L2 prefetches" @@ -1386,7 +1386,7 @@ "MetricExpr": "(CORE_POWER.LVL0_TURBO_LICENSE / 2 / tma_info_core_core_clks if #SMT_on else CORE_POWER.LVL0_TURBO_LICENSE / tma_info_core_core_clks)", "MetricGroup": "Power", "MetricName": "tma_info_system_power_license0_utilization", - "PublicDescription": "Fraction of Core cycles where the core was running with power-delivery for baseline license level 0. This includes non-AVX codes, SSE, AVX 128-bit, and low-current AVX 256-bit codes" + "PublicDescription": "Fraction of Core cycles where the core was running with power-delivery for baseline license level 0. This includes non-AVX codes, SSE, AVX 128-bit, and low-current AVX 256-bit codes." }, { "BriefDescription": "Fraction of Core cycles where the core was running with power-delivery for license level 1", @@ -1394,7 +1394,7 @@ "MetricGroup": "Power", "MetricName": "tma_info_system_power_license1_utilization", "MetricThreshold": "tma_info_system_power_license1_utilization > 0.5", - "PublicDescription": "Fraction of Core cycles where the core was running with power-delivery for license level 1. This includes high current AVX 256-bit instructions as well as low current AVX 512-bit instructions" + "PublicDescription": "Fraction of Core cycles where the core was running with power-delivery for license level 1. This includes high current AVX 256-bit instructions as well as low current AVX 512-bit instructions." }, { "BriefDescription": "Fraction of Core cycles where the core was running with power-delivery for license level 2 (introduced in SKX)", @@ -1402,7 +1402,7 @@ "MetricGroup": "Power", "MetricName": "tma_info_system_power_license2_utilization", "MetricThreshold": "tma_info_system_power_license2_utilization > 0.5", - "PublicDescription": "Fraction of Core cycles where the core was running with power-delivery for license level 2 (introduced in SKX). This includes high current AVX 512-bit instructions" + "PublicDescription": "Fraction of Core cycles where the core was running with power-delivery for license level 2 (introduced in SKX). This includes high current AVX 512-bit instructions." }, { "BriefDescription": "Fraction of cycles where both hardware Logical Processors were active", @@ -1436,7 +1436,7 @@ "MetricName": "tma_info_system_uncore_frequency" }, { - "BriefDescription": "Per-Logical Processor actual clocks when the Logical Processor is active", + "BriefDescription": "Per-Logical Processor actual clocks when the Logical Processor is active.", "MetricExpr": "CPU_CLK_UNHALTED.THREAD", "MetricGroup": "Pipeline", "MetricName": "tma_info_thread_clks" @@ -1445,15 +1445,14 @@ "BriefDescription": "Cycles Per Instruction (per Logical Processor)", "MetricExpr": "1 / tma_info_thread_ipc", "MetricGroup": "Mem;Pipeline", - "MetricName": "tma_info_thread_cpi", - "ScaleUnit": "1per_instr" + "MetricName": "tma_info_thread_cpi" }, { "BriefDescription": "The ratio of Executed- by Issued-Uops", "MetricExpr": "UOPS_EXECUTED.THREAD / UOPS_ISSUED.ANY", "MetricGroup": "Cor;Pipeline", "MetricName": "tma_info_thread_execute_per_issue", - "PublicDescription": "The ratio of Executed- by Issued-Uops. Ratio > 1 suggests high rate of uop micro-fusions. Ratio < 1 suggest high rate of \"execute\" at rename stage" + "PublicDescription": "The ratio of Executed- by Issued-Uops. Ratio > 1 suggests high rate of uop micro-fusions. Ratio < 1 suggest high rate of \"execute\" at rename stage." }, { "BriefDescription": "Instructions Per Cycle (per Logical Processor)", @@ -1479,15 +1478,15 @@ "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / BR_INST_RETIRED.NEAR_TAKEN", "MetricGroup": "Branches;Fed;FetchBW", "MetricName": "tma_info_thread_uptb", - "MetricThreshold": "tma_info_thread_uptb < 4 * 1.5" + "MetricThreshold": "tma_info_thread_uptb < 6" }, { "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to Instruction TLB (ITLB) misses", "MetricExpr": "ICACHE_TAG.STALLS / tma_info_thread_clks", "MetricGroup": "BigFootprint;BvBC;FetchLat;MemoryTLB;TopdownL3;tma_L3_group;tma_fetch_latency_group", "MetricName": "tma_itlb_misses", - "MetricThreshold": "tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", - "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Instruction TLB (ITLB) misses. Sample with: FRONTEND_RETIRED.STLB_MISS, FRONTEND_RETIRED.ITLB_MISS", + "MetricThreshold": "tma_itlb_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Instruction TLB (ITLB) misses. Sample with: FRONTEND_RETIRED.STLB_MISS_PS;FRONTEND_RETIRED.ITLB_MISS_PS", "ScaleUnit": "100%" }, { @@ -1495,7 +1494,7 @@ "MetricExpr": "max((CYCLE_ACTIVITY.STALLS_MEM_ANY - CYCLE_ACTIVITY.STALLS_L1D_MISS) / tma_info_thread_clks, 0)", "MetricGroup": "CacheHits;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_issueL1;tma_issueMC;tma_memory_bound_group", "MetricName": "tma_l1_bound", - "MetricThreshold": "tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", "PublicDescription": "This metric estimates how often the CPU was stalled without loads missing the L1 Data (L1D) cache. The L1D cache typically has the shortest latency. However; in certain cases like loads blocked on older stores; a load might suffer due to high latency even though it is being satisfied by the L1D. Another example is loads who miss in the TLB. These cases are characterized by execution unit stalls; while some non-completed demand load lives in the machine without having that demand load missing the L1 cache. Sample with: MEM_LOAD_RETIRED.L1_HIT. Related metrics: tma_clears_resteers, tma_machine_clears, tma_microcode_sequencer, tma_ms_switches, tma_ports_utilized_1", "ScaleUnit": "100%" }, @@ -1504,17 +1503,17 @@ "MetricExpr": "min(2 * (MEM_INST_RETIRED.ALL_LOADS - MEM_LOAD_RETIRED.FB_HIT - MEM_LOAD_RETIRED.L1_MISS) * 20 / 100, max(CYCLE_ACTIVITY.CYCLES_MEM_ANY - CYCLE_ACTIVITY.CYCLES_L1D_MISS, 0)) / tma_info_thread_clks", "MetricGroup": "BvML;MemoryLat;TopdownL4;tma_L4_group;tma_l1_bound_group", "MetricName": "tma_l1_latency_dependency", - "MetricThreshold": "tma_l1_latency_dependency > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_l1_latency_dependency > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", "PublicDescription": "This metric([SKL+] roughly; [LNL]) estimates fraction of cycles with demand load accesses that hit the L1D cache. The short latency of the L1D cache may be exposed in pointer-chasing memory access patterns as an example. Sample with: MEM_LOAD_RETIRED.L1_HIT", "ScaleUnit": "100%" }, { "BriefDescription": "This metric estimates how often the CPU was stalled due to L2 cache accesses by loads", "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "MEM_LOAD_RETIRED.L2_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) / (MEM_LOAD_RETIRED.L2_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) + cpu@L1D_PEND_MISS.FB_FULL\\,cmask\\=0x1@) * ((CYCLE_ACTIVITY.STALLS_L1D_MISS - CYCLE_ACTIVITY.STALLS_L2_MISS) / tma_info_thread_clks)", + "MetricExpr": "MEM_LOAD_RETIRED.L2_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) / (MEM_LOAD_RETIRED.L2_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) + cpu@L1D_PEND_MISS.FB_FULL\\,cmask\\=1@) * ((CYCLE_ACTIVITY.STALLS_L1D_MISS - CYCLE_ACTIVITY.STALLS_L2_MISS) / tma_info_thread_clks)", "MetricGroup": "BvML;CacheHits;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_l2_bound", - "MetricThreshold": "tma_l2_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_l2_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", "PublicDescription": "This metric estimates how often the CPU was stalled due to L2 cache accesses by loads. Avoiding cache misses (i.e. L1 misses/L2 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L2_HIT", "ScaleUnit": "100%" }, @@ -1523,7 +1522,7 @@ "MetricExpr": "3.5 * tma_info_system_core_frequency * MEM_LOAD_RETIRED.L2_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks", "MetricGroup": "MemoryLat;TopdownL4;tma_L4_group;tma_l2_bound_group", "MetricName": "tma_l2_hit_latency", - "MetricThreshold": "tma_l2_hit_latency > 0.05 & tma_l2_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_l2_hit_latency > 0.05 & (tma_l2_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", "PublicDescription": "This metric represents fraction of cycles with demand load accesses that hit the L2 cache under unloaded scenarios (possibly L2 latency limited). Avoiding L1 cache misses (i.e. L1 misses/L2 hits) will improve the latency. Sample with: MEM_LOAD_RETIRED.L2_HIT", "ScaleUnit": "100%" }, @@ -1532,17 +1531,17 @@ "MetricExpr": "(CYCLE_ACTIVITY.STALLS_L2_MISS - CYCLE_ACTIVITY.STALLS_L3_MISS) / tma_info_thread_clks", "MetricGroup": "CacheHits;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_l3_bound", - "MetricThreshold": "tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", - "PublicDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core. Avoiding cache misses (i.e. L2 misses/L3 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L3_HIT", + "MetricThreshold": "tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", + "PublicDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core. Avoiding cache misses (i.e. L2 misses/L3 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L3_HIT_PS", "ScaleUnit": "100%" }, { "BriefDescription": "This metric estimates fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited)", - "MetricExpr": "(20.5 * tma_info_system_core_frequency - 3.5 * tma_info_system_core_frequency) * (MEM_LOAD_RETIRED.L3_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2)) / tma_info_thread_clks", + "MetricExpr": "17 * tma_info_system_core_frequency * (MEM_LOAD_RETIRED.L3_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2)) / tma_info_thread_clks", "MetricGroup": "BvML;MemoryLat;TopdownL4;tma_L4_group;tma_issueLat;tma_l3_bound_group", "MetricName": "tma_l3_hit_latency", - "MetricThreshold": "tma_l3_hit_latency > 0.1 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", - "PublicDescription": "This metric estimates fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited). Avoiding private cache misses (i.e. L2 misses/L3 hits) will improve the latency; reduce contention with sibling physical cores and increase performance. Note the value of this node may overlap with its siblings. Sample with: MEM_LOAD_RETIRED.L3_HIT. Related metrics: tma_bottleneck_cache_memory_latency, tma_branch_resteers, tma_mem_latency, tma_store_latency", + "MetricThreshold": "tma_l3_hit_latency > 0.1 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric estimates fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited). Avoiding private cache misses (i.e. L2 misses/L3 hits) will improve the latency; reduce contention with sibling physical cores and increase performance. Note the value of this node may overlap with its siblings. Sample with: MEM_LOAD_RETIRED.L3_HIT_PS. Related metrics: tma_bottleneck_cache_memory_latency, tma_mem_latency", "ScaleUnit": "100%" }, { @@ -1550,18 +1549,18 @@ "MetricExpr": "DECODE.LCP / tma_info_thread_clks", "MetricGroup": "FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueFB", "MetricName": "tma_lcp", - "MetricThreshold": "tma_lcp > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", - "PublicDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs). Using proper compiler flags or Intel Compiler by default will certainly avoid this. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb", + "MetricThreshold": "tma_lcp > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", + "PublicDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs). Using proper compiler flags or Intel Compiler by default will certainly avoid this. #Link: Optimization Guide about LCP BKMs. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations , instructions that require no more than one uop (micro-operation)", + "BriefDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation)", "MetricExpr": "tma_retiring - tma_heavy_operations", "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_light_operations", "MetricThreshold": "tma_light_operations > 0.6", "MetricgroupNoGroup": "TopdownL2", - "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations , instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized code running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. ([ICL+] Note this may undercount due to approximation using indirect events; [ADL+] .). Sample with: INST_RETIRED.PREC_DIST", + "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized code running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. ([ICL+] Note this may undercount due to approximation using indirect events; [ADL+] .). Sample with: INST_RETIRED.PREC_DIST", "ScaleUnit": "100%" }, { @@ -1579,7 +1578,7 @@ "MetricExpr": "tma_dtlb_load - tma_load_stlb_miss", "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_load_group", "MetricName": "tma_load_stlb_hit", - "MetricThreshold": "tma_load_stlb_hit > 0.05 & tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_load_stlb_hit > 0.05 & (tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))", "ScaleUnit": "100%" }, { @@ -1587,39 +1586,39 @@ "MetricExpr": "DTLB_LOAD_MISSES.WALK_ACTIVE / tma_info_thread_clks", "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_load_group", "MetricName": "tma_load_stlb_miss", - "MetricThreshold": "tma_load_stlb_miss > 0.05 & tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_load_stlb_miss > 0.05 & (tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 1 GB pages for data load accesses", + "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 1 GB pages for data load accesses.", "MetricExpr": "tma_load_stlb_miss * DTLB_LOAD_MISSES.WALK_COMPLETED_1G / (DTLB_LOAD_MISSES.WALK_COMPLETED_4K + DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M + DTLB_LOAD_MISSES.WALK_COMPLETED_1G)", "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_load_stlb_miss_group", "MetricName": "tma_load_stlb_miss_1g", - "MetricThreshold": "tma_load_stlb_miss_1g > 0.05 & tma_load_stlb_miss > 0.05 & tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_load_stlb_miss_1g > 0.05 & (tma_load_stlb_miss > 0.05 & (tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))))", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 2 or 4 MB pages for data load accesses", + "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 2 or 4 MB pages for data load accesses.", "MetricExpr": "tma_load_stlb_miss * DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M / (DTLB_LOAD_MISSES.WALK_COMPLETED_4K + DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M + DTLB_LOAD_MISSES.WALK_COMPLETED_1G)", "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_load_stlb_miss_group", "MetricName": "tma_load_stlb_miss_2m", - "MetricThreshold": "tma_load_stlb_miss_2m > 0.05 & tma_load_stlb_miss > 0.05 & tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_load_stlb_miss_2m > 0.05 & (tma_load_stlb_miss > 0.05 & (tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))))", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 4 KB pages for data load accesses", + "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 4 KB pages for data load accesses.", "MetricExpr": "tma_load_stlb_miss * DTLB_LOAD_MISSES.WALK_COMPLETED_4K / (DTLB_LOAD_MISSES.WALK_COMPLETED_4K + DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M + DTLB_LOAD_MISSES.WALK_COMPLETED_1G)", "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_load_stlb_miss_group", "MetricName": "tma_load_stlb_miss_4k", - "MetricThreshold": "tma_load_stlb_miss_4k > 0.05 & tma_load_stlb_miss > 0.05 & tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_load_stlb_miss_4k > 0.05 & (tma_load_stlb_miss > 0.05 & (tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))))", "ScaleUnit": "100%" }, { "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from local memory", - "MetricExpr": "(80 * tma_info_system_core_frequency - 20.5 * tma_info_system_core_frequency) * MEM_LOAD_L3_MISS_RETIRED.LOCAL_DRAM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks", + "MetricExpr": "59.5 * tma_info_system_core_frequency * MEM_LOAD_L3_MISS_RETIRED.LOCAL_DRAM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks", "MetricGroup": "Server;TopdownL5;tma_L5_group;tma_mem_latency_group", "MetricName": "tma_local_mem", - "MetricThreshold": "tma_local_mem > 0.1 & tma_mem_latency > 0.1 & tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_local_mem > 0.1 & (tma_mem_latency > 0.1 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))", "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from local memory. Caching will improve the latency and increase performance. Sample with: MEM_LOAD_L3_MISS_RETIRED.LOCAL_DRAM", "ScaleUnit": "100%" }, @@ -1628,7 +1627,7 @@ "MetricExpr": "(12 * max(0, MEM_INST_RETIRED.LOCK_LOADS - L2_RQSTS.ALL_RFO) + MEM_INST_RETIRED.LOCK_LOADS / MEM_INST_RETIRED.ALL_STORES * (11 * L2_RQSTS.RFO_HIT + min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO))) / tma_info_thread_clks", "MetricGroup": "LockCont;Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_l1_bound_group", "MetricName": "tma_lock_latency", - "MetricThreshold": "tma_lock_latency > 0.2 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_lock_latency > 0.2 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", "PublicDescription": "This metric represents fraction of cycles the CPU spent handling cache misses due to lock operations. Due to the microarchitecture handling of locks; they are classified as L1_Bound regardless of what memory source satisfied them. Sample with: MEM_INST_RETIRED.LOCK_LOADS. Related metrics: tma_store_latency", "ScaleUnit": "100%" }, @@ -1645,10 +1644,10 @@ }, { "BriefDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory - DRAM ([SPR-HBM] and/or HBM)", - "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, cpu@OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD\\,cmask\\=0x4@) / tma_info_thread_clks", + "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, cpu@OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD\\,cmask\\=4@) / tma_info_thread_clks", "MetricGroup": "BvMB;MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueBW", "MetricName": "tma_mem_bandwidth", - "MetricThreshold": "tma_mem_bandwidth > 0.2 & tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_mem_bandwidth > 0.2 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", "PublicDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory - DRAM ([SPR-HBM] and/or HBM). The underlying heuristic assumes that a similar off-core traffic is generated by all IA cores. This metric does not aggregate non-data-read requests by this logical processor; requests from other IA Logical Processors/Physical Cores/sockets; or other non-IA devices like GPU; hence the maximum external memory bandwidth limits may or may not be approached when this metric is flagged (see Uncore counters for that). Related metrics: tma_bottleneck_cache_memory_bandwidth, tma_fb_full, tma_info_system_dram_bw_use, tma_sq_full", "ScaleUnit": "100%" }, @@ -1657,7 +1656,7 @@ "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD) / tma_info_thread_clks - tma_mem_bandwidth", "MetricGroup": "BvML;MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueLat", "MetricName": "tma_mem_latency", - "MetricThreshold": "tma_mem_latency > 0.1 & tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_mem_latency > 0.1 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", "PublicDescription": "This metric estimates fraction of cycles where the performance was likely hurt due to latency from external memory - DRAM ([SPR-HBM] and/or HBM). This metric does not aggregate requests from other Logical Processors/Physical Cores/sockets (see Uncore counters for that). Related metrics: tma_bottleneck_cache_memory_latency, tma_l3_hit_latency", "ScaleUnit": "100%" }, @@ -1669,11 +1668,11 @@ "MetricName": "tma_memory_bound", "MetricThreshold": "tma_memory_bound > 0.2 & tma_backend_bound > 0.2", "MetricgroupNoGroup": "TopdownL2", - "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck. Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two)", + "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck. Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two).", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of slots where the CPU was retiring memory operations , uops for memory load or store accesses", + "BriefDescription": "This metric represents fraction of slots where the CPU was retiring memory operations -- uops for memory load or store accesses.", "MetricExpr": "tma_light_operations * MEM_INST_RETIRED.ANY / INST_RETIRED.ANY", "MetricGroup": "Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group", "MetricName": "tma_memory_operations", @@ -1695,7 +1694,7 @@ "MetricExpr": "BR_MISP_RETIRED.ALL_BRANCHES / (BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT) * INT_MISC.CLEAR_RESTEER_CYCLES / tma_info_thread_clks", "MetricGroup": "BadSpec;BrMispredicts;BvMP;TopdownL4;tma_L4_group;tma_branch_resteers_group;tma_issueBM", "MetricName": "tma_mispredicts_resteers", - "MetricThreshold": "tma_mispredicts_resteers > 0.05 & tma_branch_resteers > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricThreshold": "tma_mispredicts_resteers > 0.05 & (tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))", "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Branch Misprediction at execution stage. Sample with: INT_MISC.CLEAR_RESTEER_CYCLES. Related metrics: tma_bottleneck_mispredictions, tma_branch_mispredicts, tma_info_bad_spec_branch_misprediction_cost", "ScaleUnit": "100%" }, @@ -1709,12 +1708,12 @@ "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates penalty in terms of percentage of([SKL+] injected blend uops out of all Uops Issued , the Count Domain; [ADL+] cycles)", + "BriefDescription": "This metric estimates penalty in terms of percentage of([SKL+] injected blend uops out of all Uops Issued -- the Count Domain; [ADL+] cycles)", "MetricExpr": "UOPS_ISSUED.VECTOR_WIDTH_MISMATCH / UOPS_ISSUED.ANY", "MetricGroup": "TopdownL5;tma_L5_group;tma_issueMV;tma_ports_utilized_0_group", "MetricName": "tma_mixing_vectors", "MetricThreshold": "tma_mixing_vectors > 0.05", - "PublicDescription": "This metric estimates penalty in terms of percentage of([SKL+] injected blend uops out of all Uops Issued , the Count Domain; [ADL+] cycles). Usually a Mixing_Vectors over 5% is worth investigating. Read more in Appendix B1 of the Optimizations Guide for this topic. Related metrics: tma_ms_switches", + "PublicDescription": "This metric estimates penalty in terms of percentage of([SKL+] injected blend uops out of all Uops Issued -- the Count Domain; [ADL+] cycles). Usually a Mixing_Vectors over 5% is worth investigating. Read more in Appendix B1 of the Optimizations Guide for this topic. Related metrics: tma_ms_switches", "ScaleUnit": "100%" }, { @@ -1722,7 +1721,7 @@ "MetricExpr": "2 * IDQ.MS_SWITCHES / tma_info_thread_clks", "MetricGroup": "FetchLat;MicroSeq;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueMC;tma_issueMS;tma_issueMV;tma_issueSO", "MetricName": "tma_ms_switches", - "MetricThreshold": "tma_ms_switches > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricThreshold": "tma_ms_switches > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", "PublicDescription": "This metric estimates the fraction of cycles when the CPU was stalled due to switches of uop delivery to the Microcode Sequencer (MS). Commonly used instructions are optimized for delivery by the DSB (decoded i-cache) or MITE (legacy instruction decode) pipelines. Certain operations cannot be handled natively by the execution pipeline; and must be performed by microcode (small programs injected into the execution stream). Switching to the MS too often can negatively impact performance. The MS is designated to deliver long uop flows required by CISC instructions like CPUID; or uncommon conditions like Floating Point Assists when dealing with Denormals. Sample with: IDQ.MS_SWITCHES. Related metrics: tma_bottleneck_irregular_overhead, tma_clears_resteers, tma_l1_bound, tma_machine_clears, tma_microcode_sequencer, tma_mixing_vectors, tma_serializing_operation", "ScaleUnit": "100%" }, @@ -1732,7 +1731,7 @@ "MetricGroup": "Branches;BvBO;Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group", "MetricName": "tma_non_fused_branches", "MetricThreshold": "tma_non_fused_branches > 0.1 & tma_light_operations > 0.6", - "PublicDescription": "This metric represents fraction of slots where the CPU was retiring branch instructions that were not fused. Non-conditional branches like direct JMP or CALL would count here. Can be used to examine fusible conditional jumps that were not fused", + "PublicDescription": "This metric represents fraction of slots where the CPU was retiring branch instructions that were not fused. Non-conditional branches like direct JMP or CALL would count here. Can be used to examine fusible conditional jumps that were not fused.", "ScaleUnit": "100%" }, { @@ -1740,8 +1739,8 @@ "MetricExpr": "tma_light_operations * INST_RETIRED.NOP / UOPS_RETIRED.RETIRE_SLOTS", "MetricGroup": "BvBO;Pipeline;TopdownL4;tma_L4_group;tma_other_light_ops_group", "MetricName": "tma_nop_instructions", - "MetricThreshold": "tma_nop_instructions > 0.1 & tma_other_light_ops > 0.3 & tma_light_operations > 0.6", - "PublicDescription": "This metric represents fraction of slots where the CPU was retiring NOP (no op) instructions. Compilers often use NOPs for certain address alignments - e.g. start address of a function or loop body. Sample with: INST_RETIRED.NOP", + "MetricThreshold": "tma_nop_instructions > 0.1 & (tma_other_light_ops > 0.3 & tma_light_operations > 0.6)", + "PublicDescription": "This metric represents fraction of slots where the CPU was retiring NOP (no op) instructions. Compilers often use NOPs for certain address alignments - e.g. start address of a function or loop body. Sample with: INST_RETIRED.NOP_PS", "ScaleUnit": "100%" }, { @@ -1754,19 +1753,19 @@ "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates fraction of slots the CPU was stalled due to other cases of misprediction (non-retired x86 branches or other types)", + "BriefDescription": "This metric estimates fraction of slots the CPU was stalled due to other cases of misprediction (non-retired x86 branches or other types).", "MetricExpr": "max(tma_branch_mispredicts * (1 - BR_MISP_RETIRED.ALL_BRANCHES / (INT_MISC.CLEARS_COUNT - MACHINE_CLEARS.COUNT)), 0.0001)", "MetricGroup": "BrMispredicts;BvIO;TopdownL3;tma_L3_group;tma_branch_mispredicts_group", "MetricName": "tma_other_mispredicts", - "MetricThreshold": "tma_other_mispredicts > 0.05 & tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", + "MetricThreshold": "tma_other_mispredicts > 0.05 & (tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15)", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of slots the CPU has wasted due to Nukes (Machine Clears) not related to memory ordering", + "BriefDescription": "This metric represents fraction of slots the CPU has wasted due to Nukes (Machine Clears) not related to memory ordering.", "MetricExpr": "max(tma_machine_clears * (1 - MACHINE_CLEARS.MEMORY_ORDERING / MACHINE_CLEARS.COUNT), 0.0001)", "MetricGroup": "BvIO;Machine_Clears;TopdownL3;tma_L3_group;tma_machine_clears_group", "MetricName": "tma_other_nukes", - "MetricThreshold": "tma_other_nukes > 0.05 & tma_machine_clears > 0.1 & tma_bad_speculation > 0.15", + "MetricThreshold": "tma_other_nukes > 0.05 & (tma_machine_clears > 0.1 & tma_bad_speculation > 0.15)", "ScaleUnit": "100%" }, { @@ -1775,7 +1774,7 @@ "MetricGroup": "Compute;TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P", "MetricName": "tma_port_0", "MetricThreshold": "tma_port_0 > 0.6", - "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 0 ([SNB+] ALU; [HSW+] ALU and 2nd branch). Sample with: UOPS_DISPATCHED_PORT.PORT_0. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", + "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 0 ([SNB+] ALU; [HSW+] ALU and 2nd branch). Sample with: UOPS_DISPATCHED.PORT_0. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%" }, { @@ -1784,7 +1783,7 @@ "MetricGroup": "TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P", "MetricName": "tma_port_1", "MetricThreshold": "tma_port_1 > 0.6", - "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 1 (ALU). Sample with: UOPS_DISPATCHED_PORT.PORT_1. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_5, tma_port_6, tma_ports_utilized_2", + "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 1 (ALU). Sample with: UOPS_DISPATCHED.PORT_1. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_5, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%" }, { @@ -1820,7 +1819,7 @@ "MetricGroup": "TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P", "MetricName": "tma_port_5", "MetricThreshold": "tma_port_5 > 0.6", - "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 5 ([SNB+] Branches and ALU; [HSW+] ALU). Sample with: UOPS_DISPATCHED_PORT.PORT_5. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_6, tma_ports_utilized_2", + "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 5 ([SNB+] Branches and ALU; [HSW+] ALU). Sample with: UOPS_DISPATCHED.PORT_5. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%" }, { @@ -1829,7 +1828,7 @@ "MetricGroup": "TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P", "MetricName": "tma_port_6", "MetricThreshold": "tma_port_6 > 0.6", - "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 6 ([HSW+] Primary Branch and simple ALU). Sample with: UOPS_DISPATCHED_PORT.PORT_1. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_ports_utilized_2", + "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 6 ([HSW+] Primary Branch and simple ALU). Sample with: UOPS_DISPATCHED.PORT_1. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_ports_utilized_2", "ScaleUnit": "100%" }, { @@ -1846,8 +1845,8 @@ "MetricExpr": "((tma_ports_utilized_0 * tma_info_thread_clks + (EXE_ACTIVITY.1_PORTS_UTIL + tma_retiring * EXE_ACTIVITY.2_PORTS_UTIL)) / tma_info_thread_clks if ARITH.DIVIDER_ACTIVE < CYCLE_ACTIVITY.STALLS_TOTAL - CYCLE_ACTIVITY.STALLS_MEM_ANY else (EXE_ACTIVITY.1_PORTS_UTIL + tma_retiring * EXE_ACTIVITY.2_PORTS_UTIL) / tma_info_thread_clks)", "MetricGroup": "PortsUtil;TopdownL3;tma_L3_group;tma_core_bound_group", "MetricName": "tma_ports_utilization", - "MetricThreshold": "tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", - "PublicDescription": "This metric estimates fraction of cycles the CPU performance was potentially limited due to Core computation issues (non divider-related). Two distinct categories can be attributed into this metric: (1) heavy data-dependency among contiguous instructions would manifest in this metric - such cases are often referred to as low Instruction Level Parallelism (ILP). (2) Contention on some hardware execution unit other than Divider. For example; when there are too many multiply operations", + "MetricThreshold": "tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)", + "PublicDescription": "This metric estimates fraction of cycles the CPU performance was potentially limited due to Core computation issues (non divider-related). Two distinct categories can be attributed into this metric: (1) heavy data-dependency among contiguous instructions would manifest in this metric - such cases are often referred to as low Instruction Level Parallelism (ILP). (2) Contention on some hardware execution unit other than Divider. For example; when there are too many multiply operations.", "ScaleUnit": "100%" }, { @@ -1855,8 +1854,8 @@ "MetricExpr": "EXE_ACTIVITY.EXE_BOUND_0_PORTS / tma_info_thread_clks", "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group", "MetricName": "tma_ports_utilized_0", - "MetricThreshold": "tma_ports_utilized_0 > 0.2 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", - "PublicDescription": "This metric represents fraction of cycles CPU executed no uops on any execution port (Logical Processor cycles since ICL, Physical Core cycles otherwise). Long-latency instructions like divides may contribute to this metric", + "MetricThreshold": "tma_ports_utilized_0 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric represents fraction of cycles CPU executed no uops on any execution port (Logical Processor cycles since ICL, Physical Core cycles otherwise). Long-latency instructions like divides may contribute to this metric.", "ScaleUnit": "100%" }, { @@ -1864,7 +1863,7 @@ "MetricExpr": "((UOPS_EXECUTED.CORE_CYCLES_GE_1 - UOPS_EXECUTED.CORE_CYCLES_GE_2) / 2 if #SMT_on else EXE_ACTIVITY.1_PORTS_UTIL) / tma_info_core_core_clks", "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_issueL1;tma_ports_utilization_group", "MetricName": "tma_ports_utilized_1", - "MetricThreshold": "tma_ports_utilized_1 > 0.2 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_ports_utilized_1 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", "PublicDescription": "This metric represents fraction of cycles where the CPU executed total of 1 uop per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise). This can be due to heavy data-dependency among software instructions; or over oversubscribing a particular hardware resource. In some other cases with high 1_Port_Utilized and L1_Bound; this metric can point to L1 data-cache latency bottleneck that may not necessarily manifest with complete execution starvation (due to the short L1 latency e.g. walking a linked list) - looking at the assembly can be helpful. Related metrics: tma_l1_bound", "ScaleUnit": "100%" }, @@ -1873,35 +1872,35 @@ "MetricExpr": "((UOPS_EXECUTED.CORE_CYCLES_GE_2 - UOPS_EXECUTED.CORE_CYCLES_GE_3) / 2 if #SMT_on else EXE_ACTIVITY.2_PORTS_UTIL) / tma_info_core_core_clks", "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_issue2P;tma_ports_utilization_group", "MetricName": "tma_ports_utilized_2", - "MetricThreshold": "tma_ports_utilized_2 > 0.15 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_ports_utilized_2 > 0.15 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", "PublicDescription": "This metric represents fraction of cycles CPU executed total of 2 uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise). Loop Vectorization -most compilers feature auto-Vectorization options today- reduces pressure on the execution ports as multiple elements are calculated with same uop. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of cycles CPU executed total of 3 or more uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise)", + "BriefDescription": "This metric represents fraction of cycles CPU executed total of 3 or more uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise).", "MetricExpr": "(UOPS_EXECUTED.CORE_CYCLES_GE_3 / 2 if #SMT_on else UOPS_EXECUTED.CORE_CYCLES_GE_3) / tma_info_core_core_clks", "MetricGroup": "BvCB;PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group", "MetricName": "tma_ports_utilized_3m", - "MetricThreshold": "tma_ports_utilized_3m > 0.4 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_ports_utilized_3m > 0.4 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", "ScaleUnit": "100%" }, { "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from remote cache in other sockets including synchronizations issues", "MetricConstraint": "NO_GROUP_EVENTS_NMI", - "MetricExpr": "((110 * tma_info_system_core_frequency - 20.5 * tma_info_system_core_frequency) * MEM_LOAD_L3_MISS_RETIRED.REMOTE_HITM + (110 * tma_info_system_core_frequency - 20.5 * tma_info_system_core_frequency) * MEM_LOAD_L3_MISS_RETIRED.REMOTE_FWD) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks", + "MetricExpr": "(89.5 * tma_info_system_core_frequency * MEM_LOAD_L3_MISS_RETIRED.REMOTE_HITM + 89.5 * tma_info_system_core_frequency * MEM_LOAD_L3_MISS_RETIRED.REMOTE_FWD) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks", "MetricGroup": "Offcore;Server;Snoop;TopdownL5;tma_L5_group;tma_issueSyncxn;tma_mem_latency_group", "MetricName": "tma_remote_cache", - "MetricThreshold": "tma_remote_cache > 0.05 & tma_mem_latency > 0.1 & tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", - "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from remote cache in other sockets including synchronizations issues. This is caused often due to non-optimal NUMA allocations. Sample with: MEM_LOAD_L3_MISS_RETIRED.REMOTE_HITM, MEM_LOAD_L3_MISS_RETIRED.REMOTE_FWD. Related metrics: tma_bottleneck_memory_synchronization, tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_machine_clears", + "MetricThreshold": "tma_remote_cache > 0.05 & (tma_mem_latency > 0.1 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))", + "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from remote cache in other sockets including synchronizations issues. This is caused often due to non-optimal NUMA allocations. #link to NUMA article. Sample with: MEM_LOAD_L3_MISS_RETIRED.REMOTE_HITM_PS;MEM_LOAD_L3_MISS_RETIRED.REMOTE_FWD_PS. Related metrics: tma_bottleneck_memory_synchronization, tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_machine_clears", "ScaleUnit": "100%" }, { "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from remote memory", - "MetricExpr": "(147.5 * tma_info_system_core_frequency - 20.5 * tma_info_system_core_frequency) * MEM_LOAD_L3_MISS_RETIRED.REMOTE_DRAM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks", + "MetricExpr": "127 * tma_info_system_core_frequency * MEM_LOAD_L3_MISS_RETIRED.REMOTE_DRAM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks", "MetricGroup": "Server;Snoop;TopdownL5;tma_L5_group;tma_mem_latency_group", "MetricName": "tma_remote_mem", - "MetricThreshold": "tma_remote_mem > 0.1 & tma_mem_latency > 0.1 & tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", - "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from remote memory. This is caused often due to non-optimal NUMA allocations. Sample with: MEM_LOAD_L3_MISS_RETIRED.REMOTE_DRAM", + "MetricThreshold": "tma_remote_mem > 0.1 & (tma_mem_latency > 0.1 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))", + "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from remote memory. This is caused often due to non-optimal NUMA allocations. #link to NUMA article. Sample with: MEM_LOAD_L3_MISS_RETIRED.REMOTE_DRAM_PS", "ScaleUnit": "100%" }, { @@ -1919,7 +1918,7 @@ "MetricExpr": "PARTIAL_RAT_STALLS.SCOREBOARD / tma_info_thread_clks", "MetricGroup": "BvIO;PortsUtil;TopdownL3;tma_L3_group;tma_core_bound_group;tma_issueSO", "MetricName": "tma_serializing_operation", - "MetricThreshold": "tma_serializing_operation > 0.1 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_serializing_operation > 0.1 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)", "PublicDescription": "This metric represents fraction of cycles the CPU issue-pipeline was stalled due to serializing operations. Instructions like CPUID; WRMSR or LFENCE serialize the out-of-order execution which may limit performance. Sample with: PARTIAL_RAT_STALLS.SCOREBOARD. Related metrics: tma_ms_switches", "ScaleUnit": "100%" }, @@ -1928,8 +1927,8 @@ "MetricExpr": "40 * ROB_MISC_EVENTS.PAUSE_INST / tma_info_thread_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_serializing_operation_group", "MetricName": "tma_slow_pause", - "MetricThreshold": "tma_slow_pause > 0.05 & tma_serializing_operation > 0.1 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", - "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to PAUSE Instructions. Sample with: ROB_MISC_EVENTS.PAUSE_INST", + "MetricThreshold": "tma_slow_pause > 0.05 & (tma_serializing_operation > 0.1 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to PAUSE Instructions. Sample with: MISC_RETIRED.PAUSE_INST", "ScaleUnit": "100%" }, { @@ -1939,7 +1938,7 @@ "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group", "MetricName": "tma_split_loads", "MetricThreshold": "tma_split_loads > 0.3", - "PublicDescription": "This metric estimates fraction of cycles handling memory load split accesses - load that cross 64-byte cache line boundary. Sample with: MEM_INST_RETIRED.SPLIT_LOADS", + "PublicDescription": "This metric estimates fraction of cycles handling memory load split accesses - load that cross 64-byte cache line boundary. Sample with: MEM_INST_RETIRED.SPLIT_LOADS_PS", "ScaleUnit": "100%" }, { @@ -1947,8 +1946,8 @@ "MetricExpr": "MEM_INST_RETIRED.SPLIT_STORES / tma_info_core_core_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_issueSpSt;tma_store_bound_group", "MetricName": "tma_split_stores", - "MetricThreshold": "tma_split_stores > 0.2 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", - "PublicDescription": "This metric represents rate of split store accesses. Consider aligning your data to the 64-byte cache line granularity. Sample with: MEM_INST_RETIRED.SPLIT_STORES. Related metrics: tma_port_4", + "MetricThreshold": "tma_split_stores > 0.2 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric represents rate of split store accesses. Consider aligning your data to the 64-byte cache line granularity. Sample with: MEM_INST_RETIRED.SPLIT_STORES_PS. Related metrics: tma_port_4", "ScaleUnit": "100%" }, { @@ -1956,7 +1955,7 @@ "MetricExpr": "(OFFCORE_REQUESTS_BUFFER.SQ_FULL / 2 if #SMT_on else OFFCORE_REQUESTS_BUFFER.SQ_FULL) / tma_info_core_core_clks", "MetricGroup": "BvMB;MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_issueBW;tma_l3_bound_group", "MetricName": "tma_sq_full", - "MetricThreshold": "tma_sq_full > 0.3 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_sq_full > 0.3 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", "PublicDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors). Related metrics: tma_bottleneck_cache_memory_bandwidth, tma_fb_full, tma_info_system_dram_bw_use, tma_mem_bandwidth", "ScaleUnit": "100%" }, @@ -1965,8 +1964,8 @@ "MetricExpr": "EXE_ACTIVITY.BOUND_ON_STORES / tma_info_thread_clks", "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_store_bound", - "MetricThreshold": "tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", - "PublicDescription": "This metric estimates how often CPU was stalled due to RFO store memory accesses; RFO store issue a read-for-ownership request before the write. Even though store accesses do not typically stall out-of-order CPUs; there are few cases where stores can lead to actual stalls. This metric will be flagged should RFO stores be a bottleneck. Sample with: MEM_INST_RETIRED.ALL_STORES", + "MetricThreshold": "tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", + "PublicDescription": "This metric estimates how often CPU was stalled due to RFO store memory accesses; RFO store issue a read-for-ownership request before the write. Even though store accesses do not typically stall out-of-order CPUs; there are few cases where stores can lead to actual stalls. This metric will be flagged should RFO stores be a bottleneck. Sample with: MEM_INST_RETIRED.ALL_STORES_PS", "ScaleUnit": "100%" }, { @@ -1974,8 +1973,8 @@ "MetricExpr": "13 * LD_BLOCKS.STORE_FORWARD / tma_info_thread_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group", "MetricName": "tma_store_fwd_blk", - "MetricThreshold": "tma_store_fwd_blk > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", - "PublicDescription": "This metric roughly estimates fraction of cycles when the memory subsystem had loads blocked since they could not forward data from earlier (in program order) overlapping stores. To streamline memory operations in the pipeline; a load can avoid waiting for memory if a prior in-flight store is writing the data that the load wants to read (store forwarding process). However; in some cases the load may be blocked for a significant time pending the store forward. For example; when the prior store is writing a smaller region than the load is reading", + "MetricThreshold": "tma_store_fwd_blk > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric roughly estimates fraction of cycles when the memory subsystem had loads blocked since they could not forward data from earlier (in program order) overlapping stores. To streamline memory operations in the pipeline; a load can avoid waiting for memory if a prior in-flight store is writing the data that the load wants to read (store forwarding process). However; in some cases the load may be blocked for a significant time pending the store forward. For example; when the prior store is writing a smaller region than the load is reading.", "ScaleUnit": "100%" }, { @@ -1984,8 +1983,8 @@ "MetricExpr": "(L2_RQSTS.RFO_HIT * 11 * (1 - MEM_INST_RETIRED.LOCK_LOADS / MEM_INST_RETIRED.ALL_STORES) + (1 - MEM_INST_RETIRED.LOCK_LOADS / MEM_INST_RETIRED.ALL_STORES) * min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO)) / tma_info_thread_clks", "MetricGroup": "BvML;LockCont;MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_issueSL;tma_store_bound_group", "MetricName": "tma_store_latency", - "MetricThreshold": "tma_store_latency > 0.1 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", - "PublicDescription": "This metric estimates fraction of cycles the CPU spent handling L1D store misses. Store accesses usually less impact out-of-order core performance; however; holding resources for longer time can lead into undesired implications (e.g. contention on L1D fill-buffer entries - see FB_Full). Related metrics: tma_branch_resteers, tma_fb_full, tma_l3_hit_latency, tma_lock_latency", + "MetricThreshold": "tma_store_latency > 0.1 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric estimates fraction of cycles the CPU spent handling L1D store misses. Store accesses usually less impact out-of-order core performance; however; holding resources for longer time can lead into undesired implications (e.g. contention on L1D fill-buffer entries - see FB_Full). Related metrics: tma_fb_full, tma_lock_latency", "ScaleUnit": "100%" }, { @@ -2001,7 +2000,7 @@ "MetricExpr": "tma_dtlb_store - tma_store_stlb_miss", "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_store_group", "MetricName": "tma_store_stlb_hit", - "MetricThreshold": "tma_store_stlb_hit > 0.05 & tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_store_stlb_hit > 0.05 & (tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))", "ScaleUnit": "100%" }, { @@ -2009,31 +2008,31 @@ "MetricExpr": "DTLB_STORE_MISSES.WALK_ACTIVE / tma_info_core_core_clks", "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_store_group", "MetricName": "tma_store_stlb_miss", - "MetricThreshold": "tma_store_stlb_miss > 0.05 & tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_store_stlb_miss > 0.05 & (tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 1 GB pages for data store accesses", + "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 1 GB pages for data store accesses.", "MetricExpr": "tma_store_stlb_miss * DTLB_STORE_MISSES.WALK_COMPLETED_1G / (DTLB_STORE_MISSES.WALK_COMPLETED_4K + DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M + DTLB_STORE_MISSES.WALK_COMPLETED_1G)", "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_store_stlb_miss_group", "MetricName": "tma_store_stlb_miss_1g", - "MetricThreshold": "tma_store_stlb_miss_1g > 0.05 & tma_store_stlb_miss > 0.05 & tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_store_stlb_miss_1g > 0.05 & (tma_store_stlb_miss > 0.05 & (tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))))", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 2 or 4 MB pages for data store accesses", + "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 2 or 4 MB pages for data store accesses.", "MetricExpr": "tma_store_stlb_miss * DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M / (DTLB_STORE_MISSES.WALK_COMPLETED_4K + DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M + DTLB_STORE_MISSES.WALK_COMPLETED_1G)", "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_store_stlb_miss_group", "MetricName": "tma_store_stlb_miss_2m", - "MetricThreshold": "tma_store_stlb_miss_2m > 0.05 & tma_store_stlb_miss > 0.05 & tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_store_stlb_miss_2m > 0.05 & (tma_store_stlb_miss > 0.05 & (tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))))", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 4 KB pages for data store accesses", + "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 4 KB pages for data store accesses.", "MetricExpr": "tma_store_stlb_miss * DTLB_STORE_MISSES.WALK_COMPLETED_4K / (DTLB_STORE_MISSES.WALK_COMPLETED_4K + DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M + DTLB_STORE_MISSES.WALK_COMPLETED_1G)", "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_store_stlb_miss_group", "MetricName": "tma_store_stlb_miss_4k", - "MetricThreshold": "tma_store_stlb_miss_4k > 0.05 & tma_store_stlb_miss > 0.05 & tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_store_stlb_miss_4k > 0.05 & (tma_store_stlb_miss > 0.05 & (tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))))", "ScaleUnit": "100%" }, { @@ -2041,7 +2040,7 @@ "MetricExpr": "9 * BACLEARS.ANY / tma_info_thread_clks", "MetricGroup": "BigFootprint;BvBC;FetchLat;TopdownL4;tma_L4_group;tma_branch_resteers_group", "MetricName": "tma_unknown_branches", - "MetricThreshold": "tma_unknown_branches > 0.05 & tma_branch_resteers > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricThreshold": "tma_unknown_branches > 0.05 & (tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))", "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to new branch address clears. These are fetched branches the Branch Prediction Unit was unable to recognize (e.g. first time the branch is fetched or hitting BTB capacity limit) hence called Unknown Branches. Sample with: BACLEARS.ANY", "ScaleUnit": "100%" }, @@ -2050,8 +2049,8 @@ "MetricExpr": "tma_retiring * UOPS_EXECUTED.X87 / UOPS_EXECUTED.THREAD", "MetricGroup": "Compute;TopdownL4;tma_L4_group;tma_fp_arith_group", "MetricName": "tma_x87_use", - "MetricThreshold": "tma_x87_use > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6", - "PublicDescription": "This metric serves as an approximation of legacy x87 usage. It accounts for instructions beyond X87 FP arithmetic operations; hence may be used as a thermometer to avoid X87 high usage and preferably upgrade to modern ISA. See Tip under Tuning Hint", + "MetricThreshold": "tma_x87_use > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6)", + "PublicDescription": "This metric serves as an approximation of legacy x87 usage. It accounts for instructions beyond X87 FP arithmetic operations; hence may be used as a thermometer to avoid X87 high usage and preferably upgrade to modern ISA. See Tip under Tuning Hint.", "ScaleUnit": "100%" }, { diff --git a/tools/perf/pmu-events/arch/x86/cascadelakex/other.json b/tools/perf/pmu-events/arch/x86/cascadelakex/other.json index f25693b17b8b..51833bce994e 100644 --- a/tools/perf/pmu-events/arch/x86/cascadelakex/other.json +++ b/tools/perf/pmu-events/arch/x86/cascadelakex/other.json @@ -36,62 +36,6 @@ "UMask": "0x40" }, { - "BriefDescription": "CORE_SNOOP_RESPONSE.RSP_IFWDFE", - "Counter": "0,1,2,3", - "EventCode": "0xEF", - "EventName": "CORE_SNOOP_RESPONSE.RSP_IFWDFE", - "SampleAfterValue": "2000003", - "UMask": "0x20" - }, - { - "BriefDescription": "CORE_SNOOP_RESPONSE.RSP_IFWDM", - "Counter": "0,1,2,3", - "EventCode": "0xEF", - "EventName": "CORE_SNOOP_RESPONSE.RSP_IFWDM", - "SampleAfterValue": "2000003", - "UMask": "0x10" - }, - { - "BriefDescription": "CORE_SNOOP_RESPONSE.RSP_IHITFSE", - "Counter": "0,1,2,3", - "EventCode": "0xEF", - "EventName": "CORE_SNOOP_RESPONSE.RSP_IHITFSE", - "SampleAfterValue": "2000003", - "UMask": "0x2" - }, - { - "BriefDescription": "CORE_SNOOP_RESPONSE.RSP_IHITI", - "Counter": "0,1,2,3", - "EventCode": "0xEF", - "EventName": "CORE_SNOOP_RESPONSE.RSP_IHITI", - "SampleAfterValue": "2000003", - "UMask": "0x1" - }, - { - "BriefDescription": "CORE_SNOOP_RESPONSE.RSP_SFWDFE", - "Counter": "0,1,2,3", - "EventCode": "0xEF", - "EventName": "CORE_SNOOP_RESPONSE.RSP_SFWDFE", - "SampleAfterValue": "2000003", - "UMask": "0x40" - }, - { - "BriefDescription": "CORE_SNOOP_RESPONSE.RSP_SFWDM", - "Counter": "0,1,2,3", - "EventCode": "0xEF", - "EventName": "CORE_SNOOP_RESPONSE.RSP_SFWDM", - "SampleAfterValue": "2000003", - "UMask": "0x8" - }, - { - "BriefDescription": "CORE_SNOOP_RESPONSE.RSP_SHITFSE", - "Counter": "0,1,2,3", - "EventCode": "0xEF", - "EventName": "CORE_SNOOP_RESPONSE.RSP_SHITFSE", - "SampleAfterValue": "2000003", - "UMask": "0x4" - }, - { "BriefDescription": "Number of hardware interrupts received by the processor.", "Counter": "0,1,2,3", "EventCode": "0xCB", @@ -101,24 +45,6 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts number of cache lines that are dropped and not written back to L3 as they are deemed to be less likely to be reused shortly", - "Counter": "0,1,2,3", - "EventCode": "0xFE", - "EventName": "IDI_MISC.WB_DOWNGRADE", - "PublicDescription": "Counts number of cache lines that are dropped and not written back to L3 as they are deemed to be less likely to be reused shortly.", - "SampleAfterValue": "100003", - "UMask": "0x4" - }, - { - "BriefDescription": "Counts number of cache lines that are allocated and written back to L3 with the intention that they are more likely to be reused shortly", - "Counter": "0,1,2,3", - "EventCode": "0xFE", - "EventName": "IDI_MISC.WB_UPGRADE", - "PublicDescription": "Counts number of cache lines that are allocated and written back to L3 with the intention that they are more likely to be reused shortly.", - "SampleAfterValue": "100003", - "UMask": "0x2" - }, - { "BriefDescription": "OCR.ALL_DATA_RD.ANY_RESPONSE have any response type.", "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -669,336 +595,6 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all demand code reads have any response type.", - "Counter": "0,1,2,3", - "EventCode": "0xB7, 0xBB", - "EventName": "OCR.DEMAND_CODE_RD.ANY_RESPONSE", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x10004", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts all demand code reads OCR.DEMAND_CODE_RD.PMM_HIT_LOCAL_PMM.ANY_SNOOP", - "Counter": "0,1,2,3", - "EventCode": "0xB7, 0xBB", - "EventName": "OCR.DEMAND_CODE_RD.PMM_HIT_LOCAL_PMM.ANY_SNOOP", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x3F80400004", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts all demand code reads OCR.DEMAND_CODE_RD.PMM_HIT_LOCAL_PMM.SNOOP_NONE", - "Counter": "0,1,2,3", - "EventCode": "0xB7, 0xBB", - "EventName": "OCR.DEMAND_CODE_RD.PMM_HIT_LOCAL_PMM.SNOOP_NONE", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x80400004", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts all demand code reads OCR.DEMAND_CODE_RD.PMM_HIT_LOCAL_PMM.SNOOP_NOT_NEEDED", - "Counter": "0,1,2,3", - "EventCode": "0xB7, 0xBB", - "EventName": "OCR.DEMAND_CODE_RD.PMM_HIT_LOCAL_PMM.SNOOP_NOT_NEEDED", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x100400004", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts all demand code reads OCR.DEMAND_CODE_RD.SUPPLIER_NONE.ANY_SNOOP", - "Counter": "0,1,2,3", - "EventCode": "0xB7, 0xBB", - "EventName": "OCR.DEMAND_CODE_RD.SUPPLIER_NONE.ANY_SNOOP", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x3F80020004", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts all demand code reads OCR.DEMAND_CODE_RD.SUPPLIER_NONE.HITM_OTHER_CORE", - "Counter": "0,1,2,3", - "EventCode": "0xB7, 0xBB", - "EventName": "OCR.DEMAND_CODE_RD.SUPPLIER_NONE.HITM_OTHER_CORE", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x1000020004", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts all demand code reads OCR.DEMAND_CODE_RD.SUPPLIER_NONE.HIT_OTHER_CORE_FWD", - "Counter": "0,1,2,3", - "EventCode": "0xB7, 0xBB", - "EventName": "OCR.DEMAND_CODE_RD.SUPPLIER_NONE.HIT_OTHER_CORE_FWD", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x800020004", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts all demand code reads OCR.DEMAND_CODE_RD.SUPPLIER_NONE.HIT_OTHER_CORE_NO_FWD", - "Counter": "0,1,2,3", - "EventCode": "0xB7, 0xBB", - "EventName": "OCR.DEMAND_CODE_RD.SUPPLIER_NONE.HIT_OTHER_CORE_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x400020004", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts all demand code reads OCR.DEMAND_CODE_RD.SUPPLIER_NONE.NO_SNOOP_NEEDED", - "Counter": "0,1,2,3", - "EventCode": "0xB7, 0xBB", - "EventName": "OCR.DEMAND_CODE_RD.SUPPLIER_NONE.NO_SNOOP_NEEDED", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x100020004", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts all demand code reads", - "Counter": "0,1,2,3", - "EventCode": "0xB7, 0xBB", - "EventName": "OCR.DEMAND_CODE_RD.SUPPLIER_NONE.SNOOP_MISS", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x200020004", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts all demand code reads", - "Counter": "0,1,2,3", - "EventCode": "0xB7, 0xBB", - "EventName": "OCR.DEMAND_CODE_RD.SUPPLIER_NONE.SNOOP_NONE", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x80020004", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts demand data reads have any response type.", - "Counter": "0,1,2,3", - "EventCode": "0xB7, 0xBB", - "EventName": "OCR.DEMAND_DATA_RD.ANY_RESPONSE", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x10001", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts demand data reads OCR.DEMAND_DATA_RD.PMM_HIT_LOCAL_PMM.ANY_SNOOP", - "Counter": "0,1,2,3", - "EventCode": "0xB7, 0xBB", - "EventName": "OCR.DEMAND_DATA_RD.PMM_HIT_LOCAL_PMM.ANY_SNOOP", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x3F80400001", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts demand data reads OCR.DEMAND_DATA_RD.PMM_HIT_LOCAL_PMM.SNOOP_NONE", - "Counter": "0,1,2,3", - "EventCode": "0xB7, 0xBB", - "EventName": "OCR.DEMAND_DATA_RD.PMM_HIT_LOCAL_PMM.SNOOP_NONE", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x80400001", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts demand data reads OCR.DEMAND_DATA_RD.PMM_HIT_LOCAL_PMM.SNOOP_NOT_NEEDED", - "Counter": "0,1,2,3", - "EventCode": "0xB7, 0xBB", - "EventName": "OCR.DEMAND_DATA_RD.PMM_HIT_LOCAL_PMM.SNOOP_NOT_NEEDED", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x100400001", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts demand data reads OCR.DEMAND_DATA_RD.SUPPLIER_NONE.ANY_SNOOP", - "Counter": "0,1,2,3", - "EventCode": "0xB7, 0xBB", - "EventName": "OCR.DEMAND_DATA_RD.SUPPLIER_NONE.ANY_SNOOP", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x3F80020001", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts demand data reads OCR.DEMAND_DATA_RD.SUPPLIER_NONE.HITM_OTHER_CORE", - "Counter": "0,1,2,3", - "EventCode": "0xB7, 0xBB", - "EventName": "OCR.DEMAND_DATA_RD.SUPPLIER_NONE.HITM_OTHER_CORE", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x1000020001", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts demand data reads OCR.DEMAND_DATA_RD.SUPPLIER_NONE.HIT_OTHER_CORE_FWD", - "Counter": "0,1,2,3", - "EventCode": "0xB7, 0xBB", - "EventName": "OCR.DEMAND_DATA_RD.SUPPLIER_NONE.HIT_OTHER_CORE_FWD", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x800020001", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts demand data reads OCR.DEMAND_DATA_RD.SUPPLIER_NONE.HIT_OTHER_CORE_NO_FWD", - "Counter": "0,1,2,3", - "EventCode": "0xB7, 0xBB", - "EventName": "OCR.DEMAND_DATA_RD.SUPPLIER_NONE.HIT_OTHER_CORE_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x400020001", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts demand data reads OCR.DEMAND_DATA_RD.SUPPLIER_NONE.NO_SNOOP_NEEDED", - "Counter": "0,1,2,3", - "EventCode": "0xB7, 0xBB", - "EventName": "OCR.DEMAND_DATA_RD.SUPPLIER_NONE.NO_SNOOP_NEEDED", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x100020001", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts demand data reads", - "Counter": "0,1,2,3", - "EventCode": "0xB7, 0xBB", - "EventName": "OCR.DEMAND_DATA_RD.SUPPLIER_NONE.SNOOP_MISS", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x200020001", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts demand data reads", - "Counter": "0,1,2,3", - "EventCode": "0xB7, 0xBB", - "EventName": "OCR.DEMAND_DATA_RD.SUPPLIER_NONE.SNOOP_NONE", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x80020001", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts all demand data writes (RFOs) have any response type.", - "Counter": "0,1,2,3", - "EventCode": "0xB7, 0xBB", - "EventName": "OCR.DEMAND_RFO.ANY_RESPONSE", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x10002", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts all demand data writes (RFOs) OCR.DEMAND_RFO.PMM_HIT_LOCAL_PMM.ANY_SNOOP", - "Counter": "0,1,2,3", - "EventCode": "0xB7, 0xBB", - "EventName": "OCR.DEMAND_RFO.PMM_HIT_LOCAL_PMM.ANY_SNOOP", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x3F80400002", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts all demand data writes (RFOs) OCR.DEMAND_RFO.PMM_HIT_LOCAL_PMM.SNOOP_NONE", - "Counter": "0,1,2,3", - "EventCode": "0xB7, 0xBB", - "EventName": "OCR.DEMAND_RFO.PMM_HIT_LOCAL_PMM.SNOOP_NONE", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x80400002", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts all demand data writes (RFOs) OCR.DEMAND_RFO.PMM_HIT_LOCAL_PMM.SNOOP_NOT_NEEDED", - "Counter": "0,1,2,3", - "EventCode": "0xB7, 0xBB", - "EventName": "OCR.DEMAND_RFO.PMM_HIT_LOCAL_PMM.SNOOP_NOT_NEEDED", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x100400002", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts all demand data writes (RFOs) OCR.DEMAND_RFO.SUPPLIER_NONE.ANY_SNOOP", - "Counter": "0,1,2,3", - "EventCode": "0xB7, 0xBB", - "EventName": "OCR.DEMAND_RFO.SUPPLIER_NONE.ANY_SNOOP", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x3F80020002", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts all demand data writes (RFOs) OCR.DEMAND_RFO.SUPPLIER_NONE.HITM_OTHER_CORE", - "Counter": "0,1,2,3", - "EventCode": "0xB7, 0xBB", - "EventName": "OCR.DEMAND_RFO.SUPPLIER_NONE.HITM_OTHER_CORE", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x1000020002", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts all demand data writes (RFOs) OCR.DEMAND_RFO.SUPPLIER_NONE.HIT_OTHER_CORE_FWD", - "Counter": "0,1,2,3", - "EventCode": "0xB7, 0xBB", - "EventName": "OCR.DEMAND_RFO.SUPPLIER_NONE.HIT_OTHER_CORE_FWD", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x800020002", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts all demand data writes (RFOs) OCR.DEMAND_RFO.SUPPLIER_NONE.HIT_OTHER_CORE_NO_FWD", - "Counter": "0,1,2,3", - "EventCode": "0xB7, 0xBB", - "EventName": "OCR.DEMAND_RFO.SUPPLIER_NONE.HIT_OTHER_CORE_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x400020002", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts all demand data writes (RFOs) OCR.DEMAND_RFO.SUPPLIER_NONE.NO_SNOOP_NEEDED", - "Counter": "0,1,2,3", - "EventCode": "0xB7, 0xBB", - "EventName": "OCR.DEMAND_RFO.SUPPLIER_NONE.NO_SNOOP_NEEDED", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x100020002", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts all demand data writes (RFOs)", - "Counter": "0,1,2,3", - "EventCode": "0xB7, 0xBB", - "EventName": "OCR.DEMAND_RFO.SUPPLIER_NONE.SNOOP_MISS", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x200020002", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts all demand data writes (RFOs)", - "Counter": "0,1,2,3", - "EventCode": "0xB7, 0xBB", - "EventName": "OCR.DEMAND_RFO.SUPPLIER_NONE.SNOOP_NONE", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x80020002", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { "BriefDescription": "Counts any other requests have any response type.", "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", diff --git a/tools/perf/pmu-events/arch/x86/clearwaterforest/cache.json b/tools/perf/pmu-events/arch/x86/clearwaterforest/cache.json index 875361b30f1d..ecb7dc252208 100644 --- a/tools/perf/pmu-events/arch/x86/clearwaterforest/cache.json +++ b/tools/perf/pmu-events/arch/x86/clearwaterforest/cache.json @@ -22,6 +22,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xd0", "EventName": "MEM_UOPS_RETIRED.ALL_LOADS", + "PublicDescription": "Counts the number of load ops retired. Available PDIST counters: 0,1", "SampleAfterValue": "1000003", "UMask": "0x81" }, @@ -30,6 +31,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xd0", "EventName": "MEM_UOPS_RETIRED.ALL_STORES", + "PublicDescription": "Counts the number of store ops retired. Available PDIST counters: 0,1", "SampleAfterValue": "1000003", "UMask": "0x82" }, @@ -40,6 +42,7 @@ "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_1024", "MSRIndex": "0x3F6", "MSRValue": "0x400", + "PublicDescription": "Counts the number of tagged load uops retired that exceed the latency threshold defined in MEC_CR_PEBS_LD_LAT_THRESHOLD - Only counts with PEBS enabled. Available PDIST counters: 0,1", "SampleAfterValue": "1000003", "UMask": "0x5" }, @@ -50,6 +53,7 @@ "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_128", "MSRIndex": "0x3F6", "MSRValue": "0x80", + "PublicDescription": "Counts the number of tagged load uops retired that exceed the latency threshold defined in MEC_CR_PEBS_LD_LAT_THRESHOLD - Only counts with PEBS enabled. Available PDIST counters: 0,1", "SampleAfterValue": "1000003", "UMask": "0x5" }, @@ -60,6 +64,7 @@ "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_16", "MSRIndex": "0x3F6", "MSRValue": "0x10", + "PublicDescription": "Counts the number of tagged load uops retired that exceed the latency threshold defined in MEC_CR_PEBS_LD_LAT_THRESHOLD - Only counts with PEBS enabled. Available PDIST counters: 0,1", "SampleAfterValue": "1000003", "UMask": "0x5" }, @@ -70,6 +75,7 @@ "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_2048", "MSRIndex": "0x3F6", "MSRValue": "0x800", + "PublicDescription": "Counts the number of tagged load uops retired that exceed the latency threshold defined in MEC_CR_PEBS_LD_LAT_THRESHOLD - Only counts with PEBS enabled. Available PDIST counters: 0,1", "SampleAfterValue": "1000003", "UMask": "0x5" }, @@ -80,6 +86,7 @@ "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_256", "MSRIndex": "0x3F6", "MSRValue": "0x100", + "PublicDescription": "Counts the number of tagged load uops retired that exceed the latency threshold defined in MEC_CR_PEBS_LD_LAT_THRESHOLD - Only counts with PEBS enabled. Available PDIST counters: 0,1", "SampleAfterValue": "1000003", "UMask": "0x5" }, @@ -90,6 +97,7 @@ "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_32", "MSRIndex": "0x3F6", "MSRValue": "0x20", + "PublicDescription": "Counts the number of tagged load uops retired that exceed the latency threshold defined in MEC_CR_PEBS_LD_LAT_THRESHOLD - Only counts with PEBS enabled. Available PDIST counters: 0,1", "SampleAfterValue": "1000003", "UMask": "0x5" }, @@ -100,6 +108,7 @@ "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_4", "MSRIndex": "0x3F6", "MSRValue": "0x4", + "PublicDescription": "Counts the number of tagged load uops retired that exceed the latency threshold defined in MEC_CR_PEBS_LD_LAT_THRESHOLD - Only counts with PEBS enabled. Available PDIST counters: 0,1", "SampleAfterValue": "1000003", "UMask": "0x5" }, @@ -110,6 +119,7 @@ "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_512", "MSRIndex": "0x3F6", "MSRValue": "0x200", + "PublicDescription": "Counts the number of tagged load uops retired that exceed the latency threshold defined in MEC_CR_PEBS_LD_LAT_THRESHOLD - Only counts with PEBS enabled. Available PDIST counters: 0,1", "SampleAfterValue": "1000003", "UMask": "0x5" }, @@ -120,6 +130,7 @@ "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_64", "MSRIndex": "0x3F6", "MSRValue": "0x40", + "PublicDescription": "Counts the number of tagged load uops retired that exceed the latency threshold defined in MEC_CR_PEBS_LD_LAT_THRESHOLD - Only counts with PEBS enabled. Available PDIST counters: 0,1", "SampleAfterValue": "1000003", "UMask": "0x5" }, @@ -130,6 +141,7 @@ "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_8", "MSRIndex": "0x3F6", "MSRValue": "0x8", + "PublicDescription": "Counts the number of tagged load uops retired that exceed the latency threshold defined in MEC_CR_PEBS_LD_LAT_THRESHOLD - Only counts with PEBS enabled. Available PDIST counters: 0,1", "SampleAfterValue": "1000003", "UMask": "0x5" }, @@ -138,7 +150,30 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xd0", "EventName": "MEM_UOPS_RETIRED.STORE_LATENCY", + "PublicDescription": "Counts the number of stores uops retired same as MEM_UOPS_RETIRED.ALL_STORES Available PDIST counters: 0,1", "SampleAfterValue": "1000003", "UMask": "0x6" + }, + { + "BriefDescription": "Counts demand data reads that have any type of response.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xB7", + "EventName": "OCR.DEMAND_DATA_RD.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x10001", + "PublicDescription": "Counts demand data reads that have any type of response. Available PDIST counters: 0", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts demand read for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that have any type of response.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xB7", + "EventName": "OCR.DEMAND_RFO.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x10002", + "PublicDescription": "Counts demand read for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that have any type of response. Available PDIST counters: 0", + "SampleAfterValue": "100003", + "UMask": "0x1" } ] diff --git a/tools/perf/pmu-events/arch/x86/clearwaterforest/memory.json b/tools/perf/pmu-events/arch/x86/clearwaterforest/memory.json index f5007e56f39b..58e543550279 100644 --- a/tools/perf/pmu-events/arch/x86/clearwaterforest/memory.json +++ b/tools/perf/pmu-events/arch/x86/clearwaterforest/memory.json @@ -6,6 +6,7 @@ "EventName": "OCR.DEMAND_DATA_RD.L3_MISS", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x33FBFC00001", + "PublicDescription": "Counts demand data reads that were not supplied by the L3 cache. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -16,6 +17,7 @@ "EventName": "OCR.DEMAND_RFO.L3_MISS", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x33FBFC00002", + "PublicDescription": "Counts demand read for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that were not supplied by the L3 cache. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" } diff --git a/tools/perf/pmu-events/arch/x86/clearwaterforest/other.json b/tools/perf/pmu-events/arch/x86/clearwaterforest/other.json deleted file mode 100644 index 80454e497f83..000000000000 --- a/tools/perf/pmu-events/arch/x86/clearwaterforest/other.json +++ /dev/null @@ -1,22 +0,0 @@ -[ - { - "BriefDescription": "Counts demand data reads that have any type of response.", - "Counter": "0,1,2,3,4,5,6,7", - "EventCode": "0xB7", - "EventName": "OCR.DEMAND_DATA_RD.ANY_RESPONSE", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x10001", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts demand read for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that have any type of response.", - "Counter": "0,1,2,3,4,5,6,7", - "EventCode": "0xB7", - "EventName": "OCR.DEMAND_RFO.ANY_RESPONSE", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x10002", - "SampleAfterValue": "100003", - "UMask": "0x1" - } -] diff --git a/tools/perf/pmu-events/arch/x86/clearwaterforest/pipeline.json b/tools/perf/pmu-events/arch/x86/clearwaterforest/pipeline.json index 6a5faa704b85..26bd12fefa3d 100644 --- a/tools/perf/pmu-events/arch/x86/clearwaterforest/pipeline.json +++ b/tools/perf/pmu-events/arch/x86/clearwaterforest/pipeline.json @@ -4,7 +4,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.ALL_BRANCHES", - "PublicDescription": "Counts the total number of instructions in which the instruction pointer (IP) of the processor is resteered due to a branch instruction and the branch instruction successfully retires. All branch type instructions are accounted for.", + "PublicDescription": "Counts the total number of instructions in which the instruction pointer (IP) of the processor is resteered due to a branch instruction and the branch instruction successfully retires. All branch type instructions are accounted for. Available PDIST counters: 0,1", "SampleAfterValue": "1000003" }, { @@ -12,7 +12,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.ALL_BRANCHES", - "PublicDescription": "Counts the total number of mispredicted branch instructions retired. All branch type instructions are accounted for. Prediction of the branch target address enables the processor to begin executing instructions before the non-speculative execution path is known. The branch prediction unit (BPU) predicts the target address based on the instruction pointer (IP) of the branch and on the execution path through which execution reached this IP. A branch misprediction occurs when the prediction is wrong, and results in discarding all instructions executed in the speculative path and re-fetching from the correct path.", + "PublicDescription": "Counts the total number of mispredicted branch instructions retired. All branch type instructions are accounted for. Prediction of the branch target address enables the processor to begin executing instructions before the non-speculative execution path is known. The branch prediction unit (BPU) predicts the target address based on the instruction pointer (IP) of the branch and on the execution path through which execution reached this IP. A branch misprediction occurs when the prediction is wrong, and results in discarding all instructions executed in the speculative path and re-fetching from the correct path. Available PDIST counters: 0,1", "SampleAfterValue": "1000003" }, { @@ -63,6 +63,7 @@ "BriefDescription": "Fixed Counter: Counts the number of instructions retired.", "Counter": "Fixed counter 0", "EventName": "INST_RETIRED.ANY", + "PublicDescription": "Fixed Counter: Counts the number of instructions retired. Available PDIST counters: 32", "SampleAfterValue": "1000003", "UMask": "0x1" }, @@ -71,6 +72,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc0", "EventName": "INST_RETIRED.ANY_P", + "PublicDescription": "Counts the number of instructions retired. Available PDIST counters: 0,1", "SampleAfterValue": "1000003" }, { diff --git a/tools/perf/pmu-events/arch/x86/elkhartlake/cache.json b/tools/perf/pmu-events/arch/x86/elkhartlake/cache.json index 7882dca9d5e1..3410caf8a57a 100644 --- a/tools/perf/pmu-events/arch/x86/elkhartlake/cache.json +++ b/tools/perf/pmu-events/arch/x86/elkhartlake/cache.json @@ -161,6 +161,7 @@ "EventCode": "0xd1", "EventName": "MEM_LOAD_UOPS_RETIRED.DRAM_HIT", "PEBS": "1", + "PublicDescription": "Counts the number of load uops retired that hit in DRAM. Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0x80" }, @@ -171,6 +172,7 @@ "EventCode": "0xd1", "EventName": "MEM_LOAD_UOPS_RETIRED.HITM", "PEBS": "1", + "PublicDescription": "Counts the number of load uops retired that hit in the L3 cache, in which a snoop was required and modified data was forwarded from another core or module. Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0x20" }, @@ -181,6 +183,7 @@ "EventCode": "0xd1", "EventName": "MEM_LOAD_UOPS_RETIRED.L1_HIT", "PEBS": "1", + "PublicDescription": "Counts the number of load uops retired that hit in the L1 data cache. Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0x1" }, @@ -191,6 +194,7 @@ "EventCode": "0xd1", "EventName": "MEM_LOAD_UOPS_RETIRED.L1_MISS", "PEBS": "1", + "PublicDescription": "Counts the number of load uops retired that miss in the L1 data cache. Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0x8" }, @@ -201,6 +205,7 @@ "EventCode": "0xd1", "EventName": "MEM_LOAD_UOPS_RETIRED.L2_HIT", "PEBS": "1", + "PublicDescription": "Counts the number of load uops retired that hit in the L2 cache. Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0x2" }, @@ -211,6 +216,7 @@ "EventCode": "0xd1", "EventName": "MEM_LOAD_UOPS_RETIRED.L2_MISS", "PEBS": "1", + "PublicDescription": "Counts the number of load uops retired that miss in the L2 cache. Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0x10" }, @@ -221,6 +227,7 @@ "EventCode": "0xd1", "EventName": "MEM_LOAD_UOPS_RETIRED.L3_HIT", "PEBS": "1", + "PublicDescription": "Counts the number of load uops retired that hit in the L3 cache. Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0x4" }, @@ -231,7 +238,7 @@ "EventCode": "0xd0", "EventName": "MEM_UOPS_RETIRED.ALL", "PEBS": "1", - "PublicDescription": "Counts the number of memory uops retired. A single uop that performs both a load AND a store will be counted as 1, not 2 (e.g. ADD [mem], CONST)", + "PublicDescription": "Counts the number of memory uops retired. A single uop that performs both a load AND a store will be counted as 1, not 2 (e.g. ADD [mem], CONST) Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0x83" }, @@ -242,7 +249,7 @@ "EventCode": "0xd0", "EventName": "MEM_UOPS_RETIRED.ALL_LOADS", "PEBS": "1", - "PublicDescription": "Counts the total number of load uops retired.", + "PublicDescription": "Counts the total number of load uops retired. Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0x81" }, @@ -253,7 +260,7 @@ "EventCode": "0xd0", "EventName": "MEM_UOPS_RETIRED.ALL_STORES", "PEBS": "1", - "PublicDescription": "Counts the total number of store uops retired.", + "PublicDescription": "Counts the total number of store uops retired. Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0x82" }, @@ -264,6 +271,7 @@ "EventCode": "0xd0", "EventName": "MEM_UOPS_RETIRED.LOCK_LOADS", "PEBS": "1", + "PublicDescription": "Counts the number of load uops retired that performed one or more locks. Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0x21" }, @@ -274,6 +282,7 @@ "EventCode": "0xd0", "EventName": "MEM_UOPS_RETIRED.SPLIT", "PEBS": "1", + "PublicDescription": "Counts the number of memory uops retired that were splits. Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0x43" }, @@ -284,6 +293,7 @@ "EventCode": "0xd0", "EventName": "MEM_UOPS_RETIRED.SPLIT_LOADS", "PEBS": "1", + "PublicDescription": "Counts the number of retired split load uops. Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0x41" }, @@ -294,6 +304,7 @@ "EventCode": "0xd0", "EventName": "MEM_UOPS_RETIRED.SPLIT_STORES", "PEBS": "1", + "PublicDescription": "Counts the number of retired split store uops. Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0x42" }, @@ -304,6 +315,7 @@ "EventName": "OCR.ALL_CODE_RD.L3_HIT", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x1F803C0044", + "PublicDescription": "Counts all code reads that were supplied by the L3 cache. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -314,6 +326,7 @@ "EventName": "OCR.ALL_CODE_RD.L3_HIT.SNOOP_HITM", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x10003C0044", + "PublicDescription": "Counts all code reads that were supplied by the L3 cache where a snoop was sent, the snoop hit, and modified data was forwarded. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -324,6 +337,7 @@ "EventName": "OCR.ALL_CODE_RD.L3_HIT.SNOOP_HIT_NO_FWD", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x4003C0044", + "PublicDescription": "Counts all code reads that were supplied by the L3 cache where a snoop was sent, the snoop hit, but no data was forwarded. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -334,6 +348,7 @@ "EventName": "OCR.ALL_CODE_RD.L3_HIT.SNOOP_HIT_WITH_FWD", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x8003C0044", + "PublicDescription": "Counts all code reads that were supplied by the L3 cache where a snoop was sent, the snoop hit, and non-modified data was forwarded. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -344,6 +359,7 @@ "EventName": "OCR.ALL_CODE_RD.L3_HIT.SNOOP_MISS", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x2003C0044", + "PublicDescription": "Counts all code reads that were supplied by the L3 cache where a snoop was sent but the snoop missed. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -354,6 +370,18 @@ "EventName": "OCR.ALL_CODE_RD.L3_HIT.SNOOP_NOT_NEEDED", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x1003C0044", + "PublicDescription": "Counts all code reads that were supplied by the L3 cache where no snoop was needed to satisfy the request. Available PDIST counters: 0", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts modified writebacks from L1 cache and L2 cache that have any type of response.", + "Counter": "0,1,2,3", + "EventCode": "0XB7", + "EventName": "OCR.COREWB_M.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x3000000010000", + "PublicDescription": "Counts modified writebacks from L1 cache and L2 cache that have any type of response. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -364,6 +392,29 @@ "EventName": "OCR.COREWB_M.L3_HIT", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x3001F803C0000", + "PublicDescription": "Counts modified writebacks from L1 cache and L2 cache that were supplied by the L3 cache. Available PDIST counters: 0", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts modified writebacks from L1 cache and L2 cache that have an outstanding request. Returns the number of cycles until the response is received (i.e. XQ to XQ latency).", + "Counter": "0,1,2,3", + "EventCode": "0XB7", + "EventName": "OCR.COREWB_M.OUTSTANDING", + "MSRIndex": "0x1a6", + "MSRValue": "0x8003000000000000", + "PublicDescription": "Counts modified writebacks from L1 cache and L2 cache that have an outstanding request. Returns the number of cycles until the response is received (i.e. XQ to XQ latency). Available PDIST counters: 0", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that have any type of response.", + "Counter": "0,1,2,3", + "EventCode": "0XB7", + "EventName": "OCR.DEMAND_CODE_RD.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x10004", + "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that have any type of response. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -374,6 +425,7 @@ "EventName": "OCR.DEMAND_CODE_RD.L3_HIT", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x1F803C0004", + "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were supplied by the L3 cache. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -384,6 +436,7 @@ "EventName": "OCR.DEMAND_CODE_RD.L3_HIT.SNOOP_HITM", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x10003C0004", + "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were supplied by the L3 cache where a snoop was sent, the snoop hit, and modified data was forwarded. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -394,6 +447,7 @@ "EventName": "OCR.DEMAND_CODE_RD.L3_HIT.SNOOP_HIT_NO_FWD", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x4003C0004", + "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were supplied by the L3 cache where a snoop was sent, the snoop hit, but no data was forwarded. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -404,6 +458,7 @@ "EventName": "OCR.DEMAND_CODE_RD.L3_HIT.SNOOP_HIT_WITH_FWD", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x8003C0004", + "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were supplied by the L3 cache where a snoop was sent, the snoop hit, and non-modified data was forwarded. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -414,6 +469,7 @@ "EventName": "OCR.DEMAND_CODE_RD.L3_HIT.SNOOP_MISS", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x2003C0004", + "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were supplied by the L3 cache where a snoop was sent but the snoop missed. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -424,6 +480,18 @@ "EventName": "OCR.DEMAND_CODE_RD.L3_HIT.SNOOP_NOT_NEEDED", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x1003C0004", + "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were supplied by the L3 cache where no snoop was needed to satisfy the request. Available PDIST counters: 0", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts cacheable demand data reads, L1 data cache hardware prefetches and software prefetches (except PREFETCHW) that have any type of response.", + "Counter": "0,1,2,3", + "EventCode": "0XB7", + "EventName": "OCR.DEMAND_DATA_AND_L1PF_RD.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x10001", + "PublicDescription": "Counts cacheable demand data reads, L1 data cache hardware prefetches and software prefetches (except PREFETCHW) that have any type of response. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -434,6 +502,7 @@ "EventName": "OCR.DEMAND_DATA_AND_L1PF_RD.L3_HIT", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x1F803C0001", + "PublicDescription": "Counts cacheable demand data reads, L1 data cache hardware prefetches and software prefetches (except PREFETCHW) that were supplied by the L3 cache. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -444,6 +513,7 @@ "EventName": "OCR.DEMAND_DATA_AND_L1PF_RD.L3_HIT.SNOOP_HITM", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x10003C0001", + "PublicDescription": "Counts cacheable demand data reads, L1 data cache hardware prefetches and software prefetches (except PREFETCHW) that were supplied by the L3 cache where a snoop was sent, the snoop hit, and modified data was forwarded. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -454,6 +524,7 @@ "EventName": "OCR.DEMAND_DATA_AND_L1PF_RD.L3_HIT.SNOOP_HIT_NO_FWD", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x4003C0001", + "PublicDescription": "Counts cacheable demand data reads, L1 data cache hardware prefetches and software prefetches (except PREFETCHW) that were supplied by the L3 cache where a snoop was sent, the snoop hit, but no data was forwarded. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -464,6 +535,7 @@ "EventName": "OCR.DEMAND_DATA_AND_L1PF_RD.L3_HIT.SNOOP_HIT_WITH_FWD", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x8003C0001", + "PublicDescription": "Counts cacheable demand data reads, L1 data cache hardware prefetches and software prefetches (except PREFETCHW) that were supplied by the L3 cache where a snoop was sent, the snoop hit, and non-modified data was forwarded. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -474,6 +546,7 @@ "EventName": "OCR.DEMAND_DATA_AND_L1PF_RD.L3_HIT.SNOOP_MISS", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x2003C0001", + "PublicDescription": "Counts cacheable demand data reads, L1 data cache hardware prefetches and software prefetches (except PREFETCHW) that were supplied by the L3 cache where a snoop was sent but the snoop missed. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -484,6 +557,30 @@ "EventName": "OCR.DEMAND_DATA_AND_L1PF_RD.L3_HIT.SNOOP_NOT_NEEDED", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x1003C0001", + "PublicDescription": "Counts cacheable demand data reads, L1 data cache hardware prefetches and software prefetches (except PREFETCHW) that were supplied by the L3 cache where no snoop was needed to satisfy the request. Available PDIST counters: 0", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts cacheable demand data reads, L1 data cache hardware prefetches and software prefetches (except PREFETCHW) that have an outstanding request. Returns the number of cycles until the response is received (i.e. XQ to XQ latency).", + "Counter": "0,1,2,3", + "EventCode": "0XB7", + "EventName": "OCR.DEMAND_DATA_AND_L1PF_RD.OUTSTANDING", + "MSRIndex": "0x1a6", + "MSRValue": "0x8000000000000001", + "PublicDescription": "Counts cacheable demand data reads, L1 data cache hardware prefetches and software prefetches (except PREFETCHW) that have an outstanding request. Returns the number of cycles until the response is received (i.e. XQ to XQ latency). Available PDIST counters: 0", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event OCR.DEMAND_DATA_AND_L1PF_RD.ANY_RESPONSE", + "Counter": "0,1,2,3", + "Deprecated": "1", + "EventCode": "0XB7", + "EventName": "OCR.DEMAND_DATA_RD.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x10001", + "PublicDescription": "This event is deprecated. Refer to new event OCR.DEMAND_DATA_AND_L1PF_RD.ANY_RESPONSE Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -495,6 +592,7 @@ "EventName": "OCR.DEMAND_DATA_RD.L3_HIT", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x1F803C0001", + "PublicDescription": "This event is deprecated. Refer to new event OCR.DEMAND_DATA_AND_L1PF_RD.L3_HIT Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -506,6 +604,7 @@ "EventName": "OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x10003C0001", + "PublicDescription": "This event is deprecated. Refer to new event OCR.DEMAND_DATA_AND_L1PF_RD.L3_HIT.SNOOP_HITM Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -517,6 +616,7 @@ "EventName": "OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_NO_FWD", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x4003C0001", + "PublicDescription": "This event is deprecated. Refer to new event OCR.DEMAND_DATA_AND_L1PF_RD.L3_HIT.SNOOP_HIT_NO_FWD Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -528,6 +628,7 @@ "EventName": "OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x8003C0001", + "PublicDescription": "This event is deprecated. Refer to new event OCR.DEMAND_DATA_AND_L1PF_RD.L3_HIT.SNOOP_HIT_WITH_FWD Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -539,6 +640,7 @@ "EventName": "OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_MISS", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x2003C0001", + "PublicDescription": "This event is deprecated. Refer to new event OCR.DEMAND_DATA_AND_L1PF_RD.L3_HIT.SNOOP_MISS Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -550,6 +652,30 @@ "EventName": "OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_NOT_NEEDED", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x1003C0001", + "PublicDescription": "This event is deprecated. Refer to new event OCR.DEMAND_DATA_AND_L1PF_RD.L3_HIT.SNOOP_NOT_NEEDED Available PDIST counters: 0", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event OCR.DEMAND_DATA_AND_L1PF_RD.OUTSTANDING", + "Counter": "0,1,2,3", + "Deprecated": "1", + "EventCode": "0XB7", + "EventName": "OCR.DEMAND_DATA_RD.OUTSTANDING", + "MSRIndex": "0x1a6", + "MSRValue": "0x8000000000000001", + "PublicDescription": "This event is deprecated. Refer to new event OCR.DEMAND_DATA_AND_L1PF_RD.OUTSTANDING Available PDIST counters: 0", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that have any type of response.", + "Counter": "0,1,2,3", + "EventCode": "0XB7", + "EventName": "OCR.DEMAND_RFO.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x10002", + "PublicDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that have any type of response. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -560,6 +686,7 @@ "EventName": "OCR.DEMAND_RFO.L3_HIT", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x1F803C0002", + "PublicDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that were supplied by the L3 cache. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -570,6 +697,7 @@ "EventName": "OCR.DEMAND_RFO.L3_HIT.SNOOP_HITM", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x10003C0002", + "PublicDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that were supplied by the L3 cache where a snoop was sent, the snoop hit, and modified data was forwarded. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -580,6 +708,7 @@ "EventName": "OCR.DEMAND_RFO.L3_HIT.SNOOP_HIT_NO_FWD", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x4003C0002", + "PublicDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that were supplied by the L3 cache where a snoop was sent, the snoop hit, but no data was forwarded. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -590,6 +719,7 @@ "EventName": "OCR.DEMAND_RFO.L3_HIT.SNOOP_HIT_WITH_FWD", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x8003C0002", + "PublicDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that were supplied by the L3 cache where a snoop was sent, the snoop hit, and non-modified data was forwarded. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -600,6 +730,7 @@ "EventName": "OCR.DEMAND_RFO.L3_HIT.SNOOP_MISS", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x2003C0002", + "PublicDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that were supplied by the L3 cache where a snoop was sent but the snoop missed. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -610,6 +741,18 @@ "EventName": "OCR.DEMAND_RFO.L3_HIT.SNOOP_NOT_NEEDED", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x1003C0002", + "PublicDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that were supplied by the L3 cache where no snoop was needed to satisfy the request. Available PDIST counters: 0", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that have an outstanding request. Returns the number of cycles until the response is received (i.e. XQ to XQ latency).", + "Counter": "0,1,2,3", + "EventCode": "0XB7", + "EventName": "OCR.DEMAND_RFO.OUTSTANDING", + "MSRIndex": "0x1a6", + "MSRValue": "0x8000000000000002", + "PublicDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that have an outstanding request. Returns the number of cycles until the response is received (i.e. XQ to XQ latency). Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -620,6 +763,18 @@ "EventName": "OCR.FULL_STREAMING_WR.L3_HIT", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x801F803C0000", + "PublicDescription": "Counts streaming stores which modify a full 64 byte cacheline that were supplied by the L3 cache. Available PDIST counters: 0", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts L1 data cache hardware prefetches and software prefetches (except PREFETCHW and PFRFO) that have any type of response.", + "Counter": "0,1,2,3", + "EventCode": "0XB7", + "EventName": "OCR.HWPF_L1D_AND_SWPF.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x10400", + "PublicDescription": "Counts L1 data cache hardware prefetches and software prefetches (except PREFETCHW and PFRFO) that have any type of response. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -630,6 +785,18 @@ "EventName": "OCR.HWPF_L1D_AND_SWPF.L3_HIT.SNOOP_HITM", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x10003C0400", + "PublicDescription": "Counts L1 data cache hardware prefetches and software prefetches (except PREFETCHW and PFRFO) that were supplied by the L3 cache where a snoop was sent, the snoop hit, and modified data was forwarded. Available PDIST counters: 0", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts L2 cache hardware prefetch code reads (written to the L2 cache only) that have any type of response.", + "Counter": "0,1,2,3", + "EventCode": "0XB7", + "EventName": "OCR.HWPF_L2_CODE_RD.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x10040", + "PublicDescription": "Counts L2 cache hardware prefetch code reads (written to the L2 cache only) that have any type of response. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -640,6 +807,7 @@ "EventName": "OCR.HWPF_L2_CODE_RD.L3_HIT", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x1F803C0040", + "PublicDescription": "Counts L2 cache hardware prefetch code reads (written to the L2 cache only) that were supplied by the L3 cache. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -650,6 +818,7 @@ "EventName": "OCR.HWPF_L2_CODE_RD.L3_HIT.SNOOP_HITM", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x10003C0040", + "PublicDescription": "Counts L2 cache hardware prefetch code reads (written to the L2 cache only) that were supplied by the L3 cache where a snoop was sent, the snoop hit, and modified data was forwarded. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -660,6 +829,7 @@ "EventName": "OCR.HWPF_L2_CODE_RD.L3_HIT.SNOOP_HIT_NO_FWD", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x4003C0040", + "PublicDescription": "Counts L2 cache hardware prefetch code reads (written to the L2 cache only) that were supplied by the L3 cache where a snoop was sent, the snoop hit, but no data was forwarded. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -670,6 +840,7 @@ "EventName": "OCR.HWPF_L2_CODE_RD.L3_HIT.SNOOP_HIT_WITH_FWD", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x8003C0040", + "PublicDescription": "Counts L2 cache hardware prefetch code reads (written to the L2 cache only) that were supplied by the L3 cache where a snoop was sent, the snoop hit, and non-modified data was forwarded. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -680,6 +851,7 @@ "EventName": "OCR.HWPF_L2_CODE_RD.L3_HIT.SNOOP_MISS", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x2003C0040", + "PublicDescription": "Counts L2 cache hardware prefetch code reads (written to the L2 cache only) that were supplied by the L3 cache where a snoop was sent but the snoop missed. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -690,6 +862,29 @@ "EventName": "OCR.HWPF_L2_CODE_RD.L3_HIT.SNOOP_NOT_NEEDED", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x1003C0040", + "PublicDescription": "Counts L2 cache hardware prefetch code reads (written to the L2 cache only) that were supplied by the L3 cache where no snoop was needed to satisfy the request. Available PDIST counters: 0", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts L2 cache hardware prefetch code reads (written to the L2 cache only) that have an outstanding request. Returns the number of cycles until the response is received (i.e. XQ to XQ latency).", + "Counter": "0,1,2,3", + "EventCode": "0XB7", + "EventName": "OCR.HWPF_L2_CODE_RD.OUTSTANDING", + "MSRIndex": "0x1a6", + "MSRValue": "0x8000000000000040", + "PublicDescription": "Counts L2 cache hardware prefetch code reads (written to the L2 cache only) that have an outstanding request. Returns the number of cycles until the response is received (i.e. XQ to XQ latency). Available PDIST counters: 0", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts L2 cache hardware prefetch data reads (written to the L2 cache only) that have any type of response.", + "Counter": "0,1,2,3", + "EventCode": "0XB7", + "EventName": "OCR.HWPF_L2_DATA_RD.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x10010", + "PublicDescription": "Counts L2 cache hardware prefetch data reads (written to the L2 cache only) that have any type of response. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -700,6 +895,7 @@ "EventName": "OCR.HWPF_L2_DATA_RD.L3_HIT", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x1F803C0010", + "PublicDescription": "Counts L2 cache hardware prefetch data reads (written to the L2 cache only) that were supplied by the L3 cache. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -710,6 +906,7 @@ "EventName": "OCR.HWPF_L2_DATA_RD.L3_HIT.SNOOP_HITM", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x10003C0010", + "PublicDescription": "Counts L2 cache hardware prefetch data reads (written to the L2 cache only) that were supplied by the L3 cache where a snoop was sent, the snoop hit, and modified data was forwarded. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -720,6 +917,7 @@ "EventName": "OCR.HWPF_L2_DATA_RD.L3_HIT.SNOOP_HIT_NO_FWD", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x4003C0010", + "PublicDescription": "Counts L2 cache hardware prefetch data reads (written to the L2 cache only) that were supplied by the L3 cache where a snoop was sent, the snoop hit, but no data was forwarded. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -730,6 +928,7 @@ "EventName": "OCR.HWPF_L2_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x8003C0010", + "PublicDescription": "Counts L2 cache hardware prefetch data reads (written to the L2 cache only) that were supplied by the L3 cache where a snoop was sent, the snoop hit, and non-modified data was forwarded. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -740,6 +939,7 @@ "EventName": "OCR.HWPF_L2_DATA_RD.L3_HIT.SNOOP_MISS", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x2003C0010", + "PublicDescription": "Counts L2 cache hardware prefetch data reads (written to the L2 cache only) that were supplied by the L3 cache where a snoop was sent but the snoop missed. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -750,6 +950,18 @@ "EventName": "OCR.HWPF_L2_DATA_RD.L3_HIT.SNOOP_NOT_NEEDED", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x1003C0010", + "PublicDescription": "Counts L2 cache hardware prefetch data reads (written to the L2 cache only) that were supplied by the L3 cache where no snoop was needed to satisfy the request. Available PDIST counters: 0", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts L2 cache hardware prefetch RFOs (written to the L2 cache only) that have any type of response.", + "Counter": "0,1,2,3", + "EventCode": "0XB7", + "EventName": "OCR.HWPF_L2_RFO.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x10020", + "PublicDescription": "Counts L2 cache hardware prefetch RFOs (written to the L2 cache only) that have any type of response. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -760,6 +972,7 @@ "EventName": "OCR.HWPF_L2_RFO.L3_HIT", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x1F803C0020", + "PublicDescription": "Counts L2 cache hardware prefetch RFOs (written to the L2 cache only) that were supplied by the L3 cache. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -770,6 +983,7 @@ "EventName": "OCR.HWPF_L2_RFO.L3_HIT.SNOOP_HITM", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x10003C0020", + "PublicDescription": "Counts L2 cache hardware prefetch RFOs (written to the L2 cache only) that were supplied by the L3 cache where a snoop was sent, the snoop hit, and modified data was forwarded. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -780,6 +994,7 @@ "EventName": "OCR.HWPF_L2_RFO.L3_HIT.SNOOP_HIT_NO_FWD", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x4003C0020", + "PublicDescription": "Counts L2 cache hardware prefetch RFOs (written to the L2 cache only) that were supplied by the L3 cache where a snoop was sent, the snoop hit, but no data was forwarded. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -790,6 +1005,7 @@ "EventName": "OCR.HWPF_L2_RFO.L3_HIT.SNOOP_HIT_WITH_FWD", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x8003C0020", + "PublicDescription": "Counts L2 cache hardware prefetch RFOs (written to the L2 cache only) that were supplied by the L3 cache where a snoop was sent, the snoop hit, and non-modified data was forwarded. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -800,6 +1016,7 @@ "EventName": "OCR.HWPF_L2_RFO.L3_HIT.SNOOP_MISS", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x2003C0020", + "PublicDescription": "Counts L2 cache hardware prefetch RFOs (written to the L2 cache only) that were supplied by the L3 cache where a snoop was sent but the snoop missed. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -810,6 +1027,29 @@ "EventName": "OCR.HWPF_L2_RFO.L3_HIT.SNOOP_NOT_NEEDED", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x1003C0020", + "PublicDescription": "Counts L2 cache hardware prefetch RFOs (written to the L2 cache only) that were supplied by the L3 cache where no snoop was needed to satisfy the request. Available PDIST counters: 0", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts L2 cache hardware prefetch RFOs (written to the L2 cache only) that have an outstanding request. Returns the number of cycles until the response is received (i.e. XQ to XQ latency).", + "Counter": "0,1,2,3", + "EventCode": "0XB7", + "EventName": "OCR.HWPF_L2_RFO.OUTSTANDING", + "MSRIndex": "0x1a6", + "MSRValue": "0x8000000000000020", + "PublicDescription": "Counts L2 cache hardware prefetch RFOs (written to the L2 cache only) that have an outstanding request. Returns the number of cycles until the response is received (i.e. XQ to XQ latency). Available PDIST counters: 0", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts modified writebacks from L1 cache that miss the L2 cache that have any type of response.", + "Counter": "0,1,2,3", + "EventCode": "0XB7", + "EventName": "OCR.L1WB_M.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x1000000010000", + "PublicDescription": "Counts modified writebacks from L1 cache that miss the L2 cache that have any type of response. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -820,6 +1060,18 @@ "EventName": "OCR.L1WB_M.L3_HIT", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x1001F803C0000", + "PublicDescription": "Counts modified writebacks from L1 cache that miss the L2 cache that were supplied by the L3 cache. Available PDIST counters: 0", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts modified writeBacks from L2 cache that miss the L3 cache that have any type of response.", + "Counter": "0,1,2,3", + "EventCode": "0XB7", + "EventName": "OCR.L2WB_M.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x2000000010000", + "PublicDescription": "Counts modified writeBacks from L2 cache that miss the L3 cache that have any type of response. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -830,6 +1082,7 @@ "EventName": "OCR.L2WB_M.L3_HIT", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x2001F803C0000", + "PublicDescription": "Counts modified writeBacks from L2 cache that miss the L3 cache that were supplied by the L3 cache. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -840,6 +1093,18 @@ "EventName": "OCR.PARTIAL_STREAMING_WR.L3_HIT", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x401F803C0000", + "PublicDescription": "Counts streaming stores which modify only part of a 64 byte cacheline that were supplied by the L3 cache. Available PDIST counters: 0", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts all data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that have any type of response.", + "Counter": "0,1,2,3", + "EventCode": "0XB7", + "EventName": "OCR.READS_TO_CORE.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x10477", + "PublicDescription": "Counts all data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that have any type of response. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -850,6 +1115,7 @@ "EventName": "OCR.READS_TO_CORE.L3_HIT", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x1F803C0477", + "PublicDescription": "Counts all data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by the L3 cache. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -860,6 +1126,7 @@ "EventName": "OCR.READS_TO_CORE.L3_HIT.SNOOP_HITM", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x10003C0477", + "PublicDescription": "Counts all data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by the L3 cache where a snoop was sent, the snoop hit, and modified data was forwarded. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -870,6 +1137,7 @@ "EventName": "OCR.READS_TO_CORE.L3_HIT.SNOOP_HIT_NO_FWD", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x4003C0477", + "PublicDescription": "Counts all data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by the L3 cache where a snoop was sent, the snoop hit, but no data was forwarded. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -880,6 +1148,7 @@ "EventName": "OCR.READS_TO_CORE.L3_HIT.SNOOP_HIT_WITH_FWD", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x8003C0477", + "PublicDescription": "Counts all data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by the L3 cache where a snoop was sent, the snoop hit, and non-modified data was forwarded. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -890,6 +1159,7 @@ "EventName": "OCR.READS_TO_CORE.L3_HIT.SNOOP_MISS", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x2003C0477", + "PublicDescription": "Counts all data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by the L3 cache where a snoop was sent but the snoop missed. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -900,6 +1170,18 @@ "EventName": "OCR.READS_TO_CORE.L3_HIT.SNOOP_NOT_NEEDED", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x1003C0477", + "PublicDescription": "Counts all data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by the L3 cache where no snoop was needed to satisfy the request. Available PDIST counters: 0", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts all data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that have an outstanding request. Returns the number of cycles until the response is received (i.e. XQ to XQ latency).", + "Counter": "0,1,2,3", + "EventCode": "0XB7", + "EventName": "OCR.READS_TO_CORE.OUTSTANDING", + "MSRIndex": "0x1a6", + "MSRValue": "0x8000000000000477", + "PublicDescription": "Counts all data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that have an outstanding request. Returns the number of cycles until the response is received (i.e. XQ to XQ latency). Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -910,6 +1192,7 @@ "EventName": "OCR.STREAMING_WR.L3_HIT", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x1F803C0800", + "PublicDescription": "Counts streaming stores that were supplied by the L3 cache. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -920,6 +1203,7 @@ "EventName": "OCR.UC_RD.L3_HIT", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x101F803C0000", + "PublicDescription": "Counts uncached memory reads that were supplied by the L3 cache. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -930,6 +1214,7 @@ "EventName": "OCR.UC_RD.L3_HIT.SNOOP_HITM", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x1010003C0000", + "PublicDescription": "Counts uncached memory reads that were supplied by the L3 cache where a snoop was sent, the snoop hit, and modified data was forwarded. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -940,6 +1225,7 @@ "EventName": "OCR.UC_RD.L3_HIT.SNOOP_HIT_NO_FWD", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x1004003C0000", + "PublicDescription": "Counts uncached memory reads that were supplied by the L3 cache where a snoop was sent, the snoop hit, but no data was forwarded. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -950,6 +1236,7 @@ "EventName": "OCR.UC_RD.L3_HIT.SNOOP_HIT_WITH_FWD", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x1008003C0000", + "PublicDescription": "Counts uncached memory reads that were supplied by the L3 cache where a snoop was sent, the snoop hit, and non-modified data was forwarded. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -960,6 +1247,7 @@ "EventName": "OCR.UC_RD.L3_HIT.SNOOP_MISS", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x1002003C0000", + "PublicDescription": "Counts uncached memory reads that were supplied by the L3 cache where a snoop was sent but the snoop missed. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -970,6 +1258,7 @@ "EventName": "OCR.UC_RD.L3_HIT.SNOOP_NOT_NEEDED", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x1001003C0000", + "PublicDescription": "Counts uncached memory reads that were supplied by the L3 cache where no snoop was needed to satisfy the request. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -980,6 +1269,7 @@ "EventName": "OCR.UC_WR.L3_HIT", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x201F803C0000", + "PublicDescription": "Counts uncached memory writes that were supplied by the L3 cache. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, diff --git a/tools/perf/pmu-events/arch/x86/elkhartlake/floating-point.json b/tools/perf/pmu-events/arch/x86/elkhartlake/floating-point.json index 79a4beba4b78..f47d97dfe0d9 100644 --- a/tools/perf/pmu-events/arch/x86/elkhartlake/floating-point.json +++ b/tools/perf/pmu-events/arch/x86/elkhartlake/floating-point.json @@ -23,6 +23,7 @@ "EventCode": "0xc2", "EventName": "UOPS_RETIRED.FPDIV", "PEBS": "1", + "PublicDescription": "Counts the number of floating point divide uops retired (x87 and SSE, including x87 sqrt). Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x8" } diff --git a/tools/perf/pmu-events/arch/x86/elkhartlake/memory.json b/tools/perf/pmu-events/arch/x86/elkhartlake/memory.json index 34306ec24e9b..417cd78fc048 100644 --- a/tools/perf/pmu-events/arch/x86/elkhartlake/memory.json +++ b/tools/perf/pmu-events/arch/x86/elkhartlake/memory.json @@ -13,6 +13,7 @@ "EventCode": "0x13", "EventName": "MISALIGN_MEM_REF.LOAD_PAGE_SPLIT", "PEBS": "1", + "PublicDescription": "Counts the number of misaligned load uops that are 4K page splits. Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0x2" }, @@ -22,16 +23,29 @@ "EventCode": "0x13", "EventName": "MISALIGN_MEM_REF.STORE_PAGE_SPLIT", "PEBS": "1", + "PublicDescription": "Counts the number of misaligned store uops that are 4K page splits. Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0x4" }, { + "BriefDescription": "Counts all code reads that were supplied by DRAM.", + "Counter": "0,1,2,3", + "EventCode": "0XB7", + "EventName": "OCR.ALL_CODE_RD.DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x184000044", + "PublicDescription": "Counts all code reads that were supplied by DRAM. Available PDIST counters: 0", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { "BriefDescription": "Counts all code reads that were not supplied by the L3 cache.", "Counter": "0,1,2,3", "EventCode": "0XB7", "EventName": "OCR.ALL_CODE_RD.L3_MISS", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x2184000044", + "PublicDescription": "Counts all code reads that were not supplied by the L3 cache. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -42,6 +56,18 @@ "EventName": "OCR.ALL_CODE_RD.L3_MISS_LOCAL", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x2184000044", + "PublicDescription": "Counts all code reads that were not supplied by the L3 cache. Available PDIST counters: 0", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts all code reads that were supplied by DRAM.", + "Counter": "0,1,2,3", + "EventCode": "0XB7", + "EventName": "OCR.ALL_CODE_RD.LOCAL_DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x184000044", + "PublicDescription": "Counts all code reads that were supplied by DRAM. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -52,6 +78,7 @@ "EventName": "OCR.COREWB_M.L3_MISS", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x3002184000000", + "PublicDescription": "Counts modified writebacks from L1 cache and L2 cache that were not supplied by the L3 cache. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -62,6 +89,18 @@ "EventName": "OCR.COREWB_M.L3_MISS_LOCAL", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x3002184000000", + "PublicDescription": "Counts modified writebacks from L1 cache and L2 cache that were not supplied by the L3 cache. Available PDIST counters: 0", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were supplied by DRAM.", + "Counter": "0,1,2,3", + "EventCode": "0XB7", + "EventName": "OCR.DEMAND_CODE_RD.DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x184000004", + "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were supplied by DRAM. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -72,6 +111,7 @@ "EventName": "OCR.DEMAND_CODE_RD.L3_MISS", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x2184000004", + "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were not supplied by the L3 cache. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -82,6 +122,29 @@ "EventName": "OCR.DEMAND_CODE_RD.L3_MISS_LOCAL", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x2184000004", + "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were not supplied by the L3 cache. Available PDIST counters: 0", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were supplied by DRAM.", + "Counter": "0,1,2,3", + "EventCode": "0XB7", + "EventName": "OCR.DEMAND_CODE_RD.LOCAL_DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x184000004", + "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were supplied by DRAM. Available PDIST counters: 0", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts cacheable demand data reads, L1 data cache hardware prefetches and software prefetches (except PREFETCHW) that were supplied by DRAM.", + "Counter": "0,1,2,3", + "EventCode": "0XB7", + "EventName": "OCR.DEMAND_DATA_AND_L1PF_RD.DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x184000001", + "PublicDescription": "Counts cacheable demand data reads, L1 data cache hardware prefetches and software prefetches (except PREFETCHW) that were supplied by DRAM. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -92,6 +155,7 @@ "EventName": "OCR.DEMAND_DATA_AND_L1PF_RD.L3_MISS", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x2184000001", + "PublicDescription": "Counts cacheable demand data reads, L1 data cache hardware prefetches and software prefetches (except PREFETCHW) that were not supplied by the L3 cache. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -102,6 +166,30 @@ "EventName": "OCR.DEMAND_DATA_AND_L1PF_RD.L3_MISS_LOCAL", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x2184000001", + "PublicDescription": "Counts cacheable demand data reads, L1 data cache hardware prefetches and software prefetches (except PREFETCHW) that were not supplied by the L3 cache. Available PDIST counters: 0", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts cacheable demand data reads, L1 data cache hardware prefetches and software prefetches (except PREFETCHW) that were supplied by DRAM.", + "Counter": "0,1,2,3", + "EventCode": "0XB7", + "EventName": "OCR.DEMAND_DATA_AND_L1PF_RD.LOCAL_DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x184000001", + "PublicDescription": "Counts cacheable demand data reads, L1 data cache hardware prefetches and software prefetches (except PREFETCHW) that were supplied by DRAM. Available PDIST counters: 0", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event OCR.DEMAND_DATA_AND_L1PF_RD.DRAM", + "Counter": "0,1,2,3", + "Deprecated": "1", + "EventCode": "0XB7", + "EventName": "OCR.DEMAND_DATA_RD.DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x184000001", + "PublicDescription": "This event is deprecated. Refer to new event OCR.DEMAND_DATA_AND_L1PF_RD.DRAM Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -113,6 +201,7 @@ "EventName": "OCR.DEMAND_DATA_RD.L3_MISS", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x2184000001", + "PublicDescription": "This event is deprecated. Refer to new event OCR.DEMAND_DATA_AND_L1PF_RD.L3_MISS Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -124,6 +213,30 @@ "EventName": "OCR.DEMAND_DATA_RD.L3_MISS_LOCAL", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x2184000001", + "PublicDescription": "This event is deprecated. Refer to new event OCR.DEMAND_DATA_AND_L1PF_RD.L3_MISS_LOCAL Available PDIST counters: 0", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event OCR.DEMAND_DATA_AND_L1PF_RD.LOCAL_DRAM", + "Counter": "0,1,2,3", + "Deprecated": "1", + "EventCode": "0XB7", + "EventName": "OCR.DEMAND_DATA_RD.LOCAL_DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x184000001", + "PublicDescription": "This event is deprecated. Refer to new event OCR.DEMAND_DATA_AND_L1PF_RD.LOCAL_DRAM Available PDIST counters: 0", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that were supplied by DRAM.", + "Counter": "0,1,2,3", + "EventCode": "0XB7", + "EventName": "OCR.DEMAND_RFO.DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x184000002", + "PublicDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that were supplied by DRAM. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -134,6 +247,7 @@ "EventName": "OCR.DEMAND_RFO.L3_MISS", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x2184000002", + "PublicDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that were not supplied by the L3 cache. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -144,6 +258,18 @@ "EventName": "OCR.DEMAND_RFO.L3_MISS_LOCAL", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x2184000002", + "PublicDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that were not supplied by the L3 cache. Available PDIST counters: 0", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that were supplied by DRAM.", + "Counter": "0,1,2,3", + "EventCode": "0XB7", + "EventName": "OCR.DEMAND_RFO.LOCAL_DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x184000002", + "PublicDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that were supplied by DRAM. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -154,6 +280,7 @@ "EventName": "OCR.FULL_STREAMING_WR.L3_MISS", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x802184000000", + "PublicDescription": "Counts streaming stores which modify a full 64 byte cacheline that were not supplied by the L3 cache. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -164,6 +291,18 @@ "EventName": "OCR.FULL_STREAMING_WR.L3_MISS_LOCAL", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x802184000000", + "PublicDescription": "Counts streaming stores which modify a full 64 byte cacheline that were not supplied by the L3 cache. Available PDIST counters: 0", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts L2 cache hardware prefetch code reads (written to the L2 cache only) that were supplied by DRAM.", + "Counter": "0,1,2,3", + "EventCode": "0XB7", + "EventName": "OCR.HWPF_L2_CODE_RD.DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x184000040", + "PublicDescription": "Counts L2 cache hardware prefetch code reads (written to the L2 cache only) that were supplied by DRAM. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -174,6 +313,7 @@ "EventName": "OCR.HWPF_L2_CODE_RD.L3_MISS", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x2184000040", + "PublicDescription": "Counts L2 cache hardware prefetch code reads (written to the L2 cache only) that were not supplied by the L3 cache. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -184,6 +324,29 @@ "EventName": "OCR.HWPF_L2_CODE_RD.L3_MISS_LOCAL", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x2184000040", + "PublicDescription": "Counts L2 cache hardware prefetch code reads (written to the L2 cache only) that were not supplied by the L3 cache. Available PDIST counters: 0", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts L2 cache hardware prefetch code reads (written to the L2 cache only) that were supplied by DRAM.", + "Counter": "0,1,2,3", + "EventCode": "0XB7", + "EventName": "OCR.HWPF_L2_CODE_RD.LOCAL_DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x184000040", + "PublicDescription": "Counts L2 cache hardware prefetch code reads (written to the L2 cache only) that were supplied by DRAM. Available PDIST counters: 0", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts L2 cache hardware prefetch data reads (written to the L2 cache only) that were supplied by DRAM.", + "Counter": "0,1,2,3", + "EventCode": "0XB7", + "EventName": "OCR.HWPF_L2_DATA_RD.DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x184000010", + "PublicDescription": "Counts L2 cache hardware prefetch data reads (written to the L2 cache only) that were supplied by DRAM. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -194,6 +357,7 @@ "EventName": "OCR.HWPF_L2_DATA_RD.L3_MISS", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x2184000010", + "PublicDescription": "Counts L2 cache hardware prefetch data reads (written to the L2 cache only) that were not supplied by the L3 cache. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -204,6 +368,29 @@ "EventName": "OCR.HWPF_L2_DATA_RD.L3_MISS_LOCAL", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x2184000010", + "PublicDescription": "Counts L2 cache hardware prefetch data reads (written to the L2 cache only) that were not supplied by the L3 cache. Available PDIST counters: 0", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts L2 cache hardware prefetch data reads (written to the L2 cache only) that were supplied by DRAM.", + "Counter": "0,1,2,3", + "EventCode": "0XB7", + "EventName": "OCR.HWPF_L2_DATA_RD.LOCAL_DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x184000010", + "PublicDescription": "Counts L2 cache hardware prefetch data reads (written to the L2 cache only) that were supplied by DRAM. Available PDIST counters: 0", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts L2 cache hardware prefetch RFOs (written to the L2 cache only) that were supplied by DRAM.", + "Counter": "0,1,2,3", + "EventCode": "0XB7", + "EventName": "OCR.HWPF_L2_RFO.DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x184000020", + "PublicDescription": "Counts L2 cache hardware prefetch RFOs (written to the L2 cache only) that were supplied by DRAM. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -214,6 +401,7 @@ "EventName": "OCR.HWPF_L2_RFO.L3_MISS", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x2184000020", + "PublicDescription": "Counts L2 cache hardware prefetch RFOs (written to the L2 cache only) that were not supplied by the L3 cache. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -224,6 +412,18 @@ "EventName": "OCR.HWPF_L2_RFO.L3_MISS_LOCAL", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x2184000020", + "PublicDescription": "Counts L2 cache hardware prefetch RFOs (written to the L2 cache only) that were not supplied by the L3 cache. Available PDIST counters: 0", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts L2 cache hardware prefetch RFOs (written to the L2 cache only) that were supplied by DRAM.", + "Counter": "0,1,2,3", + "EventCode": "0XB7", + "EventName": "OCR.HWPF_L2_RFO.LOCAL_DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x184000020", + "PublicDescription": "Counts L2 cache hardware prefetch RFOs (written to the L2 cache only) that were supplied by DRAM. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -234,6 +434,7 @@ "EventName": "OCR.L1WB_M.L3_MISS", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x1002184000000", + "PublicDescription": "Counts modified writebacks from L1 cache that miss the L2 cache that were not supplied by the L3 cache. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -244,6 +445,7 @@ "EventName": "OCR.L1WB_M.L3_MISS_LOCAL", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x1002184000000", + "PublicDescription": "Counts modified writebacks from L1 cache that miss the L2 cache that were not supplied by the L3 cache. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -254,6 +456,7 @@ "EventName": "OCR.L2WB_M.L3_MISS", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x2002184000000", + "PublicDescription": "Counts modified writeBacks from L2 cache that miss the L3 cache that were not supplied by the L3 cache. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -264,6 +467,7 @@ "EventName": "OCR.L2WB_M.L3_MISS_LOCAL", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x2002184000000", + "PublicDescription": "Counts modified writeBacks from L2 cache that miss the L3 cache that were not supplied by the L3 cache. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -274,6 +478,7 @@ "EventName": "OCR.OTHER.L3_MISS", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x2184008000", + "PublicDescription": "Counts miscellaneous requests, such as I/O accesses, that were not supplied by the L3 cache. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -284,6 +489,7 @@ "EventName": "OCR.OTHER.L3_MISS_LOCAL", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x2184008000", + "PublicDescription": "Counts miscellaneous requests, such as I/O accesses, that were not supplied by the L3 cache. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -294,6 +500,7 @@ "EventName": "OCR.PARTIAL_STREAMING_WR.L3_MISS", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x402184000000", + "PublicDescription": "Counts streaming stores which modify only part of a 64 byte cacheline that were not supplied by the L3 cache. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -304,6 +511,7 @@ "EventName": "OCR.PARTIAL_STREAMING_WR.L3_MISS_LOCAL", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x402184000000", + "PublicDescription": "Counts streaming stores which modify only part of a 64 byte cacheline that were not supplied by the L3 cache. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -314,6 +522,18 @@ "EventName": "OCR.PREFETCHES.L3_MISS", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x2184000470", + "PublicDescription": "Counts all hardware and software prefetches that were not supplied by the L3 cache. Available PDIST counters: 0", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts all data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by DRAM.", + "Counter": "0,1,2,3", + "EventCode": "0XB7", + "EventName": "OCR.READS_TO_CORE.DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x184000477", + "PublicDescription": "Counts all data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by DRAM. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -324,6 +544,7 @@ "EventName": "OCR.READS_TO_CORE.L3_MISS", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x2184000477", + "PublicDescription": "Counts all data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were not supplied by the L3 cache. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -334,6 +555,18 @@ "EventName": "OCR.READS_TO_CORE.L3_MISS_LOCAL", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x2184000477", + "PublicDescription": "Counts all data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were not supplied by the L3 cache. Available PDIST counters: 0", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts all data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by DRAM.", + "Counter": "0,1,2,3", + "EventCode": "0XB7", + "EventName": "OCR.READS_TO_CORE.LOCAL_DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x184000477", + "PublicDescription": "Counts all data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by DRAM. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -344,6 +577,7 @@ "EventName": "OCR.STREAMING_WR.L3_MISS", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x2184000800", + "PublicDescription": "Counts streaming stores that were not supplied by the L3 cache. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -354,6 +588,18 @@ "EventName": "OCR.STREAMING_WR.L3_MISS_LOCAL", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x2184000800", + "PublicDescription": "Counts streaming stores that were not supplied by the L3 cache. Available PDIST counters: 0", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts uncached memory reads that were supplied by DRAM.", + "Counter": "0,1,2,3", + "EventCode": "0XB7", + "EventName": "OCR.UC_RD.DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x100184000000", + "PublicDescription": "Counts uncached memory reads that were supplied by DRAM. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -364,6 +610,7 @@ "EventName": "OCR.UC_RD.L3_MISS", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x102184000000", + "PublicDescription": "Counts uncached memory reads that were not supplied by the L3 cache. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -374,6 +621,18 @@ "EventName": "OCR.UC_RD.L3_MISS_LOCAL", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x102184000000", + "PublicDescription": "Counts uncached memory reads that were not supplied by the L3 cache. Available PDIST counters: 0", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts uncached memory reads that were supplied by DRAM.", + "Counter": "0,1,2,3", + "EventCode": "0XB7", + "EventName": "OCR.UC_RD.LOCAL_DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x100184000000", + "PublicDescription": "Counts uncached memory reads that were supplied by DRAM. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -384,6 +643,7 @@ "EventName": "OCR.UC_WR.L3_MISS", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x202184000000", + "PublicDescription": "Counts uncached memory writes that were not supplied by the L3 cache. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -394,6 +654,7 @@ "EventName": "OCR.UC_WR.L3_MISS_LOCAL", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x202184000000", + "PublicDescription": "Counts uncached memory writes that were not supplied by the L3 cache. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" } diff --git a/tools/perf/pmu-events/arch/x86/elkhartlake/other.json b/tools/perf/pmu-events/arch/x86/elkhartlake/other.json index 57613207f7ad..2cdc6b64f31d 100644 --- a/tools/perf/pmu-events/arch/x86/elkhartlake/other.json +++ b/tools/perf/pmu-events/arch/x86/elkhartlake/other.json @@ -113,26 +113,7 @@ "EventName": "OCR.ALL_CODE_RD.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x10044", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts all code reads that were supplied by DRAM.", - "Counter": "0,1,2,3", - "EventCode": "0XB7", - "EventName": "OCR.ALL_CODE_RD.DRAM", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x184000044", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts all code reads that were supplied by DRAM.", - "Counter": "0,1,2,3", - "EventCode": "0XB7", - "EventName": "OCR.ALL_CODE_RD.LOCAL_DRAM", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x184000044", + "PublicDescription": "Counts all code reads that have any type of response. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -143,180 +124,7 @@ "EventName": "OCR.ALL_CODE_RD.OUTSTANDING", "MSRIndex": "0x1a6", "MSRValue": "0x8000000000000044", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts modified writebacks from L1 cache and L2 cache that have any type of response.", - "Counter": "0,1,2,3", - "EventCode": "0XB7", - "EventName": "OCR.COREWB_M.ANY_RESPONSE", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x3000000010000", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts modified writebacks from L1 cache and L2 cache that have an outstanding request. Returns the number of cycles until the response is received (i.e. XQ to XQ latency).", - "Counter": "0,1,2,3", - "EventCode": "0XB7", - "EventName": "OCR.COREWB_M.OUTSTANDING", - "MSRIndex": "0x1a6", - "MSRValue": "0x8003000000000000", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that have any type of response.", - "Counter": "0,1,2,3", - "EventCode": "0XB7", - "EventName": "OCR.DEMAND_CODE_RD.ANY_RESPONSE", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x10004", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were supplied by DRAM.", - "Counter": "0,1,2,3", - "EventCode": "0XB7", - "EventName": "OCR.DEMAND_CODE_RD.DRAM", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x184000004", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were supplied by DRAM.", - "Counter": "0,1,2,3", - "EventCode": "0XB7", - "EventName": "OCR.DEMAND_CODE_RD.LOCAL_DRAM", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x184000004", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts cacheable demand data reads, L1 data cache hardware prefetches and software prefetches (except PREFETCHW) that have any type of response.", - "Counter": "0,1,2,3", - "EventCode": "0XB7", - "EventName": "OCR.DEMAND_DATA_AND_L1PF_RD.ANY_RESPONSE", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x10001", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts cacheable demand data reads, L1 data cache hardware prefetches and software prefetches (except PREFETCHW) that were supplied by DRAM.", - "Counter": "0,1,2,3", - "EventCode": "0XB7", - "EventName": "OCR.DEMAND_DATA_AND_L1PF_RD.DRAM", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x184000001", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts cacheable demand data reads, L1 data cache hardware prefetches and software prefetches (except PREFETCHW) that were supplied by DRAM.", - "Counter": "0,1,2,3", - "EventCode": "0XB7", - "EventName": "OCR.DEMAND_DATA_AND_L1PF_RD.LOCAL_DRAM", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x184000001", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts cacheable demand data reads, L1 data cache hardware prefetches and software prefetches (except PREFETCHW) that have an outstanding request. Returns the number of cycles until the response is received (i.e. XQ to XQ latency).", - "Counter": "0,1,2,3", - "EventCode": "0XB7", - "EventName": "OCR.DEMAND_DATA_AND_L1PF_RD.OUTSTANDING", - "MSRIndex": "0x1a6", - "MSRValue": "0x8000000000000001", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event OCR.DEMAND_DATA_AND_L1PF_RD.ANY_RESPONSE", - "Counter": "0,1,2,3", - "Deprecated": "1", - "EventCode": "0XB7", - "EventName": "OCR.DEMAND_DATA_RD.ANY_RESPONSE", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x10001", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event OCR.DEMAND_DATA_AND_L1PF_RD.DRAM", - "Counter": "0,1,2,3", - "Deprecated": "1", - "EventCode": "0XB7", - "EventName": "OCR.DEMAND_DATA_RD.DRAM", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x184000001", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event OCR.DEMAND_DATA_AND_L1PF_RD.LOCAL_DRAM", - "Counter": "0,1,2,3", - "Deprecated": "1", - "EventCode": "0XB7", - "EventName": "OCR.DEMAND_DATA_RD.LOCAL_DRAM", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x184000001", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event OCR.DEMAND_DATA_AND_L1PF_RD.OUTSTANDING", - "Counter": "0,1,2,3", - "Deprecated": "1", - "EventCode": "0XB7", - "EventName": "OCR.DEMAND_DATA_RD.OUTSTANDING", - "MSRIndex": "0x1a6", - "MSRValue": "0x8000000000000001", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that have any type of response.", - "Counter": "0,1,2,3", - "EventCode": "0XB7", - "EventName": "OCR.DEMAND_RFO.ANY_RESPONSE", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x10002", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that were supplied by DRAM.", - "Counter": "0,1,2,3", - "EventCode": "0XB7", - "EventName": "OCR.DEMAND_RFO.DRAM", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x184000002", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that were supplied by DRAM.", - "Counter": "0,1,2,3", - "EventCode": "0XB7", - "EventName": "OCR.DEMAND_RFO.LOCAL_DRAM", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x184000002", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that have an outstanding request. Returns the number of cycles until the response is received (i.e. XQ to XQ latency).", - "Counter": "0,1,2,3", - "EventCode": "0XB7", - "EventName": "OCR.DEMAND_RFO.OUTSTANDING", - "MSRIndex": "0x1a6", - "MSRValue": "0x8000000000000002", + "PublicDescription": "Counts all code reads that have an outstanding request. Returns the number of cycles until the response is received (i.e. XQ to XQ latency). Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -327,146 +135,7 @@ "EventName": "OCR.FULL_STREAMING_WR.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x800000010000", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts L1 data cache hardware prefetches and software prefetches (except PREFETCHW and PFRFO) that have any type of response.", - "Counter": "0,1,2,3", - "EventCode": "0XB7", - "EventName": "OCR.HWPF_L1D_AND_SWPF.ANY_RESPONSE", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x10400", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts L2 cache hardware prefetch code reads (written to the L2 cache only) that have any type of response.", - "Counter": "0,1,2,3", - "EventCode": "0XB7", - "EventName": "OCR.HWPF_L2_CODE_RD.ANY_RESPONSE", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x10040", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts L2 cache hardware prefetch code reads (written to the L2 cache only) that were supplied by DRAM.", - "Counter": "0,1,2,3", - "EventCode": "0XB7", - "EventName": "OCR.HWPF_L2_CODE_RD.DRAM", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x184000040", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts L2 cache hardware prefetch code reads (written to the L2 cache only) that were supplied by DRAM.", - "Counter": "0,1,2,3", - "EventCode": "0XB7", - "EventName": "OCR.HWPF_L2_CODE_RD.LOCAL_DRAM", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x184000040", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts L2 cache hardware prefetch code reads (written to the L2 cache only) that have an outstanding request. Returns the number of cycles until the response is received (i.e. XQ to XQ latency).", - "Counter": "0,1,2,3", - "EventCode": "0XB7", - "EventName": "OCR.HWPF_L2_CODE_RD.OUTSTANDING", - "MSRIndex": "0x1a6", - "MSRValue": "0x8000000000000040", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts L2 cache hardware prefetch data reads (written to the L2 cache only) that have any type of response.", - "Counter": "0,1,2,3", - "EventCode": "0XB7", - "EventName": "OCR.HWPF_L2_DATA_RD.ANY_RESPONSE", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x10010", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts L2 cache hardware prefetch data reads (written to the L2 cache only) that were supplied by DRAM.", - "Counter": "0,1,2,3", - "EventCode": "0XB7", - "EventName": "OCR.HWPF_L2_DATA_RD.DRAM", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x184000010", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts L2 cache hardware prefetch data reads (written to the L2 cache only) that were supplied by DRAM.", - "Counter": "0,1,2,3", - "EventCode": "0XB7", - "EventName": "OCR.HWPF_L2_DATA_RD.LOCAL_DRAM", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x184000010", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts L2 cache hardware prefetch RFOs (written to the L2 cache only) that have any type of response.", - "Counter": "0,1,2,3", - "EventCode": "0XB7", - "EventName": "OCR.HWPF_L2_RFO.ANY_RESPONSE", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x10020", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts L2 cache hardware prefetch RFOs (written to the L2 cache only) that were supplied by DRAM.", - "Counter": "0,1,2,3", - "EventCode": "0XB7", - "EventName": "OCR.HWPF_L2_RFO.DRAM", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x184000020", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts L2 cache hardware prefetch RFOs (written to the L2 cache only) that were supplied by DRAM.", - "Counter": "0,1,2,3", - "EventCode": "0XB7", - "EventName": "OCR.HWPF_L2_RFO.LOCAL_DRAM", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x184000020", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts L2 cache hardware prefetch RFOs (written to the L2 cache only) that have an outstanding request. Returns the number of cycles until the response is received (i.e. XQ to XQ latency).", - "Counter": "0,1,2,3", - "EventCode": "0XB7", - "EventName": "OCR.HWPF_L2_RFO.OUTSTANDING", - "MSRIndex": "0x1a6", - "MSRValue": "0x8000000000000020", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts modified writebacks from L1 cache that miss the L2 cache that have any type of response.", - "Counter": "0,1,2,3", - "EventCode": "0XB7", - "EventName": "OCR.L1WB_M.ANY_RESPONSE", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x1000000010000", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts modified writeBacks from L2 cache that miss the L3 cache that have any type of response.", - "Counter": "0,1,2,3", - "EventCode": "0XB7", - "EventName": "OCR.L2WB_M.ANY_RESPONSE", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x2000000010000", + "PublicDescription": "Counts streaming stores which modify a full 64 byte cacheline that have any type of response. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -477,6 +146,7 @@ "EventName": "OCR.OTHER.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x18000", + "PublicDescription": "Counts miscellaneous requests, such as I/O accesses, that have any type of response. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -487,6 +157,7 @@ "EventName": "OCR.PARTIAL_STREAMING_WR.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x400000010000", + "PublicDescription": "Counts streaming stores which modify only part of a 64 byte cacheline that have any type of response. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -497,46 +168,7 @@ "EventName": "OCR.PREFETCHES.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x10470", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts all data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that have any type of response.", - "Counter": "0,1,2,3", - "EventCode": "0XB7", - "EventName": "OCR.READS_TO_CORE.ANY_RESPONSE", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x10477", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts all data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by DRAM.", - "Counter": "0,1,2,3", - "EventCode": "0XB7", - "EventName": "OCR.READS_TO_CORE.DRAM", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x184000477", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts all data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by DRAM.", - "Counter": "0,1,2,3", - "EventCode": "0XB7", - "EventName": "OCR.READS_TO_CORE.LOCAL_DRAM", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x184000477", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts all data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that have an outstanding request. Returns the number of cycles until the response is received (i.e. XQ to XQ latency).", - "Counter": "0,1,2,3", - "EventCode": "0XB7", - "EventName": "OCR.READS_TO_CORE.OUTSTANDING", - "MSRIndex": "0x1a6", - "MSRValue": "0x8000000000000477", + "PublicDescription": "Counts all hardware and software prefetches that have any type of response. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -547,6 +179,7 @@ "EventName": "OCR.STREAMING_WR.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x10800", + "PublicDescription": "Counts streaming stores that have any type of response. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -557,26 +190,7 @@ "EventName": "OCR.UC_RD.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x100000010000", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts uncached memory reads that were supplied by DRAM.", - "Counter": "0,1,2,3", - "EventCode": "0XB7", - "EventName": "OCR.UC_RD.DRAM", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x100184000000", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts uncached memory reads that were supplied by DRAM.", - "Counter": "0,1,2,3", - "EventCode": "0XB7", - "EventName": "OCR.UC_RD.LOCAL_DRAM", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x100184000000", + "PublicDescription": "Counts uncached memory reads that have any type of response. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -587,6 +201,7 @@ "EventName": "OCR.UC_RD.OUTSTANDING", "MSRIndex": "0x1a6", "MSRValue": "0x8000100000000000", + "PublicDescription": "Counts uncached memory reads that have an outstanding request. Returns the number of cycles until the response is received (i.e. XQ to XQ latency). Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -597,6 +212,7 @@ "EventName": "OCR.UC_WR.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x200000010000", + "PublicDescription": "Counts uncached memory writes that have any type of response. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" } diff --git a/tools/perf/pmu-events/arch/x86/elkhartlake/pipeline.json b/tools/perf/pmu-events/arch/x86/elkhartlake/pipeline.json index e4e7902c1162..0fc2e821b14a 100644 --- a/tools/perf/pmu-events/arch/x86/elkhartlake/pipeline.json +++ b/tools/perf/pmu-events/arch/x86/elkhartlake/pipeline.json @@ -5,7 +5,7 @@ "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.ALL_BRANCHES", "PEBS": "1", - "PublicDescription": "Counts the total number of instructions in which the instruction pointer (IP) of the processor is resteered due to a branch instruction and the branch instruction successfully retires. All branch type instructions are accounted for.", + "PublicDescription": "Counts the total number of instructions in which the instruction pointer (IP) of the processor is resteered due to a branch instruction and the branch instruction successfully retires. All branch type instructions are accounted for. Available PDIST counters: 0", "SampleAfterValue": "200003" }, { @@ -14,6 +14,7 @@ "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.CALL", "PEBS": "1", + "PublicDescription": "Counts the number of near CALL branch instructions retired. Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0xf9" }, @@ -23,6 +24,7 @@ "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.FAR_BRANCH", "PEBS": "1", + "PublicDescription": "Counts the number of far branch instructions retired, includes far jump, far call and return, and interrupt call and return. Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0xbf" }, @@ -32,6 +34,7 @@ "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.IND_CALL", "PEBS": "1", + "PublicDescription": "Counts the number of near indirect CALL branch instructions retired. Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0xfb" }, @@ -41,6 +44,7 @@ "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.JCC", "PEBS": "1", + "PublicDescription": "Counts the number of retired JCC (Jump on Conditional Code) branch instructions retired, includes both taken and not taken branches. Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0x7e" }, @@ -50,6 +54,7 @@ "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.NON_RETURN_IND", "PEBS": "1", + "PublicDescription": "Counts the number of near indirect JMP and near indirect CALL branch instructions retired. Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0xeb" }, @@ -59,6 +64,7 @@ "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.REL_CALL", "PEBS": "1", + "PublicDescription": "Counts the number of near relative CALL branch instructions retired. Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0xfd" }, @@ -68,6 +74,7 @@ "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.RETURN", "PEBS": "1", + "PublicDescription": "Counts the number of near RET branch instructions retired. Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0xf7" }, @@ -77,6 +84,7 @@ "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.TAKEN_JCC", "PEBS": "1", + "PublicDescription": "Counts the number of taken JCC (Jump on Conditional Code) branch instructions retired. Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0xfe" }, @@ -86,7 +94,7 @@ "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.ALL_BRANCHES", "PEBS": "1", - "PublicDescription": "Counts the total number of mispredicted branch instructions retired. All branch type instructions are accounted for. Prediction of the branch target address enables the processor to begin executing instructions before the non-speculative execution path is known. The branch prediction unit (BPU) predicts the target address based on the instruction pointer (IP) of the branch and on the execution path through which execution reached this IP. A branch misprediction occurs when the prediction is wrong, and results in discarding all instructions executed in the speculative path and re-fetching from the correct path.", + "PublicDescription": "Counts the total number of mispredicted branch instructions retired. All branch type instructions are accounted for. Prediction of the branch target address enables the processor to begin executing instructions before the non-speculative execution path is known. The branch prediction unit (BPU) predicts the target address based on the instruction pointer (IP) of the branch and on the execution path through which execution reached this IP. A branch misprediction occurs when the prediction is wrong, and results in discarding all instructions executed in the speculative path and re-fetching from the correct path. Available PDIST counters: 0", "SampleAfterValue": "200003" }, { @@ -95,6 +103,7 @@ "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.IND_CALL", "PEBS": "1", + "PublicDescription": "Counts the number of mispredicted near indirect CALL branch instructions retired. Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0xfb" }, @@ -104,6 +113,7 @@ "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.JCC", "PEBS": "1", + "PublicDescription": "Counts the number of mispredicted JCC (Jump on Conditional Code) branch instructions retired. Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0x7e" }, @@ -113,6 +123,7 @@ "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.NON_RETURN_IND", "PEBS": "1", + "PublicDescription": "Counts the number of mispredicted near indirect JMP and near indirect CALL branch instructions retired. Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0xeb" }, @@ -122,6 +133,7 @@ "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.RETURN", "PEBS": "1", + "PublicDescription": "Counts the number of mispredicted near RET branch instructions retired. Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0xf7" }, @@ -131,6 +143,7 @@ "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.TAKEN_JCC", "PEBS": "1", + "PublicDescription": "Counts the number of mispredicted taken JCC (Jump on Conditional Code) branch instructions retired. Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0xfe" }, @@ -206,7 +219,7 @@ "Counter": "Fixed counter 0", "EventName": "INST_RETIRED.ANY", "PEBS": "1", - "PublicDescription": "Counts the total number of instructions that retired. For instructions that consist of multiple uops, this event counts the retirement of the last uop of the instruction. This event continues counting during hardware interrupts, traps, and inside interrupt handlers. This event uses fixed counter 0.", + "PublicDescription": "Counts the total number of instructions that retired. For instructions that consist of multiple uops, this event counts the retirement of the last uop of the instruction. This event continues counting during hardware interrupts, traps, and inside interrupt handlers. This event uses fixed counter 0. Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x1" }, @@ -216,7 +229,7 @@ "EventCode": "0xc0", "EventName": "INST_RETIRED.ANY_P", "PEBS": "1", - "PublicDescription": "Counts the total number of instructions that retired. For instructions that consist of multiple uops, this event counts the retirement of the last uop of the instruction. This event continues counting during hardware interrupts, traps, and inside interrupt handlers. This event uses a programmable general purpose performance counter.", + "PublicDescription": "Counts the total number of instructions that retired. For instructions that consist of multiple uops, this event counts the retirement of the last uop of the instruction. This event continues counting during hardware interrupts, traps, and inside interrupt handlers. This event uses a programmable general purpose performance counter. Available PDIST counters: 0", "SampleAfterValue": "2000003" }, { @@ -225,6 +238,7 @@ "EventCode": "0x03", "EventName": "LD_BLOCKS.4K_ALIAS", "PEBS": "1", + "PublicDescription": "Counts the number of retired loads that are blocked because it initially appears to be store forward blocked, but subsequently is shown not to be blocked based on 4K alias check. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x4" }, @@ -234,6 +248,7 @@ "EventCode": "0x03", "EventName": "LD_BLOCKS.ALL", "PEBS": "1", + "PublicDescription": "Counts the number of retired loads that are blocked for any of the following reasons: DTLB miss, address alias, store forward or data unknown (includes memory disambiguation blocks and ESP consuming load blocks). Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x10" }, @@ -243,6 +258,7 @@ "EventCode": "0x03", "EventName": "LD_BLOCKS.DATA_UNKNOWN", "PEBS": "1", + "PublicDescription": "Counts the number of retired loads that are blocked because its address exactly matches an older store whose data is not ready. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x1" }, @@ -252,6 +268,7 @@ "EventCode": "0x03", "EventName": "LD_BLOCKS.STORE_FORWARD", "PEBS": "1", + "PublicDescription": "Counts the number of retired loads that are blocked because its address partially overlapped with an older store. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x2" }, @@ -464,6 +481,7 @@ "EventCode": "0xc2", "EventName": "TOPDOWN_RETIRING.ALL", "PEBS": "1", + "PublicDescription": "Counts the total number of consumed retirement slots. Available PDIST counters: 0", "SampleAfterValue": "1000003" }, { @@ -480,6 +498,7 @@ "EventCode": "0xc2", "EventName": "UOPS_RETIRED.ALL", "PEBS": "1", + "PublicDescription": "Counts the total number of uops retired. Available PDIST counters: 0", "SampleAfterValue": "2000003" }, { @@ -488,6 +507,7 @@ "EventCode": "0xc2", "EventName": "UOPS_RETIRED.IDIV", "PEBS": "1", + "PublicDescription": "Counts the number of integer divide uops retired. Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x10" }, @@ -497,7 +517,7 @@ "EventCode": "0xc2", "EventName": "UOPS_RETIRED.MS", "PEBS": "1", - "PublicDescription": "Counts the number of uops that are from complex flows issued by the Microcode Sequencer (MS). This includes uops from flows due to complex instructions, faults, assists, and inserted flows.", + "PublicDescription": "Counts the number of uops that are from complex flows issued by the Microcode Sequencer (MS). This includes uops from flows due to complex instructions, faults, assists, and inserted flows. Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x1" }, @@ -507,6 +527,7 @@ "EventCode": "0xc2", "EventName": "UOPS_RETIRED.X87", "PEBS": "1", + "PublicDescription": "Counts the number of x87 uops retired, includes those in MS flows. Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x2" } diff --git a/tools/perf/pmu-events/arch/x86/elkhartlake/virtual-memory.json b/tools/perf/pmu-events/arch/x86/elkhartlake/virtual-memory.json index f9a6caed8776..bf56d72bb4a7 100644 --- a/tools/perf/pmu-events/arch/x86/elkhartlake/virtual-memory.json +++ b/tools/perf/pmu-events/arch/x86/elkhartlake/virtual-memory.json @@ -242,6 +242,7 @@ "EventCode": "0x03", "EventName": "LD_BLOCKS.DTLB_MISS", "PEBS": "1", + "PublicDescription": "Counts the number of retired loads that are blocked due to a first level TLB miss. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x8" }, @@ -252,6 +253,7 @@ "EventCode": "0xd0", "EventName": "MEM_UOPS_RETIRED.DTLB_MISS", "PEBS": "1", + "PublicDescription": "Counts the number of memory uops retired that missed in the second level TLB. Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0x13" }, @@ -262,6 +264,7 @@ "EventCode": "0xd0", "EventName": "MEM_UOPS_RETIRED.DTLB_MISS_LOADS", "PEBS": "1", + "PublicDescription": "Counts the number of load uops retired that miss in the second Level TLB. Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0x11" }, @@ -272,6 +275,7 @@ "EventCode": "0xd0", "EventName": "MEM_UOPS_RETIRED.DTLB_MISS_STORES", "PEBS": "1", + "PublicDescription": "Counts the number of store uops retired that miss in the second level TLB. Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0x12" } diff --git a/tools/perf/pmu-events/arch/x86/emeraldrapids/cache.json b/tools/perf/pmu-events/arch/x86/emeraldrapids/cache.json index 3b0581151d63..10bdb193c16f 100644 --- a/tools/perf/pmu-events/arch/x86/emeraldrapids/cache.json +++ b/tools/perf/pmu-events/arch/x86/emeraldrapids/cache.json @@ -4,6 +4,7 @@ "Counter": "0,1,2,3", "EventCode": "0x51", "EventName": "L1D.HWPF_MISS", + "PublicDescription": "L1D.HWPF_MISS Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x20" }, @@ -12,7 +13,7 @@ "Counter": "0,1,2,3", "EventCode": "0x51", "EventName": "L1D.REPLACEMENT", - "PublicDescription": "Counts L1D data line replacements including opportunistic replacements, and replacements that require stall-for-replace or block-for-replace.", + "PublicDescription": "Counts L1D data line replacements including opportunistic replacements, and replacements that require stall-for-replace or block-for-replace. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -21,7 +22,7 @@ "Counter": "0,1,2,3", "EventCode": "0x48", "EventName": "L1D_PEND_MISS.FB_FULL", - "PublicDescription": "Counts number of cycles a demand request has waited due to L1D Fill Buffer (FB) unavailability. Demand requests include cacheable/uncacheable demand load, store, lock or SW prefetch accesses.", + "PublicDescription": "Counts number of cycles a demand request has waited due to L1D Fill Buffer (FB) unavailability. Demand requests include cacheable/uncacheable demand load, store, lock or SW prefetch accesses. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x2" }, @@ -32,7 +33,7 @@ "EdgeDetect": "1", "EventCode": "0x48", "EventName": "L1D_PEND_MISS.FB_FULL_PERIODS", - "PublicDescription": "Counts number of phases a demand request has waited due to L1D Fill Buffer (FB) unavailability. Demand requests include cacheable/uncacheable demand load, store, lock or SW prefetch accesses.", + "PublicDescription": "Counts number of phases a demand request has waited due to L1D Fill Buffer (FB) unavailability. Demand requests include cacheable/uncacheable demand load, store, lock or SW prefetch accesses. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x2" }, @@ -42,6 +43,7 @@ "Deprecated": "1", "EventCode": "0x48", "EventName": "L1D_PEND_MISS.L2_STALL", + "PublicDescription": "This event is deprecated. Refer to new event L1D_PEND_MISS.L2_STALLS Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x4" }, @@ -50,7 +52,7 @@ "Counter": "0,1,2,3", "EventCode": "0x48", "EventName": "L1D_PEND_MISS.L2_STALLS", - "PublicDescription": "Counts number of cycles a demand request has waited due to L1D due to lack of L2 resources. Demand requests include cacheable/uncacheable demand load, store, lock or SW prefetch accesses.", + "PublicDescription": "Counts number of cycles a demand request has waited due to L1D due to lack of L2 resources. Demand requests include cacheable/uncacheable demand load, store, lock or SW prefetch accesses. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x4" }, @@ -59,7 +61,7 @@ "Counter": "0,1,2,3", "EventCode": "0x48", "EventName": "L1D_PEND_MISS.PENDING", - "PublicDescription": "Counts number of L1D misses that are outstanding in each cycle, that is each cycle the number of Fill Buffers (FB) outstanding required by Demand Reads. FB either is held by demand loads, or it is held by non-demand loads and gets hit at least once by demand. The valid outstanding interval is defined until the FB deallocation by one of the following ways: from FB allocation, if FB is allocated by demand from the demand Hit FB, if it is allocated by hardware or software prefetch. Note: In the L1D, a Demand Read contains cacheable or noncacheable demand loads, including ones causing cache-line splits and reads due to page walks resulted from any request type.", + "PublicDescription": "Counts number of L1D misses that are outstanding in each cycle, that is each cycle the number of Fill Buffers (FB) outstanding required by Demand Reads. FB either is held by demand loads, or it is held by non-demand loads and gets hit at least once by demand. The valid outstanding interval is defined until the FB deallocation by one of the following ways: from FB allocation, if FB is allocated by demand from the demand Hit FB, if it is allocated by hardware or software prefetch. Note: In the L1D, a Demand Read contains cacheable or noncacheable demand loads, including ones causing cache-line splits and reads due to page walks resulted from any request type. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x1" }, @@ -69,7 +71,7 @@ "CounterMask": "1", "EventCode": "0x48", "EventName": "L1D_PEND_MISS.PENDING_CYCLES", - "PublicDescription": "Counts duration of L1D miss outstanding in cycles.", + "PublicDescription": "Counts duration of L1D miss outstanding in cycles. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x1" }, @@ -78,7 +80,7 @@ "Counter": "0,1,2,3", "EventCode": "0x25", "EventName": "L2_LINES_IN.ALL", - "PublicDescription": "Counts the number of L2 cache lines filling the L2. Counting does not cover rejects.", + "PublicDescription": "Counts the number of L2 cache lines filling the L2. Counting does not cover rejects. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1f" }, @@ -87,7 +89,7 @@ "Counter": "0,1,2,3", "EventCode": "0x26", "EventName": "L2_LINES_OUT.NON_SILENT", - "PublicDescription": "Counts the number of lines that are evicted by L2 cache when triggered by an L2 cache fill. Those lines are in Modified state. Modified lines are written back to L3", + "PublicDescription": "Counts the number of lines that are evicted by L2 cache when triggered by an L2 cache fill. Those lines are in Modified state. Modified lines are written back to L3 Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0x2" }, @@ -96,7 +98,7 @@ "Counter": "0,1,2,3", "EventCode": "0x26", "EventName": "L2_LINES_OUT.SILENT", - "PublicDescription": "Counts the number of lines that are silently dropped by L2 cache. These lines are typically in Shared or Exclusive state. A non-threaded event.", + "PublicDescription": "Counts the number of lines that are silently dropped by L2 cache. These lines are typically in Shared or Exclusive state. A non-threaded event. Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0x1" }, @@ -105,7 +107,7 @@ "Counter": "0,1,2,3", "EventCode": "0x26", "EventName": "L2_LINES_OUT.USELESS_HWPF", - "PublicDescription": "Counts the number of cache lines that have been prefetched by the L2 hardware prefetcher but not used by demand access when evicted from the L2 cache", + "PublicDescription": "Counts the number of cache lines that have been prefetched by the L2 hardware prefetcher but not used by demand access when evicted from the L2 cache Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0x4" }, @@ -114,7 +116,7 @@ "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_REQUEST.ALL", - "PublicDescription": "Counts all requests that were hit or true misses in L2 cache. True-miss excludes misses that were merged with ongoing L2 misses. [This event is alias to L2_RQSTS.REFERENCES]", + "PublicDescription": "Counts all requests that were hit or true misses in L2 cache. True-miss excludes misses that were merged with ongoing L2 misses. [This event is alias to L2_RQSTS.REFERENCES] Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0xff" }, @@ -123,7 +125,7 @@ "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_REQUEST.MISS", - "PublicDescription": "Counts read requests of any type with true-miss in the L2 cache. True-miss excludes L2 misses that were merged with ongoing L2 misses. [This event is alias to L2_RQSTS.MISS]", + "PublicDescription": "Counts read requests of any type with true-miss in the L2 cache. True-miss excludes L2 misses that were merged with ongoing L2 misses. [This event is alias to L2_RQSTS.MISS] Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0x3f" }, @@ -132,7 +134,7 @@ "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_RQSTS.ALL_CODE_RD", - "PublicDescription": "Counts the total number of L2 code requests.", + "PublicDescription": "Counts the total number of L2 code requests. Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0xe4" }, @@ -141,7 +143,7 @@ "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_RQSTS.ALL_DEMAND_DATA_RD", - "PublicDescription": "Counts Demand Data Read requests accessing the L2 cache. These requests may hit or miss L2 cache. True-miss exclude misses that were merged with ongoing L2 misses. An access is counted once.", + "PublicDescription": "Counts Demand Data Read requests accessing the L2 cache. These requests may hit or miss L2 cache. True-miss exclude misses that were merged with ongoing L2 misses. An access is counted once. Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0xe1" }, @@ -150,7 +152,7 @@ "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_RQSTS.ALL_DEMAND_MISS", - "PublicDescription": "Counts demand requests that miss L2 cache.", + "PublicDescription": "Counts demand requests that miss L2 cache. Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0x27" }, @@ -159,7 +161,7 @@ "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_RQSTS.ALL_DEMAND_REFERENCES", - "PublicDescription": "Counts demand requests to L2 cache.", + "PublicDescription": "Counts demand requests to L2 cache. Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0xe7" }, @@ -168,6 +170,7 @@ "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_RQSTS.ALL_HWPF", + "PublicDescription": "L2_RQSTS.ALL_HWPF Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0xf0" }, @@ -176,7 +179,7 @@ "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_RQSTS.ALL_RFO", - "PublicDescription": "Counts the total number of RFO (read for ownership) requests to L2 cache. L2 RFO requests include both L1D demand RFO misses as well as L1D RFO prefetches.", + "PublicDescription": "Counts the total number of RFO (read for ownership) requests to L2 cache. L2 RFO requests include both L1D demand RFO misses as well as L1D RFO prefetches. Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0xe2" }, @@ -185,7 +188,7 @@ "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_RQSTS.CODE_RD_HIT", - "PublicDescription": "Counts L2 cache hits when fetching instructions, code reads.", + "PublicDescription": "Counts L2 cache hits when fetching instructions, code reads. Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0xc4" }, @@ -194,7 +197,7 @@ "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_RQSTS.CODE_RD_MISS", - "PublicDescription": "Counts L2 cache misses when fetching instructions.", + "PublicDescription": "Counts L2 cache misses when fetching instructions. Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0x24" }, @@ -203,7 +206,7 @@ "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_RQSTS.DEMAND_DATA_RD_HIT", - "PublicDescription": "Counts the number of demand Data Read requests initiated by load instructions that hit L2 cache.", + "PublicDescription": "Counts the number of demand Data Read requests initiated by load instructions that hit L2 cache. Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0xc1" }, @@ -212,7 +215,7 @@ "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_RQSTS.DEMAND_DATA_RD_MISS", - "PublicDescription": "Counts demand Data Read requests with true-miss in the L2 cache. True-miss excludes misses that were merged with ongoing L2 misses. An access is counted once.", + "PublicDescription": "Counts demand Data Read requests with true-miss in the L2 cache. True-miss excludes misses that were merged with ongoing L2 misses. An access is counted once. Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0x21" }, @@ -221,6 +224,7 @@ "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_RQSTS.HWPF_MISS", + "PublicDescription": "L2_RQSTS.HWPF_MISS Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0x30" }, @@ -229,7 +233,7 @@ "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_RQSTS.MISS", - "PublicDescription": "Counts read requests of any type with true-miss in the L2 cache. True-miss excludes L2 misses that were merged with ongoing L2 misses. [This event is alias to L2_REQUEST.MISS]", + "PublicDescription": "Counts read requests of any type with true-miss in the L2 cache. True-miss excludes L2 misses that were merged with ongoing L2 misses. [This event is alias to L2_REQUEST.MISS] Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0x3f" }, @@ -238,7 +242,7 @@ "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_RQSTS.REFERENCES", - "PublicDescription": "Counts all requests that were hit or true misses in L2 cache. True-miss excludes misses that were merged with ongoing L2 misses. [This event is alias to L2_REQUEST.ALL]", + "PublicDescription": "Counts all requests that were hit or true misses in L2 cache. True-miss excludes misses that were merged with ongoing L2 misses. [This event is alias to L2_REQUEST.ALL] Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0xff" }, @@ -247,7 +251,7 @@ "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_RQSTS.RFO_HIT", - "PublicDescription": "Counts the RFO (Read-for-Ownership) requests that hit L2 cache.", + "PublicDescription": "Counts the RFO (Read-for-Ownership) requests that hit L2 cache. Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0xc2" }, @@ -256,7 +260,7 @@ "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_RQSTS.RFO_MISS", - "PublicDescription": "Counts the RFO (Read-for-Ownership) requests that miss L2 cache.", + "PublicDescription": "Counts the RFO (Read-for-Ownership) requests that miss L2 cache. Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0x22" }, @@ -265,7 +269,7 @@ "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_RQSTS.SWPF_HIT", - "PublicDescription": "Counts Software prefetch requests that hit the L2 cache. Accounts for PREFETCHNTA and PREFETCHT0/1/2 instructions when FB is not full.", + "PublicDescription": "Counts Software prefetch requests that hit the L2 cache. Accounts for PREFETCHNTA and PREFETCHT0/1/2 instructions when FB is not full. Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0xc8" }, @@ -274,7 +278,7 @@ "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_RQSTS.SWPF_MISS", - "PublicDescription": "Counts Software prefetch requests that miss the L2 cache. Accounts for PREFETCHNTA and PREFETCHT0/1/2 instructions when FB is not full.", + "PublicDescription": "Counts Software prefetch requests that miss the L2 cache. Accounts for PREFETCHNTA and PREFETCHT0/1/2 instructions when FB is not full. Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0x28" }, @@ -283,7 +287,7 @@ "Counter": "0,1,2,3", "EventCode": "0x23", "EventName": "L2_TRANS.L2_WB", - "PublicDescription": "Counts L2 writebacks that access L2 cache.", + "PublicDescription": "Counts L2 writebacks that access L2 cache. Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0x40" }, @@ -292,7 +296,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0x2e", "EventName": "LONGEST_LAT_CACHE.MISS", - "PublicDescription": "Counts core-originated cacheable requests that miss the L3 cache (Longest Latency cache). Requests include data and code reads, Reads-for-Ownership (RFOs), speculative accesses and hardware prefetches to the L1 and L2. It does not include hardware prefetches to the L3, and may not count other types of requests to the L3.", + "PublicDescription": "Counts core-originated cacheable requests that miss the L3 cache (Longest Latency cache). Requests include data and code reads, Reads-for-Ownership (RFOs), speculative accesses and hardware prefetches to the L1 and L2. It does not include hardware prefetches to the L3, and may not count other types of requests to the L3. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x41" }, @@ -301,7 +305,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0x2e", "EventName": "LONGEST_LAT_CACHE.REFERENCE", - "PublicDescription": "Counts core-originated cacheable requests to the L3 cache (Longest Latency cache). Requests include data and code reads, Reads-for-Ownership (RFOs), speculative accesses and hardware prefetches to the L1 and L2. It does not include hardware prefetches to the L3, and may not count other types of requests to the L3.", + "PublicDescription": "Counts core-originated cacheable requests to the L3 cache (Longest Latency cache). Requests include data and code reads, Reads-for-Ownership (RFOs), speculative accesses and hardware prefetches to the L1 and L2. It does not include hardware prefetches to the L3, and may not count other types of requests to the L3. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x4f" }, @@ -311,7 +315,7 @@ "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_INST_RETIRED.ALL_LOADS", - "PublicDescription": "Counts all retired load instructions. This event accounts for SW prefetch instructions of PREFETCHNTA or PREFETCHT0/1/2 or PREFETCHW.", + "PublicDescription": "Counts all retired load instructions. This event accounts for SW prefetch instructions of PREFETCHNTA or PREFETCHT0/1/2 or PREFETCHW. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x81" }, @@ -321,7 +325,7 @@ "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_INST_RETIRED.ALL_STORES", - "PublicDescription": "Counts all retired store instructions.", + "PublicDescription": "Counts all retired store instructions. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x82" }, @@ -331,7 +335,7 @@ "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_INST_RETIRED.ANY", - "PublicDescription": "Counts all retired memory instructions - loads and stores.", + "PublicDescription": "Counts all retired memory instructions - loads and stores. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x83" }, @@ -341,7 +345,7 @@ "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_INST_RETIRED.LOCK_LOADS", - "PublicDescription": "Counts retired load instructions with locked access.", + "PublicDescription": "Counts retired load instructions with locked access. Available PDIST counters: 0", "SampleAfterValue": "100007", "UMask": "0x21" }, @@ -351,7 +355,7 @@ "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_INST_RETIRED.SPLIT_LOADS", - "PublicDescription": "Counts retired load instructions that split across a cacheline boundary.", + "PublicDescription": "Counts retired load instructions that split across a cacheline boundary. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x41" }, @@ -361,7 +365,7 @@ "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_INST_RETIRED.SPLIT_STORES", - "PublicDescription": "Counts retired store instructions that split across a cacheline boundary.", + "PublicDescription": "Counts retired store instructions that split across a cacheline boundary. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x42" }, @@ -371,7 +375,7 @@ "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_INST_RETIRED.STLB_MISS_LOADS", - "PublicDescription": "Number of retired load instructions that (start a) miss in the 2nd-level TLB (STLB).", + "PublicDescription": "Number of retired load instructions that (start a) miss in the 2nd-level TLB (STLB). Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x11" }, @@ -381,7 +385,7 @@ "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_INST_RETIRED.STLB_MISS_STORES", - "PublicDescription": "Number of retired store instructions that (start a) miss in the 2nd-level TLB (STLB).", + "PublicDescription": "Number of retired store instructions that (start a) miss in the 2nd-level TLB (STLB). Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x12" }, @@ -390,7 +394,7 @@ "Counter": "0,1,2,3", "EventCode": "0x43", "EventName": "MEM_LOAD_COMPLETED.L1_MISS_ANY", - "PublicDescription": "Number of completed demand load requests that missed the L1 data cache including shadow misses (FB hits, merge to an ongoing L1D miss)", + "PublicDescription": "Number of completed demand load requests that missed the L1 data cache including shadow misses (FB hits, merge to an ongoing L1D miss) Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0xfd" }, @@ -400,7 +404,7 @@ "Data_LA": "1", "EventCode": "0xd2", "EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD", - "PublicDescription": "Counts retired load instructions whose data sources were HitM responses from shared L3.", + "PublicDescription": "Counts retired load instructions whose data sources were HitM responses from shared L3. Available PDIST counters: 0", "SampleAfterValue": "20011", "UMask": "0x4" }, @@ -410,7 +414,7 @@ "Data_LA": "1", "EventCode": "0xd2", "EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS", - "PublicDescription": "Counts the retired load instructions whose data sources were L3 hit and cross-core snoop missed in on-pkg core cache.", + "PublicDescription": "Counts the retired load instructions whose data sources were L3 hit and cross-core snoop missed in on-pkg core cache. Available PDIST counters: 0", "SampleAfterValue": "20011", "UMask": "0x1" }, @@ -420,7 +424,7 @@ "Data_LA": "1", "EventCode": "0xd2", "EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_NONE", - "PublicDescription": "Counts retired load instructions whose data sources were hits in L3 without snoops required.", + "PublicDescription": "Counts retired load instructions whose data sources were hits in L3 without snoops required. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x8" }, @@ -430,7 +434,7 @@ "Data_LA": "1", "EventCode": "0xd2", "EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_NO_FWD", - "PublicDescription": "Counts retired load instructions whose data sources were L3 and cross-core snoop hits in on-pkg core cache.", + "PublicDescription": "Counts retired load instructions whose data sources were L3 and cross-core snoop hits in on-pkg core cache. Available PDIST counters: 0", "SampleAfterValue": "20011", "UMask": "0x2" }, @@ -440,7 +444,7 @@ "Data_LA": "1", "EventCode": "0xd3", "EventName": "MEM_LOAD_L3_MISS_RETIRED.LOCAL_DRAM", - "PublicDescription": "Retired load instructions which data sources missed L3 but serviced from local DRAM.", + "PublicDescription": "Retired load instructions which data sources missed L3 but serviced from local DRAM. Available PDIST counters: 0", "SampleAfterValue": "100007", "UMask": "0x1" }, @@ -450,6 +454,7 @@ "Data_LA": "1", "EventCode": "0xd3", "EventName": "MEM_LOAD_L3_MISS_RETIRED.REMOTE_DRAM", + "PublicDescription": "MEM_LOAD_L3_MISS_RETIRED.REMOTE_DRAM Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x2" }, @@ -459,7 +464,7 @@ "Data_LA": "1", "EventCode": "0xd3", "EventName": "MEM_LOAD_L3_MISS_RETIRED.REMOTE_FWD", - "PublicDescription": "Retired load instructions whose data sources was forwarded from a remote cache.", + "PublicDescription": "Retired load instructions whose data sources was forwarded from a remote cache. Available PDIST counters: 0", "SampleAfterValue": "100007", "UMask": "0x8" }, @@ -469,6 +474,7 @@ "Data_LA": "1", "EventCode": "0xd3", "EventName": "MEM_LOAD_L3_MISS_RETIRED.REMOTE_HITM", + "PublicDescription": "MEM_LOAD_L3_MISS_RETIRED.REMOTE_HITM Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x4" }, @@ -478,7 +484,7 @@ "Data_LA": "1", "EventCode": "0xd4", "EventName": "MEM_LOAD_MISC_RETIRED.UC", - "PublicDescription": "Retired instructions with at least one load to uncacheable memory-type, or at least one cache-line split locked access (Bus Lock).", + "PublicDescription": "Retired instructions with at least one load to uncacheable memory-type, or at least one cache-line split locked access (Bus Lock). Available PDIST counters: 0", "SampleAfterValue": "100007", "UMask": "0x4" }, @@ -488,7 +494,7 @@ "Data_LA": "1", "EventCode": "0xd1", "EventName": "MEM_LOAD_RETIRED.FB_HIT", - "PublicDescription": "Counts retired load instructions with at least one uop was load missed in L1 but hit FB (Fill Buffers) due to preceding miss to the same cache line with data not ready.", + "PublicDescription": "Counts retired load instructions with at least one uop was load missed in L1 but hit FB (Fill Buffers) due to preceding miss to the same cache line with data not ready. Available PDIST counters: 0", "SampleAfterValue": "100007", "UMask": "0x40" }, @@ -498,7 +504,7 @@ "Data_LA": "1", "EventCode": "0xd1", "EventName": "MEM_LOAD_RETIRED.L1_HIT", - "PublicDescription": "Counts retired load instructions with at least one uop that hit in the L1 data cache. This event includes all SW prefetches and lock instructions regardless of the data source.", + "PublicDescription": "Counts retired load instructions with at least one uop that hit in the L1 data cache. This event includes all SW prefetches and lock instructions regardless of the data source. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x1" }, @@ -508,7 +514,7 @@ "Data_LA": "1", "EventCode": "0xd1", "EventName": "MEM_LOAD_RETIRED.L1_MISS", - "PublicDescription": "Counts retired load instructions with at least one uop that missed in the L1 cache.", + "PublicDescription": "Counts retired load instructions with at least one uop that missed in the L1 cache. Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0x8" }, @@ -518,7 +524,7 @@ "Data_LA": "1", "EventCode": "0xd1", "EventName": "MEM_LOAD_RETIRED.L2_HIT", - "PublicDescription": "Counts retired load instructions with L2 cache hits as data sources.", + "PublicDescription": "Counts retired load instructions with L2 cache hits as data sources. Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0x2" }, @@ -528,7 +534,7 @@ "Data_LA": "1", "EventCode": "0xd1", "EventName": "MEM_LOAD_RETIRED.L2_MISS", - "PublicDescription": "Counts retired load instructions missed L2 cache as data sources.", + "PublicDescription": "Counts retired load instructions missed L2 cache as data sources. Available PDIST counters: 0", "SampleAfterValue": "100021", "UMask": "0x10" }, @@ -538,7 +544,7 @@ "Data_LA": "1", "EventCode": "0xd1", "EventName": "MEM_LOAD_RETIRED.L3_HIT", - "PublicDescription": "Counts retired load instructions with at least one uop that hit in the L3 cache.", + "PublicDescription": "Counts retired load instructions with at least one uop that hit in the L3 cache. Available PDIST counters: 0", "SampleAfterValue": "100021", "UMask": "0x4" }, @@ -548,7 +554,7 @@ "Data_LA": "1", "EventCode": "0xd1", "EventName": "MEM_LOAD_RETIRED.L3_MISS", - "PublicDescription": "Counts retired load instructions with at least one uop that missed in the L3 cache.", + "PublicDescription": "Counts retired load instructions with at least one uop that missed in the L3 cache. Available PDIST counters: 0", "SampleAfterValue": "50021", "UMask": "0x20" }, @@ -557,6 +563,7 @@ "Counter": "0,1,2,3", "EventCode": "0x44", "EventName": "MEM_STORE_RETIRED.L2_HIT", + "PublicDescription": "MEM_STORE_RETIRED.L2_HIT Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0x1" }, @@ -565,17 +572,29 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xe5", "EventName": "MEM_UOP_RETIRED.ANY", - "PublicDescription": "Number of retired micro-operations (uops) for load or store memory accesses", + "PublicDescription": "Number of retired micro-operations (uops) for load or store memory accesses Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x3" }, { + "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that have any type of response.", + "Counter": "0,1,2,3", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.DEMAND_CODE_RD.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x10004", + "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that have any type of response. Available PDIST counters: 0", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that hit in the L3 or were snooped from another core's caches on the same socket.", "Counter": "0,1,2,3", "EventCode": "0x2A,0x2B", "EventName": "OCR.DEMAND_CODE_RD.L3_HIT", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x3F803C0004", + "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that hit in the L3 or were snooped from another core's caches on the same socket. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -586,6 +605,7 @@ "EventName": "OCR.DEMAND_CODE_RD.L3_HIT.SNOOP_HITM", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x10003C0004", + "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that resulted in a snoop hit a modified line in another core's caches which forwarded the data. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -596,6 +616,7 @@ "EventName": "OCR.DEMAND_CODE_RD.SNC_CACHE.HITM", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x1008000004", + "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that hit a modified line in a distant L3 Cache or were snooped from a distant core's L1/L2 caches on this socket when the system is in SNC (sub-NUMA cluster) mode. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -606,6 +627,18 @@ "EventName": "OCR.DEMAND_CODE_RD.SNC_CACHE.HIT_WITH_FWD", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x808000004", + "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that either hit a non-modified line in a distant L3 Cache or were snooped from a distant core's L1/L2 caches on this socket when the system is in SNC (sub-NUMA cluster) mode. Available PDIST counters: 0", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts demand data reads that have any type of response.", + "Counter": "0,1,2,3", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.DEMAND_DATA_RD.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x10001", + "PublicDescription": "Counts demand data reads that have any type of response. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -616,6 +649,7 @@ "EventName": "OCR.DEMAND_DATA_RD.L3_HIT", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x3F803C0001", + "PublicDescription": "Counts demand data reads that hit in the L3 or were snooped from another core's caches on the same socket. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -626,6 +660,7 @@ "EventName": "OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x10003C0001", + "PublicDescription": "Counts demand data reads that resulted in a snoop hit a modified line in another core's caches which forwarded the data. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -636,6 +671,7 @@ "EventName": "OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_NO_FWD", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x4003C0001", + "PublicDescription": "Counts demand data reads that resulted in a snoop that hit in another core, which did not forward the data. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -646,6 +682,7 @@ "EventName": "OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x8003C0001", + "PublicDescription": "Counts demand data reads that resulted in a snoop hit in another core's caches which forwarded the unmodified data to the requesting core. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -656,6 +693,7 @@ "EventName": "OCR.DEMAND_DATA_RD.REMOTE_CACHE.SNOOP_HITM", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x1030000001", + "PublicDescription": "Counts demand data reads that were supplied by a cache on a remote socket where a snoop hit a modified line in another core's caches which forwarded the data. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -666,6 +704,7 @@ "EventName": "OCR.DEMAND_DATA_RD.REMOTE_CACHE.SNOOP_HIT_WITH_FWD", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x830000001", + "PublicDescription": "Counts demand data reads that were supplied by a cache on a remote socket where a snoop hit in another core's caches which forwarded the unmodified data to the requesting core. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -676,6 +715,7 @@ "EventName": "OCR.DEMAND_DATA_RD.SNC_CACHE.HITM", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x1008000001", + "PublicDescription": "Counts demand data reads that hit a modified line in a distant L3 Cache or were snooped from a distant core's L1/L2 caches on this socket when the system is in SNC (sub-NUMA cluster) mode. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -686,6 +726,18 @@ "EventName": "OCR.DEMAND_DATA_RD.SNC_CACHE.HIT_WITH_FWD", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x808000001", + "PublicDescription": "Counts demand data reads that either hit a non-modified line in a distant L3 Cache or were snooped from a distant core's L1/L2 caches on this socket when the system is in SNC (sub-NUMA cluster) mode. Available PDIST counters: 0", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts demand reads for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that have any type of response.", + "Counter": "0,1,2,3", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.DEMAND_RFO.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x3F3FFC0002", + "PublicDescription": "Counts demand reads for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that have any type of response. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -696,6 +748,7 @@ "EventName": "OCR.DEMAND_RFO.L3_HIT", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x3F803C0002", + "PublicDescription": "Counts demand reads for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that hit in the L3 or were snooped from another core's caches on the same socket. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -706,6 +759,7 @@ "EventName": "OCR.DEMAND_RFO.L3_HIT.SNOOP_HITM", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x10003C0002", + "PublicDescription": "Counts demand reads for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that resulted in a snoop hit a modified line in another core's caches which forwarded the data. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -716,6 +770,7 @@ "EventName": "OCR.DEMAND_RFO.SNC_CACHE.HITM", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x1008000002", + "PublicDescription": "Counts demand reads for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that hit a modified line in a distant L3 Cache or were snooped from a distant core's L1/L2 caches on this socket when the system is in SNC (sub-NUMA cluster) mode. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -726,6 +781,40 @@ "EventName": "OCR.DEMAND_RFO.SNC_CACHE.HIT_WITH_FWD", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x808000002", + "PublicDescription": "Counts demand reads for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that either hit a non-modified line in a distant L3 Cache or were snooped from a distant core's L1/L2 caches on this socket when the system is in SNC (sub-NUMA cluster) mode. Available PDIST counters: 0", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts data load hardware prefetch requests to the L1 data cache that have any type of response.", + "Counter": "0,1,2,3", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.HWPF_L1D.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x10400", + "PublicDescription": "Counts data load hardware prefetch requests to the L1 data cache that have any type of response. Available PDIST counters: 0", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts hardware prefetches (which bring data to L2) that have any type of response.", + "Counter": "0,1,2,3", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.HWPF_L2.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x10070", + "PublicDescription": "Counts hardware prefetches (which bring data to L2) that have any type of response. Available PDIST counters: 0", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts hardware prefetches to the L3 only that have any type of response.", + "Counter": "0,1,2,3", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.HWPF_L3.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x12380", + "PublicDescription": "Counts hardware prefetches to the L3 only that have any type of response. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -736,6 +825,40 @@ "EventName": "OCR.HWPF_L3.L3_HIT", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x80082380", + "PublicDescription": "Counts hardware prefetches to the L3 only that hit in the L3 or were snooped from another core's caches on the same socket. Available PDIST counters: 0", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts hardware prefetches to the L3 only that were not supplied by the local socket's L1, L2, or L3 caches and the cacheline was homed in a remote socket.", + "Counter": "0,1,2,3", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.HWPF_L3.REMOTE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x90002380", + "PublicDescription": "Counts hardware prefetches to the L3 only that were not supplied by the local socket's L1, L2, or L3 caches and the cacheline was homed in a remote socket. Available PDIST counters: 0", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts writebacks of modified cachelines and streaming stores that have any type of response.", + "Counter": "0,1,2,3", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.MODIFIED_WRITE.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x10808", + "PublicDescription": "Counts writebacks of modified cachelines and streaming stores that have any type of response. Available PDIST counters: 0", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that have any type of response.", + "Counter": "0,1,2,3", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.READS_TO_CORE.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x3F3FFC4477", + "PublicDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that have any type of response. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -746,6 +869,7 @@ "EventName": "OCR.READS_TO_CORE.L3_HIT", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x3F003C4477", + "PublicDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that hit in the L3 or were snooped from another core's caches on the same socket. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -756,6 +880,7 @@ "EventName": "OCR.READS_TO_CORE.L3_HIT.SNOOP_HITM", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x10003C4477", + "PublicDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that resulted in a snoop hit a modified line in another core's caches which forwarded the data. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -766,6 +891,7 @@ "EventName": "OCR.READS_TO_CORE.L3_HIT.SNOOP_HIT_NO_FWD", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x4003C4477", + "PublicDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that resulted in a snoop that hit in another core, which did not forward the data. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -776,6 +902,18 @@ "EventName": "OCR.READS_TO_CORE.L3_HIT.SNOOP_HIT_WITH_FWD", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x8003C4477", + "PublicDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that resulted in a snoop hit in another core's caches which forwarded the unmodified data to the requesting core. Available PDIST counters: 0", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were not supplied by the local socket's L1, L2, or L3 caches and were supplied by a remote socket.", + "Counter": "0,1,2,3", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.READS_TO_CORE.REMOTE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x3F33004477", + "PublicDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were not supplied by the local socket's L1, L2, or L3 caches and were supplied by a remote socket. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -786,6 +924,7 @@ "EventName": "OCR.READS_TO_CORE.REMOTE_CACHE.SNOOP_FWD", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x1830004477", + "PublicDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by a cache on a remote socket where a snoop was sent and data was returned (Modified or Not Modified). Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -796,6 +935,7 @@ "EventName": "OCR.READS_TO_CORE.REMOTE_CACHE.SNOOP_HITM", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x1030004477", + "PublicDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by a cache on a remote socket where a snoop hit a modified line in another core's caches which forwarded the data. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -806,6 +946,7 @@ "EventName": "OCR.READS_TO_CORE.REMOTE_CACHE.SNOOP_HIT_WITH_FWD", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x830004477", + "PublicDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by a cache on a remote socket where a snoop hit in another core's caches which forwarded the unmodified data to the requesting core. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -816,6 +957,7 @@ "EventName": "OCR.READS_TO_CORE.SNC_CACHE.HITM", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x1008004477", + "PublicDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that hit a modified line in a distant L3 Cache or were snooped from a distant core's L1/L2 caches on this socket when the system is in SNC (sub-NUMA cluster) mode. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -826,6 +968,7 @@ "EventName": "OCR.READS_TO_CORE.SNC_CACHE.HIT_WITH_FWD", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x808004477", + "PublicDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that either hit a non-modified line in a distant L3 Cache or were snooped from a distant core's L1/L2 caches on this socket when the system is in SNC (sub-NUMA cluster) mode. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -836,6 +979,7 @@ "EventName": "OCR.RFO_TO_CORE.L3_HIT_M", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x1F80040022", + "PublicDescription": "Counts demand reads for ownership (RFO), hardware prefetch RFOs (which bring data to L2), and software prefetches for exclusive ownership (PREFETCHW) that hit to a (M)odified cacheline in the L3 or snoop filter. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -846,6 +990,7 @@ "EventName": "OCR.STREAMING_WR.L3_HIT", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x80080800", + "PublicDescription": "Counts streaming stores that hit in the L3 or were snooped from another core's caches on the same socket. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -854,6 +999,7 @@ "Counter": "0,1,2,3", "EventCode": "0x21", "EventName": "OFFCORE_REQUESTS.ALL_REQUESTS", + "PublicDescription": "OFFCORE_REQUESTS.ALL_REQUESTS Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x80" }, @@ -862,7 +1008,7 @@ "Counter": "0,1,2,3", "EventCode": "0x21", "EventName": "OFFCORE_REQUESTS.DATA_RD", - "PublicDescription": "Counts the demand and prefetch data reads. All Core Data Reads include cacheable 'Demands' and L2 prefetchers (not L3 prefetchers). Counting also covers reads due to page walks resulted from any request type.", + "PublicDescription": "Counts the demand and prefetch data reads. All Core Data Reads include cacheable 'Demands' and L2 prefetchers (not L3 prefetchers). Counting also covers reads due to page walks resulted from any request type. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x8" }, @@ -871,7 +1017,7 @@ "Counter": "0,1,2,3", "EventCode": "0x21", "EventName": "OFFCORE_REQUESTS.DEMAND_CODE_RD", - "PublicDescription": "Counts both cacheable and non-cacheable code read requests.", + "PublicDescription": "Counts both cacheable and non-cacheable code read requests. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x2" }, @@ -880,7 +1026,7 @@ "Counter": "0,1,2,3", "EventCode": "0x21", "EventName": "OFFCORE_REQUESTS.DEMAND_DATA_RD", - "PublicDescription": "Counts the Demand Data Read requests sent to uncore. Use it in conjunction with OFFCORE_REQUESTS_OUTSTANDING to determine average latency in the uncore.", + "PublicDescription": "Counts the Demand Data Read requests sent to uncore. Use it in conjunction with OFFCORE_REQUESTS_OUTSTANDING to determine average latency in the uncore. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -889,7 +1035,7 @@ "Counter": "0,1,2,3", "EventCode": "0x21", "EventName": "OFFCORE_REQUESTS.DEMAND_RFO", - "PublicDescription": "Counts the demand RFO (read for ownership) requests including regular RFOs, locks, ItoM.", + "PublicDescription": "Counts the demand RFO (read for ownership) requests including regular RFOs, locks, ItoM. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x4" }, @@ -899,6 +1045,7 @@ "Deprecated": "1", "EventCode": "0x20", "EventName": "OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD", + "PublicDescription": "This event is deprecated. Refer to new event OFFCORE_REQUESTS_OUTSTANDING.DATA_RD Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x8" }, @@ -908,6 +1055,7 @@ "CounterMask": "1", "EventCode": "0x20", "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD", + "PublicDescription": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x8" }, @@ -917,7 +1065,7 @@ "CounterMask": "1", "EventCode": "0x20", "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_CODE_RD", - "PublicDescription": "Counts the number of offcore outstanding Code Reads transactions in the super queue every cycle. The 'Offcore outstanding' state of the transaction lasts from the L2 miss until the sending transaction completion to requestor (SQ deallocation). See the corresponding Umask under OFFCORE_REQUESTS.", + "PublicDescription": "Counts the number of offcore outstanding Code Reads transactions in the super queue every cycle. The 'Offcore outstanding' state of the transaction lasts from the L2 miss until the sending transaction completion to requestor (SQ deallocation). See the corresponding Umask under OFFCORE_REQUESTS. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x2" }, @@ -927,6 +1075,7 @@ "CounterMask": "1", "EventCode": "0x20", "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_DATA_RD", + "PublicDescription": "Cycles where at least 1 outstanding demand data read request is pending. Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x1" }, @@ -936,6 +1085,7 @@ "CounterMask": "1", "EventCode": "0x20", "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO", + "PublicDescription": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x4" }, @@ -944,6 +1094,7 @@ "Counter": "0,1,2,3", "EventCode": "0x20", "EventName": "OFFCORE_REQUESTS_OUTSTANDING.DATA_RD", + "PublicDescription": "OFFCORE_REQUESTS_OUTSTANDING.DATA_RD Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x8" }, @@ -952,7 +1103,7 @@ "Counter": "0,1,2,3", "EventCode": "0x20", "EventName": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_CODE_RD", - "PublicDescription": "Counts the number of offcore outstanding Code Reads transactions in the super queue every cycle. The 'Offcore outstanding' state of the transaction lasts from the L2 miss until the sending transaction completion to requestor (SQ deallocation). See the corresponding Umask under OFFCORE_REQUESTS.", + "PublicDescription": "Counts the number of offcore outstanding Code Reads transactions in the super queue every cycle. The 'Offcore outstanding' state of the transaction lasts from the L2 miss until the sending transaction completion to requestor (SQ deallocation). See the corresponding Umask under OFFCORE_REQUESTS. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x2" }, @@ -961,7 +1112,7 @@ "Counter": "0,1,2,3", "EventCode": "0x20", "EventName": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD", - "PublicDescription": "For every cycle, increments by the number of outstanding demand data read requests pending. Requests are considered outstanding from the time they miss the core's L2 cache until the transaction completion message is sent to the requestor.", + "PublicDescription": "For every cycle, increments by the number of outstanding demand data read requests pending. Requests are considered outstanding from the time they miss the core's L2 cache until the transaction completion message is sent to the requestor. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x1" }, @@ -970,7 +1121,7 @@ "Counter": "0,1,2,3", "EventCode": "0x2c", "EventName": "SQ_MISC.BUS_LOCK", - "PublicDescription": "Counts the more expensive bus lock needed to enforce cache coherency for certain memory accesses that need to be done atomically. Can be created by issuing an atomic instruction (via the LOCK prefix) which causes a cache line split or accesses uncacheable memory.", + "PublicDescription": "Counts the more expensive bus lock needed to enforce cache coherency for certain memory accesses that need to be done atomically. Can be created by issuing an atomic instruction (via the LOCK prefix) which causes a cache line split or accesses uncacheable memory. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x10" }, @@ -979,6 +1130,7 @@ "Counter": "0,1,2,3", "EventCode": "0x40", "EventName": "SW_PREFETCH_ACCESS.ANY", + "PublicDescription": "Counts the number of PREFETCHNTA, PREFETCHW, PREFETCHT0, PREFETCHT1 or PREFETCHT2 instructions executed. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0xf" }, @@ -987,7 +1139,7 @@ "Counter": "0,1,2,3", "EventCode": "0x40", "EventName": "SW_PREFETCH_ACCESS.NTA", - "PublicDescription": "Counts the number of PREFETCHNTA instructions executed.", + "PublicDescription": "Counts the number of PREFETCHNTA instructions executed. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -996,7 +1148,7 @@ "Counter": "0,1,2,3", "EventCode": "0x40", "EventName": "SW_PREFETCH_ACCESS.PREFETCHW", - "PublicDescription": "Counts the number of PREFETCHW instructions executed.", + "PublicDescription": "Counts the number of PREFETCHW instructions executed. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x8" }, @@ -1005,7 +1157,7 @@ "Counter": "0,1,2,3", "EventCode": "0x40", "EventName": "SW_PREFETCH_ACCESS.T0", - "PublicDescription": "Counts the number of PREFETCHT0 instructions executed.", + "PublicDescription": "Counts the number of PREFETCHT0 instructions executed. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x2" }, @@ -1014,7 +1166,7 @@ "Counter": "0,1,2,3", "EventCode": "0x40", "EventName": "SW_PREFETCH_ACCESS.T1_T2", - "PublicDescription": "Counts the number of PREFETCHT1 or PREFETCHT2 instructions executed.", + "PublicDescription": "Counts the number of PREFETCHT1 or PREFETCHT2 instructions executed. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x4" } diff --git a/tools/perf/pmu-events/arch/x86/emeraldrapids/emr-metrics.json b/tools/perf/pmu-events/arch/x86/emeraldrapids/emr-metrics.json index d3b51fa6ec1c..34e1cbcd722c 100644 --- a/tools/perf/pmu-events/arch/x86/emeraldrapids/emr-metrics.json +++ b/tools/perf/pmu-events/arch/x86/emeraldrapids/emr-metrics.json @@ -300,7 +300,7 @@ "ScaleUnit": "1per_instr" }, { - "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution ports for ALU operations", + "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution ports for ALU operations.", "MetricExpr": "(UOPS_DISPATCHED.PORT_0 + UOPS_DISPATCHED.PORT_1 + UOPS_DISPATCHED.PORT_5_11 + UOPS_DISPATCHED.PORT_6) / (5 * tma_info_core_core_clks)", "MetricGroup": "TopdownL5;tma_L5_group;tma_ports_utilized_3m_group", "MetricName": "tma_alu_op_utilization", @@ -312,7 +312,7 @@ "MetricExpr": "EXE.AMX_BUSY / tma_info_core_core_clks", "MetricGroup": "BvCB;Compute;HPC;Server;TopdownL3;tma_L3_group;tma_core_bound_group", "MetricName": "tma_amx_busy", - "MetricThreshold": "tma_amx_busy > 0.5 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_amx_busy > 0.5 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)", "ScaleUnit": "100%" }, { @@ -320,12 +320,12 @@ "MetricExpr": "78 * ASSISTS.ANY / tma_info_thread_slots", "MetricGroup": "BvIO;TopdownL4;tma_L4_group;tma_microcode_sequencer_group", "MetricName": "tma_assists", - "MetricThreshold": "tma_assists > 0.1 & tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1", + "MetricThreshold": "tma_assists > 0.1 & (tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1)", "PublicDescription": "This metric estimates fraction of slots the CPU retired uops delivered by the Microcode_Sequencer as a result of Assists. Assists are long sequences of uops that are required in certain corner-cases for operations that cannot be handled natively by the execution pipeline. For example; when working with very small floating point values (so-called Denormals); the FP units are not set up to perform these operations natively. Instead; a sequence of instructions to perform the computation on the Denormals is injected into the pipeline. Since these microcode sequences might be dozens of uops long; Assists can be extremely deleterious to performance and they can be avoided in many cases. Sample with: ASSISTS.ANY", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates fraction of slots the CPU retired uops as a result of handing SSE to AVX* or AVX* to SSE transition Assists", + "BriefDescription": "This metric estimates fraction of slots the CPU retired uops as a result of handing SSE to AVX* or AVX* to SSE transition Assists.", "MetricExpr": "63 * ASSISTS.SSE_AVX_MIX / tma_info_thread_slots", "MetricGroup": "HPC;TopdownL5;tma_L5_group;tma_assists_group", "MetricName": "tma_avx_assists", @@ -335,7 +335,7 @@ { "BriefDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend", "DefaultMetricgroupName": "TopdownL1", - "MetricExpr": "topdown\\-be\\-bound / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * slots", + "MetricExpr": "topdown\\-be\\-bound / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * tma_info_thread_slots", "MetricGroup": "BvOB;Default;TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_backend_bound", "MetricThreshold": "tma_backend_bound > 0.2", @@ -351,12 +351,12 @@ "MetricName": "tma_bad_speculation", "MetricThreshold": "tma_bad_speculation > 0.15", "MetricgroupNoGroup": "TopdownL1;Default", - "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example", + "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.", "ScaleUnit": "100%" }, { "BriefDescription": "Total pipeline cost of instruction fetch related bottlenecks by large code footprint programs (i-side cache; TLB and BTB misses)", - "MetricExpr": "100 * tma_fetch_latency * (tma_itlb_misses + tma_icache_misses + tma_unknown_branches) / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches)", + "MetricExpr": "100 * tma_fetch_latency * (tma_itlb_misses + tma_icache_misses + tma_unknown_branches) / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches)", "MetricGroup": "BigFootprint;BvBC;Fed;Frontend;IcMiss;MemoryTLB", "MetricName": "tma_bottleneck_big_code", "MetricThreshold": "tma_bottleneck_big_code > 20" @@ -371,7 +371,7 @@ }, { "BriefDescription": "Total pipeline cost of external Memory- or Cache-Bandwidth related bottlenecks", - "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_mem_bandwidth / (tma_mem_bandwidth + tma_mem_latency)) + tma_memory_bound * (tma_l3_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_sq_full / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_memory_bound * (tma_l1_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_fb_full / (tma_dtlb_load + tma_store_fwd_blk + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_fb_full)))", + "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_mem_bandwidth / (tma_mem_bandwidth + tma_mem_latency)) + tma_memory_bound * (tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_sq_full / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_fb_full / (tma_dtlb_load + tma_fb_full + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)))", "MetricGroup": "BvMB;Mem;MemoryBW;Offcore;tma_issueBW", "MetricName": "tma_bottleneck_cache_memory_bandwidth", "MetricThreshold": "tma_bottleneck_cache_memory_bandwidth > 20", @@ -379,7 +379,7 @@ }, { "BriefDescription": "Total pipeline cost of external Memory- or Cache-Latency related bottlenecks", - "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_mem_latency / (tma_mem_bandwidth + tma_mem_latency)) + tma_memory_bound * (tma_l3_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_l3_hit_latency / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_memory_bound * tma_l2_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound) + tma_memory_bound * (tma_l1_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_l1_latency_dependency / (tma_dtlb_load + tma_store_fwd_blk + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_fb_full)) + tma_memory_bound * (tma_l1_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_lock_latency / (tma_dtlb_load + tma_store_fwd_blk + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_fb_full)) + tma_memory_bound * (tma_l1_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_split_loads / (tma_dtlb_load + tma_store_fwd_blk + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_fb_full)) + tma_memory_bound * (tma_store_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_split_stores / (tma_store_latency + tma_false_sharing + tma_split_stores + tma_streaming_stores + tma_dtlb_store)) + tma_memory_bound * (tma_store_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_store_latency / (tma_store_latency + tma_false_sharing + tma_split_stores + tma_streaming_stores + tma_dtlb_store)))", + "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_mem_latency / (tma_mem_bandwidth + tma_mem_latency)) + tma_memory_bound * (tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_l3_hit_latency / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_memory_bound * tma_l2_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) + tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_l1_latency_dependency / (tma_dtlb_load + tma_fb_full + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_lock_latency / (tma_dtlb_load + tma_fb_full + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_split_loads / (tma_dtlb_load + tma_fb_full + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_memory_bound * (tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_split_stores / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency + tma_streaming_stores)) + tma_memory_bound * (tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_store_latency / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency + tma_streaming_stores)))", "MetricGroup": "BvML;Mem;MemoryLat;Offcore;tma_issueLat", "MetricName": "tma_bottleneck_cache_memory_latency", "MetricThreshold": "tma_bottleneck_cache_memory_latency > 20", @@ -387,22 +387,22 @@ }, { "BriefDescription": "Total pipeline cost when the execution is compute-bound - an estimation", - "MetricExpr": "100 * (tma_core_bound * tma_divider / (tma_divider + tma_serializing_operation + tma_amx_busy + tma_ports_utilization) + tma_core_bound * tma_amx_busy / (tma_divider + tma_serializing_operation + tma_amx_busy + tma_ports_utilization) + tma_core_bound * (tma_ports_utilization / (tma_divider + tma_serializing_operation + tma_amx_busy + tma_ports_utilization)) * (tma_ports_utilized_3m / (tma_ports_utilized_0 + tma_ports_utilized_1 + tma_ports_utilized_2 + tma_ports_utilized_3m)))", + "MetricExpr": "100 * (tma_core_bound * tma_divider / (tma_amx_busy + tma_divider + tma_ports_utilization + tma_serializing_operation) + tma_core_bound * tma_amx_busy / (tma_amx_busy + tma_divider + tma_ports_utilization + tma_serializing_operation) + tma_core_bound * (tma_ports_utilization / (tma_amx_busy + tma_divider + tma_ports_utilization + tma_serializing_operation)) * (tma_ports_utilized_3m / (tma_ports_utilized_0 + tma_ports_utilized_1 + tma_ports_utilized_2 + tma_ports_utilized_3m)))", "MetricGroup": "BvCB;Cor;tma_issueComp", "MetricName": "tma_bottleneck_compute_bound_est", "MetricThreshold": "tma_bottleneck_compute_bound_est > 20", - "PublicDescription": "Total pipeline cost when the execution is compute-bound - an estimation. Covers Core Bound when High ILP as well as when long-latency execution units are busy" + "PublicDescription": "Total pipeline cost when the execution is compute-bound - an estimation. Covers Core Bound when High ILP as well as when long-latency execution units are busy. Related metrics: " }, { "BriefDescription": "Total pipeline cost of instruction fetch bandwidth related bottlenecks (when the front-end could not sustain operations delivery to the back-end)", - "MetricExpr": "100 * (tma_frontend_bound - (1 - 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts) * tma_fetch_latency * tma_mispredicts_resteers / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches) - (1 - INST_RETIRED.REP_ITERATION / cpu@UOPS_RETIRED.MS\\,cmask\\=0x1@) * (tma_fetch_latency * (tma_ms_switches + tma_branch_resteers * (tma_clears_resteers + tma_mispredicts_resteers * tma_other_mispredicts / tma_branch_mispredicts) / (tma_mispredicts_resteers + tma_clears_resteers + tma_unknown_branches)) / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches) + tma_fetch_bandwidth * tma_ms / (tma_mite + tma_dsb + tma_ms))) - tma_bottleneck_big_code", + "MetricExpr": "100 * (tma_frontend_bound - (1 - 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts) * tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) - (1 - INST_RETIRED.REP_ITERATION / cpu@UOPS_RETIRED.MS\\,cmask\\=1@) * (tma_fetch_latency * (tma_ms_switches + tma_branch_resteers * (tma_clears_resteers + tma_mispredicts_resteers * tma_other_mispredicts / tma_branch_mispredicts) / (tma_clears_resteers + tma_mispredicts_resteers + tma_unknown_branches)) / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) + tma_fetch_bandwidth * tma_ms / (tma_dsb + tma_mite + tma_ms))) - tma_bottleneck_big_code", "MetricGroup": "BvFB;Fed;FetchBW;Frontend", "MetricName": "tma_bottleneck_instruction_fetch_bw", "MetricThreshold": "tma_bottleneck_instruction_fetch_bw > 20" }, { "BriefDescription": "Total pipeline cost of irregular execution (e.g", - "MetricExpr": "100 * ((1 - INST_RETIRED.REP_ITERATION / cpu@UOPS_RETIRED.MS\\,cmask\\=0x1@) * (tma_fetch_latency * (tma_ms_switches + tma_branch_resteers * (tma_clears_resteers + tma_mispredicts_resteers * tma_other_mispredicts / tma_branch_mispredicts) / (tma_mispredicts_resteers + tma_clears_resteers + tma_unknown_branches)) / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches) + tma_fetch_bandwidth * tma_ms / (tma_mite + tma_dsb + tma_ms)) + 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts * tma_branch_mispredicts + tma_machine_clears * tma_other_nukes / tma_other_nukes + tma_core_bound * (tma_serializing_operation + RS.EMPTY_RESOURCE / tma_info_thread_clks * tma_ports_utilized_0) / (tma_divider + tma_serializing_operation + tma_amx_busy + tma_ports_utilization) + tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * tma_heavy_operations)", + "MetricExpr": "100 * ((1 - INST_RETIRED.REP_ITERATION / cpu@UOPS_RETIRED.MS\\,cmask\\=1@) * (tma_fetch_latency * (tma_ms_switches + tma_branch_resteers * (tma_clears_resteers + tma_mispredicts_resteers * tma_other_mispredicts / tma_branch_mispredicts) / (tma_clears_resteers + tma_mispredicts_resteers + tma_unknown_branches)) / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) + tma_fetch_bandwidth * tma_ms / (tma_dsb + tma_mite + tma_ms)) + 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts * tma_branch_mispredicts + tma_machine_clears * tma_other_nukes / tma_other_nukes + tma_core_bound * (tma_serializing_operation + RS.EMPTY_RESOURCE / tma_info_thread_clks * tma_ports_utilized_0) / (tma_amx_busy + tma_divider + tma_ports_utilization + tma_serializing_operation) + tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * tma_heavy_operations)", "MetricGroup": "Bad;BvIO;Cor;Ret;tma_issueMS", "MetricName": "tma_bottleneck_irregular_overhead", "MetricThreshold": "tma_bottleneck_irregular_overhead > 10", @@ -410,7 +410,7 @@ }, { "BriefDescription": "Total pipeline cost of Memory Address Translation related bottlenecks (data-side TLBs)", - "MetricExpr": "100 * (tma_memory_bound * (tma_l1_bound / max(tma_memory_bound, tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_dtlb_load / max(tma_l1_bound, tma_dtlb_load + tma_store_fwd_blk + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_fb_full)) + tma_memory_bound * (tma_store_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_dtlb_store / (tma_store_latency + tma_false_sharing + tma_split_stores + tma_streaming_stores + tma_dtlb_store)))", + "MetricExpr": "100 * (tma_memory_bound * (tma_l1_bound / max(tma_memory_bound, tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_dtlb_load / max(tma_l1_bound, tma_dtlb_load + tma_fb_full + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_memory_bound * (tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_dtlb_store / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency + tma_streaming_stores)))", "MetricGroup": "BvMT;Mem;MemoryTLB;Offcore;tma_issueTLB", "MetricName": "tma_bottleneck_memory_data_tlbs", "MetricThreshold": "tma_bottleneck_memory_data_tlbs > 20", @@ -418,7 +418,7 @@ }, { "BriefDescription": "Total pipeline cost of Memory Synchronization related bottlenecks (data transfers and coherency updates across processors)", - "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound) * (tma_mem_latency / (tma_mem_bandwidth + tma_mem_latency)) * tma_remote_cache / (tma_local_mem + tma_remote_mem + tma_remote_cache) + tma_l3_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound) * (tma_contested_accesses + tma_data_sharing) / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full) + tma_store_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound) * tma_false_sharing / (tma_store_latency + tma_false_sharing + tma_split_stores + tma_streaming_stores + tma_dtlb_store - tma_store_latency)) + tma_machine_clears * (1 - tma_other_nukes / tma_other_nukes))", + "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_mem_latency / (tma_mem_bandwidth + tma_mem_latency)) * tma_remote_cache / (tma_local_mem + tma_remote_cache + tma_remote_mem) + tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_contested_accesses + tma_data_sharing) / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full) + tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * tma_false_sharing / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency + tma_streaming_stores - tma_store_latency)) + tma_machine_clears * (1 - tma_other_nukes / tma_other_nukes))", "MetricGroup": "BvMS;LockCont;Mem;Offcore;tma_issueSyncxn", "MetricName": "tma_bottleneck_memory_synchronization", "MetricThreshold": "tma_bottleneck_memory_synchronization > 10", @@ -426,7 +426,7 @@ }, { "BriefDescription": "Total pipeline cost of Branch Misprediction related bottlenecks", - "MetricExpr": "100 * (1 - 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts) * (tma_branch_mispredicts + tma_fetch_latency * tma_mispredicts_resteers / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches))", + "MetricExpr": "100 * (1 - 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts) * (tma_branch_mispredicts + tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches))", "MetricGroup": "Bad;BadSpec;BrMispredicts;BvMP;tma_issueBM", "MetricName": "tma_bottleneck_mispredictions", "MetricThreshold": "tma_bottleneck_mispredictions > 20", @@ -438,10 +438,10 @@ "MetricGroup": "BvOB;Cor;Offcore", "MetricName": "tma_bottleneck_other_bottlenecks", "MetricThreshold": "tma_bottleneck_other_bottlenecks > 20", - "PublicDescription": "Total pipeline cost of remaining bottlenecks in the back-end. Examples include data-dependencies (Core Bound when Low ILP) and other unlisted memory-related stalls" + "PublicDescription": "Total pipeline cost of remaining bottlenecks in the back-end. Examples include data-dependencies (Core Bound when Low ILP) and other unlisted memory-related stalls." }, { - "BriefDescription": "Total pipeline cost of \"useful operations\" - the portion of Retiring category not covered by Branching_Overhead nor Irregular_Overhead", + "BriefDescription": "Total pipeline cost of \"useful operations\" - the portion of Retiring category not covered by Branching_Overhead nor Irregular_Overhead.", "MetricExpr": "100 * (tma_retiring - (BR_INST_RETIRED.ALL_BRANCHES + 2 * BR_INST_RETIRED.NEAR_CALL + INST_RETIRED.NOP) / tma_info_thread_slots - tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * tma_heavy_operations)", "MetricGroup": "BvUW;Ret", "MetricName": "tma_bottleneck_useful_work", @@ -450,7 +450,7 @@ { "BriefDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction", "DefaultMetricgroupName": "TopdownL2", - "MetricExpr": "topdown\\-br\\-mispredict / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * slots", + "MetricExpr": "topdown\\-br\\-mispredict / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * tma_info_thread_slots", "MetricGroup": "BadSpec;BrMispredicts;BvMP;Default;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueBM", "MetricName": "tma_branch_mispredicts", "MetricThreshold": "tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", @@ -463,24 +463,24 @@ "MetricExpr": "INT_MISC.CLEAR_RESTEER_CYCLES / tma_info_thread_clks + tma_unknown_branches", "MetricGroup": "FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group", "MetricName": "tma_branch_resteers", - "MetricThreshold": "tma_branch_resteers > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", - "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers. Branch Resteers estimates the Frontend delay in fetching operations from corrected path; following all sorts of miss-predicted branches. For example; branchy code with lots of miss-predictions might get categorized under Branch Resteers. Note the value of this node may overlap with its siblings. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_l3_hit_latency, tma_store_latency", + "MetricThreshold": "tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers. Branch Resteers estimates the Frontend delay in fetching operations from corrected path; following all sorts of miss-predicted branches. For example; branchy code with lots of miss-predictions might get categorized under Branch Resteers. Note the value of this node may overlap with its siblings. Sample with: BR_MISP_RETIRED.ALL_BRANCHES", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due staying in C0.1 power-performance optimized state (Faster wakeup time; Smaller power savings)", + "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due staying in C0.1 power-performance optimized state (Faster wakeup time; Smaller power savings).", "MetricExpr": "CPU_CLK_UNHALTED.C01 / tma_info_thread_clks", "MetricGroup": "C0Wait;TopdownL4;tma_L4_group;tma_serializing_operation_group", "MetricName": "tma_c01_wait", - "MetricThreshold": "tma_c01_wait > 0.05 & tma_serializing_operation > 0.1 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_c01_wait > 0.05 & (tma_serializing_operation > 0.1 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due staying in C0.2 power-performance optimized state (Slower wakeup time; Larger power savings)", + "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due staying in C0.2 power-performance optimized state (Slower wakeup time; Larger power savings).", "MetricExpr": "CPU_CLK_UNHALTED.C02 / tma_info_thread_clks", "MetricGroup": "C0Wait;TopdownL4;tma_L4_group;tma_serializing_operation_group", "MetricName": "tma_c02_wait", - "MetricThreshold": "tma_c02_wait > 0.05 & tma_serializing_operation > 0.1 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_c02_wait > 0.05 & (tma_serializing_operation > 0.1 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", "ScaleUnit": "100%" }, { @@ -488,8 +488,8 @@ "MetricExpr": "max(0, tma_microcode_sequencer - tma_assists)", "MetricGroup": "TopdownL4;tma_L4_group;tma_microcode_sequencer_group", "MetricName": "tma_cisc", - "MetricThreshold": "tma_cisc > 0.1 & tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1", - "PublicDescription": "This metric estimates fraction of cycles the CPU retired uops originated from CISC (complex instruction set computer) instruction. A CISC instruction has multiple uops that are required to perform the instruction's functionality as in the case of read-modify-write as an example. Since these instructions require multiple uops they may or may not imply sub-optimal use of machine resources. Sample with: FRONTEND_RETIRED.MS_FLOWS", + "MetricThreshold": "tma_cisc > 0.1 & (tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1)", + "PublicDescription": "This metric estimates fraction of cycles the CPU retired uops originated from CISC (complex instruction set computer) instruction. A CISC instruction has multiple uops that are required to perform the instruction's functionality as in the case of read-modify-write as an example. Since these instructions require multiple uops they may or may not imply sub-optimal use of machine resources.", "ScaleUnit": "100%" }, { @@ -497,24 +497,24 @@ "MetricExpr": "(1 - tma_branch_mispredicts / tma_bad_speculation) * INT_MISC.CLEAR_RESTEER_CYCLES / tma_info_thread_clks", "MetricGroup": "BadSpec;MachineClears;TopdownL4;tma_L4_group;tma_branch_resteers_group;tma_issueMC", "MetricName": "tma_clears_resteers", - "MetricThreshold": "tma_clears_resteers > 0.05 & tma_branch_resteers > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricThreshold": "tma_clears_resteers > 0.05 & (tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))", "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Machine Clears. Sample with: INT_MISC.CLEAR_RESTEER_CYCLES. Related metrics: tma_l1_bound, tma_machine_clears, tma_microcode_sequencer, tma_ms_switches", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates fraction of cycles the CPU was stalled due to instruction cache misses that hit in the L2 cache", + "BriefDescription": "This metric estimates fraction of cycles the CPU was stalled due to instruction cache misses that hit in the L2 cache.", "MetricExpr": "max(0, tma_icache_misses - tma_code_l2_miss)", "MetricGroup": "FetchLat;IcMiss;Offcore;TopdownL4;tma_L4_group;tma_icache_misses_group", "MetricName": "tma_code_l2_hit", - "MetricThreshold": "tma_code_l2_hit > 0.05 & tma_icache_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricThreshold": "tma_code_l2_hit > 0.05 & (tma_icache_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates fraction of cycles the CPU was stalled due to instruction cache misses that miss in the L2 cache", + "BriefDescription": "This metric estimates fraction of cycles the CPU was stalled due to instruction cache misses that miss in the L2 cache.", "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_CODE_RD / tma_info_thread_clks", "MetricGroup": "FetchLat;IcMiss;Offcore;TopdownL4;tma_L4_group;tma_icache_misses_group", "MetricName": "tma_code_l2_miss", - "MetricThreshold": "tma_code_l2_miss > 0.05 & tma_icache_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricThreshold": "tma_code_l2_miss > 0.05 & (tma_icache_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))", "ScaleUnit": "100%" }, { @@ -522,7 +522,7 @@ "MetricExpr": "max(0, tma_itlb_misses - tma_code_stlb_miss)", "MetricGroup": "FetchLat;MemoryTLB;TopdownL4;tma_L4_group;tma_itlb_misses_group", "MetricName": "tma_code_stlb_hit", - "MetricThreshold": "tma_code_stlb_hit > 0.05 & tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricThreshold": "tma_code_stlb_hit > 0.05 & (tma_itlb_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))", "ScaleUnit": "100%" }, { @@ -530,32 +530,33 @@ "MetricExpr": "ITLB_MISSES.WALK_ACTIVE / tma_info_thread_clks", "MetricGroup": "FetchLat;MemoryTLB;TopdownL4;tma_L4_group;tma_itlb_misses_group", "MetricName": "tma_code_stlb_miss", - "MetricThreshold": "tma_code_stlb_miss > 0.05 & tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricThreshold": "tma_code_stlb_miss > 0.05 & (tma_itlb_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 2 or 4 MB pages for (instruction) code accesses", + "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 2 or 4 MB pages for (instruction) code accesses.", "MetricExpr": "tma_code_stlb_miss * ITLB_MISSES.WALK_COMPLETED_2M_4M / (ITLB_MISSES.WALK_COMPLETED_4K + ITLB_MISSES.WALK_COMPLETED_2M_4M)", "MetricGroup": "FetchLat;MemoryTLB;TopdownL5;tma_L5_group;tma_code_stlb_miss_group", "MetricName": "tma_code_stlb_miss_2m", - "MetricThreshold": "tma_code_stlb_miss_2m > 0.05 & tma_code_stlb_miss > 0.05 & tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricThreshold": "tma_code_stlb_miss_2m > 0.05 & (tma_code_stlb_miss > 0.05 & (tma_itlb_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)))", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 4 KB pages for (instruction) code accesses", + "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 4 KB pages for (instruction) code accesses.", "MetricExpr": "tma_code_stlb_miss * ITLB_MISSES.WALK_COMPLETED_4K / (ITLB_MISSES.WALK_COMPLETED_4K + ITLB_MISSES.WALK_COMPLETED_2M_4M)", "MetricGroup": "FetchLat;MemoryTLB;TopdownL5;tma_L5_group;tma_code_stlb_miss_group", "MetricName": "tma_code_stlb_miss_4k", - "MetricThreshold": "tma_code_stlb_miss_4k > 0.05 & tma_code_stlb_miss > 0.05 & tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricThreshold": "tma_code_stlb_miss_4k > 0.05 & (tma_code_stlb_miss > 0.05 & (tma_itlb_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)))", "ScaleUnit": "100%" }, { "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses", - "MetricExpr": "((81 * tma_info_system_core_frequency - 4.4 * tma_info_system_core_frequency) * (MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD * (OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM / (OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM + OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD))) + (79 * tma_info_system_core_frequency - 4.4 * tma_info_system_core_frequency) * MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "(76.6 * tma_info_system_core_frequency * (MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD * (OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM / (OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM + OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD))) + 74.6 * tma_info_system_core_frequency * MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks", "MetricGroup": "BvMS;DataSharing;LockCont;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group", "MetricName": "tma_contested_accesses", - "MetricThreshold": "tma_contested_accesses > 0.05 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", - "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses. Contested accesses occur when data written by one Logical Processor are read by another Logical Processor on a different Physical Core. Examples of contested accesses include synchronizations such as locks; true data sharing such as modified locked variables; and false sharing. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD, MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS. Related metrics: tma_bottleneck_memory_synchronization, tma_data_sharing, tma_false_sharing, tma_machine_clears, tma_remote_cache", + "MetricThreshold": "tma_contested_accesses > 0.05 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses. Contested accesses occur when data written by one Logical Processor are read by another Logical Processor on a different Physical Core. Examples of contested accesses include synchronizations such as locks; true data sharing such as modified locked variables; and false sharing. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD;MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS. Related metrics: tma_bottleneck_memory_synchronization, tma_data_sharing, tma_false_sharing, tma_machine_clears, tma_remote_cache", "ScaleUnit": "100%" }, { @@ -566,24 +567,25 @@ "MetricName": "tma_core_bound", "MetricThreshold": "tma_core_bound > 0.1 & tma_backend_bound > 0.2", "MetricgroupNoGroup": "TopdownL2;Default", - "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck. Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations)", + "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck. Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations).", "ScaleUnit": "100%" }, { "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses", - "MetricExpr": "(79 * tma_info_system_core_frequency - 4.4 * tma_info_system_core_frequency) * (MEM_LOAD_L3_HIT_RETIRED.XSNP_NO_FWD + MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD * (1 - OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM / (OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM + OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD))) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "74.6 * tma_info_system_core_frequency * (MEM_LOAD_L3_HIT_RETIRED.XSNP_NO_FWD + MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD * (1 - OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM / (OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM + OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD))) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks", "MetricGroup": "BvMS;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group", "MetricName": "tma_data_sharing", - "MetricThreshold": "tma_data_sharing > 0.05 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_data_sharing > 0.05 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses. Data shared by multiple Logical Processors (even just read shared) may cause increased access latency due to cache coherency. Excessive data sharing can drastically harm multithreaded performance. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_NO_FWD. Related metrics: tma_bottleneck_memory_synchronization, tma_contested_accesses, tma_false_sharing, tma_machine_clears, tma_remote_cache", "ScaleUnit": "100%" }, { "BriefDescription": "This metric represents fraction of cycles where decoder-0 was the only active decoder", - "MetricExpr": "(cpu@INST_DECODED.DECODERS\\,cmask\\=0x1@ - cpu@INST_DECODED.DECODERS\\,cmask\\=0x2@) / tma_info_core_core_clks / 2", + "MetricExpr": "(cpu@INST_DECODED.DECODERS\\,cmask\\=1@ - cpu@INST_DECODED.DECODERS\\,cmask\\=2@) / tma_info_core_core_clks / 2", "MetricGroup": "DSBmiss;FetchBW;TopdownL4;tma_L4_group;tma_issueD0;tma_mite_group", "MetricName": "tma_decoder0_alone", - "MetricThreshold": "tma_decoder0_alone > 0.1 & tma_mite > 0.1 & tma_fetch_bandwidth > 0.2", + "MetricThreshold": "tma_decoder0_alone > 0.1 & (tma_mite > 0.1 & tma_fetch_bandwidth > 0.2)", "PublicDescription": "This metric represents fraction of cycles where decoder-0 was the only active decoder. Related metrics: tma_few_uops_instructions", "ScaleUnit": "100%" }, @@ -592,8 +594,8 @@ "MetricExpr": "ARITH.DIV_ACTIVE / tma_info_thread_clks", "MetricGroup": "BvCB;TopdownL3;tma_L3_group;tma_core_bound_group", "MetricName": "tma_divider", - "MetricThreshold": "tma_divider > 0.2 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", - "PublicDescription": "This metric represents fraction of cycles where the Divider unit was active. Divide and square root instructions are performed by the Divider unit and can take considerably longer latency than integer or Floating Point addition; subtraction; or multiplication. Sample with: ARITH.DIVIDER_ACTIVE", + "MetricThreshold": "tma_divider > 0.2 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)", + "PublicDescription": "This metric represents fraction of cycles where the Divider unit was active. Divide and square root instructions are performed by the Divider unit and can take considerably longer latency than integer or Floating Point addition; subtraction; or multiplication. Sample with: ARITH.DIV_ACTIVE", "ScaleUnit": "100%" }, { @@ -601,7 +603,7 @@ "MetricExpr": "MEMORY_ACTIVITY.STALLS_L3_MISS / tma_info_thread_clks", "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_dram_bound", - "MetricThreshold": "tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", "PublicDescription": "This metric estimates how often the CPU was stalled on accesses to external memory (DRAM) by loads. Better caching can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L3_MISS", "ScaleUnit": "100%" }, @@ -611,7 +613,7 @@ "MetricGroup": "DSB;FetchBW;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group", "MetricName": "tma_dsb", "MetricThreshold": "tma_dsb > 0.15 & tma_fetch_bandwidth > 0.2", - "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to DSB (decoded uop cache) fetch pipeline. For example; inefficient utilization of the DSB cache structure or bank conflict when reading from it; are categorized here", + "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to DSB (decoded uop cache) fetch pipeline. For example; inefficient utilization of the DSB cache structure or bank conflict when reading from it; are categorized here.", "ScaleUnit": "100%" }, { @@ -619,34 +621,34 @@ "MetricExpr": "DSB2MITE_SWITCHES.PENALTY_CYCLES / tma_info_thread_clks", "MetricGroup": "DSBmiss;FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueFB", "MetricName": "tma_dsb_switches", - "MetricThreshold": "tma_dsb_switches > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", - "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines. The DSB (decoded i-cache) is a Uop Cache where the front-end directly delivers Uops (micro operations) avoiding heavy x86 decoding. The DSB pipeline has shorter latency and delivered higher bandwidth than the MITE (legacy instruction decode pipeline). Switching between the two pipelines can cause penalties hence this metric measures the exposed penalty. Sample with: FRONTEND_RETIRED.DSB_MISS. Related metrics: tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp", + "MetricThreshold": "tma_dsb_switches > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines. The DSB (decoded i-cache) is a Uop Cache where the front-end directly delivers Uops (micro operations) avoiding heavy x86 decoding. The DSB pipeline has shorter latency and delivered higher bandwidth than the MITE (legacy instruction decode pipeline). Switching between the two pipelines can cause penalties hence this metric measures the exposed penalty. Sample with: FRONTEND_RETIRED.DSB_MISS_PS. Related metrics: tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp", "ScaleUnit": "100%" }, { "BriefDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses", - "MetricExpr": "min(7 * cpu@DTLB_LOAD_MISSES.STLB_HIT\\,cmask\\=0x1@ + DTLB_LOAD_MISSES.WALK_ACTIVE, max(CYCLE_ACTIVITY.CYCLES_MEM_ANY - MEMORY_ACTIVITY.CYCLES_L1D_MISS, 0)) / tma_info_thread_clks", + "MetricExpr": "min(7 * cpu@DTLB_LOAD_MISSES.STLB_HIT\\,cmask\\=1@ + DTLB_LOAD_MISSES.WALK_ACTIVE, max(CYCLE_ACTIVITY.CYCLES_MEM_ANY - MEMORY_ACTIVITY.CYCLES_L1D_MISS, 0)) / tma_info_thread_clks", "MetricGroup": "BvMT;MemoryTLB;TopdownL4;tma_L4_group;tma_issueTLB;tma_l1_bound_group", "MetricName": "tma_dtlb_load", - "MetricThreshold": "tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", - "PublicDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses. TLBs (Translation Look-aside Buffers) are processor caches for recently used entries out of the Page Tables that are used to map virtual- to physical-addresses by the operating system. This metric approximates the potential delay of demand loads missing the first-level data TLB (assuming worst case scenario with back to back misses to different pages). This includes hitting in the second-level TLB (STLB) as well as performing a hardware page walk on an STLB miss. Sample with: MEM_INST_RETIRED.STLB_MISS_LOADS. Related metrics: tma_bottleneck_memory_data_tlbs, tma_dtlb_store", + "MetricThreshold": "tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses. TLBs (Translation Look-aside Buffers) are processor caches for recently used entries out of the Page Tables that are used to map virtual- to physical-addresses by the operating system. This metric approximates the potential delay of demand loads missing the first-level data TLB (assuming worst case scenario with back to back misses to different pages). This includes hitting in the second-level TLB (STLB) as well as performing a hardware page walk on an STLB miss. Sample with: MEM_INST_RETIRED.STLB_MISS_LOADS_PS. Related metrics: tma_bottleneck_memory_data_tlbs, tma_dtlb_store", "ScaleUnit": "100%" }, { "BriefDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses", - "MetricExpr": "(7 * cpu@DTLB_STORE_MISSES.STLB_HIT\\,cmask\\=0x1@ + DTLB_STORE_MISSES.WALK_ACTIVE) / tma_info_core_core_clks", + "MetricExpr": "(7 * cpu@DTLB_STORE_MISSES.STLB_HIT\\,cmask\\=1@ + DTLB_STORE_MISSES.WALK_ACTIVE) / tma_info_core_core_clks", "MetricGroup": "BvMT;MemoryTLB;TopdownL4;tma_L4_group;tma_issueTLB;tma_store_bound_group", "MetricName": "tma_dtlb_store", - "MetricThreshold": "tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", - "PublicDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses. As with ordinary data caching; focus on improving data locality and reducing working-set size to reduce DTLB overhead. Additionally; consider using profile-guided optimization (PGO) to collocate frequently-used data on the same page. Try using larger page sizes for large amounts of frequently-used data. Sample with: MEM_INST_RETIRED.STLB_MISS_STORES. Related metrics: tma_bottleneck_memory_data_tlbs, tma_dtlb_load", + "MetricThreshold": "tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses. As with ordinary data caching; focus on improving data locality and reducing working-set size to reduce DTLB overhead. Additionally; consider using profile-guided optimization (PGO) to collocate frequently-used data on the same page. Try using larger page sizes for large amounts of frequently-used data. Sample with: MEM_INST_RETIRED.STLB_MISS_STORES_PS. Related metrics: tma_bottleneck_memory_data_tlbs, tma_dtlb_load", "ScaleUnit": "100%" }, { "BriefDescription": "This metric roughly estimates how often CPU was handling synchronizations due to False Sharing", - "MetricExpr": "(170 * tma_info_system_core_frequency * cpu@OCR.DEMAND_RFO.L3_MISS\\,offcore_rsp\\=0x103b800002@ + 81 * tma_info_system_core_frequency * OCR.DEMAND_RFO.L3_HIT.SNOOP_HITM) / tma_info_thread_clks", + "MetricExpr": "(170 * tma_info_system_core_frequency * OCR.DEMAND_RFO.L3_MISS@offcore_rsp\\=0x103b800002@ + 81 * tma_info_system_core_frequency * OCR.DEMAND_RFO.L3_HIT.SNOOP_HITM) / tma_info_thread_clks", "MetricGroup": "BvMS;DataSharing;LockCont;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_store_bound_group", "MetricName": "tma_false_sharing", - "MetricThreshold": "tma_false_sharing > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_false_sharing > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", "PublicDescription": "This metric roughly estimates how often CPU was handling synchronizations due to False Sharing. False Sharing is a multithreading hiccup; where multiple Logical Processors contend on different data-elements mapped into the same cache line. Sample with: OCR.DEMAND_RFO.L3_HIT.SNOOP_HITM. Related metrics: tma_bottleneck_memory_synchronization, tma_contested_accesses, tma_data_sharing, tma_machine_clears, tma_remote_cache", "ScaleUnit": "100%" }, @@ -667,7 +669,7 @@ "MetricName": "tma_fetch_bandwidth", "MetricThreshold": "tma_fetch_bandwidth > 0.2", "MetricgroupNoGroup": "TopdownL2;Default", - "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues. For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Sample with: FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1, FRONTEND_RETIRED.LATENCY_GE_1, FRONTEND_RETIRED.LATENCY_GE_2. Related metrics: tma_dsb_switches, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp", + "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues. For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Sample with: FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1;FRONTEND_RETIRED.LATENCY_GE_1;FRONTEND_RETIRED.LATENCY_GE_2. Related metrics: tma_dsb_switches, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp", "ScaleUnit": "100%" }, { @@ -678,7 +680,7 @@ "MetricName": "tma_fetch_latency", "MetricThreshold": "tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", "MetricgroupNoGroup": "TopdownL2;Default", - "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues. For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: FRONTEND_RETIRED.LATENCY_GE_16, FRONTEND_RETIRED.LATENCY_GE_8", + "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues. For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: FRONTEND_RETIRED.LATENCY_GE_16_PS;FRONTEND_RETIRED.LATENCY_GE_8_PS", "ScaleUnit": "100%" }, { @@ -696,7 +698,7 @@ "MetricGroup": "HPC;TopdownL3;tma_L3_group;tma_light_operations_group", "MetricName": "tma_fp_arith", "MetricThreshold": "tma_fp_arith > 0.2 & tma_light_operations > 0.6", - "PublicDescription": "This metric represents overall arithmetic floating-point (FP) operations fraction the CPU has executed (retired). Note this metric's value may exceed its parent due to use of \"Uops\" CountDomain and FMA double-counting", + "PublicDescription": "This metric represents overall arithmetic floating-point (FP) operations fraction the CPU has executed (retired). Note this metric's value may exceed its parent due to use of \"Uops\" CountDomain and FMA double-counting.", "ScaleUnit": "100%" }, { @@ -705,15 +707,15 @@ "MetricGroup": "HPC;TopdownL5;tma_L5_group;tma_assists_group", "MetricName": "tma_fp_assists", "MetricThreshold": "tma_fp_assists > 0.1", - "PublicDescription": "This metric roughly estimates fraction of slots the CPU retired uops as a result of handing Floating Point (FP) Assists. FP Assist may apply when working with very small floating point values (so-called Denormals)", + "PublicDescription": "This metric roughly estimates fraction of slots the CPU retired uops as a result of handing Floating Point (FP) Assists. FP Assist may apply when working with very small floating point values (so-called Denormals).", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of cycles where the Floating-Point Divider unit was active", + "BriefDescription": "This metric represents fraction of cycles where the Floating-Point Divider unit was active.", "MetricExpr": "ARITH.FPDIV_ACTIVE / tma_info_thread_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_divider_group", "MetricName": "tma_fp_divider", - "MetricThreshold": "tma_fp_divider > 0.2 & tma_divider > 0.2 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_fp_divider > 0.2 & (tma_divider > 0.2 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", "ScaleUnit": "100%" }, { @@ -721,8 +723,8 @@ "MetricExpr": "(FP_ARITH_INST_RETIRED.SCALAR + FP_ARITH_INST_RETIRED2.SCALAR) / (tma_retiring * tma_info_thread_slots)", "MetricGroup": "Compute;Flops;TopdownL4;tma_L4_group;tma_fp_arith_group;tma_issue2P", "MetricName": "tma_fp_scalar", - "MetricThreshold": "tma_fp_scalar > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6", - "PublicDescription": "This metric approximates arithmetic floating-point (FP) scalar uops fraction the CPU has retired. May overcount due to FMA double counting. Related metrics: tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_6, tma_ports_utilized_2", + "MetricThreshold": "tma_fp_scalar > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6)", + "PublicDescription": "This metric approximates arithmetic floating-point (FP) scalar uops fraction the CPU has retired. May overcount due to FMA double counting. Related metrics: tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%" }, { @@ -730,8 +732,8 @@ "MetricExpr": "(FP_ARITH_INST_RETIRED.VECTOR + FP_ARITH_INST_RETIRED2.VECTOR) / (tma_retiring * tma_info_thread_slots)", "MetricGroup": "Compute;Flops;TopdownL4;tma_L4_group;tma_fp_arith_group;tma_issue2P", "MetricName": "tma_fp_vector", - "MetricThreshold": "tma_fp_vector > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6", - "PublicDescription": "This metric approximates arithmetic floating-point (FP) vector uops fraction the CPU has retired aggregated across all vector widths. May overcount due to FMA double counting. Related metrics: tma_fp_scalar, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_6, tma_ports_utilized_2", + "MetricThreshold": "tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6)", + "PublicDescription": "This metric approximates arithmetic floating-point (FP) vector uops fraction the CPU has retired aggregated across all vector widths. May overcount due to FMA double counting. Related metrics: tma_fp_scalar, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%" }, { @@ -739,8 +741,8 @@ "MetricExpr": "(FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED2.128B_PACKED_HALF) / (tma_retiring * tma_info_thread_slots)", "MetricGroup": "Compute;Flops;TopdownL5;tma_L5_group;tma_fp_vector_group;tma_issue2P", "MetricName": "tma_fp_vector_128b", - "MetricThreshold": "tma_fp_vector_128b > 0.1 & tma_fp_vector > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6", - "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 128-bit wide vectors. May overcount due to FMA double counting prior to LNL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_6, tma_ports_utilized_2", + "MetricThreshold": "tma_fp_vector_128b > 0.1 & (tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6))", + "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 128-bit wide vectors. May overcount due to FMA double counting prior to LNL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%" }, { @@ -748,8 +750,8 @@ "MetricExpr": "(FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE + FP_ARITH_INST_RETIRED2.256B_PACKED_HALF) / (tma_retiring * tma_info_thread_slots)", "MetricGroup": "Compute;Flops;TopdownL5;tma_L5_group;tma_fp_vector_group;tma_issue2P", "MetricName": "tma_fp_vector_256b", - "MetricThreshold": "tma_fp_vector_256b > 0.1 & tma_fp_vector > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6", - "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 256-bit wide vectors. May overcount due to FMA double counting prior to LNL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_6, tma_ports_utilized_2", + "MetricThreshold": "tma_fp_vector_256b > 0.1 & (tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6))", + "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 256-bit wide vectors. May overcount due to FMA double counting prior to LNL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%" }, { @@ -757,8 +759,8 @@ "MetricExpr": "(FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE + FP_ARITH_INST_RETIRED2.512B_PACKED_HALF) / (tma_retiring * tma_info_thread_slots)", "MetricGroup": "Compute;Flops;TopdownL5;tma_L5_group;tma_fp_vector_group;tma_issue2P", "MetricName": "tma_fp_vector_512b", - "MetricThreshold": "tma_fp_vector_512b > 0.1 & tma_fp_vector > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6", - "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 512-bit wide vectors. May overcount due to FMA double counting. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_6, tma_ports_utilized_2", + "MetricThreshold": "tma_fp_vector_512b > 0.1 & (tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6))", + "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 512-bit wide vectors. May overcount due to FMA double counting. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%" }, { @@ -769,27 +771,27 @@ "MetricName": "tma_frontend_bound", "MetricThreshold": "tma_frontend_bound > 0.15", "MetricgroupNoGroup": "TopdownL1;Default", - "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound. Sample with: FRONTEND_RETIRED.LATENCY_GE_4", + "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound. Sample with: FRONTEND_RETIRED.LATENCY_GE_4_PS", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of slots where the CPU was retiring fused instructions , where one uop can represent multiple contiguous instructions", + "BriefDescription": "This metric represents fraction of slots where the CPU was retiring fused instructions -- where one uop can represent multiple contiguous instructions", "MetricExpr": "tma_light_operations * INST_RETIRED.MACRO_FUSED / (tma_retiring * tma_info_thread_slots)", "MetricGroup": "Branches;BvBO;Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group", "MetricName": "tma_fused_instructions", "MetricThreshold": "tma_fused_instructions > 0.1 & tma_light_operations > 0.6", - "PublicDescription": "This metric represents fraction of slots where the CPU was retiring fused instructions , where one uop can represent multiple contiguous instructions. CMP+JCC or DEC+JCC are common examples of legacy fusions. {([MTL] Note new MOV+OP and Load+OP fusions appear under Other_Light_Ops in MTL!)}", + "PublicDescription": "This metric represents fraction of slots where the CPU was retiring fused instructions -- where one uop can represent multiple contiguous instructions. CMP+JCC or DEC+JCC are common examples of legacy fusions. {([MTL] Note new MOV+OP and Load+OP fusions appear under Other_Light_Ops in MTL!)}", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations , instructions that require two or more uops or micro-coded sequences", + "BriefDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences", "DefaultMetricgroupName": "TopdownL2", - "MetricExpr": "topdown\\-heavy\\-ops / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * slots", + "MetricExpr": "topdown\\-heavy\\-ops / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * tma_info_thread_slots", "MetricGroup": "Default;Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_heavy_operations", "MetricThreshold": "tma_heavy_operations > 0.1", "MetricgroupNoGroup": "TopdownL2;Default", - "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations , instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences.([ICL+] Note this may overcount due to approximation using indirect events; [ADL+]). Sample with: UOPS_RETIRED.HEAVY", + "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences.([ICL+] Note this may overcount due to approximation using indirect events; [ADL+]). Sample with: UOPS_RETIRED.HEAVY", "ScaleUnit": "100%" }, { @@ -797,8 +799,8 @@ "MetricExpr": "ICACHE_DATA.STALLS / tma_info_thread_clks", "MetricGroup": "BigFootprint;BvBC;FetchLat;IcMiss;TopdownL3;tma_L3_group;tma_fetch_latency_group", "MetricName": "tma_icache_misses", - "MetricThreshold": "tma_icache_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", - "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to instruction cache misses. Sample with: FRONTEND_RETIRED.L2_MISS, FRONTEND_RETIRED.L1I_MISS", + "MetricThreshold": "tma_icache_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to instruction cache misses. Sample with: FRONTEND_RETIRED.L2_MISS_PS;FRONTEND_RETIRED.L1I_MISS_PS", "ScaleUnit": "100%" }, { @@ -809,28 +811,28 @@ "PublicDescription": "Branch Misprediction Cost: Cycles representing fraction of TMA slots wasted per non-speculative branch misprediction (retired JEClear). Related metrics: tma_bottleneck_mispredictions, tma_branch_mispredicts, tma_mispredicts_resteers" }, { - "BriefDescription": "Instructions per retired Mispredicts for conditional non-taken branches (lower number means higher occurrence rate)", + "BriefDescription": "Instructions per retired Mispredicts for conditional non-taken branches (lower number means higher occurrence rate).", "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.COND_NTAKEN", "MetricGroup": "Bad;BrMispredicts", "MetricName": "tma_info_bad_spec_ipmisp_cond_ntaken", "MetricThreshold": "tma_info_bad_spec_ipmisp_cond_ntaken < 200" }, { - "BriefDescription": "Instructions per retired Mispredicts for conditional taken branches (lower number means higher occurrence rate)", + "BriefDescription": "Instructions per retired Mispredicts for conditional taken branches (lower number means higher occurrence rate).", "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.COND_TAKEN", "MetricGroup": "Bad;BrMispredicts", "MetricName": "tma_info_bad_spec_ipmisp_cond_taken", "MetricThreshold": "tma_info_bad_spec_ipmisp_cond_taken < 200" }, { - "BriefDescription": "Instructions per retired Mispredicts for indirect CALL or JMP branches (lower number means higher occurrence rate)", + "BriefDescription": "Instructions per retired Mispredicts for indirect CALL or JMP branches (lower number means higher occurrence rate).", "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.INDIRECT", "MetricGroup": "Bad;BrMispredicts", "MetricName": "tma_info_bad_spec_ipmisp_indirect", - "MetricThreshold": "tma_info_bad_spec_ipmisp_indirect < 1000" + "MetricThreshold": "tma_info_bad_spec_ipmisp_indirect < 1e3" }, { - "BriefDescription": "Instructions per retired Mispredicts for return branches (lower number means higher occurrence rate)", + "BriefDescription": "Instructions per retired Mispredicts for return branches (lower number means higher occurrence rate).", "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.RET", "MetricGroup": "Bad;BrMispredicts", "MetricName": "tma_info_bad_spec_ipmisp_ret", @@ -858,7 +860,7 @@ }, { "BriefDescription": "Total pipeline cost of DSB (uop cache) hits - subset of the Instruction_Fetch_BW Bottleneck", - "MetricExpr": "100 * (tma_frontend_bound * (tma_fetch_bandwidth / (tma_fetch_latency + tma_fetch_bandwidth)) * (tma_dsb / (tma_mite + tma_dsb + tma_ms)))", + "MetricExpr": "100 * (tma_frontend_bound * (tma_fetch_bandwidth / (tma_fetch_bandwidth + tma_fetch_latency)) * (tma_dsb / (tma_dsb + tma_mite + tma_ms)))", "MetricGroup": "DSB;Fed;FetchBW;tma_issueFB", "MetricName": "tma_info_botlnk_l2_dsb_bandwidth", "MetricThreshold": "tma_info_botlnk_l2_dsb_bandwidth > 10", @@ -866,7 +868,7 @@ }, { "BriefDescription": "Total pipeline cost of DSB (uop cache) misses - subset of the Instruction_Fetch_BW Bottleneck", - "MetricExpr": "100 * (tma_fetch_latency * tma_dsb_switches / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches) + tma_fetch_bandwidth * tma_mite / (tma_mite + tma_dsb + tma_ms))", + "MetricExpr": "100 * (tma_fetch_latency * tma_dsb_switches / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) + tma_fetch_bandwidth * tma_mite / (tma_dsb + tma_mite + tma_ms))", "MetricGroup": "DSBmiss;Fed;tma_issueFB", "MetricName": "tma_info_botlnk_l2_dsb_misses", "MetricThreshold": "tma_info_botlnk_l2_dsb_misses > 10", @@ -874,10 +876,11 @@ }, { "BriefDescription": "Total pipeline cost of Instruction Cache misses - subset of the Big_Code Bottleneck", - "MetricExpr": "100 * (tma_fetch_latency * tma_icache_misses / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches))", + "MetricExpr": "100 * (tma_fetch_latency * tma_icache_misses / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches))", "MetricGroup": "Fed;FetchLat;IcMiss;tma_issueFL", "MetricName": "tma_info_botlnk_l2_ic_misses", - "MetricThreshold": "tma_info_botlnk_l2_ic_misses > 5" + "MetricThreshold": "tma_info_botlnk_l2_ic_misses > 5", + "PublicDescription": "Total pipeline cost of Instruction Cache misses - subset of the Big_Code Bottleneck. Related metrics: " }, { "BriefDescription": "Fraction of branches that are CALL or RET", @@ -938,11 +941,11 @@ "MetricExpr": "(FP_ARITH_DISPATCHED.PORT_0 + FP_ARITH_DISPATCHED.PORT_1 + FP_ARITH_DISPATCHED.PORT_5) / (2 * tma_info_core_core_clks)", "MetricGroup": "Cor;Flops;HPC", "MetricName": "tma_info_core_fp_arith_utilization", - "PublicDescription": "Actual per-core usage of the Floating Point non-X87 execution units (regardless of precision or vector-width). Values > 1 are possible due to ([BDW+] Fused-Multiply Add (FMA) counting - common; [ADL+] use all of ADD/MUL/FMA in Scalar or 128/256-bit vectors - less common)" + "PublicDescription": "Actual per-core usage of the Floating Point non-X87 execution units (regardless of precision or vector-width). Values > 1 are possible due to ([BDW+] Fused-Multiply Add (FMA) counting - common; [ADL+] use all of ADD/MUL/FMA in Scalar or 128/256-bit vectors - less common)." }, { "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is execution) per thread (logical-processor)", - "MetricExpr": "UOPS_EXECUTED.THREAD / cpu@UOPS_EXECUTED.THREAD\\,cmask\\=0x1@", + "MetricExpr": "UOPS_EXECUTED.THREAD / cpu@UOPS_EXECUTED.THREAD\\,cmask\\=1@", "MetricGroup": "Backend;Cor;Pipeline;PortsUtil", "MetricName": "tma_info_core_ilp" }, @@ -955,20 +958,20 @@ "PublicDescription": "Fraction of Uops delivered by the DSB (aka Decoded ICache; or Uop Cache). Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_inst_mix_iptb, tma_lcp" }, { - "BriefDescription": "Average number of cycles of a switch from the DSB fetch-unit to MITE fetch unit - see DSB_Switches tree node for details", - "MetricExpr": "DSB2MITE_SWITCHES.PENALTY_CYCLES / cpu@DSB2MITE_SWITCHES.PENALTY_CYCLES\\,cmask\\=0x1\\,edge\\=0x1@", + "BriefDescription": "Average number of cycles of a switch from the DSB fetch-unit to MITE fetch unit - see DSB_Switches tree node for details.", + "MetricExpr": "DSB2MITE_SWITCHES.PENALTY_CYCLES / cpu@DSB2MITE_SWITCHES.PENALTY_CYCLES\\,cmask\\=1\\,edge@", "MetricGroup": "DSBmiss", "MetricName": "tma_info_frontend_dsb_switch_cost" }, { "BriefDescription": "Average number of Uops issued by front-end when it issued something", - "MetricExpr": "UOPS_ISSUED.ANY / cpu@UOPS_ISSUED.ANY\\,cmask\\=0x1@", + "MetricExpr": "UOPS_ISSUED.ANY / cpu@UOPS_ISSUED.ANY\\,cmask\\=1@", "MetricGroup": "Fed;FetchBW", "MetricName": "tma_info_frontend_fetch_upc" }, { "BriefDescription": "Average Latency for L1 instruction cache misses", - "MetricExpr": "ICACHE_DATA.STALLS / cpu@ICACHE_DATA.STALLS\\,cmask\\=0x1\\,edge\\=0x1@", + "MetricExpr": "ICACHE_DATA.STALLS / cpu@ICACHE_DATA.STALLS\\,cmask\\=1\\,edge@", "MetricGroup": "Fed;FetchLat;IcMiss", "MetricName": "tma_info_frontend_icache_miss_latency" }, @@ -1005,13 +1008,13 @@ }, { "BriefDescription": "Average number of cycles the front-end was delayed due to an Unknown Branch detection", - "MetricExpr": "INT_MISC.UNKNOWN_BRANCH_CYCLES / cpu@INT_MISC.UNKNOWN_BRANCH_CYCLES\\,cmask\\=0x1\\,edge\\=0x1@", + "MetricExpr": "INT_MISC.UNKNOWN_BRANCH_CYCLES / cpu@INT_MISC.UNKNOWN_BRANCH_CYCLES\\,cmask\\=1\\,edge@", "MetricGroup": "Fed", "MetricName": "tma_info_frontend_unknown_branch_cost", - "PublicDescription": "Average number of cycles the front-end was delayed due to an Unknown Branch detection. See Unknown_Branches node" + "PublicDescription": "Average number of cycles the front-end was delayed due to an Unknown Branch detection. See Unknown_Branches node." }, { - "BriefDescription": "Branch instructions per taken branch", + "BriefDescription": "Branch instructions per taken branch.", "MetricExpr": "BR_INST_RETIRED.ALL_BRANCHES / BR_INST_RETIRED.NEAR_TAKEN", "MetricGroup": "Branches;Fed;PGO", "MetricName": "tma_info_inst_mix_bptkbranch" @@ -1029,7 +1032,7 @@ "MetricGroup": "Flops;InsType", "MetricName": "tma_info_inst_mix_iparith", "MetricThreshold": "tma_info_inst_mix_iparith < 10", - "PublicDescription": "Instructions per FP Arithmetic instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting. Approximated prior to BDW" + "PublicDescription": "Instructions per FP Arithmetic instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting. Approximated prior to BDW." }, { "BriefDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number means higher occurrence rate)", @@ -1037,7 +1040,7 @@ "MetricGroup": "Flops;FpVector;InsType", "MetricName": "tma_info_inst_mix_iparith_avx128", "MetricThreshold": "tma_info_inst_mix_iparith_avx128 < 10", - "PublicDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting" + "PublicDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting." }, { "BriefDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means higher occurrence rate)", @@ -1045,7 +1048,7 @@ "MetricGroup": "Flops;FpVector;InsType", "MetricName": "tma_info_inst_mix_iparith_avx256", "MetricThreshold": "tma_info_inst_mix_iparith_avx256 < 10", - "PublicDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting" + "PublicDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting." }, { "BriefDescription": "Instructions per FP Arithmetic AVX 512-bit instruction (lower number means higher occurrence rate)", @@ -1053,7 +1056,7 @@ "MetricGroup": "Flops;FpVector;InsType", "MetricName": "tma_info_inst_mix_iparith_avx512", "MetricThreshold": "tma_info_inst_mix_iparith_avx512 < 10", - "PublicDescription": "Instructions per FP Arithmetic AVX 512-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting" + "PublicDescription": "Instructions per FP Arithmetic AVX 512-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting." }, { "BriefDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction (lower number means higher occurrence rate)", @@ -1061,7 +1064,7 @@ "MetricGroup": "Flops;FpScalar;InsType", "MetricName": "tma_info_inst_mix_iparith_scalar_dp", "MetricThreshold": "tma_info_inst_mix_iparith_scalar_dp < 10", - "PublicDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting" + "PublicDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting." }, { "BriefDescription": "Instructions per FP Arithmetic Scalar Half-Precision instruction (lower number means higher occurrence rate)", @@ -1069,7 +1072,7 @@ "MetricGroup": "Flops;FpScalar;InsType;Server", "MetricName": "tma_info_inst_mix_iparith_scalar_hp", "MetricThreshold": "tma_info_inst_mix_iparith_scalar_hp < 10", - "PublicDescription": "Instructions per FP Arithmetic Scalar Half-Precision instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting" + "PublicDescription": "Instructions per FP Arithmetic Scalar Half-Precision instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting." }, { "BriefDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction (lower number means higher occurrence rate)", @@ -1077,7 +1080,7 @@ "MetricGroup": "Flops;FpScalar;InsType", "MetricName": "tma_info_inst_mix_iparith_scalar_sp", "MetricThreshold": "tma_info_inst_mix_iparith_scalar_sp < 10", - "PublicDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting" + "PublicDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting." }, { "BriefDescription": "Instructions per Branch (lower number means higher occurrence rate)", @@ -1132,7 +1135,7 @@ "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_TAKEN", "MetricGroup": "Branches;Fed;FetchBW;Frontend;PGO;tma_issueFB", "MetricName": "tma_info_inst_mix_iptb", - "MetricThreshold": "tma_info_inst_mix_iptb < 6 * 2 + 1", + "MetricThreshold": "tma_info_inst_mix_iptb < 13", "PublicDescription": "Instructions per taken branch. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_lcp" }, { @@ -1269,7 +1272,7 @@ }, { "BriefDescription": "Average Parallel L2 cache miss demand Loads", - "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD / cpu@OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD\\,cmask\\=0x1@", + "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD / cpu@OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD\\,cmask\\=1@", "MetricGroup": "Memory_BW;Offcore", "MetricName": "tma_info_memory_latency_load_l2_mlp" }, @@ -1334,21 +1337,21 @@ "MetricExpr": "64 * OCR.READS_TO_CORE.DRAM / 1e9 / tma_info_system_time", "MetricGroup": "HPC;Mem;MemoryBW;SoC", "MetricName": "tma_info_memory_soc_r2c_dram_bw", - "PublicDescription": "Average DRAM BW for Reads-to-Core (R2C) covering for memory attached to local- and remote-socket. See R2C_Offcore_BW" + "PublicDescription": "Average DRAM BW for Reads-to-Core (R2C) covering for memory attached to local- and remote-socket. See R2C_Offcore_BW." }, { "BriefDescription": "Average L3-cache miss BW for Reads-to-Core (R2C)", "MetricExpr": "64 * OCR.READS_TO_CORE.L3_MISS / 1e9 / tma_info_system_time", "MetricGroup": "HPC;Mem;MemoryBW;SoC", "MetricName": "tma_info_memory_soc_r2c_l3m_bw", - "PublicDescription": "Average L3-cache miss BW for Reads-to-Core (R2C). This covering going to DRAM or other memory off-chip memory tears. See R2C_Offcore_BW" + "PublicDescription": "Average L3-cache miss BW for Reads-to-Core (R2C). This covering going to DRAM or other memory off-chip memory tears. See R2C_Offcore_BW." }, { "BriefDescription": "Average Off-core access BW for Reads-to-Core (R2C)", "MetricExpr": "64 * OCR.READS_TO_CORE.ANY_RESPONSE / 1e9 / tma_info_system_time", "MetricGroup": "HPC;Mem;MemoryBW;SoC", "MetricName": "tma_info_memory_soc_r2c_offcore_bw", - "PublicDescription": "Average Off-core access BW for Reads-to-Core (R2C). R2C account for demand or prefetch load/RFO/code access that fill data into the Core caches" + "PublicDescription": "Average Off-core access BW for Reads-to-Core (R2C). R2C account for demand or prefetch load/RFO/code access that fill data into the Core caches." }, { "BriefDescription": "STLB (2nd level TLB) code speculative misses per kilo instruction (misses of any page-size that complete the page walk)", @@ -1376,8 +1379,8 @@ "MetricName": "tma_info_memory_tlb_store_stlb_mpki" }, { - "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is execution) per core", - "MetricExpr": "UOPS_EXECUTED.THREAD / (UOPS_EXECUTED.CORE_CYCLES_GE_1 / 2 if #SMT_on else cpu@UOPS_EXECUTED.THREAD\\,cmask\\=0x1@)", + "BriefDescription": "", + "MetricExpr": "UOPS_EXECUTED.THREAD / (UOPS_EXECUTED.CORE_CYCLES_GE_1 / 2 if #SMT_on else cpu@UOPS_EXECUTED.THREAD\\,cmask\\=1@)", "MetricGroup": "Cor;Pipeline;PortsUtil;SMT", "MetricName": "tma_info_pipeline_execute" }, @@ -1398,18 +1401,18 @@ "MetricExpr": "INST_RETIRED.ANY / ASSISTS.ANY", "MetricGroup": "MicroSeq;Pipeline;Ret;Retire", "MetricName": "tma_info_pipeline_ipassist", - "MetricThreshold": "tma_info_pipeline_ipassist < 100000", + "MetricThreshold": "tma_info_pipeline_ipassist < 100e3", "PublicDescription": "Instructions per a microcode Assist invocation. See Assists tree node for details (lower number means higher occurrence rate)" }, { - "BriefDescription": "Average number of Uops retired in cycles where at least one uop has retired", - "MetricExpr": "tma_retiring * tma_info_thread_slots / cpu@UOPS_RETIRED.SLOTS\\,cmask\\=0x1@", + "BriefDescription": "Average number of Uops retired in cycles where at least one uop has retired.", + "MetricExpr": "tma_retiring * tma_info_thread_slots / cpu@UOPS_RETIRED.SLOTS\\,cmask\\=1@", "MetricGroup": "Pipeline;Ret", "MetricName": "tma_info_pipeline_retire" }, { "BriefDescription": "Estimated fraction of retirement-cycles dealing with repeat instructions", - "MetricExpr": "INST_RETIRED.REP_ITERATION / cpu@UOPS_RETIRED.SLOTS\\,cmask\\=0x1@", + "MetricExpr": "INST_RETIRED.REP_ITERATION / cpu@UOPS_RETIRED.SLOTS\\,cmask\\=1@", "MetricGroup": "MicroSeq;Pipeline;Ret", "MetricName": "tma_info_pipeline_strings_cycles", "MetricThreshold": "tma_info_pipeline_strings_cycles > 0.1" @@ -1472,14 +1475,13 @@ "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.FAR_BRANCH:u", "MetricGroup": "Branches;OS", "MetricName": "tma_info_system_ipfarbranch", - "MetricThreshold": "tma_info_system_ipfarbranch < 1000000" + "MetricThreshold": "tma_info_system_ipfarbranch < 1e6" }, { "BriefDescription": "Cycles Per Instruction for the Operating System (OS) Kernel mode", "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P:k / INST_RETIRED.ANY_P:k", "MetricGroup": "OS", - "MetricName": "tma_info_system_kernel_cpi", - "ScaleUnit": "1per_instr" + "MetricName": "tma_info_system_kernel_cpi" }, { "BriefDescription": "Fraction of cycles spent in the Operating System (OS) Kernel mode", @@ -1490,7 +1492,7 @@ }, { "BriefDescription": "Average latency of data read request to external DRAM memory [in nanoseconds]", - "MetricExpr": "1e9 * (UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_DDR / UNC_CHA_TOR_INSERTS.IA_MISS_DRD_DDR) / cha_0@event\\=0x0@", + "MetricExpr": "1e9 * (UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_DDR / UNC_CHA_TOR_INSERTS.IA_MISS_DRD_DDR) / uncore_cha_0@event\\=0x1@", "MetricGroup": "MemOffcore;MemoryLat;Server;SoC", "MetricName": "tma_info_system_mem_dram_read_latency", "PublicDescription": "Average latency of data read request to external DRAM memory [in nanoseconds]. Accounts for demand loads and L1/L2 data-read prefetches" @@ -1500,11 +1502,11 @@ "MetricExpr": "UNC_CHA_RxC_IRQ1_REJECT.PA_MATCH / UNC_CHA_CLOCKTICKS", "MetricGroup": "LockCont;MemOffcore;Server;SoC", "MetricName": "tma_info_system_mem_irq_duplicate_address", - "MetricThreshold": "(tma_info_system_mem_irq_duplicate_address > 0.1)" + "MetricThreshold": "tma_info_system_mem_irq_duplicate_address > 0.1" }, { "BriefDescription": "Average number of parallel data read requests to external memory", - "MetricExpr": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD / cha@UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD\\,thresh\\=0x1@", + "MetricExpr": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD / UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD@thresh\\=1@", "MetricGroup": "Mem;MemoryBW;SoC", "MetricName": "tma_info_system_mem_parallel_reads", "PublicDescription": "Average number of parallel data read requests to external memory. Accounts for demand loads and L1/L2 prefetches" @@ -1538,7 +1540,7 @@ }, { "BriefDescription": "Socket actual clocks when any core is active on that socket", - "MetricExpr": "cha_0@event\\=0x0@", + "MetricExpr": "uncore_cha_0@event\\=0x1@", "MetricGroup": "SoC", "MetricName": "tma_info_system_socket_clks" }, @@ -1568,7 +1570,7 @@ "MetricName": "tma_info_system_upi_data_transmit_bw" }, { - "BriefDescription": "Per-Logical Processor actual clocks when the Logical Processor is active", + "BriefDescription": "Per-Logical Processor actual clocks when the Logical Processor is active.", "MetricExpr": "CPU_CLK_UNHALTED.THREAD", "MetricGroup": "Pipeline", "MetricName": "tma_info_thread_clks" @@ -1577,15 +1579,14 @@ "BriefDescription": "Cycles Per Instruction (per Logical Processor)", "MetricExpr": "1 / tma_info_thread_ipc", "MetricGroup": "Mem;Pipeline", - "MetricName": "tma_info_thread_cpi", - "ScaleUnit": "1per_instr" + "MetricName": "tma_info_thread_cpi" }, { "BriefDescription": "The ratio of Executed- by Issued-Uops", "MetricExpr": "UOPS_EXECUTED.THREAD / UOPS_ISSUED.ANY", "MetricGroup": "Cor;Pipeline", "MetricName": "tma_info_thread_execute_per_issue", - "PublicDescription": "The ratio of Executed- by Issued-Uops. Ratio > 1 suggests high rate of uop micro-fusions. Ratio < 1 suggest high rate of \"execute\" at rename stage" + "PublicDescription": "The ratio of Executed- by Issued-Uops. Ratio > 1 suggests high rate of uop micro-fusions. Ratio < 1 suggest high rate of \"execute\" at rename stage." }, { "BriefDescription": "Instructions Per Cycle (per Logical Processor)", @@ -1595,13 +1596,13 @@ }, { "BriefDescription": "Total issue-pipeline slots (per-Physical Core till ICL; per-Logical Processor ICL onward)", - "MetricExpr": "slots", + "MetricExpr": "TOPDOWN.SLOTS", "MetricGroup": "TmaL1;tma_L1_group", "MetricName": "tma_info_thread_slots" }, { "BriefDescription": "Fraction of Physical Core issue-slots utilized by this Logical Processor", - "MetricExpr": "(tma_info_thread_slots / (slots / 2) if #SMT_on else 1)", + "MetricExpr": "(tma_info_thread_slots / (TOPDOWN.SLOTS / 2) if #SMT_on else 1)", "MetricGroup": "SMT;TmaL1;tma_L1_group", "MetricName": "tma_info_thread_slots_utilization" }, @@ -1617,14 +1618,14 @@ "MetricExpr": "tma_retiring * tma_info_thread_slots / BR_INST_RETIRED.NEAR_TAKEN", "MetricGroup": "Branches;Fed;FetchBW", "MetricName": "tma_info_thread_uptb", - "MetricThreshold": "tma_info_thread_uptb < 6 * 1.5" + "MetricThreshold": "tma_info_thread_uptb < 9" }, { - "BriefDescription": "This metric represents fraction of cycles where the Integer Divider unit was active", + "BriefDescription": "This metric represents fraction of cycles where the Integer Divider unit was active.", "MetricExpr": "tma_divider - tma_fp_divider", "MetricGroup": "TopdownL4;tma_L4_group;tma_divider_group", "MetricName": "tma_int_divider", - "MetricThreshold": "tma_int_divider > 0.2 & tma_divider > 0.2 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_int_divider > 0.2 & (tma_divider > 0.2 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", "ScaleUnit": "100%" }, { @@ -1633,7 +1634,7 @@ "MetricGroup": "Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group", "MetricName": "tma_int_operations", "MetricThreshold": "tma_int_operations > 0.1 & tma_light_operations > 0.6", - "PublicDescription": "This metric represents overall Integer (Int) select operations fraction the CPU has executed (retired). Vector/Matrix Int operations and shuffles are counted. Note this metric's value may exceed its parent due to use of \"Uops\" CountDomain", + "PublicDescription": "This metric represents overall Integer (Int) select operations fraction the CPU has executed (retired). Vector/Matrix Int operations and shuffles are counted. Note this metric's value may exceed its parent due to use of \"Uops\" CountDomain.", "ScaleUnit": "100%" }, { @@ -1641,8 +1642,8 @@ "MetricExpr": "(INT_VEC_RETIRED.ADD_128 + INT_VEC_RETIRED.VNNI_128) / (tma_retiring * tma_info_thread_slots)", "MetricGroup": "Compute;IntVector;Pipeline;TopdownL4;tma_L4_group;tma_int_operations_group;tma_issue2P", "MetricName": "tma_int_vector_128b", - "MetricThreshold": "tma_int_vector_128b > 0.1 & tma_int_operations > 0.1 & tma_light_operations > 0.6", - "PublicDescription": "This metric represents 128-bit vector Integer ADD/SUB/SAD or VNNI (Vector Neural Network Instructions) uops fraction the CPU has retired. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_6, tma_ports_utilized_2", + "MetricThreshold": "tma_int_vector_128b > 0.1 & (tma_int_operations > 0.1 & tma_light_operations > 0.6)", + "PublicDescription": "This metric represents 128-bit vector Integer ADD/SUB/SAD or VNNI (Vector Neural Network Instructions) uops fraction the CPU has retired. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%" }, { @@ -1650,8 +1651,8 @@ "MetricExpr": "(INT_VEC_RETIRED.ADD_256 + INT_VEC_RETIRED.MUL_256 + INT_VEC_RETIRED.VNNI_256) / (tma_retiring * tma_info_thread_slots)", "MetricGroup": "Compute;IntVector;Pipeline;TopdownL4;tma_L4_group;tma_int_operations_group;tma_issue2P", "MetricName": "tma_int_vector_256b", - "MetricThreshold": "tma_int_vector_256b > 0.1 & tma_int_operations > 0.1 & tma_light_operations > 0.6", - "PublicDescription": "This metric represents 256-bit vector Integer ADD/SUB/SAD/MUL or VNNI (Vector Neural Network Instructions) uops fraction the CPU has retired. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_port_0, tma_port_1, tma_port_6, tma_ports_utilized_2", + "MetricThreshold": "tma_int_vector_256b > 0.1 & (tma_int_operations > 0.1 & tma_light_operations > 0.6)", + "PublicDescription": "This metric represents 256-bit vector Integer ADD/SUB/SAD/MUL or VNNI (Vector Neural Network Instructions) uops fraction the CPU has retired. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%" }, { @@ -1659,8 +1660,8 @@ "MetricExpr": "ICACHE_TAG.STALLS / tma_info_thread_clks", "MetricGroup": "BigFootprint;BvBC;FetchLat;MemoryTLB;TopdownL3;tma_L3_group;tma_fetch_latency_group", "MetricName": "tma_itlb_misses", - "MetricThreshold": "tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", - "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Instruction TLB (ITLB) misses. Sample with: FRONTEND_RETIRED.STLB_MISS, FRONTEND_RETIRED.ITLB_MISS", + "MetricThreshold": "tma_itlb_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Instruction TLB (ITLB) misses. Sample with: FRONTEND_RETIRED.STLB_MISS_PS;FRONTEND_RETIRED.ITLB_MISS_PS", "ScaleUnit": "100%" }, { @@ -1668,7 +1669,7 @@ "MetricExpr": "max((EXE_ACTIVITY.BOUND_ON_LOADS - MEMORY_ACTIVITY.STALLS_L1D_MISS) / tma_info_thread_clks, 0)", "MetricGroup": "CacheHits;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_issueL1;tma_issueMC;tma_memory_bound_group", "MetricName": "tma_l1_bound", - "MetricThreshold": "tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", "PublicDescription": "This metric estimates how often the CPU was stalled without loads missing the L1 Data (L1D) cache. The L1D cache typically has the shortest latency. However; in certain cases like loads blocked on older stores; a load might suffer due to high latency even though it is being satisfied by the L1D. Another example is loads who miss in the TLB. These cases are characterized by execution unit stalls; while some non-completed demand load lives in the machine without having that demand load missing the L1 cache. Sample with: MEM_LOAD_RETIRED.L1_HIT. Related metrics: tma_clears_resteers, tma_machine_clears, tma_microcode_sequencer, tma_ms_switches, tma_ports_utilized_1", "ScaleUnit": "100%" }, @@ -1677,7 +1678,7 @@ "MetricExpr": "min(2 * (MEM_INST_RETIRED.ALL_LOADS - MEM_LOAD_RETIRED.FB_HIT - MEM_LOAD_RETIRED.L1_MISS) * 20 / 100, max(CYCLE_ACTIVITY.CYCLES_MEM_ANY - MEMORY_ACTIVITY.CYCLES_L1D_MISS, 0)) / tma_info_thread_clks", "MetricGroup": "BvML;MemoryLat;TopdownL4;tma_L4_group;tma_l1_bound_group", "MetricName": "tma_l1_latency_dependency", - "MetricThreshold": "tma_l1_latency_dependency > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_l1_latency_dependency > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", "PublicDescription": "This metric([SKL+] roughly; [LNL]) estimates fraction of cycles with demand load accesses that hit the L1D cache. The short latency of the L1D cache may be exposed in pointer-chasing memory access patterns as an example. Sample with: MEM_LOAD_RETIRED.L1_HIT", "ScaleUnit": "100%" }, @@ -1686,16 +1687,17 @@ "MetricExpr": "(MEMORY_ACTIVITY.STALLS_L1D_MISS - MEMORY_ACTIVITY.STALLS_L2_MISS) / tma_info_thread_clks", "MetricGroup": "BvML;CacheHits;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_l2_bound", - "MetricThreshold": "tma_l2_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_l2_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", "PublicDescription": "This metric estimates how often the CPU was stalled due to L2 cache accesses by loads. Avoiding cache misses (i.e. L1 misses/L2 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L2_HIT", "ScaleUnit": "100%" }, { "BriefDescription": "This metric represents fraction of cycles with demand load accesses that hit the L2 cache under unloaded scenarios (possibly L2 latency limited)", + "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "4.4 * tma_info_system_core_frequency * MEM_LOAD_RETIRED.L2_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks", "MetricGroup": "MemoryLat;TopdownL4;tma_L4_group;tma_l2_bound_group", "MetricName": "tma_l2_hit_latency", - "MetricThreshold": "tma_l2_hit_latency > 0.05 & tma_l2_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_l2_hit_latency > 0.05 & (tma_l2_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", "PublicDescription": "This metric represents fraction of cycles with demand load accesses that hit the L2 cache under unloaded scenarios (possibly L2 latency limited). Avoiding L1 cache misses (i.e. L1 misses/L2 hits) will improve the latency. Sample with: MEM_LOAD_RETIRED.L2_HIT", "ScaleUnit": "100%" }, @@ -1704,17 +1706,18 @@ "MetricExpr": "(MEMORY_ACTIVITY.STALLS_L2_MISS - MEMORY_ACTIVITY.STALLS_L3_MISS) / tma_info_thread_clks", "MetricGroup": "CacheHits;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_l3_bound", - "MetricThreshold": "tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", - "PublicDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core. Avoiding cache misses (i.e. L2 misses/L3 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L3_HIT", + "MetricThreshold": "tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", + "PublicDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core. Avoiding cache misses (i.e. L2 misses/L3 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L3_HIT_PS", "ScaleUnit": "100%" }, { "BriefDescription": "This metric estimates fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited)", - "MetricExpr": "(37 * tma_info_system_core_frequency - 4.4 * tma_info_system_core_frequency) * (MEM_LOAD_RETIRED.L3_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2)) / tma_info_thread_clks", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "32.6 * tma_info_system_core_frequency * (MEM_LOAD_RETIRED.L3_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2)) / tma_info_thread_clks", "MetricGroup": "BvML;MemoryLat;TopdownL4;tma_L4_group;tma_issueLat;tma_l3_bound_group", "MetricName": "tma_l3_hit_latency", - "MetricThreshold": "tma_l3_hit_latency > 0.1 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", - "PublicDescription": "This metric estimates fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited). Avoiding private cache misses (i.e. L2 misses/L3 hits) will improve the latency; reduce contention with sibling physical cores and increase performance. Note the value of this node may overlap with its siblings. Sample with: MEM_LOAD_RETIRED.L3_HIT. Related metrics: tma_bottleneck_cache_memory_latency, tma_branch_resteers, tma_mem_latency, tma_store_latency", + "MetricThreshold": "tma_l3_hit_latency > 0.1 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric estimates fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited). Avoiding private cache misses (i.e. L2 misses/L3 hits) will improve the latency; reduce contention with sibling physical cores and increase performance. Note the value of this node may overlap with its siblings. Sample with: MEM_LOAD_RETIRED.L3_HIT_PS. Related metrics: tma_bottleneck_cache_memory_latency, tma_mem_latency", "ScaleUnit": "100%" }, { @@ -1722,19 +1725,19 @@ "MetricExpr": "DECODE.LCP / tma_info_thread_clks", "MetricGroup": "FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueFB", "MetricName": "tma_lcp", - "MetricThreshold": "tma_lcp > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", - "PublicDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs). Using proper compiler flags or Intel Compiler by default will certainly avoid this. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb", + "MetricThreshold": "tma_lcp > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", + "PublicDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs). Using proper compiler flags or Intel Compiler by default will certainly avoid this. #Link: Optimization Guide about LCP BKMs. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations , instructions that require no more than one uop (micro-operation)", + "BriefDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation)", "DefaultMetricgroupName": "TopdownL2", "MetricExpr": "max(0, tma_retiring - tma_heavy_operations)", "MetricGroup": "Default;Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_light_operations", "MetricThreshold": "tma_light_operations > 0.6", "MetricgroupNoGroup": "TopdownL2;Default", - "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations , instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized code running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. ([ICL+] Note this may undercount due to approximation using indirect events; [ADL+] .). Sample with: INST_RETIRED.PREC_DIST", + "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized code running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. ([ICL+] Note this may undercount due to approximation using indirect events; [ADL+] .). Sample with: INST_RETIRED.PREC_DIST", "ScaleUnit": "100%" }, { @@ -1751,7 +1754,7 @@ "MetricExpr": "tma_dtlb_load - tma_load_stlb_miss", "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_load_group", "MetricName": "tma_load_stlb_hit", - "MetricThreshold": "tma_load_stlb_hit > 0.05 & tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_load_stlb_hit > 0.05 & (tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))", "ScaleUnit": "100%" }, { @@ -1759,39 +1762,39 @@ "MetricExpr": "DTLB_LOAD_MISSES.WALK_ACTIVE / tma_info_thread_clks", "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_load_group", "MetricName": "tma_load_stlb_miss", - "MetricThreshold": "tma_load_stlb_miss > 0.05 & tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_load_stlb_miss > 0.05 & (tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 1 GB pages for data load accesses", + "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 1 GB pages for data load accesses.", "MetricExpr": "tma_load_stlb_miss * DTLB_LOAD_MISSES.WALK_COMPLETED_1G / (DTLB_LOAD_MISSES.WALK_COMPLETED_4K + DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M + DTLB_LOAD_MISSES.WALK_COMPLETED_1G)", "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_load_stlb_miss_group", "MetricName": "tma_load_stlb_miss_1g", - "MetricThreshold": "tma_load_stlb_miss_1g > 0.05 & tma_load_stlb_miss > 0.05 & tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_load_stlb_miss_1g > 0.05 & (tma_load_stlb_miss > 0.05 & (tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))))", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 2 or 4 MB pages for data load accesses", + "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 2 or 4 MB pages for data load accesses.", "MetricExpr": "tma_load_stlb_miss * DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M / (DTLB_LOAD_MISSES.WALK_COMPLETED_4K + DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M + DTLB_LOAD_MISSES.WALK_COMPLETED_1G)", "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_load_stlb_miss_group", "MetricName": "tma_load_stlb_miss_2m", - "MetricThreshold": "tma_load_stlb_miss_2m > 0.05 & tma_load_stlb_miss > 0.05 & tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_load_stlb_miss_2m > 0.05 & (tma_load_stlb_miss > 0.05 & (tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))))", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 4 KB pages for data load accesses", + "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 4 KB pages for data load accesses.", "MetricExpr": "tma_load_stlb_miss * DTLB_LOAD_MISSES.WALK_COMPLETED_4K / (DTLB_LOAD_MISSES.WALK_COMPLETED_4K + DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M + DTLB_LOAD_MISSES.WALK_COMPLETED_1G)", "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_load_stlb_miss_group", "MetricName": "tma_load_stlb_miss_4k", - "MetricThreshold": "tma_load_stlb_miss_4k > 0.05 & tma_load_stlb_miss > 0.05 & tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_load_stlb_miss_4k > 0.05 & (tma_load_stlb_miss > 0.05 & (tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))))", "ScaleUnit": "100%" }, { "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from local memory", - "MetricExpr": "(109 * tma_info_system_core_frequency - 37 * tma_info_system_core_frequency) * MEM_LOAD_L3_MISS_RETIRED.LOCAL_DRAM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks", + "MetricExpr": "72 * tma_info_system_core_frequency * MEM_LOAD_L3_MISS_RETIRED.LOCAL_DRAM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks", "MetricGroup": "Server;TopdownL5;tma_L5_group;tma_mem_latency_group", "MetricName": "tma_local_mem", - "MetricThreshold": "tma_local_mem > 0.1 & tma_mem_latency > 0.1 & tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_local_mem > 0.1 & (tma_mem_latency > 0.1 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))", "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from local memory. Caching will improve the latency and increase performance. Sample with: MEM_LOAD_L3_MISS_RETIRED.LOCAL_DRAM", "ScaleUnit": "100%" }, @@ -1800,7 +1803,7 @@ "MetricExpr": "(16 * max(0, MEM_INST_RETIRED.LOCK_LOADS - L2_RQSTS.ALL_RFO) + MEM_INST_RETIRED.LOCK_LOADS / MEM_INST_RETIRED.ALL_STORES * (10 * L2_RQSTS.RFO_HIT + min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO))) / tma_info_thread_clks", "MetricGroup": "LockCont;Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_l1_bound_group", "MetricName": "tma_lock_latency", - "MetricThreshold": "tma_lock_latency > 0.2 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_lock_latency > 0.2 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", "PublicDescription": "This metric represents fraction of cycles the CPU spent handling cache misses due to lock operations. Due to the microarchitecture handling of locks; they are classified as L1_Bound regardless of what memory source satisfied them. Sample with: MEM_INST_RETIRED.LOCK_LOADS. Related metrics: tma_store_latency", "ScaleUnit": "100%" }, @@ -1816,19 +1819,19 @@ "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to memory bandwidth Allocation feature (RDT's memory bandwidth throttling)", + "BriefDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to memory bandwidth Allocation feature (RDT's memory bandwidth throttling).", "MetricExpr": "INT_MISC.MBA_STALLS / tma_info_thread_clks", "MetricGroup": "MemoryBW;Offcore;Server;TopdownL5;tma_L5_group;tma_mem_bandwidth_group", "MetricName": "tma_mba_stalls", - "MetricThreshold": "tma_mba_stalls > 0.1 & tma_mem_bandwidth > 0.2 & tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_mba_stalls > 0.1 & (tma_mem_bandwidth > 0.2 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))", "ScaleUnit": "100%" }, { "BriefDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory - DRAM ([SPR-HBM] and/or HBM)", - "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, cpu@OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD\\,cmask\\=0x4@) / tma_info_thread_clks", + "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, cpu@OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD\\,cmask\\=4@) / tma_info_thread_clks", "MetricGroup": "BvMB;MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueBW", "MetricName": "tma_mem_bandwidth", - "MetricThreshold": "tma_mem_bandwidth > 0.2 & tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_mem_bandwidth > 0.2 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", "PublicDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory - DRAM ([SPR-HBM] and/or HBM). The underlying heuristic assumes that a similar off-core traffic is generated by all IA cores. This metric does not aggregate non-data-read requests by this logical processor; requests from other IA Logical Processors/Physical Cores/sockets; or other non-IA devices like GPU; hence the maximum external memory bandwidth limits may or may not be approached when this metric is flagged (see Uncore counters for that). Related metrics: tma_bottleneck_cache_memory_bandwidth, tma_fb_full, tma_info_system_dram_bw_use, tma_sq_full", "ScaleUnit": "100%" }, @@ -1837,32 +1840,32 @@ "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD) / tma_info_thread_clks - tma_mem_bandwidth", "MetricGroup": "BvML;MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueLat", "MetricName": "tma_mem_latency", - "MetricThreshold": "tma_mem_latency > 0.1 & tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_mem_latency > 0.1 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", "PublicDescription": "This metric estimates fraction of cycles where the performance was likely hurt due to latency from external memory - DRAM ([SPR-HBM] and/or HBM). This metric does not aggregate requests from other Logical Processors/Physical Cores/sockets (see Uncore counters for that). Related metrics: tma_bottleneck_cache_memory_latency, tma_l3_hit_latency", "ScaleUnit": "100%" }, { "BriefDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck", "DefaultMetricgroupName": "TopdownL2", - "MetricExpr": "topdown\\-mem\\-bound / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * slots", + "MetricExpr": "topdown\\-mem\\-bound / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * tma_info_thread_slots", "MetricGroup": "Backend;Default;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_memory_bound", "MetricThreshold": "tma_memory_bound > 0.2 & tma_backend_bound > 0.2", "MetricgroupNoGroup": "TopdownL2;Default", - "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck. Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two)", + "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck. Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two).", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to LFENCE Instructions", + "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to LFENCE Instructions.", "MetricConstraint": "NO_GROUP_EVENTS_NMI", "MetricExpr": "13 * MISC2_RETIRED.LFENCE / tma_info_thread_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_serializing_operation_group", "MetricName": "tma_memory_fence", - "MetricThreshold": "tma_memory_fence > 0.05 & tma_serializing_operation > 0.1 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_memory_fence > 0.05 & (tma_serializing_operation > 0.1 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of slots where the CPU was retiring memory operations , uops for memory load or store accesses", + "BriefDescription": "This metric represents fraction of slots where the CPU was retiring memory operations -- uops for memory load or store accesses.", "MetricExpr": "tma_light_operations * MEM_UOP_RETIRED.ANY / (tma_retiring * tma_info_thread_slots)", "MetricGroup": "Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group", "MetricName": "tma_memory_operations", @@ -1883,7 +1886,7 @@ "MetricExpr": "tma_branch_mispredicts / tma_bad_speculation * INT_MISC.CLEAR_RESTEER_CYCLES / tma_info_thread_clks", "MetricGroup": "BadSpec;BrMispredicts;BvMP;TopdownL4;tma_L4_group;tma_branch_resteers_group;tma_issueBM", "MetricName": "tma_mispredicts_resteers", - "MetricThreshold": "tma_mispredicts_resteers > 0.05 & tma_branch_resteers > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricThreshold": "tma_mispredicts_resteers > 0.05 & (tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))", "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Branch Misprediction at execution stage. Sample with: INT_MISC.CLEAR_RESTEER_CYCLES. Related metrics: tma_bottleneck_mispredictions, tma_branch_mispredicts, tma_info_bad_spec_branch_misprediction_cost", "ScaleUnit": "100%" }, @@ -1897,17 +1900,17 @@ "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates penalty in terms of percentage of([SKL+] injected blend uops out of all Uops Issued , the Count Domain; [ADL+] cycles)", + "BriefDescription": "This metric estimates penalty in terms of percentage of([SKL+] injected blend uops out of all Uops Issued -- the Count Domain; [ADL+] cycles)", "MetricExpr": "160 * ASSISTS.SSE_AVX_MIX / tma_info_thread_clks", "MetricGroup": "TopdownL5;tma_L5_group;tma_issueMV;tma_ports_utilized_0_group", "MetricName": "tma_mixing_vectors", "MetricThreshold": "tma_mixing_vectors > 0.05", - "PublicDescription": "This metric estimates penalty in terms of percentage of([SKL+] injected blend uops out of all Uops Issued , the Count Domain; [ADL+] cycles). Usually a Mixing_Vectors over 5% is worth investigating. Read more in Appendix B1 of the Optimizations Guide for this topic. Related metrics: tma_ms_switches", + "PublicDescription": "This metric estimates penalty in terms of percentage of([SKL+] injected blend uops out of all Uops Issued -- the Count Domain; [ADL+] cycles). Usually a Mixing_Vectors over 5% is worth investigating. Read more in Appendix B1 of the Optimizations Guide for this topic. Related metrics: tma_ms_switches", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to the Microcode Sequencer (MS) unit - see Microcode_Sequencer node for details", - "MetricExpr": "max(IDQ.MS_CYCLES_ANY, cpu@UOPS_RETIRED.MS\\,cmask\\=0x1@ / (UOPS_RETIRED.SLOTS / UOPS_ISSUED.ANY)) / tma_info_core_core_clks / 2", + "BriefDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to the Microcode Sequencer (MS) unit - see Microcode_Sequencer node for details.", + "MetricExpr": "max(IDQ.MS_CYCLES_ANY, cpu@UOPS_RETIRED.MS\\,cmask\\=1@ / (UOPS_RETIRED.SLOTS / UOPS_ISSUED.ANY)) / tma_info_core_core_clks / 2", "MetricGroup": "MicroSeq;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group", "MetricName": "tma_ms", "MetricThreshold": "tma_ms > 0.05 & tma_fetch_bandwidth > 0.2", @@ -1915,11 +1918,11 @@ }, { "BriefDescription": "This metric estimates the fraction of cycles when the CPU was stalled due to switches of uop delivery to the Microcode Sequencer (MS)", - "MetricExpr": "3 * cpu@UOPS_RETIRED.MS\\,cmask\\=0x1\\,edge\\=0x1@ / (UOPS_RETIRED.SLOTS / UOPS_ISSUED.ANY) / tma_info_thread_clks", + "MetricExpr": "3 * cpu@UOPS_RETIRED.MS\\,cmask\\=1\\,edge@ / (UOPS_RETIRED.SLOTS / UOPS_ISSUED.ANY) / tma_info_thread_clks", "MetricGroup": "FetchLat;MicroSeq;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueMC;tma_issueMS;tma_issueMV;tma_issueSO", "MetricName": "tma_ms_switches", - "MetricThreshold": "tma_ms_switches > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", - "PublicDescription": "This metric estimates the fraction of cycles when the CPU was stalled due to switches of uop delivery to the Microcode Sequencer (MS). Commonly used instructions are optimized for delivery by the DSB (decoded i-cache) or MITE (legacy instruction decode) pipelines. Certain operations cannot be handled natively by the execution pipeline; and must be performed by microcode (small programs injected into the execution stream). Switching to the MS too often can negatively impact performance. The MS is designated to deliver long uop flows required by CISC instructions like CPUID; or uncommon conditions like Floating Point Assists when dealing with Denormals. Sample with: FRONTEND_RETIRED.MS_FLOWS. Related metrics: tma_bottleneck_irregular_overhead, tma_clears_resteers, tma_l1_bound, tma_machine_clears, tma_microcode_sequencer, tma_mixing_vectors, tma_serializing_operation", + "MetricThreshold": "tma_ms_switches > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", + "PublicDescription": "This metric estimates the fraction of cycles when the CPU was stalled due to switches of uop delivery to the Microcode Sequencer (MS). Commonly used instructions are optimized for delivery by the DSB (decoded i-cache) or MITE (legacy instruction decode) pipelines. Certain operations cannot be handled natively by the execution pipeline; and must be performed by microcode (small programs injected into the execution stream). Switching to the MS too often can negatively impact performance. The MS is designated to deliver long uop flows required by CISC instructions like CPUID; or uncommon conditions like Floating Point Assists when dealing with Denormals. Sample with: IDQ.MS_SWITCHES. Related metrics: tma_bottleneck_irregular_overhead, tma_clears_resteers, tma_l1_bound, tma_machine_clears, tma_microcode_sequencer, tma_mixing_vectors, tma_serializing_operation", "ScaleUnit": "100%" }, { @@ -1928,7 +1931,7 @@ "MetricGroup": "Branches;BvBO;Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group", "MetricName": "tma_non_fused_branches", "MetricThreshold": "tma_non_fused_branches > 0.1 & tma_light_operations > 0.6", - "PublicDescription": "This metric represents fraction of slots where the CPU was retiring branch instructions that were not fused. Non-conditional branches like direct JMP or CALL would count here. Can be used to examine fusible conditional jumps that were not fused", + "PublicDescription": "This metric represents fraction of slots where the CPU was retiring branch instructions that were not fused. Non-conditional branches like direct JMP or CALL would count here. Can be used to examine fusible conditional jumps that were not fused.", "ScaleUnit": "100%" }, { @@ -1936,7 +1939,7 @@ "MetricExpr": "tma_light_operations * INST_RETIRED.NOP / (tma_retiring * tma_info_thread_slots)", "MetricGroup": "BvBO;Pipeline;TopdownL4;tma_L4_group;tma_other_light_ops_group", "MetricName": "tma_nop_instructions", - "MetricThreshold": "tma_nop_instructions > 0.1 & tma_other_light_ops > 0.3 & tma_light_operations > 0.6", + "MetricThreshold": "tma_nop_instructions > 0.1 & (tma_other_light_ops > 0.3 & tma_light_operations > 0.6)", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring NOP (no op) instructions. Compilers often use NOPs for certain address alignments - e.g. start address of a function or loop body. Sample with: INST_RETIRED.NOP", "ScaleUnit": "100%" }, @@ -1950,19 +1953,19 @@ "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates fraction of slots the CPU was stalled due to other cases of misprediction (non-retired x86 branches or other types)", + "BriefDescription": "This metric estimates fraction of slots the CPU was stalled due to other cases of misprediction (non-retired x86 branches or other types).", "MetricExpr": "max(tma_branch_mispredicts * (1 - BR_MISP_RETIRED.ALL_BRANCHES / (INT_MISC.CLEARS_COUNT - MACHINE_CLEARS.COUNT)), 0.0001)", "MetricGroup": "BrMispredicts;BvIO;TopdownL3;tma_L3_group;tma_branch_mispredicts_group", "MetricName": "tma_other_mispredicts", - "MetricThreshold": "tma_other_mispredicts > 0.05 & tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", + "MetricThreshold": "tma_other_mispredicts > 0.05 & (tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15)", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of slots the CPU has wasted due to Nukes (Machine Clears) not related to memory ordering", + "BriefDescription": "This metric represents fraction of slots the CPU has wasted due to Nukes (Machine Clears) not related to memory ordering.", "MetricExpr": "max(tma_machine_clears * (1 - MACHINE_CLEARS.MEMORY_ORDERING / MACHINE_CLEARS.COUNT), 0.0001)", "MetricGroup": "BvIO;Machine_Clears;TopdownL3;tma_L3_group;tma_machine_clears_group", "MetricName": "tma_other_nukes", - "MetricThreshold": "tma_other_nukes > 0.05 & tma_machine_clears > 0.1 & tma_bad_speculation > 0.15", + "MetricThreshold": "tma_other_nukes > 0.05 & (tma_machine_clears > 0.1 & tma_bad_speculation > 0.15)", "ScaleUnit": "100%" }, { @@ -1971,7 +1974,7 @@ "MetricGroup": "TopdownL5;tma_L5_group;tma_assists_group", "MetricName": "tma_page_faults", "MetricThreshold": "tma_page_faults > 0.05", - "PublicDescription": "This metric roughly estimates fraction of slots the CPU retired uops as a result of handing Page Faults. A Page Fault may apply on first application access to a memory page. Note operating system handling of page faults accounts for the majority of its cost", + "PublicDescription": "This metric roughly estimates fraction of slots the CPU retired uops as a result of handing Page Faults. A Page Fault may apply on first application access to a memory page. Note operating system handling of page faults accounts for the majority of its cost.", "ScaleUnit": "100%" }, { @@ -1980,7 +1983,7 @@ "MetricGroup": "Compute;TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P", "MetricName": "tma_port_0", "MetricThreshold": "tma_port_0 > 0.6", - "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 0 ([SNB+] ALU; [HSW+] ALU and 2nd branch). Sample with: UOPS_DISPATCHED.PORT_0. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_1, tma_port_6, tma_ports_utilized_2", + "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 0 ([SNB+] ALU; [HSW+] ALU and 2nd branch). Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%" }, { @@ -1989,7 +1992,7 @@ "MetricGroup": "TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P", "MetricName": "tma_port_1", "MetricThreshold": "tma_port_1 > 0.6", - "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 1 (ALU). Sample with: UOPS_DISPATCHED.PORT_1. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_6, tma_ports_utilized_2", + "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 1 (ALU). Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_5, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%" }, { @@ -1998,7 +2001,7 @@ "MetricGroup": "TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P", "MetricName": "tma_port_6", "MetricThreshold": "tma_port_6 > 0.6", - "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 6 ([HSW+] Primary Branch and simple ALU). Sample with: UOPS_DISPATCHED.PORT_1. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_ports_utilized_2", + "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 6 ([HSW+] Primary Branch and simple ALU). Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_ports_utilized_2", "ScaleUnit": "100%" }, { @@ -2006,8 +2009,8 @@ "MetricExpr": "((tma_ports_utilized_0 * tma_info_thread_clks + (EXE_ACTIVITY.1_PORTS_UTIL + tma_retiring * EXE_ACTIVITY.2_3_PORTS_UTIL)) / tma_info_thread_clks if ARITH.DIV_ACTIVE < CYCLE_ACTIVITY.STALLS_TOTAL - EXE_ACTIVITY.BOUND_ON_LOADS else (EXE_ACTIVITY.1_PORTS_UTIL + tma_retiring * EXE_ACTIVITY.2_3_PORTS_UTIL) / tma_info_thread_clks)", "MetricGroup": "PortsUtil;TopdownL3;tma_L3_group;tma_core_bound_group", "MetricName": "tma_ports_utilization", - "MetricThreshold": "tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", - "PublicDescription": "This metric estimates fraction of cycles the CPU performance was potentially limited due to Core computation issues (non divider-related). Two distinct categories can be attributed into this metric: (1) heavy data-dependency among contiguous instructions would manifest in this metric - such cases are often referred to as low Instruction Level Parallelism (ILP). (2) Contention on some hardware execution unit other than Divider. For example; when there are too many multiply operations", + "MetricThreshold": "tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)", + "PublicDescription": "This metric estimates fraction of cycles the CPU performance was potentially limited due to Core computation issues (non divider-related). Two distinct categories can be attributed into this metric: (1) heavy data-dependency among contiguous instructions would manifest in this metric - such cases are often referred to as low Instruction Level Parallelism (ILP). (2) Contention on some hardware execution unit other than Divider. For example; when there are too many multiply operations.", "ScaleUnit": "100%" }, { @@ -2015,8 +2018,8 @@ "MetricExpr": "(EXE_ACTIVITY.EXE_BOUND_0_PORTS + max(RS.EMPTY_RESOURCE - RESOURCE_STALLS.SCOREBOARD, 0)) / tma_info_thread_clks * (CYCLE_ACTIVITY.STALLS_TOTAL - EXE_ACTIVITY.BOUND_ON_LOADS) / tma_info_thread_clks", "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group", "MetricName": "tma_ports_utilized_0", - "MetricThreshold": "tma_ports_utilized_0 > 0.2 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", - "PublicDescription": "This metric represents fraction of cycles CPU executed no uops on any execution port (Logical Processor cycles since ICL, Physical Core cycles otherwise). Long-latency instructions like divides may contribute to this metric", + "MetricThreshold": "tma_ports_utilized_0 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric represents fraction of cycles CPU executed no uops on any execution port (Logical Processor cycles since ICL, Physical Core cycles otherwise). Long-latency instructions like divides may contribute to this metric.", "ScaleUnit": "100%" }, { @@ -2024,7 +2027,7 @@ "MetricExpr": "EXE_ACTIVITY.1_PORTS_UTIL / tma_info_thread_clks", "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_issueL1;tma_ports_utilization_group", "MetricName": "tma_ports_utilized_1", - "MetricThreshold": "tma_ports_utilized_1 > 0.2 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_ports_utilized_1 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", "PublicDescription": "This metric represents fraction of cycles where the CPU executed total of 1 uop per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise). This can be due to heavy data-dependency among software instructions; or over oversubscribing a particular hardware resource. In some other cases with high 1_Port_Utilized and L1_Bound; this metric can point to L1 data-cache latency bottleneck that may not necessarily manifest with complete execution starvation (due to the short L1 latency e.g. walking a linked list) - looking at the assembly can be helpful. Sample with: EXE_ACTIVITY.1_PORTS_UTIL. Related metrics: tma_l1_bound", "ScaleUnit": "100%" }, @@ -2034,8 +2037,8 @@ "MetricExpr": "EXE_ACTIVITY.2_PORTS_UTIL / tma_info_thread_clks", "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_issue2P;tma_ports_utilization_group", "MetricName": "tma_ports_utilized_2", - "MetricThreshold": "tma_ports_utilized_2 > 0.15 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", - "PublicDescription": "This metric represents fraction of cycles CPU executed total of 2 uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise). Loop Vectorization -most compilers feature auto-Vectorization options today- reduces pressure on the execution ports as multiple elements are calculated with same uop. Sample with: EXE_ACTIVITY.2_PORTS_UTIL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_6", + "MetricThreshold": "tma_ports_utilized_2 > 0.15 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric represents fraction of cycles CPU executed total of 2 uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise). Loop Vectorization -most compilers feature auto-Vectorization options today- reduces pressure on the execution ports as multiple elements are calculated with same uop. Sample with: EXE_ACTIVITY.2_PORTS_UTIL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_port_6", "ScaleUnit": "100%" }, { @@ -2044,32 +2047,32 @@ "MetricExpr": "UOPS_EXECUTED.CYCLES_GE_3 / tma_info_thread_clks", "MetricGroup": "BvCB;PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group", "MetricName": "tma_ports_utilized_3m", - "MetricThreshold": "tma_ports_utilized_3m > 0.4 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_ports_utilized_3m > 0.4 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", "PublicDescription": "This metric represents fraction of cycles CPU executed total of 3 or more uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise). Sample with: UOPS_EXECUTED.CYCLES_GE_3", "ScaleUnit": "100%" }, { "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from remote cache in other sockets including synchronizations issues", - "MetricExpr": "((170 * tma_info_system_core_frequency - 37 * tma_info_system_core_frequency) * MEM_LOAD_L3_MISS_RETIRED.REMOTE_HITM + (170 * tma_info_system_core_frequency - 37 * tma_info_system_core_frequency) * MEM_LOAD_L3_MISS_RETIRED.REMOTE_FWD) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks", + "MetricExpr": "(133 * tma_info_system_core_frequency * MEM_LOAD_L3_MISS_RETIRED.REMOTE_HITM + 133 * tma_info_system_core_frequency * MEM_LOAD_L3_MISS_RETIRED.REMOTE_FWD) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks", "MetricGroup": "Offcore;Server;Snoop;TopdownL5;tma_L5_group;tma_issueSyncxn;tma_mem_latency_group", "MetricName": "tma_remote_cache", - "MetricThreshold": "tma_remote_cache > 0.05 & tma_mem_latency > 0.1 & tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", - "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from remote cache in other sockets including synchronizations issues. This is caused often due to non-optimal NUMA allocations. Sample with: MEM_LOAD_L3_MISS_RETIRED.REMOTE_HITM, MEM_LOAD_L3_MISS_RETIRED.REMOTE_FWD. Related metrics: tma_bottleneck_memory_synchronization, tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_machine_clears", + "MetricThreshold": "tma_remote_cache > 0.05 & (tma_mem_latency > 0.1 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))", + "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from remote cache in other sockets including synchronizations issues. This is caused often due to non-optimal NUMA allocations. #link to NUMA article. Sample with: MEM_LOAD_L3_MISS_RETIRED.REMOTE_HITM_PS;MEM_LOAD_L3_MISS_RETIRED.REMOTE_FWD_PS. Related metrics: tma_bottleneck_memory_synchronization, tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_machine_clears", "ScaleUnit": "100%" }, { "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from remote memory", - "MetricExpr": "(190 * tma_info_system_core_frequency - 37 * tma_info_system_core_frequency) * MEM_LOAD_L3_MISS_RETIRED.REMOTE_DRAM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks", + "MetricExpr": "153 * tma_info_system_core_frequency * MEM_LOAD_L3_MISS_RETIRED.REMOTE_DRAM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks", "MetricGroup": "Server;Snoop;TopdownL5;tma_L5_group;tma_mem_latency_group", "MetricName": "tma_remote_mem", - "MetricThreshold": "tma_remote_mem > 0.1 & tma_mem_latency > 0.1 & tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", - "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from remote memory. This is caused often due to non-optimal NUMA allocations. Sample with: MEM_LOAD_L3_MISS_RETIRED.REMOTE_DRAM", + "MetricThreshold": "tma_remote_mem > 0.1 & (tma_mem_latency > 0.1 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))", + "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from remote memory. This is caused often due to non-optimal NUMA allocations. #link to NUMA article. Sample with: MEM_LOAD_L3_MISS_RETIRED.REMOTE_DRAM_PS", "ScaleUnit": "100%" }, { "BriefDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired", "DefaultMetricgroupName": "TopdownL1", - "MetricExpr": "topdown\\-retiring / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * slots", + "MetricExpr": "topdown\\-retiring / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * tma_info_thread_slots", "MetricGroup": "BvUW;Default;TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_retiring", "MetricThreshold": "tma_retiring > 0.7 | tma_heavy_operations > 0.1", @@ -2082,7 +2085,7 @@ "MetricExpr": "RESOURCE_STALLS.SCOREBOARD / tma_info_thread_clks + tma_c02_wait", "MetricGroup": "BvIO;PortsUtil;TopdownL3;tma_L3_group;tma_core_bound_group;tma_issueSO", "MetricName": "tma_serializing_operation", - "MetricThreshold": "tma_serializing_operation > 0.1 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_serializing_operation > 0.1 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)", "PublicDescription": "This metric represents fraction of cycles the CPU issue-pipeline was stalled due to serializing operations. Instructions like CPUID; WRMSR or LFENCE serialize the out-of-order execution which may limit performance. Sample with: RESOURCE_STALLS.SCOREBOARD. Related metrics: tma_ms_switches", "ScaleUnit": "100%" }, @@ -2091,8 +2094,8 @@ "MetricExpr": "tma_light_operations * INT_VEC_RETIRED.SHUFFLES / (tma_retiring * tma_info_thread_slots)", "MetricGroup": "HPC;Pipeline;TopdownL4;tma_L4_group;tma_other_light_ops_group", "MetricName": "tma_shuffles_256b", - "MetricThreshold": "tma_shuffles_256b > 0.1 & tma_other_light_ops > 0.3 & tma_light_operations > 0.6", - "PublicDescription": "This metric represents fraction of slots where the CPU was retiring Shuffle operations of 256-bit vector size (FP or Integer). Shuffles may incur slow cross \"vector lane\" data transfers", + "MetricThreshold": "tma_shuffles_256b > 0.1 & (tma_other_light_ops > 0.3 & tma_light_operations > 0.6)", + "PublicDescription": "This metric represents fraction of slots where the CPU was retiring Shuffle operations of 256-bit vector size (FP or Integer). Shuffles may incur slow cross \"vector lane\" data transfers.", "ScaleUnit": "100%" }, { @@ -2101,7 +2104,7 @@ "MetricExpr": "CPU_CLK_UNHALTED.PAUSE / tma_info_thread_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_serializing_operation_group", "MetricName": "tma_slow_pause", - "MetricThreshold": "tma_slow_pause > 0.05 & tma_serializing_operation > 0.1 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_slow_pause > 0.05 & (tma_serializing_operation > 0.1 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to PAUSE Instructions. Sample with: CPU_CLK_UNHALTED.PAUSE_INST", "ScaleUnit": "100%" }, @@ -2111,7 +2114,7 @@ "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group", "MetricName": "tma_split_loads", "MetricThreshold": "tma_split_loads > 0.3", - "PublicDescription": "This metric estimates fraction of cycles handling memory load split accesses - load that cross 64-byte cache line boundary. Sample with: MEM_INST_RETIRED.SPLIT_LOADS", + "PublicDescription": "This metric estimates fraction of cycles handling memory load split accesses - load that cross 64-byte cache line boundary. Sample with: MEM_INST_RETIRED.SPLIT_LOADS_PS", "ScaleUnit": "100%" }, { @@ -2119,8 +2122,8 @@ "MetricExpr": "MEM_INST_RETIRED.SPLIT_STORES / tma_info_core_core_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_issueSpSt;tma_store_bound_group", "MetricName": "tma_split_stores", - "MetricThreshold": "tma_split_stores > 0.2 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", - "PublicDescription": "This metric represents rate of split store accesses. Consider aligning your data to the 64-byte cache line granularity. Sample with: MEM_INST_RETIRED.SPLIT_STORES", + "MetricThreshold": "tma_split_stores > 0.2 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric represents rate of split store accesses. Consider aligning your data to the 64-byte cache line granularity. Sample with: MEM_INST_RETIRED.SPLIT_STORES_PS. Related metrics: tma_port_4", "ScaleUnit": "100%" }, { @@ -2128,7 +2131,7 @@ "MetricExpr": "(XQ.FULL_CYCLES + L1D_PEND_MISS.L2_STALLS) / tma_info_thread_clks", "MetricGroup": "BvMB;MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_issueBW;tma_l3_bound_group", "MetricName": "tma_sq_full", - "MetricThreshold": "tma_sq_full > 0.3 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_sq_full > 0.3 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", "PublicDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors). Related metrics: tma_bottleneck_cache_memory_bandwidth, tma_fb_full, tma_info_system_dram_bw_use, tma_mem_bandwidth", "ScaleUnit": "100%" }, @@ -2137,8 +2140,8 @@ "MetricExpr": "EXE_ACTIVITY.BOUND_ON_STORES / tma_info_thread_clks", "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_store_bound", - "MetricThreshold": "tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", - "PublicDescription": "This metric estimates how often CPU was stalled due to RFO store memory accesses; RFO store issue a read-for-ownership request before the write. Even though store accesses do not typically stall out-of-order CPUs; there are few cases where stores can lead to actual stalls. This metric will be flagged should RFO stores be a bottleneck. Sample with: MEM_INST_RETIRED.ALL_STORES", + "MetricThreshold": "tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", + "PublicDescription": "This metric estimates how often CPU was stalled due to RFO store memory accesses; RFO store issue a read-for-ownership request before the write. Even though store accesses do not typically stall out-of-order CPUs; there are few cases where stores can lead to actual stalls. This metric will be flagged should RFO stores be a bottleneck. Sample with: MEM_INST_RETIRED.ALL_STORES_PS", "ScaleUnit": "100%" }, { @@ -2146,8 +2149,8 @@ "MetricExpr": "13 * LD_BLOCKS.STORE_FORWARD / tma_info_thread_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group", "MetricName": "tma_store_fwd_blk", - "MetricThreshold": "tma_store_fwd_blk > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", - "PublicDescription": "This metric roughly estimates fraction of cycles when the memory subsystem had loads blocked since they could not forward data from earlier (in program order) overlapping stores. To streamline memory operations in the pipeline; a load can avoid waiting for memory if a prior in-flight store is writing the data that the load wants to read (store forwarding process). However; in some cases the load may be blocked for a significant time pending the store forward. For example; when the prior store is writing a smaller region than the load is reading", + "MetricThreshold": "tma_store_fwd_blk > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric roughly estimates fraction of cycles when the memory subsystem had loads blocked since they could not forward data from earlier (in program order) overlapping stores. To streamline memory operations in the pipeline; a load can avoid waiting for memory if a prior in-flight store is writing the data that the load wants to read (store forwarding process). However; in some cases the load may be blocked for a significant time pending the store forward. For example; when the prior store is writing a smaller region than the load is reading.", "ScaleUnit": "100%" }, { @@ -2155,8 +2158,8 @@ "MetricExpr": "(MEM_STORE_RETIRED.L2_HIT * 10 * (1 - MEM_INST_RETIRED.LOCK_LOADS / MEM_INST_RETIRED.ALL_STORES) + (1 - MEM_INST_RETIRED.LOCK_LOADS / MEM_INST_RETIRED.ALL_STORES) * min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO)) / tma_info_thread_clks", "MetricGroup": "BvML;LockCont;MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_issueSL;tma_store_bound_group", "MetricName": "tma_store_latency", - "MetricThreshold": "tma_store_latency > 0.1 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", - "PublicDescription": "This metric estimates fraction of cycles the CPU spent handling L1D store misses. Store accesses usually less impact out-of-order core performance; however; holding resources for longer time can lead into undesired implications (e.g. contention on L1D fill-buffer entries - see FB_Full). Related metrics: tma_branch_resteers, tma_fb_full, tma_l3_hit_latency, tma_lock_latency", + "MetricThreshold": "tma_store_latency > 0.1 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric estimates fraction of cycles the CPU spent handling L1D store misses. Store accesses usually less impact out-of-order core performance; however; holding resources for longer time can lead into undesired implications (e.g. contention on L1D fill-buffer entries - see FB_Full). Related metrics: tma_fb_full, tma_lock_latency", "ScaleUnit": "100%" }, { @@ -2173,7 +2176,7 @@ "MetricExpr": "tma_dtlb_store - tma_store_stlb_miss", "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_store_group", "MetricName": "tma_store_stlb_hit", - "MetricThreshold": "tma_store_stlb_hit > 0.05 & tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_store_stlb_hit > 0.05 & (tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))", "ScaleUnit": "100%" }, { @@ -2181,31 +2184,31 @@ "MetricExpr": "DTLB_STORE_MISSES.WALK_ACTIVE / tma_info_core_core_clks", "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_store_group", "MetricName": "tma_store_stlb_miss", - "MetricThreshold": "tma_store_stlb_miss > 0.05 & tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_store_stlb_miss > 0.05 & (tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 1 GB pages for data store accesses", + "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 1 GB pages for data store accesses.", "MetricExpr": "tma_store_stlb_miss * DTLB_STORE_MISSES.WALK_COMPLETED_1G / (DTLB_STORE_MISSES.WALK_COMPLETED_4K + DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M + DTLB_STORE_MISSES.WALK_COMPLETED_1G)", "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_store_stlb_miss_group", "MetricName": "tma_store_stlb_miss_1g", - "MetricThreshold": "tma_store_stlb_miss_1g > 0.05 & tma_store_stlb_miss > 0.05 & tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_store_stlb_miss_1g > 0.05 & (tma_store_stlb_miss > 0.05 & (tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))))", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 2 or 4 MB pages for data store accesses", + "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 2 or 4 MB pages for data store accesses.", "MetricExpr": "tma_store_stlb_miss * DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M / (DTLB_STORE_MISSES.WALK_COMPLETED_4K + DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M + DTLB_STORE_MISSES.WALK_COMPLETED_1G)", "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_store_stlb_miss_group", "MetricName": "tma_store_stlb_miss_2m", - "MetricThreshold": "tma_store_stlb_miss_2m > 0.05 & tma_store_stlb_miss > 0.05 & tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_store_stlb_miss_2m > 0.05 & (tma_store_stlb_miss > 0.05 & (tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))))", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 4 KB pages for data store accesses", + "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 4 KB pages for data store accesses.", "MetricExpr": "tma_store_stlb_miss * DTLB_STORE_MISSES.WALK_COMPLETED_4K / (DTLB_STORE_MISSES.WALK_COMPLETED_4K + DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M + DTLB_STORE_MISSES.WALK_COMPLETED_1G)", "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_store_stlb_miss_group", "MetricName": "tma_store_stlb_miss_4k", - "MetricThreshold": "tma_store_stlb_miss_4k > 0.05 & tma_store_stlb_miss > 0.05 & tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_store_stlb_miss_4k > 0.05 & (tma_store_stlb_miss > 0.05 & (tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))))", "ScaleUnit": "100%" }, { @@ -2213,7 +2216,7 @@ "MetricExpr": "9 * OCR.STREAMING_WR.ANY_RESPONSE / tma_info_thread_clks", "MetricGroup": "MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_issueSmSt;tma_store_bound_group", "MetricName": "tma_streaming_stores", - "MetricThreshold": "tma_streaming_stores > 0.2 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_streaming_stores > 0.2 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", "PublicDescription": "This metric estimates how often CPU was stalled due to Streaming store memory accesses; Streaming store optimize out a read request required by RFO stores. Even though store accesses do not typically stall out-of-order CPUs; there are few cases where stores can lead to actual stalls. This metric will be flagged should Streaming stores be a bottleneck. Sample with: OCR.STREAMING_WR.ANY_RESPONSE. Related metrics: tma_fb_full", "ScaleUnit": "100%" }, @@ -2222,7 +2225,7 @@ "MetricExpr": "INT_MISC.UNKNOWN_BRANCH_CYCLES / tma_info_thread_clks", "MetricGroup": "BigFootprint;BvBC;FetchLat;TopdownL4;tma_L4_group;tma_branch_resteers_group", "MetricName": "tma_unknown_branches", - "MetricThreshold": "tma_unknown_branches > 0.05 & tma_branch_resteers > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricThreshold": "tma_unknown_branches > 0.05 & (tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))", "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to new branch address clears. These are fetched branches the Branch Prediction Unit was unable to recognize (e.g. first time the branch is fetched or hitting BTB capacity limit) hence called Unknown Branches. Sample with: FRONTEND_RETIRED.UNKNOWN_BRANCH", "ScaleUnit": "100%" }, @@ -2231,8 +2234,8 @@ "MetricExpr": "tma_retiring * UOPS_EXECUTED.X87 / UOPS_EXECUTED.THREAD", "MetricGroup": "Compute;TopdownL4;tma_L4_group;tma_fp_arith_group", "MetricName": "tma_x87_use", - "MetricThreshold": "tma_x87_use > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6", - "PublicDescription": "This metric serves as an approximation of legacy x87 usage. It accounts for instructions beyond X87 FP arithmetic operations; hence may be used as a thermometer to avoid X87 high usage and preferably upgrade to modern ISA. See Tip under Tuning Hint", + "MetricThreshold": "tma_x87_use > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6)", + "PublicDescription": "This metric serves as an approximation of legacy x87 usage. It accounts for instructions beyond X87 FP arithmetic operations; hence may be used as a thermometer to avoid X87 high usage and preferably upgrade to modern ISA. See Tip under Tuning Hint.", "ScaleUnit": "100%" }, { diff --git a/tools/perf/pmu-events/arch/x86/emeraldrapids/floating-point.json b/tools/perf/pmu-events/arch/x86/emeraldrapids/floating-point.json index bc475e163227..8c9207750c82 100644 --- a/tools/perf/pmu-events/arch/x86/emeraldrapids/floating-point.json +++ b/tools/perf/pmu-events/arch/x86/emeraldrapids/floating-point.json @@ -5,6 +5,7 @@ "CounterMask": "1", "EventCode": "0xb0", "EventName": "ARITH.FPDIV_ACTIVE", + "PublicDescription": "ARITH.FPDIV_ACTIVE Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x1" }, @@ -13,7 +14,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc1", "EventName": "ASSISTS.FP", - "PublicDescription": "Counts all microcode Floating Point assists.", + "PublicDescription": "Counts all microcode Floating Point assists. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x2" }, @@ -22,6 +23,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc1", "EventName": "ASSISTS.SSE_AVX_MIX", + "PublicDescription": "ASSISTS.SSE_AVX_MIX Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x10" }, @@ -30,6 +32,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xb3", "EventName": "FP_ARITH_DISPATCHED.PORT_0", + "PublicDescription": "FP_ARITH_DISPATCHED.PORT_0 [This event is alias to FP_ARITH_DISPATCHED.V0] Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x1" }, @@ -38,6 +41,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xb3", "EventName": "FP_ARITH_DISPATCHED.PORT_1", + "PublicDescription": "FP_ARITH_DISPATCHED.PORT_1 [This event is alias to FP_ARITH_DISPATCHED.V1] Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x2" }, @@ -46,6 +50,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xb3", "EventName": "FP_ARITH_DISPATCHED.PORT_5", + "PublicDescription": "FP_ARITH_DISPATCHED.PORT_5 [This event is alias to FP_ARITH_DISPATCHED.V2] Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x4" }, @@ -54,6 +59,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xb3", "EventName": "FP_ARITH_DISPATCHED.V0", + "PublicDescription": "FP_ARITH_DISPATCHED.V0 [This event is alias to FP_ARITH_DISPATCHED.PORT_0] Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x1" }, @@ -62,6 +68,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xb3", "EventName": "FP_ARITH_DISPATCHED.V1", + "PublicDescription": "FP_ARITH_DISPATCHED.V1 [This event is alias to FP_ARITH_DISPATCHED.PORT_1] Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x2" }, @@ -70,6 +77,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xb3", "EventName": "FP_ARITH_DISPATCHED.V2", + "PublicDescription": "FP_ARITH_DISPATCHED.V2 [This event is alias to FP_ARITH_DISPATCHED.PORT_5] Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x4" }, @@ -78,7 +86,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc7", "EventName": "FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE", - "PublicDescription": "Number of SSE/AVX computational 128-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 2 computation operations, one for each element. Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.", + "PublicDescription": "Number of SSE/AVX computational 128-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 2 computation operations, one for each element. Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x4" }, @@ -87,7 +95,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc7", "EventName": "FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE", - "PublicDescription": "Number of SSE/AVX computational 128-bit packed single precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 4 computation operations, one for each element. Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT RSQRT RCP DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.", + "PublicDescription": "Number of SSE/AVX computational 128-bit packed single precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 4 computation operations, one for each element. Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT RSQRT RCP DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x8" }, @@ -96,7 +104,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc7", "EventName": "FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE", - "PublicDescription": "Number of SSE/AVX computational 256-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 4 computation operations, one for each element. Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.", + "PublicDescription": "Number of SSE/AVX computational 256-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 4 computation operations, one for each element. Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x10" }, @@ -105,7 +113,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc7", "EventName": "FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE", - "PublicDescription": "Number of SSE/AVX computational 256-bit packed single precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 8 computation operations, one for each element. Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT RSQRT RCP DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.", + "PublicDescription": "Number of SSE/AVX computational 256-bit packed single precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 8 computation operations, one for each element. Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT RSQRT RCP DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x20" }, @@ -114,7 +122,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc7", "EventName": "FP_ARITH_INST_RETIRED.4_FLOPS", - "PublicDescription": "Number of SSE/AVX computational 128-bit packed single precision and 256-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 2 or/and 4 computation operations, one for each element. Applies to SSE* and AVX* packed single precision floating-point and packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX RCP14 RSQRT14 SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.", + "PublicDescription": "Number of SSE/AVX computational 128-bit packed single precision and 256-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 2 or/and 4 computation operations, one for each element. Applies to SSE* and AVX* packed single precision floating-point and packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX RCP14 RSQRT14 SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x18" }, @@ -123,7 +131,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc7", "EventName": "FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE", - "PublicDescription": "Number of SSE/AVX computational 512-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 8 computation operations, one for each element. Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT RSQRT14 RCP14 FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.", + "PublicDescription": "Number of SSE/AVX computational 512-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 8 computation operations, one for each element. Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT RSQRT14 RCP14 FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x40" }, @@ -132,7 +140,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc7", "EventName": "FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE", - "PublicDescription": "Number of SSE/AVX computational 512-bit packed single precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 16 computation operations, one for each element. Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT RSQRT14 RCP14 FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.", + "PublicDescription": "Number of SSE/AVX computational 512-bit packed single precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 16 computation operations, one for each element. Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT RSQRT14 RCP14 FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x80" }, @@ -141,7 +149,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc7", "EventName": "FP_ARITH_INST_RETIRED.8_FLOPS", - "PublicDescription": "Number of SSE/AVX computational 256-bit packed single precision and 512-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 8 computation operations, one for each element. Applies to SSE* and AVX* packed single precision and double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT RSQRT RSQRT14 RCP RCP14 DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.", + "PublicDescription": "Number of SSE/AVX computational 256-bit packed single precision and 512-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 8 computation operations, one for each element. Applies to SSE* and AVX* packed single precision and double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT RSQRT RSQRT14 RCP RCP14 DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x60" }, @@ -150,7 +158,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc7", "EventName": "FP_ARITH_INST_RETIRED.SCALAR", - "PublicDescription": "Number of SSE/AVX computational scalar single precision and double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 1 computational operation. Applies to SSE* and AVX* scalar single precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT RSQRT RCP FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.", + "PublicDescription": "Number of SSE/AVX computational scalar single precision and double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 1 computational operation. Applies to SSE* and AVX* scalar single precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT RSQRT RCP FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x3" }, @@ -159,7 +167,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc7", "EventName": "FP_ARITH_INST_RETIRED.SCALAR_DOUBLE", - "PublicDescription": "Number of SSE/AVX computational scalar double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 1 computational operation. Applies to SSE* and AVX* scalar double precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.", + "PublicDescription": "Number of SSE/AVX computational scalar double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 1 computational operation. Applies to SSE* and AVX* scalar double precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -168,7 +176,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc7", "EventName": "FP_ARITH_INST_RETIRED.SCALAR_SINGLE", - "PublicDescription": "Number of SSE/AVX computational scalar single precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 1 computational operation. Applies to SSE* and AVX* scalar single precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT RSQRT RCP FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.", + "PublicDescription": "Number of SSE/AVX computational scalar single precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 1 computational operation. Applies to SSE* and AVX* scalar single precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT RSQRT RCP FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x2" }, @@ -177,7 +185,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc7", "EventName": "FP_ARITH_INST_RETIRED.VECTOR", - "PublicDescription": "Number of any Vector retired FP arithmetic instructions. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.", + "PublicDescription": "Number of any Vector retired FP arithmetic instructions. The DAZ and FTZ flags in the MXCSR register need to be set when using these events. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0xfc" }, @@ -186,6 +194,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xcf", "EventName": "FP_ARITH_INST_RETIRED2.128B_PACKED_HALF", + "PublicDescription": "FP_ARITH_INST_RETIRED2.128B_PACKED_HALF Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x4" }, @@ -194,6 +203,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xcf", "EventName": "FP_ARITH_INST_RETIRED2.256B_PACKED_HALF", + "PublicDescription": "FP_ARITH_INST_RETIRED2.256B_PACKED_HALF Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x8" }, @@ -202,6 +212,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xcf", "EventName": "FP_ARITH_INST_RETIRED2.512B_PACKED_HALF", + "PublicDescription": "FP_ARITH_INST_RETIRED2.512B_PACKED_HALF Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x10" }, @@ -210,6 +221,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xcf", "EventName": "FP_ARITH_INST_RETIRED2.COMPLEX_SCALAR_HALF", + "PublicDescription": "FP_ARITH_INST_RETIRED2.COMPLEX_SCALAR_HALF Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x2" }, @@ -218,7 +230,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xcf", "EventName": "FP_ARITH_INST_RETIRED2.SCALAR", - "PublicDescription": "FP_ARITH_INST_RETIRED2.SCALAR", + "PublicDescription": "FP_ARITH_INST_RETIRED2.SCALAR Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x3" }, @@ -227,6 +239,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xcf", "EventName": "FP_ARITH_INST_RETIRED2.SCALAR_HALF", + "PublicDescription": "FP_ARITH_INST_RETIRED2.SCALAR_HALF Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -235,7 +248,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xcf", "EventName": "FP_ARITH_INST_RETIRED2.VECTOR", - "PublicDescription": "FP_ARITH_INST_RETIRED2.VECTOR", + "PublicDescription": "FP_ARITH_INST_RETIRED2.VECTOR Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1c" } diff --git a/tools/perf/pmu-events/arch/x86/emeraldrapids/frontend.json b/tools/perf/pmu-events/arch/x86/emeraldrapids/frontend.json index bf68493d4509..9fe9d62b867a 100644 --- a/tools/perf/pmu-events/arch/x86/emeraldrapids/frontend.json +++ b/tools/perf/pmu-events/arch/x86/emeraldrapids/frontend.json @@ -4,7 +4,7 @@ "Counter": "0,1,2,3", "EventCode": "0x60", "EventName": "BACLEARS.ANY", - "PublicDescription": "Number of times the front-end is resteered when it finds a branch instruction in a fetch line. This is called Unknown Branch which occurs for the first time a branch instruction is fetched or when the branch is not tracked by the BPU (Branch Prediction Unit) anymore.", + "PublicDescription": "Number of times the front-end is resteered when it finds a branch instruction in a fetch line. This is called Unknown Branch which occurs for the first time a branch instruction is fetched or when the branch is not tracked by the BPU (Branch Prediction Unit) anymore. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -13,7 +13,7 @@ "Counter": "0,1,2,3", "EventCode": "0x87", "EventName": "DECODE.LCP", - "PublicDescription": "Counts cycles that the Instruction Length decoder (ILD) stalls occurred due to dynamically changing prefix length of the decoded instruction (by operand size prefix instruction 0x66, address size prefix instruction 0x67 or REX.W for Intel64). Count is proportional to the number of prefixes in a 16B-line. This may result in a three-cycle penalty for each LCP (Length changing prefix) in a 16-byte chunk.", + "PublicDescription": "Counts cycles that the Instruction Length decoder (ILD) stalls occurred due to dynamically changing prefix length of the decoded instruction (by operand size prefix instruction 0x66, address size prefix instruction 0x67 or REX.W for Intel64). Count is proportional to the number of prefixes in a 16B-line. This may result in a three-cycle penalty for each LCP (Length changing prefix) in a 16-byte chunk. Available PDIST counters: 0", "SampleAfterValue": "500009", "UMask": "0x1" }, @@ -22,6 +22,7 @@ "Counter": "0,1,2,3", "EventCode": "0x87", "EventName": "DECODE.MS_BUSY", + "PublicDescription": "Cycles the Microcode Sequencer is busy. Available PDIST counters: 0", "SampleAfterValue": "500009", "UMask": "0x2" }, @@ -30,7 +31,7 @@ "Counter": "0,1,2,3", "EventCode": "0x61", "EventName": "DSB2MITE_SWITCHES.PENALTY_CYCLES", - "PublicDescription": "Decode Stream Buffer (DSB) is a Uop-cache that holds translations of previously fetched instructions that were decoded by the legacy x86 decode pipeline (MITE). This event counts fetch penalty cycles when a transition occurs from DSB to MITE.", + "PublicDescription": "Decode Stream Buffer (DSB) is a Uop-cache that holds translations of previously fetched instructions that were decoded by the legacy x86 decode pipeline (MITE). This event counts fetch penalty cycles when a transition occurs from DSB to MITE. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x2" }, @@ -41,7 +42,7 @@ "EventName": "FRONTEND_RETIRED.ANY_DSB_MISS", "MSRIndex": "0x3F7", "MSRValue": "0x1", - "PublicDescription": "Counts retired Instructions that experienced DSB (Decode stream buffer i.e. the decoded instruction-cache) miss.", + "PublicDescription": "Counts retired Instructions that experienced DSB (Decode stream buffer i.e. the decoded instruction-cache) miss. Available PDIST counters: 0", "SampleAfterValue": "100007", "UMask": "0x1" }, @@ -52,7 +53,7 @@ "EventName": "FRONTEND_RETIRED.DSB_MISS", "MSRIndex": "0x3F7", "MSRValue": "0x11", - "PublicDescription": "Number of retired Instructions that experienced a critical DSB (Decode stream buffer i.e. the decoded instruction-cache) miss. Critical means stalls were exposed to the back-end as a result of the DSB miss.", + "PublicDescription": "Number of retired Instructions that experienced a critical DSB (Decode stream buffer i.e. the decoded instruction-cache) miss. Critical means stalls were exposed to the back-end as a result of the DSB miss. Available PDIST counters: 0", "SampleAfterValue": "100007", "UMask": "0x1" }, @@ -63,7 +64,7 @@ "EventName": "FRONTEND_RETIRED.ITLB_MISS", "MSRIndex": "0x3F7", "MSRValue": "0x14", - "PublicDescription": "Counts retired Instructions that experienced iTLB (Instruction TLB) true miss.", + "PublicDescription": "Counts retired Instructions that experienced iTLB (Instruction TLB) true miss. Available PDIST counters: 0", "SampleAfterValue": "100007", "UMask": "0x1" }, @@ -74,7 +75,7 @@ "EventName": "FRONTEND_RETIRED.L1I_MISS", "MSRIndex": "0x3F7", "MSRValue": "0x12", - "PublicDescription": "Counts retired Instructions who experienced Instruction L1 Cache true miss.", + "PublicDescription": "Counts retired Instructions who experienced Instruction L1 Cache true miss. Available PDIST counters: 0", "SampleAfterValue": "100007", "UMask": "0x1" }, @@ -85,7 +86,7 @@ "EventName": "FRONTEND_RETIRED.L2_MISS", "MSRIndex": "0x3F7", "MSRValue": "0x13", - "PublicDescription": "Counts retired Instructions who experienced Instruction L2 Cache true miss.", + "PublicDescription": "Counts retired Instructions who experienced Instruction L2 Cache true miss. Available PDIST counters: 0", "SampleAfterValue": "100007", "UMask": "0x1" }, @@ -96,7 +97,7 @@ "EventName": "FRONTEND_RETIRED.LATENCY_GE_1", "MSRIndex": "0x3F7", "MSRValue": "0x600106", - "PublicDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of at least 1 cycle which was not interrupted by a back-end stall.", + "PublicDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of at least 1 cycle which was not interrupted by a back-end stall. Available PDIST counters: 0", "SampleAfterValue": "100007", "UMask": "0x1" }, @@ -107,7 +108,7 @@ "EventName": "FRONTEND_RETIRED.LATENCY_GE_128", "MSRIndex": "0x3F7", "MSRValue": "0x608006", - "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 128 cycles which was not interrupted by a back-end stall.", + "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 128 cycles which was not interrupted by a back-end stall. Available PDIST counters: 0", "SampleAfterValue": "100007", "UMask": "0x1" }, @@ -118,7 +119,7 @@ "EventName": "FRONTEND_RETIRED.LATENCY_GE_16", "MSRIndex": "0x3F7", "MSRValue": "0x601006", - "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 16 cycles. During this period the front-end delivered no uops.", + "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 16 cycles. During this period the front-end delivered no uops. Available PDIST counters: 0", "SampleAfterValue": "100007", "UMask": "0x1" }, @@ -129,7 +130,7 @@ "EventName": "FRONTEND_RETIRED.LATENCY_GE_2", "MSRIndex": "0x3F7", "MSRValue": "0x600206", - "PublicDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of at least 2 cycles which was not interrupted by a back-end stall.", + "PublicDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of at least 2 cycles which was not interrupted by a back-end stall. Available PDIST counters: 0", "SampleAfterValue": "100007", "UMask": "0x1" }, @@ -140,7 +141,7 @@ "EventName": "FRONTEND_RETIRED.LATENCY_GE_256", "MSRIndex": "0x3F7", "MSRValue": "0x610006", - "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 256 cycles which was not interrupted by a back-end stall.", + "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 256 cycles which was not interrupted by a back-end stall. Available PDIST counters: 0", "SampleAfterValue": "100007", "UMask": "0x1" }, @@ -151,7 +152,7 @@ "EventName": "FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1", "MSRIndex": "0x3F7", "MSRValue": "0x100206", - "PublicDescription": "Counts retired instructions that are delivered to the back-end after the front-end had at least 1 bubble-slot for a period of 2 cycles. A bubble-slot is an empty issue-pipeline slot while there was no RAT stall.", + "PublicDescription": "Counts retired instructions that are delivered to the back-end after the front-end had at least 1 bubble-slot for a period of 2 cycles. A bubble-slot is an empty issue-pipeline slot while there was no RAT stall. Available PDIST counters: 0", "SampleAfterValue": "100007", "UMask": "0x1" }, @@ -162,7 +163,7 @@ "EventName": "FRONTEND_RETIRED.LATENCY_GE_32", "MSRIndex": "0x3F7", "MSRValue": "0x602006", - "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 32 cycles. During this period the front-end delivered no uops.", + "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 32 cycles. During this period the front-end delivered no uops. Available PDIST counters: 0", "SampleAfterValue": "100007", "UMask": "0x1" }, @@ -173,7 +174,7 @@ "EventName": "FRONTEND_RETIRED.LATENCY_GE_4", "MSRIndex": "0x3F7", "MSRValue": "0x600406", - "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 4 cycles which was not interrupted by a back-end stall.", + "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 4 cycles which was not interrupted by a back-end stall. Available PDIST counters: 0", "SampleAfterValue": "100007", "UMask": "0x1" }, @@ -184,7 +185,7 @@ "EventName": "FRONTEND_RETIRED.LATENCY_GE_512", "MSRIndex": "0x3F7", "MSRValue": "0x620006", - "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 512 cycles which was not interrupted by a back-end stall.", + "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 512 cycles which was not interrupted by a back-end stall. Available PDIST counters: 0", "SampleAfterValue": "100007", "UMask": "0x1" }, @@ -195,7 +196,7 @@ "EventName": "FRONTEND_RETIRED.LATENCY_GE_64", "MSRIndex": "0x3F7", "MSRValue": "0x604006", - "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 64 cycles which was not interrupted by a back-end stall.", + "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 64 cycles which was not interrupted by a back-end stall. Available PDIST counters: 0", "SampleAfterValue": "100007", "UMask": "0x1" }, @@ -206,7 +207,7 @@ "EventName": "FRONTEND_RETIRED.LATENCY_GE_8", "MSRIndex": "0x3F7", "MSRValue": "0x600806", - "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 8 cycles. During this period the front-end delivered no uops.", + "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 8 cycles. During this period the front-end delivered no uops. Available PDIST counters: 0", "SampleAfterValue": "100007", "UMask": "0x1" }, @@ -217,6 +218,7 @@ "EventName": "FRONTEND_RETIRED.MS_FLOWS", "MSRIndex": "0x3F7", "MSRValue": "0x8", + "PublicDescription": "FRONTEND_RETIRED.MS_FLOWS Available PDIST counters: 0", "SampleAfterValue": "100007", "UMask": "0x1" }, @@ -227,7 +229,7 @@ "EventName": "FRONTEND_RETIRED.STLB_MISS", "MSRIndex": "0x3F7", "MSRValue": "0x15", - "PublicDescription": "Counts retired Instructions that experienced STLB (2nd level TLB) true miss.", + "PublicDescription": "Counts retired Instructions that experienced STLB (2nd level TLB) true miss. Available PDIST counters: 0", "SampleAfterValue": "100007", "UMask": "0x1" }, @@ -238,6 +240,7 @@ "EventName": "FRONTEND_RETIRED.UNKNOWN_BRANCH", "MSRIndex": "0x3F7", "MSRValue": "0x17", + "PublicDescription": "FRONTEND_RETIRED.UNKNOWN_BRANCH Available PDIST counters: 0", "SampleAfterValue": "100007", "UMask": "0x1" }, @@ -246,7 +249,7 @@ "Counter": "0,1,2,3", "EventCode": "0x80", "EventName": "ICACHE_DATA.STALLS", - "PublicDescription": "Counts cycles where a code line fetch is stalled due to an L1 instruction cache miss. The decode pipeline works at a 32 Byte granularity.", + "PublicDescription": "Counts cycles where a code line fetch is stalled due to an L1 instruction cache miss. The decode pipeline works at a 32 Byte granularity. Available PDIST counters: 0", "SampleAfterValue": "500009", "UMask": "0x4" }, @@ -257,6 +260,7 @@ "EdgeDetect": "1", "EventCode": "0x80", "EventName": "ICACHE_DATA.STALL_PERIODS", + "PublicDescription": "ICACHE_DATA.STALL_PERIODS Available PDIST counters: 0", "SampleAfterValue": "500009", "UMask": "0x4" }, @@ -265,7 +269,7 @@ "Counter": "0,1,2,3", "EventCode": "0x83", "EventName": "ICACHE_TAG.STALLS", - "PublicDescription": "Counts cycles where a code fetch is stalled due to L1 instruction cache tag miss.", + "PublicDescription": "Counts cycles where a code fetch is stalled due to L1 instruction cache tag miss. Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0x4" }, @@ -275,7 +279,7 @@ "CounterMask": "1", "EventCode": "0x79", "EventName": "IDQ.DSB_CYCLES_ANY", - "PublicDescription": "Counts the number of cycles uops were delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path.", + "PublicDescription": "Counts the number of cycles uops were delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path. Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x8" }, @@ -285,7 +289,7 @@ "CounterMask": "6", "EventCode": "0x79", "EventName": "IDQ.DSB_CYCLES_OK", - "PublicDescription": "Counts the number of cycles where optimal number of uops was delivered to the Instruction Decode Queue (IDQ) from the DSB (Decode Stream Buffer) path. Count includes uops that may 'bypass' the IDQ.", + "PublicDescription": "Counts the number of cycles where optimal number of uops was delivered to the Instruction Decode Queue (IDQ) from the DSB (Decode Stream Buffer) path. Count includes uops that may 'bypass' the IDQ. Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x8" }, @@ -294,7 +298,7 @@ "Counter": "0,1,2,3", "EventCode": "0x79", "EventName": "IDQ.DSB_UOPS", - "PublicDescription": "Counts the number of uops delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path.", + "PublicDescription": "Counts the number of uops delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path. Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x8" }, @@ -304,7 +308,7 @@ "CounterMask": "1", "EventCode": "0x79", "EventName": "IDQ.MITE_CYCLES_ANY", - "PublicDescription": "Counts the number of cycles uops were delivered to the Instruction Decode Queue (IDQ) from the MITE (legacy decode pipeline) path. During these cycles uops are not being delivered from the Decode Stream Buffer (DSB).", + "PublicDescription": "Counts the number of cycles uops were delivered to the Instruction Decode Queue (IDQ) from the MITE (legacy decode pipeline) path. During these cycles uops are not being delivered from the Decode Stream Buffer (DSB). Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x4" }, @@ -314,7 +318,7 @@ "CounterMask": "6", "EventCode": "0x79", "EventName": "IDQ.MITE_CYCLES_OK", - "PublicDescription": "Counts the number of cycles where optimal number of uops was delivered to the Instruction Decode Queue (IDQ) from the MITE (legacy decode pipeline) path. During these cycles uops are not being delivered from the Decode Stream Buffer (DSB).", + "PublicDescription": "Counts the number of cycles where optimal number of uops was delivered to the Instruction Decode Queue (IDQ) from the MITE (legacy decode pipeline) path. During these cycles uops are not being delivered from the Decode Stream Buffer (DSB). Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x4" }, @@ -323,7 +327,7 @@ "Counter": "0,1,2,3", "EventCode": "0x79", "EventName": "IDQ.MITE_UOPS", - "PublicDescription": "Counts the number of uops delivered to Instruction Decode Queue (IDQ) from the MITE path. This also means that uops are not being delivered from the Decode Stream Buffer (DSB).", + "PublicDescription": "Counts the number of uops delivered to Instruction Decode Queue (IDQ) from the MITE path. This also means that uops are not being delivered from the Decode Stream Buffer (DSB). Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x4" }, @@ -333,7 +337,7 @@ "CounterMask": "1", "EventCode": "0x79", "EventName": "IDQ.MS_CYCLES_ANY", - "PublicDescription": "Counts cycles during which uops are being delivered to Instruction Decode Queue (IDQ) while the Microcode Sequencer (MS) is busy. Uops maybe initiated by Decode Stream Buffer (DSB) or MITE.", + "PublicDescription": "Counts cycles during which uops are being delivered to Instruction Decode Queue (IDQ) while the Microcode Sequencer (MS) is busy. Uops maybe initiated by Decode Stream Buffer (DSB) or MITE. Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x20" }, @@ -344,7 +348,7 @@ "EdgeDetect": "1", "EventCode": "0x79", "EventName": "IDQ.MS_SWITCHES", - "PublicDescription": "Number of switches from DSB (Decode Stream Buffer) or MITE (legacy decode pipeline) to the Microcode Sequencer.", + "PublicDescription": "Number of switches from DSB (Decode Stream Buffer) or MITE (legacy decode pipeline) to the Microcode Sequencer. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x20" }, @@ -353,7 +357,7 @@ "Counter": "0,1,2,3", "EventCode": "0x79", "EventName": "IDQ.MS_UOPS", - "PublicDescription": "Counts the total number of uops delivered by the Microcode Sequencer (MS).", + "PublicDescription": "Counts the total number of uops delivered by the Microcode Sequencer (MS). Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x20" }, @@ -362,7 +366,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0x9c", "EventName": "IDQ_BUBBLES.CORE", - "PublicDescription": "Counts the number of uops not delivered to by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle. [This event is alias to IDQ_UOPS_NOT_DELIVERED.CORE]", + "PublicDescription": "Counts the number of uops not delivered to by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle. [This event is alias to IDQ_UOPS_NOT_DELIVERED.CORE] Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x1" }, @@ -372,7 +376,7 @@ "CounterMask": "6", "EventCode": "0x9c", "EventName": "IDQ_BUBBLES.CYCLES_0_UOPS_DELIV.CORE", - "PublicDescription": "Counts the number of cycles when no uops were delivered by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle. [This event is alias to IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE]", + "PublicDescription": "Counts the number of cycles when no uops were delivered by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle. [This event is alias to IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE] Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x1" }, @@ -383,7 +387,7 @@ "EventCode": "0x9c", "EventName": "IDQ_BUBBLES.CYCLES_FE_WAS_OK", "Invert": "1", - "PublicDescription": "Counts the number of cycles when the optimal number of uops were delivered by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle. [This event is alias to IDQ_UOPS_NOT_DELIVERED.CYCLES_FE_WAS_OK]", + "PublicDescription": "Counts the number of cycles when the optimal number of uops were delivered by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle. [This event is alias to IDQ_UOPS_NOT_DELIVERED.CYCLES_FE_WAS_OK] Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x1" }, @@ -392,7 +396,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0x9c", "EventName": "IDQ_UOPS_NOT_DELIVERED.CORE", - "PublicDescription": "Counts the number of uops not delivered to by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle. [This event is alias to IDQ_BUBBLES.CORE]", + "PublicDescription": "Counts the number of uops not delivered to by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle. [This event is alias to IDQ_BUBBLES.CORE] Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x1" }, @@ -402,7 +406,7 @@ "CounterMask": "6", "EventCode": "0x9c", "EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE", - "PublicDescription": "Counts the number of cycles when no uops were delivered by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle. [This event is alias to IDQ_BUBBLES.CYCLES_0_UOPS_DELIV.CORE]", + "PublicDescription": "Counts the number of cycles when no uops were delivered by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle. [This event is alias to IDQ_BUBBLES.CYCLES_0_UOPS_DELIV.CORE] Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x1" }, @@ -413,7 +417,7 @@ "EventCode": "0x9c", "EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_FE_WAS_OK", "Invert": "1", - "PublicDescription": "Counts the number of cycles when the optimal number of uops were delivered by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle. [This event is alias to IDQ_BUBBLES.CYCLES_FE_WAS_OK]", + "PublicDescription": "Counts the number of cycles when the optimal number of uops were delivered by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle. [This event is alias to IDQ_BUBBLES.CYCLES_FE_WAS_OK] Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x1" } diff --git a/tools/perf/pmu-events/arch/x86/emeraldrapids/memory.json b/tools/perf/pmu-events/arch/x86/emeraldrapids/memory.json index 41d4120d4dae..7c3f9b76d367 100644 --- a/tools/perf/pmu-events/arch/x86/emeraldrapids/memory.json +++ b/tools/perf/pmu-events/arch/x86/emeraldrapids/memory.json @@ -5,6 +5,7 @@ "CounterMask": "6", "EventCode": "0xa3", "EventName": "CYCLE_ACTIVITY.STALLS_L3_MISS", + "PublicDescription": "Execution stalls while L3 cache miss demand load is outstanding. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x6" }, @@ -13,7 +14,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc3", "EventName": "MACHINE_CLEARS.MEMORY_ORDERING", - "PublicDescription": "Counts the number of Machine Clears detected dye to memory ordering. Memory Ordering Machine Clears may apply when a memory read may not conform to the memory ordering rules of the x86 architecture", + "PublicDescription": "Counts the number of Machine Clears detected dye to memory ordering. Memory Ordering Machine Clears may apply when a memory read may not conform to the memory ordering rules of the x86 architecture Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x2" }, @@ -23,6 +24,7 @@ "CounterMask": "2", "EventCode": "0x47", "EventName": "MEMORY_ACTIVITY.CYCLES_L1D_MISS", + "PublicDescription": "Cycles while L1 cache miss demand load is outstanding. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x2" }, @@ -32,6 +34,7 @@ "CounterMask": "3", "EventCode": "0x47", "EventName": "MEMORY_ACTIVITY.STALLS_L1D_MISS", + "PublicDescription": "Execution stalls while L1 cache miss demand load is outstanding. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x3" }, @@ -41,7 +44,7 @@ "CounterMask": "5", "EventCode": "0x47", "EventName": "MEMORY_ACTIVITY.STALLS_L2_MISS", - "PublicDescription": "Execution stalls while L2 cache miss demand cacheable load request is outstanding (will not count for uncacheable demand requests e.g. bus lock).", + "PublicDescription": "Execution stalls while L2 cache miss demand cacheable load request is outstanding (will not count for uncacheable demand requests e.g. bus lock). Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x5" }, @@ -51,7 +54,7 @@ "CounterMask": "9", "EventCode": "0x47", "EventName": "MEMORY_ACTIVITY.STALLS_L3_MISS", - "PublicDescription": "Execution stalls while L3 cache miss demand cacheable load request is outstanding (will not count for uncacheable demand requests e.g. bus lock).", + "PublicDescription": "Execution stalls while L3 cache miss demand cacheable load request is outstanding (will not count for uncacheable demand requests e.g. bus lock). Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x9" }, @@ -169,17 +172,62 @@ "Data_LA": "1", "EventCode": "0xcd", "EventName": "MEM_TRANS_RETIRED.STORE_SAMPLE", - "PublicDescription": "Counts Retired memory accesses with at least 1 store operation. This PEBS event is the precisely-distributed (PDist) trigger covering all stores uops for sampling by the PEBS Store Latency Facility. The facility is described in Intel SDM Volume 3 section 19.9.8", + "PublicDescription": "Counts Retired memory accesses with at least 1 store operation. This PEBS event is the precisely-distributed (PDist) trigger covering all stores uops for sampling by the PEBS Store Latency Facility. The facility is described in Intel SDM Volume 3 section 19.9.8 Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x2" }, { + "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were supplied by DRAM.", + "Counter": "0,1,2,3", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.DEMAND_CODE_RD.DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x73C000004", + "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were supplied by DRAM. Available PDIST counters: 0", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were not supplied by the local socket's L1, L2, or L3 caches.", "Counter": "0,1,2,3", "EventCode": "0x2A,0x2B", "EventName": "OCR.DEMAND_CODE_RD.L3_MISS", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x3FBFC00004", + "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were not supplied by the local socket's L1, L2, or L3 caches. Available PDIST counters: 0", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were supplied by DRAM attached to this socket, unless in Sub NUMA Cluster(SNC) Mode. In SNC Mode counts only those DRAM accesses that are controlled by the close SNC Cluster.", + "Counter": "0,1,2,3", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.DEMAND_CODE_RD.LOCAL_DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x104000004", + "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were supplied by DRAM attached to this socket, unless in Sub NUMA Cluster(SNC) Mode. In SNC Mode counts only those DRAM accesses that are controlled by the close SNC Cluster. Available PDIST counters: 0", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were supplied by DRAM on a distant memory controller of this socket when the system is in SNC (sub-NUMA cluster) mode.", + "Counter": "0,1,2,3", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.DEMAND_CODE_RD.SNC_DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x708000004", + "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were supplied by DRAM on a distant memory controller of this socket when the system is in SNC (sub-NUMA cluster) mode. Available PDIST counters: 0", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts demand data reads that were supplied by DRAM.", + "Counter": "0,1,2,3", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.DEMAND_DATA_RD.DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x73C000001", + "PublicDescription": "Counts demand data reads that were supplied by DRAM. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -190,6 +238,51 @@ "EventName": "OCR.DEMAND_DATA_RD.L3_MISS", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x3FBFC00001", + "PublicDescription": "Counts demand data reads that were not supplied by the local socket's L1, L2, or L3 caches. Available PDIST counters: 0", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts demand data reads that were supplied by DRAM attached to this socket, unless in Sub NUMA Cluster(SNC) Mode. In SNC Mode counts only those DRAM accesses that are controlled by the close SNC Cluster.", + "Counter": "0,1,2,3", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.DEMAND_DATA_RD.LOCAL_DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x104000001", + "PublicDescription": "Counts demand data reads that were supplied by DRAM attached to this socket, unless in Sub NUMA Cluster(SNC) Mode. In SNC Mode counts only those DRAM accesses that are controlled by the close SNC Cluster. Available PDIST counters: 0", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts demand data reads that were supplied by DRAM attached to another socket.", + "Counter": "0,1,2,3", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.DEMAND_DATA_RD.REMOTE_DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x730000001", + "PublicDescription": "Counts demand data reads that were supplied by DRAM attached to another socket. Available PDIST counters: 0", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts demand data reads that were supplied by DRAM on a distant memory controller of this socket when the system is in SNC (sub-NUMA cluster) mode.", + "Counter": "0,1,2,3", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.DEMAND_DATA_RD.SNC_DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x708000001", + "PublicDescription": "Counts demand data reads that were supplied by DRAM on a distant memory controller of this socket when the system is in SNC (sub-NUMA cluster) mode. Available PDIST counters: 0", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts demand reads for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that were supplied by DRAM.", + "Counter": "0,1,2,3", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.DEMAND_RFO.DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x73C000002", + "PublicDescription": "Counts demand reads for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that were supplied by DRAM. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -200,6 +293,29 @@ "EventName": "OCR.DEMAND_RFO.L3_MISS", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x3F3FC00002", + "PublicDescription": "Counts demand reads for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that were not supplied by the local socket's L1, L2, or L3 caches. Available PDIST counters: 0", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts demand reads for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that were supplied by DRAM attached to this socket, unless in Sub NUMA Cluster(SNC) Mode. In SNC Mode counts only those DRAM accesses that are controlled by the close SNC Cluster.", + "Counter": "0,1,2,3", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.DEMAND_RFO.LOCAL_DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x104000002", + "PublicDescription": "Counts demand reads for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that were supplied by DRAM attached to this socket, unless in Sub NUMA Cluster(SNC) Mode. In SNC Mode counts only those DRAM accesses that are controlled by the close SNC Cluster. Available PDIST counters: 0", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts demand reads for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that were supplied by DRAM on a distant memory controller of this socket when the system is in SNC (sub-NUMA cluster) mode.", + "Counter": "0,1,2,3", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.DEMAND_RFO.SNC_DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x708000002", + "PublicDescription": "Counts demand reads for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that were supplied by DRAM on a distant memory controller of this socket when the system is in SNC (sub-NUMA cluster) mode. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -210,6 +326,7 @@ "EventName": "OCR.HWPF_L3.L3_MISS", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x94002380", + "PublicDescription": "Counts hardware prefetches to the L3 only that missed the local socket's L1, L2, and L3 caches. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -220,6 +337,18 @@ "EventName": "OCR.HWPF_L3.L3_MISS_LOCAL", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x84002380", + "PublicDescription": "Counts hardware prefetches to the L3 only that were not supplied by the local socket's L1, L2, or L3 caches and the cacheline is homed locally. Available PDIST counters: 0", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by DRAM.", + "Counter": "0,1,2,3", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.READS_TO_CORE.DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x73C004477", + "PublicDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by DRAM. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -230,6 +359,7 @@ "EventName": "OCR.READS_TO_CORE.L3_MISS", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x3F3FC04477", + "PublicDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were not supplied by the local socket's L1, L2, or L3 caches. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -240,6 +370,7 @@ "EventName": "OCR.READS_TO_CORE.L3_MISS_LOCAL", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x3F04C04477", + "PublicDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were not supplied by the local socket's L1, L2, or L3 caches and the cacheline is homed locally. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -250,6 +381,62 @@ "EventName": "OCR.READS_TO_CORE.L3_MISS_LOCAL_SOCKET", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x70CC04477", + "PublicDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that missed the L3 Cache and were supplied by the local socket (DRAM or PMM), whether or not in Sub NUMA Cluster(SNC) Mode. In SNC Mode counts PMM or DRAM accesses that are controlled by the close or distant SNC Cluster. It does not count misses to the L3 which go to Local CXL Type 2 Memory or Local Non DRAM. Available PDIST counters: 0", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by DRAM attached to this socket, unless in Sub NUMA Cluster(SNC) Mode. In SNC Mode counts only those DRAM accesses that are controlled by the close SNC Cluster.", + "Counter": "0,1,2,3", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.READS_TO_CORE.LOCAL_DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x104004477", + "PublicDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by DRAM attached to this socket, unless in Sub NUMA Cluster(SNC) Mode. In SNC Mode counts only those DRAM accesses that are controlled by the close SNC Cluster. Available PDIST counters: 0", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by DRAM attached to this socket, whether or not in Sub NUMA Cluster(SNC) Mode. In SNC Mode counts DRAM accesses that are controlled by the close or distant SNC Cluster.", + "Counter": "0,1,2,3", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.READS_TO_CORE.LOCAL_SOCKET_DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x70C004477", + "PublicDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by DRAM attached to this socket, whether or not in Sub NUMA Cluster(SNC) Mode. In SNC Mode counts DRAM accesses that are controlled by the close or distant SNC Cluster. Available PDIST counters: 0", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by DRAM attached to another socket.", + "Counter": "0,1,2,3", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.READS_TO_CORE.REMOTE_DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x730004477", + "PublicDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by DRAM attached to another socket. Available PDIST counters: 0", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by DRAM or PMM attached to another socket.", + "Counter": "0,1,2,3", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.READS_TO_CORE.REMOTE_MEMORY", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x733004477", + "PublicDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by DRAM or PMM attached to another socket. Available PDIST counters: 0", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by DRAM on a distant memory controller of this socket when the system is in SNC (sub-NUMA cluster) mode.", + "Counter": "0,1,2,3", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.READS_TO_CORE.SNC_DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x708004477", + "PublicDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by DRAM on a distant memory controller of this socket when the system is in SNC (sub-NUMA cluster) mode. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -260,6 +447,7 @@ "EventName": "OCR.STREAMING_WR.L3_MISS", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x94000800", + "PublicDescription": "Counts streaming stores that missed the local socket's L1, L2, and L3 caches. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -270,6 +458,18 @@ "EventName": "OCR.STREAMING_WR.L3_MISS_LOCAL", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x84000800", + "PublicDescription": "Counts streaming stores that were not supplied by the local socket's L1, L2, or L3 caches and the cacheline is homed locally. Available PDIST counters: 0", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts Demand RFOs, ItoM's, PREFECTHW's, Hardware RFO Prefetches to the L1/L2 and Streaming stores that likely resulted in a store to Memory (DRAM or PMM)", + "Counter": "0,1,2,3", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.WRITE_ESTIMATE.MEMORY", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0xFBFF80822", + "PublicDescription": "Counts Demand RFOs, ItoM's, PREFECTHW's, Hardware RFO Prefetches to the L1/L2 and Streaming stores that likely resulted in a store to Memory (DRAM or PMM) Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -278,6 +478,7 @@ "Counter": "0,1,2,3", "EventCode": "0x21", "EventName": "OFFCORE_REQUESTS.L3_MISS_DEMAND_DATA_RD", + "PublicDescription": "Counts demand data read requests that miss the L3 cache. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x10" }, @@ -286,7 +487,7 @@ "Counter": "0,1,2,3", "EventCode": "0x20", "EventName": "OFFCORE_REQUESTS_OUTSTANDING.L3_MISS_DEMAND_DATA_RD", - "PublicDescription": "For every cycle, increments by the number of demand data read requests pending that are known to have missed the L3 cache. Note that this does not capture all elapsed cycles while requests are outstanding - only cycles from when the requests were known by the requesting core to have missed the L3 cache.", + "PublicDescription": "For every cycle, increments by the number of demand data read requests pending that are known to have missed the L3 cache. Note that this does not capture all elapsed cycles while requests are outstanding - only cycles from when the requests were known by the requesting core to have missed the L3 cache. Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x10" }, @@ -295,7 +496,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc9", "EventName": "RTM_RETIRED.ABORTED", - "PublicDescription": "Counts the number of times RTM abort was triggered.", + "PublicDescription": "Counts the number of times RTM abort was triggered. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x4" }, @@ -304,7 +505,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc9", "EventName": "RTM_RETIRED.ABORTED_EVENTS", - "PublicDescription": "Counts the number of times an RTM execution aborted due to none of the previous 3 categories (e.g. interrupt).", + "PublicDescription": "Counts the number of times an RTM execution aborted due to none of the previous 3 categories (e.g. interrupt). Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x80" }, @@ -313,7 +514,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc9", "EventName": "RTM_RETIRED.ABORTED_MEM", - "PublicDescription": "Counts the number of times an RTM execution aborted due to various memory events (e.g. read/write capacity and conflicts).", + "PublicDescription": "Counts the number of times an RTM execution aborted due to various memory events (e.g. read/write capacity and conflicts). Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x8" }, @@ -322,7 +523,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc9", "EventName": "RTM_RETIRED.ABORTED_MEMTYPE", - "PublicDescription": "Counts the number of times an RTM execution aborted due to incompatible memory type.", + "PublicDescription": "Counts the number of times an RTM execution aborted due to incompatible memory type. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x40" }, @@ -331,7 +532,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc9", "EventName": "RTM_RETIRED.ABORTED_UNFRIENDLY", - "PublicDescription": "Counts the number of times an RTM execution aborted due to HLE-unfriendly instructions.", + "PublicDescription": "Counts the number of times an RTM execution aborted due to HLE-unfriendly instructions. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x20" }, @@ -340,7 +541,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc9", "EventName": "RTM_RETIRED.COMMIT", - "PublicDescription": "Counts the number of times RTM commit succeeded.", + "PublicDescription": "Counts the number of times RTM commit succeeded. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x2" }, @@ -349,7 +550,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc9", "EventName": "RTM_RETIRED.START", - "PublicDescription": "Counts the number of times we entered an RTM region. Does not count nested transactions.", + "PublicDescription": "Counts the number of times we entered an RTM region. Does not count nested transactions. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -358,7 +559,7 @@ "Counter": "0,1,2,3", "EventCode": "0x54", "EventName": "TX_MEM.ABORT_CAPACITY_READ", - "PublicDescription": "Speculatively counts the number of Transactional Synchronization Extensions (TSX) aborts due to a data capacity limitation for transactional reads", + "PublicDescription": "Speculatively counts the number of Transactional Synchronization Extensions (TSX) aborts due to a data capacity limitation for transactional reads Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x80" }, @@ -367,7 +568,7 @@ "Counter": "0,1,2,3", "EventCode": "0x54", "EventName": "TX_MEM.ABORT_CAPACITY_WRITE", - "PublicDescription": "Speculatively counts the number of Transactional Synchronization Extensions (TSX) aborts due to a data capacity limitation for transactional writes.", + "PublicDescription": "Speculatively counts the number of Transactional Synchronization Extensions (TSX) aborts due to a data capacity limitation for transactional writes. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x2" }, @@ -376,7 +577,7 @@ "Counter": "0,1,2,3", "EventCode": "0x54", "EventName": "TX_MEM.ABORT_CONFLICT", - "PublicDescription": "Counts the number of times a TSX line had a cache conflict.", + "PublicDescription": "Counts the number of times a TSX line had a cache conflict. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" } diff --git a/tools/perf/pmu-events/arch/x86/emeraldrapids/other.json b/tools/perf/pmu-events/arch/x86/emeraldrapids/other.json index c424facf1b95..a58d65556609 100644 --- a/tools/perf/pmu-events/arch/x86/emeraldrapids/other.json +++ b/tools/perf/pmu-events/arch/x86/emeraldrapids/other.json @@ -4,354 +4,28 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc1", "EventName": "ASSISTS.PAGE_FAULT", + "PublicDescription": "ASSISTS.PAGE_FAULT Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x8" }, { - "BriefDescription": "Counts the cycles where the AMX (Advance Matrix Extension) unit is busy performing an operation.", - "Counter": "0,1,2,3,4,5,6,7", - "EventCode": "0xb7", - "EventName": "EXE.AMX_BUSY", - "SampleAfterValue": "2000003", - "UMask": "0x2" - }, - { - "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that have any type of response.", - "Counter": "0,1,2,3", - "EventCode": "0x2A,0x2B", - "EventName": "OCR.DEMAND_CODE_RD.ANY_RESPONSE", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x10004", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were supplied by DRAM.", - "Counter": "0,1,2,3", - "EventCode": "0x2A,0x2B", - "EventName": "OCR.DEMAND_CODE_RD.DRAM", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x73C000004", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were supplied by DRAM attached to this socket, unless in Sub NUMA Cluster(SNC) Mode. In SNC Mode counts only those DRAM accesses that are controlled by the close SNC Cluster.", - "Counter": "0,1,2,3", - "EventCode": "0x2A,0x2B", - "EventName": "OCR.DEMAND_CODE_RD.LOCAL_DRAM", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x104000004", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were supplied by DRAM on a distant memory controller of this socket when the system is in SNC (sub-NUMA cluster) mode.", - "Counter": "0,1,2,3", - "EventCode": "0x2A,0x2B", - "EventName": "OCR.DEMAND_CODE_RD.SNC_DRAM", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x708000004", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts demand data reads that have any type of response.", - "Counter": "0,1,2,3", - "EventCode": "0x2A,0x2B", - "EventName": "OCR.DEMAND_DATA_RD.ANY_RESPONSE", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x10001", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts demand data reads that were supplied by DRAM.", - "Counter": "0,1,2,3", - "EventCode": "0x2A,0x2B", - "EventName": "OCR.DEMAND_DATA_RD.DRAM", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x73C000001", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts demand data reads that were supplied by DRAM attached to this socket, unless in Sub NUMA Cluster(SNC) Mode. In SNC Mode counts only those DRAM accesses that are controlled by the close SNC Cluster.", - "Counter": "0,1,2,3", - "EventCode": "0x2A,0x2B", - "EventName": "OCR.DEMAND_DATA_RD.LOCAL_DRAM", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x104000001", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts demand data reads that were supplied by DRAM attached to another socket.", - "Counter": "0,1,2,3", - "EventCode": "0x2A,0x2B", - "EventName": "OCR.DEMAND_DATA_RD.REMOTE_DRAM", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x730000001", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts demand data reads that were supplied by DRAM on a distant memory controller of this socket when the system is in SNC (sub-NUMA cluster) mode.", - "Counter": "0,1,2,3", - "EventCode": "0x2A,0x2B", - "EventName": "OCR.DEMAND_DATA_RD.SNC_DRAM", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x708000001", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts demand reads for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that have any type of response.", - "Counter": "0,1,2,3", - "EventCode": "0x2A,0x2B", - "EventName": "OCR.DEMAND_RFO.ANY_RESPONSE", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x3F3FFC0002", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts demand reads for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that were supplied by DRAM.", - "Counter": "0,1,2,3", - "EventCode": "0x2A,0x2B", - "EventName": "OCR.DEMAND_RFO.DRAM", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x73C000002", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts demand reads for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that were supplied by DRAM attached to this socket, unless in Sub NUMA Cluster(SNC) Mode. In SNC Mode counts only those DRAM accesses that are controlled by the close SNC Cluster.", - "Counter": "0,1,2,3", - "EventCode": "0x2A,0x2B", - "EventName": "OCR.DEMAND_RFO.LOCAL_DRAM", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x104000002", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts demand reads for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that were supplied by DRAM on a distant memory controller of this socket when the system is in SNC (sub-NUMA cluster) mode.", - "Counter": "0,1,2,3", - "EventCode": "0x2A,0x2B", - "EventName": "OCR.DEMAND_RFO.SNC_DRAM", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x708000002", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts data load hardware prefetch requests to the L1 data cache that have any type of response.", - "Counter": "0,1,2,3", - "EventCode": "0x2A,0x2B", - "EventName": "OCR.HWPF_L1D.ANY_RESPONSE", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x10400", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts hardware prefetches (which bring data to L2) that have any type of response.", - "Counter": "0,1,2,3", - "EventCode": "0x2A,0x2B", - "EventName": "OCR.HWPF_L2.ANY_RESPONSE", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x10070", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts hardware prefetches to the L3 only that have any type of response.", - "Counter": "0,1,2,3", - "EventCode": "0x2A,0x2B", - "EventName": "OCR.HWPF_L3.ANY_RESPONSE", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x12380", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts hardware prefetches to the L3 only that were not supplied by the local socket's L1, L2, or L3 caches and the cacheline was homed in a remote socket.", - "Counter": "0,1,2,3", - "EventCode": "0x2A,0x2B", - "EventName": "OCR.HWPF_L3.REMOTE", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x90002380", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts writebacks of modified cachelines and streaming stores that have any type of response.", - "Counter": "0,1,2,3", - "EventCode": "0x2A,0x2B", - "EventName": "OCR.MODIFIED_WRITE.ANY_RESPONSE", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x10808", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that have any type of response.", - "Counter": "0,1,2,3", - "EventCode": "0x2A,0x2B", - "EventName": "OCR.READS_TO_CORE.ANY_RESPONSE", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x3F3FFC4477", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by DRAM.", - "Counter": "0,1,2,3", - "EventCode": "0x2A,0x2B", - "EventName": "OCR.READS_TO_CORE.DRAM", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x73C004477", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by DRAM attached to this socket, unless in Sub NUMA Cluster(SNC) Mode. In SNC Mode counts only those DRAM accesses that are controlled by the close SNC Cluster.", - "Counter": "0,1,2,3", - "EventCode": "0x2A,0x2B", - "EventName": "OCR.READS_TO_CORE.LOCAL_DRAM", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x104004477", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by DRAM attached to this socket, whether or not in Sub NUMA Cluster(SNC) Mode. In SNC Mode counts DRAM accesses that are controlled by the close or distant SNC Cluster.", - "Counter": "0,1,2,3", - "EventCode": "0x2A,0x2B", - "EventName": "OCR.READS_TO_CORE.LOCAL_SOCKET_DRAM", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x70C004477", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were not supplied by the local socket's L1, L2, or L3 caches and were supplied by a remote socket.", - "Counter": "0,1,2,3", - "EventCode": "0x2A,0x2B", - "EventName": "OCR.READS_TO_CORE.REMOTE", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x3F33004477", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by DRAM attached to another socket.", - "Counter": "0,1,2,3", - "EventCode": "0x2A,0x2B", - "EventName": "OCR.READS_TO_CORE.REMOTE_DRAM", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x730004477", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by DRAM or PMM attached to another socket.", - "Counter": "0,1,2,3", - "EventCode": "0x2A,0x2B", - "EventName": "OCR.READS_TO_CORE.REMOTE_MEMORY", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x733004477", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by DRAM on a distant memory controller of this socket when the system is in SNC (sub-NUMA cluster) mode.", - "Counter": "0,1,2,3", - "EventCode": "0x2A,0x2B", - "EventName": "OCR.READS_TO_CORE.SNC_DRAM", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x708004477", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { "BriefDescription": "Counts streaming stores that have any type of response.", "Counter": "0,1,2,3", "EventCode": "0x2A,0x2B", "EventName": "OCR.STREAMING_WR.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x10800", + "PublicDescription": "Counts streaming stores that have any type of response. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, { - "BriefDescription": "Counts Demand RFOs, ItoM's, PREFECTHW's, Hardware RFO Prefetches to the L1/L2 and Streaming stores that likely resulted in a store to Memory (DRAM or PMM)", - "Counter": "0,1,2,3", - "EventCode": "0x2A,0x2B", - "EventName": "OCR.WRITE_ESTIMATE.MEMORY", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0xFBFF80822", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Cycles when Reservation Station (RS) is empty for the thread.", - "Counter": "0,1,2,3,4,5,6,7", - "EventCode": "0xa5", - "EventName": "RS.EMPTY", - "PublicDescription": "Counts cycles during which the reservation station (RS) is empty for this logical processor. This is usually caused when the front-end pipeline runs into starvation periods (e.g. branch mispredictions or i-cache misses)", - "SampleAfterValue": "1000003", - "UMask": "0x7" - }, - { - "BriefDescription": "Counts end of periods where the Reservation Station (RS) was empty.", - "Counter": "0,1,2,3,4,5,6,7", - "CounterMask": "1", - "EdgeDetect": "1", - "EventCode": "0xa5", - "EventName": "RS.EMPTY_COUNT", - "Invert": "1", - "PublicDescription": "Counts end of periods where the Reservation Station (RS) was empty. Could be useful to closely sample on front-end latency issues (see the FRONTEND_RETIRED event of designated precise events)", - "SampleAfterValue": "100003", - "UMask": "0x7" - }, - { - "BriefDescription": "Cycles when Reservation Station (RS) is empty due to a resource in the back-end", - "Counter": "0,1,2,3,4,5,6,7", - "EventCode": "0xa5", - "EventName": "RS.EMPTY_RESOURCE", - "SampleAfterValue": "1000003", - "UMask": "0x1" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event RS.EMPTY_COUNT", - "Counter": "0,1,2,3,4,5,6,7", - "CounterMask": "1", - "Deprecated": "1", - "EdgeDetect": "1", - "EventCode": "0xa5", - "EventName": "RS_EMPTY.COUNT", - "Invert": "1", - "SampleAfterValue": "100003", - "UMask": "0x7" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event RS.EMPTY", - "Counter": "0,1,2,3,4,5,6,7", - "Deprecated": "1", - "EventCode": "0xa5", - "EventName": "RS_EMPTY.CYCLES", - "SampleAfterValue": "1000003", - "UMask": "0x7" - }, - { "BriefDescription": "Cycles the uncore cannot take further requests", "Counter": "0,1,2,3", "CounterMask": "1", "EventCode": "0x2d", "EventName": "XQ.FULL_CYCLES", - "PublicDescription": "number of cycles when the thread is active and the uncore cannot take any further requests (for example prefetches, loads or stores initiated by the Core that miss the L2 cache).", + "PublicDescription": "number of cycles when the thread is active and the uncore cannot take any further requests (for example prefetches, loads or stores initiated by the Core that miss the L2 cache). Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x1" } diff --git a/tools/perf/pmu-events/arch/x86/emeraldrapids/pipeline.json b/tools/perf/pmu-events/arch/x86/emeraldrapids/pipeline.json index 50cacfbbc7cf..00b05a77c289 100644 --- a/tools/perf/pmu-events/arch/x86/emeraldrapids/pipeline.json +++ b/tools/perf/pmu-events/arch/x86/emeraldrapids/pipeline.json @@ -6,6 +6,7 @@ "Deprecated": "1", "EventCode": "0xb0", "EventName": "ARITH.DIVIDER_ACTIVE", + "PublicDescription": "This event is deprecated. Refer to new event ARITH.DIV_ACTIVE Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x9" }, @@ -15,7 +16,7 @@ "CounterMask": "1", "EventCode": "0xb0", "EventName": "ARITH.DIV_ACTIVE", - "PublicDescription": "Counts cycles when divide unit is busy executing divide or square root operations. Accounts for integer and floating-point operations.", + "PublicDescription": "Counts cycles when divide unit is busy executing divide or square root operations. Accounts for integer and floating-point operations. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x9" }, @@ -26,6 +27,7 @@ "Deprecated": "1", "EventCode": "0xb0", "EventName": "ARITH.FP_DIVIDER_ACTIVE", + "PublicDescription": "This event is deprecated. Refer to new event ARITH.FPDIV_ACTIVE Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x1" }, @@ -35,6 +37,7 @@ "CounterMask": "1", "EventCode": "0xb0", "EventName": "ARITH.IDIV_ACTIVE", + "PublicDescription": "This event counts the cycles the integer divider is busy. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x8" }, @@ -45,6 +48,7 @@ "Deprecated": "1", "EventCode": "0xb0", "EventName": "ARITH.INT_DIVIDER_ACTIVE", + "PublicDescription": "This event is deprecated. Refer to new event ARITH.IDIV_ACTIVE Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x8" }, @@ -53,7 +57,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc1", "EventName": "ASSISTS.ANY", - "PublicDescription": "Counts the number of occurrences where a microcode assist is invoked by hardware. Examples include AD (page Access Dirty), FP and AVX related assists.", + "PublicDescription": "Counts the number of occurrences where a microcode assist is invoked by hardware. Examples include AD (page Access Dirty), FP and AVX related assists. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1b" }, @@ -62,7 +66,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.ALL_BRANCHES", - "PublicDescription": "Counts all branch instructions retired.", + "PublicDescription": "Counts all branch instructions retired. Available PDIST counters: 0", "SampleAfterValue": "400009" }, { @@ -70,7 +74,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.COND", - "PublicDescription": "Counts conditional branch instructions retired.", + "PublicDescription": "Counts conditional branch instructions retired. Available PDIST counters: 0", "SampleAfterValue": "400009", "UMask": "0x11" }, @@ -79,7 +83,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.COND_NTAKEN", - "PublicDescription": "Counts not taken branch instructions retired.", + "PublicDescription": "Counts not taken branch instructions retired. Available PDIST counters: 0", "SampleAfterValue": "400009", "UMask": "0x10" }, @@ -88,7 +92,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.COND_TAKEN", - "PublicDescription": "Counts taken conditional branch instructions retired.", + "PublicDescription": "Counts taken conditional branch instructions retired. Available PDIST counters: 0", "SampleAfterValue": "400009", "UMask": "0x1" }, @@ -97,7 +101,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.FAR_BRANCH", - "PublicDescription": "Counts far branch instructions retired.", + "PublicDescription": "Counts far branch instructions retired. Available PDIST counters: 0", "SampleAfterValue": "100007", "UMask": "0x40" }, @@ -106,7 +110,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.INDIRECT", - "PublicDescription": "Counts near indirect branch instructions retired excluding returns. TSX abort is an indirect branch.", + "PublicDescription": "Counts near indirect branch instructions retired excluding returns. TSX abort is an indirect branch. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x80" }, @@ -115,7 +119,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.NEAR_CALL", - "PublicDescription": "Counts both direct and indirect near call instructions retired.", + "PublicDescription": "Counts both direct and indirect near call instructions retired. Available PDIST counters: 0", "SampleAfterValue": "100007", "UMask": "0x2" }, @@ -124,7 +128,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.NEAR_RETURN", - "PublicDescription": "Counts return instructions retired.", + "PublicDescription": "Counts return instructions retired. Available PDIST counters: 0", "SampleAfterValue": "100007", "UMask": "0x8" }, @@ -133,7 +137,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.NEAR_TAKEN", - "PublicDescription": "Counts taken branch instructions retired.", + "PublicDescription": "Counts taken branch instructions retired. Available PDIST counters: 0", "SampleAfterValue": "400009", "UMask": "0x20" }, @@ -142,7 +146,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.ALL_BRANCHES", - "PublicDescription": "Counts all the retired branch instructions that were mispredicted by the processor. A branch misprediction occurs when the processor incorrectly predicts the destination of the branch. When the misprediction is discovered at execution, all the instructions executed in the wrong (speculative) path must be discarded, and the processor must start fetching from the correct path.", + "PublicDescription": "Counts all the retired branch instructions that were mispredicted by the processor. A branch misprediction occurs when the processor incorrectly predicts the destination of the branch. When the misprediction is discovered at execution, all the instructions executed in the wrong (speculative) path must be discarded, and the processor must start fetching from the correct path. Available PDIST counters: 0", "SampleAfterValue": "400009" }, { @@ -150,7 +154,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.COND", - "PublicDescription": "Counts mispredicted conditional branch instructions retired.", + "PublicDescription": "Counts mispredicted conditional branch instructions retired. Available PDIST counters: 0", "SampleAfterValue": "400009", "UMask": "0x11" }, @@ -159,7 +163,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.COND_NTAKEN", - "PublicDescription": "Counts the number of conditional branch instructions retired that were mispredicted and the branch direction was not taken.", + "PublicDescription": "Counts the number of conditional branch instructions retired that were mispredicted and the branch direction was not taken. Available PDIST counters: 0", "SampleAfterValue": "400009", "UMask": "0x10" }, @@ -168,7 +172,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.COND_TAKEN", - "PublicDescription": "Counts taken conditional mispredicted branch instructions retired.", + "PublicDescription": "Counts taken conditional mispredicted branch instructions retired. Available PDIST counters: 0", "SampleAfterValue": "400009", "UMask": "0x1" }, @@ -177,7 +181,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.INDIRECT", - "PublicDescription": "Counts miss-predicted near indirect branch instructions retired excluding returns. TSX abort is an indirect branch.", + "PublicDescription": "Counts miss-predicted near indirect branch instructions retired excluding returns. TSX abort is an indirect branch. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x80" }, @@ -186,7 +190,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.INDIRECT_CALL", - "PublicDescription": "Counts retired mispredicted indirect (near taken) CALL instructions, including both register and memory indirect.", + "PublicDescription": "Counts retired mispredicted indirect (near taken) CALL instructions, including both register and memory indirect. Available PDIST counters: 0", "SampleAfterValue": "400009", "UMask": "0x2" }, @@ -195,7 +199,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.NEAR_TAKEN", - "PublicDescription": "Counts number of near branch instructions retired that were mispredicted and taken.", + "PublicDescription": "Counts number of near branch instructions retired that were mispredicted and taken. Available PDIST counters: 0", "SampleAfterValue": "400009", "UMask": "0x20" }, @@ -204,7 +208,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.RET", - "PublicDescription": "This is a non-precise version (that is, does not use PEBS) of the event that counts mispredicted return instructions retired.", + "PublicDescription": "This is a non-precise version (that is, does not use PEBS) of the event that counts mispredicted return instructions retired. Available PDIST counters: 0", "SampleAfterValue": "100007", "UMask": "0x8" }, @@ -213,7 +217,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xec", "EventName": "CPU_CLK_UNHALTED.C01", - "PublicDescription": "Counts core clocks when the thread is in the C0.1 light-weight slower wakeup time but more power saving optimized state. This state can be entered via the TPAUSE or UMWAIT instructions.", + "PublicDescription": "Counts core clocks when the thread is in the C0.1 light-weight slower wakeup time but more power saving optimized state. This state can be entered via the TPAUSE or UMWAIT instructions. Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x10" }, @@ -222,7 +226,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xec", "EventName": "CPU_CLK_UNHALTED.C02", - "PublicDescription": "Counts core clocks when the thread is in the C0.2 light-weight faster wakeup time but less power saving optimized state. This state can be entered via the TPAUSE or UMWAIT instructions.", + "PublicDescription": "Counts core clocks when the thread is in the C0.2 light-weight faster wakeup time but less power saving optimized state. This state can be entered via the TPAUSE or UMWAIT instructions. Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x20" }, @@ -231,7 +235,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xec", "EventName": "CPU_CLK_UNHALTED.C0_WAIT", - "PublicDescription": "Counts core clocks when the thread is in the C0.1 or C0.2 power saving optimized states (TPAUSE or UMWAIT instructions) or running the PAUSE instruction.", + "PublicDescription": "Counts core clocks when the thread is in the C0.1 or C0.2 power saving optimized states (TPAUSE or UMWAIT instructions) or running the PAUSE instruction. Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x70" }, @@ -240,7 +244,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xec", "EventName": "CPU_CLK_UNHALTED.DISTRIBUTED", - "PublicDescription": "This event distributes cycle counts between active hyperthreads, i.e., those in C0. A hyperthread becomes inactive when it executes the HLT or MWAIT instructions. If all other hyperthreads are inactive (or disabled or do not exist), all counts are attributed to this hyperthread. To obtain the full count when the Core is active, sum the counts from each hyperthread.", + "PublicDescription": "This event distributes cycle counts between active hyperthreads, i.e., those in C0. A hyperthread becomes inactive when it executes the HLT or MWAIT instructions. If all other hyperthreads are inactive (or disabled or do not exist), all counts are attributed to this hyperthread. To obtain the full count when the Core is active, sum the counts from each hyperthread. Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x2" }, @@ -249,7 +253,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0x3c", "EventName": "CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE", - "PublicDescription": "Counts Core crystal clock cycles when current thread is unhalted and the other thread is halted.", + "PublicDescription": "Counts Core crystal clock cycles when current thread is unhalted and the other thread is halted. Available PDIST counters: 0", "SampleAfterValue": "25003", "UMask": "0x2" }, @@ -258,6 +262,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xec", "EventName": "CPU_CLK_UNHALTED.PAUSE", + "PublicDescription": "CPU_CLK_UNHALTED.PAUSE Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x40" }, @@ -268,6 +273,7 @@ "EdgeDetect": "1", "EventCode": "0xec", "EventName": "CPU_CLK_UNHALTED.PAUSE_INST", + "PublicDescription": "CPU_CLK_UNHALTED.PAUSE_INST Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x40" }, @@ -276,7 +282,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0x3c", "EventName": "CPU_CLK_UNHALTED.REF_DISTRIBUTED", - "PublicDescription": "This event distributes Core crystal clock cycle counts between active hyperthreads, i.e., those in C0 sleep-state. A hyperthread becomes inactive when it executes the HLT or MWAIT instructions. If one thread is active in a core, all counts are attributed to this hyperthread. To obtain the full count when the Core is active, sum the counts from each hyperthread.", + "PublicDescription": "This event distributes Core crystal clock cycle counts between active hyperthreads, i.e., those in C0 sleep-state. A hyperthread becomes inactive when it executes the HLT or MWAIT instructions. If one thread is active in a core, all counts are attributed to this hyperthread. To obtain the full count when the Core is active, sum the counts from each hyperthread. Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x8" }, @@ -293,7 +299,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0x3c", "EventName": "CPU_CLK_UNHALTED.REF_TSC_P", - "PublicDescription": "Counts the number of reference cycles when the core is not in a halt state. The core enters the halt state when it is running the HLT instruction or the MWAIT instruction. This event is not affected by core frequency changes (for example, P states, TM2 transitions) but has the same incrementing frequency as the time stamp counter. This event can approximate elapsed time while the core was not in a halt state. It is counted on a dedicated fixed counter, leaving the four (eight when Hyperthreading is disabled) programmable counters available for other events. Note: On all current platforms this event stops counting during 'throttling (TM)' states duty off periods the processor is 'halted'. The counter update is done at a lower clock rate then the core clock the overflow status bit for this counter may appear 'sticky'. After the counter has overflowed and software clears the overflow status bit and resets the counter to less than MAX. The reset value to the counter is not clocked immediately so the overflow status bit will flip 'high (1)' and generate another PMI (if enabled) after which the reset value gets clocked into the counter. Therefore, software will get the interrupt, read the overflow status bit '1 for bit 34 while the counter value is less than MAX. Software should ignore this case.", + "PublicDescription": "Counts the number of reference cycles when the core is not in a halt state. The core enters the halt state when it is running the HLT instruction or the MWAIT instruction. This event is not affected by core frequency changes (for example, P states, TM2 transitions) but has the same incrementing frequency as the time stamp counter. This event can approximate elapsed time while the core was not in a halt state. It is counted on a dedicated fixed counter, leaving the four (eight when Hyperthreading is disabled) programmable counters available for other events. Note: On all current platforms this event stops counting during 'throttling (TM)' states duty off periods the processor is 'halted'. The counter update is done at a lower clock rate then the core clock the overflow status bit for this counter may appear 'sticky'. After the counter has overflowed and software clears the overflow status bit and resets the counter to less than MAX. The reset value to the counter is not clocked immediately so the overflow status bit will flip 'high (1)' and generate another PMI (if enabled) after which the reset value gets clocked into the counter. Therefore, software will get the interrupt, read the overflow status bit '1 for bit 34 while the counter value is less than MAX. Software should ignore this case. Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x1" }, @@ -310,7 +316,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0x3c", "EventName": "CPU_CLK_UNHALTED.THREAD_P", - "PublicDescription": "This is an architectural event that counts the number of thread cycles while the thread is not in a halt state. The thread enters the halt state when it is running the HLT instruction. The core frequency may change from time to time due to power or thermal throttling. For this reason, this event may have a changing ratio with regards to wall clock time.", + "PublicDescription": "This is an architectural event that counts the number of thread cycles while the thread is not in a halt state. The thread enters the halt state when it is running the HLT instruction. The core frequency may change from time to time due to power or thermal throttling. For this reason, this event may have a changing ratio with regards to wall clock time. Available PDIST counters: 0", "SampleAfterValue": "2000003" }, { @@ -319,6 +325,7 @@ "CounterMask": "8", "EventCode": "0xa3", "EventName": "CYCLE_ACTIVITY.CYCLES_L1D_MISS", + "PublicDescription": "Cycles while L1 cache miss demand load is outstanding. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x8" }, @@ -328,6 +335,7 @@ "CounterMask": "1", "EventCode": "0xa3", "EventName": "CYCLE_ACTIVITY.CYCLES_L2_MISS", + "PublicDescription": "Cycles while L2 cache miss demand load is outstanding. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x1" }, @@ -337,6 +345,7 @@ "CounterMask": "16", "EventCode": "0xa3", "EventName": "CYCLE_ACTIVITY.CYCLES_MEM_ANY", + "PublicDescription": "Cycles while memory subsystem has an outstanding load. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x10" }, @@ -346,6 +355,7 @@ "CounterMask": "12", "EventCode": "0xa3", "EventName": "CYCLE_ACTIVITY.STALLS_L1D_MISS", + "PublicDescription": "Execution stalls while L1 cache miss demand load is outstanding. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0xc" }, @@ -355,6 +365,7 @@ "CounterMask": "5", "EventCode": "0xa3", "EventName": "CYCLE_ACTIVITY.STALLS_L2_MISS", + "PublicDescription": "Execution stalls while L2 cache miss demand load is outstanding. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x5" }, @@ -364,15 +375,25 @@ "CounterMask": "4", "EventCode": "0xa3", "EventName": "CYCLE_ACTIVITY.STALLS_TOTAL", + "PublicDescription": "Total execution stalls. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x4" }, { + "BriefDescription": "Counts the cycles where the AMX (Advance Matrix Extension) unit is busy performing an operation.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xb7", + "EventName": "EXE.AMX_BUSY", + "PublicDescription": "Counts the cycles where the AMX (Advance Matrix Extension) unit is busy performing an operation. Available PDIST counters: 0", + "SampleAfterValue": "2000003", + "UMask": "0x2" + }, + { "BriefDescription": "Cycles total of 1 uop is executed on all ports and Reservation Station was not empty.", "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xa6", "EventName": "EXE_ACTIVITY.1_PORTS_UTIL", - "PublicDescription": "Counts cycles during which a total of 1 uop was executed on all ports and Reservation Station (RS) was not empty.", + "PublicDescription": "Counts cycles during which a total of 1 uop was executed on all ports and Reservation Station (RS) was not empty. Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x2" }, @@ -381,6 +402,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xa6", "EventName": "EXE_ACTIVITY.2_3_PORTS_UTIL", + "PublicDescription": "Cycles total of 2 or 3 uops are executed on all ports and Reservation Station (RS) was not empty. Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0xc" }, @@ -389,7 +411,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xa6", "EventName": "EXE_ACTIVITY.2_PORTS_UTIL", - "PublicDescription": "Counts cycles during which a total of 2 uops were executed on all ports and Reservation Station (RS) was not empty.", + "PublicDescription": "Counts cycles during which a total of 2 uops were executed on all ports and Reservation Station (RS) was not empty. Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x4" }, @@ -398,7 +420,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xa6", "EventName": "EXE_ACTIVITY.3_PORTS_UTIL", - "PublicDescription": "Cycles total of 3 uops are executed on all ports and Reservation Station (RS) was not empty.", + "PublicDescription": "Cycles total of 3 uops are executed on all ports and Reservation Station (RS) was not empty. Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x8" }, @@ -407,7 +429,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xa6", "EventName": "EXE_ACTIVITY.4_PORTS_UTIL", - "PublicDescription": "Cycles total of 4 uops are executed on all ports and Reservation Station (RS) was not empty.", + "PublicDescription": "Cycles total of 4 uops are executed on all ports and Reservation Station (RS) was not empty. Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x10" }, @@ -417,6 +439,7 @@ "CounterMask": "5", "EventCode": "0xa6", "EventName": "EXE_ACTIVITY.BOUND_ON_LOADS", + "PublicDescription": "Execution stalls while memory subsystem has an outstanding load. Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x21" }, @@ -426,7 +449,7 @@ "CounterMask": "2", "EventCode": "0xa6", "EventName": "EXE_ACTIVITY.BOUND_ON_STORES", - "PublicDescription": "Counts cycles where the Store Buffer was full and no loads caused an execution stall.", + "PublicDescription": "Counts cycles where the Store Buffer was full and no loads caused an execution stall. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x40" }, @@ -435,7 +458,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xa6", "EventName": "EXE_ACTIVITY.EXE_BOUND_0_PORTS", - "PublicDescription": "Number of cycles total of 0 uops executed on all ports, Reservation Station (RS) was not empty, the Store Buffer (SB) was not full and there was no outstanding load.", + "PublicDescription": "Number of cycles total of 0 uops executed on all ports, Reservation Station (RS) was not empty, the Store Buffer (SB) was not full and there was no outstanding load. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x80" }, @@ -444,7 +467,7 @@ "Counter": "0,1,2,3", "EventCode": "0x75", "EventName": "INST_DECODED.DECODERS", - "PublicDescription": "Number of decoders utilized in a cycle when the MITE (legacy decode pipeline) fetches instructions.", + "PublicDescription": "Number of decoders utilized in a cycle when the MITE (legacy decode pipeline) fetches instructions. Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x1" }, @@ -452,7 +475,7 @@ "BriefDescription": "Number of instructions retired. Fixed Counter - architectural event", "Counter": "Fixed counter 0", "EventName": "INST_RETIRED.ANY", - "PublicDescription": "Counts the number of X86 instructions retired - an Architectural PerfMon event. Counting continues during hardware interrupts, traps, and inside interrupt handlers. Notes: INST_RETIRED.ANY is counted by a designated fixed counter freeing up programmable counters to count other events. INST_RETIRED.ANY_P is counted by a programmable counter.", + "PublicDescription": "Counts the number of X86 instructions retired - an Architectural PerfMon event. Counting continues during hardware interrupts, traps, and inside interrupt handlers. Notes: INST_RETIRED.ANY is counted by a designated fixed counter freeing up programmable counters to count other events. INST_RETIRED.ANY_P is counted by a programmable counter. Available PDIST counters: 32", "SampleAfterValue": "2000003", "UMask": "0x1" }, @@ -469,6 +492,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc0", "EventName": "INST_RETIRED.MACRO_FUSED", + "PublicDescription": "INST_RETIRED.MACRO_FUSED Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x10" }, @@ -477,7 +501,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc0", "EventName": "INST_RETIRED.NOP", - "PublicDescription": "Counts all retired NOP or ENDBR32/64 instructions", + "PublicDescription": "Counts all retired NOP or ENDBR32/64 instructions Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x2" }, @@ -485,7 +509,7 @@ "BriefDescription": "Precise instruction retired with PEBS precise-distribution", "Counter": "Fixed counter 0", "EventName": "INST_RETIRED.PREC_DIST", - "PublicDescription": "A version of INST_RETIRED that allows for a precise distribution of samples across instructions retired. It utilizes the Precise Distribution of Instructions Retired (PDIR++) feature to fix bias in how retired instructions get sampled. Use on Fixed Counter 0.", + "PublicDescription": "A version of INST_RETIRED that allows for a precise distribution of samples across instructions retired. It utilizes the Precise Distribution of Instructions Retired (PDIR++) feature to fix bias in how retired instructions get sampled. Use on Fixed Counter 0. Available PDIST counters: 32", "SampleAfterValue": "2000003", "UMask": "0x1" }, @@ -494,7 +518,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc0", "EventName": "INST_RETIRED.REP_ITERATION", - "PublicDescription": "Number of iterations of Repeat (REP) string retired instructions such as MOVS, CMPS, and SCAS. Each has a byte, word, and doubleword version and string instructions can be repeated using a repetition prefix, REP, that allows their architectural execution to be repeated a number of times as specified by the RCX register. Note the number of iterations is implementation-dependent.", + "PublicDescription": "Number of iterations of Repeat (REP) string retired instructions such as MOVS, CMPS, and SCAS. Each has a byte, word, and doubleword version and string instructions can be repeated using a repetition prefix, REP, that allows their architectural execution to be repeated a number of times as specified by the RCX register. Note the number of iterations is implementation-dependent. Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x8" }, @@ -505,7 +529,7 @@ "EdgeDetect": "1", "EventCode": "0xad", "EventName": "INT_MISC.CLEARS_COUNT", - "PublicDescription": "Counts the number of speculative clears due to any type of branch misprediction or machine clears", + "PublicDescription": "Counts the number of speculative clears due to any type of branch misprediction or machine clears Available PDIST counters: 0", "SampleAfterValue": "500009", "UMask": "0x1" }, @@ -514,7 +538,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xad", "EventName": "INT_MISC.CLEAR_RESTEER_CYCLES", - "PublicDescription": "Cycles after recovery from a branch misprediction or machine clear till the first uop is issued from the resteered path.", + "PublicDescription": "Cycles after recovery from a branch misprediction or machine clear till the first uop is issued from the resteered path. Available PDIST counters: 0", "SampleAfterValue": "500009", "UMask": "0x80" }, @@ -523,6 +547,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xad", "EventName": "INT_MISC.MBA_STALLS", + "PublicDescription": "INT_MISC.MBA_STALLS Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x20" }, @@ -531,7 +556,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xad", "EventName": "INT_MISC.RECOVERY_CYCLES", - "PublicDescription": "Counts core cycles when the Resource allocator was stalled due to recovery from an earlier branch misprediction or machine clear event.", + "PublicDescription": "Counts core cycles when the Resource allocator was stalled due to recovery from an earlier branch misprediction or machine clear event. Available PDIST counters: 0", "SampleAfterValue": "500009", "UMask": "0x1" }, @@ -542,6 +567,7 @@ "EventName": "INT_MISC.UNKNOWN_BRANCH_CYCLES", "MSRIndex": "0x3F7", "MSRValue": "0x7", + "PublicDescription": "Bubble cycles of BAClear (Unknown Branch). Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x40" }, @@ -550,7 +576,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xad", "EventName": "INT_MISC.UOP_DROPPING", - "PublicDescription": "Estimated number of Top-down Microarchitecture Analysis slots that got dropped due to non front-end reasons", + "PublicDescription": "Estimated number of Top-down Microarchitecture Analysis slots that got dropped due to non front-end reasons Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x10" }, @@ -559,6 +585,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xe7", "EventName": "INT_VEC_RETIRED.128BIT", + "PublicDescription": "INT_VEC_RETIRED.128BIT Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x13" }, @@ -567,6 +594,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xe7", "EventName": "INT_VEC_RETIRED.256BIT", + "PublicDescription": "INT_VEC_RETIRED.256BIT Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0xac" }, @@ -575,7 +603,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xe7", "EventName": "INT_VEC_RETIRED.ADD_128", - "PublicDescription": "Number of retired integer ADD/SUB (regular or horizontal), SAD 128-bit vector instructions.", + "PublicDescription": "Number of retired integer ADD/SUB (regular or horizontal), SAD 128-bit vector instructions. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x3" }, @@ -584,7 +612,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xe7", "EventName": "INT_VEC_RETIRED.ADD_256", - "PublicDescription": "Number of retired integer ADD/SUB (regular or horizontal), SAD 256-bit vector instructions.", + "PublicDescription": "Number of retired integer ADD/SUB (regular or horizontal), SAD 256-bit vector instructions. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0xc" }, @@ -593,6 +621,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xe7", "EventName": "INT_VEC_RETIRED.MUL_256", + "PublicDescription": "INT_VEC_RETIRED.MUL_256 Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x80" }, @@ -601,6 +630,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xe7", "EventName": "INT_VEC_RETIRED.SHUFFLES", + "PublicDescription": "INT_VEC_RETIRED.SHUFFLES Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x40" }, @@ -609,6 +639,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xe7", "EventName": "INT_VEC_RETIRED.VNNI_128", + "PublicDescription": "INT_VEC_RETIRED.VNNI_128 Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x10" }, @@ -617,6 +648,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xe7", "EventName": "INT_VEC_RETIRED.VNNI_256", + "PublicDescription": "INT_VEC_RETIRED.VNNI_256 Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x20" }, @@ -625,7 +657,7 @@ "Counter": "0,1,2,3", "EventCode": "0x03", "EventName": "LD_BLOCKS.ADDRESS_ALIAS", - "PublicDescription": "Counts the number of times a load got blocked due to false dependencies in MOB due to partial compare on address.", + "PublicDescription": "Counts the number of times a load got blocked due to false dependencies in MOB due to partial compare on address. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x4" }, @@ -634,7 +666,7 @@ "Counter": "0,1,2,3", "EventCode": "0x03", "EventName": "LD_BLOCKS.NO_SR", - "PublicDescription": "Counts the number of times that split load operations are temporarily blocked because all resources for handling the split accesses are in use.", + "PublicDescription": "Counts the number of times that split load operations are temporarily blocked because all resources for handling the split accesses are in use. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x88" }, @@ -643,7 +675,7 @@ "Counter": "0,1,2,3", "EventCode": "0x03", "EventName": "LD_BLOCKS.STORE_FORWARD", - "PublicDescription": "Counts the number of times where store forwarding was prevented for a load operation. The most common case is a load blocked due to the address of memory access (partially) overlapping with a preceding uncompleted store. Note: See the table of not supported store forwards in the Optimization Guide.", + "PublicDescription": "Counts the number of times where store forwarding was prevented for a load operation. The most common case is a load blocked due to the address of memory access (partially) overlapping with a preceding uncompleted store. Note: See the table of not supported store forwards in the Optimization Guide. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x82" }, @@ -652,7 +684,7 @@ "Counter": "0,1,2,3", "EventCode": "0x4c", "EventName": "LOAD_HIT_PREFETCH.SWPF", - "PublicDescription": "Counts all not software-prefetch load dispatches that hit the fill buffer (FB) allocated for the software prefetch. It can also be incremented by some lock instructions. So it should only be used with profiling so that the locks can be excluded by ASM (Assembly File) inspection of the nearby instructions.", + "PublicDescription": "Counts all not software-prefetch load dispatches that hit the fill buffer (FB) allocated for the software prefetch. It can also be incremented by some lock instructions. So it should only be used with profiling so that the locks can be excluded by ASM (Assembly File) inspection of the nearby instructions. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -662,7 +694,7 @@ "CounterMask": "1", "EventCode": "0xa8", "EventName": "LSD.CYCLES_ACTIVE", - "PublicDescription": "Counts the cycles when at least one uop is delivered by the LSD (Loop-stream detector).", + "PublicDescription": "Counts the cycles when at least one uop is delivered by the LSD (Loop-stream detector). Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x1" }, @@ -672,7 +704,7 @@ "CounterMask": "6", "EventCode": "0xa8", "EventName": "LSD.CYCLES_OK", - "PublicDescription": "Counts the cycles when optimal number of uops is delivered by the LSD (Loop-stream detector).", + "PublicDescription": "Counts the cycles when optimal number of uops is delivered by the LSD (Loop-stream detector). Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x1" }, @@ -681,7 +713,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xa8", "EventName": "LSD.UOPS", - "PublicDescription": "Counts the number of uops delivered to the back-end by the LSD(Loop Stream Detector).", + "PublicDescription": "Counts the number of uops delivered to the back-end by the LSD(Loop Stream Detector). Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x1" }, @@ -692,7 +724,7 @@ "EdgeDetect": "1", "EventCode": "0xc3", "EventName": "MACHINE_CLEARS.COUNT", - "PublicDescription": "Counts the number of machine clears (nukes) of any type.", + "PublicDescription": "Counts the number of machine clears (nukes) of any type. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -701,7 +733,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc3", "EventName": "MACHINE_CLEARS.SMC", - "PublicDescription": "Counts self-modifying code (SMC) detected, which causes a machine clear.", + "PublicDescription": "Counts self-modifying code (SMC) detected, which causes a machine clear. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x4" }, @@ -710,7 +742,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xe0", "EventName": "MISC2_RETIRED.LFENCE", - "PublicDescription": "number of LFENCE retired instructions", + "PublicDescription": "number of LFENCE retired instructions Available PDIST counters: 0", "SampleAfterValue": "400009", "UMask": "0x20" }, @@ -719,7 +751,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xcc", "EventName": "MISC_RETIRED.LBR_INSERTS", - "PublicDescription": "Increments when an entry is added to the Last Branch Record (LBR) array (or removed from the array in case of RETURNs in call stack mode). The event requires LBR enable via IA32_DEBUGCTL MSR and branch type selection via MSR_LBR_SELECT.", + "PublicDescription": "Increments when an entry is added to the Last Branch Record (LBR) array (or removed from the array in case of RETURNs in call stack mode). The event requires LBR enable via IA32_DEBUGCTL MSR and branch type selection via MSR_LBR_SELECT. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x20" }, @@ -728,7 +760,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xa2", "EventName": "RESOURCE_STALLS.SB", - "PublicDescription": "Counts allocation stall cycles caused by the store buffer (SB) being full. This counts cycles that the pipeline back-end blocked uop delivery from the front-end.", + "PublicDescription": "Counts allocation stall cycles caused by the store buffer (SB) being full. This counts cycles that the pipeline back-end blocked uop delivery from the front-end. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x8" }, @@ -737,15 +769,69 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xa2", "EventName": "RESOURCE_STALLS.SCOREBOARD", + "PublicDescription": "Counts cycles where the pipeline is stalled due to serializing operations. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x2" }, { + "BriefDescription": "Cycles when Reservation Station (RS) is empty for the thread.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xa5", + "EventName": "RS.EMPTY", + "PublicDescription": "Counts cycles during which the reservation station (RS) is empty for this logical processor. This is usually caused when the front-end pipeline runs into starvation periods (e.g. branch mispredictions or i-cache misses) Available PDIST counters: 0", + "SampleAfterValue": "1000003", + "UMask": "0x7" + }, + { + "BriefDescription": "Counts end of periods where the Reservation Station (RS) was empty.", + "Counter": "0,1,2,3,4,5,6,7", + "CounterMask": "1", + "EdgeDetect": "1", + "EventCode": "0xa5", + "EventName": "RS.EMPTY_COUNT", + "Invert": "1", + "PublicDescription": "Counts end of periods where the Reservation Station (RS) was empty. Could be useful to closely sample on front-end latency issues (see the FRONTEND_RETIRED event of designated precise events) Available PDIST counters: 0", + "SampleAfterValue": "100003", + "UMask": "0x7" + }, + { + "BriefDescription": "Cycles when Reservation Station (RS) is empty due to a resource in the back-end", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xa5", + "EventName": "RS.EMPTY_RESOURCE", + "PublicDescription": "Cycles when Reservation Station (RS) is empty due to a resource in the back-end Available PDIST counters: 0", + "SampleAfterValue": "1000003", + "UMask": "0x1" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event RS.EMPTY_COUNT", + "Counter": "0,1,2,3,4,5,6,7", + "CounterMask": "1", + "Deprecated": "1", + "EdgeDetect": "1", + "EventCode": "0xa5", + "EventName": "RS_EMPTY.COUNT", + "Invert": "1", + "PublicDescription": "This event is deprecated. Refer to new event RS.EMPTY_COUNT Available PDIST counters: 0", + "SampleAfterValue": "100003", + "UMask": "0x7" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event RS.EMPTY", + "Counter": "0,1,2,3,4,5,6,7", + "Deprecated": "1", + "EventCode": "0xa5", + "EventName": "RS_EMPTY.CYCLES", + "PublicDescription": "This event is deprecated. Refer to new event RS.EMPTY Available PDIST counters: 0", + "SampleAfterValue": "1000003", + "UMask": "0x7" + }, + { "BriefDescription": "TMA slots where no uops were being issued due to lack of back-end resources.", "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xa4", "EventName": "TOPDOWN.BACKEND_BOUND_SLOTS", - "PublicDescription": "Number of slots in TMA method where no micro-operations were being issued from front-end to back-end of the machine due to lack of back-end resources.", + "PublicDescription": "Number of slots in TMA method where no micro-operations were being issued from front-end to back-end of the machine due to lack of back-end resources. Available PDIST counters: 0", "SampleAfterValue": "10000003", "UMask": "0x2" }, @@ -754,7 +840,7 @@ "Counter": "0", "EventCode": "0xa4", "EventName": "TOPDOWN.BAD_SPEC_SLOTS", - "PublicDescription": "Number of slots of TMA method that were wasted due to incorrect speculation. It covers all types of control-flow or data-related mis-speculations.", + "PublicDescription": "Number of slots of TMA method that were wasted due to incorrect speculation. It covers all types of control-flow or data-related mis-speculations. Available PDIST counters: 0", "SampleAfterValue": "10000003", "UMask": "0x4" }, @@ -763,7 +849,7 @@ "Counter": "0", "EventCode": "0xa4", "EventName": "TOPDOWN.BR_MISPREDICT_SLOTS", - "PublicDescription": "Number of TMA slots that were wasted due to incorrect speculation by (any type of) branch mispredictions. This event estimates number of speculative operations that were issued but not retired as well as the out-of-order engine recovery past a branch misprediction.", + "PublicDescription": "Number of TMA slots that were wasted due to incorrect speculation by (any type of) branch mispredictions. This event estimates number of speculative operations that were issued but not retired as well as the out-of-order engine recovery past a branch misprediction. Available PDIST counters: 0", "SampleAfterValue": "10000003", "UMask": "0x8" }, @@ -772,6 +858,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xa4", "EventName": "TOPDOWN.MEMORY_BOUND_SLOTS", + "PublicDescription": "TOPDOWN.MEMORY_BOUND_SLOTS Available PDIST counters: 0", "SampleAfterValue": "10000003", "UMask": "0x10" }, @@ -788,7 +875,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xa4", "EventName": "TOPDOWN.SLOTS_P", - "PublicDescription": "Counts the number of available slots for an unhalted logical processor. The event increments by machine-width of the narrowest pipeline as employed by the Top-down Microarchitecture Analysis method. The count is distributed among unhalted logical processors (hyper-threads) who share the same physical core.", + "PublicDescription": "Counts the number of available slots for an unhalted logical processor. The event increments by machine-width of the narrowest pipeline as employed by the Top-down Microarchitecture Analysis method. The count is distributed among unhalted logical processors (hyper-threads) who share the same physical core. Available PDIST counters: 0", "SampleAfterValue": "10000003", "UMask": "0x1" }, @@ -797,6 +884,7 @@ "Counter": "0,1,2,3", "EventCode": "0x76", "EventName": "UOPS_DECODED.DEC0_UOPS", + "PublicDescription": "UOPS_DECODED.DEC0_UOPS Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x1" }, @@ -805,7 +893,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xb2", "EventName": "UOPS_DISPATCHED.PORT_0", - "PublicDescription": "Number of uops dispatch to execution port 0.", + "PublicDescription": "Number of uops dispatch to execution port 0. Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x1" }, @@ -814,7 +902,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xb2", "EventName": "UOPS_DISPATCHED.PORT_1", - "PublicDescription": "Number of uops dispatch to execution port 1.", + "PublicDescription": "Number of uops dispatch to execution port 1. Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x2" }, @@ -823,7 +911,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xb2", "EventName": "UOPS_DISPATCHED.PORT_2_3_10", - "PublicDescription": "Number of uops dispatch to execution ports 2, 3 and 10", + "PublicDescription": "Number of uops dispatch to execution ports 2, 3 and 10 Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x4" }, @@ -832,7 +920,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xb2", "EventName": "UOPS_DISPATCHED.PORT_4_9", - "PublicDescription": "Number of uops dispatch to execution ports 4 and 9", + "PublicDescription": "Number of uops dispatch to execution ports 4 and 9 Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x10" }, @@ -841,7 +929,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xb2", "EventName": "UOPS_DISPATCHED.PORT_5_11", - "PublicDescription": "Number of uops dispatch to execution ports 5 and 11", + "PublicDescription": "Number of uops dispatch to execution ports 5 and 11 Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x20" }, @@ -850,7 +938,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xb2", "EventName": "UOPS_DISPATCHED.PORT_6", - "PublicDescription": "Number of uops dispatch to execution port 6.", + "PublicDescription": "Number of uops dispatch to execution port 6. Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x40" }, @@ -859,7 +947,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xb2", "EventName": "UOPS_DISPATCHED.PORT_7_8", - "PublicDescription": "Number of uops dispatch to execution ports 7 and 8.", + "PublicDescription": "Number of uops dispatch to execution ports 7 and 8. Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x80" }, @@ -868,7 +956,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xb1", "EventName": "UOPS_EXECUTED.CORE", - "PublicDescription": "Counts the number of uops executed from any thread.", + "PublicDescription": "Counts the number of uops executed from any thread. Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x2" }, @@ -878,7 +966,7 @@ "CounterMask": "1", "EventCode": "0xb1", "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_1", - "PublicDescription": "Counts cycles when at least 1 micro-op is executed from any thread on physical core.", + "PublicDescription": "Counts cycles when at least 1 micro-op is executed from any thread on physical core. Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x2" }, @@ -888,7 +976,7 @@ "CounterMask": "2", "EventCode": "0xb1", "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_2", - "PublicDescription": "Counts cycles when at least 2 micro-ops are executed from any thread on physical core.", + "PublicDescription": "Counts cycles when at least 2 micro-ops are executed from any thread on physical core. Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x2" }, @@ -898,7 +986,7 @@ "CounterMask": "3", "EventCode": "0xb1", "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_3", - "PublicDescription": "Counts cycles when at least 3 micro-ops are executed from any thread on physical core.", + "PublicDescription": "Counts cycles when at least 3 micro-ops are executed from any thread on physical core. Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x2" }, @@ -908,7 +996,7 @@ "CounterMask": "4", "EventCode": "0xb1", "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_4", - "PublicDescription": "Counts cycles when at least 4 micro-ops are executed from any thread on physical core.", + "PublicDescription": "Counts cycles when at least 4 micro-ops are executed from any thread on physical core. Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x2" }, @@ -918,7 +1006,7 @@ "CounterMask": "1", "EventCode": "0xb1", "EventName": "UOPS_EXECUTED.CYCLES_GE_1", - "PublicDescription": "Cycles where at least 1 uop was executed per-thread.", + "PublicDescription": "Cycles where at least 1 uop was executed per-thread. Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x1" }, @@ -928,7 +1016,7 @@ "CounterMask": "2", "EventCode": "0xb1", "EventName": "UOPS_EXECUTED.CYCLES_GE_2", - "PublicDescription": "Cycles where at least 2 uops were executed per-thread.", + "PublicDescription": "Cycles where at least 2 uops were executed per-thread. Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x1" }, @@ -938,7 +1026,7 @@ "CounterMask": "3", "EventCode": "0xb1", "EventName": "UOPS_EXECUTED.CYCLES_GE_3", - "PublicDescription": "Cycles where at least 3 uops were executed per-thread.", + "PublicDescription": "Cycles where at least 3 uops were executed per-thread. Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x1" }, @@ -948,7 +1036,7 @@ "CounterMask": "4", "EventCode": "0xb1", "EventName": "UOPS_EXECUTED.CYCLES_GE_4", - "PublicDescription": "Cycles where at least 4 uops were executed per-thread.", + "PublicDescription": "Cycles where at least 4 uops were executed per-thread. Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x1" }, @@ -959,7 +1047,7 @@ "EventCode": "0xb1", "EventName": "UOPS_EXECUTED.STALLS", "Invert": "1", - "PublicDescription": "Counts cycles during which no uops were dispatched from the Reservation Station (RS) per thread.", + "PublicDescription": "Counts cycles during which no uops were dispatched from the Reservation Station (RS) per thread. Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x1" }, @@ -971,6 +1059,7 @@ "EventCode": "0xb1", "EventName": "UOPS_EXECUTED.STALL_CYCLES", "Invert": "1", + "PublicDescription": "This event is deprecated. Refer to new event UOPS_EXECUTED.STALLS Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x1" }, @@ -979,6 +1068,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xb1", "EventName": "UOPS_EXECUTED.THREAD", + "PublicDescription": "Counts the number of uops to be executed per-thread each cycle. Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x1" }, @@ -987,7 +1077,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xb1", "EventName": "UOPS_EXECUTED.X87", - "PublicDescription": "Counts the number of x87 uops executed.", + "PublicDescription": "Counts the number of x87 uops executed. Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x10" }, @@ -996,7 +1086,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xae", "EventName": "UOPS_ISSUED.ANY", - "PublicDescription": "Counts the number of uops that the Resource Allocation Table (RAT) issues to the Reservation Station (RS).", + "PublicDescription": "Counts the number of uops that the Resource Allocation Table (RAT) issues to the Reservation Station (RS). Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x1" }, @@ -1006,6 +1096,7 @@ "CounterMask": "1", "EventCode": "0xae", "EventName": "UOPS_ISSUED.CYCLES", + "PublicDescription": "UOPS_ISSUED.CYCLES Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x1" }, @@ -1015,7 +1106,7 @@ "CounterMask": "1", "EventCode": "0xc2", "EventName": "UOPS_RETIRED.CYCLES", - "PublicDescription": "Counts cycles where at least one uop has retired.", + "PublicDescription": "Counts cycles where at least one uop has retired. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x2" }, @@ -1024,7 +1115,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc2", "EventName": "UOPS_RETIRED.HEAVY", - "PublicDescription": "Counts the number of retired micro-operations (uops) except the last uop of each instruction. An instruction that is decoded into less than two uops does not contribute to the count.", + "PublicDescription": "Counts the number of retired micro-operations (uops) except the last uop of each instruction. An instruction that is decoded into less than two uops does not contribute to the count. Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x1" }, @@ -1035,6 +1126,7 @@ "EventName": "UOPS_RETIRED.MS", "MSRIndex": "0x3F7", "MSRValue": "0x8", + "PublicDescription": "UOPS_RETIRED.MS Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x4" }, @@ -1043,7 +1135,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc2", "EventName": "UOPS_RETIRED.SLOTS", - "PublicDescription": "Counts the retirement slots used each cycle.", + "PublicDescription": "Counts the retirement slots used each cycle. Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x2" }, @@ -1054,7 +1146,7 @@ "EventCode": "0xc2", "EventName": "UOPS_RETIRED.STALLS", "Invert": "1", - "PublicDescription": "This event counts cycles without actually retired uops.", + "PublicDescription": "This event counts cycles without actually retired uops. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x2" }, @@ -1066,6 +1158,7 @@ "EventCode": "0xc2", "EventName": "UOPS_RETIRED.STALL_CYCLES", "Invert": "1", + "PublicDescription": "This event is deprecated. Refer to new event UOPS_RETIRED.STALLS Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x2" } diff --git a/tools/perf/pmu-events/arch/x86/emeraldrapids/virtual-memory.json b/tools/perf/pmu-events/arch/x86/emeraldrapids/virtual-memory.json index 609a9549cbf3..3d3f88600e26 100644 --- a/tools/perf/pmu-events/arch/x86/emeraldrapids/virtual-memory.json +++ b/tools/perf/pmu-events/arch/x86/emeraldrapids/virtual-memory.json @@ -4,7 +4,7 @@ "Counter": "0,1,2,3", "EventCode": "0x12", "EventName": "DTLB_LOAD_MISSES.STLB_HIT", - "PublicDescription": "Counts loads that miss the DTLB (Data TLB) and hit the STLB (Second level TLB).", + "PublicDescription": "Counts loads that miss the DTLB (Data TLB) and hit the STLB (Second level TLB). Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x20" }, @@ -14,7 +14,7 @@ "CounterMask": "1", "EventCode": "0x12", "EventName": "DTLB_LOAD_MISSES.WALK_ACTIVE", - "PublicDescription": "Counts cycles when at least one PMH (Page Miss Handler) is busy with a page walk for a demand load.", + "PublicDescription": "Counts cycles when at least one PMH (Page Miss Handler) is busy with a page walk for a demand load. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x10" }, @@ -23,7 +23,7 @@ "Counter": "0,1,2,3", "EventCode": "0x12", "EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED", - "PublicDescription": "Counts completed page walks (all page sizes) caused by demand data loads. This implies it missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.", + "PublicDescription": "Counts completed page walks (all page sizes) caused by demand data loads. This implies it missed in the DTLB and further levels of TLB. The page walk can end with or without a fault. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0xe" }, @@ -32,7 +32,7 @@ "Counter": "0,1,2,3", "EventCode": "0x12", "EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED_1G", - "PublicDescription": "Counts completed page walks (1G sizes) caused by demand data loads. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.", + "PublicDescription": "Counts completed page walks (1G sizes) caused by demand data loads. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x8" }, @@ -41,7 +41,7 @@ "Counter": "0,1,2,3", "EventCode": "0x12", "EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M", - "PublicDescription": "Counts completed page walks (2M/4M sizes) caused by demand data loads. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.", + "PublicDescription": "Counts completed page walks (2M/4M sizes) caused by demand data loads. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x4" }, @@ -50,7 +50,7 @@ "Counter": "0,1,2,3", "EventCode": "0x12", "EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED_4K", - "PublicDescription": "Counts completed page walks (4K sizes) caused by demand data loads. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.", + "PublicDescription": "Counts completed page walks (4K sizes) caused by demand data loads. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x2" }, @@ -59,7 +59,7 @@ "Counter": "0,1,2,3", "EventCode": "0x12", "EventName": "DTLB_LOAD_MISSES.WALK_PENDING", - "PublicDescription": "Counts the number of page walks outstanding for a demand load in the PMH (Page Miss Handler) each cycle.", + "PublicDescription": "Counts the number of page walks outstanding for a demand load in the PMH (Page Miss Handler) each cycle. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x10" }, @@ -68,7 +68,7 @@ "Counter": "0,1,2,3", "EventCode": "0x13", "EventName": "DTLB_STORE_MISSES.STLB_HIT", - "PublicDescription": "Counts stores that miss the DTLB (Data TLB) and hit the STLB (2nd Level TLB).", + "PublicDescription": "Counts stores that miss the DTLB (Data TLB) and hit the STLB (2nd Level TLB). Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x20" }, @@ -78,7 +78,7 @@ "CounterMask": "1", "EventCode": "0x13", "EventName": "DTLB_STORE_MISSES.WALK_ACTIVE", - "PublicDescription": "Counts cycles when at least one PMH (Page Miss Handler) is busy with a page walk for a store.", + "PublicDescription": "Counts cycles when at least one PMH (Page Miss Handler) is busy with a page walk for a store. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x10" }, @@ -87,7 +87,7 @@ "Counter": "0,1,2,3", "EventCode": "0x13", "EventName": "DTLB_STORE_MISSES.WALK_COMPLETED", - "PublicDescription": "Counts completed page walks (all page sizes) caused by demand data stores. This implies it missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.", + "PublicDescription": "Counts completed page walks (all page sizes) caused by demand data stores. This implies it missed in the DTLB and further levels of TLB. The page walk can end with or without a fault. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0xe" }, @@ -96,7 +96,7 @@ "Counter": "0,1,2,3", "EventCode": "0x13", "EventName": "DTLB_STORE_MISSES.WALK_COMPLETED_1G", - "PublicDescription": "Counts completed page walks (1G sizes) caused by demand data stores. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.", + "PublicDescription": "Counts completed page walks (1G sizes) caused by demand data stores. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x8" }, @@ -105,7 +105,7 @@ "Counter": "0,1,2,3", "EventCode": "0x13", "EventName": "DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M", - "PublicDescription": "Counts completed page walks (2M/4M sizes) caused by demand data stores. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.", + "PublicDescription": "Counts completed page walks (2M/4M sizes) caused by demand data stores. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x4" }, @@ -114,7 +114,7 @@ "Counter": "0,1,2,3", "EventCode": "0x13", "EventName": "DTLB_STORE_MISSES.WALK_COMPLETED_4K", - "PublicDescription": "Counts completed page walks (4K sizes) caused by demand data stores. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.", + "PublicDescription": "Counts completed page walks (4K sizes) caused by demand data stores. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x2" }, @@ -123,7 +123,7 @@ "Counter": "0,1,2,3", "EventCode": "0x13", "EventName": "DTLB_STORE_MISSES.WALK_PENDING", - "PublicDescription": "Counts the number of page walks outstanding for a store in the PMH (Page Miss Handler) each cycle.", + "PublicDescription": "Counts the number of page walks outstanding for a store in the PMH (Page Miss Handler) each cycle. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x10" }, @@ -132,7 +132,7 @@ "Counter": "0,1,2,3", "EventCode": "0x11", "EventName": "ITLB_MISSES.STLB_HIT", - "PublicDescription": "Counts instruction fetch requests that miss the ITLB (Instruction TLB) and hit the STLB (Second-level TLB).", + "PublicDescription": "Counts instruction fetch requests that miss the ITLB (Instruction TLB) and hit the STLB (Second-level TLB). Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x20" }, @@ -142,7 +142,7 @@ "CounterMask": "1", "EventCode": "0x11", "EventName": "ITLB_MISSES.WALK_ACTIVE", - "PublicDescription": "Counts cycles when at least one PMH (Page Miss Handler) is busy with a page walk for a code (instruction fetch) request.", + "PublicDescription": "Counts cycles when at least one PMH (Page Miss Handler) is busy with a page walk for a code (instruction fetch) request. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x10" }, @@ -151,7 +151,7 @@ "Counter": "0,1,2,3", "EventCode": "0x11", "EventName": "ITLB_MISSES.WALK_COMPLETED", - "PublicDescription": "Counts completed page walks (all page sizes) caused by a code fetch. This implies it missed in the ITLB (Instruction TLB) and further levels of TLB. The page walk can end with or without a fault.", + "PublicDescription": "Counts completed page walks (all page sizes) caused by a code fetch. This implies it missed in the ITLB (Instruction TLB) and further levels of TLB. The page walk can end with or without a fault. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0xe" }, @@ -160,7 +160,7 @@ "Counter": "0,1,2,3", "EventCode": "0x11", "EventName": "ITLB_MISSES.WALK_COMPLETED_2M_4M", - "PublicDescription": "Counts completed page walks (2M/4M page sizes) caused by a code fetch. This implies it missed in the ITLB (Instruction TLB) and further levels of TLB. The page walk can end with or without a fault.", + "PublicDescription": "Counts completed page walks (2M/4M page sizes) caused by a code fetch. This implies it missed in the ITLB (Instruction TLB) and further levels of TLB. The page walk can end with or without a fault. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x4" }, @@ -169,7 +169,7 @@ "Counter": "0,1,2,3", "EventCode": "0x11", "EventName": "ITLB_MISSES.WALK_COMPLETED_4K", - "PublicDescription": "Counts completed page walks (4K page sizes) caused by a code fetch. This implies it missed in the ITLB (Instruction TLB) and further levels of TLB. The page walk can end with or without a fault.", + "PublicDescription": "Counts completed page walks (4K page sizes) caused by a code fetch. This implies it missed in the ITLB (Instruction TLB) and further levels of TLB. The page walk can end with or without a fault. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x2" }, @@ -178,7 +178,7 @@ "Counter": "0,1,2,3", "EventCode": "0x11", "EventName": "ITLB_MISSES.WALK_PENDING", - "PublicDescription": "Counts the number of page walks outstanding for an outstanding code (instruction fetch) request in the PMH (Page Miss Handler) each cycle.", + "PublicDescription": "Counts the number of page walks outstanding for an outstanding code (instruction fetch) request in the PMH (Page Miss Handler) each cycle. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x10" } diff --git a/tools/perf/pmu-events/arch/x86/grandridge/cache.json b/tools/perf/pmu-events/arch/x86/grandridge/cache.json index 04802e254e51..877052db1490 100644 --- a/tools/perf/pmu-events/arch/x86/grandridge/cache.json +++ b/tools/perf/pmu-events/arch/x86/grandridge/cache.json @@ -1,5 +1,92 @@ [ { + "BriefDescription": "Counts the number of L1D cacheline (dirty) evictions caused by load misses, stores, and prefetches.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x51", + "EventName": "DL1.DIRTY_EVICTION", + "PublicDescription": "Counts the number of L1D cacheline (dirty) evictions caused by load misses, stores, and prefetches. Does not count evictions or dirty writebacks caused by snoops. Does not count a replacement unless a (dirty) line was written back.", + "SampleAfterValue": "200003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts the number of cache lines filled into the L2 cache that are in Exclusive state", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x25", + "EventName": "L2_LINES_IN.E", + "PublicDescription": "Counts the number of cache lines filled into the L2 cache that are in Exclusive state. Counts on a per core basis.", + "SampleAfterValue": "1000003", + "UMask": "0x4" + }, + { + "BriefDescription": "Counts the number of cache lines filled into the L2 cache that are in Forward state", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x25", + "EventName": "L2_LINES_IN.F", + "PublicDescription": "Counts the number of cache lines filled into the L2 cache that are in Forward state. Counts on a per core basis.", + "SampleAfterValue": "1000003", + "UMask": "0x10" + }, + { + "BriefDescription": "Counts the number of cache lines filled into the L2 cache that are in Modified state", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x25", + "EventName": "L2_LINES_IN.M", + "PublicDescription": "Counts the number of cache lines filled into the L2 cache that are in Modified state. Counts on a per core basis.", + "SampleAfterValue": "1000003", + "UMask": "0x8" + }, + { + "BriefDescription": "Counts the number of cache lines filled into the L2 cache that are in Shared state", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x25", + "EventName": "L2_LINES_IN.S", + "PublicDescription": "Counts the number of cache lines filled into the L2 cache that are in Shared state. Counts on a per core basis.", + "SampleAfterValue": "1000003", + "UMask": "0x2" + }, + { + "BriefDescription": "Counts the number of L2 cache lines that are evicted due to an L2 cache fill", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x26", + "EventName": "L2_LINES_OUT.NON_SILENT", + "PublicDescription": "Counts the number of L2 cache lines that are evicted due to an L2 cache fill. Increments on the core that brought the line in originally.", + "SampleAfterValue": "1000003", + "UMask": "0x2" + }, + { + "BriefDescription": "Counts the number of L2 cache lines that are silently dropped due to an L2 cache fill", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x26", + "EventName": "L2_LINES_OUT.SILENT", + "PublicDescription": "Counts the number of L2 cache lines that are silently dropped due to an L2 cache fill. Increments on the core that brought the line in originally.", + "SampleAfterValue": "1000003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts the number of L2 Cache Accesses that resulted in a Hit from a front door request only (does not include rejects or recycles), per core event", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x24", + "EventName": "L2_REQUEST.HIT", + "SampleAfterValue": "200003", + "UMask": "0x2" + }, + { + "BriefDescription": "Counts the number of total L2 Cache Accesses that resulted in a Miss from a front door request only (does not include rejects or recycles), per core event", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x24", + "EventName": "L2_REQUEST.MISS", + "SampleAfterValue": "200003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts the number of L2 Cache Accesses that miss the L2 and get BBL reject short and long rejects, per core event", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x24", + "EventName": "L2_REQUEST.REJECTS", + "SampleAfterValue": "200003", + "UMask": "0x4" + }, + { "BriefDescription": "Counts the number of cacheable memory requests that miss in the LLC. Counts on a per core basis.", "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0x2e", @@ -35,7 +122,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts the number of unhalted cycles when the core is stalled due to an icache or itlb miss which hit in the LLC.", + "BriefDescription": "Counts the number of unhalted cycles when the core is stalled due to an ICACHE or ITLB miss which hit in the LLC. If the core has access to an L3 cache, an LLC hit refers to an L3 cache hit, otherwise it counts zeros.", "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0x35", "EventName": "MEM_BOUND_STALLS_IFETCH.LLC_HIT", @@ -43,7 +130,7 @@ "UMask": "0x6" }, { - "BriefDescription": "Counts the number of unhalted cycles when the core is stalled due to an icache or itlb miss which missed all the caches.", + "BriefDescription": "Counts the number of unhalted cycles when the core is stalled due to an ICACHE or ITLB miss which missed all the caches. If the core has access to an L3 cache, an LLC miss refers to an L3 cache miss, otherwise it is an L2 cache miss.", "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0x35", "EventName": "MEM_BOUND_STALLS_IFETCH.LLC_MISS", @@ -68,7 +155,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts the number of unhalted cycles when the core is stalled due to a demand load miss which hit in the LLC.", + "BriefDescription": "Counts the number of unhalted cycles when the core is stalled due to a demand load miss which hit in the LLC. If the core has access to an L3 cache, an LLC hit refers to an L3 cache hit, otherwise it counts zeros.", "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0x34", "EventName": "MEM_BOUND_STALLS_LOAD.LLC_HIT", @@ -76,7 +163,7 @@ "UMask": "0x6" }, { - "BriefDescription": "Counts the number of unhalted cycles when the core is stalled due to a demand load miss which missed all the local caches.", + "BriefDescription": "Counts the number of unhalted cycles when the core is stalled due to a demand load miss which missed all the local caches. If the core has access to an L3 cache, an LLC miss refers to an L3 cache miss, otherwise it is an L2 cache miss.", "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0x34", "EventName": "MEM_BOUND_STALLS_LOAD.LLC_MISS", @@ -84,6 +171,14 @@ "UMask": "0x78" }, { + "BriefDescription": "Counts the number of unhalted cycles when the core is stalled to a store buffer full condition", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x34", + "EventName": "MEM_BOUND_STALLS_LOAD.SBFULL", + "SampleAfterValue": "1000003", + "UMask": "0x80" + }, + { "BriefDescription": "Counts the number of load ops retired that miss the L3 cache and hit in DRAM", "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xd3", @@ -336,6 +431,33 @@ "UMask": "0x42" }, { + "BriefDescription": "Counts the number of memory uops retired that missed in the second level TLB.", + "Counter": "0,1,2,3,4,5,6,7", + "Data_LA": "1", + "EventCode": "0xd0", + "EventName": "MEM_UOPS_RETIRED.STLB_MISS", + "SampleAfterValue": "200003", + "UMask": "0x13" + }, + { + "BriefDescription": "Counts the number of load uops retired that miss in the second Level TLB.", + "Counter": "0,1,2,3,4,5,6,7", + "Data_LA": "1", + "EventCode": "0xd0", + "EventName": "MEM_UOPS_RETIRED.STLB_MISS_LOADS", + "SampleAfterValue": "200003", + "UMask": "0x11" + }, + { + "BriefDescription": "Counts the number of store uops retired that miss in the second level TLB.", + "Counter": "0,1,2,3,4,5,6,7", + "Data_LA": "1", + "EventCode": "0xd0", + "EventName": "MEM_UOPS_RETIRED.STLB_MISS_STORES", + "SampleAfterValue": "200003", + "UMask": "0x12" + }, + { "BriefDescription": "Counts the number of stores uops retired same as MEM_UOPS_RETIRED.ALL_STORES", "Counter": "0,1,2,3,4,5,6,7", "Data_LA": "1", @@ -345,12 +467,24 @@ "UMask": "0x6" }, { + "BriefDescription": "Counts demand data reads that have any type of response.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xB7", + "EventName": "OCR.DEMAND_DATA_RD.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x10001", + "PublicDescription": "Counts demand data reads that have any type of response. Available PDIST counters: 0", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { "BriefDescription": "Counts demand data reads that were supplied by the L3 cache where a snoop was sent, the snoop hit, and modified data was forwarded.", "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xB7", "EventName": "OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x10003C0001", + "PublicDescription": "Counts demand data reads that were supplied by the L3 cache where a snoop was sent, the snoop hit, and modified data was forwarded. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -361,6 +495,18 @@ "EventName": "OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x8003C0001", + "PublicDescription": "Counts demand data reads that were supplied by the L3 cache where a snoop was sent, the snoop hit, and non-modified data was forwarded. Available PDIST counters: 0", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that have any type of response.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xB7", + "EventName": "OCR.DEMAND_RFO.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x10002", + "PublicDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that have any type of response. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -371,6 +517,7 @@ "EventName": "OCR.DEMAND_RFO.L3_HIT.SNOOP_HITM", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x10003C0002", + "PublicDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that were supplied by the L3 cache where a snoop was sent, the snoop hit, and modified data was forwarded. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, diff --git a/tools/perf/pmu-events/arch/x86/grandridge/counter.json b/tools/perf/pmu-events/arch/x86/grandridge/counter.json index 9fd5d8ad6d3b..d9ac3aca5bd5 100644 --- a/tools/perf/pmu-events/arch/x86/grandridge/counter.json +++ b/tools/perf/pmu-events/arch/x86/grandridge/counter.json @@ -37,6 +37,6 @@ { "Unit": "CHACMS", "CountersNumFixed": "0", - "CountersNumGeneric": 4 + "CountersNumGeneric": "4" } ]
\ No newline at end of file diff --git a/tools/perf/pmu-events/arch/x86/grandridge/frontend.json b/tools/perf/pmu-events/arch/x86/grandridge/frontend.json index 7cdf611efb23..fef5cba533bb 100644 --- a/tools/perf/pmu-events/arch/x86/grandridge/frontend.json +++ b/tools/perf/pmu-events/arch/x86/grandridge/frontend.json @@ -31,5 +31,13 @@ "EventName": "ICACHE.MISSES", "SampleAfterValue": "200003", "UMask": "0x2" + }, + { + "BriefDescription": "Counts the number of cycles that the micro-sequencer is busy.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xe7", + "EventName": "MS_DECODED.MS_BUSY", + "SampleAfterValue": "1000003", + "UMask": "0x4" } ] diff --git a/tools/perf/pmu-events/arch/x86/grandridge/grr-metrics.json b/tools/perf/pmu-events/arch/x86/grandridge/grr-metrics.json index 2f9959c61718..1c6dba7b2822 100644 --- a/tools/perf/pmu-events/arch/x86/grandridge/grr-metrics.json +++ b/tools/perf/pmu-events/arch/x86/grandridge/grr-metrics.json @@ -216,15 +216,17 @@ { "BriefDescription": "Counts the number of issue slots that were not consumed by the backend due to certain allocation restrictions", "MetricExpr": "tma_core_bound", - "MetricGroup": "Slots;TopdownL3;tma_L3_group;tma_core_bound_group", + "MetricGroup": "TopdownL3;tma_L3_group;tma_core_bound_group", "MetricName": "tma_allocation_restriction", + "MetricThreshold": "tma_allocation_restriction > 0.1 & (tma_core_bound > 0.1 & tma_backend_bound > 0.1)", "ScaleUnit": "100%" }, { "BriefDescription": "Counts the total number of issue slots that were not consumed by the backend due to backend stalls", "MetricExpr": "TOPDOWN_BE_BOUND.ALL_P / (6 * CPU_CLK_UNHALTED.CORE)", - "MetricGroup": "Slots;TopdownL1;tma_L1_group", + "MetricGroup": "TopdownL1;tma_L1_group", "MetricName": "tma_backend_bound", + "MetricThreshold": "tma_backend_bound > 0.1", "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "Counts the total number of issue slots that were not consumed by the backend due to backend stalls. Note that uops must be available for consumption in order for this event to count. If a uop is not available (IQ is empty), this event will not count", "ScaleUnit": "100%" @@ -232,92 +234,104 @@ { "BriefDescription": "Counts the total number of issue slots that were not consumed by the backend because allocation is stalled due to a mispredicted jump or a machine clear", "MetricExpr": "TOPDOWN_BAD_SPECULATION.ALL_P / (6 * CPU_CLK_UNHALTED.CORE)", - "MetricGroup": "Slots;TopdownL1;tma_L1_group", + "MetricGroup": "TopdownL1;tma_L1_group", "MetricName": "tma_bad_speculation", + "MetricThreshold": "tma_bad_speculation > 0.15", "MetricgroupNoGroup": "TopdownL1", - "PublicDescription": "Counts the total number of issue slots that were not consumed by the backend because allocation is stalled due to a mispredicted jump or a machine clear. Only issue slots wasted due to fast nukes such as memory ordering nukes are counted. Other nukes are not accounted for. Counts all issue slots blocked during this recovery window including relevant microcode flows and while uops are not yet available in the instruction queue (IQ). Also includes the issue slots that were consumed by the backend but were thrown away because they were younger than the mispredict or machine clear", + "PublicDescription": "Counts the total number of issue slots that were not consumed by the backend because allocation is stalled due to a mispredicted jump or a machine clear. Only issue slots wasted due to fast nukes such as memory ordering nukes are counted. Other nukes are not accounted for. Counts all issue slots blocked during this recovery window including relevant microcode flows and while uops are not yet available in the instruction queue (IQ). Also includes the issue slots that were consumed by the backend but were thrown away because they were younger than the mispredict or machine clear.", "ScaleUnit": "100%" }, { "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to BACLEARS, which occurs when the Branch Target Buffer (BTB) prediction or lack thereof, was corrected by a later branch predictor in the frontend", "MetricExpr": "TOPDOWN_FE_BOUND.BRANCH_DETECT / (6 * CPU_CLK_UNHALTED.CORE)", - "MetricGroup": "Slots;TopdownL3;tma_L3_group;tma_ifetch_latency_group", + "MetricGroup": "TopdownL3;tma_L3_group;tma_ifetch_latency_group", "MetricName": "tma_branch_detect", - "PublicDescription": "Counts the number of issue slots that were not delivered by the frontend due to BACLEARS, which occurs when the Branch Target Buffer (BTB) prediction or lack thereof, was corrected by a later branch predictor in the frontend. Includes BACLEARS due to all branch types including conditional and unconditional jumps, returns, and indirect branches", + "MetricThreshold": "tma_branch_detect > 0.05 & (tma_ifetch_latency > 0.15 & tma_frontend_bound > 0.2)", + "PublicDescription": "Counts the number of issue slots that were not delivered by the frontend due to BACLEARS, which occurs when the Branch Target Buffer (BTB) prediction or lack thereof, was corrected by a later branch predictor in the frontend. Includes BACLEARS due to all branch types including conditional and unconditional jumps, returns, and indirect branches.", "ScaleUnit": "100%" }, { "BriefDescription": "Counts the number of issue slots that were not consumed by the backend due to branch mispredicts", "MetricExpr": "TOPDOWN_BAD_SPECULATION.MISPREDICT / (6 * CPU_CLK_UNHALTED.CORE)", - "MetricGroup": "Slots;TopdownL2;tma_L2_group;tma_bad_speculation_group", + "MetricGroup": "TopdownL2;tma_L2_group;tma_bad_speculation_group", "MetricName": "tma_branch_mispredicts", + "MetricThreshold": "tma_branch_mispredicts > 0.05 & tma_bad_speculation > 0.15", "MetricgroupNoGroup": "TopdownL2", "ScaleUnit": "100%" }, { - "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to BTCLEARS, which occurs when the Branch Target Buffer (BTB) predicts a taken branch", + "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to BTCLEARS, which occurs when the Branch Target Buffer (BTB) predicts a taken branch.", "MetricExpr": "TOPDOWN_FE_BOUND.BRANCH_RESTEER / (6 * CPU_CLK_UNHALTED.CORE)", - "MetricGroup": "Slots;TopdownL3;tma_L3_group;tma_ifetch_latency_group", + "MetricGroup": "TopdownL3;tma_L3_group;tma_ifetch_latency_group", "MetricName": "tma_branch_resteer", + "MetricThreshold": "tma_branch_resteer > 0.05 & (tma_ifetch_latency > 0.15 & tma_frontend_bound > 0.2)", "ScaleUnit": "100%" }, { - "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to the microcode sequencer (MS)", + "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to the microcode sequencer (MS).", "MetricExpr": "TOPDOWN_FE_BOUND.CISC / (6 * CPU_CLK_UNHALTED.CORE)", - "MetricGroup": "Slots;TopdownL3;tma_L3_group;tma_ifetch_bandwidth_group", + "MetricGroup": "TopdownL3;tma_L3_group;tma_ifetch_bandwidth_group", "MetricName": "tma_cisc", + "MetricThreshold": "tma_cisc > 0.05 & (tma_ifetch_bandwidth > 0.1 & tma_frontend_bound > 0.2)", "ScaleUnit": "100%" }, { "BriefDescription": "Counts the number of cycles due to backend bound stalls that are bounded by core restrictions and not attributed to an outstanding load or stores, or resource limitation", "MetricExpr": "TOPDOWN_BE_BOUND.ALLOC_RESTRICTIONS / (6 * CPU_CLK_UNHALTED.CORE)", - "MetricGroup": "Slots;TopdownL2;tma_L2_group;tma_backend_bound_group", + "MetricGroup": "TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_core_bound", + "MetricThreshold": "tma_core_bound > 0.1 & tma_backend_bound > 0.1", "MetricgroupNoGroup": "TopdownL2", "ScaleUnit": "100%" }, { - "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to decode stalls", + "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to decode stalls.", "MetricExpr": "TOPDOWN_FE_BOUND.DECODE / (6 * CPU_CLK_UNHALTED.CORE)", - "MetricGroup": "Slots;TopdownL3;tma_L3_group;tma_ifetch_bandwidth_group", + "MetricGroup": "TopdownL3;tma_L3_group;tma_ifetch_bandwidth_group", "MetricName": "tma_decode", + "MetricThreshold": "tma_decode > 0.05 & (tma_ifetch_bandwidth > 0.1 & tma_frontend_bound > 0.2)", "ScaleUnit": "100%" }, { "BriefDescription": "Counts the number of issue slots that were not consumed by the backend due to a machine clear that does not require the use of microcode, classified as a fast nuke, due to memory ordering, memory disambiguation and memory renaming", "MetricExpr": "TOPDOWN_BAD_SPECULATION.FASTNUKE / (6 * CPU_CLK_UNHALTED.CORE)", - "MetricGroup": "Slots;TopdownL3;tma_L3_group;tma_machine_clears_group", + "MetricGroup": "TopdownL3;tma_L3_group;tma_machine_clears_group", "MetricName": "tma_fast_nuke", + "MetricThreshold": "tma_fast_nuke > 0.05 & (tma_machine_clears > 0.05 & tma_bad_speculation > 0.15)", "ScaleUnit": "100%" }, { - "BriefDescription": "Counts the number of issue slots that were not consumed by the backend due to frontend stalls", + "BriefDescription": "Counts the number of issue slots that were not consumed by the backend due to frontend stalls.", "MetricExpr": "TOPDOWN_FE_BOUND.ALL_P / (6 * CPU_CLK_UNHALTED.CORE)", - "MetricGroup": "Slots;TopdownL1;tma_L1_group", + "MetricGroup": "TopdownL1;tma_L1_group", "MetricName": "tma_frontend_bound", + "MetricThreshold": "tma_frontend_bound > 0.2", "MetricgroupNoGroup": "TopdownL1", "ScaleUnit": "100%" }, { - "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to instruction cache misses", + "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to instruction cache misses.", "MetricExpr": "TOPDOWN_FE_BOUND.ICACHE / (6 * CPU_CLK_UNHALTED.CORE)", - "MetricGroup": "Slots;TopdownL3;tma_L3_group;tma_ifetch_latency_group", + "MetricGroup": "TopdownL3;tma_L3_group;tma_ifetch_latency_group", "MetricName": "tma_icache_misses", + "MetricThreshold": "tma_icache_misses > 0.05 & (tma_ifetch_latency > 0.15 & tma_frontend_bound > 0.2)", "ScaleUnit": "100%" }, { - "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to frontend bandwidth restrictions due to decode, predecode, cisc, and other limitations", + "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to frontend bandwidth restrictions due to decode, predecode, cisc, and other limitations.", "MetricExpr": "TOPDOWN_FE_BOUND.FRONTEND_BANDWIDTH / (6 * CPU_CLK_UNHALTED.CORE)", - "MetricGroup": "Slots;TopdownL2;tma_L2_group;tma_frontend_bound_group", + "MetricGroup": "TopdownL2;tma_L2_group;tma_frontend_bound_group", "MetricName": "tma_ifetch_bandwidth", + "MetricThreshold": "tma_ifetch_bandwidth > 0.1 & tma_frontend_bound > 0.2", "MetricgroupNoGroup": "TopdownL2", "ScaleUnit": "100%" }, { - "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to frontend latency restrictions due to icache misses, itlb misses, branch detection, and resteer limitations", + "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to frontend latency restrictions due to icache misses, itlb misses, branch detection, and resteer limitations.", "MetricExpr": "TOPDOWN_FE_BOUND.FRONTEND_LATENCY / (6 * CPU_CLK_UNHALTED.CORE)", - "MetricGroup": "Slots;TopdownL2;tma_L2_group;tma_frontend_bound_group", + "MetricGroup": "TopdownL2;tma_L2_group;tma_frontend_bound_group", "MetricName": "tma_ifetch_latency", + "MetricThreshold": "tma_ifetch_latency > 0.15 & tma_frontend_bound > 0.2", "MetricgroupNoGroup": "TopdownL2", "ScaleUnit": "100%" }, @@ -348,33 +362,28 @@ { "BriefDescription": "Percentage of time that retirement is stalled due to a first level data TLB miss", "MetricExpr": "100 * (LD_HEAD.DTLB_MISS_AT_RET + LD_HEAD.PGWALK_AT_RET) / CPU_CLK_UNHALTED.CORE", - "MetricGroup": "Cycles", - "MetricName": "tma_info_bottleneck_dtlb_miss_bound_cycles", - "ScaleUnit": "100%" + "MetricName": "tma_info_bottleneck_%_dtlb_miss_bound_cycles" }, { "BriefDescription": "Percentage of time that allocation and retirement is stalled by the Frontend Cluster due to an Ifetch Miss, either Icache or ITLB Miss", "MetricExpr": "100 * MEM_BOUND_STALLS_IFETCH.ALL / CPU_CLK_UNHALTED.CORE", - "MetricGroup": "Cycles;Ifetch", - "MetricName": "tma_info_bottleneck_ifetch_miss_bound_cycles", - "PublicDescription": "Percentage of time that allocation and retirement is stalled by the Frontend Cluster due to an Ifetch Miss, either Icache or ITLB Miss. See Info.Ifetch_Bound", - "ScaleUnit": "100%" + "MetricGroup": "Ifetch", + "MetricName": "tma_info_bottleneck_%_ifetch_miss_bound_cycles", + "PublicDescription": "Percentage of time that allocation and retirement is stalled by the Frontend Cluster due to an Ifetch Miss, either Icache or ITLB Miss. See Info.Ifetch_Bound" }, { "BriefDescription": "Percentage of time that retirement is stalled due to an L1 miss", "MetricExpr": "100 * MEM_BOUND_STALLS_LOAD.ALL / CPU_CLK_UNHALTED.CORE", - "MetricGroup": "Cycles;Load_Store_Miss", - "MetricName": "tma_info_bottleneck_load_miss_bound_cycles", - "PublicDescription": "Percentage of time that retirement is stalled due to an L1 miss. See Info.Load_Miss_Bound", - "ScaleUnit": "100%" + "MetricGroup": "Load_Store_Miss", + "MetricName": "tma_info_bottleneck_%_load_miss_bound_cycles", + "PublicDescription": "Percentage of time that retirement is stalled due to an L1 miss. See Info.Load_Miss_Bound" }, { "BriefDescription": "Percentage of time that retirement is stalled by the Memory Cluster due to a pipeline stall", "MetricExpr": "100 * LD_HEAD.ANY_AT_RET / CPU_CLK_UNHALTED.CORE", - "MetricGroup": "Cycles;Mem_Exec", - "MetricName": "tma_info_bottleneck_mem_exec_bound_cycles", - "PublicDescription": "Percentage of time that retirement is stalled by the Memory Cluster due to a pipeline stall. See Info.Mem_Exec_Bound", - "ScaleUnit": "100%" + "MetricGroup": "Mem_Exec", + "MetricName": "tma_info_bottleneck_%_mem_exec_bound_cycles", + "PublicDescription": "Percentage of time that retirement is stalled by the Memory Cluster due to a pipeline stall. See Info.Mem_Exec_Bound" }, { "BriefDescription": "Instructions per Branch (lower number means higher occurrence rate)", @@ -429,26 +438,22 @@ { "BriefDescription": "Percentage of time that allocation is stalled due to load buffer full", "MetricExpr": "100 * MEM_SCHEDULER_BLOCK.LD_BUF / CPU_CLK_UNHALTED.CORE", - "MetricName": "tma_info_buffer_stalls_load_buffer_stall_cycles", - "ScaleUnit": "100%" + "MetricName": "tma_info_buffer_stalls_%_load_buffer_stall_cycles" }, { "BriefDescription": "Percentage of time that allocation is stalled due to memory reservation stations full", "MetricExpr": "100 * MEM_SCHEDULER_BLOCK.RSV / CPU_CLK_UNHALTED.CORE", - "MetricName": "tma_info_buffer_stalls_mem_rsv_stall_cycles", - "ScaleUnit": "100%" + "MetricName": "tma_info_buffer_stalls_%_mem_rsv_stall_cycles" }, { "BriefDescription": "Percentage of time that allocation is stalled due to store buffer full", "MetricExpr": "100 * MEM_SCHEDULER_BLOCK.ST_BUF / CPU_CLK_UNHALTED.CORE", - "MetricName": "tma_info_buffer_stalls_store_buffer_stall_cycles", - "ScaleUnit": "100%" + "MetricName": "tma_info_buffer_stalls_%_store_buffer_stall_cycles" }, { "BriefDescription": "Cycles Per Instruction", "MetricExpr": "CPU_CLK_UNHALTED.CORE / INST_RETIRED.ANY", - "MetricName": "tma_info_core_cpi", - "ScaleUnit": "1per_instr" + "MetricName": "tma_info_core_cpi" }, { "BriefDescription": "Floating Point Operations Per Cycle", @@ -469,28 +474,46 @@ { "BriefDescription": "Percentage of ifetch miss bound stalls, where the ifetch miss hits in the L2", "MetricExpr": "100 * MEM_BOUND_STALLS_IFETCH.L2_HIT / MEM_BOUND_STALLS_IFETCH.ALL", - "MetricName": "tma_info_ifetch_miss_bound_ifetchmissbound_with_l2hit", - "ScaleUnit": "100%" + "MetricName": "tma_info_ifetch_miss_bound_%_ifetchmissbound_with_l2hit" + }, + { + "BriefDescription": "Percentage of ifetch miss bound stalls, where the ifetch miss doesn't hit in the L2", + "MetricExpr": "100 * (MEM_BOUND_STALLS_IFETCH.LLC_HIT + MEM_BOUND_STALLS_IFETCH.LLC_MISS) / MEM_BOUND_STALLS_IFETCH.ALL", + "MetricName": "tma_info_ifetch_miss_bound_%_ifetchmissbound_with_l2miss" }, { "BriefDescription": "Percentage of ifetch miss bound stalls, where the ifetch miss hits in the L3", "MetricExpr": "100 * MEM_BOUND_STALLS_IFETCH.LLC_HIT / MEM_BOUND_STALLS_IFETCH.ALL", - "MetricName": "tma_info_ifetch_miss_bound_ifetchmissbound_with_l3hit", - "ScaleUnit": "100%" + "MetricName": "tma_info_ifetch_miss_bound_%_ifetchmissbound_with_l3hit" + }, + { + "BriefDescription": "Percentage of ifetch miss bound stalls, where the ifetch miss subsequently misses in the L3", + "MetricExpr": "100 * MEM_BOUND_STALLS_IFETCH.LLC_MISS / MEM_BOUND_STALLS_IFETCH.ALL", + "MetricName": "tma_info_ifetch_miss_bound_%_ifetchmissbound_with_l3miss" }, { "BriefDescription": "Percentage of memory bound stalls where retirement is stalled due to an L1 miss that hit the L2", "MetricExpr": "100 * MEM_BOUND_STALLS_LOAD.L2_HIT / MEM_BOUND_STALLS_LOAD.ALL", "MetricGroup": "load_store_bound", - "MetricName": "tma_info_load_miss_bound_loadmissbound_with_l2hit", - "ScaleUnit": "100%" + "MetricName": "tma_info_load_miss_bound_%_loadmissbound_with_l2hit" + }, + { + "BriefDescription": "Percentage of memory bound stalls where retirement is stalled due to an L1 miss that subsequently misses in the L2", + "MetricExpr": "100 * (MEM_BOUND_STALLS_LOAD.LLC_HIT + MEM_BOUND_STALLS_LOAD.LLC_MISS) / MEM_BOUND_STALLS_LOAD.ALL", + "MetricGroup": "load_store_bound", + "MetricName": "tma_info_load_miss_bound_%_loadmissbound_with_l2miss" }, { "BriefDescription": "Percentage of memory bound stalls where retirement is stalled due to an L1 miss that hit the L3", "MetricExpr": "100 * MEM_BOUND_STALLS_LOAD.LLC_HIT / MEM_BOUND_STALLS_LOAD.ALL", "MetricGroup": "load_store_bound", - "MetricName": "tma_info_load_miss_bound_loadmissbound_with_l3hit", - "ScaleUnit": "100%" + "MetricName": "tma_info_load_miss_bound_%_loadmissbound_with_l3hit" + }, + { + "BriefDescription": "Percentage of memory bound stalls where retirement is stalled due to an L1 miss that subsequently misses the L3", + "MetricExpr": "100 * MEM_BOUND_STALLS_LOAD.LLC_MISS / MEM_BOUND_STALLS_LOAD.ALL", + "MetricGroup": "load_store_bound", + "MetricName": "tma_info_load_miss_bound_%_loadmissbound_with_l3miss" }, { "BriefDescription": "Counts the number of cycles that the oldest load of the load buffer is stalled at retirement due to a pipeline block", @@ -528,44 +551,37 @@ { "BriefDescription": "Percentage of total non-speculative loads with an address aliasing block", "MetricExpr": "100 * LD_BLOCKS.ADDRESS_ALIAS / MEM_UOPS_RETIRED.ALL_LOADS", - "MetricName": "tma_info_mem_exec_blocks_loads_with_adressaliasing", - "ScaleUnit": "100%" + "MetricName": "tma_info_mem_exec_blocks_%_loads_with_adressaliasing" }, { "BriefDescription": "Percentage of total non-speculative loads with a store forward or unknown store address block", "MetricExpr": "100 * LD_BLOCKS.DATA_UNKNOWN / MEM_UOPS_RETIRED.ALL_LOADS", - "MetricName": "tma_info_mem_exec_blocks_loads_with_storefwdblk", - "ScaleUnit": "100%" + "MetricName": "tma_info_mem_exec_blocks_%_loads_with_storefwdblk" }, { "BriefDescription": "Percentage of Memory Execution Bound due to a first level data cache miss", "MetricExpr": "100 * LD_HEAD.L1_MISS_AT_RET / LD_HEAD.ANY_AT_RET", - "MetricName": "tma_info_mem_exec_bound_loadhead_with_l1miss", - "ScaleUnit": "100%" + "MetricName": "tma_info_mem_exec_bound_%_loadhead_with_l1miss" }, { "BriefDescription": "Percentage of Memory Execution Bound due to other block cases, such as pipeline conflicts, fences, etc", "MetricExpr": "100 * LD_HEAD.OTHER_AT_RET / LD_HEAD.ANY_AT_RET", - "MetricName": "tma_info_mem_exec_bound_loadhead_with_otherpipelineblks", - "ScaleUnit": "100%" + "MetricName": "tma_info_mem_exec_bound_%_loadhead_with_otherpipelineblks" }, { "BriefDescription": "Percentage of Memory Execution Bound due to a pagewalk", "MetricExpr": "100 * LD_HEAD.PGWALK_AT_RET / LD_HEAD.ANY_AT_RET", - "MetricName": "tma_info_mem_exec_bound_loadhead_with_pagewalk", - "ScaleUnit": "100%" + "MetricName": "tma_info_mem_exec_bound_%_loadhead_with_pagewalk" }, { "BriefDescription": "Percentage of Memory Execution Bound due to a second level TLB miss", "MetricExpr": "100 * LD_HEAD.DTLB_MISS_AT_RET / LD_HEAD.ANY_AT_RET", - "MetricName": "tma_info_mem_exec_bound_loadhead_with_stlbhit", - "ScaleUnit": "100%" + "MetricName": "tma_info_mem_exec_bound_%_loadhead_with_stlbhit" }, { "BriefDescription": "Percentage of Memory Execution Bound due to a store forward address match", "MetricExpr": "100 * LD_HEAD.ST_ADDR_AT_RET / LD_HEAD.ANY_AT_RET", - "MetricName": "tma_info_mem_exec_bound_loadhead_with_storefwding", - "ScaleUnit": "100%" + "MetricName": "tma_info_mem_exec_bound_%_loadhead_with_storefwding" }, { "BriefDescription": "Instructions per Load", @@ -595,8 +611,7 @@ { "BriefDescription": "Percentage of time that the core is stalled due to a TPAUSE or UMWAIT instruction", "MetricExpr": "100 * SERIALIZATION.C01_MS_SCB / (6 * CPU_CLK_UNHALTED.CORE)", - "MetricName": "tma_info_serialization_tpause_cycles", - "ScaleUnit": "100%" + "MetricName": "tma_info_serialization_%_tpause_cycles" }, { "BriefDescription": "Average CPU Utilization", @@ -612,17 +627,20 @@ }, { "BriefDescription": "Fraction of cycles spent in Kernel mode", - "MetricExpr": "CPU_CLK_UNHALTED.CORE_P:k / CPU_CLK_UNHALTED.CORE", + "MetricExpr": "cpu@CPU_CLK_UNHALTED.CORE_P@k / CPU_CLK_UNHALTED.CORE", + "MetricGroup": "Summary", "MetricName": "tma_info_system_kernel_utilization" }, { "BriefDescription": "PerfMon Event Multiplexing accuracy indicator", "MetricExpr": "CPU_CLK_UNHALTED.CORE_P / CPU_CLK_UNHALTED.CORE", - "MetricName": "tma_info_system_mux" + "MetricName": "tma_info_system_mux", + "MetricThreshold": "tma_info_system_mux > 1.1 | tma_info_system_mux < 0.9" }, { "BriefDescription": "Average Frequency Utilization relative nominal frequency", "MetricExpr": "CPU_CLK_UNHALTED.CORE / CPU_CLK_UNHALTED.REF_TSC", + "MetricGroup": "Power", "MetricName": "tma_info_system_turbo_utilization" }, { @@ -646,90 +664,102 @@ "MetricName": "tma_info_uop_mix_x87_uop_ratio" }, { - "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to Instruction Table Lookaside Buffer (ITLB) misses", + "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to Instruction Table Lookaside Buffer (ITLB) misses.", "MetricExpr": "TOPDOWN_FE_BOUND.ITLB_MISS / (6 * CPU_CLK_UNHALTED.CORE)", - "MetricGroup": "Slots;TopdownL3;tma_L3_group;tma_ifetch_latency_group", + "MetricGroup": "TopdownL3;tma_L3_group;tma_ifetch_latency_group", "MetricName": "tma_itlb_misses", + "MetricThreshold": "tma_itlb_misses > 0.05 & (tma_ifetch_latency > 0.15 & tma_frontend_bound > 0.2)", "ScaleUnit": "100%" }, { "BriefDescription": "Counts the total number of issue slots that were not consumed by the backend because allocation is stalled due to a machine clear (nuke) of any kind including memory ordering and memory disambiguation", "MetricExpr": "TOPDOWN_BAD_SPECULATION.MACHINE_CLEARS / (6 * CPU_CLK_UNHALTED.CORE)", - "MetricGroup": "Slots;TopdownL2;tma_L2_group;tma_bad_speculation_group", + "MetricGroup": "TopdownL2;tma_L2_group;tma_bad_speculation_group", "MetricName": "tma_machine_clears", + "MetricThreshold": "tma_machine_clears > 0.05 & tma_bad_speculation > 0.15", "MetricgroupNoGroup": "TopdownL2", "ScaleUnit": "100%" }, { "BriefDescription": "Counts the number of issue slots that were not consumed by the backend due to memory reservation stalls in which a scheduler is not able to accept uops", "MetricExpr": "TOPDOWN_BE_BOUND.MEM_SCHEDULER / (6 * CPU_CLK_UNHALTED.CORE)", - "MetricGroup": "Slots;TopdownL3;tma_L3_group;tma_resource_bound_group", + "MetricGroup": "TopdownL3;tma_L3_group;tma_resource_bound_group", "MetricName": "tma_mem_scheduler", + "MetricThreshold": "tma_mem_scheduler > 0.1 & (tma_resource_bound > 0.2 & tma_backend_bound > 0.1)", "ScaleUnit": "100%" }, { "BriefDescription": "Counts the number of issue slots that were not consumed by the backend due to IEC or FPC RAT stalls, which can be due to FIQ or IEC reservation stalls in which the integer, floating point or SIMD scheduler is not able to accept uops", "MetricExpr": "TOPDOWN_BE_BOUND.NON_MEM_SCHEDULER / (6 * CPU_CLK_UNHALTED.CORE)", - "MetricGroup": "Slots;TopdownL3;tma_L3_group;tma_resource_bound_group", + "MetricGroup": "TopdownL3;tma_L3_group;tma_resource_bound_group", "MetricName": "tma_non_mem_scheduler", + "MetricThreshold": "tma_non_mem_scheduler > 0.1 & (tma_resource_bound > 0.2 & tma_backend_bound > 0.1)", "ScaleUnit": "100%" }, { "BriefDescription": "Counts the number of issue slots that were not consumed by the backend due to a machine clear that requires the use of microcode (slow nuke)", "MetricExpr": "TOPDOWN_BAD_SPECULATION.NUKE / (6 * CPU_CLK_UNHALTED.CORE)", - "MetricGroup": "Slots;TopdownL3;tma_L3_group;tma_machine_clears_group", + "MetricGroup": "TopdownL3;tma_L3_group;tma_machine_clears_group", "MetricName": "tma_nuke", + "MetricThreshold": "tma_nuke > 0.05 & (tma_machine_clears > 0.05 & tma_bad_speculation > 0.15)", "ScaleUnit": "100%" }, { - "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to other common frontend stalls not categorized", + "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to other common frontend stalls not categorized.", "MetricExpr": "TOPDOWN_FE_BOUND.OTHER / (6 * CPU_CLK_UNHALTED.CORE)", - "MetricGroup": "Slots;TopdownL3;tma_L3_group;tma_ifetch_bandwidth_group", + "MetricGroup": "TopdownL3;tma_L3_group;tma_ifetch_bandwidth_group", "MetricName": "tma_other_fb", + "MetricThreshold": "tma_other_fb > 0.05 & (tma_ifetch_bandwidth > 0.1 & tma_frontend_bound > 0.2)", "ScaleUnit": "100%" }, { - "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to wrong predecodes", + "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to wrong predecodes.", "MetricExpr": "TOPDOWN_FE_BOUND.PREDECODE / (6 * CPU_CLK_UNHALTED.CORE)", - "MetricGroup": "Slots;TopdownL3;tma_L3_group;tma_ifetch_bandwidth_group", + "MetricGroup": "TopdownL3;tma_L3_group;tma_ifetch_bandwidth_group", "MetricName": "tma_predecode", + "MetricThreshold": "tma_predecode > 0.05 & (tma_ifetch_bandwidth > 0.1 & tma_frontend_bound > 0.2)", "ScaleUnit": "100%" }, { "BriefDescription": "Counts the number of issue slots that were not consumed by the backend due to the physical register file unable to accept an entry (marble stalls)", "MetricExpr": "TOPDOWN_BE_BOUND.REGISTER / (6 * CPU_CLK_UNHALTED.CORE)", - "MetricGroup": "Slots;TopdownL3;tma_L3_group;tma_resource_bound_group", + "MetricGroup": "TopdownL3;tma_L3_group;tma_resource_bound_group", "MetricName": "tma_register", + "MetricThreshold": "tma_register > 0.1 & (tma_resource_bound > 0.2 & tma_backend_bound > 0.1)", "ScaleUnit": "100%" }, { "BriefDescription": "Counts the number of issue slots that were not consumed by the backend due to the reorder buffer being full (ROB stalls)", "MetricExpr": "TOPDOWN_BE_BOUND.REORDER_BUFFER / (6 * CPU_CLK_UNHALTED.CORE)", - "MetricGroup": "Slots;TopdownL3;tma_L3_group;tma_resource_bound_group", + "MetricGroup": "TopdownL3;tma_L3_group;tma_resource_bound_group", "MetricName": "tma_reorder_buffer", + "MetricThreshold": "tma_reorder_buffer > 0.1 & (tma_resource_bound > 0.2 & tma_backend_bound > 0.1)", "ScaleUnit": "100%" }, { "BriefDescription": "Counts the number of cycles the core is stalled due to a resource limitation", "MetricExpr": "tma_backend_bound - tma_core_bound", - "MetricGroup": "Slots;TopdownL2;tma_L2_group;tma_backend_bound_group", + "MetricGroup": "TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_resource_bound", + "MetricThreshold": "tma_resource_bound > 0.2 & tma_backend_bound > 0.1", "MetricgroupNoGroup": "TopdownL2", "ScaleUnit": "100%" }, { "BriefDescription": "Counts the number of issue slots that result in retirement slots", "MetricExpr": "TOPDOWN_RETIRING.ALL_P / (6 * CPU_CLK_UNHALTED.CORE)", - "MetricGroup": "Slots;TopdownL1;tma_L1_group", + "MetricGroup": "TopdownL1;tma_L1_group", "MetricName": "tma_retiring", + "MetricThreshold": "tma_retiring > 0.75", "MetricgroupNoGroup": "TopdownL1", "ScaleUnit": "100%" }, { "BriefDescription": "Counts the number of issue slots that were not consumed by the backend due to scoreboards from the instruction queue (IQ), jump execution unit (JEU), or microcode sequencer (MS)", "MetricExpr": "TOPDOWN_BE_BOUND.SERIALIZATION / (6 * CPU_CLK_UNHALTED.CORE)", - "MetricGroup": "Slots;TopdownL3;tma_L3_group;tma_resource_bound_group", + "MetricGroup": "TopdownL3;tma_L3_group;tma_resource_bound_group", "MetricName": "tma_serialization", + "MetricThreshold": "tma_serialization > 0.1 & (tma_resource_bound > 0.2 & tma_backend_bound > 0.1)", "ScaleUnit": "100%" }, { diff --git a/tools/perf/pmu-events/arch/x86/grandridge/memory.json b/tools/perf/pmu-events/arch/x86/grandridge/memory.json index 22d23077618e..48b6301e7696 100644 --- a/tools/perf/pmu-events/arch/x86/grandridge/memory.json +++ b/tools/perf/pmu-events/arch/x86/grandridge/memory.json @@ -79,6 +79,7 @@ "EventName": "OCR.DEMAND_DATA_RD.L3_MISS", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x3FBFC00001", + "PublicDescription": "Counts demand data reads that were not supplied by the L3 cache. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -89,6 +90,7 @@ "EventName": "OCR.DEMAND_RFO.L3_MISS", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x3FBFC00002", + "PublicDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that were not supplied by the L3 cache. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" } diff --git a/tools/perf/pmu-events/arch/x86/grandridge/other.json b/tools/perf/pmu-events/arch/x86/grandridge/other.json index 28f9a4c3ea84..ea34103a8292 100644 --- a/tools/perf/pmu-events/arch/x86/grandridge/other.json +++ b/tools/perf/pmu-events/arch/x86/grandridge/other.json @@ -9,41 +9,14 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts demand data reads that have any type of response.", - "Counter": "0,1,2,3,4,5,6,7", - "EventCode": "0xB7", - "EventName": "OCR.DEMAND_DATA_RD.ANY_RESPONSE", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x10001", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that have any type of response.", - "Counter": "0,1,2,3,4,5,6,7", - "EventCode": "0xB7", - "EventName": "OCR.DEMAND_RFO.ANY_RESPONSE", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x10002", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { "BriefDescription": "Counts streaming stores that have any type of response.", "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xB7", "EventName": "OCR.STREAMING_WR.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x10800", + "PublicDescription": "Counts streaming stores that have any type of response. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" - }, - { - "BriefDescription": "Counts the number of issue slots in a UMWAIT or TPAUSE instruction where no uop issues due to the instruction putting the CPU into the C0.1 activity state.", - "Counter": "0,1,2,3,4,5,6,7", - "EventCode": "0x75", - "EventName": "SERIALIZATION.C01_MS_SCB", - "SampleAfterValue": "200003", - "UMask": "0x4" } ] diff --git a/tools/perf/pmu-events/arch/x86/grandridge/pipeline.json b/tools/perf/pmu-events/arch/x86/grandridge/pipeline.json index 40fa4f5ae261..f56d8d816e53 100644 --- a/tools/perf/pmu-events/arch/x86/grandridge/pipeline.json +++ b/tools/perf/pmu-events/arch/x86/grandridge/pipeline.json @@ -57,6 +57,14 @@ "UMask": "0xfb" }, { + "BriefDescription": "Counts the number of near indirect JMP branch instructions retired.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc4", + "EventName": "BR_INST_RETIRED.INDIRECT_JMP", + "SampleAfterValue": "200003", + "UMask": "0xef" + }, + { "BriefDescription": "This event is deprecated. Refer to new event BR_INST_RETIRED.INDIRECT_CALL", "Counter": "0,1,2,3,4,5,6,7", "Deprecated": "1", @@ -82,6 +90,30 @@ "UMask": "0xf7" }, { + "BriefDescription": "Counts the number of near taken branch instructions retired.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc4", + "EventName": "BR_INST_RETIRED.NEAR_TAKEN", + "SampleAfterValue": "200003", + "UMask": "0xc0" + }, + { + "BriefDescription": "Counts the number of near relative CALL branch instructions retired.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc4", + "EventName": "BR_INST_RETIRED.REL_CALL", + "SampleAfterValue": "200003", + "UMask": "0xfd" + }, + { + "BriefDescription": "Counts the number of near relative JMP branch instructions retired.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc4", + "EventName": "BR_INST_RETIRED.REL_JMP", + "SampleAfterValue": "200003", + "UMask": "0xdf" + }, + { "BriefDescription": "Counts the total number of mispredicted branch instructions retired for all branch types.", "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc5", @@ -122,6 +154,14 @@ "UMask": "0xfb" }, { + "BriefDescription": "Counts the number of mispredicted near indirect JMP branch instructions retired.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc5", + "EventName": "BR_MISP_RETIRED.INDIRECT_JMP", + "SampleAfterValue": "200003", + "UMask": "0xef" + }, + { "BriefDescription": "Counts the number of mispredicted near taken branch instructions retired.", "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc5", @@ -185,6 +225,7 @@ "BriefDescription": "Fixed Counter: Counts the number of instructions retired", "Counter": "Fixed counter 0", "EventName": "INST_RETIRED.ANY", + "PublicDescription": "Fixed Counter: Counts the number of instructions retired Available PDIST counters: 32", "SampleAfterValue": "2000003", "UMask": "0x1" }, @@ -236,8 +277,9 @@ "UMask": "0x20" }, { - "BriefDescription": "Counts the number of machine clears that flush the pipeline and restart the machine with the use of microcode due to SMC, MEMORY_ORDERING, FP_ASSISTS, PAGE_FAULT, DISAMBIGUATION, and FPC_VIRTUAL_TRAP.", + "BriefDescription": "This event is deprecated.", "Counter": "0,1,2,3,4,5,6,7", + "Deprecated": "1", "EventCode": "0xc3", "EventName": "MACHINE_CLEARS.SLOW", "SampleAfterValue": "20003", @@ -260,6 +302,14 @@ "UMask": "0x1" }, { + "BriefDescription": "Counts the number of issue slots in a UMWAIT or TPAUSE instruction where no uop issues due to the instruction putting the CPU into the C0.1 activity state.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x75", + "EventName": "SERIALIZATION.C01_MS_SCB", + "SampleAfterValue": "200003", + "UMask": "0x4" + }, + { "BriefDescription": "Counts the number of issue slots that were not consumed by the backend because allocation is stalled due to a mispredicted jump or a machine clear. [This event is alias to TOPDOWN_BAD_SPECULATION.ALL_P]", "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0x73", diff --git a/tools/perf/pmu-events/arch/x86/grandridge/uncore-cache.json b/tools/perf/pmu-events/arch/x86/grandridge/uncore-cache.json index 6a80cf6cbd36..b89ab6e5cfb5 100644 --- a/tools/perf/pmu-events/arch/x86/grandridge/uncore-cache.json +++ b/tools/perf/pmu-events/arch/x86/grandridge/uncore-cache.json @@ -9,6 +9,16 @@ "Unit": "CHACMS" }, { + "BriefDescription": "Counts the number of cycles FAST trigger is received from the global FAST distress wire.", + "Counter": "0,1,2,3", + "EventCode": "0x34", + "EventName": "UNC_CHACMS_RING_SRC_THRTL", + "Experimental": "1", + "PerPkg": "1", + "PortMask": "0x000", + "Unit": "CHACMS" + }, + { "BriefDescription": "Number of CHA clock cycles while the event is enabled", "Counter": "0,1,2,3", "EventCode": "0x01", @@ -531,6 +541,26 @@ "Unit": "CHA" }, { + "BriefDescription": "Ingress (from CMS) Allocations : IRQ : Counts number of allocations per cycle into the specified Ingress queue.", + "Counter": "0,1,2,3", + "EventCode": "0x13", + "EventName": "UNC_CHA_RxC_INSERTS.IRQ", + "Experimental": "1", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Ingress (from CMS) Occupancy : IRQ : Counts number of entries in the specified Ingress queue in each cycle.", + "Counter": "0", + "EventCode": "0x11", + "EventName": "UNC_CHA_RxC_OCCUPANCY.IRQ", + "Experimental": "1", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CHA" + }, + { "BriefDescription": "All TOR Inserts", "Counter": "0,1,2,3", "EventCode": "0x35", @@ -603,7 +633,7 @@ "Unit": "CHA" }, { - "BriefDescription": "Data read opt prefetch from local IA that miss the cache", + "BriefDescription": "Data read opt prefetch from local IA", "Counter": "0,1,2,3", "EventCode": "0x35", "EventName": "UNC_CHA_TOR_INSERTS.IA_DRD_OPT_PREF", @@ -764,7 +794,7 @@ "Unit": "CHA" }, { - "BriefDescription": "Last level cache prefetch read for ownership from local IA that miss the cache", + "BriefDescription": "Last level cache prefetch read for ownership from local IA", "Counter": "0,1,2,3", "EventCode": "0x35", "EventName": "UNC_CHA_TOR_INSERTS.IA_LLCPREFRFO", @@ -859,7 +889,7 @@ "EventCode": "0x35", "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_DRD_OPT_PREF_LOCAL", "PerPkg": "1", - "PublicDescription": "TOR Inserts : DRd_Opt_Prefs issued by iA Cores that missed the LLC", + "PublicDescription": "TOR Inserts : Data read opt prefetch from local iA that missed the LLC targeting local memory", "UMask": "0xc8a6fe01", "Unit": "CHA" }, @@ -934,7 +964,7 @@ "Unit": "CHA" }, { - "BriefDescription": "Read for ownership from local IA that miss the cache", + "BriefDescription": "Read for ownership from local IA that miss the LLC targeting local memory", "Counter": "0,1,2,3", "EventCode": "0x35", "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_RFO_LOCAL", @@ -954,7 +984,7 @@ "Unit": "CHA" }, { - "BriefDescription": "Read for ownership prefetch from local IA that miss the cache", + "BriefDescription": "Read for ownership prefetch from local IA that miss the LLC targeting local memory", "Counter": "0,1,2,3", "EventCode": "0x35", "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_RFO_PREF_LOCAL", @@ -1024,7 +1054,7 @@ "Unit": "CHA" }, { - "BriefDescription": "Read for ownership from local IA that miss the cache", + "BriefDescription": "Read for ownership from local IA", "Counter": "0,1,2,3", "EventCode": "0x35", "EventName": "UNC_CHA_TOR_INSERTS.IA_RFO", @@ -1034,7 +1064,7 @@ "Unit": "CHA" }, { - "BriefDescription": "Read for ownership prefetch from local IA that miss the cache", + "BriefDescription": "Read for ownership prefetch from local IA", "Counter": "0,1,2,3", "EventCode": "0x35", "EventName": "UNC_CHA_TOR_INSERTS.IA_RFO_PREF", @@ -1406,7 +1436,6 @@ "Counter": "0", "EventCode": "0x36", "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_DRD_OPT", - "Experimental": "1", "PerPkg": "1", "PublicDescription": "TOR Occupancy : DRd_Opts issued by iA Cores", "UMask": "0xc827ff01", diff --git a/tools/perf/pmu-events/arch/x86/grandridge/uncore-memory.json b/tools/perf/pmu-events/arch/x86/grandridge/uncore-memory.json index e75b3050ccd5..6a11e5505957 100644 --- a/tools/perf/pmu-events/arch/x86/grandridge/uncore-memory.json +++ b/tools/perf/pmu-events/arch/x86/grandridge/uncore-memory.json @@ -189,6 +189,256 @@ "Unit": "IMC" }, { + "BriefDescription": "# of cycles MR4 temp readings forced 2x refresh", + "Counter": "0,1,2,3", + "EventCode": "0xA7", + "EventName": "UNC_M_MR4_2XREF_CYCLES.SCH0_DIMM0", + "Experimental": "1", + "PerPkg": "1", + "PublicDescription": "-", + "UMask": "0x1", + "Unit": "IMC" + }, + { + "BriefDescription": "# of cycles MR4 temp readings forced 2x refresh", + "Counter": "0,1,2,3", + "EventCode": "0xA7", + "EventName": "UNC_M_MR4_2XREF_CYCLES.SCH0_DIMM1", + "Experimental": "1", + "PerPkg": "1", + "PublicDescription": "-", + "UMask": "0x2", + "Unit": "IMC" + }, + { + "BriefDescription": "# of cycles MR4 temp readings forced 2x refresh", + "Counter": "0,1,2,3", + "EventCode": "0xA7", + "EventName": "UNC_M_MR4_2XREF_CYCLES.SCH1_DIMM0", + "Experimental": "1", + "PerPkg": "1", + "PublicDescription": "-", + "UMask": "0x4", + "Unit": "IMC" + }, + { + "BriefDescription": "# of cycles MR4 temp readings forced 2x refresh", + "Counter": "0,1,2,3", + "EventCode": "0xA7", + "EventName": "UNC_M_MR4_2XREF_CYCLES.SCH1_DIMM1", + "Experimental": "1", + "PerPkg": "1", + "PublicDescription": "-", + "UMask": "0x8", + "Unit": "IMC" + }, + { + "BriefDescription": "# of cycles MR4 MRRs was triggered/running", + "Counter": "0,1,2,3", + "EventCode": "0xA6", + "EventName": "UNC_M_PDC_MR4ACTIVE_CYCLES.SCH0_DIMM0", + "Experimental": "1", + "PerPkg": "1", + "PublicDescription": "-", + "UMask": "0x1", + "Unit": "IMC" + }, + { + "BriefDescription": "# of cycles MR4 MRRs was triggered/running", + "Counter": "0,1,2,3", + "EventCode": "0xA6", + "EventName": "UNC_M_PDC_MR4ACTIVE_CYCLES.SCH0_DIMM1", + "Experimental": "1", + "PerPkg": "1", + "PublicDescription": "-", + "UMask": "0x2", + "Unit": "IMC" + }, + { + "BriefDescription": "# of cycles MR4 MRRs was triggered/running", + "Counter": "0,1,2,3", + "EventCode": "0xA6", + "EventName": "UNC_M_PDC_MR4ACTIVE_CYCLES.SCH1_DIMM0", + "Experimental": "1", + "PerPkg": "1", + "PublicDescription": "-", + "UMask": "0x4", + "Unit": "IMC" + }, + { + "BriefDescription": "# of cycles MR4 MRRs was triggered/running", + "Counter": "0,1,2,3", + "EventCode": "0xA6", + "EventName": "UNC_M_PDC_MR4ACTIVE_CYCLES.SCH1_DIMM1", + "Experimental": "1", + "PerPkg": "1", + "PublicDescription": "-", + "UMask": "0x8", + "Unit": "IMC" + }, + { + "BriefDescription": "# of cycles a given rank is in Power Down Mode", + "Counter": "0,1,2,3", + "EventCode": "0x47", + "EventName": "UNC_M_POWERDOWN_CYCLES.SCH0_RANK0", + "Experimental": "1", + "PerPkg": "1", + "PublicDescription": "-", + "UMask": "0x1", + "Unit": "IMC" + }, + { + "BriefDescription": "# of cycles a given rank is in Power Down Mode", + "Counter": "0,1,2,3", + "EventCode": "0x47", + "EventName": "UNC_M_POWERDOWN_CYCLES.SCH0_RANK1", + "Experimental": "1", + "PerPkg": "1", + "PublicDescription": "-", + "UMask": "0x2", + "Unit": "IMC" + }, + { + "BriefDescription": "# of cycles a given rank is in Power Down Mode", + "Counter": "0,1,2,3", + "EventCode": "0x47", + "EventName": "UNC_M_POWERDOWN_CYCLES.SCH0_RANK2", + "Experimental": "1", + "PerPkg": "1", + "PublicDescription": "-", + "UMask": "0x4", + "Unit": "IMC" + }, + { + "BriefDescription": "# of cycles a given rank is in Power Down Mode", + "Counter": "0,1,2,3", + "EventCode": "0x47", + "EventName": "UNC_M_POWERDOWN_CYCLES.SCH0_RANK3", + "Experimental": "1", + "PerPkg": "1", + "PublicDescription": "-", + "UMask": "0x8", + "Unit": "IMC" + }, + { + "BriefDescription": "# of cycles a given rank is in Power Down Mode", + "Counter": "0,1,2,3", + "EventCode": "0x47", + "EventName": "UNC_M_POWERDOWN_CYCLES.SCH1_RANK0", + "Experimental": "1", + "PerPkg": "1", + "PublicDescription": "-", + "UMask": "0x10", + "Unit": "IMC" + }, + { + "BriefDescription": "# of cycles a given rank is in Power Down Mode", + "Counter": "0,1,2,3", + "EventCode": "0x47", + "EventName": "UNC_M_POWERDOWN_CYCLES.SCH1_RANK1", + "Experimental": "1", + "PerPkg": "1", + "PublicDescription": "-", + "UMask": "0x20", + "Unit": "IMC" + }, + { + "BriefDescription": "# of cycles a given rank is in Power Down Mode", + "Counter": "0,1,2,3", + "EventCode": "0x47", + "EventName": "UNC_M_POWERDOWN_CYCLES.SCH1_RANK2", + "Experimental": "1", + "PerPkg": "1", + "PublicDescription": "-", + "UMask": "0x40", + "Unit": "IMC" + }, + { + "BriefDescription": "# of cycles a given rank is in Power Down Mode", + "Counter": "0,1,2,3", + "EventCode": "0x47", + "EventName": "UNC_M_POWERDOWN_CYCLES.SCH1_RANK3", + "Experimental": "1", + "PerPkg": "1", + "PublicDescription": "-", + "UMask": "0x80", + "Unit": "IMC" + }, + { + "BriefDescription": "# of cycles a given rank is in Power Down Mode and all pages are closed", + "Counter": "0,1,2,3", + "EventCode": "0x88", + "EventName": "UNC_M_POWER_CHANNEL_PPD_CYCLES", + "Experimental": "1", + "PerPkg": "1", + "PublicDescription": "-", + "Unit": "IMC" + }, + { + "BriefDescription": "# of cycles Throttling at Critical level on specified DIMM and throttle level is zero.", + "Counter": "0,1,2,3", + "EventCode": "0x89", + "EventName": "UNC_M_POWER_CRITICAL_THROTTLE_CYCLES.SLOT0", + "Experimental": "1", + "PerPkg": "1", + "PublicDescription": "-", + "UMask": "0x1", + "Unit": "IMC" + }, + { + "BriefDescription": "# of cycles Throttling at Critical level on specified DIMM and throttle level is zero.", + "Counter": "0,1,2,3", + "EventCode": "0x89", + "EventName": "UNC_M_POWER_CRITICAL_THROTTLE_CYCLES.SLOT1", + "Experimental": "1", + "PerPkg": "1", + "PublicDescription": "-", + "UMask": "0x2", + "Unit": "IMC" + }, + { + "BriefDescription": "UNC_M_POWER_THROTTLE_CYCLES.BW_SLOT0", + "Counter": "0,1,2,3", + "EventCode": "0x46", + "EventName": "UNC_M_POWER_THROTTLE_CYCLES.BW_SLOT0", + "Experimental": "1", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "IMC" + }, + { + "BriefDescription": "UNC_M_POWER_THROTTLE_CYCLES.BW_SLOT1", + "Counter": "0,1,2,3", + "EventCode": "0x46", + "EventName": "UNC_M_POWER_THROTTLE_CYCLES.BW_SLOT1", + "Experimental": "1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "IMC" + }, + { + "BriefDescription": "MR4 temp reading is throttling", + "Counter": "0,1,2,3", + "EventCode": "0x46", + "EventName": "UNC_M_POWER_THROTTLE_CYCLES.MR4BLKEN", + "Experimental": "1", + "PerPkg": "1", + "PublicDescription": "-", + "UMask": "0x8", + "Unit": "IMC" + }, + { + "BriefDescription": "RAPL is throttling", + "Counter": "0,1,2,3", + "EventCode": "0x46", + "EventName": "UNC_M_POWER_THROTTLE_CYCLES.RAPLBLK", + "Experimental": "1", + "PerPkg": "1", + "PublicDescription": "-", + "UMask": "0x4", + "Unit": "IMC" + }, + { "BriefDescription": "DRAM Precharge commands. : Counts the number of DRAM Precharge commands sent on this channel.", "Counter": "0,1,2,3", "EventCode": "0x03", @@ -361,6 +611,94 @@ "Unit": "IMC" }, { + "BriefDescription": "# of cycles Throttling at Critical level on specified DIMM", + "Counter": "0,1,2,3", + "EventCode": "0x8e", + "EventName": "UNC_M_THROTTLE_CRIT_CYCLES.SLOT0", + "Experimental": "1", + "PerPkg": "1", + "PublicDescription": "-", + "UMask": "0x1", + "Unit": "IMC" + }, + { + "BriefDescription": "# of cycles Throttling at Critical level on specified DIMM", + "Counter": "0,1,2,3", + "EventCode": "0x8e", + "EventName": "UNC_M_THROTTLE_CRIT_CYCLES.SLOT1", + "Experimental": "1", + "PerPkg": "1", + "PublicDescription": "-", + "UMask": "0x2", + "Unit": "IMC" + }, + { + "BriefDescription": "# of cycles Throttling at High level on specified DIMM", + "Counter": "0,1,2,3", + "EventCode": "0x8d", + "EventName": "UNC_M_THROTTLE_HIGH_CYCLES.SLOT0", + "Experimental": "1", + "PerPkg": "1", + "PublicDescription": "-", + "UMask": "0x1", + "Unit": "IMC" + }, + { + "BriefDescription": "# of cycles Throttling at High level on specified DIMM", + "Counter": "0,1,2,3", + "EventCode": "0x8d", + "EventName": "UNC_M_THROTTLE_HIGH_CYCLES.SLOT1", + "Experimental": "1", + "PerPkg": "1", + "PublicDescription": "-", + "UMask": "0x2", + "Unit": "IMC" + }, + { + "BriefDescription": "# of cycles Throttling at Normal level on specified DIMM", + "Counter": "0,1,2,3", + "EventCode": "0x8b", + "EventName": "UNC_M_THROTTLE_LOW_CYCLES.SLOT0", + "Experimental": "1", + "PerPkg": "1", + "PublicDescription": "-", + "UMask": "0x1", + "Unit": "IMC" + }, + { + "BriefDescription": "# of cycles Throttling at Normal level on specified DIMM", + "Counter": "0,1,2,3", + "EventCode": "0x8b", + "EventName": "UNC_M_THROTTLE_LOW_CYCLES.SLOT1", + "Experimental": "1", + "PerPkg": "1", + "PublicDescription": "-", + "UMask": "0x2", + "Unit": "IMC" + }, + { + "BriefDescription": "# of cycles Throttling at Mid level on specified DIMM", + "Counter": "0,1,2,3", + "EventCode": "0x8c", + "EventName": "UNC_M_THROTTLE_MID_CYCLES.SLOT0", + "Experimental": "1", + "PerPkg": "1", + "PublicDescription": "-", + "UMask": "0x1", + "Unit": "IMC" + }, + { + "BriefDescription": "# of cycles Throttling at Mid level on specified DIMM", + "Counter": "0,1,2,3", + "EventCode": "0x8c", + "EventName": "UNC_M_THROTTLE_MID_CYCLES.SLOT1", + "Experimental": "1", + "PerPkg": "1", + "PublicDescription": "-", + "UMask": "0x2", + "Unit": "IMC" + }, + { "BriefDescription": "Write Pending Queue Allocations", "Counter": "0,1,2,3", "EventCode": "0x22", diff --git a/tools/perf/pmu-events/arch/x86/graniterapids/cache.json b/tools/perf/pmu-events/arch/x86/graniterapids/cache.json index d155da8610d8..32f99a8a3871 100644 --- a/tools/perf/pmu-events/arch/x86/graniterapids/cache.json +++ b/tools/perf/pmu-events/arch/x86/graniterapids/cache.json @@ -4,6 +4,7 @@ "Counter": "0,1,2,3", "EventCode": "0x51", "EventName": "L1D.HWPF_MISS", + "PublicDescription": "L1D.HWPF_MISS Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x20" }, @@ -12,7 +13,7 @@ "Counter": "0,1,2,3", "EventCode": "0x51", "EventName": "L1D.REPLACEMENT", - "PublicDescription": "Counts L1D data line replacements including opportunistic replacements, and replacements that require stall-for-replace or block-for-replace.", + "PublicDescription": "Counts L1D data line replacements including opportunistic replacements, and replacements that require stall-for-replace or block-for-replace. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -21,7 +22,7 @@ "Counter": "0,1,2,3", "EventCode": "0x48", "EventName": "L1D_PEND_MISS.FB_FULL", - "PublicDescription": "Counts number of cycles a demand request has waited due to L1D Fill Buffer (FB) unavailability. Demand requests include cacheable/uncacheable demand load, store, lock or SW prefetch accesses.", + "PublicDescription": "Counts number of cycles a demand request has waited due to L1D Fill Buffer (FB) unavailability. Demand requests include cacheable/uncacheable demand load, store, lock or SW prefetch accesses. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x2" }, @@ -32,7 +33,7 @@ "EdgeDetect": "1", "EventCode": "0x48", "EventName": "L1D_PEND_MISS.FB_FULL_PERIODS", - "PublicDescription": "Counts number of phases a demand request has waited due to L1D Fill Buffer (FB) unavailability. Demand requests include cacheable/uncacheable demand load, store, lock or SW prefetch accesses.", + "PublicDescription": "Counts number of phases a demand request has waited due to L1D Fill Buffer (FB) unavailability. Demand requests include cacheable/uncacheable demand load, store, lock or SW prefetch accesses. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x2" }, @@ -41,7 +42,7 @@ "Counter": "0,1,2,3", "EventCode": "0x48", "EventName": "L1D_PEND_MISS.L2_STALLS", - "PublicDescription": "Counts number of cycles a demand request has waited due to L1D due to lack of L2 resources. Demand requests include cacheable/uncacheable demand load, store, lock or SW prefetch accesses.", + "PublicDescription": "Counts number of cycles a demand request has waited due to L1D due to lack of L2 resources. Demand requests include cacheable/uncacheable demand load, store, lock or SW prefetch accesses. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x4" }, @@ -50,7 +51,7 @@ "Counter": "0,1,2,3", "EventCode": "0x48", "EventName": "L1D_PEND_MISS.PENDING", - "PublicDescription": "Counts number of L1D misses that are outstanding in each cycle, that is each cycle the number of Fill Buffers (FB) outstanding required by Demand Reads. FB either is held by demand loads, or it is held by non-demand loads and gets hit at least once by demand. The valid outstanding interval is defined until the FB deallocation by one of the following ways: from FB allocation, if FB is allocated by demand from the demand Hit FB, if it is allocated by hardware or software prefetch. Note: In the L1D, a Demand Read contains cacheable or noncacheable demand loads, including ones causing cache-line splits and reads due to page walks resulted from any request type.", + "PublicDescription": "Counts number of L1D misses that are outstanding in each cycle, that is each cycle the number of Fill Buffers (FB) outstanding required by Demand Reads. FB either is held by demand loads, or it is held by non-demand loads and gets hit at least once by demand. The valid outstanding interval is defined until the FB deallocation by one of the following ways: from FB allocation, if FB is allocated by demand from the demand Hit FB, if it is allocated by hardware or software prefetch. Note: In the L1D, a Demand Read contains cacheable or noncacheable demand loads, including ones causing cache-line splits and reads due to page walks resulted from any request type. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x1" }, @@ -60,7 +61,7 @@ "CounterMask": "1", "EventCode": "0x48", "EventName": "L1D_PEND_MISS.PENDING_CYCLES", - "PublicDescription": "Counts duration of L1D miss outstanding in cycles.", + "PublicDescription": "Counts duration of L1D miss outstanding in cycles. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x1" }, @@ -69,7 +70,7 @@ "Counter": "0,1,2,3", "EventCode": "0x25", "EventName": "L2_LINES_IN.ALL", - "PublicDescription": "Counts the number of L2 cache lines filling the L2. Counting does not cover rejects.", + "PublicDescription": "Counts the number of L2 cache lines filling the L2. Counting does not cover rejects. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1f" }, @@ -78,7 +79,7 @@ "Counter": "0,1,2,3", "EventCode": "0x26", "EventName": "L2_LINES_OUT.NON_SILENT", - "PublicDescription": "Counts the number of lines that are evicted by L2 cache when triggered by an L2 cache fill. Those lines are in Modified state. Modified lines are written back to L3", + "PublicDescription": "Counts the number of lines that are evicted by L2 cache when triggered by an L2 cache fill. Those lines are in Modified state. Modified lines are written back to L3 Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0x2" }, @@ -87,7 +88,7 @@ "Counter": "0,1,2,3", "EventCode": "0x26", "EventName": "L2_LINES_OUT.SILENT", - "PublicDescription": "Counts the number of lines that are silently dropped by L2 cache. These lines are typically in Shared or Exclusive state. A non-threaded event.", + "PublicDescription": "Counts the number of lines that are silently dropped by L2 cache. These lines are typically in Shared or Exclusive state. A non-threaded event. Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0x1" }, @@ -96,7 +97,7 @@ "Counter": "0,1,2,3", "EventCode": "0x26", "EventName": "L2_LINES_OUT.USELESS_HWPF", - "PublicDescription": "Counts the number of cache lines that have been prefetched by the L2 hardware prefetcher but not used by demand access when evicted from the L2 cache", + "PublicDescription": "Counts the number of cache lines that have been prefetched by the L2 hardware prefetcher but not used by demand access when evicted from the L2 cache Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0x4" }, @@ -105,7 +106,7 @@ "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_REQUEST.ALL", - "PublicDescription": "Counts all requests that were hit or true misses in L2 cache. True-miss excludes misses that were merged with ongoing L2 misses. [This event is alias to L2_RQSTS.REFERENCES]", + "PublicDescription": "Counts all requests that were hit or true misses in L2 cache. True-miss excludes misses that were merged with ongoing L2 misses. [This event is alias to L2_RQSTS.REFERENCES] Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0xff" }, @@ -114,7 +115,7 @@ "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_REQUEST.HIT", - "PublicDescription": "Counts all requests that hit L2 cache. [This event is alias to L2_RQSTS.HIT]", + "PublicDescription": "Counts all requests that hit L2 cache. [This event is alias to L2_RQSTS.HIT] Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0xdf" }, @@ -123,7 +124,7 @@ "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_REQUEST.MISS", - "PublicDescription": "Counts read requests of any type with true-miss in the L2 cache. True-miss excludes L2 misses that were merged with ongoing L2 misses. [This event is alias to L2_RQSTS.MISS]", + "PublicDescription": "Counts read requests of any type with true-miss in the L2 cache. True-miss excludes L2 misses that were merged with ongoing L2 misses. [This event is alias to L2_RQSTS.MISS] Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0x3f" }, @@ -132,7 +133,7 @@ "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_RQSTS.ALL_CODE_RD", - "PublicDescription": "Counts the total number of L2 code requests.", + "PublicDescription": "Counts the total number of L2 code requests. Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0xe4" }, @@ -141,7 +142,7 @@ "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_RQSTS.ALL_DEMAND_DATA_RD", - "PublicDescription": "Counts Demand Data Read requests accessing the L2 cache. These requests may hit or miss L2 cache. True-miss exclude misses that were merged with ongoing L2 misses. An access is counted once.", + "PublicDescription": "Counts Demand Data Read requests accessing the L2 cache. These requests may hit or miss L2 cache. True-miss exclude misses that were merged with ongoing L2 misses. An access is counted once. Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0xe1" }, @@ -150,7 +151,7 @@ "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_RQSTS.ALL_DEMAND_MISS", - "PublicDescription": "Counts demand requests that miss L2 cache.", + "PublicDescription": "Counts demand requests that miss L2 cache. Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0x27" }, @@ -159,7 +160,7 @@ "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_RQSTS.ALL_DEMAND_REFERENCES", - "PublicDescription": "Counts demand requests to L2 cache.", + "PublicDescription": "Counts demand requests to L2 cache. Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0xe7" }, @@ -168,6 +169,7 @@ "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_RQSTS.ALL_HWPF", + "PublicDescription": "L2_RQSTS.ALL_HWPF Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0xf0" }, @@ -176,7 +178,7 @@ "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_RQSTS.ALL_RFO", - "PublicDescription": "Counts the total number of RFO (read for ownership) requests to L2 cache. L2 RFO requests include both L1D demand RFO misses as well as L1D RFO prefetches.", + "PublicDescription": "Counts the total number of RFO (read for ownership) requests to L2 cache. L2 RFO requests include both L1D demand RFO misses as well as L1D RFO prefetches. Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0xe2" }, @@ -185,7 +187,7 @@ "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_RQSTS.CODE_RD_HIT", - "PublicDescription": "Counts L2 cache hits when fetching instructions, code reads.", + "PublicDescription": "Counts L2 cache hits when fetching instructions, code reads. Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0xc4" }, @@ -194,7 +196,7 @@ "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_RQSTS.CODE_RD_MISS", - "PublicDescription": "Counts L2 cache misses when fetching instructions.", + "PublicDescription": "Counts L2 cache misses when fetching instructions. Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0x24" }, @@ -203,7 +205,7 @@ "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_RQSTS.DEMAND_DATA_RD_HIT", - "PublicDescription": "Counts the number of demand Data Read requests initiated by load instructions that hit L2 cache.", + "PublicDescription": "Counts the number of demand Data Read requests initiated by load instructions that hit L2 cache. Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0xc1" }, @@ -212,7 +214,7 @@ "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_RQSTS.DEMAND_DATA_RD_MISS", - "PublicDescription": "Counts demand Data Read requests with true-miss in the L2 cache. True-miss excludes misses that were merged with ongoing L2 misses. An access is counted once.", + "PublicDescription": "Counts demand Data Read requests with true-miss in the L2 cache. True-miss excludes misses that were merged with ongoing L2 misses. An access is counted once. Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0x21" }, @@ -221,7 +223,7 @@ "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_RQSTS.HIT", - "PublicDescription": "Counts all requests that hit L2 cache. [This event is alias to L2_REQUEST.HIT]", + "PublicDescription": "Counts all requests that hit L2 cache. [This event is alias to L2_REQUEST.HIT] Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0xdf" }, @@ -230,6 +232,7 @@ "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_RQSTS.HWPF_MISS", + "PublicDescription": "L2_RQSTS.HWPF_MISS Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0x30" }, @@ -238,7 +241,7 @@ "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_RQSTS.MISS", - "PublicDescription": "Counts read requests of any type with true-miss in the L2 cache. True-miss excludes L2 misses that were merged with ongoing L2 misses. [This event is alias to L2_REQUEST.MISS]", + "PublicDescription": "Counts read requests of any type with true-miss in the L2 cache. True-miss excludes L2 misses that were merged with ongoing L2 misses. [This event is alias to L2_REQUEST.MISS] Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0x3f" }, @@ -247,7 +250,7 @@ "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_RQSTS.REFERENCES", - "PublicDescription": "Counts all requests that were hit or true misses in L2 cache. True-miss excludes misses that were merged with ongoing L2 misses. [This event is alias to L2_REQUEST.ALL]", + "PublicDescription": "Counts all requests that were hit or true misses in L2 cache. True-miss excludes misses that were merged with ongoing L2 misses. [This event is alias to L2_REQUEST.ALL] Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0xff" }, @@ -256,7 +259,7 @@ "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_RQSTS.RFO_HIT", - "PublicDescription": "Counts the RFO (Read-for-Ownership) requests that hit L2 cache.", + "PublicDescription": "Counts the RFO (Read-for-Ownership) requests that hit L2 cache. Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0xc2" }, @@ -265,7 +268,7 @@ "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_RQSTS.RFO_MISS", - "PublicDescription": "Counts the RFO (Read-for-Ownership) requests that miss L2 cache.", + "PublicDescription": "Counts the RFO (Read-for-Ownership) requests that miss L2 cache. Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0x22" }, @@ -274,7 +277,7 @@ "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_RQSTS.SWPF_HIT", - "PublicDescription": "Counts Software prefetch requests that hit the L2 cache. Accounts for PREFETCHNTA and PREFETCHT0/1/2 instructions when FB is not full.", + "PublicDescription": "Counts Software prefetch requests that hit the L2 cache. Accounts for PREFETCHNTA and PREFETCHT0/1/2 instructions when FB is not full. Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0xc8" }, @@ -283,7 +286,7 @@ "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_RQSTS.SWPF_MISS", - "PublicDescription": "Counts Software prefetch requests that miss the L2 cache. Accounts for PREFETCHNTA and PREFETCHT0/1/2 instructions when FB is not full.", + "PublicDescription": "Counts Software prefetch requests that miss the L2 cache. Accounts for PREFETCHNTA and PREFETCHT0/1/2 instructions when FB is not full. Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0x28" }, @@ -292,7 +295,7 @@ "Counter": "0,1,2,3", "EventCode": "0x23", "EventName": "L2_TRANS.L2_WB", - "PublicDescription": "Counts L2 writebacks that access L2 cache.", + "PublicDescription": "Counts L2 writebacks that access L2 cache. Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0x40" }, @@ -301,7 +304,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0x2e", "EventName": "LONGEST_LAT_CACHE.MISS", - "PublicDescription": "Counts core-originated cacheable requests that miss the L3 cache (Longest Latency cache). Requests include data and code reads, Reads-for-Ownership (RFOs), speculative accesses and hardware prefetches to the L1 and L2. It does not include hardware prefetches to the L3, and may not count other types of requests to the L3.", + "PublicDescription": "Counts core-originated cacheable requests that miss the L3 cache (Longest Latency cache). Requests include data and code reads, Reads-for-Ownership (RFOs), speculative accesses and hardware prefetches to the L1 and L2. It does not include hardware prefetches to the L3, and may not count other types of requests to the L3. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x41" }, @@ -310,7 +313,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0x2e", "EventName": "LONGEST_LAT_CACHE.REFERENCE", - "PublicDescription": "Counts core-originated cacheable requests to the L3 cache (Longest Latency cache). Requests include data and code reads, Reads-for-Ownership (RFOs), speculative accesses and hardware prefetches to the L1 and L2. It does not include hardware prefetches to the L3, and may not count other types of requests to the L3.", + "PublicDescription": "Counts core-originated cacheable requests to the L3 cache (Longest Latency cache). Requests include data and code reads, Reads-for-Ownership (RFOs), speculative accesses and hardware prefetches to the L1 and L2. It does not include hardware prefetches to the L3, and may not count other types of requests to the L3. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x4f" }, @@ -320,7 +323,7 @@ "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_INST_RETIRED.ALL_LOADS", - "PublicDescription": "Counts all retired load instructions. This event accounts for SW prefetch instructions of PREFETCHNTA or PREFETCHT0/1/2 or PREFETCHW.", + "PublicDescription": "Counts all retired load instructions. This event accounts for SW prefetch instructions of PREFETCHNTA or PREFETCHT0/1/2 or PREFETCHW. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x81" }, @@ -330,7 +333,7 @@ "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_INST_RETIRED.ALL_STORES", - "PublicDescription": "Counts all retired store instructions.", + "PublicDescription": "Counts all retired store instructions. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x82" }, @@ -340,7 +343,7 @@ "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_INST_RETIRED.ANY", - "PublicDescription": "Counts all retired memory instructions - loads and stores.", + "PublicDescription": "Counts all retired memory instructions - loads and stores. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x83" }, @@ -350,7 +353,10 @@ "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_INST_RETIRED.LOCK_LOADS", - "PublicDescription": "Counts retired load instructions with locked access.", + "PublicDescription": "Counts retired load instructions with locked access. Available PDIST counters: 0", + "RetirementLatencyMax": 5156, + "RetirementLatencyMean": 63.76, + "RetirementLatencyMin": 15, "SampleAfterValue": "100007", "UMask": "0x21" }, @@ -360,7 +366,10 @@ "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_INST_RETIRED.SPLIT_LOADS", - "PublicDescription": "Counts retired load instructions that split across a cacheline boundary.", + "PublicDescription": "Counts retired load instructions that split across a cacheline boundary. Available PDIST counters: 0", + "RetirementLatencyMax": 4704, + "RetirementLatencyMean": 3.97, + "RetirementLatencyMin": 0, "SampleAfterValue": "100003", "UMask": "0x41" }, @@ -370,7 +379,10 @@ "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_INST_RETIRED.SPLIT_STORES", - "PublicDescription": "Counts retired store instructions that split across a cacheline boundary.", + "PublicDescription": "Counts retired store instructions that split across a cacheline boundary. Available PDIST counters: 0", + "RetirementLatencyMax": 65535, + "RetirementLatencyMean": 19.0, + "RetirementLatencyMin": 0, "SampleAfterValue": "100003", "UMask": "0x42" }, @@ -380,7 +392,10 @@ "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_INST_RETIRED.STLB_HIT_LOADS", - "PublicDescription": "Number of retired load instructions with a clean hit in the 2nd-level TLB (STLB).", + "PublicDescription": "Number of retired load instructions with a clean hit in the 2nd-level TLB (STLB). Available PDIST counters: 0", + "RetirementLatencyMax": 3424, + "RetirementLatencyMean": 1.57, + "RetirementLatencyMin": 0, "SampleAfterValue": "100003", "UMask": "0x9" }, @@ -390,7 +405,10 @@ "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_INST_RETIRED.STLB_HIT_STORES", - "PublicDescription": "Number of retired store instructions that hit in the 2nd-level TLB (STLB).", + "PublicDescription": "Number of retired store instructions that hit in the 2nd-level TLB (STLB). Available PDIST counters: 0", + "RetirementLatencyMax": 65535, + "RetirementLatencyMean": 5.24, + "RetirementLatencyMin": 0, "SampleAfterValue": "100003", "UMask": "0xa" }, @@ -400,7 +418,7 @@ "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_INST_RETIRED.STLB_MISS_LOADS", - "PublicDescription": "Number of retired load instructions that (start a) miss in the 2nd-level TLB (STLB).", + "PublicDescription": "Number of retired load instructions that (start a) miss in the 2nd-level TLB (STLB). Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x11" }, @@ -410,7 +428,7 @@ "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_INST_RETIRED.STLB_MISS_STORES", - "PublicDescription": "Number of retired store instructions that (start a) miss in the 2nd-level TLB (STLB).", + "PublicDescription": "Number of retired store instructions that (start a) miss in the 2nd-level TLB (STLB). Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x12" }, @@ -419,7 +437,7 @@ "Counter": "0,1,2,3", "EventCode": "0x43", "EventName": "MEM_LOAD_COMPLETED.L1_MISS_ANY", - "PublicDescription": "Number of completed demand load requests that missed the L1 data cache including shadow misses (FB hits, merge to an ongoing L1D miss)", + "PublicDescription": "Number of completed demand load requests that missed the L1 data cache including shadow misses (FB hits, merge to an ongoing L1D miss) Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0xfd" }, @@ -429,7 +447,10 @@ "Data_LA": "1", "EventCode": "0xd2", "EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD", - "PublicDescription": "Counts retired load instructions whose data sources were HitM responses from shared L3.", + "PublicDescription": "Counts retired load instructions whose data sources were HitM responses from shared L3. Available PDIST counters: 0", + "RetirementLatencyMax": 4472, + "RetirementLatencyMean": 353.04, + "RetirementLatencyMin": 0, "SampleAfterValue": "20011", "UMask": "0x4" }, @@ -439,7 +460,10 @@ "Data_LA": "1", "EventCode": "0xd2", "EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS", - "PublicDescription": "Counts the retired load instructions whose data sources were L3 hit and cross-core snoop missed in on-pkg core cache.", + "PublicDescription": "Counts the retired load instructions whose data sources were L3 hit and cross-core snoop missed in on-pkg core cache. Available PDIST counters: 0", + "RetirementLatencyMax": 830, + "RetirementLatencyMean": 125.27, + "RetirementLatencyMin": 0, "SampleAfterValue": "20011", "UMask": "0x1" }, @@ -449,7 +473,7 @@ "Data_LA": "1", "EventCode": "0xd2", "EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_NONE", - "PublicDescription": "Counts retired load instructions whose data sources were hits in L3 without snoops required.", + "PublicDescription": "Counts retired load instructions whose data sources were hits in L3 without snoops required. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x8" }, @@ -459,7 +483,10 @@ "Data_LA": "1", "EventCode": "0xd2", "EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_NO_FWD", - "PublicDescription": "Counts retired load instructions whose data sources were L3 and cross-core snoop hits in on-pkg core cache.", + "PublicDescription": "Counts retired load instructions whose data sources were L3 and cross-core snoop hits in on-pkg core cache. Available PDIST counters: 0", + "RetirementLatencyMax": 3939, + "RetirementLatencyMean": 289.9, + "RetirementLatencyMin": 0, "SampleAfterValue": "20011", "UMask": "0x2" }, @@ -469,7 +496,10 @@ "Data_LA": "1", "EventCode": "0xd3", "EventName": "MEM_LOAD_L3_MISS_RETIRED.LOCAL_DRAM", - "PublicDescription": "Retired load instructions which data sources missed L3 but serviced from local DRAM.", + "PublicDescription": "Retired load instructions which data sources missed L3 but serviced from local DRAM. Available PDIST counters: 0", + "RetirementLatencyMax": 4146, + "RetirementLatencyMean": 115.83, + "RetirementLatencyMin": 0, "SampleAfterValue": "100007", "UMask": "0x1" }, @@ -479,6 +509,10 @@ "Data_LA": "1", "EventCode": "0xd3", "EventName": "MEM_LOAD_L3_MISS_RETIRED.REMOTE_DRAM", + "PublicDescription": "MEM_LOAD_L3_MISS_RETIRED.REMOTE_DRAM Available PDIST counters: 0", + "RetirementLatencyMax": 3572, + "RetirementLatencyMean": 430.22, + "RetirementLatencyMin": 0, "SampleAfterValue": "1000003", "UMask": "0x2" }, @@ -488,7 +522,10 @@ "Data_LA": "1", "EventCode": "0xd3", "EventName": "MEM_LOAD_L3_MISS_RETIRED.REMOTE_FWD", - "PublicDescription": "Retired load instructions whose data sources was forwarded from a remote cache.", + "PublicDescription": "Retired load instructions whose data sources was forwarded from a remote cache. Available PDIST counters: 0", + "RetirementLatencyMax": 8552, + "RetirementLatencyMean": 125.36, + "RetirementLatencyMin": 0, "SampleAfterValue": "100007", "UMask": "0x8" }, @@ -498,6 +535,10 @@ "Data_LA": "1", "EventCode": "0xd3", "EventName": "MEM_LOAD_L3_MISS_RETIRED.REMOTE_HITM", + "PublicDescription": "MEM_LOAD_L3_MISS_RETIRED.REMOTE_HITM Available PDIST counters: 0", + "RetirementLatencyMax": 2580, + "RetirementLatencyMean": 135.29, + "RetirementLatencyMin": 0, "SampleAfterValue": "1000003", "UMask": "0x4" }, @@ -507,7 +548,7 @@ "Data_LA": "1", "EventCode": "0xd4", "EventName": "MEM_LOAD_MISC_RETIRED.UC", - "PublicDescription": "Retired instructions with at least one load to uncacheable memory-type, or at least one cache-line split locked access (Bus Lock).", + "PublicDescription": "Retired instructions with at least one load to uncacheable memory-type, or at least one cache-line split locked access (Bus Lock). Available PDIST counters: 0", "SampleAfterValue": "100007", "UMask": "0x4" }, @@ -517,7 +558,7 @@ "Data_LA": "1", "EventCode": "0xd1", "EventName": "MEM_LOAD_RETIRED.FB_HIT", - "PublicDescription": "Counts retired load instructions with at least one uop was load missed in L1 but hit FB (Fill Buffers) due to preceding miss to the same cache line with data not ready.", + "PublicDescription": "Counts retired load instructions with at least one uop was load missed in L1 but hit FB (Fill Buffers) due to preceding miss to the same cache line with data not ready. Available PDIST counters: 0", "SampleAfterValue": "100007", "UMask": "0x40" }, @@ -527,7 +568,7 @@ "Data_LA": "1", "EventCode": "0xd1", "EventName": "MEM_LOAD_RETIRED.L1_HIT", - "PublicDescription": "Counts retired load instructions with at least one uop that hit in the L1 data cache. This event includes all SW prefetches and lock instructions regardless of the data source.", + "PublicDescription": "Counts retired load instructions with at least one uop that hit in the L1 data cache. This event includes all SW prefetches and lock instructions regardless of the data source. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x1" }, @@ -537,7 +578,7 @@ "Data_LA": "1", "EventCode": "0xd1", "EventName": "MEM_LOAD_RETIRED.L1_MISS", - "PublicDescription": "Counts retired load instructions with at least one uop that missed in the L1 cache.", + "PublicDescription": "Counts retired load instructions with at least one uop that missed in the L1 cache. Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0x8" }, @@ -547,7 +588,10 @@ "Data_LA": "1", "EventCode": "0xd1", "EventName": "MEM_LOAD_RETIRED.L2_HIT", - "PublicDescription": "Counts retired load instructions with L2 cache hits as data sources.", + "PublicDescription": "Counts retired load instructions with L2 cache hits as data sources. Available PDIST counters: 0", + "RetirementLatencyMax": 7140, + "RetirementLatencyMean": 5.71, + "RetirementLatencyMin": 0, "SampleAfterValue": "200003", "UMask": "0x2" }, @@ -557,7 +601,7 @@ "Data_LA": "1", "EventCode": "0xd1", "EventName": "MEM_LOAD_RETIRED.L2_MISS", - "PublicDescription": "Counts retired load instructions missed L2 cache as data sources.", + "PublicDescription": "Counts retired load instructions missed L2 cache as data sources. Available PDIST counters: 0", "SampleAfterValue": "100021", "UMask": "0x10" }, @@ -567,7 +611,10 @@ "Data_LA": "1", "EventCode": "0xd1", "EventName": "MEM_LOAD_RETIRED.L3_HIT", - "PublicDescription": "Counts retired load instructions with at least one uop that hit in the L3 cache.", + "PublicDescription": "Counts retired load instructions with at least one uop that hit in the L3 cache. Available PDIST counters: 0", + "RetirementLatencyMax": 5630, + "RetirementLatencyMean": 57.64, + "RetirementLatencyMin": 0, "SampleAfterValue": "100021", "UMask": "0x4" }, @@ -577,7 +624,7 @@ "Data_LA": "1", "EventCode": "0xd1", "EventName": "MEM_LOAD_RETIRED.L3_MISS", - "PublicDescription": "Counts retired load instructions with at least one uop that missed in the L3 cache.", + "PublicDescription": "Counts retired load instructions with at least one uop that missed in the L3 cache. Available PDIST counters: 0", "SampleAfterValue": "50021", "UMask": "0x20" }, @@ -586,6 +633,7 @@ "Counter": "0,1,2,3", "EventCode": "0x44", "EventName": "MEM_STORE_RETIRED.L2_HIT", + "PublicDescription": "MEM_STORE_RETIRED.L2_HIT Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0x1" }, @@ -594,17 +642,29 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xe5", "EventName": "MEM_UOP_RETIRED.ANY", - "PublicDescription": "Number of retired micro-operations (uops) for load or store memory accesses", + "PublicDescription": "Number of retired micro-operations (uops) for load or store memory accesses Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x3" }, { + "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that have any type of response.", + "Counter": "0,1,2,3", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.DEMAND_CODE_RD.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x10004", + "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that have any type of response. Available PDIST counters: 0", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that hit in the L3 or were snooped from another core's caches on the same socket.", "Counter": "0,1,2,3", "EventCode": "0x2A,0x2B", "EventName": "OCR.DEMAND_CODE_RD.L3_HIT", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x3F803C0004", + "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that hit in the L3 or were snooped from another core's caches on the same socket. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -615,6 +675,18 @@ "EventName": "OCR.DEMAND_CODE_RD.L3_HIT.SNOOP_HITM", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x10003C0004", + "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that resulted in a snoop hit a modified line in another core's caches which forwarded the data. Available PDIST counters: 0", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts demand data reads that have any type of response.", + "Counter": "0,1,2,3", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.DEMAND_DATA_RD.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x10001", + "PublicDescription": "Counts demand data reads that have any type of response. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -625,6 +697,7 @@ "EventName": "OCR.DEMAND_DATA_RD.L3_HIT", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x3F803C0001", + "PublicDescription": "Counts demand data reads that hit in the L3 or were snooped from another core's caches on the same socket. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -635,6 +708,7 @@ "EventName": "OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x10003C0001", + "PublicDescription": "Counts demand data reads that resulted in a snoop hit a modified line in another core's caches which forwarded the data. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -645,6 +719,7 @@ "EventName": "OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_NO_FWD", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x4003C0001", + "PublicDescription": "Counts demand data reads that resulted in a snoop that hit in another core, which did not forward the data. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -655,6 +730,7 @@ "EventName": "OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x8003C0001", + "PublicDescription": "Counts demand data reads that resulted in a snoop hit in another core's caches which forwarded the unmodified data to the requesting core. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -665,6 +741,7 @@ "EventName": "OCR.DEMAND_DATA_RD.REMOTE_CACHE.SNOOP_HITM", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x1030000001", + "PublicDescription": "Counts demand data reads that were supplied by a cache on a remote socket where a snoop hit a modified line in another core's caches which forwarded the data. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -675,6 +752,40 @@ "EventName": "OCR.DEMAND_DATA_RD.REMOTE_CACHE.SNOOP_HIT_WITH_FWD", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x830000001", + "PublicDescription": "Counts demand data reads that were supplied by a cache on a remote socket where a snoop hit in another core's caches which forwarded the unmodified data to the requesting core. Available PDIST counters: 0", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts demand data reads that hit a modified line in a distant L3 Cache or were snooped from a distant core's L1/L2 caches on this socket when the system is in SNC (sub-NUMA cluster) mode.", + "Counter": "0,1,2,3", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.DEMAND_DATA_RD.SNC_CACHE.HITM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x1008000001", + "PublicDescription": "Counts demand data reads that hit a modified line in a distant L3 Cache or were snooped from a distant core's L1/L2 caches on this socket when the system is in SNC (sub-NUMA cluster) mode. Available PDIST counters: 0", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts demand data reads that either hit a non-modified line in a distant L3 Cache or were snooped from a distant core's L1/L2 caches on this socket when the system is in SNC (sub-NUMA cluster) mode.", + "Counter": "0,1,2,3", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.DEMAND_DATA_RD.SNC_CACHE.HIT_WITH_FWD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x808000001", + "PublicDescription": "Counts demand data reads that either hit a non-modified line in a distant L3 Cache or were snooped from a distant core's L1/L2 caches on this socket when the system is in SNC (sub-NUMA cluster) mode. Available PDIST counters: 0", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts demand reads for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that have any type of response.", + "Counter": "0,1,2,3", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.DEMAND_RFO.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x3F3FFC0002", + "PublicDescription": "Counts demand reads for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that have any type of response. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -685,6 +796,7 @@ "EventName": "OCR.DEMAND_RFO.L3_HIT", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x3F803C0002", + "PublicDescription": "Counts demand reads for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that hit in the L3 or were snooped from another core's caches on the same socket. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -695,6 +807,29 @@ "EventName": "OCR.DEMAND_RFO.L3_HIT.SNOOP_HITM", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x10003C0002", + "PublicDescription": "Counts demand reads for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that resulted in a snoop hit a modified line in another core's caches which forwarded the data. Available PDIST counters: 0", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts writebacks of modified cachelines and streaming stores that have any type of response.", + "Counter": "0,1,2,3", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.MODIFIED_WRITE.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x10808", + "PublicDescription": "Counts writebacks of modified cachelines and streaming stores that have any type of response. Available PDIST counters: 0", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that have any type of response.", + "Counter": "0,1,2,3", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.READS_TO_CORE.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x3F3FFC4477", + "PublicDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that have any type of response. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -705,6 +840,7 @@ "EventName": "OCR.READS_TO_CORE.L3_HIT", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x3F003C4477", + "PublicDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that hit in the L3 or were snooped from another core's caches on the same socket. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -715,6 +851,18 @@ "EventName": "OCR.READS_TO_CORE.L3_HIT.SNOOP_HITM", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x10003C4477", + "PublicDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that resulted in a snoop hit a modified line in another core's caches which forwarded the data. Available PDIST counters: 0", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were not supplied by the local socket's L1, L2, or L3 caches and were supplied by a remote socket.", + "Counter": "0,1,2,3", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.READS_TO_CORE.REMOTE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x3F33004477", + "PublicDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were not supplied by the local socket's L1, L2, or L3 caches and were supplied by a remote socket. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -725,6 +873,7 @@ "EventName": "OCR.READS_TO_CORE.REMOTE_CACHE.SNOOP_FWD", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x1830004477", + "PublicDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by a cache on a remote socket where a snoop was sent and data was returned (Modified or Not Modified). Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -735,6 +884,7 @@ "EventName": "OCR.READS_TO_CORE.REMOTE_CACHE.SNOOP_HITM", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x1030004477", + "PublicDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by a cache on a remote socket where a snoop hit a modified line in another core's caches which forwarded the data. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -745,6 +895,7 @@ "EventName": "OCR.READS_TO_CORE.REMOTE_CACHE.SNOOP_HIT_WITH_FWD", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x830004477", + "PublicDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by a cache on a remote socket where a snoop hit in another core's caches which forwarded the unmodified data to the requesting core. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -755,6 +906,7 @@ "EventName": "OCR.READS_TO_CORE.SNC_CACHE.HITM", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x1008004477", + "PublicDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that hit a modified line in a distant L3 Cache or were snooped from a distant core's L1/L2 caches on this socket when the system is in SNC (sub-NUMA cluster) mode. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -765,6 +917,7 @@ "EventName": "OCR.READS_TO_CORE.SNC_CACHE.HIT_WITH_FWD", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x808004477", + "PublicDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that either hit a non-modified line in a distant L3 Cache or were snooped from a distant core's L1/L2 caches on this socket when the system is in SNC (sub-NUMA cluster) mode. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -775,6 +928,7 @@ "EventName": "OCR.RFO_TO_CORE.L3_HIT_M", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x1F80040022", + "PublicDescription": "Counts demand reads for ownership (RFO), hardware prefetch RFOs (which bring data to L2), and software prefetches for exclusive ownership (PREFETCHW) that hit to a (M)odified cacheline in the L3 or snoop filter. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -783,7 +937,7 @@ "Counter": "0,1,2,3", "EventCode": "0x21", "EventName": "OFFCORE_REQUESTS.ALL_REQUESTS", - "PublicDescription": "Counts memory transactions reached the super queue including requests initiated by the core, all L3 prefetches, page walks, etc..", + "PublicDescription": "Counts memory transactions reached the super queue including requests initiated by the core, all L3 prefetches, page walks, etc.. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x80" }, @@ -792,7 +946,7 @@ "Counter": "0,1,2,3", "EventCode": "0x21", "EventName": "OFFCORE_REQUESTS.DATA_RD", - "PublicDescription": "Counts the demand and prefetch data reads. All Core Data Reads include cacheable 'Demands' and L2 prefetchers (not L3 prefetchers). Counting also covers reads due to page walks resulted from any request type.", + "PublicDescription": "Counts the demand and prefetch data reads. All Core Data Reads include cacheable 'Demands' and L2 prefetchers (not L3 prefetchers). Counting also covers reads due to page walks resulted from any request type. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x8" }, @@ -801,7 +955,7 @@ "Counter": "0,1,2,3", "EventCode": "0x21", "EventName": "OFFCORE_REQUESTS.DEMAND_CODE_RD", - "PublicDescription": "Counts both cacheable and Non-Cacheable code read requests.", + "PublicDescription": "Counts both cacheable and Non-Cacheable code read requests. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x2" }, @@ -810,7 +964,7 @@ "Counter": "0,1,2,3", "EventCode": "0x21", "EventName": "OFFCORE_REQUESTS.DEMAND_DATA_RD", - "PublicDescription": "Counts the Demand Data Read requests sent to uncore. Use it in conjunction with OFFCORE_REQUESTS_OUTSTANDING to determine average latency in the uncore.", + "PublicDescription": "Counts the Demand Data Read requests sent to uncore. Use it in conjunction with OFFCORE_REQUESTS_OUTSTANDING to determine average latency in the uncore. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -819,7 +973,7 @@ "Counter": "0,1,2,3", "EventCode": "0x21", "EventName": "OFFCORE_REQUESTS.DEMAND_RFO", - "PublicDescription": "Counts the demand RFO (read for ownership) requests including regular RFOs, locks, ItoM.", + "PublicDescription": "Counts the demand RFO (read for ownership) requests including regular RFOs, locks, ItoM. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x4" }, @@ -829,7 +983,7 @@ "CounterMask": "1", "EventCode": "0x20", "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD", - "PublicDescription": "Counts cycles when offcore outstanding cacheable Core Data Read transactions are present in the super queue. A transaction is considered to be in the Offcore outstanding state between L2 miss and transaction completion sent to requestor (SQ de-allocation). See corresponding Umask under OFFCORE_REQUESTS.", + "PublicDescription": "Counts cycles when offcore outstanding cacheable Core Data Read transactions are present in the super queue. A transaction is considered to be in the Offcore outstanding state between L2 miss and transaction completion sent to requestor (SQ de-allocation). See corresponding Umask under OFFCORE_REQUESTS. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x8" }, @@ -839,7 +993,7 @@ "CounterMask": "1", "EventCode": "0x20", "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_CODE_RD", - "PublicDescription": "Counts the number of offcore outstanding Code Reads transactions in the super queue every cycle. The 'Offcore outstanding' state of the transaction lasts from the L2 miss until the sending transaction completion to requestor (SQ deallocation). See the corresponding Umask under OFFCORE_REQUESTS.", + "PublicDescription": "Counts the number of offcore outstanding Code Reads transactions in the super queue every cycle. The 'Offcore outstanding' state of the transaction lasts from the L2 miss until the sending transaction completion to requestor (SQ deallocation). See the corresponding Umask under OFFCORE_REQUESTS. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x2" }, @@ -849,6 +1003,7 @@ "CounterMask": "1", "EventCode": "0x20", "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_DATA_RD", + "PublicDescription": "Cycles where at least 1 outstanding demand data read request is pending. Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x1" }, @@ -858,7 +1013,7 @@ "CounterMask": "1", "EventCode": "0x20", "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO", - "PublicDescription": "Counts the number of offcore outstanding demand rfo Reads transactions in the super queue every cycle. The 'Offcore outstanding' state of the transaction lasts from the L2 miss until the sending transaction completion to requestor (SQ deallocation). See the corresponding Umask under OFFCORE_REQUESTS.", + "PublicDescription": "Counts the number of offcore outstanding demand rfo Reads transactions in the super queue every cycle. The 'Offcore outstanding' state of the transaction lasts from the L2 miss until the sending transaction completion to requestor (SQ deallocation). See the corresponding Umask under OFFCORE_REQUESTS. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x4" }, @@ -867,6 +1022,7 @@ "Counter": "0,1,2,3", "EventCode": "0x20", "EventName": "OFFCORE_REQUESTS_OUTSTANDING.DATA_RD", + "PublicDescription": "OFFCORE_REQUESTS_OUTSTANDING.DATA_RD Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x8" }, @@ -875,7 +1031,7 @@ "Counter": "0,1,2,3", "EventCode": "0x20", "EventName": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_CODE_RD", - "PublicDescription": "Counts the number of offcore outstanding Code Reads transactions in the super queue every cycle. The 'Offcore outstanding' state of the transaction lasts from the L2 miss until the sending transaction completion to requestor (SQ deallocation). See the corresponding Umask under OFFCORE_REQUESTS.", + "PublicDescription": "Counts the number of offcore outstanding Code Reads transactions in the super queue every cycle. The 'Offcore outstanding' state of the transaction lasts from the L2 miss until the sending transaction completion to requestor (SQ deallocation). See the corresponding Umask under OFFCORE_REQUESTS. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x2" }, @@ -884,7 +1040,7 @@ "Counter": "0,1,2,3", "EventCode": "0x20", "EventName": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD", - "PublicDescription": "For every cycle, increments by the number of outstanding demand data read requests pending. Requests are considered outstanding from the time they miss the core's L2 cache until the transaction completion message is sent to the requestor.", + "PublicDescription": "For every cycle, increments by the number of outstanding demand data read requests pending. Requests are considered outstanding from the time they miss the core's L2 cache until the transaction completion message is sent to the requestor. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x1" }, @@ -893,7 +1049,7 @@ "Counter": "0,1,2,3", "EventCode": "0x20", "EventName": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_RFO", - "PublicDescription": "Counts the number of off-core outstanding read-for-ownership (RFO) store transactions every cycle. An RFO transaction is considered to be in the Off-core outstanding state between L2 cache miss and transaction completion.", + "PublicDescription": "Counts the number of off-core outstanding read-for-ownership (RFO) store transactions every cycle. An RFO transaction is considered to be in the Off-core outstanding state between L2 cache miss and transaction completion. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x4" }, @@ -902,7 +1058,7 @@ "Counter": "0,1,2,3", "EventCode": "0x2c", "EventName": "SQ_MISC.BUS_LOCK", - "PublicDescription": "Counts the more expensive bus lock needed to enforce cache coherency for certain memory accesses that need to be done atomically. Can be created by issuing an atomic instruction (via the LOCK prefix) which causes a cache line split or accesses uncacheable memory.", + "PublicDescription": "Counts the more expensive bus lock needed to enforce cache coherency for certain memory accesses that need to be done atomically. Can be created by issuing an atomic instruction (via the LOCK prefix) which causes a cache line split or accesses uncacheable memory. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x10" }, @@ -911,6 +1067,7 @@ "Counter": "0,1,2,3", "EventCode": "0x40", "EventName": "SW_PREFETCH_ACCESS.ANY", + "PublicDescription": "Counts the number of PREFETCHNTA, PREFETCHW, PREFETCHT0, PREFETCHT1 or PREFETCHT2 instructions executed. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0xf" }, @@ -919,7 +1076,7 @@ "Counter": "0,1,2,3", "EventCode": "0x40", "EventName": "SW_PREFETCH_ACCESS.NTA", - "PublicDescription": "Counts the number of PREFETCHNTA instructions executed.", + "PublicDescription": "Counts the number of PREFETCHNTA instructions executed. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -928,7 +1085,7 @@ "Counter": "0,1,2,3", "EventCode": "0x40", "EventName": "SW_PREFETCH_ACCESS.PREFETCHW", - "PublicDescription": "Counts the number of PREFETCHW instructions executed.", + "PublicDescription": "Counts the number of PREFETCHW instructions executed. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x8" }, @@ -937,7 +1094,7 @@ "Counter": "0,1,2,3", "EventCode": "0x40", "EventName": "SW_PREFETCH_ACCESS.T0", - "PublicDescription": "Counts the number of PREFETCHT0 instructions executed.", + "PublicDescription": "Counts the number of PREFETCHT0 instructions executed. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x2" }, @@ -946,7 +1103,7 @@ "Counter": "0,1,2,3", "EventCode": "0x40", "EventName": "SW_PREFETCH_ACCESS.T1_T2", - "PublicDescription": "Counts the number of PREFETCHT1 or PREFETCHT2 instructions executed.", + "PublicDescription": "Counts the number of PREFETCHT1 or PREFETCHT2 instructions executed. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x4" } diff --git a/tools/perf/pmu-events/arch/x86/graniterapids/counter.json b/tools/perf/pmu-events/arch/x86/graniterapids/counter.json index 137da7efa8b1..5d3b202eadd3 100644 --- a/tools/perf/pmu-events/arch/x86/graniterapids/counter.json +++ b/tools/perf/pmu-events/arch/x86/graniterapids/counter.json @@ -73,5 +73,10 @@ "Unit": "MDF", "CountersNumFixed": "0", "CountersNumGeneric": "4" + }, + { + "Unit": "UBOX", + "CountersNumFixed": "0", + "CountersNumGeneric": "2" } ]
\ No newline at end of file diff --git a/tools/perf/pmu-events/arch/x86/graniterapids/floating-point.json b/tools/perf/pmu-events/arch/x86/graniterapids/floating-point.json index 59789eee060c..1832dd952f66 100644 --- a/tools/perf/pmu-events/arch/x86/graniterapids/floating-point.json +++ b/tools/perf/pmu-events/arch/x86/graniterapids/floating-point.json @@ -5,6 +5,7 @@ "CounterMask": "1", "EventCode": "0xb0", "EventName": "ARITH.FPDIV_ACTIVE", + "PublicDescription": "This event counts the cycles the floating point divider is busy. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x1" }, @@ -13,7 +14,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc1", "EventName": "ASSISTS.FP", - "PublicDescription": "Counts all microcode Floating Point assists.", + "PublicDescription": "Counts all microcode Floating Point assists. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x2" }, @@ -22,6 +23,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc1", "EventName": "ASSISTS.SSE_AVX_MIX", + "PublicDescription": "ASSISTS.SSE_AVX_MIX Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x10" }, @@ -30,6 +32,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xb3", "EventName": "FP_ARITH_DISPATCHED.PORT_0", + "PublicDescription": "FP_ARITH_DISPATCHED.PORT_0 [This event is alias to FP_ARITH_DISPATCHED.V0] Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x1" }, @@ -38,6 +41,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xb3", "EventName": "FP_ARITH_DISPATCHED.PORT_1", + "PublicDescription": "FP_ARITH_DISPATCHED.PORT_1 [This event is alias to FP_ARITH_DISPATCHED.V1] Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x2" }, @@ -46,6 +50,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xb3", "EventName": "FP_ARITH_DISPATCHED.PORT_5", + "PublicDescription": "FP_ARITH_DISPATCHED.PORT_5 [This event is alias to FP_ARITH_DISPATCHED.V2] Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x4" }, @@ -54,6 +59,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xb3", "EventName": "FP_ARITH_DISPATCHED.V0", + "PublicDescription": "FP_ARITH_DISPATCHED.V0 [This event is alias to FP_ARITH_DISPATCHED.PORT_0] Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x1" }, @@ -62,6 +68,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xb3", "EventName": "FP_ARITH_DISPATCHED.V1", + "PublicDescription": "FP_ARITH_DISPATCHED.V1 [This event is alias to FP_ARITH_DISPATCHED.PORT_1] Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x2" }, @@ -70,6 +77,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xb3", "EventName": "FP_ARITH_DISPATCHED.V2", + "PublicDescription": "FP_ARITH_DISPATCHED.V2 [This event is alias to FP_ARITH_DISPATCHED.PORT_5] Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x4" }, @@ -78,7 +86,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc7", "EventName": "FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE", - "PublicDescription": "Number of SSE/AVX computational 128-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 2 computation operations, one for each element. Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.", + "PublicDescription": "Number of SSE/AVX computational 128-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 2 computation operations, one for each element. Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x4" }, @@ -87,7 +95,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc7", "EventName": "FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE", - "PublicDescription": "Number of SSE/AVX computational 128-bit packed single precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 4 computation operations, one for each element. Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT RSQRT RCP DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.", + "PublicDescription": "Number of SSE/AVX computational 128-bit packed single precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 4 computation operations, one for each element. Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT RSQRT RCP DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x8" }, @@ -96,7 +104,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc7", "EventName": "FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE", - "PublicDescription": "Number of SSE/AVX computational 256-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 4 computation operations, one for each element. Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.", + "PublicDescription": "Number of SSE/AVX computational 256-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 4 computation operations, one for each element. Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x10" }, @@ -105,7 +113,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc7", "EventName": "FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE", - "PublicDescription": "Number of SSE/AVX computational 256-bit packed single precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 8 computation operations, one for each element. Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT RSQRT RCP DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.", + "PublicDescription": "Number of SSE/AVX computational 256-bit packed single precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 8 computation operations, one for each element. Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT RSQRT RCP DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x20" }, @@ -114,7 +122,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc7", "EventName": "FP_ARITH_INST_RETIRED.4_FLOPS", - "PublicDescription": "Number of SSE/AVX computational 128-bit packed single precision and 256-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 2 or/and 4 computation operations, one for each element. Applies to SSE* and AVX* packed single precision floating-point and packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX RCP14 RSQRT14 SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.", + "PublicDescription": "Number of SSE/AVX computational 128-bit packed single precision and 256-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 2 or/and 4 computation operations, one for each element. Applies to SSE* and AVX* packed single precision floating-point and packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX RCP14 RSQRT14 SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x18" }, @@ -123,7 +131,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc7", "EventName": "FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE", - "PublicDescription": "Number of SSE/AVX computational 512-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 8 computation operations, one for each element. Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT RSQRT14 RCP14 FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.", + "PublicDescription": "Number of SSE/AVX computational 512-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 8 computation operations, one for each element. Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT RSQRT14 RCP14 FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x40" }, @@ -132,7 +140,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc7", "EventName": "FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE", - "PublicDescription": "Number of SSE/AVX computational 512-bit packed single precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 16 computation operations, one for each element. Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT RSQRT14 RCP14 FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.", + "PublicDescription": "Number of SSE/AVX computational 512-bit packed single precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 16 computation operations, one for each element. Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT RSQRT14 RCP14 FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x80" }, @@ -141,7 +149,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc7", "EventName": "FP_ARITH_INST_RETIRED.8_FLOPS", - "PublicDescription": "Number of SSE/AVX computational 256-bit packed single precision and 512-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 8 computation operations, one for each element. Applies to SSE* and AVX* packed single precision and double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT RSQRT RSQRT14 RCP RCP14 DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.", + "PublicDescription": "Number of SSE/AVX computational 256-bit packed single precision and 512-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 8 computation operations, one for each element. Applies to SSE* and AVX* packed single precision and double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT RSQRT RSQRT14 RCP RCP14 DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x60" }, @@ -150,7 +158,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc7", "EventName": "FP_ARITH_INST_RETIRED.SCALAR", - "PublicDescription": "Number of SSE/AVX computational scalar single precision and double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 1 computational operation. Applies to SSE* and AVX* scalar single precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT RSQRT RCP FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.", + "PublicDescription": "Number of SSE/AVX computational scalar single precision and double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 1 computational operation. Applies to SSE* and AVX* scalar single precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT RSQRT RCP FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x3" }, @@ -159,7 +167,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc7", "EventName": "FP_ARITH_INST_RETIRED.SCALAR_DOUBLE", - "PublicDescription": "Number of SSE/AVX computational scalar double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 1 computational operation. Applies to SSE* and AVX* scalar double precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.", + "PublicDescription": "Number of SSE/AVX computational scalar double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 1 computational operation. Applies to SSE* and AVX* scalar double precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -168,7 +176,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc7", "EventName": "FP_ARITH_INST_RETIRED.SCALAR_SINGLE", - "PublicDescription": "Number of SSE/AVX computational scalar single precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 1 computational operation. Applies to SSE* and AVX* scalar single precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT RSQRT RCP FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.", + "PublicDescription": "Number of SSE/AVX computational scalar single precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 1 computational operation. Applies to SSE* and AVX* scalar single precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT RSQRT RCP FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x2" }, @@ -177,7 +185,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc7", "EventName": "FP_ARITH_INST_RETIRED.VECTOR", - "PublicDescription": "Number of any Vector retired FP arithmetic instructions. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.", + "PublicDescription": "Number of any Vector retired FP arithmetic instructions. The DAZ and FTZ flags in the MXCSR register need to be set when using these events. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0xfc" }, @@ -186,6 +194,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xcf", "EventName": "FP_ARITH_INST_RETIRED2.128B_PACKED_HALF", + "PublicDescription": "FP_ARITH_INST_RETIRED2.128B_PACKED_HALF Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x4" }, @@ -194,6 +203,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xcf", "EventName": "FP_ARITH_INST_RETIRED2.256B_PACKED_HALF", + "PublicDescription": "FP_ARITH_INST_RETIRED2.256B_PACKED_HALF Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x8" }, @@ -202,6 +212,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xcf", "EventName": "FP_ARITH_INST_RETIRED2.512B_PACKED_HALF", + "PublicDescription": "FP_ARITH_INST_RETIRED2.512B_PACKED_HALF Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x10" }, @@ -210,6 +221,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xcf", "EventName": "FP_ARITH_INST_RETIRED2.COMPLEX_SCALAR_HALF", + "PublicDescription": "FP_ARITH_INST_RETIRED2.COMPLEX_SCALAR_HALF Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x2" }, @@ -218,7 +230,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xcf", "EventName": "FP_ARITH_INST_RETIRED2.SCALAR", - "PublicDescription": "FP_ARITH_INST_RETIRED2.SCALAR", + "PublicDescription": "FP_ARITH_INST_RETIRED2.SCALAR Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x3" }, @@ -227,6 +239,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xcf", "EventName": "FP_ARITH_INST_RETIRED2.SCALAR_HALF", + "PublicDescription": "FP_ARITH_INST_RETIRED2.SCALAR_HALF Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -235,7 +248,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xcf", "EventName": "FP_ARITH_INST_RETIRED2.VECTOR", - "PublicDescription": "FP_ARITH_INST_RETIRED2.VECTOR", + "PublicDescription": "FP_ARITH_INST_RETIRED2.VECTOR Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1c" } diff --git a/tools/perf/pmu-events/arch/x86/graniterapids/frontend.json b/tools/perf/pmu-events/arch/x86/graniterapids/frontend.json index dc81055941b1..b7cd92fbecd5 100644 --- a/tools/perf/pmu-events/arch/x86/graniterapids/frontend.json +++ b/tools/perf/pmu-events/arch/x86/graniterapids/frontend.json @@ -4,7 +4,7 @@ "Counter": "0,1,2,3", "EventCode": "0x60", "EventName": "BACLEARS.ANY", - "PublicDescription": "Number of times the front-end is resteered when it finds a branch instruction in a fetch line. This is called Unknown Branch which occurs for the first time a branch instruction is fetched or when the branch is not tracked by the BPU (Branch Prediction Unit) anymore.", + "PublicDescription": "Number of times the front-end is resteered when it finds a branch instruction in a fetch line. This is called Unknown Branch which occurs for the first time a branch instruction is fetched or when the branch is not tracked by the BPU (Branch Prediction Unit) anymore. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -13,7 +13,7 @@ "Counter": "0,1,2,3", "EventCode": "0x87", "EventName": "DECODE.LCP", - "PublicDescription": "Counts cycles that the Instruction Length decoder (ILD) stalls occurred due to dynamically changing prefix length of the decoded instruction (by operand size prefix instruction 0x66, address size prefix instruction 0x67 or REX.W for Intel64). Count is proportional to the number of prefixes in a 16B-line. This may result in a three-cycle penalty for each LCP (Length changing prefix) in a 16-byte chunk.", + "PublicDescription": "Counts cycles that the Instruction Length decoder (ILD) stalls occurred due to dynamically changing prefix length of the decoded instruction (by operand size prefix instruction 0x66, address size prefix instruction 0x67 or REX.W for Intel64). Count is proportional to the number of prefixes in a 16B-line. This may result in a three-cycle penalty for each LCP (Length changing prefix) in a 16-byte chunk. Available PDIST counters: 0", "SampleAfterValue": "500009", "UMask": "0x1" }, @@ -22,6 +22,7 @@ "Counter": "0,1,2,3", "EventCode": "0x87", "EventName": "DECODE.MS_BUSY", + "PublicDescription": "Cycles the Microcode Sequencer is busy. Available PDIST counters: 0", "SampleAfterValue": "500009", "UMask": "0x2" }, @@ -30,7 +31,7 @@ "Counter": "0,1,2,3", "EventCode": "0x61", "EventName": "DSB2MITE_SWITCHES.PENALTY_CYCLES", - "PublicDescription": "Decode Stream Buffer (DSB) is a Uop-cache that holds translations of previously fetched instructions that were decoded by the legacy x86 decode pipeline (MITE). This event counts fetch penalty cycles when a transition occurs from DSB to MITE.", + "PublicDescription": "Decode Stream Buffer (DSB) is a Uop-cache that holds translations of previously fetched instructions that were decoded by the legacy x86 decode pipeline (MITE). This event counts fetch penalty cycles when a transition occurs from DSB to MITE. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x2" }, @@ -41,7 +42,7 @@ "EventName": "FRONTEND_RETIRED.ANY_ANT", "MSRIndex": "0x3F7", "MSRValue": "0x9", - "PublicDescription": "Always Not Taken (ANT) conditional retired branches (no BTB entry and not mispredicted)", + "PublicDescription": "Always Not Taken (ANT) conditional retired branches (no BTB entry and not mispredicted) Available PDIST counters: 0", "SampleAfterValue": "100007", "UMask": "0x3" }, @@ -52,7 +53,10 @@ "EventName": "FRONTEND_RETIRED.ANY_DSB_MISS", "MSRIndex": "0x3F7", "MSRValue": "0x1", - "PublicDescription": "Counts retired Instructions that experienced DSB (Decode stream buffer i.e. the decoded instruction-cache) miss.", + "PublicDescription": "Counts retired Instructions that experienced DSB (Decode stream buffer i.e. the decoded instruction-cache) miss. Available PDIST counters: 0", + "RetirementLatencyMax": 65535, + "RetirementLatencyMean": 2.46, + "RetirementLatencyMin": 0, "SampleAfterValue": "100007", "UMask": "0x3" }, @@ -63,7 +67,7 @@ "EventName": "FRONTEND_RETIRED.DSB_MISS", "MSRIndex": "0x3F7", "MSRValue": "0x11", - "PublicDescription": "Number of retired Instructions that experienced a critical DSB (Decode stream buffer i.e. the decoded instruction-cache) miss. Critical means stalls were exposed to the back-end as a result of the DSB miss.", + "PublicDescription": "Number of retired Instructions that experienced a critical DSB (Decode stream buffer i.e. the decoded instruction-cache) miss. Critical means stalls were exposed to the back-end as a result of the DSB miss. Available PDIST counters: 0", "SampleAfterValue": "100007", "UMask": "0x3" }, @@ -74,7 +78,10 @@ "EventName": "FRONTEND_RETIRED.ITLB_MISS", "MSRIndex": "0x3F7", "MSRValue": "0x14", - "PublicDescription": "Counts retired Instructions that experienced iTLB (Instruction TLB) true miss.", + "PublicDescription": "Counts retired Instructions that experienced iTLB (Instruction TLB) true miss. Available PDIST counters: 0", + "RetirementLatencyMax": 980, + "RetirementLatencyMean": 41.96, + "RetirementLatencyMin": 0, "SampleAfterValue": "100007", "UMask": "0x3" }, @@ -85,7 +92,10 @@ "EventName": "FRONTEND_RETIRED.L1I_MISS", "MSRIndex": "0x3F7", "MSRValue": "0x12", - "PublicDescription": "Counts retired Instructions who experienced Instruction L1 Cache true miss.", + "PublicDescription": "Counts retired Instructions who experienced Instruction L1 Cache true miss. Available PDIST counters: 0", + "RetirementLatencyMax": 1785, + "RetirementLatencyMean": 9.83, + "RetirementLatencyMin": 0, "SampleAfterValue": "100007", "UMask": "0x3" }, @@ -96,7 +106,10 @@ "EventName": "FRONTEND_RETIRED.L2_MISS", "MSRIndex": "0x3F7", "MSRValue": "0x13", - "PublicDescription": "Counts retired Instructions who experienced Instruction L2 Cache true miss.", + "PublicDescription": "Counts retired Instructions who experienced Instruction L2 Cache true miss. Available PDIST counters: 0", + "RetirementLatencyMax": 2854, + "RetirementLatencyMean": 137.41, + "RetirementLatencyMin": 0, "SampleAfterValue": "100007", "UMask": "0x3" }, @@ -107,7 +120,7 @@ "EventName": "FRONTEND_RETIRED.LATENCY_GE_1", "MSRIndex": "0x3F7", "MSRValue": "0x600106", - "PublicDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of at least 1 cycle which was not interrupted by a back-end stall.", + "PublicDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of at least 1 cycle which was not interrupted by a back-end stall. Available PDIST counters: 0", "SampleAfterValue": "100007", "UMask": "0x3" }, @@ -118,7 +131,7 @@ "EventName": "FRONTEND_RETIRED.LATENCY_GE_128", "MSRIndex": "0x3F7", "MSRValue": "0x608006", - "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 128 cycles which was not interrupted by a back-end stall.", + "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 128 cycles which was not interrupted by a back-end stall. Available PDIST counters: 0", "SampleAfterValue": "100007", "UMask": "0x3" }, @@ -129,7 +142,7 @@ "EventName": "FRONTEND_RETIRED.LATENCY_GE_16", "MSRIndex": "0x3F7", "MSRValue": "0x601006", - "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 16 cycles. During this period the front-end delivered no uops.", + "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 16 cycles. During this period the front-end delivered no uops. Available PDIST counters: 0", "SampleAfterValue": "100007", "UMask": "0x3" }, @@ -140,7 +153,7 @@ "EventName": "FRONTEND_RETIRED.LATENCY_GE_2", "MSRIndex": "0x3F7", "MSRValue": "0x600206", - "PublicDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of at least 2 cycles which was not interrupted by a back-end stall.", + "PublicDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of at least 2 cycles which was not interrupted by a back-end stall. Available PDIST counters: 0", "SampleAfterValue": "100007", "UMask": "0x3" }, @@ -151,7 +164,7 @@ "EventName": "FRONTEND_RETIRED.LATENCY_GE_256", "MSRIndex": "0x3F7", "MSRValue": "0x610006", - "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 256 cycles which was not interrupted by a back-end stall.", + "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 256 cycles which was not interrupted by a back-end stall. Available PDIST counters: 0", "SampleAfterValue": "100007", "UMask": "0x3" }, @@ -162,7 +175,7 @@ "EventName": "FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1", "MSRIndex": "0x3F7", "MSRValue": "0x100206", - "PublicDescription": "Counts retired instructions that are delivered to the back-end after the front-end had at least 1 bubble-slot for a period of 2 cycles. A bubble-slot is an empty issue-pipeline slot while there was no RAT stall.", + "PublicDescription": "Counts retired instructions that are delivered to the back-end after the front-end had at least 1 bubble-slot for a period of 2 cycles. A bubble-slot is an empty issue-pipeline slot while there was no RAT stall. Available PDIST counters: 0", "SampleAfterValue": "100007", "UMask": "0x3" }, @@ -173,7 +186,7 @@ "EventName": "FRONTEND_RETIRED.LATENCY_GE_32", "MSRIndex": "0x3F7", "MSRValue": "0x602006", - "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 32 cycles. During this period the front-end delivered no uops.", + "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 32 cycles. During this period the front-end delivered no uops. Available PDIST counters: 0", "SampleAfterValue": "100007", "UMask": "0x3" }, @@ -184,7 +197,7 @@ "EventName": "FRONTEND_RETIRED.LATENCY_GE_4", "MSRIndex": "0x3F7", "MSRValue": "0x600406", - "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 4 cycles which was not interrupted by a back-end stall.", + "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 4 cycles which was not interrupted by a back-end stall. Available PDIST counters: 0", "SampleAfterValue": "100007", "UMask": "0x3" }, @@ -195,7 +208,7 @@ "EventName": "FRONTEND_RETIRED.LATENCY_GE_512", "MSRIndex": "0x3F7", "MSRValue": "0x620006", - "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 512 cycles which was not interrupted by a back-end stall.", + "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 512 cycles which was not interrupted by a back-end stall. Available PDIST counters: 0", "SampleAfterValue": "100007", "UMask": "0x3" }, @@ -206,7 +219,7 @@ "EventName": "FRONTEND_RETIRED.LATENCY_GE_64", "MSRIndex": "0x3F7", "MSRValue": "0x604006", - "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 64 cycles which was not interrupted by a back-end stall.", + "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 64 cycles which was not interrupted by a back-end stall. Available PDIST counters: 0", "SampleAfterValue": "100007", "UMask": "0x3" }, @@ -217,7 +230,7 @@ "EventName": "FRONTEND_RETIRED.LATENCY_GE_8", "MSRIndex": "0x3F7", "MSRValue": "0x600806", - "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 8 cycles. During this period the front-end delivered no uops.", + "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 8 cycles. During this period the front-end delivered no uops. Available PDIST counters: 0", "SampleAfterValue": "100007", "UMask": "0x3" }, @@ -228,7 +241,7 @@ "EventName": "FRONTEND_RETIRED.LATE_SWPF", "MSRIndex": "0x3F7", "MSRValue": "0xA", - "PublicDescription": "Number of Instruction Cache demand miss in shadow of an on-going i-fetch cache-line triggered by PREFETCHIT0/1 instructions", + "PublicDescription": "Number of Instruction Cache demand miss in shadow of an on-going i-fetch cache-line triggered by PREFETCHIT0/1 instructions Available PDIST counters: 0", "SampleAfterValue": "100007", "UMask": "0x3" }, @@ -239,7 +252,7 @@ "EventName": "FRONTEND_RETIRED.MISP_ANT", "MSRIndex": "0x3F7", "MSRValue": "0x9", - "PublicDescription": "ANT retired branches that got just mispredicted", + "PublicDescription": "ANT retired branches that got just mispredicted Available PDIST counters: 0", "SampleAfterValue": "100007", "UMask": "0x2" }, @@ -250,6 +263,10 @@ "EventName": "FRONTEND_RETIRED.MS_FLOWS", "MSRIndex": "0x3F7", "MSRValue": "0x8", + "PublicDescription": "FRONTEND_RETIRED.MS_FLOWS Available PDIST counters: 0", + "RetirementLatencyMax": 65535, + "RetirementLatencyMean": 77.14, + "RetirementLatencyMin": 0, "SampleAfterValue": "100007", "UMask": "0x3" }, @@ -260,7 +277,10 @@ "EventName": "FRONTEND_RETIRED.STLB_MISS", "MSRIndex": "0x3F7", "MSRValue": "0x15", - "PublicDescription": "Counts retired Instructions that experienced STLB (2nd level TLB) true miss.", + "PublicDescription": "Counts retired Instructions that experienced STLB (2nd level TLB) true miss. Available PDIST counters: 0", + "RetirementLatencyMax": 754, + "RetirementLatencyMean": 206.85, + "RetirementLatencyMin": 0, "SampleAfterValue": "100007", "UMask": "0x3" }, @@ -271,6 +291,10 @@ "EventName": "FRONTEND_RETIRED.UNKNOWN_BRANCH", "MSRIndex": "0x3F7", "MSRValue": "0x17", + "PublicDescription": "FRONTEND_RETIRED.UNKNOWN_BRANCH Available PDIST counters: 0", + "RetirementLatencyMax": 532, + "RetirementLatencyMean": 3.85, + "RetirementLatencyMin": 0, "SampleAfterValue": "100007", "UMask": "0x3" }, @@ -279,7 +303,7 @@ "Counter": "0,1,2,3", "EventCode": "0x80", "EventName": "ICACHE_DATA.STALLS", - "PublicDescription": "Counts cycles where a code line fetch is stalled due to an L1 instruction cache miss. The decode pipeline works at a 32 Byte granularity.", + "PublicDescription": "Counts cycles where a code line fetch is stalled due to an L1 instruction cache miss. The decode pipeline works at a 32 Byte granularity. Available PDIST counters: 0", "SampleAfterValue": "500009", "UMask": "0x4" }, @@ -290,6 +314,7 @@ "EdgeDetect": "1", "EventCode": "0x80", "EventName": "ICACHE_DATA.STALL_PERIODS", + "PublicDescription": "ICACHE_DATA.STALL_PERIODS Available PDIST counters: 0", "SampleAfterValue": "500009", "UMask": "0x4" }, @@ -298,7 +323,7 @@ "Counter": "0,1,2,3", "EventCode": "0x83", "EventName": "ICACHE_TAG.STALLS", - "PublicDescription": "Counts cycles where a code fetch is stalled due to L1 instruction cache tag miss.", + "PublicDescription": "Counts cycles where a code fetch is stalled due to L1 instruction cache tag miss. Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0x4" }, @@ -308,7 +333,7 @@ "CounterMask": "1", "EventCode": "0x79", "EventName": "IDQ.DSB_CYCLES_ANY", - "PublicDescription": "Counts the number of cycles uops were delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path.", + "PublicDescription": "Counts the number of cycles uops were delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path. Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x8" }, @@ -318,7 +343,7 @@ "CounterMask": "6", "EventCode": "0x79", "EventName": "IDQ.DSB_CYCLES_OK", - "PublicDescription": "Counts the number of cycles where optimal number of uops was delivered to the Instruction Decode Queue (IDQ) from the DSB (Decode Stream Buffer) path. Count includes uops that may 'bypass' the IDQ.", + "PublicDescription": "Counts the number of cycles where optimal number of uops was delivered to the Instruction Decode Queue (IDQ) from the DSB (Decode Stream Buffer) path. Count includes uops that may 'bypass' the IDQ. Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x8" }, @@ -327,7 +352,7 @@ "Counter": "0,1,2,3", "EventCode": "0x79", "EventName": "IDQ.DSB_UOPS", - "PublicDescription": "Counts the number of uops delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path.", + "PublicDescription": "Counts the number of uops delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path. Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x8" }, @@ -337,7 +362,7 @@ "CounterMask": "1", "EventCode": "0x79", "EventName": "IDQ.MITE_CYCLES_ANY", - "PublicDescription": "Counts the number of cycles uops were delivered to the Instruction Decode Queue (IDQ) from the MITE (legacy decode pipeline) path. During these cycles uops are not being delivered from the Decode Stream Buffer (DSB).", + "PublicDescription": "Counts the number of cycles uops were delivered to the Instruction Decode Queue (IDQ) from the MITE (legacy decode pipeline) path. During these cycles uops are not being delivered from the Decode Stream Buffer (DSB). Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x4" }, @@ -347,7 +372,7 @@ "CounterMask": "6", "EventCode": "0x79", "EventName": "IDQ.MITE_CYCLES_OK", - "PublicDescription": "Counts the number of cycles where optimal number of uops was delivered to the Instruction Decode Queue (IDQ) from the MITE (legacy decode pipeline) path. During these cycles uops are not being delivered from the Decode Stream Buffer (DSB).", + "PublicDescription": "Counts the number of cycles where optimal number of uops was delivered to the Instruction Decode Queue (IDQ) from the MITE (legacy decode pipeline) path. During these cycles uops are not being delivered from the Decode Stream Buffer (DSB). Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x4" }, @@ -356,7 +381,7 @@ "Counter": "0,1,2,3", "EventCode": "0x79", "EventName": "IDQ.MITE_UOPS", - "PublicDescription": "Counts the number of uops delivered to Instruction Decode Queue (IDQ) from the MITE path. This also means that uops are not being delivered from the Decode Stream Buffer (DSB).", + "PublicDescription": "Counts the number of uops delivered to Instruction Decode Queue (IDQ) from the MITE path. This also means that uops are not being delivered from the Decode Stream Buffer (DSB). Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x4" }, @@ -366,7 +391,7 @@ "CounterMask": "1", "EventCode": "0x79", "EventName": "IDQ.MS_CYCLES_ANY", - "PublicDescription": "Counts cycles during which uops are being delivered to Instruction Decode Queue (IDQ) while the Microcode Sequencer (MS) is busy. Uops maybe initiated by Decode Stream Buffer (DSB) or MITE.", + "PublicDescription": "Counts cycles during which uops are being delivered to Instruction Decode Queue (IDQ) while the Microcode Sequencer (MS) is busy. Uops maybe initiated by Decode Stream Buffer (DSB) or MITE. Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x20" }, @@ -377,7 +402,7 @@ "EdgeDetect": "1", "EventCode": "0x79", "EventName": "IDQ.MS_SWITCHES", - "PublicDescription": "Number of switches from DSB (Decode Stream Buffer) or MITE (legacy decode pipeline) to the Microcode Sequencer.", + "PublicDescription": "Number of switches from DSB (Decode Stream Buffer) or MITE (legacy decode pipeline) to the Microcode Sequencer. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x20" }, @@ -386,7 +411,7 @@ "Counter": "0,1,2,3", "EventCode": "0x79", "EventName": "IDQ.MS_UOPS", - "PublicDescription": "Counts the number of uops initiated by MITE or Decode Stream Buffer (DSB) and delivered to Instruction Decode Queue (IDQ) while the Microcode Sequencer (MS) is busy. Counting includes uops that may 'bypass' the IDQ.", + "PublicDescription": "Counts the number of uops initiated by MITE or Decode Stream Buffer (DSB) and delivered to Instruction Decode Queue (IDQ) while the Microcode Sequencer (MS) is busy. Counting includes uops that may 'bypass' the IDQ. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x20" }, @@ -395,7 +420,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0x9c", "EventName": "IDQ_BUBBLES.CORE", - "PublicDescription": "This event counts a subset of the Topdown Slots event that when no operation was delivered to the back-end pipeline due to instruction fetch limitations when the back-end could have accepted more operations. Common examples include instruction cache misses or x86 instruction decode limitations. The count may be distributed among unhalted logical processors (hyper-threads) who share the same physical core, in processors that support Intel Hyper-Threading Technology. Software can use this event as the numerator for the Frontend Bound metric (or top-level category) of the Top-down Microarchitecture Analysis method.", + "PublicDescription": "This event counts a subset of the Topdown Slots event that when no operation was delivered to the back-end pipeline due to instruction fetch limitations when the back-end could have accepted more operations. Common examples include instruction cache misses or x86 instruction decode limitations. The count may be distributed among unhalted logical processors (hyper-threads) who share the same physical core, in processors that support Intel Hyper-Threading Technology. Software can use this event as the numerator for the Frontend Bound metric (or top-level category) of the Top-down Microarchitecture Analysis method. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x1" }, @@ -405,7 +430,7 @@ "CounterMask": "6", "EventCode": "0x9c", "EventName": "IDQ_BUBBLES.CYCLES_0_UOPS_DELIV.CORE", - "PublicDescription": "Counts the number of cycles when no uops were delivered by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle. [This event is alias to IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE]", + "PublicDescription": "Counts the number of cycles when no uops were delivered by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle. [This event is alias to IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE] Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x1" }, @@ -416,7 +441,7 @@ "EventCode": "0x9c", "EventName": "IDQ_BUBBLES.CYCLES_FE_WAS_OK", "Invert": "1", - "PublicDescription": "Counts the number of cycles when the optimal number of uops were delivered by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle. [This event is alias to IDQ_UOPS_NOT_DELIVERED.CYCLES_FE_WAS_OK]", + "PublicDescription": "Counts the number of cycles when the optimal number of uops were delivered by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle. [This event is alias to IDQ_UOPS_NOT_DELIVERED.CYCLES_FE_WAS_OK] Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x1" }, @@ -425,7 +450,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0x9c", "EventName": "IDQ_UOPS_NOT_DELIVERED.CORE", - "PublicDescription": "Counts the number of uops not delivered to by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle.", + "PublicDescription": "Counts the number of uops not delivered to by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x1" }, @@ -435,7 +460,7 @@ "CounterMask": "6", "EventCode": "0x9c", "EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE", - "PublicDescription": "Counts the number of cycles when no uops were delivered by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle. [This event is alias to IDQ_BUBBLES.CYCLES_0_UOPS_DELIV.CORE]", + "PublicDescription": "Counts the number of cycles when no uops were delivered by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle. [This event is alias to IDQ_BUBBLES.CYCLES_0_UOPS_DELIV.CORE] Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x1" }, @@ -446,7 +471,7 @@ "EventCode": "0x9c", "EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_FE_WAS_OK", "Invert": "1", - "PublicDescription": "Counts the number of cycles when the optimal number of uops were delivered by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle. [This event is alias to IDQ_BUBBLES.CYCLES_FE_WAS_OK]", + "PublicDescription": "Counts the number of cycles when the optimal number of uops were delivered by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle. [This event is alias to IDQ_BUBBLES.CYCLES_FE_WAS_OK] Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x1" } diff --git a/tools/perf/pmu-events/arch/x86/graniterapids/gnr-metrics.json b/tools/perf/pmu-events/arch/x86/graniterapids/gnr-metrics.json index a345b6874606..af527f7f9d0c 100644 --- a/tools/perf/pmu-events/arch/x86/graniterapids/gnr-metrics.json +++ b/tools/perf/pmu-events/arch/x86/graniterapids/gnr-metrics.json @@ -310,7 +310,7 @@ "ScaleUnit": "1per_instr" }, { - "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution ports for ALU operations", + "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution ports for ALU operations.", "MetricExpr": "(UOPS_DISPATCHED.PORT_0 + UOPS_DISPATCHED.PORT_1 + UOPS_DISPATCHED.PORT_5_11 + UOPS_DISPATCHED.PORT_6) / (5 * tma_info_core_core_clks)", "MetricGroup": "TopdownL5;tma_L5_group;tma_ports_utilized_3m_group", "MetricName": "tma_alu_op_utilization", @@ -322,7 +322,7 @@ "MetricExpr": "EXE.AMX_BUSY / tma_info_core_core_clks", "MetricGroup": "BvCB;Compute;HPC;Server;TopdownL3;tma_L3_group;tma_core_bound_group", "MetricName": "tma_amx_busy", - "MetricThreshold": "tma_amx_busy > 0.5 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_amx_busy > 0.5 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)", "ScaleUnit": "100%" }, { @@ -330,12 +330,12 @@ "MetricExpr": "78 * ASSISTS.ANY / tma_info_thread_slots", "MetricGroup": "BvIO;TopdownL4;tma_L4_group;tma_microcode_sequencer_group", "MetricName": "tma_assists", - "MetricThreshold": "tma_assists > 0.1 & tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1", + "MetricThreshold": "tma_assists > 0.1 & (tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1)", "PublicDescription": "This metric estimates fraction of slots the CPU retired uops delivered by the Microcode_Sequencer as a result of Assists. Assists are long sequences of uops that are required in certain corner-cases for operations that cannot be handled natively by the execution pipeline. For example; when working with very small floating point values (so-called Denormals); the FP units are not set up to perform these operations natively. Instead; a sequence of instructions to perform the computation on the Denormals is injected into the pipeline. Since these microcode sequences might be dozens of uops long; Assists can be extremely deleterious to performance and they can be avoided in many cases. Sample with: ASSISTS.ANY", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates fraction of slots the CPU retired uops as a result of handing SSE to AVX* or AVX* to SSE transition Assists", + "BriefDescription": "This metric estimates fraction of slots the CPU retired uops as a result of handing SSE to AVX* or AVX* to SSE transition Assists.", "MetricExpr": "63 * ASSISTS.SSE_AVX_MIX / tma_info_thread_slots", "MetricGroup": "HPC;TopdownL5;tma_L5_group;tma_assists_group", "MetricName": "tma_avx_assists", @@ -345,7 +345,7 @@ { "BriefDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend", "DefaultMetricgroupName": "TopdownL1", - "MetricExpr": "topdown\\-be\\-bound / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * slots", + "MetricExpr": "topdown\\-be\\-bound / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * tma_info_thread_slots", "MetricGroup": "BvOB;Default;TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_backend_bound", "MetricThreshold": "tma_backend_bound > 0.2", @@ -361,12 +361,12 @@ "MetricName": "tma_bad_speculation", "MetricThreshold": "tma_bad_speculation > 0.15", "MetricgroupNoGroup": "TopdownL1;Default", - "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example", + "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.", "ScaleUnit": "100%" }, { "BriefDescription": "Total pipeline cost of instruction fetch related bottlenecks by large code footprint programs (i-side cache; TLB and BTB misses)", - "MetricExpr": "100 * tma_fetch_latency * (tma_itlb_misses + tma_icache_misses + tma_unknown_branches) / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches)", + "MetricExpr": "100 * tma_fetch_latency * (tma_itlb_misses + tma_icache_misses + tma_unknown_branches) / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches)", "MetricGroup": "BigFootprint;BvBC;Fed;Frontend;IcMiss;MemoryTLB", "MetricName": "tma_bottleneck_big_code", "MetricThreshold": "tma_bottleneck_big_code > 20" @@ -381,7 +381,7 @@ }, { "BriefDescription": "Total pipeline cost of external Memory- or Cache-Bandwidth related bottlenecks", - "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_mem_bandwidth / (tma_mem_bandwidth + tma_mem_latency)) + tma_memory_bound * (tma_l3_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_sq_full / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_memory_bound * (tma_l1_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_fb_full / (tma_dtlb_load + tma_store_fwd_blk + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_fb_full)))", + "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_mem_bandwidth / (tma_mem_bandwidth + tma_mem_latency)) + tma_memory_bound * (tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_sq_full / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_fb_full / (tma_dtlb_load + tma_fb_full + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)))", "MetricGroup": "BvMB;Mem;MemoryBW;Offcore;tma_issueBW", "MetricName": "tma_bottleneck_cache_memory_bandwidth", "MetricThreshold": "tma_bottleneck_cache_memory_bandwidth > 20", @@ -389,7 +389,7 @@ }, { "BriefDescription": "Total pipeline cost of external Memory- or Cache-Latency related bottlenecks", - "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_mem_latency / (tma_mem_bandwidth + tma_mem_latency)) + tma_memory_bound * (tma_l3_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_l3_hit_latency / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_memory_bound * tma_l2_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound) + tma_memory_bound * (tma_l1_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_l1_latency_dependency / (tma_dtlb_load + tma_store_fwd_blk + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_fb_full)) + tma_memory_bound * (tma_l1_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_lock_latency / (tma_dtlb_load + tma_store_fwd_blk + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_fb_full)) + tma_memory_bound * (tma_l1_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_split_loads / (tma_dtlb_load + tma_store_fwd_blk + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_fb_full)) + tma_memory_bound * (tma_store_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_split_stores / (tma_store_latency + tma_false_sharing + tma_split_stores + tma_streaming_stores + tma_dtlb_store)) + tma_memory_bound * (tma_store_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_store_latency / (tma_store_latency + tma_false_sharing + tma_split_stores + tma_streaming_stores + tma_dtlb_store)))", + "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_mem_latency / (tma_mem_bandwidth + tma_mem_latency)) + tma_memory_bound * (tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_l3_hit_latency / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_memory_bound * tma_l2_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) + tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_l1_latency_dependency / (tma_dtlb_load + tma_fb_full + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_lock_latency / (tma_dtlb_load + tma_fb_full + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_split_loads / (tma_dtlb_load + tma_fb_full + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_memory_bound * (tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_split_stores / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency + tma_streaming_stores)) + tma_memory_bound * (tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_store_latency / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency + tma_streaming_stores)))", "MetricGroup": "BvML;Mem;MemoryLat;Offcore;tma_issueLat", "MetricName": "tma_bottleneck_cache_memory_latency", "MetricThreshold": "tma_bottleneck_cache_memory_latency > 20", @@ -397,22 +397,22 @@ }, { "BriefDescription": "Total pipeline cost when the execution is compute-bound - an estimation", - "MetricExpr": "100 * (tma_core_bound * tma_divider / (tma_divider + tma_serializing_operation + tma_amx_busy + tma_ports_utilization) + tma_core_bound * tma_amx_busy / (tma_divider + tma_serializing_operation + tma_amx_busy + tma_ports_utilization) + tma_core_bound * (tma_ports_utilization / (tma_divider + tma_serializing_operation + tma_amx_busy + tma_ports_utilization)) * (tma_ports_utilized_3m / (tma_ports_utilized_0 + tma_ports_utilized_1 + tma_ports_utilized_2 + tma_ports_utilized_3m)))", + "MetricExpr": "100 * (tma_core_bound * tma_divider / (tma_amx_busy + tma_divider + tma_ports_utilization + tma_serializing_operation) + tma_core_bound * tma_amx_busy / (tma_amx_busy + tma_divider + tma_ports_utilization + tma_serializing_operation) + tma_core_bound * (tma_ports_utilization / (tma_amx_busy + tma_divider + tma_ports_utilization + tma_serializing_operation)) * (tma_ports_utilized_3m / (tma_ports_utilized_0 + tma_ports_utilized_1 + tma_ports_utilized_2 + tma_ports_utilized_3m)))", "MetricGroup": "BvCB;Cor;tma_issueComp", "MetricName": "tma_bottleneck_compute_bound_est", "MetricThreshold": "tma_bottleneck_compute_bound_est > 20", - "PublicDescription": "Total pipeline cost when the execution is compute-bound - an estimation. Covers Core Bound when High ILP as well as when long-latency execution units are busy" + "PublicDescription": "Total pipeline cost when the execution is compute-bound - an estimation. Covers Core Bound when High ILP as well as when long-latency execution units are busy. Related metrics: " }, { "BriefDescription": "Total pipeline cost of instruction fetch bandwidth related bottlenecks (when the front-end could not sustain operations delivery to the back-end)", - "MetricExpr": "100 * (tma_frontend_bound - (1 - 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts) * tma_fetch_latency * tma_mispredicts_resteers / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches) - (1 - INST_RETIRED.REP_ITERATION / cpu@UOPS_RETIRED.MS\\,cmask\\=0x1@) * (tma_fetch_latency * (tma_ms_switches + tma_branch_resteers * (tma_clears_resteers + tma_mispredicts_resteers * tma_other_mispredicts / tma_branch_mispredicts) / (tma_mispredicts_resteers + tma_clears_resteers + tma_unknown_branches)) / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches) + tma_fetch_bandwidth * tma_ms / (tma_mite + tma_dsb + tma_ms))) - tma_bottleneck_big_code", + "MetricExpr": "100 * (tma_frontend_bound - (1 - 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts) * tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) - (1 - INST_RETIRED.REP_ITERATION / cpu@UOPS_RETIRED.MS\\,cmask\\=1@) * (tma_fetch_latency * (tma_ms_switches + tma_branch_resteers * (tma_clears_resteers + tma_mispredicts_resteers * tma_other_mispredicts / tma_branch_mispredicts) / (tma_clears_resteers + tma_mispredicts_resteers + tma_unknown_branches)) / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) + tma_fetch_bandwidth * tma_ms / (tma_dsb + tma_mite + tma_ms))) - tma_bottleneck_big_code", "MetricGroup": "BvFB;Fed;FetchBW;Frontend", "MetricName": "tma_bottleneck_instruction_fetch_bw", "MetricThreshold": "tma_bottleneck_instruction_fetch_bw > 20" }, { "BriefDescription": "Total pipeline cost of irregular execution (e.g", - "MetricExpr": "100 * ((1 - INST_RETIRED.REP_ITERATION / cpu@UOPS_RETIRED.MS\\,cmask\\=0x1@) * (tma_fetch_latency * (tma_ms_switches + tma_branch_resteers * (tma_clears_resteers + tma_mispredicts_resteers * tma_other_mispredicts / tma_branch_mispredicts) / (tma_mispredicts_resteers + tma_clears_resteers + tma_unknown_branches)) / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches) + tma_fetch_bandwidth * tma_ms / (tma_mite + tma_dsb + tma_ms)) + 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts * tma_branch_mispredicts + tma_machine_clears * tma_other_nukes / tma_other_nukes + tma_core_bound * (tma_serializing_operation + RS.EMPTY_RESOURCE / tma_info_thread_clks * tma_ports_utilized_0) / (tma_divider + tma_serializing_operation + tma_amx_busy + tma_ports_utilization) + tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * tma_heavy_operations)", + "MetricExpr": "100 * ((1 - INST_RETIRED.REP_ITERATION / cpu@UOPS_RETIRED.MS\\,cmask\\=1@) * (tma_fetch_latency * (tma_ms_switches + tma_branch_resteers * (tma_clears_resteers + tma_mispredicts_resteers * tma_other_mispredicts / tma_branch_mispredicts) / (tma_clears_resteers + tma_mispredicts_resteers + tma_unknown_branches)) / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) + tma_fetch_bandwidth * tma_ms / (tma_dsb + tma_mite + tma_ms)) + 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts * tma_branch_mispredicts + tma_machine_clears * tma_other_nukes / tma_other_nukes + tma_core_bound * (tma_serializing_operation + RS.EMPTY_RESOURCE / tma_info_thread_clks * tma_ports_utilized_0) / (tma_amx_busy + tma_divider + tma_ports_utilization + tma_serializing_operation) + tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * tma_heavy_operations)", "MetricGroup": "Bad;BvIO;Cor;Ret;tma_issueMS", "MetricName": "tma_bottleneck_irregular_overhead", "MetricThreshold": "tma_bottleneck_irregular_overhead > 10", @@ -420,7 +420,7 @@ }, { "BriefDescription": "Total pipeline cost of Memory Address Translation related bottlenecks (data-side TLBs)", - "MetricExpr": "100 * (tma_memory_bound * (tma_l1_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_dtlb_load / (tma_dtlb_load + tma_store_fwd_blk + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_fb_full)) + tma_memory_bound * (tma_store_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_dtlb_store / (tma_store_latency + tma_false_sharing + tma_split_stores + tma_streaming_stores + tma_dtlb_store)))", + "MetricExpr": "100 * (tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_dtlb_load / (tma_dtlb_load + tma_fb_full + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_memory_bound * (tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_dtlb_store / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency + tma_streaming_stores)))", "MetricGroup": "BvMT;Mem;MemoryTLB;Offcore;tma_issueTLB", "MetricName": "tma_bottleneck_memory_data_tlbs", "MetricThreshold": "tma_bottleneck_memory_data_tlbs > 20", @@ -428,7 +428,7 @@ }, { "BriefDescription": "Total pipeline cost of Memory Synchronization related bottlenecks (data transfers and coherency updates across processors)", - "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound) * (tma_mem_latency / (tma_mem_bandwidth + tma_mem_latency)) * tma_remote_cache / (tma_local_mem + tma_remote_mem + tma_remote_cache) + tma_l3_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound) * (tma_contested_accesses + tma_data_sharing) / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full) + tma_store_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound) * tma_false_sharing / (tma_store_latency + tma_false_sharing + tma_split_stores + tma_streaming_stores + tma_dtlb_store - tma_store_latency)) + tma_machine_clears * (1 - tma_other_nukes / tma_other_nukes))", + "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_mem_latency / (tma_mem_bandwidth + tma_mem_latency)) * tma_remote_cache / (tma_local_mem + tma_remote_cache + tma_remote_mem) + tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_contested_accesses + tma_data_sharing) / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full) + tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * tma_false_sharing / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency + tma_streaming_stores - tma_store_latency)) + tma_machine_clears * (1 - tma_other_nukes / tma_other_nukes))", "MetricGroup": "BvMS;LockCont;Mem;Offcore;tma_issueSyncxn", "MetricName": "tma_bottleneck_memory_synchronization", "MetricThreshold": "tma_bottleneck_memory_synchronization > 10", @@ -436,7 +436,7 @@ }, { "BriefDescription": "Total pipeline cost of Branch Misprediction related bottlenecks", - "MetricExpr": "100 * (1 - 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts) * (tma_branch_mispredicts + tma_fetch_latency * tma_mispredicts_resteers / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches))", + "MetricExpr": "100 * (1 - 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts) * (tma_branch_mispredicts + tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches))", "MetricGroup": "Bad;BadSpec;BrMispredicts;BvMP;tma_issueBM", "MetricName": "tma_bottleneck_mispredictions", "MetricThreshold": "tma_bottleneck_mispredictions > 20", @@ -448,10 +448,10 @@ "MetricGroup": "BvOB;Cor;Offcore", "MetricName": "tma_bottleneck_other_bottlenecks", "MetricThreshold": "tma_bottleneck_other_bottlenecks > 20", - "PublicDescription": "Total pipeline cost of remaining bottlenecks in the back-end. Examples include data-dependencies (Core Bound when Low ILP) and other unlisted memory-related stalls" + "PublicDescription": "Total pipeline cost of remaining bottlenecks in the back-end. Examples include data-dependencies (Core Bound when Low ILP) and other unlisted memory-related stalls." }, { - "BriefDescription": "Total pipeline cost of \"useful operations\" - the portion of Retiring category not covered by Branching_Overhead nor Irregular_Overhead", + "BriefDescription": "Total pipeline cost of \"useful operations\" - the portion of Retiring category not covered by Branching_Overhead nor Irregular_Overhead.", "MetricExpr": "100 * (tma_retiring - (BR_INST_RETIRED.ALL_BRANCHES + 2 * BR_INST_RETIRED.NEAR_CALL + INST_RETIRED.NOP) / tma_info_thread_slots - tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * tma_heavy_operations)", "MetricGroup": "BvUW;Ret", "MetricName": "tma_bottleneck_useful_work", @@ -460,7 +460,7 @@ { "BriefDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction", "DefaultMetricgroupName": "TopdownL2", - "MetricExpr": "topdown\\-br\\-mispredict / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * slots", + "MetricExpr": "topdown\\-br\\-mispredict / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * tma_info_thread_slots", "MetricGroup": "BadSpec;BrMispredicts;BvMP;Default;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueBM", "MetricName": "tma_branch_mispredicts", "MetricThreshold": "tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", @@ -473,24 +473,24 @@ "MetricExpr": "INT_MISC.CLEAR_RESTEER_CYCLES / tma_info_thread_clks + tma_unknown_branches", "MetricGroup": "FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group", "MetricName": "tma_branch_resteers", - "MetricThreshold": "tma_branch_resteers > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", - "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers. Branch Resteers estimates the Frontend delay in fetching operations from corrected path; following all sorts of miss-predicted branches. For example; branchy code with lots of miss-predictions might get categorized under Branch Resteers. Note the value of this node may overlap with its siblings. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_l3_hit_latency, tma_store_latency", + "MetricThreshold": "tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers. Branch Resteers estimates the Frontend delay in fetching operations from corrected path; following all sorts of miss-predicted branches. For example; branchy code with lots of miss-predictions might get categorized under Branch Resteers. Note the value of this node may overlap with its siblings. Sample with: BR_MISP_RETIRED.ALL_BRANCHES", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due staying in C0.1 power-performance optimized state (Faster wakeup time; Smaller power savings)", + "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due staying in C0.1 power-performance optimized state (Faster wakeup time; Smaller power savings).", "MetricExpr": "CPU_CLK_UNHALTED.C01 / tma_info_thread_clks", "MetricGroup": "C0Wait;TopdownL4;tma_L4_group;tma_serializing_operation_group", "MetricName": "tma_c01_wait", - "MetricThreshold": "tma_c01_wait > 0.05 & tma_serializing_operation > 0.1 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_c01_wait > 0.05 & (tma_serializing_operation > 0.1 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due staying in C0.2 power-performance optimized state (Slower wakeup time; Larger power savings)", + "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due staying in C0.2 power-performance optimized state (Slower wakeup time; Larger power savings).", "MetricExpr": "CPU_CLK_UNHALTED.C02 / tma_info_thread_clks", "MetricGroup": "C0Wait;TopdownL4;tma_L4_group;tma_serializing_operation_group", "MetricName": "tma_c02_wait", - "MetricThreshold": "tma_c02_wait > 0.05 & tma_serializing_operation > 0.1 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_c02_wait > 0.05 & (tma_serializing_operation > 0.1 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", "ScaleUnit": "100%" }, { @@ -498,8 +498,8 @@ "MetricExpr": "max(0, tma_microcode_sequencer - tma_assists)", "MetricGroup": "TopdownL4;tma_L4_group;tma_microcode_sequencer_group", "MetricName": "tma_cisc", - "MetricThreshold": "tma_cisc > 0.1 & tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1", - "PublicDescription": "This metric estimates fraction of cycles the CPU retired uops originated from CISC (complex instruction set computer) instruction. A CISC instruction has multiple uops that are required to perform the instruction's functionality as in the case of read-modify-write as an example. Since these instructions require multiple uops they may or may not imply sub-optimal use of machine resources", + "MetricThreshold": "tma_cisc > 0.1 & (tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1)", + "PublicDescription": "This metric estimates fraction of cycles the CPU retired uops originated from CISC (complex instruction set computer) instruction. A CISC instruction has multiple uops that are required to perform the instruction's functionality as in the case of read-modify-write as an example. Since these instructions require multiple uops they may or may not imply sub-optimal use of machine resources.", "ScaleUnit": "100%" }, { @@ -507,24 +507,24 @@ "MetricExpr": "(1 - tma_branch_mispredicts / tma_bad_speculation) * INT_MISC.CLEAR_RESTEER_CYCLES / tma_info_thread_clks", "MetricGroup": "BadSpec;MachineClears;TopdownL4;tma_L4_group;tma_branch_resteers_group;tma_issueMC", "MetricName": "tma_clears_resteers", - "MetricThreshold": "tma_clears_resteers > 0.05 & tma_branch_resteers > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricThreshold": "tma_clears_resteers > 0.05 & (tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))", "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Machine Clears. Sample with: INT_MISC.CLEAR_RESTEER_CYCLES. Related metrics: tma_l1_bound, tma_machine_clears, tma_microcode_sequencer, tma_ms_switches", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates fraction of cycles the CPU was stalled due to instruction cache misses that hit in the L2 cache", + "BriefDescription": "This metric estimates fraction of cycles the CPU was stalled due to instruction cache misses that hit in the L2 cache.", "MetricExpr": "max(0, FRONTEND_RETIRED.L1I_MISS * FRONTEND_RETIRED.L1I_MISS:R / tma_info_thread_clks - tma_code_l2_miss)", "MetricGroup": "FetchLat;IcMiss;Offcore;TopdownL4;tma_L4_group;tma_icache_misses_group", "MetricName": "tma_code_l2_hit", - "MetricThreshold": "tma_code_l2_hit > 0.05 & tma_icache_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricThreshold": "tma_code_l2_hit > 0.05 & (tma_icache_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates fraction of cycles the CPU was stalled due to instruction cache misses that miss in the L2 cache", + "BriefDescription": "This metric estimates fraction of cycles the CPU was stalled due to instruction cache misses that miss in the L2 cache.", "MetricExpr": "FRONTEND_RETIRED.L2_MISS * FRONTEND_RETIRED.L2_MISS:R / tma_info_thread_clks", "MetricGroup": "FetchLat;IcMiss;Offcore;TopdownL4;tma_L4_group;tma_icache_misses_group", "MetricName": "tma_code_l2_miss", - "MetricThreshold": "tma_code_l2_miss > 0.05 & tma_icache_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricThreshold": "tma_code_l2_miss > 0.05 & (tma_icache_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))", "ScaleUnit": "100%" }, { @@ -532,7 +532,7 @@ "MetricExpr": "max(0, FRONTEND_RETIRED.ITLB_MISS * FRONTEND_RETIRED.ITLB_MISS:R / tma_info_thread_clks - tma_code_stlb_miss)", "MetricGroup": "FetchLat;MemoryTLB;TopdownL4;tma_L4_group;tma_itlb_misses_group", "MetricName": "tma_code_stlb_hit", - "MetricThreshold": "tma_code_stlb_hit > 0.05 & tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricThreshold": "tma_code_stlb_hit > 0.05 & (tma_itlb_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))", "ScaleUnit": "100%" }, { @@ -540,48 +540,49 @@ "MetricExpr": "FRONTEND_RETIRED.STLB_MISS * FRONTEND_RETIRED.STLB_MISS:R / tma_info_thread_clks", "MetricGroup": "FetchLat;MemoryTLB;TopdownL4;tma_L4_group;tma_itlb_misses_group", "MetricName": "tma_code_stlb_miss", - "MetricThreshold": "tma_code_stlb_miss > 0.05 & tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricThreshold": "tma_code_stlb_miss > 0.05 & (tma_itlb_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 2 or 4 MB pages for (instruction) code accesses", + "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 2 or 4 MB pages for (instruction) code accesses.", "MetricExpr": "ITLB_MISSES.WALK_ACTIVE / tma_info_thread_clks * ITLB_MISSES.WALK_COMPLETED_2M_4M / (ITLB_MISSES.WALK_COMPLETED_4K + ITLB_MISSES.WALK_COMPLETED_2M_4M)", "MetricGroup": "FetchLat;MemoryTLB;TopdownL5;tma_L5_group;tma_code_stlb_miss_group", "MetricName": "tma_code_stlb_miss_2m", - "MetricThreshold": "tma_code_stlb_miss_2m > 0.05 & tma_code_stlb_miss > 0.05 & tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricThreshold": "tma_code_stlb_miss_2m > 0.05 & (tma_code_stlb_miss > 0.05 & (tma_itlb_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)))", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 4 KB pages for (instruction) code accesses", + "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 4 KB pages for (instruction) code accesses.", "MetricExpr": "ITLB_MISSES.WALK_ACTIVE / tma_info_thread_clks * ITLB_MISSES.WALK_COMPLETED_4K / (ITLB_MISSES.WALK_COMPLETED_4K + ITLB_MISSES.WALK_COMPLETED_2M_4M)", "MetricGroup": "FetchLat;MemoryTLB;TopdownL5;tma_L5_group;tma_code_stlb_miss_group", "MetricName": "tma_code_stlb_miss_4k", - "MetricThreshold": "tma_code_stlb_miss_4k > 0.05 & tma_code_stlb_miss > 0.05 & tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricThreshold": "tma_code_stlb_miss_4k > 0.05 & (tma_code_stlb_miss > 0.05 & (tma_itlb_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)))", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to retired misprediction by non-taken conditional branches", + "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to retired misprediction by non-taken conditional branches.", "MetricExpr": "BR_MISP_RETIRED.COND_NTAKEN_COST * BR_MISP_RETIRED.COND_NTAKEN_COST:R / tma_info_thread_clks", "MetricGroup": "BrMispredicts;TopdownL3;tma_L3_group;tma_branch_mispredicts_group", "MetricName": "tma_cond_nt_mispredicts", - "MetricThreshold": "tma_cond_nt_mispredicts > 0.05 & tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", + "MetricThreshold": "tma_cond_nt_mispredicts > 0.05 & (tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15)", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to misprediction by taken conditional branches", + "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to misprediction by taken conditional branches.", "MetricExpr": "BR_MISP_RETIRED.COND_TAKEN_COST * BR_MISP_RETIRED.COND_TAKEN_COST:R / tma_info_thread_clks", "MetricGroup": "BrMispredicts;TopdownL3;tma_L3_group;tma_branch_mispredicts_group", "MetricName": "tma_cond_tk_mispredicts", - "MetricThreshold": "tma_cond_tk_mispredicts > 0.05 & tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", + "MetricThreshold": "tma_cond_tk_mispredicts > 0.05 & (tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15)", "ScaleUnit": "100%" }, { "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses", - "MetricExpr": "((min(MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS * MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS:R, MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS * (79 * tma_info_system_core_frequency) - 4.4 * tma_info_system_core_frequency) if 0 < MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS:R else MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS * (79 * tma_info_system_core_frequency) - 4.4 * tma_info_system_core_frequency) + (min(MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD * MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD:R, MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD * (81 * tma_info_system_core_frequency) - 4.4 * tma_info_system_core_frequency) if 0 < MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD:R else MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD * (81 * tma_info_system_core_frequency) - 4.4 * tma_info_system_core_frequency) * (OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM / (OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM + OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD))) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "(MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS * min(MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS:R, 74.6 * tma_info_system_core_frequency) + MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD * min(MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD:R, 76.6 * tma_info_system_core_frequency) * (OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM / (OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM + OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD))) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks", "MetricGroup": "BvMS;DataSharing;LockCont;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group", "MetricName": "tma_contested_accesses", - "MetricThreshold": "tma_contested_accesses > 0.05 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", - "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses. Contested accesses occur when data written by one Logical Processor are read by another Logical Processor on a different Physical Core. Examples of contested accesses include synchronizations such as locks; true data sharing such as modified locked variables; and false sharing. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD, MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS. Related metrics: tma_bottleneck_memory_synchronization, tma_data_sharing, tma_false_sharing, tma_machine_clears, tma_remote_cache", + "MetricThreshold": "tma_contested_accesses > 0.05 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses. Contested accesses occur when data written by one Logical Processor are read by another Logical Processor on a different Physical Core. Examples of contested accesses include synchronizations such as locks; true data sharing such as modified locked variables; and false sharing. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD;MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS. Related metrics: tma_bottleneck_memory_synchronization, tma_data_sharing, tma_false_sharing, tma_machine_clears, tma_remote_cache", "ScaleUnit": "100%" }, { @@ -592,24 +593,25 @@ "MetricName": "tma_core_bound", "MetricThreshold": "tma_core_bound > 0.1 & tma_backend_bound > 0.2", "MetricgroupNoGroup": "TopdownL2;Default", - "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck. Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations)", + "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck. Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations).", "ScaleUnit": "100%" }, { "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses", - "MetricExpr": "((min(MEM_LOAD_L3_HIT_RETIRED.XSNP_NO_FWD * MEM_LOAD_L3_HIT_RETIRED.XSNP_NO_FWD:R, MEM_LOAD_L3_HIT_RETIRED.XSNP_NO_FWD * (79 * tma_info_system_core_frequency) - 4.4 * tma_info_system_core_frequency) if 0 < MEM_LOAD_L3_HIT_RETIRED.XSNP_NO_FWD:R else MEM_LOAD_L3_HIT_RETIRED.XSNP_NO_FWD * (79 * tma_info_system_core_frequency) - 4.4 * tma_info_system_core_frequency) + (min(MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD * MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD:R, MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD * (79 * tma_info_system_core_frequency) - 4.4 * tma_info_system_core_frequency) if 0 < MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD:R else MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD * (79 * tma_info_system_core_frequency) - 4.4 * tma_info_system_core_frequency) * (1 - OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM / (OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM + OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD))) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "(MEM_LOAD_L3_HIT_RETIRED.XSNP_NO_FWD * min(MEM_LOAD_L3_HIT_RETIRED.XSNP_NO_FWD:R, 74.6 * tma_info_system_core_frequency) + MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD * min(MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD:R, 74.6 * tma_info_system_core_frequency) * (1 - OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM / (OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM + OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD))) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks", "MetricGroup": "BvMS;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group", "MetricName": "tma_data_sharing", - "MetricThreshold": "tma_data_sharing > 0.05 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_data_sharing > 0.05 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses. Data shared by multiple Logical Processors (even just read shared) may cause increased access latency due to cache coherency. Excessive data sharing can drastically harm multithreaded performance. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_NO_FWD. Related metrics: tma_bottleneck_memory_synchronization, tma_contested_accesses, tma_false_sharing, tma_machine_clears, tma_remote_cache", "ScaleUnit": "100%" }, { "BriefDescription": "This metric represents fraction of cycles where decoder-0 was the only active decoder", - "MetricExpr": "(cpu@INST_DECODED.DECODERS\\,cmask\\=0x1@ - cpu@INST_DECODED.DECODERS\\,cmask\\=0x2@) / tma_info_core_core_clks / 2", + "MetricExpr": "(cpu@INST_DECODED.DECODERS\\,cmask\\=1@ - cpu@INST_DECODED.DECODERS\\,cmask\\=2@) / tma_info_core_core_clks / 2", "MetricGroup": "DSBmiss;FetchBW;TopdownL4;tma_L4_group;tma_issueD0;tma_mite_group", "MetricName": "tma_decoder0_alone", - "MetricThreshold": "tma_decoder0_alone > 0.1 & tma_mite > 0.1 & tma_fetch_bandwidth > 0.2", + "MetricThreshold": "tma_decoder0_alone > 0.1 & (tma_mite > 0.1 & tma_fetch_bandwidth > 0.2)", "PublicDescription": "This metric represents fraction of cycles where decoder-0 was the only active decoder. Related metrics: tma_few_uops_instructions", "ScaleUnit": "100%" }, @@ -618,7 +620,7 @@ "MetricExpr": "ARITH.DIV_ACTIVE / tma_info_thread_clks", "MetricGroup": "BvCB;TopdownL3;tma_L3_group;tma_core_bound_group", "MetricName": "tma_divider", - "MetricThreshold": "tma_divider > 0.2 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_divider > 0.2 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)", "PublicDescription": "This metric represents fraction of cycles where the Divider unit was active. Divide and square root instructions are performed by the Divider unit and can take considerably longer latency than integer or Floating Point addition; subtraction; or multiplication. Sample with: ARITH.DIV_ACTIVE", "ScaleUnit": "100%" }, @@ -627,7 +629,7 @@ "MetricExpr": "MEMORY_ACTIVITY.STALLS_L3_MISS / tma_info_thread_clks", "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_dram_bound", - "MetricThreshold": "tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", "PublicDescription": "This metric estimates how often the CPU was stalled on accesses to external memory (DRAM) by loads. Better caching can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L3_MISS", "ScaleUnit": "100%" }, @@ -637,7 +639,7 @@ "MetricGroup": "DSB;FetchBW;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group", "MetricName": "tma_dsb", "MetricThreshold": "tma_dsb > 0.15 & tma_fetch_bandwidth > 0.2", - "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to DSB (decoded uop cache) fetch pipeline. For example; inefficient utilization of the DSB cache structure or bank conflict when reading from it; are categorized here", + "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to DSB (decoded uop cache) fetch pipeline. For example; inefficient utilization of the DSB cache structure or bank conflict when reading from it; are categorized here.", "ScaleUnit": "100%" }, { @@ -645,34 +647,34 @@ "MetricExpr": "DSB2MITE_SWITCHES.PENALTY_CYCLES / tma_info_thread_clks", "MetricGroup": "DSBmiss;FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueFB", "MetricName": "tma_dsb_switches", - "MetricThreshold": "tma_dsb_switches > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", - "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines. The DSB (decoded i-cache) is a Uop Cache where the front-end directly delivers Uops (micro operations) avoiding heavy x86 decoding. The DSB pipeline has shorter latency and delivered higher bandwidth than the MITE (legacy instruction decode pipeline). Switching between the two pipelines can cause penalties hence this metric measures the exposed penalty. Sample with: FRONTEND_RETIRED.DSB_MISS. Related metrics: tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp", + "MetricThreshold": "tma_dsb_switches > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines. The DSB (decoded i-cache) is a Uop Cache where the front-end directly delivers Uops (micro operations) avoiding heavy x86 decoding. The DSB pipeline has shorter latency and delivered higher bandwidth than the MITE (legacy instruction decode pipeline). Switching between the two pipelines can cause penalties hence this metric measures the exposed penalty. Sample with: FRONTEND_RETIRED.DSB_MISS_PS. Related metrics: tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp", "ScaleUnit": "100%" }, { "BriefDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses", - "MetricExpr": "(min(MEM_INST_RETIRED.STLB_HIT_LOADS * MEM_INST_RETIRED.STLB_HIT_LOADS:R, MEM_INST_RETIRED.STLB_HIT_LOADS * 7) if 0 < MEM_INST_RETIRED.STLB_HIT_LOADS:R else MEM_INST_RETIRED.STLB_HIT_LOADS * 7) / tma_info_thread_clks + tma_load_stlb_miss", + "MetricExpr": "MEM_INST_RETIRED.STLB_HIT_LOADS * min(MEM_INST_RETIRED.STLB_HIT_LOADS:R, 7) / tma_info_thread_clks + tma_load_stlb_miss", "MetricGroup": "BvMT;MemoryTLB;TopdownL4;tma_L4_group;tma_issueTLB;tma_l1_bound_group", "MetricName": "tma_dtlb_load", - "MetricThreshold": "tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", - "PublicDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses. TLBs (Translation Look-aside Buffers) are processor caches for recently used entries out of the Page Tables that are used to map virtual- to physical-addresses by the operating system. This metric approximates the potential delay of demand loads missing the first-level data TLB (assuming worst case scenario with back to back misses to different pages). This includes hitting in the second-level TLB (STLB) as well as performing a hardware page walk on an STLB miss. Sample with: MEM_INST_RETIRED.STLB_MISS_LOADS. Related metrics: tma_bottleneck_memory_data_tlbs, tma_dtlb_store", + "MetricThreshold": "tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses. TLBs (Translation Look-aside Buffers) are processor caches for recently used entries out of the Page Tables that are used to map virtual- to physical-addresses by the operating system. This metric approximates the potential delay of demand loads missing the first-level data TLB (assuming worst case scenario with back to back misses to different pages). This includes hitting in the second-level TLB (STLB) as well as performing a hardware page walk on an STLB miss. Sample with: MEM_INST_RETIRED.STLB_MISS_LOADS_PS. Related metrics: tma_bottleneck_memory_data_tlbs, tma_dtlb_store", "ScaleUnit": "100%" }, { "BriefDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses", - "MetricExpr": "(min(MEM_INST_RETIRED.STLB_HIT_STORES * MEM_INST_RETIRED.STLB_HIT_STORES:R, MEM_INST_RETIRED.STLB_HIT_STORES * 7) if 0 < MEM_INST_RETIRED.STLB_HIT_STORES:R else MEM_INST_RETIRED.STLB_HIT_STORES * 7) / tma_info_thread_clks + tma_store_stlb_miss", + "MetricExpr": "MEM_INST_RETIRED.STLB_HIT_STORES * min(MEM_INST_RETIRED.STLB_HIT_STORES:R, 7) / tma_info_thread_clks + tma_store_stlb_miss", "MetricGroup": "BvMT;MemoryTLB;TopdownL4;tma_L4_group;tma_issueTLB;tma_store_bound_group", "MetricName": "tma_dtlb_store", - "MetricThreshold": "tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", - "PublicDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses. As with ordinary data caching; focus on improving data locality and reducing working-set size to reduce DTLB overhead. Additionally; consider using profile-guided optimization (PGO) to collocate frequently-used data on the same page. Try using larger page sizes for large amounts of frequently-used data. Sample with: MEM_INST_RETIRED.STLB_MISS_STORES. Related metrics: tma_bottleneck_memory_data_tlbs, tma_dtlb_load", + "MetricThreshold": "tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses. As with ordinary data caching; focus on improving data locality and reducing working-set size to reduce DTLB overhead. Additionally; consider using profile-guided optimization (PGO) to collocate frequently-used data on the same page. Try using larger page sizes for large amounts of frequently-used data. Sample with: MEM_INST_RETIRED.STLB_MISS_STORES_PS. Related metrics: tma_bottleneck_memory_data_tlbs, tma_dtlb_load", "ScaleUnit": "100%" }, { "BriefDescription": "This metric roughly estimates how often CPU was handling synchronizations due to False Sharing", - "MetricExpr": "(170 * tma_info_system_core_frequency * cpu@OCR.DEMAND_RFO.L3_MISS\\,offcore_rsp\\=0x103b800002@ + 81 * tma_info_system_core_frequency * OCR.DEMAND_RFO.L3_HIT.SNOOP_HITM) / tma_info_thread_clks", + "MetricExpr": "(170 * tma_info_system_core_frequency * OCR.DEMAND_RFO.L3_MISS@offcore_rsp\\=0x103b800002@ + 81 * tma_info_system_core_frequency * OCR.DEMAND_RFO.L3_HIT.SNOOP_HITM) / tma_info_thread_clks", "MetricGroup": "BvMS;DataSharing;LockCont;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_store_bound_group", "MetricName": "tma_false_sharing", - "MetricThreshold": "tma_false_sharing > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_false_sharing > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", "PublicDescription": "This metric roughly estimates how often CPU was handling synchronizations due to False Sharing. False Sharing is a multithreading hiccup; where multiple Logical Processors contend on different data-elements mapped into the same cache line. Sample with: OCR.DEMAND_RFO.L3_HIT.SNOOP_HITM. Related metrics: tma_bottleneck_memory_synchronization, tma_contested_accesses, tma_data_sharing, tma_machine_clears, tma_remote_cache", "ScaleUnit": "100%" }, @@ -693,7 +695,7 @@ "MetricName": "tma_fetch_bandwidth", "MetricThreshold": "tma_fetch_bandwidth > 0.2", "MetricgroupNoGroup": "TopdownL2;Default", - "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues. For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Sample with: FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1, FRONTEND_RETIRED.LATENCY_GE_1, FRONTEND_RETIRED.LATENCY_GE_2. Related metrics: tma_dsb_switches, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp", + "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues. For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Sample with: FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1;FRONTEND_RETIRED.LATENCY_GE_1;FRONTEND_RETIRED.LATENCY_GE_2. Related metrics: tma_dsb_switches, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp", "ScaleUnit": "100%" }, { @@ -704,7 +706,7 @@ "MetricName": "tma_fetch_latency", "MetricThreshold": "tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", "MetricgroupNoGroup": "TopdownL2;Default", - "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues. For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: FRONTEND_RETIRED.LATENCY_GE_16, FRONTEND_RETIRED.LATENCY_GE_8", + "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues. For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: FRONTEND_RETIRED.LATENCY_GE_16_PS;FRONTEND_RETIRED.LATENCY_GE_8_PS", "ScaleUnit": "100%" }, { @@ -722,7 +724,7 @@ "MetricGroup": "HPC;TopdownL3;tma_L3_group;tma_light_operations_group", "MetricName": "tma_fp_arith", "MetricThreshold": "tma_fp_arith > 0.2 & tma_light_operations > 0.6", - "PublicDescription": "This metric represents overall arithmetic floating-point (FP) operations fraction the CPU has executed (retired). Note this metric's value may exceed its parent due to use of \"Uops\" CountDomain and FMA double-counting", + "PublicDescription": "This metric represents overall arithmetic floating-point (FP) operations fraction the CPU has executed (retired). Note this metric's value may exceed its parent due to use of \"Uops\" CountDomain and FMA double-counting.", "ScaleUnit": "100%" }, { @@ -731,15 +733,15 @@ "MetricGroup": "HPC;TopdownL5;tma_L5_group;tma_assists_group", "MetricName": "tma_fp_assists", "MetricThreshold": "tma_fp_assists > 0.1", - "PublicDescription": "This metric roughly estimates fraction of slots the CPU retired uops as a result of handing Floating Point (FP) Assists. FP Assist may apply when working with very small floating point values (so-called Denormals)", + "PublicDescription": "This metric roughly estimates fraction of slots the CPU retired uops as a result of handing Floating Point (FP) Assists. FP Assist may apply when working with very small floating point values (so-called Denormals).", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of cycles where the Floating-Point Divider unit was active", + "BriefDescription": "This metric represents fraction of cycles where the Floating-Point Divider unit was active.", "MetricExpr": "ARITH.FPDIV_ACTIVE / tma_info_thread_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_divider_group", "MetricName": "tma_fp_divider", - "MetricThreshold": "tma_fp_divider > 0.2 & tma_divider > 0.2 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_fp_divider > 0.2 & (tma_divider > 0.2 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", "ScaleUnit": "100%" }, { @@ -747,8 +749,8 @@ "MetricExpr": "(FP_ARITH_INST_RETIRED.SCALAR + FP_ARITH_INST_RETIRED2.SCALAR) / (tma_retiring * tma_info_thread_slots)", "MetricGroup": "Compute;Flops;TopdownL4;tma_L4_group;tma_fp_arith_group;tma_issue2P", "MetricName": "tma_fp_scalar", - "MetricThreshold": "tma_fp_scalar > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6", - "PublicDescription": "This metric approximates arithmetic floating-point (FP) scalar uops fraction the CPU has retired. May overcount due to FMA double counting. Related metrics: tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_6, tma_ports_utilized_2", + "MetricThreshold": "tma_fp_scalar > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6)", + "PublicDescription": "This metric approximates arithmetic floating-point (FP) scalar uops fraction the CPU has retired. May overcount due to FMA double counting. Related metrics: tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%" }, { @@ -756,8 +758,8 @@ "MetricExpr": "(FP_ARITH_INST_RETIRED.VECTOR + FP_ARITH_INST_RETIRED2.VECTOR) / (tma_retiring * tma_info_thread_slots)", "MetricGroup": "Compute;Flops;TopdownL4;tma_L4_group;tma_fp_arith_group;tma_issue2P", "MetricName": "tma_fp_vector", - "MetricThreshold": "tma_fp_vector > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6", - "PublicDescription": "This metric approximates arithmetic floating-point (FP) vector uops fraction the CPU has retired aggregated across all vector widths. May overcount due to FMA double counting. Related metrics: tma_fp_scalar, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_6, tma_ports_utilized_2", + "MetricThreshold": "tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6)", + "PublicDescription": "This metric approximates arithmetic floating-point (FP) vector uops fraction the CPU has retired aggregated across all vector widths. May overcount due to FMA double counting. Related metrics: tma_fp_scalar, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%" }, { @@ -765,8 +767,8 @@ "MetricExpr": "(FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED2.128B_PACKED_HALF) / (tma_retiring * tma_info_thread_slots)", "MetricGroup": "Compute;Flops;TopdownL5;tma_L5_group;tma_fp_vector_group;tma_issue2P", "MetricName": "tma_fp_vector_128b", - "MetricThreshold": "tma_fp_vector_128b > 0.1 & tma_fp_vector > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6", - "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 128-bit wide vectors. May overcount due to FMA double counting prior to LNL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_6, tma_ports_utilized_2", + "MetricThreshold": "tma_fp_vector_128b > 0.1 & (tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6))", + "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 128-bit wide vectors. May overcount due to FMA double counting prior to LNL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%" }, { @@ -774,8 +776,8 @@ "MetricExpr": "(FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE + FP_ARITH_INST_RETIRED2.256B_PACKED_HALF) / (tma_retiring * tma_info_thread_slots)", "MetricGroup": "Compute;Flops;TopdownL5;tma_L5_group;tma_fp_vector_group;tma_issue2P", "MetricName": "tma_fp_vector_256b", - "MetricThreshold": "tma_fp_vector_256b > 0.1 & tma_fp_vector > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6", - "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 256-bit wide vectors. May overcount due to FMA double counting prior to LNL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_6, tma_ports_utilized_2", + "MetricThreshold": "tma_fp_vector_256b > 0.1 & (tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6))", + "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 256-bit wide vectors. May overcount due to FMA double counting prior to LNL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%" }, { @@ -783,8 +785,8 @@ "MetricExpr": "(FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE + FP_ARITH_INST_RETIRED2.512B_PACKED_HALF) / (tma_retiring * tma_info_thread_slots)", "MetricGroup": "Compute;Flops;TopdownL5;tma_L5_group;tma_fp_vector_group;tma_issue2P", "MetricName": "tma_fp_vector_512b", - "MetricThreshold": "tma_fp_vector_512b > 0.1 & tma_fp_vector > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6", - "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 512-bit wide vectors. May overcount due to FMA double counting. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_6, tma_ports_utilized_2", + "MetricThreshold": "tma_fp_vector_512b > 0.1 & (tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6))", + "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 512-bit wide vectors. May overcount due to FMA double counting. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%" }, { @@ -795,27 +797,27 @@ "MetricName": "tma_frontend_bound", "MetricThreshold": "tma_frontend_bound > 0.15", "MetricgroupNoGroup": "TopdownL1;Default", - "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound. Sample with: FRONTEND_RETIRED.LATENCY_GE_4", + "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound. Sample with: FRONTEND_RETIRED.LATENCY_GE_4_PS", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of slots where the CPU was retiring fused instructions , where one uop can represent multiple contiguous instructions", + "BriefDescription": "This metric represents fraction of slots where the CPU was retiring fused instructions -- where one uop can represent multiple contiguous instructions", "MetricExpr": "tma_light_operations * INST_RETIRED.MACRO_FUSED / (tma_retiring * tma_info_thread_slots)", "MetricGroup": "Branches;BvBO;Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group", "MetricName": "tma_fused_instructions", "MetricThreshold": "tma_fused_instructions > 0.1 & tma_light_operations > 0.6", - "PublicDescription": "This metric represents fraction of slots where the CPU was retiring fused instructions , where one uop can represent multiple contiguous instructions. CMP+JCC or DEC+JCC are common examples of legacy fusions. {([MTL] Note new MOV+OP and Load+OP fusions appear under Other_Light_Ops in MTL!)}", + "PublicDescription": "This metric represents fraction of slots where the CPU was retiring fused instructions -- where one uop can represent multiple contiguous instructions. CMP+JCC or DEC+JCC are common examples of legacy fusions. {([MTL] Note new MOV+OP and Load+OP fusions appear under Other_Light_Ops in MTL!)}", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations , instructions that require two or more uops or micro-coded sequences", + "BriefDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences", "DefaultMetricgroupName": "TopdownL2", - "MetricExpr": "topdown\\-heavy\\-ops / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * slots", + "MetricExpr": "topdown\\-heavy\\-ops / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * tma_info_thread_slots", "MetricGroup": "Default;Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_heavy_operations", "MetricThreshold": "tma_heavy_operations > 0.1", "MetricgroupNoGroup": "TopdownL2;Default", - "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations , instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences.([ICL+] Note this may overcount due to approximation using indirect events; [ADL+]). Sample with: UOPS_RETIRED.HEAVY", + "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences.([ICL+] Note this may overcount due to approximation using indirect events; [ADL+]). Sample with: UOPS_RETIRED.HEAVY", "ScaleUnit": "100%" }, { @@ -823,24 +825,24 @@ "MetricExpr": "ICACHE_DATA.STALLS / tma_info_thread_clks", "MetricGroup": "BigFootprint;BvBC;FetchLat;IcMiss;TopdownL3;tma_L3_group;tma_fetch_latency_group", "MetricName": "tma_icache_misses", - "MetricThreshold": "tma_icache_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", - "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to instruction cache misses. Sample with: FRONTEND_RETIRED.L2_MISS, FRONTEND_RETIRED.L1I_MISS", + "MetricThreshold": "tma_icache_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to instruction cache misses. Sample with: FRONTEND_RETIRED.L2_MISS_PS;FRONTEND_RETIRED.L1I_MISS_PS", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to retired misprediction by indirect CALL instructions", + "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to retired misprediction by indirect CALL instructions.", "MetricExpr": "BR_MISP_RETIRED.INDIRECT_CALL_COST * BR_MISP_RETIRED.INDIRECT_CALL_COST:R / tma_info_thread_clks", "MetricGroup": "BrMispredicts;TopdownL3;tma_L3_group;tma_branch_mispredicts_group", "MetricName": "tma_ind_call_mispredicts", - "MetricThreshold": "tma_ind_call_mispredicts > 0.05 & tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", + "MetricThreshold": "tma_ind_call_mispredicts > 0.05 & (tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15)", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to retired misprediction by indirect JMP instructions", + "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to retired misprediction by indirect JMP instructions.", "MetricExpr": "max((BR_MISP_RETIRED.INDIRECT_COST * BR_MISP_RETIRED.INDIRECT_COST:R - BR_MISP_RETIRED.INDIRECT_CALL_COST * BR_MISP_RETIRED.INDIRECT_CALL_COST:R) / tma_info_thread_clks, 0)", "MetricGroup": "BrMispredicts;TopdownL3;tma_L3_group;tma_branch_mispredicts_group", "MetricName": "tma_ind_jump_mispredicts", - "MetricThreshold": "tma_ind_jump_mispredicts > 0.05 & tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", + "MetricThreshold": "tma_ind_jump_mispredicts > 0.05 & (tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15)", "ScaleUnit": "100%" }, { @@ -851,28 +853,28 @@ "PublicDescription": "Branch Misprediction Cost: Cycles representing fraction of TMA slots wasted per non-speculative branch misprediction (retired JEClear). Related metrics: tma_bottleneck_mispredictions, tma_branch_mispredicts, tma_mispredicts_resteers" }, { - "BriefDescription": "Instructions per retired Mispredicts for conditional non-taken branches (lower number means higher occurrence rate)", + "BriefDescription": "Instructions per retired Mispredicts for conditional non-taken branches (lower number means higher occurrence rate).", "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.COND_NTAKEN", "MetricGroup": "Bad;BrMispredicts", "MetricName": "tma_info_bad_spec_ipmisp_cond_ntaken", "MetricThreshold": "tma_info_bad_spec_ipmisp_cond_ntaken < 200" }, { - "BriefDescription": "Instructions per retired Mispredicts for conditional taken branches (lower number means higher occurrence rate)", + "BriefDescription": "Instructions per retired Mispredicts for conditional taken branches (lower number means higher occurrence rate).", "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.COND_TAKEN", "MetricGroup": "Bad;BrMispredicts", "MetricName": "tma_info_bad_spec_ipmisp_cond_taken", "MetricThreshold": "tma_info_bad_spec_ipmisp_cond_taken < 200" }, { - "BriefDescription": "Instructions per retired Mispredicts for indirect CALL or JMP branches (lower number means higher occurrence rate)", + "BriefDescription": "Instructions per retired Mispredicts for indirect CALL or JMP branches (lower number means higher occurrence rate).", "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.INDIRECT", "MetricGroup": "Bad;BrMispredicts", "MetricName": "tma_info_bad_spec_ipmisp_indirect", - "MetricThreshold": "tma_info_bad_spec_ipmisp_indirect < 1000" + "MetricThreshold": "tma_info_bad_spec_ipmisp_indirect < 1e3" }, { - "BriefDescription": "Instructions per retired Mispredicts for return branches (lower number means higher occurrence rate)", + "BriefDescription": "Instructions per retired Mispredicts for return branches (lower number means higher occurrence rate).", "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.RET", "MetricGroup": "Bad;BrMispredicts", "MetricName": "tma_info_bad_spec_ipmisp_ret", @@ -900,7 +902,7 @@ }, { "BriefDescription": "Total pipeline cost of DSB (uop cache) hits - subset of the Instruction_Fetch_BW Bottleneck", - "MetricExpr": "100 * (tma_frontend_bound * (tma_fetch_bandwidth / (tma_fetch_latency + tma_fetch_bandwidth)) * (tma_dsb / (tma_mite + tma_dsb + tma_ms)))", + "MetricExpr": "100 * (tma_frontend_bound * (tma_fetch_bandwidth / (tma_fetch_bandwidth + tma_fetch_latency)) * (tma_dsb / (tma_dsb + tma_mite + tma_ms)))", "MetricGroup": "DSB;Fed;FetchBW;tma_issueFB", "MetricName": "tma_info_botlnk_l2_dsb_bandwidth", "MetricThreshold": "tma_info_botlnk_l2_dsb_bandwidth > 10", @@ -908,7 +910,7 @@ }, { "BriefDescription": "Total pipeline cost of DSB (uop cache) misses - subset of the Instruction_Fetch_BW Bottleneck", - "MetricExpr": "100 * (tma_fetch_latency * tma_dsb_switches / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches) + tma_fetch_bandwidth * tma_mite / (tma_mite + tma_dsb + tma_ms))", + "MetricExpr": "100 * (tma_fetch_latency * tma_dsb_switches / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) + tma_fetch_bandwidth * tma_mite / (tma_dsb + tma_mite + tma_ms))", "MetricGroup": "DSBmiss;Fed;tma_issueFB", "MetricName": "tma_info_botlnk_l2_dsb_misses", "MetricThreshold": "tma_info_botlnk_l2_dsb_misses > 10", @@ -916,10 +918,11 @@ }, { "BriefDescription": "Total pipeline cost of Instruction Cache misses - subset of the Big_Code Bottleneck", - "MetricExpr": "100 * (tma_fetch_latency * tma_icache_misses / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches))", + "MetricExpr": "100 * (tma_fetch_latency * tma_icache_misses / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches))", "MetricGroup": "Fed;FetchLat;IcMiss;tma_issueFL", "MetricName": "tma_info_botlnk_l2_ic_misses", - "MetricThreshold": "tma_info_botlnk_l2_ic_misses > 5" + "MetricThreshold": "tma_info_botlnk_l2_ic_misses > 5", + "PublicDescription": "Total pipeline cost of Instruction Cache misses - subset of the Big_Code Bottleneck. Related metrics: " }, { "BriefDescription": "Fraction of branches that are CALL or RET", @@ -980,11 +983,11 @@ "MetricExpr": "(FP_ARITH_DISPATCHED.PORT_0 + FP_ARITH_DISPATCHED.PORT_1 + FP_ARITH_DISPATCHED.PORT_5) / (2 * tma_info_core_core_clks)", "MetricGroup": "Cor;Flops;HPC", "MetricName": "tma_info_core_fp_arith_utilization", - "PublicDescription": "Actual per-core usage of the Floating Point non-X87 execution units (regardless of precision or vector-width). Values > 1 are possible due to ([BDW+] Fused-Multiply Add (FMA) counting - common; [ADL+] use all of ADD/MUL/FMA in Scalar or 128/256-bit vectors - less common)" + "PublicDescription": "Actual per-core usage of the Floating Point non-X87 execution units (regardless of precision or vector-width). Values > 1 are possible due to ([BDW+] Fused-Multiply Add (FMA) counting - common; [ADL+] use all of ADD/MUL/FMA in Scalar or 128/256-bit vectors - less common)." }, { "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is execution) per thread (logical-processor)", - "MetricExpr": "UOPS_EXECUTED.THREAD / cpu@UOPS_EXECUTED.THREAD\\,cmask\\=0x1@", + "MetricExpr": "UOPS_EXECUTED.THREAD / cpu@UOPS_EXECUTED.THREAD\\,cmask\\=1@", "MetricGroup": "Backend;Cor;Pipeline;PortsUtil", "MetricName": "tma_info_core_ilp" }, @@ -997,8 +1000,8 @@ "PublicDescription": "Fraction of Uops delivered by the DSB (aka Decoded ICache; or Uop Cache). Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_inst_mix_iptb, tma_lcp" }, { - "BriefDescription": "Average number of cycles of a switch from the DSB fetch-unit to MITE fetch unit - see DSB_Switches tree node for details", - "MetricExpr": "DSB2MITE_SWITCHES.PENALTY_CYCLES / cpu@DSB2MITE_SWITCHES.PENALTY_CYCLES\\,cmask\\=0x1\\,edge\\=0x1@", + "BriefDescription": "Average number of cycles of a switch from the DSB fetch-unit to MITE fetch unit - see DSB_Switches tree node for details.", + "MetricExpr": "DSB2MITE_SWITCHES.PENALTY_CYCLES / cpu@DSB2MITE_SWITCHES.PENALTY_CYCLES\\,cmask\\=1\\,edge@", "MetricGroup": "DSBmiss", "MetricName": "tma_info_frontend_dsb_switch_cost" }, @@ -1011,7 +1014,7 @@ }, { "BriefDescription": "Average number of Uops issued by front-end when it issued something", - "MetricExpr": "UOPS_ISSUED.ANY / cpu@UOPS_ISSUED.ANY\\,cmask\\=0x1@", + "MetricExpr": "UOPS_ISSUED.ANY / cpu@UOPS_ISSUED.ANY\\,cmask\\=1@", "MetricGroup": "Fed;FetchBW", "MetricName": "tma_info_frontend_fetch_upc" }, @@ -1061,10 +1064,10 @@ }, { "BriefDescription": "Average number of cycles the front-end was delayed due to an Unknown Branch detection", - "MetricExpr": "INT_MISC.UNKNOWN_BRANCH_CYCLES / cpu@INT_MISC.UNKNOWN_BRANCH_CYCLES\\,cmask\\=0x1\\,edge\\=0x1@", + "MetricExpr": "INT_MISC.UNKNOWN_BRANCH_CYCLES / cpu@INT_MISC.UNKNOWN_BRANCH_CYCLES\\,cmask\\=1\\,edge@", "MetricGroup": "Fed", "MetricName": "tma_info_frontend_unknown_branch_cost", - "PublicDescription": "Average number of cycles the front-end was delayed due to an Unknown Branch detection. See Unknown_Branches node" + "PublicDescription": "Average number of cycles the front-end was delayed due to an Unknown Branch detection. See Unknown_Branches node." }, { "BriefDescription": "This metric represents fraction of cycles the CPU retirement was stalled likely due to retired branches who got branch address clears", @@ -1073,7 +1076,7 @@ "MetricName": "tma_info_frontend_unknown_branches_ret" }, { - "BriefDescription": "Branch instructions per taken branch", + "BriefDescription": "Branch instructions per taken branch.", "MetricExpr": "BR_INST_RETIRED.ALL_BRANCHES / BR_INST_RETIRED.NEAR_TAKEN", "MetricGroup": "Branches;Fed;PGO", "MetricName": "tma_info_inst_mix_bptkbranch" @@ -1091,7 +1094,7 @@ "MetricGroup": "Flops;InsType", "MetricName": "tma_info_inst_mix_iparith", "MetricThreshold": "tma_info_inst_mix_iparith < 10", - "PublicDescription": "Instructions per FP Arithmetic instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting. Approximated prior to BDW" + "PublicDescription": "Instructions per FP Arithmetic instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting. Approximated prior to BDW." }, { "BriefDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number means higher occurrence rate)", @@ -1099,7 +1102,7 @@ "MetricGroup": "Flops;FpVector;InsType", "MetricName": "tma_info_inst_mix_iparith_avx128", "MetricThreshold": "tma_info_inst_mix_iparith_avx128 < 10", - "PublicDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting" + "PublicDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting." }, { "BriefDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means higher occurrence rate)", @@ -1107,7 +1110,7 @@ "MetricGroup": "Flops;FpVector;InsType", "MetricName": "tma_info_inst_mix_iparith_avx256", "MetricThreshold": "tma_info_inst_mix_iparith_avx256 < 10", - "PublicDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting" + "PublicDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting." }, { "BriefDescription": "Instructions per FP Arithmetic AVX 512-bit instruction (lower number means higher occurrence rate)", @@ -1115,7 +1118,7 @@ "MetricGroup": "Flops;FpVector;InsType", "MetricName": "tma_info_inst_mix_iparith_avx512", "MetricThreshold": "tma_info_inst_mix_iparith_avx512 < 10", - "PublicDescription": "Instructions per FP Arithmetic AVX 512-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting" + "PublicDescription": "Instructions per FP Arithmetic AVX 512-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting." }, { "BriefDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction (lower number means higher occurrence rate)", @@ -1123,7 +1126,7 @@ "MetricGroup": "Flops;FpScalar;InsType", "MetricName": "tma_info_inst_mix_iparith_scalar_dp", "MetricThreshold": "tma_info_inst_mix_iparith_scalar_dp < 10", - "PublicDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting" + "PublicDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting." }, { "BriefDescription": "Instructions per FP Arithmetic Scalar Half-Precision instruction (lower number means higher occurrence rate)", @@ -1131,7 +1134,7 @@ "MetricGroup": "Flops;FpScalar;InsType;Server", "MetricName": "tma_info_inst_mix_iparith_scalar_hp", "MetricThreshold": "tma_info_inst_mix_iparith_scalar_hp < 10", - "PublicDescription": "Instructions per FP Arithmetic Scalar Half-Precision instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting" + "PublicDescription": "Instructions per FP Arithmetic Scalar Half-Precision instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting." }, { "BriefDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction (lower number means higher occurrence rate)", @@ -1139,7 +1142,7 @@ "MetricGroup": "Flops;FpScalar;InsType", "MetricName": "tma_info_inst_mix_iparith_scalar_sp", "MetricThreshold": "tma_info_inst_mix_iparith_scalar_sp < 10", - "PublicDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting" + "PublicDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting." }, { "BriefDescription": "Instructions per Branch (lower number means higher occurrence rate)", @@ -1194,7 +1197,7 @@ "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_TAKEN", "MetricGroup": "Branches;Fed;FetchBW;Frontend;PGO;tma_issueFB", "MetricName": "tma_info_inst_mix_iptb", - "MetricThreshold": "tma_info_inst_mix_iptb < 6 * 2 + 1", + "MetricThreshold": "tma_info_inst_mix_iptb < 13", "PublicDescription": "Instructions per taken branch. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_lcp" }, { @@ -1331,7 +1334,7 @@ }, { "BriefDescription": "Average Parallel L2 cache miss demand Loads", - "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD / cpu@OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD\\,cmask\\=0x1@", + "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD / cpu@OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD\\,cmask\\=1@", "MetricGroup": "Memory_BW;Offcore", "MetricName": "tma_info_memory_latency_load_l2_mlp" }, @@ -1396,21 +1399,21 @@ "MetricExpr": "64 * OCR.READS_TO_CORE.DRAM / 1e9 / tma_info_system_time", "MetricGroup": "HPC;Mem;MemoryBW;SoC", "MetricName": "tma_info_memory_soc_r2c_dram_bw", - "PublicDescription": "Average DRAM BW for Reads-to-Core (R2C) covering for memory attached to local- and remote-socket. See R2C_Offcore_BW" + "PublicDescription": "Average DRAM BW for Reads-to-Core (R2C) covering for memory attached to local- and remote-socket. See R2C_Offcore_BW." }, { "BriefDescription": "Average L3-cache miss BW for Reads-to-Core (R2C)", "MetricExpr": "64 * OCR.READS_TO_CORE.L3_MISS / 1e9 / tma_info_system_time", "MetricGroup": "HPC;Mem;MemoryBW;SoC", "MetricName": "tma_info_memory_soc_r2c_l3m_bw", - "PublicDescription": "Average L3-cache miss BW for Reads-to-Core (R2C). This covering going to DRAM or other memory off-chip memory tears. See R2C_Offcore_BW" + "PublicDescription": "Average L3-cache miss BW for Reads-to-Core (R2C). This covering going to DRAM or other memory off-chip memory tears. See R2C_Offcore_BW." }, { "BriefDescription": "Average Off-core access BW for Reads-to-Core (R2C)", "MetricExpr": "64 * OCR.READS_TO_CORE.ANY_RESPONSE / 1e9 / tma_info_system_time", "MetricGroup": "HPC;Mem;MemoryBW;SoC", "MetricName": "tma_info_memory_soc_r2c_offcore_bw", - "PublicDescription": "Average Off-core access BW for Reads-to-Core (R2C). R2C account for demand or prefetch load/RFO/code access that fill data into the Core caches" + "PublicDescription": "Average Off-core access BW for Reads-to-Core (R2C). R2C account for demand or prefetch load/RFO/code access that fill data into the Core caches." }, { "BriefDescription": "STLB (2nd level TLB) code speculative misses per kilo instruction (misses of any page-size that complete the page walk)", @@ -1452,8 +1455,8 @@ "MetricName": "tma_info_memory_tlb_store_stlb_mpki" }, { - "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is execution) per core", - "MetricExpr": "UOPS_EXECUTED.THREAD / (UOPS_EXECUTED.CORE_CYCLES_GE_1 / 2 if #SMT_on else cpu@UOPS_EXECUTED.THREAD\\,cmask\\=0x1@)", + "BriefDescription": "", + "MetricExpr": "UOPS_EXECUTED.THREAD / (UOPS_EXECUTED.CORE_CYCLES_GE_1 / 2 if #SMT_on else cpu@UOPS_EXECUTED.THREAD\\,cmask\\=1@)", "MetricGroup": "Cor;Pipeline;PortsUtil;SMT", "MetricName": "tma_info_pipeline_execute" }, @@ -1474,18 +1477,18 @@ "MetricExpr": "INST_RETIRED.ANY / ASSISTS.ANY", "MetricGroup": "MicroSeq;Pipeline;Ret;Retire", "MetricName": "tma_info_pipeline_ipassist", - "MetricThreshold": "tma_info_pipeline_ipassist < 100000", + "MetricThreshold": "tma_info_pipeline_ipassist < 100e3", "PublicDescription": "Instructions per a microcode Assist invocation. See Assists tree node for details (lower number means higher occurrence rate)" }, { - "BriefDescription": "Average number of Uops retired in cycles where at least one uop has retired", - "MetricExpr": "tma_retiring * tma_info_thread_slots / cpu@UOPS_RETIRED.SLOTS\\,cmask\\=0x1@", + "BriefDescription": "Average number of Uops retired in cycles where at least one uop has retired.", + "MetricExpr": "tma_retiring * tma_info_thread_slots / cpu@UOPS_RETIRED.SLOTS\\,cmask\\=1@", "MetricGroup": "Pipeline;Ret", "MetricName": "tma_info_pipeline_retire" }, { "BriefDescription": "Estimated fraction of retirement-cycles dealing with repeat instructions", - "MetricExpr": "INST_RETIRED.REP_ITERATION / cpu@UOPS_RETIRED.SLOTS\\,cmask\\=0x1@", + "MetricExpr": "INST_RETIRED.REP_ITERATION / cpu@UOPS_RETIRED.SLOTS\\,cmask\\=1@", "MetricGroup": "MicroSeq;Pipeline;Ret", "MetricName": "tma_info_pipeline_strings_cycles", "MetricThreshold": "tma_info_pipeline_strings_cycles > 0.1" @@ -1548,14 +1551,13 @@ "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.FAR_BRANCH:u", "MetricGroup": "Branches;OS", "MetricName": "tma_info_system_ipfarbranch", - "MetricThreshold": "tma_info_system_ipfarbranch < 1000000" + "MetricThreshold": "tma_info_system_ipfarbranch < 1e6" }, { "BriefDescription": "Cycles Per Instruction for the Operating System (OS) Kernel mode", "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P:k / INST_RETIRED.ANY_P:k", "MetricGroup": "OS", - "MetricName": "tma_info_system_kernel_cpi", - "ScaleUnit": "1per_instr" + "MetricName": "tma_info_system_kernel_cpi" }, { "BriefDescription": "Fraction of cycles spent in the Operating System (OS) Kernel mode", @@ -1566,14 +1568,14 @@ }, { "BriefDescription": "Average latency of data read request to external DRAM memory [in nanoseconds]", - "MetricExpr": "1e9 * (UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_DDR / UNC_CHA_TOR_INSERTS.IA_MISS_DRD_DDR) / cha_0@event\\=0x0@", + "MetricExpr": "1e9 * (UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_DDR / UNC_CHA_TOR_INSERTS.IA_MISS_DRD_DDR) / uncore_cha_0@event\\=0x1@", "MetricGroup": "MemOffcore;MemoryLat;Server;SoC", "MetricName": "tma_info_system_mem_dram_read_latency", "PublicDescription": "Average latency of data read request to external DRAM memory [in nanoseconds]. Accounts for demand loads and L1/L2 data-read prefetches" }, { "BriefDescription": "Average number of parallel data read requests to external memory", - "MetricExpr": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD / cha@UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD\\,thresh\\=0x1@", + "MetricExpr": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD / UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD@thresh\\=1@", "MetricGroup": "Mem;MemoryBW;SoC", "MetricName": "tma_info_system_mem_parallel_reads", "PublicDescription": "Average number of parallel data read requests to external memory. Accounts for demand loads and L1/L2 prefetches" @@ -1599,7 +1601,7 @@ }, { "BriefDescription": "Socket actual clocks when any core is active on that socket", - "MetricExpr": "cha_0@event\\=0x0@", + "MetricExpr": "uncore_cha_0@event\\=0x1@", "MetricGroup": "SoC", "MetricName": "tma_info_system_socket_clks" }, @@ -1629,7 +1631,7 @@ "MetricName": "tma_info_system_upi_data_transmit_bw" }, { - "BriefDescription": "Per-Logical Processor actual clocks when the Logical Processor is active", + "BriefDescription": "Per-Logical Processor actual clocks when the Logical Processor is active.", "MetricExpr": "CPU_CLK_UNHALTED.THREAD", "MetricGroup": "Pipeline", "MetricName": "tma_info_thread_clks" @@ -1638,15 +1640,14 @@ "BriefDescription": "Cycles Per Instruction (per Logical Processor)", "MetricExpr": "1 / tma_info_thread_ipc", "MetricGroup": "Mem;Pipeline", - "MetricName": "tma_info_thread_cpi", - "ScaleUnit": "1per_instr" + "MetricName": "tma_info_thread_cpi" }, { "BriefDescription": "The ratio of Executed- by Issued-Uops", "MetricExpr": "UOPS_EXECUTED.THREAD / UOPS_ISSUED.ANY", "MetricGroup": "Cor;Pipeline", "MetricName": "tma_info_thread_execute_per_issue", - "PublicDescription": "The ratio of Executed- by Issued-Uops. Ratio > 1 suggests high rate of uop micro-fusions. Ratio < 1 suggest high rate of \"execute\" at rename stage" + "PublicDescription": "The ratio of Executed- by Issued-Uops. Ratio > 1 suggests high rate of uop micro-fusions. Ratio < 1 suggest high rate of \"execute\" at rename stage." }, { "BriefDescription": "Instructions Per Cycle (per Logical Processor)", @@ -1656,13 +1657,13 @@ }, { "BriefDescription": "Total issue-pipeline slots (per-Physical Core till ICL; per-Logical Processor ICL onward)", - "MetricExpr": "slots", + "MetricExpr": "TOPDOWN.SLOTS", "MetricGroup": "TmaL1;tma_L1_group", "MetricName": "tma_info_thread_slots" }, { "BriefDescription": "Fraction of Physical Core issue-slots utilized by this Logical Processor", - "MetricExpr": "(tma_info_thread_slots / (slots / 2) if #SMT_on else 1)", + "MetricExpr": "(tma_info_thread_slots / (TOPDOWN.SLOTS / 2) if #SMT_on else 1)", "MetricGroup": "SMT;TmaL1;tma_L1_group", "MetricName": "tma_info_thread_slots_utilization" }, @@ -1678,14 +1679,14 @@ "MetricExpr": "tma_retiring * tma_info_thread_slots / BR_INST_RETIRED.NEAR_TAKEN", "MetricGroup": "Branches;Fed;FetchBW", "MetricName": "tma_info_thread_uptb", - "MetricThreshold": "tma_info_thread_uptb < 6 * 1.5" + "MetricThreshold": "tma_info_thread_uptb < 9" }, { - "BriefDescription": "This metric represents fraction of cycles where the Integer Divider unit was active", + "BriefDescription": "This metric represents fraction of cycles where the Integer Divider unit was active.", "MetricExpr": "tma_divider - tma_fp_divider", "MetricGroup": "TopdownL4;tma_L4_group;tma_divider_group", "MetricName": "tma_int_divider", - "MetricThreshold": "tma_int_divider > 0.2 & tma_divider > 0.2 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_int_divider > 0.2 & (tma_divider > 0.2 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", "ScaleUnit": "100%" }, { @@ -1694,7 +1695,7 @@ "MetricGroup": "Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group", "MetricName": "tma_int_operations", "MetricThreshold": "tma_int_operations > 0.1 & tma_light_operations > 0.6", - "PublicDescription": "This metric represents overall Integer (Int) select operations fraction the CPU has executed (retired). Vector/Matrix Int operations and shuffles are counted. Note this metric's value may exceed its parent due to use of \"Uops\" CountDomain", + "PublicDescription": "This metric represents overall Integer (Int) select operations fraction the CPU has executed (retired). Vector/Matrix Int operations and shuffles are counted. Note this metric's value may exceed its parent due to use of \"Uops\" CountDomain.", "ScaleUnit": "100%" }, { @@ -1702,8 +1703,8 @@ "MetricExpr": "(INT_VEC_RETIRED.ADD_128 + INT_VEC_RETIRED.VNNI_128) / (tma_retiring * tma_info_thread_slots)", "MetricGroup": "Compute;IntVector;Pipeline;TopdownL4;tma_L4_group;tma_int_operations_group;tma_issue2P", "MetricName": "tma_int_vector_128b", - "MetricThreshold": "tma_int_vector_128b > 0.1 & tma_int_operations > 0.1 & tma_light_operations > 0.6", - "PublicDescription": "This metric represents 128-bit vector Integer ADD/SUB/SAD or VNNI (Vector Neural Network Instructions) uops fraction the CPU has retired. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_6, tma_ports_utilized_2", + "MetricThreshold": "tma_int_vector_128b > 0.1 & (tma_int_operations > 0.1 & tma_light_operations > 0.6)", + "PublicDescription": "This metric represents 128-bit vector Integer ADD/SUB/SAD or VNNI (Vector Neural Network Instructions) uops fraction the CPU has retired. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%" }, { @@ -1711,8 +1712,8 @@ "MetricExpr": "(INT_VEC_RETIRED.ADD_256 + INT_VEC_RETIRED.MUL_256 + INT_VEC_RETIRED.VNNI_256) / (tma_retiring * tma_info_thread_slots)", "MetricGroup": "Compute;IntVector;Pipeline;TopdownL4;tma_L4_group;tma_int_operations_group;tma_issue2P", "MetricName": "tma_int_vector_256b", - "MetricThreshold": "tma_int_vector_256b > 0.1 & tma_int_operations > 0.1 & tma_light_operations > 0.6", - "PublicDescription": "This metric represents 256-bit vector Integer ADD/SUB/SAD/MUL or VNNI (Vector Neural Network Instructions) uops fraction the CPU has retired. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_port_0, tma_port_1, tma_port_6, tma_ports_utilized_2", + "MetricThreshold": "tma_int_vector_256b > 0.1 & (tma_int_operations > 0.1 & tma_light_operations > 0.6)", + "PublicDescription": "This metric represents 256-bit vector Integer ADD/SUB/SAD/MUL or VNNI (Vector Neural Network Instructions) uops fraction the CPU has retired. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%" }, { @@ -1720,8 +1721,8 @@ "MetricExpr": "ICACHE_TAG.STALLS / tma_info_thread_clks", "MetricGroup": "BigFootprint;BvBC;FetchLat;MemoryTLB;TopdownL3;tma_L3_group;tma_fetch_latency_group", "MetricName": "tma_itlb_misses", - "MetricThreshold": "tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", - "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Instruction TLB (ITLB) misses. Sample with: FRONTEND_RETIRED.STLB_MISS, FRONTEND_RETIRED.ITLB_MISS", + "MetricThreshold": "tma_itlb_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Instruction TLB (ITLB) misses. Sample with: FRONTEND_RETIRED.STLB_MISS_PS;FRONTEND_RETIRED.ITLB_MISS_PS", "ScaleUnit": "100%" }, { @@ -1729,7 +1730,7 @@ "MetricExpr": "max((EXE_ACTIVITY.BOUND_ON_LOADS - MEMORY_ACTIVITY.STALLS_L1D_MISS) / tma_info_thread_clks, 0)", "MetricGroup": "CacheHits;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_issueL1;tma_issueMC;tma_memory_bound_group", "MetricName": "tma_l1_bound", - "MetricThreshold": "tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", "PublicDescription": "This metric estimates how often the CPU was stalled without loads missing the L1 Data (L1D) cache. The L1D cache typically has the shortest latency. However; in certain cases like loads blocked on older stores; a load might suffer due to high latency even though it is being satisfied by the L1D. Another example is loads who miss in the TLB. These cases are characterized by execution unit stalls; while some non-completed demand load lives in the machine without having that demand load missing the L1 cache. Sample with: MEM_LOAD_RETIRED.L1_HIT. Related metrics: tma_clears_resteers, tma_machine_clears, tma_microcode_sequencer, tma_ms_switches, tma_ports_utilized_1", "ScaleUnit": "100%" }, @@ -1738,7 +1739,7 @@ "MetricExpr": "min(2 * (MEM_INST_RETIRED.ALL_LOADS - MEM_LOAD_RETIRED.FB_HIT - MEM_LOAD_RETIRED.L1_MISS) * 20 / 100, max(CYCLE_ACTIVITY.CYCLES_MEM_ANY - MEMORY_ACTIVITY.CYCLES_L1D_MISS, 0)) / tma_info_thread_clks", "MetricGroup": "BvML;MemoryLat;TopdownL4;tma_L4_group;tma_l1_bound_group", "MetricName": "tma_l1_latency_dependency", - "MetricThreshold": "tma_l1_latency_dependency > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_l1_latency_dependency > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", "PublicDescription": "This metric([SKL+] roughly; [LNL]) estimates fraction of cycles with demand load accesses that hit the L1D cache. The short latency of the L1D cache may be exposed in pointer-chasing memory access patterns as an example. Sample with: MEM_LOAD_RETIRED.L1_HIT", "ScaleUnit": "100%" }, @@ -1747,16 +1748,17 @@ "MetricExpr": "(MEMORY_ACTIVITY.STALLS_L1D_MISS - MEMORY_ACTIVITY.STALLS_L2_MISS) / tma_info_thread_clks", "MetricGroup": "BvML;CacheHits;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_l2_bound", - "MetricThreshold": "tma_l2_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_l2_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", "PublicDescription": "This metric estimates how often the CPU was stalled due to L2 cache accesses by loads. Avoiding cache misses (i.e. L1 misses/L2 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L2_HIT", "ScaleUnit": "100%" }, { "BriefDescription": "This metric represents fraction of cycles with demand load accesses that hit the L2 cache under unloaded scenarios (possibly L2 latency limited)", - "MetricExpr": "(min(MEM_LOAD_RETIRED.L2_HIT * MEM_LOAD_RETIRED.L2_HIT:R, MEM_LOAD_RETIRED.L2_HIT * (4.4 * tma_info_system_core_frequency)) if 0 < MEM_LOAD_RETIRED.L2_HIT:R else MEM_LOAD_RETIRED.L2_HIT * (4.4 * tma_info_system_core_frequency)) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "MEM_LOAD_RETIRED.L2_HIT * min(MEM_LOAD_RETIRED.L2_HIT:R, 4.4 * tma_info_system_core_frequency) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks", "MetricGroup": "MemoryLat;TopdownL4;tma_L4_group;tma_l2_bound_group", "MetricName": "tma_l2_hit_latency", - "MetricThreshold": "tma_l2_hit_latency > 0.05 & tma_l2_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_l2_hit_latency > 0.05 & (tma_l2_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", "PublicDescription": "This metric represents fraction of cycles with demand load accesses that hit the L2 cache under unloaded scenarios (possibly L2 latency limited). Avoiding L1 cache misses (i.e. L1 misses/L2 hits) will improve the latency. Sample with: MEM_LOAD_RETIRED.L2_HIT", "ScaleUnit": "100%" }, @@ -1765,17 +1767,18 @@ "MetricExpr": "(MEMORY_ACTIVITY.STALLS_L2_MISS - MEMORY_ACTIVITY.STALLS_L3_MISS) / tma_info_thread_clks", "MetricGroup": "CacheHits;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_l3_bound", - "MetricThreshold": "tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", - "PublicDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core. Avoiding cache misses (i.e. L2 misses/L3 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L3_HIT", + "MetricThreshold": "tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", + "PublicDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core. Avoiding cache misses (i.e. L2 misses/L3 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L3_HIT_PS", "ScaleUnit": "100%" }, { "BriefDescription": "This metric estimates fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited)", - "MetricExpr": "(min(MEM_LOAD_RETIRED.L3_HIT * MEM_LOAD_RETIRED.L3_HIT:R, MEM_LOAD_RETIRED.L3_HIT * (37 * tma_info_system_core_frequency) - 4.4 * tma_info_system_core_frequency) if 0 < MEM_LOAD_RETIRED.L3_HIT:R else MEM_LOAD_RETIRED.L3_HIT * (37 * tma_info_system_core_frequency) - 4.4 * tma_info_system_core_frequency) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "MEM_LOAD_RETIRED.L3_HIT * min(MEM_LOAD_RETIRED.L3_HIT:R, 32.6 * tma_info_system_core_frequency) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks", "MetricGroup": "BvML;MemoryLat;TopdownL4;tma_L4_group;tma_issueLat;tma_l3_bound_group", "MetricName": "tma_l3_hit_latency", - "MetricThreshold": "tma_l3_hit_latency > 0.1 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", - "PublicDescription": "This metric estimates fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited). Avoiding private cache misses (i.e. L2 misses/L3 hits) will improve the latency; reduce contention with sibling physical cores and increase performance. Note the value of this node may overlap with its siblings. Sample with: MEM_LOAD_RETIRED.L3_HIT. Related metrics: tma_bottleneck_cache_memory_latency, tma_branch_resteers, tma_mem_latency, tma_store_latency", + "MetricThreshold": "tma_l3_hit_latency > 0.1 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric estimates fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited). Avoiding private cache misses (i.e. L2 misses/L3 hits) will improve the latency; reduce contention with sibling physical cores and increase performance. Note the value of this node may overlap with its siblings. Sample with: MEM_LOAD_RETIRED.L3_HIT_PS. Related metrics: tma_bottleneck_cache_memory_latency, tma_mem_latency", "ScaleUnit": "100%" }, { @@ -1783,19 +1786,19 @@ "MetricExpr": "DECODE.LCP / tma_info_thread_clks", "MetricGroup": "FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueFB", "MetricName": "tma_lcp", - "MetricThreshold": "tma_lcp > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", - "PublicDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs). Using proper compiler flags or Intel Compiler by default will certainly avoid this. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb", + "MetricThreshold": "tma_lcp > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", + "PublicDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs). Using proper compiler flags or Intel Compiler by default will certainly avoid this. #Link: Optimization Guide about LCP BKMs. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations , instructions that require no more than one uop (micro-operation)", + "BriefDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation)", "DefaultMetricgroupName": "TopdownL2", "MetricExpr": "max(0, tma_retiring - tma_heavy_operations)", "MetricGroup": "Default;Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_light_operations", "MetricThreshold": "tma_light_operations > 0.6", "MetricgroupNoGroup": "TopdownL2;Default", - "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations , instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized code running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. ([ICL+] Note this may undercount due to approximation using indirect events; [ADL+] .). Sample with: INST_RETIRED.PREC_DIST", + "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized code running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. ([ICL+] Note this may undercount due to approximation using indirect events; [ADL+] .). Sample with: INST_RETIRED.PREC_DIST", "ScaleUnit": "100%" }, { @@ -1812,7 +1815,7 @@ "MetricExpr": "max(0, tma_dtlb_load - tma_load_stlb_miss)", "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_load_group", "MetricName": "tma_load_stlb_hit", - "MetricThreshold": "tma_load_stlb_hit > 0.05 & tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_load_stlb_hit > 0.05 & (tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))", "ScaleUnit": "100%" }, { @@ -1820,31 +1823,31 @@ "MetricExpr": "DTLB_LOAD_MISSES.WALK_ACTIVE / tma_info_thread_clks", "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_load_group", "MetricName": "tma_load_stlb_miss", - "MetricThreshold": "tma_load_stlb_miss > 0.05 & tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_load_stlb_miss > 0.05 & (tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 1 GB pages for data load accesses", + "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 1 GB pages for data load accesses.", "MetricExpr": "tma_load_stlb_miss * DTLB_LOAD_MISSES.WALK_COMPLETED_1G / (DTLB_LOAD_MISSES.WALK_COMPLETED_4K + DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M + DTLB_LOAD_MISSES.WALK_COMPLETED_1G)", "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_load_stlb_miss_group", "MetricName": "tma_load_stlb_miss_1g", - "MetricThreshold": "tma_load_stlb_miss_1g > 0.05 & tma_load_stlb_miss > 0.05 & tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_load_stlb_miss_1g > 0.05 & (tma_load_stlb_miss > 0.05 & (tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))))", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 2 or 4 MB pages for data load accesses", + "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 2 or 4 MB pages for data load accesses.", "MetricExpr": "tma_load_stlb_miss * DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M / (DTLB_LOAD_MISSES.WALK_COMPLETED_4K + DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M + DTLB_LOAD_MISSES.WALK_COMPLETED_1G)", "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_load_stlb_miss_group", "MetricName": "tma_load_stlb_miss_2m", - "MetricThreshold": "tma_load_stlb_miss_2m > 0.05 & tma_load_stlb_miss > 0.05 & tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_load_stlb_miss_2m > 0.05 & (tma_load_stlb_miss > 0.05 & (tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))))", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 4 KB pages for data load accesses", + "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 4 KB pages for data load accesses.", "MetricExpr": "tma_load_stlb_miss * DTLB_LOAD_MISSES.WALK_COMPLETED_4K / (DTLB_LOAD_MISSES.WALK_COMPLETED_4K + DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M + DTLB_LOAD_MISSES.WALK_COMPLETED_1G)", "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_load_stlb_miss_group", "MetricName": "tma_load_stlb_miss_4k", - "MetricThreshold": "tma_load_stlb_miss_4k > 0.05 & tma_load_stlb_miss > 0.05 & tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_load_stlb_miss_4k > 0.05 & (tma_load_stlb_miss > 0.05 & (tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))))", "ScaleUnit": "100%" }, { @@ -1852,7 +1855,7 @@ "MetricExpr": "MEM_LOAD_L3_MISS_RETIRED.LOCAL_DRAM * MEM_LOAD_L3_MISS_RETIRED.LOCAL_DRAM:R * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks", "MetricGroup": "Server;TopdownL5;tma_L5_group;tma_mem_latency_group", "MetricName": "tma_local_mem", - "MetricThreshold": "tma_local_mem > 0.1 & tma_mem_latency > 0.1 & tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_local_mem > 0.1 & (tma_mem_latency > 0.1 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))", "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from local memory. Caching will improve the latency and increase performance. Sample with: MEM_LOAD_L3_MISS_RETIRED.LOCAL_DRAM", "ScaleUnit": "100%" }, @@ -1861,7 +1864,7 @@ "MetricExpr": "MEM_INST_RETIRED.LOCK_LOADS * MEM_INST_RETIRED.LOCK_LOADS:R / tma_info_thread_clks", "MetricGroup": "LockCont;Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_l1_bound_group", "MetricName": "tma_lock_latency", - "MetricThreshold": "tma_lock_latency > 0.2 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_lock_latency > 0.2 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", "PublicDescription": "This metric represents fraction of cycles the CPU spent handling cache misses due to lock operations. Due to the microarchitecture handling of locks; they are classified as L1_Bound regardless of what memory source satisfied them. Sample with: MEM_INST_RETIRED.LOCK_LOADS. Related metrics: tma_store_latency", "ScaleUnit": "100%" }, @@ -1877,19 +1880,19 @@ "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to memory bandwidth Allocation feature (RDT's memory bandwidth throttling)", + "BriefDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to memory bandwidth Allocation feature (RDT's memory bandwidth throttling).", "MetricExpr": "INT_MISC.MBA_STALLS / tma_info_thread_clks", "MetricGroup": "MemoryBW;Offcore;Server;TopdownL5;tma_L5_group;tma_mem_bandwidth_group", "MetricName": "tma_mba_stalls", - "MetricThreshold": "tma_mba_stalls > 0.1 & tma_mem_bandwidth > 0.2 & tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_mba_stalls > 0.1 & (tma_mem_bandwidth > 0.2 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))", "ScaleUnit": "100%" }, { "BriefDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory - DRAM ([SPR-HBM] and/or HBM)", - "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, cpu@OFFCORE_REQUESTS_OUTSTANDING.DATA_RD\\,cmask\\=0x4@) / tma_info_thread_clks", + "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, cpu@OFFCORE_REQUESTS_OUTSTANDING.DATA_RD\\,cmask\\=4@) / tma_info_thread_clks", "MetricGroup": "BvMB;MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueBW", "MetricName": "tma_mem_bandwidth", - "MetricThreshold": "tma_mem_bandwidth > 0.2 & tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_mem_bandwidth > 0.2 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", "PublicDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory - DRAM ([SPR-HBM] and/or HBM). The underlying heuristic assumes that a similar off-core traffic is generated by all IA cores. This metric does not aggregate non-data-read requests by this logical processor; requests from other IA Logical Processors/Physical Cores/sockets; or other non-IA devices like GPU; hence the maximum external memory bandwidth limits may or may not be approached when this metric is flagged (see Uncore counters for that). Related metrics: tma_bottleneck_cache_memory_bandwidth, tma_fb_full, tma_info_system_dram_bw_use, tma_sq_full", "ScaleUnit": "100%" }, @@ -1898,32 +1901,32 @@ "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD) / tma_info_thread_clks - tma_mem_bandwidth", "MetricGroup": "BvML;MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueLat", "MetricName": "tma_mem_latency", - "MetricThreshold": "tma_mem_latency > 0.1 & tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_mem_latency > 0.1 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", "PublicDescription": "This metric estimates fraction of cycles where the performance was likely hurt due to latency from external memory - DRAM ([SPR-HBM] and/or HBM). This metric does not aggregate requests from other Logical Processors/Physical Cores/sockets (see Uncore counters for that). Related metrics: tma_bottleneck_cache_memory_latency, tma_l3_hit_latency", "ScaleUnit": "100%" }, { "BriefDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck", "DefaultMetricgroupName": "TopdownL2", - "MetricExpr": "topdown\\-mem\\-bound / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * slots", + "MetricExpr": "topdown\\-mem\\-bound / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * tma_info_thread_slots", "MetricGroup": "Backend;Default;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_memory_bound", "MetricThreshold": "tma_memory_bound > 0.2 & tma_backend_bound > 0.2", "MetricgroupNoGroup": "TopdownL2;Default", - "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck. Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two)", + "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck. Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two).", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to LFENCE Instructions", + "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to LFENCE Instructions.", "MetricConstraint": "NO_GROUP_EVENTS_NMI", "MetricExpr": "13 * MISC2_RETIRED.LFENCE / tma_info_thread_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_serializing_operation_group", "MetricName": "tma_memory_fence", - "MetricThreshold": "tma_memory_fence > 0.05 & tma_serializing_operation > 0.1 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_memory_fence > 0.05 & (tma_serializing_operation > 0.1 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of slots where the CPU was retiring memory operations , uops for memory load or store accesses", + "BriefDescription": "This metric represents fraction of slots where the CPU was retiring memory operations -- uops for memory load or store accesses.", "MetricExpr": "tma_light_operations * MEM_UOP_RETIRED.ANY / (tma_retiring * tma_info_thread_slots)", "MetricGroup": "Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group", "MetricName": "tma_memory_operations", @@ -1944,7 +1947,7 @@ "MetricExpr": "tma_branch_mispredicts / tma_bad_speculation * INT_MISC.CLEAR_RESTEER_CYCLES / tma_info_thread_clks", "MetricGroup": "BadSpec;BrMispredicts;BvMP;TopdownL4;tma_L4_group;tma_branch_resteers_group;tma_issueBM", "MetricName": "tma_mispredicts_resteers", - "MetricThreshold": "tma_mispredicts_resteers > 0.05 & tma_branch_resteers > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricThreshold": "tma_mispredicts_resteers > 0.05 & (tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))", "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Branch Misprediction at execution stage. Sample with: INT_MISC.CLEAR_RESTEER_CYCLES. Related metrics: tma_bottleneck_mispredictions, tma_branch_mispredicts, tma_info_bad_spec_branch_misprediction_cost", "ScaleUnit": "100%" }, @@ -1958,17 +1961,17 @@ "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates penalty in terms of percentage of([SKL+] injected blend uops out of all Uops Issued , the Count Domain; [ADL+] cycles)", + "BriefDescription": "This metric estimates penalty in terms of percentage of([SKL+] injected blend uops out of all Uops Issued -- the Count Domain; [ADL+] cycles)", "MetricExpr": "160 * ASSISTS.SSE_AVX_MIX / tma_info_thread_clks", "MetricGroup": "TopdownL5;tma_L5_group;tma_issueMV;tma_ports_utilized_0_group", "MetricName": "tma_mixing_vectors", "MetricThreshold": "tma_mixing_vectors > 0.05", - "PublicDescription": "This metric estimates penalty in terms of percentage of([SKL+] injected blend uops out of all Uops Issued , the Count Domain; [ADL+] cycles). Usually a Mixing_Vectors over 5% is worth investigating. Read more in Appendix B1 of the Optimizations Guide for this topic. Related metrics: tma_ms_switches", + "PublicDescription": "This metric estimates penalty in terms of percentage of([SKL+] injected blend uops out of all Uops Issued -- the Count Domain; [ADL+] cycles). Usually a Mixing_Vectors over 5% is worth investigating. Read more in Appendix B1 of the Optimizations Guide for this topic. Related metrics: tma_ms_switches", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to the Microcode Sequencer (MS) unit - see Microcode_Sequencer node for details", - "MetricExpr": "max(IDQ.MS_CYCLES_ANY, cpu@UOPS_RETIRED.MS\\,cmask\\=0x1@ / (UOPS_RETIRED.SLOTS / UOPS_ISSUED.ANY)) / tma_info_core_core_clks / 2", + "BriefDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to the Microcode Sequencer (MS) unit - see Microcode_Sequencer node for details.", + "MetricExpr": "max(IDQ.MS_CYCLES_ANY, cpu@UOPS_RETIRED.MS\\,cmask\\=1@ / (UOPS_RETIRED.SLOTS / UOPS_ISSUED.ANY)) / tma_info_core_core_clks / 2", "MetricGroup": "MicroSeq;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group", "MetricName": "tma_ms", "MetricThreshold": "tma_ms > 0.05 & tma_fetch_bandwidth > 0.2", @@ -1976,10 +1979,10 @@ }, { "BriefDescription": "This metric estimates the fraction of cycles when the CPU was stalled due to switches of uop delivery to the Microcode Sequencer (MS)", - "MetricExpr": "3 * cpu@UOPS_RETIRED.MS\\,cmask\\=0x1\\,edge\\=0x1@ / (UOPS_RETIRED.SLOTS / UOPS_ISSUED.ANY) / tma_info_thread_clks", + "MetricExpr": "3 * cpu@UOPS_RETIRED.MS\\,cmask\\=1\\,edge@ / (UOPS_RETIRED.SLOTS / UOPS_ISSUED.ANY) / tma_info_thread_clks", "MetricGroup": "FetchLat;MicroSeq;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueMC;tma_issueMS;tma_issueMV;tma_issueSO", "MetricName": "tma_ms_switches", - "MetricThreshold": "tma_ms_switches > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricThreshold": "tma_ms_switches > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", "PublicDescription": "This metric estimates the fraction of cycles when the CPU was stalled due to switches of uop delivery to the Microcode Sequencer (MS). Commonly used instructions are optimized for delivery by the DSB (decoded i-cache) or MITE (legacy instruction decode) pipelines. Certain operations cannot be handled natively by the execution pipeline; and must be performed by microcode (small programs injected into the execution stream). Switching to the MS too often can negatively impact performance. The MS is designated to deliver long uop flows required by CISC instructions like CPUID; or uncommon conditions like Floating Point Assists when dealing with Denormals. Sample with: IDQ.MS_SWITCHES. Related metrics: tma_bottleneck_irregular_overhead, tma_clears_resteers, tma_l1_bound, tma_machine_clears, tma_microcode_sequencer, tma_mixing_vectors, tma_serializing_operation", "ScaleUnit": "100%" }, @@ -1989,7 +1992,7 @@ "MetricGroup": "Branches;BvBO;Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group", "MetricName": "tma_non_fused_branches", "MetricThreshold": "tma_non_fused_branches > 0.1 & tma_light_operations > 0.6", - "PublicDescription": "This metric represents fraction of slots where the CPU was retiring branch instructions that were not fused. Non-conditional branches like direct JMP or CALL would count here. Can be used to examine fusible conditional jumps that were not fused", + "PublicDescription": "This metric represents fraction of slots where the CPU was retiring branch instructions that were not fused. Non-conditional branches like direct JMP or CALL would count here. Can be used to examine fusible conditional jumps that were not fused.", "ScaleUnit": "100%" }, { @@ -1997,7 +2000,7 @@ "MetricExpr": "tma_light_operations * INST_RETIRED.NOP / (tma_retiring * tma_info_thread_slots)", "MetricGroup": "BvBO;Pipeline;TopdownL4;tma_L4_group;tma_other_light_ops_group", "MetricName": "tma_nop_instructions", - "MetricThreshold": "tma_nop_instructions > 0.1 & tma_other_light_ops > 0.3 & tma_light_operations > 0.6", + "MetricThreshold": "tma_nop_instructions > 0.1 & (tma_other_light_ops > 0.3 & tma_light_operations > 0.6)", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring NOP (no op) instructions. Compilers often use NOPs for certain address alignments - e.g. start address of a function or loop body. Sample with: INST_RETIRED.NOP", "ScaleUnit": "100%" }, @@ -2011,19 +2014,19 @@ "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates fraction of slots the CPU was stalled due to other cases of misprediction (non-retired x86 branches or other types)", + "BriefDescription": "This metric estimates fraction of slots the CPU was stalled due to other cases of misprediction (non-retired x86 branches or other types).", "MetricExpr": "max(tma_branch_mispredicts * (1 - BR_MISP_RETIRED.ALL_BRANCHES / (INT_MISC.CLEARS_COUNT - MACHINE_CLEARS.COUNT)), 0.0001)", "MetricGroup": "BrMispredicts;BvIO;TopdownL3;tma_L3_group;tma_branch_mispredicts_group", "MetricName": "tma_other_mispredicts", - "MetricThreshold": "tma_other_mispredicts > 0.05 & tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", + "MetricThreshold": "tma_other_mispredicts > 0.05 & (tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15)", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of slots the CPU has wasted due to Nukes (Machine Clears) not related to memory ordering", + "BriefDescription": "This metric represents fraction of slots the CPU has wasted due to Nukes (Machine Clears) not related to memory ordering.", "MetricExpr": "max(tma_machine_clears * (1 - MACHINE_CLEARS.MEMORY_ORDERING / MACHINE_CLEARS.COUNT), 0.0001)", "MetricGroup": "BvIO;Machine_Clears;TopdownL3;tma_L3_group;tma_machine_clears_group", "MetricName": "tma_other_nukes", - "MetricThreshold": "tma_other_nukes > 0.05 & tma_machine_clears > 0.1 & tma_bad_speculation > 0.15", + "MetricThreshold": "tma_other_nukes > 0.05 & (tma_machine_clears > 0.1 & tma_bad_speculation > 0.15)", "ScaleUnit": "100%" }, { @@ -2032,7 +2035,7 @@ "MetricGroup": "TopdownL5;tma_L5_group;tma_assists_group", "MetricName": "tma_page_faults", "MetricThreshold": "tma_page_faults > 0.05", - "PublicDescription": "This metric roughly estimates fraction of slots the CPU retired uops as a result of handing Page Faults. A Page Fault may apply on first application access to a memory page. Note operating system handling of page faults accounts for the majority of its cost", + "PublicDescription": "This metric roughly estimates fraction of slots the CPU retired uops as a result of handing Page Faults. A Page Fault may apply on first application access to a memory page. Note operating system handling of page faults accounts for the majority of its cost.", "ScaleUnit": "100%" }, { @@ -2041,7 +2044,7 @@ "MetricGroup": "Compute;TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P", "MetricName": "tma_port_0", "MetricThreshold": "tma_port_0 > 0.6", - "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 0 ([SNB+] ALU; [HSW+] ALU and 2nd branch). Sample with: UOPS_DISPATCHED.PORT_0. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_1, tma_port_6, tma_ports_utilized_2", + "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 0 ([SNB+] ALU; [HSW+] ALU and 2nd branch). Sample with: UOPS_DISPATCHED.PORT_0. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%" }, { @@ -2050,7 +2053,7 @@ "MetricGroup": "TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P", "MetricName": "tma_port_1", "MetricThreshold": "tma_port_1 > 0.6", - "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 1 (ALU). Sample with: UOPS_DISPATCHED.PORT_1. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_6, tma_ports_utilized_2", + "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 1 (ALU). Sample with: UOPS_DISPATCHED.PORT_1. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_5, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%" }, { @@ -2059,7 +2062,7 @@ "MetricGroup": "TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P", "MetricName": "tma_port_6", "MetricThreshold": "tma_port_6 > 0.6", - "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 6 ([HSW+] Primary Branch and simple ALU). Sample with: UOPS_DISPATCHED.PORT_1. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_ports_utilized_2", + "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 6 ([HSW+] Primary Branch and simple ALU). Sample with: UOPS_DISPATCHED.PORT_1. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_ports_utilized_2", "ScaleUnit": "100%" }, { @@ -2067,8 +2070,8 @@ "MetricExpr": "((tma_ports_utilized_0 * tma_info_thread_clks + (EXE_ACTIVITY.1_PORTS_UTIL + tma_retiring * EXE_ACTIVITY.2_3_PORTS_UTIL)) / tma_info_thread_clks if ARITH.DIV_ACTIVE < CYCLE_ACTIVITY.STALLS_TOTAL - EXE_ACTIVITY.BOUND_ON_LOADS else (EXE_ACTIVITY.1_PORTS_UTIL + tma_retiring * EXE_ACTIVITY.2_3_PORTS_UTIL) / tma_info_thread_clks)", "MetricGroup": "PortsUtil;TopdownL3;tma_L3_group;tma_core_bound_group", "MetricName": "tma_ports_utilization", - "MetricThreshold": "tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", - "PublicDescription": "This metric estimates fraction of cycles the CPU performance was potentially limited due to Core computation issues (non divider-related). Two distinct categories can be attributed into this metric: (1) heavy data-dependency among contiguous instructions would manifest in this metric - such cases are often referred to as low Instruction Level Parallelism (ILP). (2) Contention on some hardware execution unit other than Divider. For example; when there are too many multiply operations", + "MetricThreshold": "tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)", + "PublicDescription": "This metric estimates fraction of cycles the CPU performance was potentially limited due to Core computation issues (non divider-related). Two distinct categories can be attributed into this metric: (1) heavy data-dependency among contiguous instructions would manifest in this metric - such cases are often referred to as low Instruction Level Parallelism (ILP). (2) Contention on some hardware execution unit other than Divider. For example; when there are too many multiply operations.", "ScaleUnit": "100%" }, { @@ -2076,8 +2079,8 @@ "MetricExpr": "max(EXE_ACTIVITY.EXE_BOUND_0_PORTS - RESOURCE_STALLS.SCOREBOARD, 0) / tma_info_thread_clks", "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group", "MetricName": "tma_ports_utilized_0", - "MetricThreshold": "tma_ports_utilized_0 > 0.2 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", - "PublicDescription": "This metric represents fraction of cycles CPU executed no uops on any execution port (Logical Processor cycles since ICL, Physical Core cycles otherwise). Long-latency instructions like divides may contribute to this metric", + "MetricThreshold": "tma_ports_utilized_0 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric represents fraction of cycles CPU executed no uops on any execution port (Logical Processor cycles since ICL, Physical Core cycles otherwise). Long-latency instructions like divides may contribute to this metric.", "ScaleUnit": "100%" }, { @@ -2085,7 +2088,7 @@ "MetricExpr": "EXE_ACTIVITY.1_PORTS_UTIL / tma_info_thread_clks", "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_issueL1;tma_ports_utilization_group", "MetricName": "tma_ports_utilized_1", - "MetricThreshold": "tma_ports_utilized_1 > 0.2 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_ports_utilized_1 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", "PublicDescription": "This metric represents fraction of cycles where the CPU executed total of 1 uop per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise). This can be due to heavy data-dependency among software instructions; or over oversubscribing a particular hardware resource. In some other cases with high 1_Port_Utilized and L1_Bound; this metric can point to L1 data-cache latency bottleneck that may not necessarily manifest with complete execution starvation (due to the short L1 latency e.g. walking a linked list) - looking at the assembly can be helpful. Sample with: EXE_ACTIVITY.1_PORTS_UTIL. Related metrics: tma_l1_bound", "ScaleUnit": "100%" }, @@ -2095,8 +2098,8 @@ "MetricExpr": "EXE_ACTIVITY.2_PORTS_UTIL / tma_info_thread_clks", "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_issue2P;tma_ports_utilization_group", "MetricName": "tma_ports_utilized_2", - "MetricThreshold": "tma_ports_utilized_2 > 0.15 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", - "PublicDescription": "This metric represents fraction of cycles CPU executed total of 2 uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise). Loop Vectorization -most compilers feature auto-Vectorization options today- reduces pressure on the execution ports as multiple elements are calculated with same uop. Sample with: EXE_ACTIVITY.2_PORTS_UTIL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_6", + "MetricThreshold": "tma_ports_utilized_2 > 0.15 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric represents fraction of cycles CPU executed total of 2 uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise). Loop Vectorization -most compilers feature auto-Vectorization options today- reduces pressure on the execution ports as multiple elements are calculated with same uop. Sample with: EXE_ACTIVITY.2_PORTS_UTIL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_port_6", "ScaleUnit": "100%" }, { @@ -2105,7 +2108,7 @@ "MetricExpr": "UOPS_EXECUTED.CYCLES_GE_3 / tma_info_thread_clks", "MetricGroup": "BvCB;PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group", "MetricName": "tma_ports_utilized_3m", - "MetricThreshold": "tma_ports_utilized_3m > 0.4 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_ports_utilized_3m > 0.4 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", "PublicDescription": "This metric represents fraction of cycles CPU executed total of 3 or more uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise). Sample with: UOPS_EXECUTED.CYCLES_GE_3", "ScaleUnit": "100%" }, @@ -2114,8 +2117,8 @@ "MetricExpr": "(MEM_LOAD_L3_MISS_RETIRED.REMOTE_HITM * MEM_LOAD_L3_MISS_RETIRED.REMOTE_HITM:R + MEM_LOAD_L3_MISS_RETIRED.REMOTE_FWD * MEM_LOAD_L3_MISS_RETIRED.REMOTE_FWD:R) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks", "MetricGroup": "Offcore;Server;Snoop;TopdownL5;tma_L5_group;tma_issueSyncxn;tma_mem_latency_group", "MetricName": "tma_remote_cache", - "MetricThreshold": "tma_remote_cache > 0.05 & tma_mem_latency > 0.1 & tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", - "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from remote cache in other sockets including synchronizations issues. This is caused often due to non-optimal NUMA allocations. Sample with: MEM_LOAD_L3_MISS_RETIRED.REMOTE_HITM, MEM_LOAD_L3_MISS_RETIRED.REMOTE_FWD. Related metrics: tma_bottleneck_memory_synchronization, tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_machine_clears", + "MetricThreshold": "tma_remote_cache > 0.05 & (tma_mem_latency > 0.1 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))", + "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from remote cache in other sockets including synchronizations issues. This is caused often due to non-optimal NUMA allocations. #link to NUMA article. Sample with: MEM_LOAD_L3_MISS_RETIRED.REMOTE_HITM_PS;MEM_LOAD_L3_MISS_RETIRED.REMOTE_FWD_PS. Related metrics: tma_bottleneck_memory_synchronization, tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_machine_clears", "ScaleUnit": "100%" }, { @@ -2123,22 +2126,22 @@ "MetricExpr": "MEM_LOAD_L3_MISS_RETIRED.REMOTE_DRAM * MEM_LOAD_L3_MISS_RETIRED.REMOTE_DRAM:R * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks", "MetricGroup": "Server;Snoop;TopdownL5;tma_L5_group;tma_mem_latency_group", "MetricName": "tma_remote_mem", - "MetricThreshold": "tma_remote_mem > 0.1 & tma_mem_latency > 0.1 & tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", - "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from remote memory. This is caused often due to non-optimal NUMA allocations. Sample with: MEM_LOAD_L3_MISS_RETIRED.REMOTE_DRAM", + "MetricThreshold": "tma_remote_mem > 0.1 & (tma_mem_latency > 0.1 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))", + "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from remote memory. This is caused often due to non-optimal NUMA allocations. #link to NUMA article. Sample with: MEM_LOAD_L3_MISS_RETIRED.REMOTE_DRAM_PS", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to retired misprediction by (indirect) RET instructions", + "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to retired misprediction by (indirect) RET instructions.", "MetricExpr": "BR_MISP_RETIRED.RET_COST * BR_MISP_RETIRED.RET_COST:R / tma_info_thread_clks", "MetricGroup": "BrMispredicts;TopdownL3;tma_L3_group;tma_branch_mispredicts_group", "MetricName": "tma_ret_mispredicts", - "MetricThreshold": "tma_ret_mispredicts > 0.05 & tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", + "MetricThreshold": "tma_ret_mispredicts > 0.05 & (tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15)", "ScaleUnit": "100%" }, { "BriefDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired", "DefaultMetricgroupName": "TopdownL1", - "MetricExpr": "topdown\\-retiring / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * slots", + "MetricExpr": "topdown\\-retiring / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * tma_info_thread_slots", "MetricGroup": "BvUW;Default;TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_retiring", "MetricThreshold": "tma_retiring > 0.7 | tma_heavy_operations > 0.1", @@ -2151,7 +2154,7 @@ "MetricExpr": "RESOURCE_STALLS.SCOREBOARD / tma_info_thread_clks + tma_c02_wait", "MetricGroup": "BvIO;PortsUtil;TopdownL3;tma_L3_group;tma_core_bound_group;tma_issueSO", "MetricName": "tma_serializing_operation", - "MetricThreshold": "tma_serializing_operation > 0.1 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_serializing_operation > 0.1 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)", "PublicDescription": "This metric represents fraction of cycles the CPU issue-pipeline was stalled due to serializing operations. Instructions like CPUID; WRMSR or LFENCE serialize the out-of-order execution which may limit performance. Sample with: RESOURCE_STALLS.SCOREBOARD. Related metrics: tma_ms_switches", "ScaleUnit": "100%" }, @@ -2160,8 +2163,8 @@ "MetricExpr": "tma_light_operations * INT_VEC_RETIRED.SHUFFLES / (tma_retiring * tma_info_thread_slots)", "MetricGroup": "HPC;Pipeline;TopdownL4;tma_L4_group;tma_other_light_ops_group", "MetricName": "tma_shuffles_256b", - "MetricThreshold": "tma_shuffles_256b > 0.1 & tma_other_light_ops > 0.3 & tma_light_operations > 0.6", - "PublicDescription": "This metric represents fraction of slots where the CPU was retiring Shuffle operations of 256-bit vector size (FP or Integer). Shuffles may incur slow cross \"vector lane\" data transfers", + "MetricThreshold": "tma_shuffles_256b > 0.1 & (tma_other_light_ops > 0.3 & tma_light_operations > 0.6)", + "PublicDescription": "This metric represents fraction of slots where the CPU was retiring Shuffle operations of 256-bit vector size (FP or Integer). Shuffles may incur slow cross \"vector lane\" data transfers.", "ScaleUnit": "100%" }, { @@ -2170,26 +2173,26 @@ "MetricExpr": "CPU_CLK_UNHALTED.PAUSE / tma_info_thread_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_serializing_operation_group", "MetricName": "tma_slow_pause", - "MetricThreshold": "tma_slow_pause > 0.05 & tma_serializing_operation > 0.1 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_slow_pause > 0.05 & (tma_serializing_operation > 0.1 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to PAUSE Instructions. Sample with: CPU_CLK_UNHALTED.PAUSE_INST", "ScaleUnit": "100%" }, { "BriefDescription": "This metric estimates fraction of cycles handling memory load split accesses - load that cross 64-byte cache line boundary", - "MetricExpr": "(min(MEM_INST_RETIRED.SPLIT_LOADS * MEM_INST_RETIRED.SPLIT_LOADS:R, MEM_INST_RETIRED.SPLIT_LOADS * tma_info_memory_load_miss_real_latency) if 0 < MEM_INST_RETIRED.SPLIT_LOADS:R else MEM_INST_RETIRED.SPLIT_LOADS * tma_info_memory_load_miss_real_latency) / tma_info_thread_clks", + "MetricExpr": "MEM_INST_RETIRED.SPLIT_LOADS * min(MEM_INST_RETIRED.SPLIT_LOADS:R, tma_info_memory_load_miss_real_latency) / tma_info_thread_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group", "MetricName": "tma_split_loads", "MetricThreshold": "tma_split_loads > 0.3", - "PublicDescription": "This metric estimates fraction of cycles handling memory load split accesses - load that cross 64-byte cache line boundary. Sample with: MEM_INST_RETIRED.SPLIT_LOADS", + "PublicDescription": "This metric estimates fraction of cycles handling memory load split accesses - load that cross 64-byte cache line boundary. Sample with: MEM_INST_RETIRED.SPLIT_LOADS_PS", "ScaleUnit": "100%" }, { "BriefDescription": "This metric represents rate of split store accesses", - "MetricExpr": "(min(MEM_INST_RETIRED.SPLIT_STORES * MEM_INST_RETIRED.SPLIT_STORES:R, MEM_INST_RETIRED.SPLIT_STORES) if 0 < MEM_INST_RETIRED.SPLIT_STORES:R else MEM_INST_RETIRED.SPLIT_STORES) / tma_info_thread_clks", + "MetricExpr": "MEM_INST_RETIRED.SPLIT_STORES * min(MEM_INST_RETIRED.SPLIT_STORES:R, 1) / tma_info_thread_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_issueSpSt;tma_store_bound_group", "MetricName": "tma_split_stores", - "MetricThreshold": "tma_split_stores > 0.2 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", - "PublicDescription": "This metric represents rate of split store accesses. Consider aligning your data to the 64-byte cache line granularity. Sample with: MEM_INST_RETIRED.SPLIT_STORES", + "MetricThreshold": "tma_split_stores > 0.2 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric represents rate of split store accesses. Consider aligning your data to the 64-byte cache line granularity. Sample with: MEM_INST_RETIRED.SPLIT_STORES_PS. Related metrics: tma_port_4", "ScaleUnit": "100%" }, { @@ -2197,7 +2200,7 @@ "MetricExpr": "(XQ.FULL_CYCLES + L1D_PEND_MISS.L2_STALLS) / tma_info_thread_clks", "MetricGroup": "BvMB;MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_issueBW;tma_l3_bound_group", "MetricName": "tma_sq_full", - "MetricThreshold": "tma_sq_full > 0.3 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_sq_full > 0.3 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", "PublicDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors). Related metrics: tma_bottleneck_cache_memory_bandwidth, tma_fb_full, tma_info_system_dram_bw_use, tma_mem_bandwidth", "ScaleUnit": "100%" }, @@ -2206,8 +2209,8 @@ "MetricExpr": "EXE_ACTIVITY.BOUND_ON_STORES / tma_info_thread_clks", "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_store_bound", - "MetricThreshold": "tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", - "PublicDescription": "This metric estimates how often CPU was stalled due to RFO store memory accesses; RFO store issue a read-for-ownership request before the write. Even though store accesses do not typically stall out-of-order CPUs; there are few cases where stores can lead to actual stalls. This metric will be flagged should RFO stores be a bottleneck. Sample with: MEM_INST_RETIRED.ALL_STORES", + "MetricThreshold": "tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", + "PublicDescription": "This metric estimates how often CPU was stalled due to RFO store memory accesses; RFO store issue a read-for-ownership request before the write. Even though store accesses do not typically stall out-of-order CPUs; there are few cases where stores can lead to actual stalls. This metric will be flagged should RFO stores be a bottleneck. Sample with: MEM_INST_RETIRED.ALL_STORES_PS", "ScaleUnit": "100%" }, { @@ -2215,8 +2218,8 @@ "MetricExpr": "13 * LD_BLOCKS.STORE_FORWARD / tma_info_thread_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group", "MetricName": "tma_store_fwd_blk", - "MetricThreshold": "tma_store_fwd_blk > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", - "PublicDescription": "This metric roughly estimates fraction of cycles when the memory subsystem had loads blocked since they could not forward data from earlier (in program order) overlapping stores. To streamline memory operations in the pipeline; a load can avoid waiting for memory if a prior in-flight store is writing the data that the load wants to read (store forwarding process). However; in some cases the load may be blocked for a significant time pending the store forward. For example; when the prior store is writing a smaller region than the load is reading", + "MetricThreshold": "tma_store_fwd_blk > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric roughly estimates fraction of cycles when the memory subsystem had loads blocked since they could not forward data from earlier (in program order) overlapping stores. To streamline memory operations in the pipeline; a load can avoid waiting for memory if a prior in-flight store is writing the data that the load wants to read (store forwarding process). However; in some cases the load may be blocked for a significant time pending the store forward. For example; when the prior store is writing a smaller region than the load is reading.", "ScaleUnit": "100%" }, { @@ -2224,8 +2227,8 @@ "MetricExpr": "(MEM_STORE_RETIRED.L2_HIT * 10 * (1 - MEM_INST_RETIRED.LOCK_LOADS / MEM_INST_RETIRED.ALL_STORES) + (1 - MEM_INST_RETIRED.LOCK_LOADS / MEM_INST_RETIRED.ALL_STORES) * min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO)) / tma_info_thread_clks", "MetricGroup": "BvML;LockCont;MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_issueSL;tma_store_bound_group", "MetricName": "tma_store_latency", - "MetricThreshold": "tma_store_latency > 0.1 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", - "PublicDescription": "This metric estimates fraction of cycles the CPU spent handling L1D store misses. Store accesses usually less impact out-of-order core performance; however; holding resources for longer time can lead into undesired implications (e.g. contention on L1D fill-buffer entries - see FB_Full). Related metrics: tma_branch_resteers, tma_fb_full, tma_l3_hit_latency, tma_lock_latency", + "MetricThreshold": "tma_store_latency > 0.1 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric estimates fraction of cycles the CPU spent handling L1D store misses. Store accesses usually less impact out-of-order core performance; however; holding resources for longer time can lead into undesired implications (e.g. contention on L1D fill-buffer entries - see FB_Full). Related metrics: tma_fb_full, tma_lock_latency", "ScaleUnit": "100%" }, { @@ -2242,7 +2245,7 @@ "MetricExpr": "max(0, tma_dtlb_store - tma_store_stlb_miss)", "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_store_group", "MetricName": "tma_store_stlb_hit", - "MetricThreshold": "tma_store_stlb_hit > 0.05 & tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_store_stlb_hit > 0.05 & (tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))", "ScaleUnit": "100%" }, { @@ -2250,31 +2253,31 @@ "MetricExpr": "DTLB_STORE_MISSES.WALK_ACTIVE / tma_info_core_core_clks", "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_store_group", "MetricName": "tma_store_stlb_miss", - "MetricThreshold": "tma_store_stlb_miss > 0.05 & tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_store_stlb_miss > 0.05 & (tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 1 GB pages for data store accesses", + "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 1 GB pages for data store accesses.", "MetricExpr": "tma_store_stlb_miss * DTLB_STORE_MISSES.WALK_COMPLETED_1G / (DTLB_STORE_MISSES.WALK_COMPLETED_4K + DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M + DTLB_STORE_MISSES.WALK_COMPLETED_1G)", "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_store_stlb_miss_group", "MetricName": "tma_store_stlb_miss_1g", - "MetricThreshold": "tma_store_stlb_miss_1g > 0.05 & tma_store_stlb_miss > 0.05 & tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_store_stlb_miss_1g > 0.05 & (tma_store_stlb_miss > 0.05 & (tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))))", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 2 or 4 MB pages for data store accesses", + "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 2 or 4 MB pages for data store accesses.", "MetricExpr": "tma_store_stlb_miss * DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M / (DTLB_STORE_MISSES.WALK_COMPLETED_4K + DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M + DTLB_STORE_MISSES.WALK_COMPLETED_1G)", "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_store_stlb_miss_group", "MetricName": "tma_store_stlb_miss_2m", - "MetricThreshold": "tma_store_stlb_miss_2m > 0.05 & tma_store_stlb_miss > 0.05 & tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_store_stlb_miss_2m > 0.05 & (tma_store_stlb_miss > 0.05 & (tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))))", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 4 KB pages for data store accesses", + "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 4 KB pages for data store accesses.", "MetricExpr": "tma_store_stlb_miss * DTLB_STORE_MISSES.WALK_COMPLETED_4K / (DTLB_STORE_MISSES.WALK_COMPLETED_4K + DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M + DTLB_STORE_MISSES.WALK_COMPLETED_1G)", "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_store_stlb_miss_group", "MetricName": "tma_store_stlb_miss_4k", - "MetricThreshold": "tma_store_stlb_miss_4k > 0.05 & tma_store_stlb_miss > 0.05 & tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_store_stlb_miss_4k > 0.05 & (tma_store_stlb_miss > 0.05 & (tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))))", "ScaleUnit": "100%" }, { @@ -2282,7 +2285,7 @@ "MetricExpr": "9 * OCR.STREAMING_WR.ANY_RESPONSE / tma_info_thread_clks", "MetricGroup": "MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_issueSmSt;tma_store_bound_group", "MetricName": "tma_streaming_stores", - "MetricThreshold": "tma_streaming_stores > 0.2 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_streaming_stores > 0.2 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", "PublicDescription": "This metric estimates how often CPU was stalled due to Streaming store memory accesses; Streaming store optimize out a read request required by RFO stores. Even though store accesses do not typically stall out-of-order CPUs; there are few cases where stores can lead to actual stalls. This metric will be flagged should Streaming stores be a bottleneck. Sample with: OCR.STREAMING_WR.ANY_RESPONSE. Related metrics: tma_fb_full", "ScaleUnit": "100%" }, @@ -2291,7 +2294,7 @@ "MetricExpr": "INT_MISC.UNKNOWN_BRANCH_CYCLES / tma_info_thread_clks", "MetricGroup": "BigFootprint;BvBC;FetchLat;TopdownL4;tma_L4_group;tma_branch_resteers_group", "MetricName": "tma_unknown_branches", - "MetricThreshold": "tma_unknown_branches > 0.05 & tma_branch_resteers > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricThreshold": "tma_unknown_branches > 0.05 & (tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))", "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to new branch address clears. These are fetched branches the Branch Prediction Unit was unable to recognize (e.g. first time the branch is fetched or hitting BTB capacity limit) hence called Unknown Branches. Sample with: FRONTEND_RETIRED.UNKNOWN_BRANCH", "ScaleUnit": "100%" }, @@ -2300,8 +2303,8 @@ "MetricExpr": "tma_retiring * UOPS_EXECUTED.X87 / UOPS_EXECUTED.THREAD", "MetricGroup": "Compute;TopdownL4;tma_L4_group;tma_fp_arith_group", "MetricName": "tma_x87_use", - "MetricThreshold": "tma_x87_use > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6", - "PublicDescription": "This metric serves as an approximation of legacy x87 usage. It accounts for instructions beyond X87 FP arithmetic operations; hence may be used as a thermometer to avoid X87 high usage and preferably upgrade to modern ISA. See Tip under Tuning Hint", + "MetricThreshold": "tma_x87_use > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6)", + "PublicDescription": "This metric serves as an approximation of legacy x87 usage. It accounts for instructions beyond X87 FP arithmetic operations; hence may be used as a thermometer to avoid X87 high usage and preferably upgrade to modern ISA. See Tip under Tuning Hint.", "ScaleUnit": "100%" }, { diff --git a/tools/perf/pmu-events/arch/x86/graniterapids/memory.json b/tools/perf/pmu-events/arch/x86/graniterapids/memory.json index 5da5a10275ba..4db39f304c2c 100644 --- a/tools/perf/pmu-events/arch/x86/graniterapids/memory.json +++ b/tools/perf/pmu-events/arch/x86/graniterapids/memory.json @@ -5,6 +5,7 @@ "CounterMask": "2", "EventCode": "0xa3", "EventName": "CYCLE_ACTIVITY.CYCLES_L3_MISS", + "PublicDescription": "Cycles while L3 cache miss demand load is outstanding. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x2" }, @@ -14,6 +15,7 @@ "CounterMask": "6", "EventCode": "0xa3", "EventName": "CYCLE_ACTIVITY.STALLS_L3_MISS", + "PublicDescription": "Execution stalls while L3 cache miss demand load is outstanding. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x6" }, @@ -22,7 +24,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc3", "EventName": "MACHINE_CLEARS.MEMORY_ORDERING", - "PublicDescription": "Counts the number of Machine Clears detected dye to memory ordering. Memory Ordering Machine Clears may apply when a memory read may not conform to the memory ordering rules of the x86 architecture", + "PublicDescription": "Counts the number of Machine Clears detected dye to memory ordering. Memory Ordering Machine Clears may apply when a memory read may not conform to the memory ordering rules of the x86 architecture Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x2" }, @@ -32,6 +34,7 @@ "CounterMask": "2", "EventCode": "0x47", "EventName": "MEMORY_ACTIVITY.CYCLES_L1D_MISS", + "PublicDescription": "Cycles while L1 cache miss demand load is outstanding. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x2" }, @@ -41,6 +44,7 @@ "CounterMask": "3", "EventCode": "0x47", "EventName": "MEMORY_ACTIVITY.STALLS_L1D_MISS", + "PublicDescription": "Execution stalls while L1 cache miss demand load is outstanding. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x3" }, @@ -50,7 +54,7 @@ "CounterMask": "5", "EventCode": "0x47", "EventName": "MEMORY_ACTIVITY.STALLS_L2_MISS", - "PublicDescription": "Execution stalls while L2 cache miss demand cacheable load request is outstanding (will not count for uncacheable demand requests e.g. bus lock).", + "PublicDescription": "Execution stalls while L2 cache miss demand cacheable load request is outstanding (will not count for uncacheable demand requests e.g. bus lock). Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x5" }, @@ -60,7 +64,7 @@ "CounterMask": "9", "EventCode": "0x47", "EventName": "MEMORY_ACTIVITY.STALLS_L3_MISS", - "PublicDescription": "Execution stalls while L3 cache miss demand cacheable load request is outstanding (will not count for uncacheable demand requests e.g. bus lock).", + "PublicDescription": "Execution stalls while L3 cache miss demand cacheable load request is outstanding (will not count for uncacheable demand requests e.g. bus lock). Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x9" }, @@ -72,7 +76,7 @@ "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_1024", "MSRIndex": "0x3F6", "MSRValue": "0x400", - "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 1024 cycles. Reported latency may be longer than just the memory latency.", + "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 1024 cycles. Reported latency may be longer than just the memory latency. Available PDIST counters: 0", "SampleAfterValue": "53", "UMask": "0x1" }, @@ -84,7 +88,7 @@ "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_128", "MSRIndex": "0x3F6", "MSRValue": "0x80", - "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 128 cycles. Reported latency may be longer than just the memory latency.", + "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 128 cycles. Reported latency may be longer than just the memory latency. Available PDIST counters: 0", "SampleAfterValue": "1009", "UMask": "0x1" }, @@ -96,7 +100,7 @@ "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_16", "MSRIndex": "0x3F6", "MSRValue": "0x10", - "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 16 cycles. Reported latency may be longer than just the memory latency.", + "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 16 cycles. Reported latency may be longer than just the memory latency. Available PDIST counters: 0", "SampleAfterValue": "20011", "UMask": "0x1" }, @@ -108,7 +112,7 @@ "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_2048", "MSRIndex": "0x3F6", "MSRValue": "0x800", - "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 2048 cycles. Reported latency may be longer than just the memory latency.", + "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 2048 cycles. Reported latency may be longer than just the memory latency. Available PDIST counters: 0", "SampleAfterValue": "23", "UMask": "0x1" }, @@ -120,7 +124,7 @@ "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_256", "MSRIndex": "0x3F6", "MSRValue": "0x100", - "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 256 cycles. Reported latency may be longer than just the memory latency.", + "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 256 cycles. Reported latency may be longer than just the memory latency. Available PDIST counters: 0", "SampleAfterValue": "503", "UMask": "0x1" }, @@ -132,7 +136,7 @@ "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_32", "MSRIndex": "0x3F6", "MSRValue": "0x20", - "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 32 cycles. Reported latency may be longer than just the memory latency.", + "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 32 cycles. Reported latency may be longer than just the memory latency. Available PDIST counters: 0", "SampleAfterValue": "100007", "UMask": "0x1" }, @@ -144,7 +148,7 @@ "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_4", "MSRIndex": "0x3F6", "MSRValue": "0x4", - "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 4 cycles. Reported latency may be longer than just the memory latency.", + "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 4 cycles. Reported latency may be longer than just the memory latency. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -156,7 +160,7 @@ "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_512", "MSRIndex": "0x3F6", "MSRValue": "0x200", - "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 512 cycles. Reported latency may be longer than just the memory latency.", + "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 512 cycles. Reported latency may be longer than just the memory latency. Available PDIST counters: 0", "SampleAfterValue": "101", "UMask": "0x1" }, @@ -168,7 +172,7 @@ "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_64", "MSRIndex": "0x3F6", "MSRValue": "0x40", - "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 64 cycles. Reported latency may be longer than just the memory latency.", + "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 64 cycles. Reported latency may be longer than just the memory latency. Available PDIST counters: 0", "SampleAfterValue": "2003", "UMask": "0x1" }, @@ -180,7 +184,7 @@ "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_8", "MSRIndex": "0x3F6", "MSRValue": "0x8", - "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 8 cycles. Reported latency may be longer than just the memory latency.", + "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 8 cycles. Reported latency may be longer than just the memory latency. Available PDIST counters: 0", "SampleAfterValue": "50021", "UMask": "0x1" }, @@ -190,17 +194,51 @@ "Data_LA": "1", "EventCode": "0xcd", "EventName": "MEM_TRANS_RETIRED.STORE_SAMPLE", - "PublicDescription": "Counts Retired memory accesses with at least 1 store operation. This PEBS event is the precisely-distributed (PDist) trigger covering all stores uops for sampling by the PEBS Store Latency Facility. The facility is described in Intel SDM Volume 3 section 19.9.8", + "PublicDescription": "Counts Retired memory accesses with at least 1 store operation. This PEBS event is the precisely-distributed (PDist) trigger covering all stores uops for sampling by the PEBS Store Latency Facility. The facility is described in Intel SDM Volume 3 section 19.9.8 Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x2" }, { + "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were supplied by DRAM.", + "Counter": "0,1,2,3", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.DEMAND_CODE_RD.DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x73C000004", + "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were supplied by DRAM. Available PDIST counters: 0", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were not supplied by the local socket's L1, L2, or L3 caches.", "Counter": "0,1,2,3", "EventCode": "0x2A,0x2B", "EventName": "OCR.DEMAND_CODE_RD.L3_MISS", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x3FBFC00004", + "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were not supplied by the local socket's L1, L2, or L3 caches. Available PDIST counters: 0", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were supplied by DRAM attached to this socket, unless in Sub NUMA Cluster(SNC) Mode. In SNC Mode counts only those DRAM accesses that are controlled by the close SNC Cluster.", + "Counter": "0,1,2,3", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.DEMAND_CODE_RD.LOCAL_DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x104000004", + "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were supplied by DRAM attached to this socket, unless in Sub NUMA Cluster(SNC) Mode. In SNC Mode counts only those DRAM accesses that are controlled by the close SNC Cluster. Available PDIST counters: 0", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts demand data reads that were supplied by DRAM.", + "Counter": "0,1,2,3", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.DEMAND_DATA_RD.DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x73C000001", + "PublicDescription": "Counts demand data reads that were supplied by DRAM. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -211,6 +249,40 @@ "EventName": "OCR.DEMAND_DATA_RD.L3_MISS", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x3FBFC00001", + "PublicDescription": "Counts demand data reads that were not supplied by the local socket's L1, L2, or L3 caches. Available PDIST counters: 0", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts demand data reads that were supplied by DRAM attached to this socket, unless in Sub NUMA Cluster(SNC) Mode. In SNC Mode counts only those DRAM accesses that are controlled by the close SNC Cluster.", + "Counter": "0,1,2,3", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.DEMAND_DATA_RD.LOCAL_DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x104000001", + "PublicDescription": "Counts demand data reads that were supplied by DRAM attached to this socket, unless in Sub NUMA Cluster(SNC) Mode. In SNC Mode counts only those DRAM accesses that are controlled by the close SNC Cluster. Available PDIST counters: 0", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts demand data reads that were supplied by DRAM attached to another socket.", + "Counter": "0,1,2,3", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.DEMAND_DATA_RD.REMOTE_DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x730000001", + "PublicDescription": "Counts demand data reads that were supplied by DRAM attached to another socket. Available PDIST counters: 0", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts demand reads for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that were supplied by DRAM.", + "Counter": "0,1,2,3", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.DEMAND_RFO.DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x73C000002", + "PublicDescription": "Counts demand reads for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that were supplied by DRAM. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -221,6 +293,29 @@ "EventName": "OCR.DEMAND_RFO.L3_MISS", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x3F3FC00002", + "PublicDescription": "Counts demand reads for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that were not supplied by the local socket's L1, L2, or L3 caches. Available PDIST counters: 0", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts demand reads for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that were supplied by DRAM attached to this socket, unless in Sub NUMA Cluster(SNC) Mode. In SNC Mode counts only those DRAM accesses that are controlled by the close SNC Cluster.", + "Counter": "0,1,2,3", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.DEMAND_RFO.LOCAL_DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x104000002", + "PublicDescription": "Counts demand reads for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that were supplied by DRAM attached to this socket, unless in Sub NUMA Cluster(SNC) Mode. In SNC Mode counts only those DRAM accesses that are controlled by the close SNC Cluster. Available PDIST counters: 0", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by DRAM.", + "Counter": "0,1,2,3", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.READS_TO_CORE.DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x73C004477", + "PublicDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by DRAM. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -231,6 +326,7 @@ "EventName": "OCR.READS_TO_CORE.L3_MISS", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x3F3FC04477", + "PublicDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were not supplied by the local socket's L1, L2, or L3 caches. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -241,6 +337,7 @@ "EventName": "OCR.READS_TO_CORE.L3_MISS_LOCAL", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x3F04C04477", + "PublicDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were not supplied by the local socket's L1, L2, or L3 caches and the cacheline is homed locally. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -251,6 +348,62 @@ "EventName": "OCR.READS_TO_CORE.L3_MISS_LOCAL_SOCKET", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x70CC04477", + "PublicDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that missed the L3 Cache and were supplied by the local socket (DRAM or PMM), whether or not in Sub NUMA Cluster(SNC) Mode. In SNC Mode counts PMM or DRAM accesses that are controlled by the close or distant SNC Cluster. It does not count misses to the L3 which go to Local CXL Type 2 Memory or Local Non DRAM. Available PDIST counters: 0", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by DRAM attached to this socket, unless in Sub NUMA Cluster(SNC) Mode. In SNC Mode counts only those DRAM accesses that are controlled by the close SNC Cluster.", + "Counter": "0,1,2,3", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.READS_TO_CORE.LOCAL_DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x104004477", + "PublicDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by DRAM attached to this socket, unless in Sub NUMA Cluster(SNC) Mode. In SNC Mode counts only those DRAM accesses that are controlled by the close SNC Cluster. Available PDIST counters: 0", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by DRAM attached to this socket, whether or not in Sub NUMA Cluster(SNC) Mode. In SNC Mode counts DRAM accesses that are controlled by the close or distant SNC Cluster.", + "Counter": "0,1,2,3", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.READS_TO_CORE.LOCAL_SOCKET_DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x70C004477", + "PublicDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by DRAM attached to this socket, whether or not in Sub NUMA Cluster(SNC) Mode. In SNC Mode counts DRAM accesses that are controlled by the close or distant SNC Cluster. Available PDIST counters: 0", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by DRAM attached to another socket.", + "Counter": "0,1,2,3", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.READS_TO_CORE.REMOTE_DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x730004477", + "PublicDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by DRAM attached to another socket. Available PDIST counters: 0", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by DRAM or PMM attached to another socket.", + "Counter": "0,1,2,3", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.READS_TO_CORE.REMOTE_MEMORY", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x733004477", + "PublicDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by DRAM or PMM attached to another socket. Available PDIST counters: 0", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts Demand RFOs, ItoM's, PREFECTHW's, Hardware RFO Prefetches to the L1/L2 and Streaming stores that likely resulted in a store to Memory (DRAM or PMM)", + "Counter": "0,1,2,3", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.WRITE_ESTIMATE.MEMORY", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0xFBFF80822", + "PublicDescription": "Counts Demand RFOs, ItoM's, PREFECTHW's, Hardware RFO Prefetches to the L1/L2 and Streaming stores that likely resulted in a store to Memory (DRAM or PMM) Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -259,6 +412,7 @@ "Counter": "0,1,2,3", "EventCode": "0x21", "EventName": "OFFCORE_REQUESTS.L3_MISS_DEMAND_DATA_RD", + "PublicDescription": "Counts demand data read requests that miss the L3 cache. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x10" }, @@ -268,7 +422,7 @@ "CounterMask": "1", "EventCode": "0x20", "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_L3_MISS_DEMAND_DATA_RD", - "PublicDescription": "Cycles with at least 1 Demand Data Read requests who miss L3 cache in the superQ.", + "PublicDescription": "Cycles with at least 1 Demand Data Read requests who miss L3 cache in the superQ. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x10" }, @@ -277,7 +431,7 @@ "Counter": "0,1,2,3", "EventCode": "0x20", "EventName": "OFFCORE_REQUESTS_OUTSTANDING.L3_MISS_DEMAND_DATA_RD", - "PublicDescription": "For every cycle, increments by the number of demand data read requests pending that are known to have missed the L3 cache. Note that this does not capture all elapsed cycles while requests are outstanding - only cycles from when the requests were known by the requesting core to have missed the L3 cache.", + "PublicDescription": "For every cycle, increments by the number of demand data read requests pending that are known to have missed the L3 cache. Note that this does not capture all elapsed cycles while requests are outstanding - only cycles from when the requests were known by the requesting core to have missed the L3 cache. Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x10" }, @@ -286,7 +440,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc9", "EventName": "RTM_RETIRED.ABORTED", - "PublicDescription": "Counts the number of times RTM abort was triggered.", + "PublicDescription": "Counts the number of times RTM abort was triggered. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x4" }, @@ -295,7 +449,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc9", "EventName": "RTM_RETIRED.ABORTED_EVENTS", - "PublicDescription": "Counts the number of times an RTM execution aborted due to none of the previous 3 categories (e.g. interrupt).", + "PublicDescription": "Counts the number of times an RTM execution aborted due to none of the previous 3 categories (e.g. interrupt). Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x80" }, @@ -304,7 +458,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc9", "EventName": "RTM_RETIRED.ABORTED_MEM", - "PublicDescription": "Counts the number of times an RTM execution aborted due to various memory events (e.g. read/write capacity and conflicts).", + "PublicDescription": "Counts the number of times an RTM execution aborted due to various memory events (e.g. read/write capacity and conflicts). Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x8" }, @@ -313,7 +467,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc9", "EventName": "RTM_RETIRED.ABORTED_MEMTYPE", - "PublicDescription": "Counts the number of times an RTM execution aborted due to incompatible memory type.", + "PublicDescription": "Counts the number of times an RTM execution aborted due to incompatible memory type. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x40" }, @@ -322,7 +476,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc9", "EventName": "RTM_RETIRED.ABORTED_UNFRIENDLY", - "PublicDescription": "Counts the number of times an RTM execution aborted due to HLE-unfriendly instructions.", + "PublicDescription": "Counts the number of times an RTM execution aborted due to HLE-unfriendly instructions. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x20" }, @@ -331,7 +485,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc9", "EventName": "RTM_RETIRED.COMMIT", - "PublicDescription": "Counts the number of times RTM commit succeeded.", + "PublicDescription": "Counts the number of times RTM commit succeeded. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x2" }, @@ -340,7 +494,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc9", "EventName": "RTM_RETIRED.START", - "PublicDescription": "Counts the number of times we entered an RTM region. Does not count nested transactions.", + "PublicDescription": "Counts the number of times we entered an RTM region. Does not count nested transactions. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -349,7 +503,7 @@ "Counter": "0,1,2,3", "EventCode": "0x54", "EventName": "TX_MEM.ABORT_CAPACITY_READ", - "PublicDescription": "Speculatively counts the number of Transactional Synchronization Extensions (TSX) aborts due to a data capacity limitation for transactional reads", + "PublicDescription": "Speculatively counts the number of Transactional Synchronization Extensions (TSX) aborts due to a data capacity limitation for transactional reads Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x80" }, @@ -358,7 +512,7 @@ "Counter": "0,1,2,3", "EventCode": "0x54", "EventName": "TX_MEM.ABORT_CAPACITY_WRITE", - "PublicDescription": "Speculatively counts the number of Transactional Synchronization Extensions (TSX) aborts due to a data capacity limitation for transactional writes.", + "PublicDescription": "Speculatively counts the number of Transactional Synchronization Extensions (TSX) aborts due to a data capacity limitation for transactional writes. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x2" }, @@ -367,7 +521,7 @@ "Counter": "0,1,2,3", "EventCode": "0x54", "EventName": "TX_MEM.ABORT_CONFLICT", - "PublicDescription": "Counts the number of times a TSX line had a cache conflict.", + "PublicDescription": "Counts the number of times a TSX line had a cache conflict. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" } diff --git a/tools/perf/pmu-events/arch/x86/graniterapids/other.json b/tools/perf/pmu-events/arch/x86/graniterapids/other.json index 8df37f303273..8b7aa4caec46 100644 --- a/tools/perf/pmu-events/arch/x86/graniterapids/other.json +++ b/tools/perf/pmu-events/arch/x86/graniterapids/other.json @@ -4,7 +4,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc1", "EventName": "ASSISTS.HARDWARE", - "PublicDescription": "Count all other hardware assists or traps that are not necessarily architecturally exposed (through a software handler) beyond FP; SSE-AVX mix and A/D assists who are counted by dedicated sub-events. This includes, but not limited to, assists at EXE or MEM uop writeback like AVX* load/store/gather/scatter (non-FP GSSE-assist ) , assists generated by ROB like PEBS and RTIT, Uncore trap, RAR (Remote Action Request) and CET (Control flow Enforcement Technology) assists. the event also counts for Machine Ordering count.", + "PublicDescription": "Count all other hardware assists or traps that are not necessarily architecturally exposed (through a software handler) beyond FP; SSE-AVX mix and A/D assists who are counted by dedicated sub-events. This includes, but not limited to, assists at EXE or MEM uop writeback like AVX* load/store/gather/scatter (non-FP GSSE-assist ) , assists generated by ROB like PEBS and RTIT, Uncore trap, RAR (Remote Action Request) and CET (Control flow Enforcement Technology) assists. the event also counts for Machine Ordering count. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x4" }, @@ -13,263 +13,28 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc1", "EventName": "ASSISTS.PAGE_FAULT", + "PublicDescription": "ASSISTS.PAGE_FAULT Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x8" }, { - "BriefDescription": "Counts the cycles where the AMX (Advance Matrix Extension) unit is busy performing an operation.", - "Counter": "0,1,2,3,4,5,6,7", - "EventCode": "0xb7", - "EventName": "EXE.AMX_BUSY", - "SampleAfterValue": "2000003", - "UMask": "0x2" - }, - { - "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that have any type of response.", - "Counter": "0,1,2,3", - "EventCode": "0x2A,0x2B", - "EventName": "OCR.DEMAND_CODE_RD.ANY_RESPONSE", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x10004", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were supplied by DRAM.", - "Counter": "0,1,2,3", - "EventCode": "0x2A,0x2B", - "EventName": "OCR.DEMAND_CODE_RD.DRAM", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x73C000004", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were supplied by DRAM attached to this socket, unless in Sub NUMA Cluster(SNC) Mode. In SNC Mode counts only those DRAM accesses that are controlled by the close SNC Cluster.", - "Counter": "0,1,2,3", - "EventCode": "0x2A,0x2B", - "EventName": "OCR.DEMAND_CODE_RD.LOCAL_DRAM", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x104000004", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts demand data reads that have any type of response.", - "Counter": "0,1,2,3", - "EventCode": "0x2A,0x2B", - "EventName": "OCR.DEMAND_DATA_RD.ANY_RESPONSE", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x10001", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts demand data reads that were supplied by DRAM.", - "Counter": "0,1,2,3", - "EventCode": "0x2A,0x2B", - "EventName": "OCR.DEMAND_DATA_RD.DRAM", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x73C000001", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts demand data reads that were supplied by DRAM attached to this socket, unless in Sub NUMA Cluster(SNC) Mode. In SNC Mode counts only those DRAM accesses that are controlled by the close SNC Cluster.", - "Counter": "0,1,2,3", - "EventCode": "0x2A,0x2B", - "EventName": "OCR.DEMAND_DATA_RD.LOCAL_DRAM", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x104000001", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts demand data reads that were supplied by DRAM attached to another socket.", - "Counter": "0,1,2,3", - "EventCode": "0x2A,0x2B", - "EventName": "OCR.DEMAND_DATA_RD.REMOTE_DRAM", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x730000001", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts demand reads for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that have any type of response.", - "Counter": "0,1,2,3", - "EventCode": "0x2A,0x2B", - "EventName": "OCR.DEMAND_RFO.ANY_RESPONSE", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x3F3FFC0002", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts demand reads for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that were supplied by DRAM.", - "Counter": "0,1,2,3", - "EventCode": "0x2A,0x2B", - "EventName": "OCR.DEMAND_RFO.DRAM", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x73C000002", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts demand reads for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that were supplied by DRAM attached to this socket, unless in Sub NUMA Cluster(SNC) Mode. In SNC Mode counts only those DRAM accesses that are controlled by the close SNC Cluster.", - "Counter": "0,1,2,3", - "EventCode": "0x2A,0x2B", - "EventName": "OCR.DEMAND_RFO.LOCAL_DRAM", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x104000002", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts writebacks of modified cachelines and streaming stores that have any type of response.", - "Counter": "0,1,2,3", - "EventCode": "0x2A,0x2B", - "EventName": "OCR.MODIFIED_WRITE.ANY_RESPONSE", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x10808", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that have any type of response.", - "Counter": "0,1,2,3", - "EventCode": "0x2A,0x2B", - "EventName": "OCR.READS_TO_CORE.ANY_RESPONSE", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x3F3FFC4477", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by DRAM.", - "Counter": "0,1,2,3", - "EventCode": "0x2A,0x2B", - "EventName": "OCR.READS_TO_CORE.DRAM", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x73C004477", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by DRAM attached to this socket, unless in Sub NUMA Cluster(SNC) Mode. In SNC Mode counts only those DRAM accesses that are controlled by the close SNC Cluster.", - "Counter": "0,1,2,3", - "EventCode": "0x2A,0x2B", - "EventName": "OCR.READS_TO_CORE.LOCAL_DRAM", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x104004477", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by DRAM attached to this socket, whether or not in Sub NUMA Cluster(SNC) Mode. In SNC Mode counts DRAM accesses that are controlled by the close or distant SNC Cluster.", - "Counter": "0,1,2,3", - "EventCode": "0x2A,0x2B", - "EventName": "OCR.READS_TO_CORE.LOCAL_SOCKET_DRAM", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x70C004477", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were not supplied by the local socket's L1, L2, or L3 caches and were supplied by a remote socket.", - "Counter": "0,1,2,3", - "EventCode": "0x2A,0x2B", - "EventName": "OCR.READS_TO_CORE.REMOTE", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x3F33004477", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by DRAM attached to another socket.", - "Counter": "0,1,2,3", - "EventCode": "0x2A,0x2B", - "EventName": "OCR.READS_TO_CORE.REMOTE_DRAM", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x730004477", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by DRAM or PMM attached to another socket.", - "Counter": "0,1,2,3", - "EventCode": "0x2A,0x2B", - "EventName": "OCR.READS_TO_CORE.REMOTE_MEMORY", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x733004477", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by DRAM on a distant memory controller of this socket when the system is in SNC (sub-NUMA cluster) mode.", - "Counter": "0,1,2,3", - "EventCode": "0x2A,0x2B", - "EventName": "OCR.READS_TO_CORE.SNC_DRAM", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x708004477", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { "BriefDescription": "Counts streaming stores that have any type of response.", "Counter": "0,1,2,3", "EventCode": "0x2A,0x2B", "EventName": "OCR.STREAMING_WR.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x10800", + "PublicDescription": "Counts streaming stores that have any type of response. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, { - "BriefDescription": "Counts Demand RFOs, ItoM's, PREFECTHW's, Hardware RFO Prefetches to the L1/L2 and Streaming stores that likely resulted in a store to Memory (DRAM or PMM)", - "Counter": "0,1,2,3", - "EventCode": "0x2A,0x2B", - "EventName": "OCR.WRITE_ESTIMATE.MEMORY", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0xFBFF80822", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Cycles when Reservation Station (RS) is empty for the thread.", - "Counter": "0,1,2,3,4,5,6,7", - "EventCode": "0xa5", - "EventName": "RS.EMPTY", - "PublicDescription": "Counts cycles during which the reservation station (RS) is empty for this logical processor. This is usually caused when the front-end pipeline runs into starvation periods (e.g. branch mispredictions or i-cache misses)", - "SampleAfterValue": "1000003", - "UMask": "0x7" - }, - { - "BriefDescription": "Counts end of periods where the Reservation Station (RS) was empty.", - "Counter": "0,1,2,3,4,5,6,7", - "CounterMask": "1", - "EdgeDetect": "1", - "EventCode": "0xa5", - "EventName": "RS.EMPTY_COUNT", - "Invert": "1", - "PublicDescription": "Counts end of periods where the Reservation Station (RS) was empty. Could be useful to closely sample on front-end latency issues (see the FRONTEND_RETIRED event of designated precise events)", - "SampleAfterValue": "100003", - "UMask": "0x7" - }, - { - "BriefDescription": "Cycles when RS was empty and a resource allocation stall is asserted", - "Counter": "0,1,2,3,4,5,6,7", - "EventCode": "0xa5", - "EventName": "RS.EMPTY_RESOURCE", - "SampleAfterValue": "1000003", - "UMask": "0x1" - }, - { "BriefDescription": "Cycles the uncore cannot take further requests", "Counter": "0,1,2,3", "CounterMask": "1", "EventCode": "0x2d", "EventName": "XQ.FULL_CYCLES", - "PublicDescription": "number of cycles when the thread is active and the uncore cannot take any further requests (for example prefetches, loads or stores initiated by the Core that miss the L2 cache).", + "PublicDescription": "number of cycles when the thread is active and the uncore cannot take any further requests (for example prefetches, loads or stores initiated by the Core that miss the L2 cache). Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x1" } diff --git a/tools/perf/pmu-events/arch/x86/graniterapids/pipeline.json b/tools/perf/pmu-events/arch/x86/graniterapids/pipeline.json index da6478607984..1edfdad1600d 100644 --- a/tools/perf/pmu-events/arch/x86/graniterapids/pipeline.json +++ b/tools/perf/pmu-events/arch/x86/graniterapids/pipeline.json @@ -5,7 +5,7 @@ "CounterMask": "1", "EventCode": "0xb0", "EventName": "ARITH.DIV_ACTIVE", - "PublicDescription": "Counts cycles when divide unit is busy executing divide or square root operations. Accounts for integer and floating-point operations.", + "PublicDescription": "Counts cycles when divide unit is busy executing divide or square root operations. Accounts for integer and floating-point operations. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x9" }, @@ -15,6 +15,7 @@ "CounterMask": "1", "EventCode": "0xb0", "EventName": "ARITH.IDIV_ACTIVE", + "PublicDescription": "This event counts the cycles the integer divider is busy. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x8" }, @@ -23,7 +24,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc1", "EventName": "ASSISTS.ANY", - "PublicDescription": "Counts the number of occurrences where a microcode assist is invoked by hardware. Examples include AD (page Access Dirty), FP and AVX related assists.", + "PublicDescription": "Counts the number of occurrences where a microcode assist is invoked by hardware. Examples include AD (page Access Dirty), FP and AVX related assists. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1b" }, @@ -32,7 +33,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.ALL_BRANCHES", - "PublicDescription": "Counts all branch instructions retired.", + "PublicDescription": "Counts all branch instructions retired. Available PDIST counters: 0", "SampleAfterValue": "400009" }, { @@ -40,7 +41,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.COND", - "PublicDescription": "Counts conditional branch instructions retired.", + "PublicDescription": "Counts conditional branch instructions retired. Available PDIST counters: 0", "SampleAfterValue": "400009", "UMask": "0x11" }, @@ -49,7 +50,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.COND_NTAKEN", - "PublicDescription": "Counts not taken branch instructions retired.", + "PublicDescription": "Counts not taken branch instructions retired. Available PDIST counters: 0", "SampleAfterValue": "400009", "UMask": "0x10" }, @@ -58,7 +59,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.COND_TAKEN", - "PublicDescription": "Counts taken conditional branch instructions retired.", + "PublicDescription": "Counts taken conditional branch instructions retired. Available PDIST counters: 0", "SampleAfterValue": "400009", "UMask": "0x1" }, @@ -67,7 +68,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.FAR_BRANCH", - "PublicDescription": "Counts far branch instructions retired.", + "PublicDescription": "Counts far branch instructions retired. Available PDIST counters: 0", "SampleAfterValue": "100007", "UMask": "0x40" }, @@ -76,7 +77,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.INDIRECT", - "PublicDescription": "Counts near indirect branch instructions retired excluding returns. TSX abort is an indirect branch.", + "PublicDescription": "Counts near indirect branch instructions retired excluding returns. TSX abort is an indirect branch. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x80" }, @@ -85,7 +86,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.NEAR_CALL", - "PublicDescription": "Counts both direct and indirect near call instructions retired.", + "PublicDescription": "Counts both direct and indirect near call instructions retired. Available PDIST counters: 0", "SampleAfterValue": "100007", "UMask": "0x2" }, @@ -94,7 +95,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.NEAR_RETURN", - "PublicDescription": "Counts return instructions retired.", + "PublicDescription": "Counts return instructions retired. Available PDIST counters: 0", "SampleAfterValue": "100007", "UMask": "0x8" }, @@ -103,7 +104,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.NEAR_TAKEN", - "PublicDescription": "Counts taken branch instructions retired.", + "PublicDescription": "Counts taken branch instructions retired. Available PDIST counters: 0", "SampleAfterValue": "400009", "UMask": "0x20" }, @@ -112,7 +113,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.ALL_BRANCHES", - "PublicDescription": "Counts all the retired branch instructions that were mispredicted by the processor. A branch misprediction occurs when the processor incorrectly predicts the destination of the branch. When the misprediction is discovered at execution, all the instructions executed in the wrong (speculative) path must be discarded, and the processor must start fetching from the correct path.", + "PublicDescription": "Counts all the retired branch instructions that were mispredicted by the processor. A branch misprediction occurs when the processor incorrectly predicts the destination of the branch. When the misprediction is discovered at execution, all the instructions executed in the wrong (speculative) path must be discarded, and the processor must start fetching from the correct path. Available PDIST counters: 0", "SampleAfterValue": "400009" }, { @@ -120,6 +121,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.ALL_BRANCHES_COST", + "PublicDescription": "All mispredicted branch instructions retired. This precise event may be used to get the misprediction cost via the Retire_Latency field of PEBS. It fires on the instruction that immediately follows the mispredicted branch. Available PDIST counters: 0", "SampleAfterValue": "400009", "UMask": "0x44" }, @@ -128,7 +130,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.COND", - "PublicDescription": "Counts mispredicted conditional branch instructions retired.", + "PublicDescription": "Counts mispredicted conditional branch instructions retired. Available PDIST counters: 0", "SampleAfterValue": "400009", "UMask": "0x11" }, @@ -137,6 +139,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.COND_COST", + "PublicDescription": "Mispredicted conditional branch instructions retired. This precise event may be used to get the misprediction cost via the Retire_Latency field of PEBS. It fires on the instruction that immediately follows the mispredicted branch. Available PDIST counters: 0", "SampleAfterValue": "400009", "UMask": "0x51" }, @@ -145,7 +148,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.COND_NTAKEN", - "PublicDescription": "Counts the number of conditional branch instructions retired that were mispredicted and the branch direction was not taken.", + "PublicDescription": "Counts the number of conditional branch instructions retired that were mispredicted and the branch direction was not taken. Available PDIST counters: 0", "SampleAfterValue": "400009", "UMask": "0x10" }, @@ -154,6 +157,10 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.COND_NTAKEN_COST", + "PublicDescription": "Mispredicted non-taken conditional branch instructions retired. This precise event may be used to get the misprediction cost via the Retire_Latency field of PEBS. It fires on the instruction that immediately follows the mispredicted branch. Available PDIST counters: 0", + "RetirementLatencyMax": 888, + "RetirementLatencyMean": 6.11, + "RetirementLatencyMin": 0, "SampleAfterValue": "400009", "UMask": "0x50" }, @@ -162,7 +169,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.COND_TAKEN", - "PublicDescription": "Counts taken conditional mispredicted branch instructions retired.", + "PublicDescription": "Counts taken conditional mispredicted branch instructions retired. Available PDIST counters: 0", "SampleAfterValue": "400009", "UMask": "0x1" }, @@ -171,6 +178,10 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.COND_TAKEN_COST", + "PublicDescription": "Mispredicted taken conditional branch instructions retired. This precise event may be used to get the misprediction cost via the Retire_Latency field of PEBS. It fires on the instruction that immediately follows the mispredicted branch. Available PDIST counters: 0", + "RetirementLatencyMax": 2750, + "RetirementLatencyMean": 5.09, + "RetirementLatencyMin": 0, "SampleAfterValue": "400009", "UMask": "0x41" }, @@ -179,7 +190,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.INDIRECT", - "PublicDescription": "Counts miss-predicted near indirect branch instructions retired excluding returns. TSX abort is an indirect branch.", + "PublicDescription": "Counts miss-predicted near indirect branch instructions retired excluding returns. TSX abort is an indirect branch. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x80" }, @@ -188,7 +199,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.INDIRECT_CALL", - "PublicDescription": "Counts retired mispredicted indirect (near taken) CALL instructions, including both register and memory indirect.", + "PublicDescription": "Counts retired mispredicted indirect (near taken) CALL instructions, including both register and memory indirect. Available PDIST counters: 0", "SampleAfterValue": "400009", "UMask": "0x2" }, @@ -197,6 +208,10 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.INDIRECT_CALL_COST", + "PublicDescription": "Mispredicted indirect CALL retired. This precise event may be used to get the misprediction cost via the Retire_Latency field of PEBS. It fires on the instruction that immediately follows the mispredicted branch. Available PDIST counters: 0", + "RetirementLatencyMax": 703, + "RetirementLatencyMean": 15.56, + "RetirementLatencyMin": 0, "SampleAfterValue": "400009", "UMask": "0x42" }, @@ -205,6 +220,10 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.INDIRECT_COST", + "PublicDescription": "Mispredicted near indirect branch instructions retired (excluding returns). This precise event may be used to get the misprediction cost via the Retire_Latency field of PEBS. It fires on the instruction that immediately follows the mispredicted branch. Available PDIST counters: 0", + "RetirementLatencyMax": 1562, + "RetirementLatencyMean": 11.07, + "RetirementLatencyMin": 0, "SampleAfterValue": "100003", "UMask": "0xc0" }, @@ -213,7 +232,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.NEAR_TAKEN", - "PublicDescription": "Counts number of near branch instructions retired that were mispredicted and taken.", + "PublicDescription": "Counts number of near branch instructions retired that were mispredicted and taken. Available PDIST counters: 0", "SampleAfterValue": "400009", "UMask": "0x20" }, @@ -222,6 +241,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.NEAR_TAKEN_COST", + "PublicDescription": "Mispredicted taken near branch instructions retired. This precise event may be used to get the misprediction cost via the Retire_Latency field of PEBS. It fires on the instruction that immediately follows the mispredicted branch. Available PDIST counters: 0", "SampleAfterValue": "400009", "UMask": "0x60" }, @@ -230,7 +250,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.RET", - "PublicDescription": "This is a non-precise version (that is, does not use PEBS) of the event that counts mispredicted return instructions retired.", + "PublicDescription": "This is a non-precise version (that is, does not use PEBS) of the event that counts mispredicted return instructions retired. Available PDIST counters: 0", "SampleAfterValue": "100007", "UMask": "0x8" }, @@ -239,6 +259,10 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.RET_COST", + "PublicDescription": "Mispredicted ret instructions retired. This precise event may be used to get the misprediction cost via the Retire_Latency field of PEBS. It fires on the instruction that immediately follows the mispredicted branch. Available PDIST counters: 0", + "RetirementLatencyMax": 1082, + "RetirementLatencyMean": 32.37, + "RetirementLatencyMin": 9, "SampleAfterValue": "100007", "UMask": "0x48" }, @@ -247,7 +271,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xec", "EventName": "CPU_CLK_UNHALTED.C01", - "PublicDescription": "Counts core clocks when the thread is in the C0.1 light-weight slower wakeup time but more power saving optimized state. This state can be entered via the TPAUSE or UMWAIT instructions.", + "PublicDescription": "Counts core clocks when the thread is in the C0.1 light-weight slower wakeup time but more power saving optimized state. This state can be entered via the TPAUSE or UMWAIT instructions. Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x10" }, @@ -256,7 +280,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xec", "EventName": "CPU_CLK_UNHALTED.C02", - "PublicDescription": "Counts core clocks when the thread is in the C0.2 light-weight faster wakeup time but less power saving optimized state. This state can be entered via the TPAUSE or UMWAIT instructions.", + "PublicDescription": "Counts core clocks when the thread is in the C0.2 light-weight faster wakeup time but less power saving optimized state. This state can be entered via the TPAUSE or UMWAIT instructions. Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x20" }, @@ -265,7 +289,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xec", "EventName": "CPU_CLK_UNHALTED.C0_WAIT", - "PublicDescription": "Counts core clocks when the thread is in the C0.1 or C0.2 power saving optimized states (TPAUSE or UMWAIT instructions) or running the PAUSE instruction.", + "PublicDescription": "Counts core clocks when the thread is in the C0.1 or C0.2 power saving optimized states (TPAUSE or UMWAIT instructions) or running the PAUSE instruction. Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x70" }, @@ -274,7 +298,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xec", "EventName": "CPU_CLK_UNHALTED.DISTRIBUTED", - "PublicDescription": "This event distributes cycle counts between active hyperthreads, i.e., those in C0. A hyperthread becomes inactive when it executes the HLT or MWAIT instructions. If all other hyperthreads are inactive (or disabled or do not exist), all counts are attributed to this hyperthread. To obtain the full count when the Core is active, sum the counts from each hyperthread.", + "PublicDescription": "This event distributes cycle counts between active hyperthreads, i.e., those in C0. A hyperthread becomes inactive when it executes the HLT or MWAIT instructions. If all other hyperthreads are inactive (or disabled or do not exist), all counts are attributed to this hyperthread. To obtain the full count when the Core is active, sum the counts from each hyperthread. Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x2" }, @@ -283,7 +307,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0x3c", "EventName": "CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE", - "PublicDescription": "Counts Core crystal clock cycles when current thread is unhalted and the other thread is halted.", + "PublicDescription": "Counts Core crystal clock cycles when current thread is unhalted and the other thread is halted. Available PDIST counters: 0", "SampleAfterValue": "25003", "UMask": "0x2" }, @@ -292,6 +316,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xec", "EventName": "CPU_CLK_UNHALTED.PAUSE", + "PublicDescription": "CPU_CLK_UNHALTED.PAUSE Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x40" }, @@ -302,6 +327,7 @@ "EdgeDetect": "1", "EventCode": "0xec", "EventName": "CPU_CLK_UNHALTED.PAUSE_INST", + "PublicDescription": "CPU_CLK_UNHALTED.PAUSE_INST Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x40" }, @@ -310,7 +336,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0x3c", "EventName": "CPU_CLK_UNHALTED.REF_DISTRIBUTED", - "PublicDescription": "This event distributes Core crystal clock cycle counts between active hyperthreads, i.e., those in C0 sleep-state. A hyperthread becomes inactive when it executes the HLT or MWAIT instructions. If one thread is active in a core, all counts are attributed to this hyperthread. To obtain the full count when the Core is active, sum the counts from each hyperthread.", + "PublicDescription": "This event distributes Core crystal clock cycle counts between active hyperthreads, i.e., those in C0 sleep-state. A hyperthread becomes inactive when it executes the HLT or MWAIT instructions. If one thread is active in a core, all counts are attributed to this hyperthread. To obtain the full count when the Core is active, sum the counts from each hyperthread. Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x8" }, @@ -318,7 +344,7 @@ "BriefDescription": "Reference cycles when the core is not in halt state.", "Counter": "Fixed counter 2", "EventName": "CPU_CLK_UNHALTED.REF_TSC", - "PublicDescription": "Counts the number of reference cycles when the core is not in a halt state. The core enters the halt state when it is running the HLT instruction or the MWAIT instruction. This event is not affected by core frequency changes (for example, P states, TM2 transitions) but has the same incrementing frequency as the time stamp counter. This event can approximate elapsed time while the core was not in a halt state. It is counted on a dedicated fixed counter, leaving the eight programmable counters available for other events. Note: On all current platforms this event stops counting during 'throttling (TM)' states duty off periods the processor is 'halted'. The counter update is done at a lower clock rate then the core clock the overflow status bit for this counter may appear 'sticky'. After the counter has overflowed and software clears the overflow status bit and resets the counter to less than MAX. The reset value to the counter is not clocked immediately so the overflow status bit will flip 'high (1)' and generate another PMI (if enabled) after which the reset value gets clocked into the counter. Therefore, software will get the interrupt, read the overflow status bit '1 for bit 34 while the counter value is less than MAX. Software should ignore this case.", + "PublicDescription": "Counts the number of reference cycles when the core is not in a halt state. The core enters the halt state when it is running the HLT instruction or the MWAIT instruction. This event is not affected by core frequency changes (for example, P states, TM2 transitions) but has the same incrementing frequency as the time stamp counter. This event can approximate elapsed time while the core was not in a halt state. It is counted on a dedicated fixed counter, leaving the eight programmable counters available for other events. Note: On all current platforms this event stops counting during 'throttling (TM)' states duty off periods the processor is 'halted'. The counter update is done at a lower clock rate then the core clock the overflow status bit for this counter may appear 'sticky'. After the counter has overflowed and software clears the overflow status bit and resets the counter to less than MAX. The reset value to the counter is not clocked immediately so the overflow status bit will flip 'high (1)' and generate another PMI (if enabled) after which the reset value gets clocked into the counter. Therefore, software will get the interrupt, read the overflow status bit '1 for bit 34 while the counter value is less than MAX. Software should ignore this case. Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x3" }, @@ -327,7 +353,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0x3c", "EventName": "CPU_CLK_UNHALTED.REF_TSC_P", - "PublicDescription": "Counts the number of reference cycles when the core is not in a halt state. The core enters the halt state when it is running the HLT instruction or the MWAIT instruction. This event is not affected by core frequency changes (for example, P states, TM2 transitions) but has the same incrementing frequency as the time stamp counter. This event can approximate elapsed time while the core was not in a halt state. It is counted on a dedicated fixed counter, leaving the four (eight when Hyperthreading is disabled) programmable counters available for other events. Note: On all current platforms this event stops counting during 'throttling (TM)' states duty off periods the processor is 'halted'. The counter update is done at a lower clock rate then the core clock the overflow status bit for this counter may appear 'sticky'. After the counter has overflowed and software clears the overflow status bit and resets the counter to less than MAX. The reset value to the counter is not clocked immediately so the overflow status bit will flip 'high (1)' and generate another PMI (if enabled) after which the reset value gets clocked into the counter. Therefore, software will get the interrupt, read the overflow status bit '1 for bit 34 while the counter value is less than MAX. Software should ignore this case.", + "PublicDescription": "Counts the number of reference cycles when the core is not in a halt state. The core enters the halt state when it is running the HLT instruction or the MWAIT instruction. This event is not affected by core frequency changes (for example, P states, TM2 transitions) but has the same incrementing frequency as the time stamp counter. This event can approximate elapsed time while the core was not in a halt state. It is counted on a dedicated fixed counter, leaving the four (eight when Hyperthreading is disabled) programmable counters available for other events. Note: On all current platforms this event stops counting during 'throttling (TM)' states duty off periods the processor is 'halted'. The counter update is done at a lower clock rate then the core clock the overflow status bit for this counter may appear 'sticky'. After the counter has overflowed and software clears the overflow status bit and resets the counter to less than MAX. The reset value to the counter is not clocked immediately so the overflow status bit will flip 'high (1)' and generate another PMI (if enabled) after which the reset value gets clocked into the counter. Therefore, software will get the interrupt, read the overflow status bit '1 for bit 34 while the counter value is less than MAX. Software should ignore this case. Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x1" }, @@ -335,7 +361,7 @@ "BriefDescription": "Core cycles when the thread is not in halt state", "Counter": "Fixed counter 1", "EventName": "CPU_CLK_UNHALTED.THREAD", - "PublicDescription": "Counts the number of core cycles while the thread is not in a halt state. The thread enters the halt state when it is running the HLT instruction. This event is a component in many key event ratios. The core frequency may change from time to time due to transitions associated with Enhanced Intel SpeedStep Technology or TM2. For this reason this event may have a changing ratio with regards to time. When the core frequency is constant, this event can approximate elapsed time while the core was not in the halt state. It is counted on a dedicated fixed counter, leaving the eight programmable counters available for other events.", + "PublicDescription": "Counts the number of core cycles while the thread is not in a halt state. The thread enters the halt state when it is running the HLT instruction. This event is a component in many key event ratios. The core frequency may change from time to time due to transitions associated with Enhanced Intel SpeedStep Technology or TM2. For this reason this event may have a changing ratio with regards to time. When the core frequency is constant, this event can approximate elapsed time while the core was not in the halt state. It is counted on a dedicated fixed counter, leaving the eight programmable counters available for other events. Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x2" }, @@ -344,7 +370,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0x3c", "EventName": "CPU_CLK_UNHALTED.THREAD_P", - "PublicDescription": "This is an architectural event that counts the number of thread cycles while the thread is not in a halt state. The thread enters the halt state when it is running the HLT instruction. The core frequency may change from time to time due to power or thermal throttling. For this reason, this event may have a changing ratio with regards to wall clock time.", + "PublicDescription": "This is an architectural event that counts the number of thread cycles while the thread is not in a halt state. The thread enters the halt state when it is running the HLT instruction. The core frequency may change from time to time due to power or thermal throttling. For this reason, this event may have a changing ratio with regards to wall clock time. Available PDIST counters: 0", "SampleAfterValue": "2000003" }, { @@ -353,6 +379,7 @@ "CounterMask": "8", "EventCode": "0xa3", "EventName": "CYCLE_ACTIVITY.CYCLES_L1D_MISS", + "PublicDescription": "Cycles while L1 cache miss demand load is outstanding. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x8" }, @@ -362,6 +389,7 @@ "CounterMask": "1", "EventCode": "0xa3", "EventName": "CYCLE_ACTIVITY.CYCLES_L2_MISS", + "PublicDescription": "Cycles while L2 cache miss demand load is outstanding. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x1" }, @@ -371,6 +399,7 @@ "CounterMask": "16", "EventCode": "0xa3", "EventName": "CYCLE_ACTIVITY.CYCLES_MEM_ANY", + "PublicDescription": "Cycles while memory subsystem has an outstanding load. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x10" }, @@ -380,6 +409,7 @@ "CounterMask": "12", "EventCode": "0xa3", "EventName": "CYCLE_ACTIVITY.STALLS_L1D_MISS", + "PublicDescription": "Execution stalls while L1 cache miss demand load is outstanding. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0xc" }, @@ -389,6 +419,7 @@ "CounterMask": "5", "EventCode": "0xa3", "EventName": "CYCLE_ACTIVITY.STALLS_L2_MISS", + "PublicDescription": "Execution stalls while L2 cache miss demand load is outstanding. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x5" }, @@ -398,15 +429,25 @@ "CounterMask": "4", "EventCode": "0xa3", "EventName": "CYCLE_ACTIVITY.STALLS_TOTAL", + "PublicDescription": "Total execution stalls. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x4" }, { + "BriefDescription": "Counts the cycles where the AMX (Advance Matrix Extension) unit is busy performing an operation.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xb7", + "EventName": "EXE.AMX_BUSY", + "PublicDescription": "Counts the cycles where the AMX (Advance Matrix Extension) unit is busy performing an operation. Available PDIST counters: 0", + "SampleAfterValue": "2000003", + "UMask": "0x2" + }, + { "BriefDescription": "Cycles total of 1 uop is executed on all ports and Reservation Station was not empty.", "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xa6", "EventName": "EXE_ACTIVITY.1_PORTS_UTIL", - "PublicDescription": "Counts cycles during which a total of 1 uop was executed on all ports and Reservation Station (RS) was not empty.", + "PublicDescription": "Counts cycles during which a total of 1 uop was executed on all ports and Reservation Station (RS) was not empty. Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x2" }, @@ -415,6 +456,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xa6", "EventName": "EXE_ACTIVITY.2_3_PORTS_UTIL", + "PublicDescription": "Cycles total of 2 or 3 uops are executed on all ports and Reservation Station (RS) was not empty. Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0xc" }, @@ -423,7 +465,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xa6", "EventName": "EXE_ACTIVITY.2_PORTS_UTIL", - "PublicDescription": "Counts cycles during which a total of 2 uops were executed on all ports and Reservation Station (RS) was not empty.", + "PublicDescription": "Counts cycles during which a total of 2 uops were executed on all ports and Reservation Station (RS) was not empty. Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x4" }, @@ -432,7 +474,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xa6", "EventName": "EXE_ACTIVITY.3_PORTS_UTIL", - "PublicDescription": "Cycles total of 3 uops are executed on all ports and Reservation Station (RS) was not empty.", + "PublicDescription": "Cycles total of 3 uops are executed on all ports and Reservation Station (RS) was not empty. Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x8" }, @@ -441,7 +483,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xa6", "EventName": "EXE_ACTIVITY.4_PORTS_UTIL", - "PublicDescription": "Cycles total of 4 uops are executed on all ports and Reservation Station (RS) was not empty.", + "PublicDescription": "Cycles total of 4 uops are executed on all ports and Reservation Station (RS) was not empty. Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x10" }, @@ -451,6 +493,7 @@ "CounterMask": "5", "EventCode": "0xa6", "EventName": "EXE_ACTIVITY.BOUND_ON_LOADS", + "PublicDescription": "Execution stalls while memory subsystem has an outstanding load. Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x21" }, @@ -460,7 +503,7 @@ "CounterMask": "2", "EventCode": "0xa6", "EventName": "EXE_ACTIVITY.BOUND_ON_STORES", - "PublicDescription": "Counts cycles where the Store Buffer was full and no loads caused an execution stall.", + "PublicDescription": "Counts cycles where the Store Buffer was full and no loads caused an execution stall. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x40" }, @@ -469,7 +512,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xa6", "EventName": "EXE_ACTIVITY.EXE_BOUND_0_PORTS", - "PublicDescription": "Number of cycles total of 0 uops executed on all ports, Reservation Station (RS) was not empty, the Store Buffer (SB) was not full and there was no outstanding load.", + "PublicDescription": "Number of cycles total of 0 uops executed on all ports, Reservation Station (RS) was not empty, the Store Buffer (SB) was not full and there was no outstanding load. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x80" }, @@ -478,7 +521,7 @@ "Counter": "0,1,2,3", "EventCode": "0x75", "EventName": "INST_DECODED.DECODERS", - "PublicDescription": "Number of decoders utilized in a cycle when the MITE (legacy decode pipeline) fetches instructions.", + "PublicDescription": "Number of decoders utilized in a cycle when the MITE (legacy decode pipeline) fetches instructions. Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x1" }, @@ -486,7 +529,7 @@ "BriefDescription": "Number of instructions retired. Fixed Counter - architectural event", "Counter": "Fixed counter 0", "EventName": "INST_RETIRED.ANY", - "PublicDescription": "Counts the number of X86 instructions retired - an Architectural PerfMon event. Counting continues during hardware interrupts, traps, and inside interrupt handlers. Notes: INST_RETIRED.ANY is counted by a designated fixed counter freeing up programmable counters to count other events. INST_RETIRED.ANY_P is counted by a programmable counter.", + "PublicDescription": "Counts the number of X86 instructions retired - an Architectural PerfMon event. Counting continues during hardware interrupts, traps, and inside interrupt handlers. Notes: INST_RETIRED.ANY is counted by a designated fixed counter freeing up programmable counters to count other events. INST_RETIRED.ANY_P is counted by a programmable counter. Available PDIST counters: 32", "SampleAfterValue": "2000003", "UMask": "0x1" }, @@ -503,6 +546,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc0", "EventName": "INST_RETIRED.MACRO_FUSED", + "PublicDescription": "INST_RETIRED.MACRO_FUSED Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x10" }, @@ -511,7 +555,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc0", "EventName": "INST_RETIRED.NOP", - "PublicDescription": "Counts all retired NOP or ENDBR32/64 or PREFETCHIT0/1 instructions", + "PublicDescription": "Counts all retired NOP or ENDBR32/64 or PREFETCHIT0/1 instructions Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x2" }, @@ -519,7 +563,7 @@ "BriefDescription": "Precise instruction retired with PEBS precise-distribution", "Counter": "Fixed counter 0", "EventName": "INST_RETIRED.PREC_DIST", - "PublicDescription": "A version of INST_RETIRED that allows for a precise distribution of samples across instructions retired. It utilizes the Precise Distribution of Instructions Retired (PDIR++) feature to fix bias in how retired instructions get sampled. Use on Fixed Counter 0.", + "PublicDescription": "A version of INST_RETIRED that allows for a precise distribution of samples across instructions retired. It utilizes the Precise Distribution of Instructions Retired (PDIR++) feature to fix bias in how retired instructions get sampled. Use on Fixed Counter 0. Available PDIST counters: 32", "SampleAfterValue": "2000003", "UMask": "0x1" }, @@ -528,7 +572,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc0", "EventName": "INST_RETIRED.REP_ITERATION", - "PublicDescription": "Number of iterations of Repeat (REP) string retired instructions such as MOVS, CMPS, and SCAS. Each has a byte, word, and doubleword version and string instructions can be repeated using a repetition prefix, REP, that allows their architectural execution to be repeated a number of times as specified by the RCX register. Note the number of iterations is implementation-dependent.", + "PublicDescription": "Number of iterations of Repeat (REP) string retired instructions such as MOVS, CMPS, and SCAS. Each has a byte, word, and doubleword version and string instructions can be repeated using a repetition prefix, REP, that allows their architectural execution to be repeated a number of times as specified by the RCX register. Note the number of iterations is implementation-dependent. Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x8" }, @@ -539,7 +583,7 @@ "EdgeDetect": "1", "EventCode": "0xad", "EventName": "INT_MISC.CLEARS_COUNT", - "PublicDescription": "Counts the number of speculative clears due to any type of branch misprediction or machine clears", + "PublicDescription": "Counts the number of speculative clears due to any type of branch misprediction or machine clears Available PDIST counters: 0", "SampleAfterValue": "500009", "UMask": "0x1" }, @@ -548,7 +592,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xad", "EventName": "INT_MISC.CLEAR_RESTEER_CYCLES", - "PublicDescription": "Cycles after recovery from a branch misprediction or machine clear till the first uop is issued from the resteered path.", + "PublicDescription": "Cycles after recovery from a branch misprediction or machine clear till the first uop is issued from the resteered path. Available PDIST counters: 0", "SampleAfterValue": "500009", "UMask": "0x80" }, @@ -557,6 +601,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xad", "EventName": "INT_MISC.MBA_STALLS", + "PublicDescription": "INT_MISC.MBA_STALLS Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x20" }, @@ -565,7 +610,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xad", "EventName": "INT_MISC.RECOVERY_CYCLES", - "PublicDescription": "Counts core cycles when the Resource allocator was stalled due to recovery from an earlier branch misprediction or machine clear event.", + "PublicDescription": "Counts core cycles when the Resource allocator was stalled due to recovery from an earlier branch misprediction or machine clear event. Available PDIST counters: 0", "SampleAfterValue": "500009", "UMask": "0x1" }, @@ -576,6 +621,7 @@ "EventName": "INT_MISC.UNKNOWN_BRANCH_CYCLES", "MSRIndex": "0x3F7", "MSRValue": "0x7", + "PublicDescription": "Bubble cycles of BAClear (Unknown Branch). Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x40" }, @@ -584,7 +630,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xad", "EventName": "INT_MISC.UOP_DROPPING", - "PublicDescription": "Estimated number of Top-down Microarchitecture Analysis slots that got dropped due to non front-end reasons", + "PublicDescription": "Estimated number of Top-down Microarchitecture Analysis slots that got dropped due to non front-end reasons Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x10" }, @@ -593,6 +639,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xe7", "EventName": "INT_VEC_RETIRED.128BIT", + "PublicDescription": "INT_VEC_RETIRED.128BIT Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x13" }, @@ -601,6 +648,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xe7", "EventName": "INT_VEC_RETIRED.256BIT", + "PublicDescription": "INT_VEC_RETIRED.256BIT Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0xac" }, @@ -609,7 +657,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xe7", "EventName": "INT_VEC_RETIRED.ADD_128", - "PublicDescription": "Number of retired integer ADD/SUB (regular or horizontal), SAD 128-bit vector instructions.", + "PublicDescription": "Number of retired integer ADD/SUB (regular or horizontal), SAD 128-bit vector instructions. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x3" }, @@ -618,7 +666,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xe7", "EventName": "INT_VEC_RETIRED.ADD_256", - "PublicDescription": "Number of retired integer ADD/SUB (regular or horizontal), SAD 256-bit vector instructions.", + "PublicDescription": "Number of retired integer ADD/SUB (regular or horizontal), SAD 256-bit vector instructions. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0xc" }, @@ -627,6 +675,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xe7", "EventName": "INT_VEC_RETIRED.MUL_256", + "PublicDescription": "INT_VEC_RETIRED.MUL_256 Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x80" }, @@ -635,6 +684,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xe7", "EventName": "INT_VEC_RETIRED.SHUFFLES", + "PublicDescription": "INT_VEC_RETIRED.SHUFFLES Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x40" }, @@ -643,6 +693,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xe7", "EventName": "INT_VEC_RETIRED.VNNI_128", + "PublicDescription": "INT_VEC_RETIRED.VNNI_128 Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x10" }, @@ -651,6 +702,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xe7", "EventName": "INT_VEC_RETIRED.VNNI_256", + "PublicDescription": "INT_VEC_RETIRED.VNNI_256 Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x20" }, @@ -659,7 +711,7 @@ "Counter": "0,1,2,3", "EventCode": "0x03", "EventName": "LD_BLOCKS.ADDRESS_ALIAS", - "PublicDescription": "Counts the number of times a load got blocked due to false dependencies in MOB due to partial compare on address.", + "PublicDescription": "Counts the number of times a load got blocked due to false dependencies in MOB due to partial compare on address. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x4" }, @@ -668,7 +720,7 @@ "Counter": "0,1,2,3", "EventCode": "0x03", "EventName": "LD_BLOCKS.NO_SR", - "PublicDescription": "Counts the number of times that split load operations are temporarily blocked because all resources for handling the split accesses are in use.", + "PublicDescription": "Counts the number of times that split load operations are temporarily blocked because all resources for handling the split accesses are in use. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x88" }, @@ -677,7 +729,7 @@ "Counter": "0,1,2,3", "EventCode": "0x03", "EventName": "LD_BLOCKS.STORE_FORWARD", - "PublicDescription": "Counts the number of times where store forwarding was prevented for a load operation. The most common case is a load blocked due to the address of memory access (partially) overlapping with a preceding uncompleted store. Note: See the table of not supported store forwards in the Optimization Guide.", + "PublicDescription": "Counts the number of times where store forwarding was prevented for a load operation. The most common case is a load blocked due to the address of memory access (partially) overlapping with a preceding uncompleted store. Note: See the table of not supported store forwards in the Optimization Guide. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x82" }, @@ -686,7 +738,7 @@ "Counter": "0,1,2,3", "EventCode": "0x4c", "EventName": "LOAD_HIT_PREFETCH.SWPF", - "PublicDescription": "Counts all not software-prefetch load dispatches that hit the fill buffer (FB) allocated for the software prefetch. It can also be incremented by some lock instructions. So it should only be used with profiling so that the locks can be excluded by ASM (Assembly File) inspection of the nearby instructions.", + "PublicDescription": "Counts all not software-prefetch load dispatches that hit the fill buffer (FB) allocated for the software prefetch. It can also be incremented by some lock instructions. So it should only be used with profiling so that the locks can be excluded by ASM (Assembly File) inspection of the nearby instructions. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -696,7 +748,7 @@ "CounterMask": "1", "EventCode": "0xa8", "EventName": "LSD.CYCLES_ACTIVE", - "PublicDescription": "Counts the cycles when at least one uop is delivered by the LSD (Loop-stream detector).", + "PublicDescription": "Counts the cycles when at least one uop is delivered by the LSD (Loop-stream detector). Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x1" }, @@ -706,7 +758,7 @@ "CounterMask": "6", "EventCode": "0xa8", "EventName": "LSD.CYCLES_OK", - "PublicDescription": "Counts the cycles when optimal number of uops is delivered by the LSD (Loop-stream detector).", + "PublicDescription": "Counts the cycles when optimal number of uops is delivered by the LSD (Loop-stream detector). Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x1" }, @@ -715,7 +767,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xa8", "EventName": "LSD.UOPS", - "PublicDescription": "Counts the number of uops delivered to the back-end by the LSD(Loop Stream Detector).", + "PublicDescription": "Counts the number of uops delivered to the back-end by the LSD(Loop Stream Detector). Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x1" }, @@ -726,7 +778,7 @@ "EdgeDetect": "1", "EventCode": "0xc3", "EventName": "MACHINE_CLEARS.COUNT", - "PublicDescription": "Counts the number of machine clears (nukes) of any type.", + "PublicDescription": "Counts the number of machine clears (nukes) of any type. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -735,7 +787,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc3", "EventName": "MACHINE_CLEARS.SMC", - "PublicDescription": "Counts self-modifying code (SMC) detected, which causes a machine clear.", + "PublicDescription": "Counts self-modifying code (SMC) detected, which causes a machine clear. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x4" }, @@ -744,7 +796,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xe0", "EventName": "MISC2_RETIRED.LFENCE", - "PublicDescription": "number of LFENCE retired instructions", + "PublicDescription": "number of LFENCE retired instructions Available PDIST counters: 0", "SampleAfterValue": "400009", "UMask": "0x20" }, @@ -753,7 +805,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xcc", "EventName": "MISC_RETIRED.LBR_INSERTS", - "PublicDescription": "Increments when an entry is added to the Last Branch Record (LBR) array (or removed from the array in case of RETURNs in call stack mode). The event requires LBR enable via IA32_DEBUGCTL MSR and branch type selection via MSR_LBR_SELECT.", + "PublicDescription": "Increments when an entry is added to the Last Branch Record (LBR) array (or removed from the array in case of RETURNs in call stack mode). The event requires LBR enable via IA32_DEBUGCTL MSR and branch type selection via MSR_LBR_SELECT. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x20" }, @@ -762,7 +814,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xa2", "EventName": "RESOURCE_STALLS.SB", - "PublicDescription": "Counts allocation stall cycles caused by the store buffer (SB) being full. This counts cycles that the pipeline back-end blocked uop delivery from the front-end.", + "PublicDescription": "Counts allocation stall cycles caused by the store buffer (SB) being full. This counts cycles that the pipeline back-end blocked uop delivery from the front-end. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x8" }, @@ -771,15 +823,46 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xa2", "EventName": "RESOURCE_STALLS.SCOREBOARD", + "PublicDescription": "Counts cycles where the pipeline is stalled due to serializing operations. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x2" }, { + "BriefDescription": "Cycles when Reservation Station (RS) is empty for the thread.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xa5", + "EventName": "RS.EMPTY", + "PublicDescription": "Counts cycles during which the reservation station (RS) is empty for this logical processor. This is usually caused when the front-end pipeline runs into starvation periods (e.g. branch mispredictions or i-cache misses) Available PDIST counters: 0", + "SampleAfterValue": "1000003", + "UMask": "0x7" + }, + { + "BriefDescription": "Counts end of periods where the Reservation Station (RS) was empty.", + "Counter": "0,1,2,3,4,5,6,7", + "CounterMask": "1", + "EdgeDetect": "1", + "EventCode": "0xa5", + "EventName": "RS.EMPTY_COUNT", + "Invert": "1", + "PublicDescription": "Counts end of periods where the Reservation Station (RS) was empty. Could be useful to closely sample on front-end latency issues (see the FRONTEND_RETIRED event of designated precise events) Available PDIST counters: 0", + "SampleAfterValue": "100003", + "UMask": "0x7" + }, + { + "BriefDescription": "Cycles when RS was empty and a resource allocation stall is asserted", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xa5", + "EventName": "RS.EMPTY_RESOURCE", + "PublicDescription": "Cycles when RS was empty and a resource allocation stall is asserted Available PDIST counters: 0", + "SampleAfterValue": "1000003", + "UMask": "0x1" + }, + { "BriefDescription": "This event counts a subset of the Topdown Slots event that were not consumed by the back-end pipeline due to lack of back-end resources, as a result of memory subsystem delays, execution units limitations, or other conditions.", "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xa4", "EventName": "TOPDOWN.BACKEND_BOUND_SLOTS", - "PublicDescription": "This event counts a subset of the Topdown Slots event that were not consumed by the back-end pipeline due to lack of back-end resources, as a result of memory subsystem delays, execution units limitations, or other conditions. The count is distributed among unhalted logical processors (hyper-threads) who share the same physical core, in processors that support Intel Hyper-Threading Technology. Software can use this event as the numerator for the Backend Bound metric (or top-level category) of the Top-down Microarchitecture Analysis method.", + "PublicDescription": "This event counts a subset of the Topdown Slots event that were not consumed by the back-end pipeline due to lack of back-end resources, as a result of memory subsystem delays, execution units limitations, or other conditions. The count is distributed among unhalted logical processors (hyper-threads) who share the same physical core, in processors that support Intel Hyper-Threading Technology. Software can use this event as the numerator for the Backend Bound metric (or top-level category) of the Top-down Microarchitecture Analysis method. Available PDIST counters: 0", "SampleAfterValue": "10000003", "UMask": "0x2" }, @@ -788,7 +871,7 @@ "Counter": "0", "EventCode": "0xa4", "EventName": "TOPDOWN.BAD_SPEC_SLOTS", - "PublicDescription": "Number of slots of TMA method that were wasted due to incorrect speculation. It covers all types of control-flow or data-related mis-speculations.", + "PublicDescription": "Number of slots of TMA method that were wasted due to incorrect speculation. It covers all types of control-flow or data-related mis-speculations. Available PDIST counters: 0", "SampleAfterValue": "10000003", "UMask": "0x4" }, @@ -797,7 +880,7 @@ "Counter": "0", "EventCode": "0xa4", "EventName": "TOPDOWN.BR_MISPREDICT_SLOTS", - "PublicDescription": "Number of TMA slots that were wasted due to incorrect speculation by (any type of) branch mispredictions. This event estimates number of speculative operations that were issued but not retired as well as the out-of-order engine recovery past a branch misprediction.", + "PublicDescription": "Number of TMA slots that were wasted due to incorrect speculation by (any type of) branch mispredictions. This event estimates number of speculative operations that were issued but not retired as well as the out-of-order engine recovery past a branch misprediction. Available PDIST counters: 0", "SampleAfterValue": "10000003", "UMask": "0x8" }, @@ -806,6 +889,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xa4", "EventName": "TOPDOWN.MEMORY_BOUND_SLOTS", + "PublicDescription": "TOPDOWN.MEMORY_BOUND_SLOTS Available PDIST counters: 0", "SampleAfterValue": "10000003", "UMask": "0x10" }, @@ -813,7 +897,7 @@ "BriefDescription": "TMA slots available for an unhalted logical processor. Fixed counter - architectural event", "Counter": "Fixed counter 3", "EventName": "TOPDOWN.SLOTS", - "PublicDescription": "Number of available slots for an unhalted logical processor. The event increments by machine-width of the narrowest pipeline as employed by the Top-down Microarchitecture Analysis method (TMA). The count is distributed among unhalted logical processors (hyper-threads) who share the same physical core. Software can use this event as the denominator for the top-level metrics of the TMA method. This architectural event is counted on a designated fixed counter (Fixed Counter 3).", + "PublicDescription": "Number of available slots for an unhalted logical processor. The event increments by machine-width of the narrowest pipeline as employed by the Top-down Microarchitecture Analysis method (TMA). The count is distributed among unhalted logical processors (hyper-threads) who share the same physical core. Software can use this event as the denominator for the top-level metrics of the TMA method. This architectural event is counted on a designated fixed counter (Fixed Counter 3). Available PDIST counters: 0", "SampleAfterValue": "10000003", "UMask": "0x4" }, @@ -822,7 +906,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xa4", "EventName": "TOPDOWN.SLOTS_P", - "PublicDescription": "Counts the number of available slots for an unhalted logical processor. The event increments by machine-width of the narrowest pipeline as employed by the Top-down Microarchitecture Analysis method. The count is distributed among unhalted logical processors (hyper-threads) who share the same physical core.", + "PublicDescription": "Counts the number of available slots for an unhalted logical processor. The event increments by machine-width of the narrowest pipeline as employed by the Top-down Microarchitecture Analysis method. The count is distributed among unhalted logical processors (hyper-threads) who share the same physical core. Available PDIST counters: 0", "SampleAfterValue": "10000003", "UMask": "0x1" }, @@ -831,7 +915,7 @@ "Counter": "0,1,2,3", "EventCode": "0x76", "EventName": "UOPS_DECODED.DEC0_UOPS", - "PublicDescription": "This event counts the number of not dec-by-all uops decoded by decoder 0.", + "PublicDescription": "This event counts the number of not dec-by-all uops decoded by decoder 0. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x1" }, @@ -840,7 +924,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xb2", "EventName": "UOPS_DISPATCHED.PORT_0", - "PublicDescription": "Number of uops dispatch to execution port 0.", + "PublicDescription": "Number of uops dispatch to execution port 0. Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x1" }, @@ -849,7 +933,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xb2", "EventName": "UOPS_DISPATCHED.PORT_1", - "PublicDescription": "Number of uops dispatch to execution port 1.", + "PublicDescription": "Number of uops dispatch to execution port 1. Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x2" }, @@ -858,7 +942,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xb2", "EventName": "UOPS_DISPATCHED.PORT_2_3_10", - "PublicDescription": "Number of uops dispatch to execution ports 2, 3 and 10", + "PublicDescription": "Number of uops dispatch to execution ports 2, 3 and 10 Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x4" }, @@ -867,7 +951,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xb2", "EventName": "UOPS_DISPATCHED.PORT_4_9", - "PublicDescription": "Number of uops dispatch to execution ports 4 and 9", + "PublicDescription": "Number of uops dispatch to execution ports 4 and 9 Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x10" }, @@ -876,7 +960,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xb2", "EventName": "UOPS_DISPATCHED.PORT_5_11", - "PublicDescription": "Number of uops dispatch to execution ports 5 and 11", + "PublicDescription": "Number of uops dispatch to execution ports 5 and 11 Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x20" }, @@ -885,7 +969,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xb2", "EventName": "UOPS_DISPATCHED.PORT_6", - "PublicDescription": "Number of uops dispatch to execution port 6.", + "PublicDescription": "Number of uops dispatch to execution port 6. Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x40" }, @@ -894,7 +978,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xb2", "EventName": "UOPS_DISPATCHED.PORT_7_8", - "PublicDescription": "Number of uops dispatch to execution ports 7 and 8.", + "PublicDescription": "Number of uops dispatch to execution ports 7 and 8. Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x80" }, @@ -903,7 +987,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xb1", "EventName": "UOPS_EXECUTED.CORE", - "PublicDescription": "Counts the number of uops executed from any thread.", + "PublicDescription": "Counts the number of uops executed from any thread. Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x2" }, @@ -913,7 +997,7 @@ "CounterMask": "1", "EventCode": "0xb1", "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_1", - "PublicDescription": "Counts cycles when at least 1 micro-op is executed from any thread on physical core.", + "PublicDescription": "Counts cycles when at least 1 micro-op is executed from any thread on physical core. Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x2" }, @@ -923,7 +1007,7 @@ "CounterMask": "2", "EventCode": "0xb1", "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_2", - "PublicDescription": "Counts cycles when at least 2 micro-ops are executed from any thread on physical core.", + "PublicDescription": "Counts cycles when at least 2 micro-ops are executed from any thread on physical core. Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x2" }, @@ -933,7 +1017,7 @@ "CounterMask": "3", "EventCode": "0xb1", "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_3", - "PublicDescription": "Counts cycles when at least 3 micro-ops are executed from any thread on physical core.", + "PublicDescription": "Counts cycles when at least 3 micro-ops are executed from any thread on physical core. Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x2" }, @@ -943,7 +1027,7 @@ "CounterMask": "4", "EventCode": "0xb1", "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_4", - "PublicDescription": "Counts cycles when at least 4 micro-ops are executed from any thread on physical core.", + "PublicDescription": "Counts cycles when at least 4 micro-ops are executed from any thread on physical core. Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x2" }, @@ -953,7 +1037,7 @@ "CounterMask": "1", "EventCode": "0xb1", "EventName": "UOPS_EXECUTED.CYCLES_GE_1", - "PublicDescription": "Cycles where at least 1 uop was executed per-thread.", + "PublicDescription": "Cycles where at least 1 uop was executed per-thread. Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x1" }, @@ -963,7 +1047,7 @@ "CounterMask": "2", "EventCode": "0xb1", "EventName": "UOPS_EXECUTED.CYCLES_GE_2", - "PublicDescription": "Cycles where at least 2 uops were executed per-thread.", + "PublicDescription": "Cycles where at least 2 uops were executed per-thread. Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x1" }, @@ -973,7 +1057,7 @@ "CounterMask": "3", "EventCode": "0xb1", "EventName": "UOPS_EXECUTED.CYCLES_GE_3", - "PublicDescription": "Cycles where at least 3 uops were executed per-thread.", + "PublicDescription": "Cycles where at least 3 uops were executed per-thread. Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x1" }, @@ -983,7 +1067,7 @@ "CounterMask": "4", "EventCode": "0xb1", "EventName": "UOPS_EXECUTED.CYCLES_GE_4", - "PublicDescription": "Cycles where at least 4 uops were executed per-thread.", + "PublicDescription": "Cycles where at least 4 uops were executed per-thread. Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x1" }, @@ -994,7 +1078,7 @@ "EventCode": "0xb1", "EventName": "UOPS_EXECUTED.STALLS", "Invert": "1", - "PublicDescription": "Counts cycles during which no uops were dispatched from the Reservation Station (RS) per thread.", + "PublicDescription": "Counts cycles during which no uops were dispatched from the Reservation Station (RS) per thread. Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x1" }, @@ -1003,6 +1087,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xb1", "EventName": "UOPS_EXECUTED.THREAD", + "PublicDescription": "Counts the number of uops to be executed per-thread each cycle. Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x1" }, @@ -1011,7 +1096,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xb1", "EventName": "UOPS_EXECUTED.X87", - "PublicDescription": "Counts the number of x87 uops executed.", + "PublicDescription": "Counts the number of x87 uops executed. Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x10" }, @@ -1020,7 +1105,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xae", "EventName": "UOPS_ISSUED.ANY", - "PublicDescription": "Counts the number of uops that the Resource Allocation Table (RAT) issues to the Reservation Station (RS).", + "PublicDescription": "Counts the number of uops that the Resource Allocation Table (RAT) issues to the Reservation Station (RS). Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x1" }, @@ -1030,6 +1115,7 @@ "CounterMask": "1", "EventCode": "0xae", "EventName": "UOPS_ISSUED.CYCLES", + "PublicDescription": "UOPS_ISSUED.CYCLES Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x1" }, @@ -1039,7 +1125,7 @@ "CounterMask": "1", "EventCode": "0xc2", "EventName": "UOPS_RETIRED.CYCLES", - "PublicDescription": "Counts cycles where at least one uop has retired.", + "PublicDescription": "Counts cycles where at least one uop has retired. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x2" }, @@ -1048,7 +1134,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc2", "EventName": "UOPS_RETIRED.HEAVY", - "PublicDescription": "Counts the number of retired micro-operations (uops) except the last uop of each instruction. An instruction that is decoded into less than two uops does not contribute to the count.", + "PublicDescription": "Counts the number of retired micro-operations (uops) except the last uop of each instruction. An instruction that is decoded into less than two uops does not contribute to the count. Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x1" }, @@ -1059,6 +1145,7 @@ "EventName": "UOPS_RETIRED.MS", "MSRIndex": "0x3F7", "MSRValue": "0x8", + "PublicDescription": "UOPS_RETIRED.MS Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x4" }, @@ -1067,7 +1154,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc2", "EventName": "UOPS_RETIRED.SLOTS", - "PublicDescription": "This event counts a subset of the Topdown Slots event that are utilized by operations that eventually get retired (committed) by the processor pipeline. Usually, this event positively correlates with higher performance for example, as measured by the instructions-per-cycle metric. Software can use this event as the numerator for the Retiring metric (or top-level category) of the Top-down Microarchitecture Analysis method.", + "PublicDescription": "This event counts a subset of the Topdown Slots event that are utilized by operations that eventually get retired (committed) by the processor pipeline. Usually, this event positively correlates with higher performance for example, as measured by the instructions-per-cycle metric. Software can use this event as the numerator for the Retiring metric (or top-level category) of the Top-down Microarchitecture Analysis method. Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x2" }, @@ -1078,7 +1165,7 @@ "EventCode": "0xc2", "EventName": "UOPS_RETIRED.STALLS", "Invert": "1", - "PublicDescription": "This event counts cycles without actually retired uops.", + "PublicDescription": "This event counts cycles without actually retired uops. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x2" } diff --git a/tools/perf/pmu-events/arch/x86/graniterapids/uncore-cache.json b/tools/perf/pmu-events/arch/x86/graniterapids/uncore-cache.json index 53055986534d..b782f6d54fc2 100644 --- a/tools/perf/pmu-events/arch/x86/graniterapids/uncore-cache.json +++ b/tools/perf/pmu-events/arch/x86/graniterapids/uncore-cache.json @@ -854,6 +854,16 @@ "Unit": "CHA" }, { + "BriefDescription": "Ingress (from CMS) Allocations : IRQ : Counts number of allocations per cycle into the specified Ingress queue.", + "Counter": "0,1,2,3", + "EventCode": "0x13", + "EventName": "UNC_CHA_RxC_INSERTS.IRQ", + "Experimental": "1", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CHA" + }, + { "BriefDescription": "Ingress (from CMS) Occupancy : IRQ : Counts number of entries in the specified Ingress queue in each cycle.", "Counter": "0", "EventCode": "0x11", @@ -864,6 +874,38 @@ "Unit": "CHA" }, { + "BriefDescription": "Counts snoop filter capacity evictions for entries tracking exclusive lines in the core's cache. Snoop filter capacity evictions occur when the snoop filter is full and evicts an existing entry to track a new entry. Does not count clean evictions such as when a core's cache replaces a tracked cacheline with a new cacheline.", + "Counter": "0,1,2,3", + "EventCode": "0x3d", + "EventName": "UNC_CHA_SF_EVICTION.E_STATE", + "Experimental": "1", + "PerPkg": "1", + "PublicDescription": "Snoop Filter Capacity Evictions : E state", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "Counts snoop filter capacity evictions for entries tracking modified lines in the core's cache. Snoop filter capacity evictions occur when the snoop filter is full and evicts an existing entry to track a new entry. Does not count clean evictions such as when a core's cache replaces a tracked cacheline with a new cacheline.", + "Counter": "0,1,2,3", + "EventCode": "0x3d", + "EventName": "UNC_CHA_SF_EVICTION.M_STATE", + "PerPkg": "1", + "PublicDescription": "Snoop Filter Capacity Evictions : M state", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Counts snoop filter capacity evictions for entries tracking shared lines in the core's cache. Snoop filter capacity evictions occur when the snoop filter is full and evicts an existing entry to track a new entry. Does not count clean evictions such as when a core's cache replaces a tracked cacheline with a new cacheline.", + "Counter": "0,1,2,3", + "EventCode": "0x3d", + "EventName": "UNC_CHA_SF_EVICTION.S_STATE", + "Experimental": "1", + "PerPkg": "1", + "PublicDescription": "Snoop Filter Capacity Evictions : S state", + "UMask": "0x4", + "Unit": "CHA" + }, + { "BriefDescription": "All TOR Inserts", "Counter": "0,1,2,3", "EventCode": "0x35", diff --git a/tools/perf/pmu-events/arch/x86/graniterapids/uncore-interconnect.json b/tools/perf/pmu-events/arch/x86/graniterapids/uncore-interconnect.json index 5c50275c79b0..e5bd11b27bcd 100644 --- a/tools/perf/pmu-events/arch/x86/graniterapids/uncore-interconnect.json +++ b/tools/perf/pmu-events/arch/x86/graniterapids/uncore-interconnect.json @@ -1076,7 +1076,7 @@ "Unit": "MDF" }, { - "BriefDescription": "Egress bypasses for for AD_BNC", + "BriefDescription": "Egress bypasses for AD_BNC", "Counter": "0,1,2,3", "EventCode": "0x1E", "EventName": "UNC_MDF_TxR_BYPASS.AD_BNC", @@ -1086,7 +1086,7 @@ "Unit": "MDF" }, { - "BriefDescription": "Egress bypasses for for AD_CRD", + "BriefDescription": "Egress bypasses for AD_CRD", "Counter": "0,1,2,3", "EventCode": "0x1E", "EventName": "UNC_MDF_TxR_BYPASS.AD_CRD", @@ -1096,7 +1096,7 @@ "Unit": "MDF" }, { - "BriefDescription": "Egress bypasses for for AK", + "BriefDescription": "Egress bypasses for AK", "Counter": "0,1,2,3", "EventCode": "0x1E", "EventName": "UNC_MDF_TxR_BYPASS.AK", @@ -1106,7 +1106,7 @@ "Unit": "MDF" }, { - "BriefDescription": "Egress bypasses for for BL_BNC", + "BriefDescription": "Egress bypasses for BL_BNC", "Counter": "0,1,2,3", "EventCode": "0x1E", "EventName": "UNC_MDF_TxR_BYPASS.BL_BNC", @@ -1116,7 +1116,7 @@ "Unit": "MDF" }, { - "BriefDescription": "Egress bypasses for for BL_CRD", + "BriefDescription": "Egress bypasses for BL_CRD", "Counter": "0,1,2,3", "EventCode": "0x1E", "EventName": "UNC_MDF_TxR_BYPASS.BL_CRD", @@ -1126,7 +1126,7 @@ "Unit": "MDF" }, { - "BriefDescription": "Egress bypasses for for IV", + "BriefDescription": "Egress bypasses for IV", "Counter": "0,1,2,3", "EventCode": "0x1E", "EventName": "UNC_MDF_TxR_BYPASS.IV", @@ -1136,7 +1136,7 @@ "Unit": "MDF" }, { - "BriefDescription": "Number of egress inserts for for AD_BNC", + "BriefDescription": "Number of egress inserts for AD_BNC", "Counter": "0,1,2,3", "EventCode": "0x1C", "EventName": "UNC_MDF_TxR_INSERTS.AD_BNC", @@ -1146,7 +1146,7 @@ "Unit": "MDF" }, { - "BriefDescription": "Number of egress inserts for for AD_CRD", + "BriefDescription": "Number of egress inserts for AD_CRD", "Counter": "0,1,2,3", "EventCode": "0x1C", "EventName": "UNC_MDF_TxR_INSERTS.AD_CRD", @@ -1156,7 +1156,7 @@ "Unit": "MDF" }, { - "BriefDescription": "Number of egress inserts for for AK", + "BriefDescription": "Number of egress inserts for AK", "Counter": "0,1,2,3", "EventCode": "0x1C", "EventName": "UNC_MDF_TxR_INSERTS.AK", @@ -1166,7 +1166,7 @@ "Unit": "MDF" }, { - "BriefDescription": "Number of egress inserts for for BL_BNC", + "BriefDescription": "Number of egress inserts for BL_BNC", "Counter": "0,1,2,3", "EventCode": "0x1C", "EventName": "UNC_MDF_TxR_INSERTS.BL_BNC", @@ -1176,7 +1176,7 @@ "Unit": "MDF" }, { - "BriefDescription": "Number of egress inserts for for BL_CRD", + "BriefDescription": "Number of egress inserts for BL_CRD", "Counter": "0,1,2,3", "EventCode": "0x1C", "EventName": "UNC_MDF_TxR_INSERTS.BL_CRD", @@ -1186,7 +1186,7 @@ "Unit": "MDF" }, { - "BriefDescription": "Number of egress inserts for for IV", + "BriefDescription": "Number of egress inserts for IV", "Counter": "0,1,2,3", "EventCode": "0x1C", "EventName": "UNC_MDF_TxR_INSERTS.IV", @@ -1196,7 +1196,7 @@ "Unit": "MDF" }, { - "BriefDescription": "Egress occupancy for for AD_BNC", + "BriefDescription": "Egress occupancy for AD_BNC", "Counter": "0,1,2,3", "EventCode": "0x1D", "EventName": "UNC_MDF_TxR_OCCUPANCY.AD_BNC", @@ -1206,7 +1206,7 @@ "Unit": "MDF" }, { - "BriefDescription": "Egress occupancy for for AD_CRD", + "BriefDescription": "Egress occupancy for AD_CRD", "Counter": "0,1,2,3", "EventCode": "0x1D", "EventName": "UNC_MDF_TxR_OCCUPANCY.AD_CRD", @@ -1216,7 +1216,7 @@ "Unit": "MDF" }, { - "BriefDescription": "Egress occupancy for for AK", + "BriefDescription": "Egress occupancy for AK", "Counter": "0,1,2,3", "EventCode": "0x1D", "EventName": "UNC_MDF_TxR_OCCUPANCY.AK", @@ -1226,7 +1226,7 @@ "Unit": "MDF" }, { - "BriefDescription": "Egress occupancy for for BL_BNC", + "BriefDescription": "Egress occupancy for BL_BNC", "Counter": "0,1,2,3", "EventCode": "0x1D", "EventName": "UNC_MDF_TxR_OCCUPANCY.BL_BNC", @@ -1236,7 +1236,7 @@ "Unit": "MDF" }, { - "BriefDescription": "Egress occupancy for for BL_CRD", + "BriefDescription": "Egress occupancy for BL_CRD", "Counter": "0,1,2,3", "EventCode": "0x1D", "EventName": "UNC_MDF_TxR_OCCUPANCY.BL_CRD", @@ -1246,7 +1246,7 @@ "Unit": "MDF" }, { - "BriefDescription": "Egress occupancy for for IV", + "BriefDescription": "Egress occupancy for IV", "Counter": "0,1,2,3", "EventCode": "0x1D", "EventName": "UNC_MDF_TxR_OCCUPANCY.IV", @@ -1932,5 +1932,59 @@ "Experimental": "1", "PerPkg": "1", "Unit": "UPI" + }, + { + "BriefDescription": "Message Received : Doorbell", + "Counter": "0,1", + "EventCode": "0x42", + "EventName": "UNC_U_EVENT_MSG.DOORBELL_RCVD", + "Experimental": "1", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "UBOX" + }, + { + "BriefDescription": "Message Received : Interrupt", + "Counter": "0,1", + "EventCode": "0x42", + "EventName": "UNC_U_EVENT_MSG.INT_PRIO", + "Experimental": "1", + "PerPkg": "1", + "PublicDescription": "Message Received : Interrupt : Interrupts", + "UMask": "0x10", + "Unit": "UBOX" + }, + { + "BriefDescription": "Message Received : IPI", + "Counter": "0,1", + "EventCode": "0x42", + "EventName": "UNC_U_EVENT_MSG.IPI_RCVD", + "Experimental": "1", + "PerPkg": "1", + "PublicDescription": "Message Received : IPI : Inter Processor Interrupts", + "UMask": "0x4", + "Unit": "UBOX" + }, + { + "BriefDescription": "Message Received : MSI", + "Counter": "0,1", + "EventCode": "0x42", + "EventName": "UNC_U_EVENT_MSG.MSI_RCVD", + "Experimental": "1", + "PerPkg": "1", + "PublicDescription": "Message Received : MSI : Message Signaled Interrupts - interrupts sent by devices (including PCIe via IOxAPIC) (Socket Mode only)", + "UMask": "0x2", + "Unit": "UBOX" + }, + { + "BriefDescription": "Message Received : VLW", + "Counter": "0,1", + "EventCode": "0x42", + "EventName": "UNC_U_EVENT_MSG.VLW_RCVD", + "Experimental": "1", + "PerPkg": "1", + "PublicDescription": "Message Received : VLW : Virtual Logical Wire (legacy) message were received from Uncore.", + "UMask": "0x1", + "Unit": "UBOX" } ] diff --git a/tools/perf/pmu-events/arch/x86/graniterapids/uncore-memory.json b/tools/perf/pmu-events/arch/x86/graniterapids/uncore-memory.json index 5f4783ff6ce5..b991f6e1afbe 100644 --- a/tools/perf/pmu-events/arch/x86/graniterapids/uncore-memory.json +++ b/tools/perf/pmu-events/arch/x86/graniterapids/uncore-memory.json @@ -189,6 +189,94 @@ "Unit": "IMC" }, { + "BriefDescription": "# of cycles MR4 temp readings forced 2x refresh", + "Counter": "0,1,2,3", + "EventCode": "0xA7", + "EventName": "UNC_M_MR4_2XREF_CYCLES.SCH0_DIMM0", + "Experimental": "1", + "PerPkg": "1", + "PublicDescription": "-", + "UMask": "0x1", + "Unit": "IMC" + }, + { + "BriefDescription": "# of cycles MR4 temp readings forced 2x refresh", + "Counter": "0,1,2,3", + "EventCode": "0xA7", + "EventName": "UNC_M_MR4_2XREF_CYCLES.SCH0_DIMM1", + "Experimental": "1", + "PerPkg": "1", + "PublicDescription": "-", + "UMask": "0x2", + "Unit": "IMC" + }, + { + "BriefDescription": "# of cycles MR4 temp readings forced 2x refresh", + "Counter": "0,1,2,3", + "EventCode": "0xA7", + "EventName": "UNC_M_MR4_2XREF_CYCLES.SCH1_DIMM0", + "Experimental": "1", + "PerPkg": "1", + "PublicDescription": "-", + "UMask": "0x4", + "Unit": "IMC" + }, + { + "BriefDescription": "# of cycles MR4 temp readings forced 2x refresh", + "Counter": "0,1,2,3", + "EventCode": "0xA7", + "EventName": "UNC_M_MR4_2XREF_CYCLES.SCH1_DIMM1", + "Experimental": "1", + "PerPkg": "1", + "PublicDescription": "-", + "UMask": "0x8", + "Unit": "IMC" + }, + { + "BriefDescription": "# of cycles MR4 MRRs was triggered/running", + "Counter": "0,1,2,3", + "EventCode": "0xA6", + "EventName": "UNC_M_PDC_MR4ACTIVE_CYCLES.SCH0_DIMM0", + "Experimental": "1", + "PerPkg": "1", + "PublicDescription": "-", + "UMask": "0x1", + "Unit": "IMC" + }, + { + "BriefDescription": "# of cycles MR4 MRRs was triggered/running", + "Counter": "0,1,2,3", + "EventCode": "0xA6", + "EventName": "UNC_M_PDC_MR4ACTIVE_CYCLES.SCH0_DIMM1", + "Experimental": "1", + "PerPkg": "1", + "PublicDescription": "-", + "UMask": "0x2", + "Unit": "IMC" + }, + { + "BriefDescription": "# of cycles MR4 MRRs was triggered/running", + "Counter": "0,1,2,3", + "EventCode": "0xA6", + "EventName": "UNC_M_PDC_MR4ACTIVE_CYCLES.SCH1_DIMM0", + "Experimental": "1", + "PerPkg": "1", + "PublicDescription": "-", + "UMask": "0x4", + "Unit": "IMC" + }, + { + "BriefDescription": "# of cycles MR4 MRRs was triggered/running", + "Counter": "0,1,2,3", + "EventCode": "0xA6", + "EventName": "UNC_M_PDC_MR4ACTIVE_CYCLES.SCH1_DIMM1", + "Experimental": "1", + "PerPkg": "1", + "PublicDescription": "-", + "UMask": "0x8", + "Unit": "IMC" + }, + { "BriefDescription": "# of cycles a given rank is in Power Down Mode", "Counter": "0,1,2,3", "EventCode": "0x47", @@ -287,6 +375,70 @@ "Unit": "IMC" }, { + "BriefDescription": "# of cycles Throttling at Critical level on specified DIMM and throttle level is zero.", + "Counter": "0,1,2,3", + "EventCode": "0x89", + "EventName": "UNC_M_POWER_CRITICAL_THROTTLE_CYCLES.SLOT0", + "Experimental": "1", + "PerPkg": "1", + "PublicDescription": "-", + "UMask": "0x1", + "Unit": "IMC" + }, + { + "BriefDescription": "# of cycles Throttling at Critical level on specified DIMM and throttle level is zero.", + "Counter": "0,1,2,3", + "EventCode": "0x89", + "EventName": "UNC_M_POWER_CRITICAL_THROTTLE_CYCLES.SLOT1", + "Experimental": "1", + "PerPkg": "1", + "PublicDescription": "-", + "UMask": "0x2", + "Unit": "IMC" + }, + { + "BriefDescription": "UNC_M_POWER_THROTTLE_CYCLES.BW_SLOT0", + "Counter": "0,1,2,3", + "EventCode": "0x46", + "EventName": "UNC_M_POWER_THROTTLE_CYCLES.BW_SLOT0", + "Experimental": "1", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "IMC" + }, + { + "BriefDescription": "UNC_M_POWER_THROTTLE_CYCLES.BW_SLOT1", + "Counter": "0,1,2,3", + "EventCode": "0x46", + "EventName": "UNC_M_POWER_THROTTLE_CYCLES.BW_SLOT1", + "Experimental": "1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "IMC" + }, + { + "BriefDescription": "MR4 temp reading is throttling", + "Counter": "0,1,2,3", + "EventCode": "0x46", + "EventName": "UNC_M_POWER_THROTTLE_CYCLES.MR4BLKEN", + "Experimental": "1", + "PerPkg": "1", + "PublicDescription": "-", + "UMask": "0x8", + "Unit": "IMC" + }, + { + "BriefDescription": "RAPL is throttling", + "Counter": "0,1,2,3", + "EventCode": "0x46", + "EventName": "UNC_M_POWER_THROTTLE_CYCLES.RAPLBLK", + "Experimental": "1", + "PerPkg": "1", + "PublicDescription": "-", + "UMask": "0x4", + "Unit": "IMC" + }, + { "BriefDescription": "DRAM Precharge commands. : Counts the number of DRAM Precharge commands sent on this channel.", "Counter": "0,1,2,3", "EventCode": "0x03", @@ -479,6 +631,94 @@ "Unit": "IMC" }, { + "BriefDescription": "# of cycles Throttling at Critical level on specified DIMM", + "Counter": "0,1,2,3", + "EventCode": "0x8e", + "EventName": "UNC_M_THROTTLE_CRIT_CYCLES.SLOT0", + "Experimental": "1", + "PerPkg": "1", + "PublicDescription": "-", + "UMask": "0x1", + "Unit": "IMC" + }, + { + "BriefDescription": "# of cycles Throttling at Critical level on specified DIMM", + "Counter": "0,1,2,3", + "EventCode": "0x8e", + "EventName": "UNC_M_THROTTLE_CRIT_CYCLES.SLOT1", + "Experimental": "1", + "PerPkg": "1", + "PublicDescription": "-", + "UMask": "0x2", + "Unit": "IMC" + }, + { + "BriefDescription": "# of cycles Throttling at High level on specified DIMM", + "Counter": "0,1,2,3", + "EventCode": "0x8d", + "EventName": "UNC_M_THROTTLE_HIGH_CYCLES.SLOT0", + "Experimental": "1", + "PerPkg": "1", + "PublicDescription": "-", + "UMask": "0x1", + "Unit": "IMC" + }, + { + "BriefDescription": "# of cycles Throttling at High level on specified DIMM", + "Counter": "0,1,2,3", + "EventCode": "0x8d", + "EventName": "UNC_M_THROTTLE_HIGH_CYCLES.SLOT1", + "Experimental": "1", + "PerPkg": "1", + "PublicDescription": "-", + "UMask": "0x2", + "Unit": "IMC" + }, + { + "BriefDescription": "# of cycles Throttling at Normal level on specified DIMM", + "Counter": "0,1,2,3", + "EventCode": "0x8b", + "EventName": "UNC_M_THROTTLE_LOW_CYCLES.SLOT0", + "Experimental": "1", + "PerPkg": "1", + "PublicDescription": "-", + "UMask": "0x1", + "Unit": "IMC" + }, + { + "BriefDescription": "# of cycles Throttling at Normal level on specified DIMM", + "Counter": "0,1,2,3", + "EventCode": "0x8b", + "EventName": "UNC_M_THROTTLE_LOW_CYCLES.SLOT1", + "Experimental": "1", + "PerPkg": "1", + "PublicDescription": "-", + "UMask": "0x2", + "Unit": "IMC" + }, + { + "BriefDescription": "# of cycles Throttling at Mid level on specified DIMM", + "Counter": "0,1,2,3", + "EventCode": "0x8c", + "EventName": "UNC_M_THROTTLE_MID_CYCLES.SLOT0", + "Experimental": "1", + "PerPkg": "1", + "PublicDescription": "-", + "UMask": "0x1", + "Unit": "IMC" + }, + { + "BriefDescription": "# of cycles Throttling at Mid level on specified DIMM", + "Counter": "0,1,2,3", + "EventCode": "0x8c", + "EventName": "UNC_M_THROTTLE_MID_CYCLES.SLOT1", + "Experimental": "1", + "PerPkg": "1", + "PublicDescription": "-", + "UMask": "0x2", + "Unit": "IMC" + }, + { "BriefDescription": "Write Pending Queue Allocations", "Counter": "0,1,2,3", "EventCode": "0x22", diff --git a/tools/perf/pmu-events/arch/x86/graniterapids/virtual-memory.json b/tools/perf/pmu-events/arch/x86/graniterapids/virtual-memory.json index 609a9549cbf3..3d3f88600e26 100644 --- a/tools/perf/pmu-events/arch/x86/graniterapids/virtual-memory.json +++ b/tools/perf/pmu-events/arch/x86/graniterapids/virtual-memory.json @@ -4,7 +4,7 @@ "Counter": "0,1,2,3", "EventCode": "0x12", "EventName": "DTLB_LOAD_MISSES.STLB_HIT", - "PublicDescription": "Counts loads that miss the DTLB (Data TLB) and hit the STLB (Second level TLB).", + "PublicDescription": "Counts loads that miss the DTLB (Data TLB) and hit the STLB (Second level TLB). Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x20" }, @@ -14,7 +14,7 @@ "CounterMask": "1", "EventCode": "0x12", "EventName": "DTLB_LOAD_MISSES.WALK_ACTIVE", - "PublicDescription": "Counts cycles when at least one PMH (Page Miss Handler) is busy with a page walk for a demand load.", + "PublicDescription": "Counts cycles when at least one PMH (Page Miss Handler) is busy with a page walk for a demand load. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x10" }, @@ -23,7 +23,7 @@ "Counter": "0,1,2,3", "EventCode": "0x12", "EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED", - "PublicDescription": "Counts completed page walks (all page sizes) caused by demand data loads. This implies it missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.", + "PublicDescription": "Counts completed page walks (all page sizes) caused by demand data loads. This implies it missed in the DTLB and further levels of TLB. The page walk can end with or without a fault. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0xe" }, @@ -32,7 +32,7 @@ "Counter": "0,1,2,3", "EventCode": "0x12", "EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED_1G", - "PublicDescription": "Counts completed page walks (1G sizes) caused by demand data loads. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.", + "PublicDescription": "Counts completed page walks (1G sizes) caused by demand data loads. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x8" }, @@ -41,7 +41,7 @@ "Counter": "0,1,2,3", "EventCode": "0x12", "EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M", - "PublicDescription": "Counts completed page walks (2M/4M sizes) caused by demand data loads. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.", + "PublicDescription": "Counts completed page walks (2M/4M sizes) caused by demand data loads. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x4" }, @@ -50,7 +50,7 @@ "Counter": "0,1,2,3", "EventCode": "0x12", "EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED_4K", - "PublicDescription": "Counts completed page walks (4K sizes) caused by demand data loads. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.", + "PublicDescription": "Counts completed page walks (4K sizes) caused by demand data loads. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x2" }, @@ -59,7 +59,7 @@ "Counter": "0,1,2,3", "EventCode": "0x12", "EventName": "DTLB_LOAD_MISSES.WALK_PENDING", - "PublicDescription": "Counts the number of page walks outstanding for a demand load in the PMH (Page Miss Handler) each cycle.", + "PublicDescription": "Counts the number of page walks outstanding for a demand load in the PMH (Page Miss Handler) each cycle. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x10" }, @@ -68,7 +68,7 @@ "Counter": "0,1,2,3", "EventCode": "0x13", "EventName": "DTLB_STORE_MISSES.STLB_HIT", - "PublicDescription": "Counts stores that miss the DTLB (Data TLB) and hit the STLB (2nd Level TLB).", + "PublicDescription": "Counts stores that miss the DTLB (Data TLB) and hit the STLB (2nd Level TLB). Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x20" }, @@ -78,7 +78,7 @@ "CounterMask": "1", "EventCode": "0x13", "EventName": "DTLB_STORE_MISSES.WALK_ACTIVE", - "PublicDescription": "Counts cycles when at least one PMH (Page Miss Handler) is busy with a page walk for a store.", + "PublicDescription": "Counts cycles when at least one PMH (Page Miss Handler) is busy with a page walk for a store. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x10" }, @@ -87,7 +87,7 @@ "Counter": "0,1,2,3", "EventCode": "0x13", "EventName": "DTLB_STORE_MISSES.WALK_COMPLETED", - "PublicDescription": "Counts completed page walks (all page sizes) caused by demand data stores. This implies it missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.", + "PublicDescription": "Counts completed page walks (all page sizes) caused by demand data stores. This implies it missed in the DTLB and further levels of TLB. The page walk can end with or without a fault. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0xe" }, @@ -96,7 +96,7 @@ "Counter": "0,1,2,3", "EventCode": "0x13", "EventName": "DTLB_STORE_MISSES.WALK_COMPLETED_1G", - "PublicDescription": "Counts completed page walks (1G sizes) caused by demand data stores. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.", + "PublicDescription": "Counts completed page walks (1G sizes) caused by demand data stores. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x8" }, @@ -105,7 +105,7 @@ "Counter": "0,1,2,3", "EventCode": "0x13", "EventName": "DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M", - "PublicDescription": "Counts completed page walks (2M/4M sizes) caused by demand data stores. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.", + "PublicDescription": "Counts completed page walks (2M/4M sizes) caused by demand data stores. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x4" }, @@ -114,7 +114,7 @@ "Counter": "0,1,2,3", "EventCode": "0x13", "EventName": "DTLB_STORE_MISSES.WALK_COMPLETED_4K", - "PublicDescription": "Counts completed page walks (4K sizes) caused by demand data stores. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.", + "PublicDescription": "Counts completed page walks (4K sizes) caused by demand data stores. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x2" }, @@ -123,7 +123,7 @@ "Counter": "0,1,2,3", "EventCode": "0x13", "EventName": "DTLB_STORE_MISSES.WALK_PENDING", - "PublicDescription": "Counts the number of page walks outstanding for a store in the PMH (Page Miss Handler) each cycle.", + "PublicDescription": "Counts the number of page walks outstanding for a store in the PMH (Page Miss Handler) each cycle. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x10" }, @@ -132,7 +132,7 @@ "Counter": "0,1,2,3", "EventCode": "0x11", "EventName": "ITLB_MISSES.STLB_HIT", - "PublicDescription": "Counts instruction fetch requests that miss the ITLB (Instruction TLB) and hit the STLB (Second-level TLB).", + "PublicDescription": "Counts instruction fetch requests that miss the ITLB (Instruction TLB) and hit the STLB (Second-level TLB). Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x20" }, @@ -142,7 +142,7 @@ "CounterMask": "1", "EventCode": "0x11", "EventName": "ITLB_MISSES.WALK_ACTIVE", - "PublicDescription": "Counts cycles when at least one PMH (Page Miss Handler) is busy with a page walk for a code (instruction fetch) request.", + "PublicDescription": "Counts cycles when at least one PMH (Page Miss Handler) is busy with a page walk for a code (instruction fetch) request. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x10" }, @@ -151,7 +151,7 @@ "Counter": "0,1,2,3", "EventCode": "0x11", "EventName": "ITLB_MISSES.WALK_COMPLETED", - "PublicDescription": "Counts completed page walks (all page sizes) caused by a code fetch. This implies it missed in the ITLB (Instruction TLB) and further levels of TLB. The page walk can end with or without a fault.", + "PublicDescription": "Counts completed page walks (all page sizes) caused by a code fetch. This implies it missed in the ITLB (Instruction TLB) and further levels of TLB. The page walk can end with or without a fault. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0xe" }, @@ -160,7 +160,7 @@ "Counter": "0,1,2,3", "EventCode": "0x11", "EventName": "ITLB_MISSES.WALK_COMPLETED_2M_4M", - "PublicDescription": "Counts completed page walks (2M/4M page sizes) caused by a code fetch. This implies it missed in the ITLB (Instruction TLB) and further levels of TLB. The page walk can end with or without a fault.", + "PublicDescription": "Counts completed page walks (2M/4M page sizes) caused by a code fetch. This implies it missed in the ITLB (Instruction TLB) and further levels of TLB. The page walk can end with or without a fault. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x4" }, @@ -169,7 +169,7 @@ "Counter": "0,1,2,3", "EventCode": "0x11", "EventName": "ITLB_MISSES.WALK_COMPLETED_4K", - "PublicDescription": "Counts completed page walks (4K page sizes) caused by a code fetch. This implies it missed in the ITLB (Instruction TLB) and further levels of TLB. The page walk can end with or without a fault.", + "PublicDescription": "Counts completed page walks (4K page sizes) caused by a code fetch. This implies it missed in the ITLB (Instruction TLB) and further levels of TLB. The page walk can end with or without a fault. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x2" }, @@ -178,7 +178,7 @@ "Counter": "0,1,2,3", "EventCode": "0x11", "EventName": "ITLB_MISSES.WALK_PENDING", - "PublicDescription": "Counts the number of page walks outstanding for an outstanding code (instruction fetch) request in the PMH (Page Miss Handler) each cycle.", + "PublicDescription": "Counts the number of page walks outstanding for an outstanding code (instruction fetch) request in the PMH (Page Miss Handler) each cycle. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x10" } diff --git a/tools/perf/pmu-events/arch/x86/haswell/hsw-metrics.json b/tools/perf/pmu-events/arch/x86/haswell/hsw-metrics.json index 0c1040b7e38c..b26ea70a3628 100644 --- a/tools/perf/pmu-events/arch/x86/haswell/hsw-metrics.json +++ b/tools/perf/pmu-events/arch/x86/haswell/hsw-metrics.json @@ -74,12 +74,12 @@ "MetricExpr": "LD_BLOCKS_PARTIAL.ADDRESS_ALIAS / tma_info_thread_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group", "MetricName": "tma_4k_aliasing", - "MetricThreshold": "tma_4k_aliasing > 0.2 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", - "PublicDescription": "This metric estimates how often memory load accesses were aliased by preceding stores (in program order) with a 4K address offset. False match is possible; which incur a few cycles load re-issue. However; the short re-issue duration is often hidden by the out-of-order core and HW optimizations; hence a user may safely ignore a high value of this metric unless it manages to propagate up into parent nodes of the hierarchy (e.g. to L1_Bound)", + "MetricThreshold": "tma_4k_aliasing > 0.2 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric estimates how often memory load accesses were aliased by preceding stores (in program order) with a 4K address offset. False match is possible; which incur a few cycles load re-issue. However; the short re-issue duration is often hidden by the out-of-order core and HW optimizations; hence a user may safely ignore a high value of this metric unless it manages to propagate up into parent nodes of the hierarchy (e.g. to L1_Bound).", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution ports for ALU operations", + "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution ports for ALU operations.", "MetricConstraint": "NO_GROUP_EVENTS_NMI", "MetricExpr": "(UOPS_DISPATCHED_PORT.PORT_0 + UOPS_DISPATCHED_PORT.PORT_1 + UOPS_DISPATCHED_PORT.PORT_5 + UOPS_DISPATCHED_PORT.PORT_6) / tma_info_thread_slots", "MetricGroup": "TopdownL5;tma_L5_group;tma_ports_utilized_3m_group", @@ -92,8 +92,8 @@ "MetricExpr": "66 * OTHER_ASSISTS.ANY_WB_ASSIST / tma_info_thread_slots", "MetricGroup": "BvIO;TopdownL4;tma_L4_group;tma_microcode_sequencer_group", "MetricName": "tma_assists", - "MetricThreshold": "tma_assists > 0.1 & tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1", - "PublicDescription": "This metric estimates fraction of slots the CPU retired uops delivered by the Microcode_Sequencer as a result of Assists. Assists are long sequences of uops that are required in certain corner-cases for operations that cannot be handled natively by the execution pipeline. For example; when working with very small floating point values (so-called Denormals); the FP units are not set up to perform these operations natively. Instead; a sequence of instructions to perform the computation on the Denormals is injected into the pipeline. Since these microcode sequences might be dozens of uops long; Assists can be extremely deleterious to performance and they can be avoided in many cases. Sample with: OTHER_ASSISTS.ANY_WB_ASSIST", + "MetricThreshold": "tma_assists > 0.1 & (tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1)", + "PublicDescription": "This metric estimates fraction of slots the CPU retired uops delivered by the Microcode_Sequencer as a result of Assists. Assists are long sequences of uops that are required in certain corner-cases for operations that cannot be handled natively by the execution pipeline. For example; when working with very small floating point values (so-called Denormals); the FP units are not set up to perform these operations natively. Instead; a sequence of instructions to perform the computation on the Denormals is injected into the pipeline. Since these microcode sequences might be dozens of uops long; Assists can be extremely deleterious to performance and they can be avoided in many cases. Sample with: OTHER_ASSISTS.ANY", "ScaleUnit": "100%" }, { @@ -104,7 +104,7 @@ "MetricName": "tma_backend_bound", "MetricThreshold": "tma_backend_bound > 0.2", "MetricgroupNoGroup": "TopdownL1", - "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound", + "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound.", "ScaleUnit": "100%" }, { @@ -114,7 +114,7 @@ "MetricName": "tma_bad_speculation", "MetricThreshold": "tma_bad_speculation > 0.15", "MetricgroupNoGroup": "TopdownL1", - "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example", + "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.", "ScaleUnit": "100%" }, { @@ -125,7 +125,7 @@ "MetricName": "tma_branch_mispredicts", "MetricThreshold": "tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", "MetricgroupNoGroup": "TopdownL2", - "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction. These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: BR_MISP_RETIRED.ALL_BRANCHES", + "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction. These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_info_bad_spec_branch_misprediction_cost, tma_mispredicts_resteers", "ScaleUnit": "100%" }, { @@ -133,8 +133,8 @@ "MetricExpr": "12 * (BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT + BACLEARS.ANY) / tma_info_thread_clks", "MetricGroup": "FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group", "MetricName": "tma_branch_resteers", - "MetricThreshold": "tma_branch_resteers > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", - "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers. Branch Resteers estimates the Frontend delay in fetching operations from corrected path; following all sorts of miss-predicted branches. For example; branchy code with lots of miss-predictions might get categorized under Branch Resteers. Note the value of this node may overlap with its siblings. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_l3_hit_latency, tma_store_latency", + "MetricThreshold": "tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers. Branch Resteers estimates the Frontend delay in fetching operations from corrected path; following all sorts of miss-predicted branches. For example; branchy code with lots of miss-predictions might get categorized under Branch Resteers. Note the value of this node may overlap with its siblings. Sample with: BR_MISP_RETIRED.ALL_BRANCHES", "ScaleUnit": "100%" }, { @@ -143,8 +143,8 @@ "MetricExpr": "max(0, tma_microcode_sequencer - tma_assists)", "MetricGroup": "TopdownL4;tma_L4_group;tma_microcode_sequencer_group", "MetricName": "tma_cisc", - "MetricThreshold": "tma_cisc > 0.1 & tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1", - "PublicDescription": "This metric estimates fraction of cycles the CPU retired uops originated from CISC (complex instruction set computer) instruction. A CISC instruction has multiple uops that are required to perform the instruction's functionality as in the case of read-modify-write as an example. Since these instructions require multiple uops they may or may not imply sub-optimal use of machine resources", + "MetricThreshold": "tma_cisc > 0.1 & (tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1)", + "PublicDescription": "This metric estimates fraction of cycles the CPU retired uops originated from CISC (complex instruction set computer) instruction. A CISC instruction has multiple uops that are required to perform the instruction's functionality as in the case of read-modify-write as an example. Since these instructions require multiple uops they may or may not imply sub-optimal use of machine resources.", "ScaleUnit": "100%" }, { @@ -153,8 +153,8 @@ "MetricExpr": "(60 * (MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.L3_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_RETIRED.L3_MISS))) + 43 * (MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.L3_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_RETIRED.L3_MISS)))) / tma_info_thread_clks", "MetricGroup": "BvMS;DataSharing;LockCont;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group", "MetricName": "tma_contested_accesses", - "MetricThreshold": "tma_contested_accesses > 0.05 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", - "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses. Contested accesses occur when data written by one Logical Processor are read by another Logical Processor on a different Physical Core. Examples of contested accesses include synchronizations such as locks; true data sharing such as modified locked variables; and false sharing. Sample with: MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM, MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS. Related metrics: tma_data_sharing, tma_false_sharing, tma_machine_clears", + "MetricThreshold": "tma_contested_accesses > 0.05 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses. Contested accesses occur when data written by one Logical Processor are read by another Logical Processor on a different Physical Core. Examples of contested accesses include synchronizations such as locks; true data sharing such as modified locked variables; and false sharing. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM_PS;MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS_PS. Related metrics: tma_data_sharing, tma_false_sharing, tma_machine_clears, tma_remote_cache", "ScaleUnit": "100%" }, { @@ -165,7 +165,7 @@ "MetricName": "tma_core_bound", "MetricThreshold": "tma_core_bound > 0.1 & tma_backend_bound > 0.2", "MetricgroupNoGroup": "TopdownL2", - "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck. Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations)", + "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck. Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations).", "ScaleUnit": "100%" }, { @@ -174,8 +174,8 @@ "MetricExpr": "43 * (MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.L3_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_RETIRED.L3_MISS))) / tma_info_thread_clks", "MetricGroup": "BvMS;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group", "MetricName": "tma_data_sharing", - "MetricThreshold": "tma_data_sharing > 0.05 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", - "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses. Data shared by multiple Logical Processors (even just read shared) may cause increased access latency due to cache coherency. Excessive data sharing can drastically harm multithreaded performance. Sample with: MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT. Related metrics: tma_contested_accesses, tma_false_sharing, tma_machine_clears", + "MetricThreshold": "tma_data_sharing > 0.05 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses. Data shared by multiple Logical Processors (even just read shared) may cause increased access latency due to cache coherency. Excessive data sharing can drastically harm multithreaded performance. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_HIT_PS. Related metrics: tma_contested_accesses, tma_false_sharing, tma_machine_clears, tma_remote_cache", "ScaleUnit": "100%" }, { @@ -183,8 +183,8 @@ "MetricExpr": "10 * ARITH.DIVIDER_UOPS / tma_info_core_core_clks", "MetricGroup": "BvCB;TopdownL3;tma_L3_group;tma_core_bound_group", "MetricName": "tma_divider", - "MetricThreshold": "tma_divider > 0.2 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", - "PublicDescription": "This metric represents fraction of cycles where the Divider unit was active. Divide and square root instructions are performed by the Divider unit and can take considerably longer latency than integer or Floating Point addition; subtraction; or multiplication. Sample with: ARITH.DIVIDER_UOPS", + "MetricThreshold": "tma_divider > 0.2 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)", + "PublicDescription": "This metric represents fraction of cycles where the Divider unit was active. Divide and square root instructions are performed by the Divider unit and can take considerably longer latency than integer or Floating Point addition; subtraction; or multiplication. Sample with: ARITH.DIVIDER_ACTIVE", "ScaleUnit": "100%" }, { @@ -193,8 +193,8 @@ "MetricExpr": "(1 - MEM_LOAD_UOPS_RETIRED.L3_HIT / (MEM_LOAD_UOPS_RETIRED.L3_HIT + 7 * MEM_LOAD_UOPS_RETIRED.L3_MISS)) * CYCLE_ACTIVITY.STALLS_L2_PENDING / tma_info_thread_clks", "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_dram_bound", - "MetricThreshold": "tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", - "PublicDescription": "This metric estimates how often the CPU was stalled on accesses to external memory (DRAM) by loads. Better caching can improve the latency and increase performance. Sample with: MEM_LOAD_UOPS_RETIRED.L3_MISS", + "MetricThreshold": "tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", + "PublicDescription": "This metric estimates how often the CPU was stalled on accesses to external memory (DRAM) by loads. Better caching can improve the latency and increase performance. Sample with: MEM_LOAD_UOPS_RETIRED.L3_MISS_PS", "ScaleUnit": "100%" }, { @@ -203,7 +203,7 @@ "MetricGroup": "DSB;FetchBW;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group", "MetricName": "tma_dsb", "MetricThreshold": "tma_dsb > 0.15 & tma_fetch_bandwidth > 0.2", - "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to DSB (decoded uop cache) fetch pipeline. For example; inefficient utilization of the DSB cache structure or bank conflict when reading from it; are categorized here", + "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to DSB (decoded uop cache) fetch pipeline. For example; inefficient utilization of the DSB cache structure or bank conflict when reading from it; are categorized here.", "ScaleUnit": "100%" }, { @@ -211,7 +211,7 @@ "MetricExpr": "DSB2MITE_SWITCHES.PENALTY_CYCLES / tma_info_thread_clks", "MetricGroup": "DSBmiss;FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueFB", "MetricName": "tma_dsb_switches", - "MetricThreshold": "tma_dsb_switches > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricThreshold": "tma_dsb_switches > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines. The DSB (decoded i-cache) is a Uop Cache where the front-end directly delivers Uops (micro operations) avoiding heavy x86 decoding. The DSB pipeline has shorter latency and delivered higher bandwidth than the MITE (legacy instruction decode pipeline). Switching between the two pipelines can cause penalties hence this metric measures the exposed penalty. Related metrics: tma_fetch_bandwidth, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp", "ScaleUnit": "100%" }, @@ -220,8 +220,8 @@ "MetricExpr": "(8 * DTLB_LOAD_MISSES.STLB_HIT + DTLB_LOAD_MISSES.WALK_DURATION) / tma_info_thread_clks", "MetricGroup": "BvMT;MemoryTLB;TopdownL4;tma_L4_group;tma_issueTLB;tma_l1_bound_group", "MetricName": "tma_dtlb_load", - "MetricThreshold": "tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", - "PublicDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses. TLBs (Translation Look-aside Buffers) are processor caches for recently used entries out of the Page Tables that are used to map virtual- to physical-addresses by the operating system. This metric approximates the potential delay of demand loads missing the first-level data TLB (assuming worst case scenario with back to back misses to different pages). This includes hitting in the second-level TLB (STLB) as well as performing a hardware page walk on an STLB miss. Sample with: MEM_UOPS_RETIRED.STLB_MISS_LOADS. Related metrics: tma_dtlb_store", + "MetricThreshold": "tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses. TLBs (Translation Look-aside Buffers) are processor caches for recently used entries out of the Page Tables that are used to map virtual- to physical-addresses by the operating system. This metric approximates the potential delay of demand loads missing the first-level data TLB (assuming worst case scenario with back to back misses to different pages). This includes hitting in the second-level TLB (STLB) as well as performing a hardware page walk on an STLB miss. Sample with: MEM_UOPS_RETIRED.STLB_MISS_LOADS_PS. Related metrics: tma_dtlb_store", "ScaleUnit": "100%" }, { @@ -229,8 +229,8 @@ "MetricExpr": "(8 * DTLB_STORE_MISSES.STLB_HIT + DTLB_STORE_MISSES.WALK_DURATION) / tma_info_thread_clks", "MetricGroup": "BvMT;MemoryTLB;TopdownL4;tma_L4_group;tma_issueTLB;tma_store_bound_group", "MetricName": "tma_dtlb_store", - "MetricThreshold": "tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", - "PublicDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses. As with ordinary data caching; focus on improving data locality and reducing working-set size to reduce DTLB overhead. Additionally; consider using profile-guided optimization (PGO) to collocate frequently-used data on the same page. Try using larger page sizes for large amounts of frequently-used data. Sample with: MEM_UOPS_RETIRED.STLB_MISS_STORES. Related metrics: tma_dtlb_load", + "MetricThreshold": "tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses. As with ordinary data caching; focus on improving data locality and reducing working-set size to reduce DTLB overhead. Additionally; consider using profile-guided optimization (PGO) to collocate frequently-used data on the same page. Try using larger page sizes for large amounts of frequently-used data. Sample with: MEM_UOPS_RETIRED.STLB_MISS_STORES_PS. Related metrics: tma_dtlb_load", "ScaleUnit": "100%" }, { @@ -238,18 +238,18 @@ "MetricExpr": "60 * OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.HITM_OTHER_CORE / tma_info_thread_clks", "MetricGroup": "BvMS;DataSharing;LockCont;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_store_bound_group", "MetricName": "tma_false_sharing", - "MetricThreshold": "tma_false_sharing > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", - "PublicDescription": "This metric roughly estimates how often CPU was handling synchronizations due to False Sharing. False Sharing is a multithreading hiccup; where multiple Logical Processors contend on different data-elements mapped into the same cache line. Sample with: MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM, OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.HITM_OTHER_CORE. Related metrics: tma_contested_accesses, tma_data_sharing, tma_machine_clears", + "MetricThreshold": "tma_false_sharing > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric roughly estimates how often CPU was handling synchronizations due to False Sharing. False Sharing is a multithreading hiccup; where multiple Logical Processors contend on different data-elements mapped into the same cache line. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM_PS;OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.SNOOP_HITM. Related metrics: tma_contested_accesses, tma_data_sharing, tma_machine_clears, tma_remote_cache", "ScaleUnit": "100%" }, { "BriefDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed", "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "tma_info_memory_load_miss_real_latency * cpu@L1D_PEND_MISS.REQUEST_FB_FULL\\,cmask\\=0x1@ / tma_info_thread_clks", + "MetricExpr": "tma_info_memory_load_miss_real_latency * cpu@L1D_PEND_MISS.REQUEST_FB_FULL\\,cmask\\=1@ / tma_info_thread_clks", "MetricGroup": "BvMB;MemoryBW;TopdownL4;tma_L4_group;tma_issueBW;tma_issueSL;tma_issueSmSt;tma_l1_bound_group", "MetricName": "tma_fb_full", "MetricThreshold": "tma_fb_full > 0.3", - "PublicDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed. The higher the metric value; the deeper the memory hierarchy level the misses are satisfied from (metric values >1 are valid). Often it hints on approaching bandwidth limits (to L2 cache; L3 cache or external memory). Related metrics: tma_info_system_dram_bw_use, tma_mem_bandwidth, tma_sq_full, tma_store_latency", + "PublicDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed. The higher the metric value; the deeper the memory hierarchy level the misses are satisfied from (metric values >1 are valid). Often it hints on approaching bandwidth limits (to L2 cache; L3 cache or external memory). Related metrics: tma_info_system_dram_bw_use, tma_mem_bandwidth, tma_sq_full, tma_store_latency, tma_streaming_stores", "ScaleUnit": "100%" }, { @@ -279,33 +279,33 @@ "MetricName": "tma_frontend_bound", "MetricThreshold": "tma_frontend_bound > 0.15", "MetricgroupNoGroup": "TopdownL1", - "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound", + "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound.", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations , instructions that require two or more uops or micro-coded sequences", + "BriefDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences", "MetricExpr": "tma_microcode_sequencer", "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_heavy_operations", "MetricThreshold": "tma_heavy_operations > 0.1", "MetricgroupNoGroup": "TopdownL2", - "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations , instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences.([ICL+] Note this may overcount due to approximation using indirect events; [ADL+])", + "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences.([ICL+] Note this may overcount due to approximation using indirect events; [ADL+])", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to instruction cache misses", + "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to instruction cache misses.", "MetricExpr": "ICACHE.IFDATA_STALL / tma_info_thread_clks", "MetricGroup": "BigFootprint;BvBC;FetchLat;IcMiss;TopdownL3;tma_L3_group;tma_fetch_latency_group", "MetricName": "tma_icache_misses", - "MetricThreshold": "tma_icache_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricThreshold": "tma_icache_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", "ScaleUnit": "100%" }, { - "BriefDescription": "Instructions per retired Mispredicts for indirect CALL or JMP branches (lower number means higher occurrence rate)", + "BriefDescription": "Instructions per retired Mispredicts for indirect CALL or JMP branches (lower number means higher occurrence rate).", "MetricExpr": "tma_info_inst_mix_instructions / (UOPS_RETIRED.RETIRE_SLOTS / UOPS_ISSUED.ANY * BR_MISP_EXEC.INDIRECT)", "MetricGroup": "Bad;BrMispredicts", "MetricName": "tma_info_bad_spec_ipmisp_indirect", - "MetricThreshold": "tma_info_bad_spec_ipmisp_indirect < 1000" + "MetricThreshold": "tma_info_bad_spec_ipmisp_indirect < 1e3" }, { "BriefDescription": "Number of Instructions per non-speculative Branch Misprediction (JEClear) (lower number means higher occurrence rate)", @@ -316,7 +316,7 @@ }, { "BriefDescription": "Core actual clocks when any Logical Processor is active on the Physical Core", - "MetricExpr": "(CPU_CLK_UNHALTED.THREAD_ANY / 2 if #SMT_on else tma_info_thread_clks)", + "MetricExpr": "(CPU_CLK_UNHALTED.THREAD / 2 * (1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK) if #core_wide < 1 else (CPU_CLK_UNHALTED.THREAD_ANY / 2 if #SMT_on else tma_info_thread_clks))", "MetricGroup": "SMT", "MetricName": "tma_info_core_core_clks" }, @@ -328,7 +328,7 @@ }, { "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is execution) per thread (logical-processor)", - "MetricExpr": "(UOPS_EXECUTED.CORE / 2 / (cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x1@ / 2 if #SMT_on else cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x1@) if #SMT_on else UOPS_EXECUTED.CORE / (cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x1@ / 2 if #SMT_on else cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x1@))", + "MetricExpr": "(UOPS_EXECUTED.CORE / 2 / (cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ / 2 if #SMT_on else cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@) if #SMT_on else UOPS_EXECUTED.CORE / (cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ / 2 if #SMT_on else cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@))", "MetricGroup": "Backend;Cor;Pipeline;PortsUtil", "MetricName": "tma_info_core_ilp" }, @@ -353,7 +353,7 @@ "MetricName": "tma_info_frontend_tbpc" }, { - "BriefDescription": "Branch instructions per taken branch", + "BriefDescription": "Branch instructions per taken branch.", "MetricExpr": "BR_INST_RETIRED.ALL_BRANCHES / BR_INST_RETIRED.NEAR_TAKEN", "MetricGroup": "Branches;Fed;PGO", "MetricName": "tma_info_inst_mix_bptkbranch" @@ -398,7 +398,7 @@ "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_TAKEN", "MetricGroup": "Branches;Fed;FetchBW;Frontend;PGO;tma_issueFB", "MetricName": "tma_info_inst_mix_iptb", - "MetricThreshold": "tma_info_inst_mix_iptb < 4 * 2 + 1", + "MetricThreshold": "tma_info_inst_mix_iptb < 9", "PublicDescription": "Instructions per taken branch. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_frontend_dsb_coverage, tma_lcp" }, { @@ -502,8 +502,8 @@ "MetricThreshold": "tma_info_memory_tlb_page_walks_utilization > 0.5" }, { - "BriefDescription": "Average number of Uops retired in cycles where at least one uop has retired", - "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / cpu@UOPS_RETIRED.RETIRE_SLOTS\\,cmask\\=0x1@", + "BriefDescription": "Average number of Uops retired in cycles where at least one uop has retired.", + "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / cpu@UOPS_RETIRED.RETIRE_SLOTS\\,cmask\\=1@", "MetricGroup": "Pipeline;Ret", "MetricName": "tma_info_pipeline_retire" }, @@ -537,14 +537,13 @@ "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.FAR_BRANCH:u", "MetricGroup": "Branches;OS", "MetricName": "tma_info_system_ipfarbranch", - "MetricThreshold": "tma_info_system_ipfarbranch < 1000000" + "MetricThreshold": "tma_info_system_ipfarbranch < 1e6" }, { "BriefDescription": "Cycles Per Instruction for the Operating System (OS) Kernel mode", "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P:k / INST_RETIRED.ANY_P:k", "MetricGroup": "OS", - "MetricName": "tma_info_system_kernel_cpi", - "ScaleUnit": "1per_instr" + "MetricName": "tma_info_system_kernel_cpi" }, { "BriefDescription": "Fraction of cycles spent in the Operating System (OS) Kernel mode", @@ -592,7 +591,7 @@ "MetricName": "tma_info_system_turbo_utilization" }, { - "BriefDescription": "Per-Logical Processor actual clocks when the Logical Processor is active", + "BriefDescription": "Per-Logical Processor actual clocks when the Logical Processor is active.", "MetricExpr": "CPU_CLK_UNHALTED.THREAD", "MetricGroup": "Pipeline", "MetricName": "tma_info_thread_clks" @@ -601,8 +600,7 @@ "BriefDescription": "Cycles Per Instruction (per Logical Processor)", "MetricExpr": "1 / tma_info_thread_ipc", "MetricGroup": "Mem;Pipeline", - "MetricName": "tma_info_thread_cpi", - "ScaleUnit": "1per_instr" + "MetricName": "tma_info_thread_cpi" }, { "BriefDescription": "Instructions Per Cycle (per Logical Processor)", @@ -628,14 +626,14 @@ "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / BR_INST_RETIRED.NEAR_TAKEN", "MetricGroup": "Branches;Fed;FetchBW", "MetricName": "tma_info_thread_uptb", - "MetricThreshold": "tma_info_thread_uptb < 4 * 1.5" + "MetricThreshold": "tma_info_thread_uptb < 6" }, { "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to Instruction TLB (ITLB) misses", "MetricExpr": "(14 * ITLB_MISSES.STLB_HIT + ITLB_MISSES.WALK_DURATION) / tma_info_thread_clks", "MetricGroup": "BigFootprint;BvBC;FetchLat;MemoryTLB;TopdownL3;tma_L3_group;tma_fetch_latency_group", "MetricName": "tma_itlb_misses", - "MetricThreshold": "tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricThreshold": "tma_itlb_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Instruction TLB (ITLB) misses. Sample with: ITLB_MISSES.WALK_COMPLETED", "ScaleUnit": "100%" }, @@ -644,8 +642,8 @@ "MetricExpr": "max((min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.STALLS_LDM_PENDING) - CYCLE_ACTIVITY.STALLS_L1D_PENDING) / tma_info_thread_clks, 0)", "MetricGroup": "CacheHits;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_issueL1;tma_issueMC;tma_memory_bound_group", "MetricName": "tma_l1_bound", - "MetricThreshold": "tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", - "PublicDescription": "This metric estimates how often the CPU was stalled without loads missing the L1 Data (L1D) cache. The L1D cache typically has the shortest latency. However; in certain cases like loads blocked on older stores; a load might suffer due to high latency even though it is being satisfied by the L1D. Another example is loads who miss in the TLB. These cases are characterized by execution unit stalls; while some non-completed demand load lives in the machine without having that demand load missing the L1 cache. Sample with: MEM_LOAD_UOPS_RETIRED.L1_HIT. Related metrics: tma_machine_clears, tma_microcode_sequencer, tma_ms_switches, tma_ports_utilized_1", + "MetricThreshold": "tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", + "PublicDescription": "This metric estimates how often the CPU was stalled without loads missing the L1 Data (L1D) cache. The L1D cache typically has the shortest latency. However; in certain cases like loads blocked on older stores; a load might suffer due to high latency even though it is being satisfied by the L1D. Another example is loads who miss in the TLB. These cases are characterized by execution unit stalls; while some non-completed demand load lives in the machine without having that demand load missing the L1 cache. Sample with: MEM_LOAD_UOPS_RETIRED.L1_HIT_PS. Related metrics: tma_clears_resteers, tma_machine_clears, tma_microcode_sequencer, tma_ms_switches, tma_ports_utilized_1", "ScaleUnit": "100%" }, { @@ -653,8 +651,8 @@ "MetricExpr": "(CYCLE_ACTIVITY.STALLS_L1D_PENDING - CYCLE_ACTIVITY.STALLS_L2_PENDING) / tma_info_thread_clks", "MetricGroup": "BvML;CacheHits;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_l2_bound", - "MetricThreshold": "tma_l2_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", - "PublicDescription": "This metric estimates how often the CPU was stalled due to L2 cache accesses by loads. Avoiding cache misses (i.e. L1 misses/L2 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_UOPS_RETIRED.L2_HIT", + "MetricThreshold": "tma_l2_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", + "PublicDescription": "This metric estimates how often the CPU was stalled due to L2 cache accesses by loads. Avoiding cache misses (i.e. L1 misses/L2 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_UOPS_RETIRED.L2_HIT_PS", "ScaleUnit": "100%" }, { @@ -663,8 +661,8 @@ "MetricExpr": "MEM_LOAD_UOPS_RETIRED.L3_HIT / (MEM_LOAD_UOPS_RETIRED.L3_HIT + 7 * MEM_LOAD_UOPS_RETIRED.L3_MISS) * CYCLE_ACTIVITY.STALLS_L2_PENDING / tma_info_thread_clks", "MetricGroup": "CacheHits;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_l3_bound", - "MetricThreshold": "tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", - "PublicDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core. Avoiding cache misses (i.e. L2 misses/L3 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_UOPS_RETIRED.L3_HIT", + "MetricThreshold": "tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", + "PublicDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core. Avoiding cache misses (i.e. L2 misses/L3 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_UOPS_RETIRED.L3_HIT_PS", "ScaleUnit": "100%" }, { @@ -673,8 +671,8 @@ "MetricExpr": "29 * (MEM_LOAD_UOPS_RETIRED.L3_HIT * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.L3_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_RETIRED.L3_MISS))) / tma_info_thread_clks", "MetricGroup": "BvML;MemoryLat;TopdownL4;tma_L4_group;tma_issueLat;tma_l3_bound_group", "MetricName": "tma_l3_hit_latency", - "MetricThreshold": "tma_l3_hit_latency > 0.1 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", - "PublicDescription": "This metric estimates fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited). Avoiding private cache misses (i.e. L2 misses/L3 hits) will improve the latency; reduce contention with sibling physical cores and increase performance. Note the value of this node may overlap with its siblings. Sample with: MEM_LOAD_UOPS_RETIRED.L3_HIT. Related metrics: tma_branch_resteers, tma_mem_latency, tma_store_latency", + "MetricThreshold": "tma_l3_hit_latency > 0.1 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric estimates fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited). Avoiding private cache misses (i.e. L2 misses/L3 hits) will improve the latency; reduce contention with sibling physical cores and increase performance. Note the value of this node may overlap with its siblings. Sample with: MEM_LOAD_UOPS_RETIRED.L3_HIT_PS. Related metrics: tma_mem_latency", "ScaleUnit": "100%" }, { @@ -682,18 +680,18 @@ "MetricExpr": "ILD_STALL.LCP / tma_info_thread_clks", "MetricGroup": "FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueFB", "MetricName": "tma_lcp", - "MetricThreshold": "tma_lcp > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", - "PublicDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs). Using proper compiler flags or Intel Compiler by default will certainly avoid this. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb", + "MetricThreshold": "tma_lcp > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", + "PublicDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs). Using proper compiler flags or Intel Compiler by default will certainly avoid this. #Link: Optimization Guide about LCP BKMs. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations , instructions that require no more than one uop (micro-operation)", + "BriefDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation)", "MetricExpr": "tma_retiring - tma_heavy_operations", "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_light_operations", "MetricThreshold": "tma_light_operations > 0.6", "MetricgroupNoGroup": "TopdownL2", - "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations , instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized code running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. ([ICL+] Note this may undercount due to approximation using indirect events; [ADL+] .). Sample with: INST_RETIRED.PREC_DIST", + "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized code running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. ([ICL+] Note this may undercount due to approximation using indirect events; [ADL+] .). Sample with: INST_RETIRED.PREC_DIST", "ScaleUnit": "100%" }, { @@ -712,8 +710,8 @@ "MetricExpr": "MEM_UOPS_RETIRED.LOCK_LOADS / MEM_UOPS_RETIRED.ALL_STORES * min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO) / tma_info_thread_clks", "MetricGroup": "LockCont;Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_l1_bound_group", "MetricName": "tma_lock_latency", - "MetricThreshold": "tma_lock_latency > 0.2 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", - "PublicDescription": "This metric represents fraction of cycles the CPU spent handling cache misses due to lock operations. Due to the microarchitecture handling of locks; they are classified as L1_Bound regardless of what memory source satisfied them. Sample with: MEM_UOPS_RETIRED.LOCK_LOADS. Related metrics: tma_store_latency", + "MetricThreshold": "tma_lock_latency > 0.2 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric represents fraction of cycles the CPU spent handling cache misses due to lock operations. Due to the microarchitecture handling of locks; they are classified as L1_Bound regardless of what memory source satisfied them. Sample with: MEM_UOPS_RETIRED.LOCK_LOADS_PS. Related metrics: tma_store_latency", "ScaleUnit": "100%" }, { @@ -724,15 +722,15 @@ "MetricName": "tma_machine_clears", "MetricThreshold": "tma_machine_clears > 0.1 & tma_bad_speculation > 0.15", "MetricgroupNoGroup": "TopdownL2", - "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears. These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT. Related metrics: tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_l1_bound, tma_microcode_sequencer, tma_ms_switches", + "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears. These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT. Related metrics: tma_clears_resteers, tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_l1_bound, tma_microcode_sequencer, tma_ms_switches, tma_remote_cache", "ScaleUnit": "100%" }, { "BriefDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory - DRAM ([SPR-HBM] and/or HBM)", - "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, cpu@OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD\\,cmask\\=0x6@) / tma_info_thread_clks", + "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, cpu@OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD\\,cmask\\=6@) / tma_info_thread_clks", "MetricGroup": "BvMB;MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueBW", "MetricName": "tma_mem_bandwidth", - "MetricThreshold": "tma_mem_bandwidth > 0.2 & tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_mem_bandwidth > 0.2 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", "PublicDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory - DRAM ([SPR-HBM] and/or HBM). The underlying heuristic assumes that a similar off-core traffic is generated by all IA cores. This metric does not aggregate non-data-read requests by this logical processor; requests from other IA Logical Processors/Physical Cores/sockets; or other non-IA devices like GPU; hence the maximum external memory bandwidth limits may or may not be approached when this metric is flagged (see Uncore counters for that). Related metrics: tma_fb_full, tma_info_system_dram_bw_use, tma_sq_full", "ScaleUnit": "100%" }, @@ -741,19 +739,19 @@ "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD) / tma_info_thread_clks - tma_mem_bandwidth", "MetricGroup": "BvML;MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueLat", "MetricName": "tma_mem_latency", - "MetricThreshold": "tma_mem_latency > 0.1 & tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_mem_latency > 0.1 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", "PublicDescription": "This metric estimates fraction of cycles where the performance was likely hurt due to latency from external memory - DRAM ([SPR-HBM] and/or HBM). This metric does not aggregate requests from other Logical Processors/Physical Cores/sockets (see Uncore counters for that). Related metrics: tma_l3_hit_latency", "ScaleUnit": "100%" }, { "BriefDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck", "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "(min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.STALLS_LDM_PENDING) + RESOURCE_STALLS.SB) / (min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.CYCLES_NO_EXECUTE) + (cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x1@ - (cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x3@ if tma_info_thread_ipc > 1.8 else cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x2@)) / 2 - (RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else 0) + RESOURCE_STALLS.SB if #SMT_on else min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.CYCLES_NO_EXECUTE) + cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x1@ - (cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x3@ if tma_info_thread_ipc > 1.8 else cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x2@) - (RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else 0) + RESOURCE_STALLS.SB) * tma_backend_bound", + "MetricExpr": "((min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.STALLS_LDM_PENDING) + RESOURCE_STALLS.SB) / (min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.CYCLES_NO_EXECUTE) + (cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ - (cpu@UOPS_EXECUTED.CORE\\,cmask\\=3@ if tma_info_thread_ipc > 1.8 else cpu@UOPS_EXECUTED.CORE\\,cmask\\=2@)) / 2 - (RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else 0) + RESOURCE_STALLS.SB) if #SMT_on else min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.CYCLES_NO_EXECUTE) + cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ - (cpu@UOPS_EXECUTED.CORE\\,cmask\\=3@ if tma_info_thread_ipc > 1.8 else cpu@UOPS_EXECUTED.CORE\\,cmask\\=2@) - (RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else 0) + RESOURCE_STALLS.SB) * tma_backend_bound", "MetricGroup": "Backend;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_memory_bound", "MetricThreshold": "tma_memory_bound > 0.2 & tma_backend_bound > 0.2", "MetricgroupNoGroup": "TopdownL2", - "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck. Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two)", + "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck. Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two).", "ScaleUnit": "100%" }, { @@ -762,7 +760,7 @@ "MetricGroup": "MicroSeq;TopdownL3;tma_L3_group;tma_heavy_operations_group;tma_issueMC;tma_issueMS", "MetricName": "tma_microcode_sequencer", "MetricThreshold": "tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1", - "PublicDescription": "This metric represents fraction of slots the CPU was retiring uops fetched by the Microcode Sequencer (MS) unit. The MS is used for CISC instructions not supported by the default decoders (like repeat move strings; or CPUID); or by microcode assists used to address some operation modes (like in Floating Point assists). These cases can often be avoided. Sample with: IDQ.MS_UOPS. Related metrics: tma_l1_bound, tma_machine_clears, tma_ms_switches", + "PublicDescription": "This metric represents fraction of slots the CPU was retiring uops fetched by the Microcode Sequencer (MS) unit. The MS is used for CISC instructions not supported by the default decoders (like repeat move strings; or CPUID); or by microcode assists used to address some operation modes (like in Floating Point assists). These cases can often be avoided. Sample with: IDQ.MS_UOPS. Related metrics: tma_clears_resteers, tma_l1_bound, tma_machine_clears, tma_ms_switches", "ScaleUnit": "100%" }, { @@ -771,7 +769,7 @@ "MetricGroup": "DSBmiss;FetchBW;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group", "MetricName": "tma_mite", "MetricThreshold": "tma_mite > 0.1 & tma_fetch_bandwidth > 0.2", - "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to the MITE pipeline (the legacy decode pipeline). This pipeline is used for code that was not pre-cached in the DSB or LSD. For example; inefficiencies due to asymmetric decoders; use of long immediate or LCP can manifest as MITE fetch bandwidth bottleneck", + "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to the MITE pipeline (the legacy decode pipeline). This pipeline is used for code that was not pre-cached in the DSB or LSD. For example; inefficiencies due to asymmetric decoders; use of long immediate or LCP can manifest as MITE fetch bandwidth bottleneck.", "ScaleUnit": "100%" }, { @@ -779,8 +777,8 @@ "MetricExpr": "2 * IDQ.MS_SWITCHES / tma_info_thread_clks", "MetricGroup": "FetchLat;MicroSeq;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueMC;tma_issueMS;tma_issueMV;tma_issueSO", "MetricName": "tma_ms_switches", - "MetricThreshold": "tma_ms_switches > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", - "PublicDescription": "This metric estimates the fraction of cycles when the CPU was stalled due to switches of uop delivery to the Microcode Sequencer (MS). Commonly used instructions are optimized for delivery by the DSB (decoded i-cache) or MITE (legacy instruction decode) pipelines. Certain operations cannot be handled natively by the execution pipeline; and must be performed by microcode (small programs injected into the execution stream). Switching to the MS too often can negatively impact performance. The MS is designated to deliver long uop flows required by CISC instructions like CPUID; or uncommon conditions like Floating Point Assists when dealing with Denormals. Sample with: IDQ.MS_SWITCHES. Related metrics: tma_l1_bound, tma_machine_clears, tma_microcode_sequencer", + "MetricThreshold": "tma_ms_switches > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", + "PublicDescription": "This metric estimates the fraction of cycles when the CPU was stalled due to switches of uop delivery to the Microcode Sequencer (MS). Commonly used instructions are optimized for delivery by the DSB (decoded i-cache) or MITE (legacy instruction decode) pipelines. Certain operations cannot be handled natively by the execution pipeline; and must be performed by microcode (small programs injected into the execution stream). Switching to the MS too often can negatively impact performance. The MS is designated to deliver long uop flows required by CISC instructions like CPUID; or uncommon conditions like Floating Point Assists when dealing with Denormals. Sample with: IDQ.MS_SWITCHES. Related metrics: tma_clears_resteers, tma_l1_bound, tma_machine_clears, tma_microcode_sequencer, tma_mixing_vectors, tma_serializing_operation", "ScaleUnit": "100%" }, { @@ -789,7 +787,7 @@ "MetricGroup": "Compute;TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P", "MetricName": "tma_port_0", "MetricThreshold": "tma_port_0 > 0.6", - "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 0 ([SNB+] ALU; [HSW+] ALU and 2nd branch). Sample with: UOPS_DISPATCHED_PORT.PORT_0. Related metrics: tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", + "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 0 ([SNB+] ALU; [HSW+] ALU and 2nd branch). Sample with: UOPS_DISPATCHED.PORT_0. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%" }, { @@ -798,7 +796,7 @@ "MetricGroup": "TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P", "MetricName": "tma_port_1", "MetricThreshold": "tma_port_1 > 0.6", - "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 1 (ALU). Sample with: UOPS_DISPATCHED_PORT.PORT_1. Related metrics: tma_port_0, tma_port_5, tma_port_6, tma_ports_utilized_2", + "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 1 (ALU). Sample with: UOPS_DISPATCHED.PORT_1. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_5, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%" }, { @@ -834,7 +832,7 @@ "MetricGroup": "TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P", "MetricName": "tma_port_5", "MetricThreshold": "tma_port_5 > 0.6", - "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 5 ([SNB+] Branches and ALU; [HSW+] ALU). Sample with: UOPS_DISPATCHED_PORT.PORT_5. Related metrics: tma_port_0, tma_port_1, tma_port_6, tma_ports_utilized_2", + "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 5 ([SNB+] Branches and ALU; [HSW+] ALU). Sample with: UOPS_DISPATCHED.PORT_5. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%" }, { @@ -843,7 +841,7 @@ "MetricGroup": "TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P", "MetricName": "tma_port_6", "MetricThreshold": "tma_port_6 > 0.6", - "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 6 ([HSW+] Primary Branch and simple ALU). Sample with: UOPS_DISPATCHED_PORT.PORT_1. Related metrics: tma_port_0, tma_port_1, tma_port_5, tma_ports_utilized_2", + "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 6 ([HSW+] Primary Branch and simple ALU). Sample with: UOPS_DISPATCHED.PORT_1. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_ports_utilized_2", "ScaleUnit": "100%" }, { @@ -858,46 +856,46 @@ { "BriefDescription": "This metric estimates fraction of cycles the CPU performance was potentially limited due to Core computation issues (non divider-related)", "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "((min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.CYCLES_NO_EXECUTE) + (cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x1@ - (cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x3@ if tma_info_thread_ipc > 1.8 else cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x2@)) / 2 - (RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else 0) + RESOURCE_STALLS.SB if #SMT_on else min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.CYCLES_NO_EXECUTE) + cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x1@ - (cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x3@ if tma_info_thread_ipc > 1.8 else cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x2@) - (RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else 0) + RESOURCE_STALLS.SB) - RESOURCE_STALLS.SB - min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.STALLS_LDM_PENDING)) / tma_info_thread_clks", + "MetricExpr": "(min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.CYCLES_NO_EXECUTE) + (cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ - (cpu@UOPS_EXECUTED.CORE\\,cmask\\=3@ if tma_info_thread_ipc > 1.8 else cpu@UOPS_EXECUTED.CORE\\,cmask\\=2@)) / 2 - (RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else 0) + RESOURCE_STALLS.SB if #SMT_on else min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.CYCLES_NO_EXECUTE) + cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ - (cpu@UOPS_EXECUTED.CORE\\,cmask\\=3@ if tma_info_thread_ipc > 1.8 else cpu@UOPS_EXECUTED.CORE\\,cmask\\=2@) - (RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else 0) + RESOURCE_STALLS.SB - RESOURCE_STALLS.SB - min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.STALLS_LDM_PENDING)) / tma_info_thread_clks", "MetricGroup": "PortsUtil;TopdownL3;tma_L3_group;tma_core_bound_group", "MetricName": "tma_ports_utilization", - "MetricThreshold": "tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", - "PublicDescription": "This metric estimates fraction of cycles the CPU performance was potentially limited due to Core computation issues (non divider-related). Two distinct categories can be attributed into this metric: (1) heavy data-dependency among contiguous instructions would manifest in this metric - such cases are often referred to as low Instruction Level Parallelism (ILP). (2) Contention on some hardware execution unit other than Divider. For example; when there are too many multiply operations", + "MetricThreshold": "tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)", + "PublicDescription": "This metric estimates fraction of cycles the CPU performance was potentially limited due to Core computation issues (non divider-related). Two distinct categories can be attributed into this metric: (1) heavy data-dependency among contiguous instructions would manifest in this metric - such cases are often referred to as low Instruction Level Parallelism (ILP). (2) Contention on some hardware execution unit other than Divider. For example; when there are too many multiply operations.", "ScaleUnit": "100%" }, { "BriefDescription": "This metric represents fraction of cycles CPU executed no uops on any execution port (Logical Processor cycles since ICL, Physical Core cycles otherwise)", - "MetricExpr": "(cpu@UOPS_EXECUTED.CORE\\,inv\\=0x1\\,cmask\\=0x1@ / 2 if #SMT_on else min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.CYCLES_NO_EXECUTE) - (RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else 0)) / tma_info_core_core_clks", + "MetricExpr": "(cpu@UOPS_EXECUTED.CORE\\,inv\\,cmask\\=1@ / 2 if #SMT_on else (min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.CYCLES_NO_EXECUTE) - (RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else 0)) / tma_info_core_core_clks)", "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group", "MetricName": "tma_ports_utilized_0", - "MetricThreshold": "tma_ports_utilized_0 > 0.2 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", - "PublicDescription": "This metric represents fraction of cycles CPU executed no uops on any execution port (Logical Processor cycles since ICL, Physical Core cycles otherwise). Long-latency instructions like divides may contribute to this metric", + "MetricThreshold": "tma_ports_utilized_0 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric represents fraction of cycles CPU executed no uops on any execution port (Logical Processor cycles since ICL, Physical Core cycles otherwise). Long-latency instructions like divides may contribute to this metric.", "ScaleUnit": "100%" }, { "BriefDescription": "This metric represents fraction of cycles where the CPU executed total of 1 uop per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise)", - "MetricExpr": "((cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x1@ - cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x2@) / 2 if #SMT_on else cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x1@ - cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x2@) / tma_info_core_core_clks", + "MetricExpr": "((cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ - cpu@UOPS_EXECUTED.CORE\\,cmask\\=2@) / 2 if #SMT_on else (cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ - cpu@UOPS_EXECUTED.CORE\\,cmask\\=2@) / tma_info_core_core_clks)", "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_issueL1;tma_ports_utilization_group", "MetricName": "tma_ports_utilized_1", - "MetricThreshold": "tma_ports_utilized_1 > 0.2 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_ports_utilized_1 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", "PublicDescription": "This metric represents fraction of cycles where the CPU executed total of 1 uop per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise). This can be due to heavy data-dependency among software instructions; or over oversubscribing a particular hardware resource. In some other cases with high 1_Port_Utilized and L1_Bound; this metric can point to L1 data-cache latency bottleneck that may not necessarily manifest with complete execution starvation (due to the short L1 latency e.g. walking a linked list) - looking at the assembly can be helpful. Related metrics: tma_l1_bound", "ScaleUnit": "100%" }, { "BriefDescription": "This metric represents fraction of cycles CPU executed total of 2 uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise)", - "MetricExpr": "((cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x2@ - cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x3@) / 2 if #SMT_on else cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x2@ - cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x3@) / tma_info_core_core_clks", + "MetricExpr": "((cpu@UOPS_EXECUTED.CORE\\,cmask\\=2@ - cpu@UOPS_EXECUTED.CORE\\,cmask\\=3@) / 2 if #SMT_on else (cpu@UOPS_EXECUTED.CORE\\,cmask\\=2@ - cpu@UOPS_EXECUTED.CORE\\,cmask\\=3@) / tma_info_core_core_clks)", "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_issue2P;tma_ports_utilization_group", "MetricName": "tma_ports_utilized_2", - "MetricThreshold": "tma_ports_utilized_2 > 0.15 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", - "PublicDescription": "This metric represents fraction of cycles CPU executed total of 2 uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise). Loop Vectorization -most compilers feature auto-Vectorization options today- reduces pressure on the execution ports as multiple elements are calculated with same uop. Related metrics: tma_port_0, tma_port_1, tma_port_5, tma_port_6", + "MetricThreshold": "tma_ports_utilized_2 > 0.15 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric represents fraction of cycles CPU executed total of 2 uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise). Loop Vectorization -most compilers feature auto-Vectorization options today- reduces pressure on the execution ports as multiple elements are calculated with same uop. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of cycles CPU executed total of 3 or more uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise)", - "MetricExpr": "(cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x3@ / 2 if #SMT_on else cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x3@) / tma_info_core_core_clks", + "BriefDescription": "This metric represents fraction of cycles CPU executed total of 3 or more uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise).", + "MetricExpr": "(cpu@UOPS_EXECUTED.CORE\\,cmask\\=3@ / 2 if #SMT_on else cpu@UOPS_EXECUTED.CORE\\,cmask\\=3@) / tma_info_core_core_clks", "MetricGroup": "BvCB;PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group", "MetricName": "tma_ports_utilized_3m", - "MetricThreshold": "tma_ports_utilized_3m > 0.4 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_ports_utilized_3m > 0.4 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", "ScaleUnit": "100%" }, { @@ -917,7 +915,7 @@ "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group", "MetricName": "tma_split_loads", "MetricThreshold": "tma_split_loads > 0.3", - "PublicDescription": "This metric estimates fraction of cycles handling memory load split accesses - load that cross 64-byte cache line boundary. Sample with: MEM_UOPS_RETIRED.SPLIT_LOADS", + "PublicDescription": "This metric estimates fraction of cycles handling memory load split accesses - load that cross 64-byte cache line boundary. Sample with: MEM_UOPS_RETIRED.SPLIT_LOADS_PS", "ScaleUnit": "100%" }, { @@ -925,8 +923,8 @@ "MetricExpr": "2 * MEM_UOPS_RETIRED.SPLIT_STORES / tma_info_core_core_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_issueSpSt;tma_store_bound_group", "MetricName": "tma_split_stores", - "MetricThreshold": "tma_split_stores > 0.2 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", - "PublicDescription": "This metric represents rate of split store accesses. Consider aligning your data to the 64-byte cache line granularity. Sample with: MEM_UOPS_RETIRED.SPLIT_STORES. Related metrics: tma_port_4", + "MetricThreshold": "tma_split_stores > 0.2 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric represents rate of split store accesses. Consider aligning your data to the 64-byte cache line granularity. Sample with: MEM_UOPS_RETIRED.SPLIT_STORES_PS. Related metrics: tma_port_4", "ScaleUnit": "100%" }, { @@ -934,7 +932,7 @@ "MetricExpr": "(OFFCORE_REQUESTS_BUFFER.SQ_FULL / 2 if #SMT_on else OFFCORE_REQUESTS_BUFFER.SQ_FULL) / tma_info_core_core_clks", "MetricGroup": "BvMB;MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_issueBW;tma_l3_bound_group", "MetricName": "tma_sq_full", - "MetricThreshold": "tma_sq_full > 0.3 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_sq_full > 0.3 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", "PublicDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors). Related metrics: tma_fb_full, tma_info_system_dram_bw_use, tma_mem_bandwidth", "ScaleUnit": "100%" }, @@ -943,8 +941,8 @@ "MetricExpr": "RESOURCE_STALLS.SB / tma_info_thread_clks", "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_store_bound", - "MetricThreshold": "tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", - "PublicDescription": "This metric estimates how often CPU was stalled due to RFO store memory accesses; RFO store issue a read-for-ownership request before the write. Even though store accesses do not typically stall out-of-order CPUs; there are few cases where stores can lead to actual stalls. This metric will be flagged should RFO stores be a bottleneck. Sample with: MEM_UOPS_RETIRED.ALL_STORES", + "MetricThreshold": "tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", + "PublicDescription": "This metric estimates how often CPU was stalled due to RFO store memory accesses; RFO store issue a read-for-ownership request before the write. Even though store accesses do not typically stall out-of-order CPUs; there are few cases where stores can lead to actual stalls. This metric will be flagged should RFO stores be a bottleneck. Sample with: MEM_UOPS_RETIRED.ALL_STORES_PS", "ScaleUnit": "100%" }, { @@ -952,8 +950,8 @@ "MetricExpr": "13 * LD_BLOCKS.STORE_FORWARD / tma_info_thread_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group", "MetricName": "tma_store_fwd_blk", - "MetricThreshold": "tma_store_fwd_blk > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", - "PublicDescription": "This metric roughly estimates fraction of cycles when the memory subsystem had loads blocked since they could not forward data from earlier (in program order) overlapping stores. To streamline memory operations in the pipeline; a load can avoid waiting for memory if a prior in-flight store is writing the data that the load wants to read (store forwarding process). However; in some cases the load may be blocked for a significant time pending the store forward. For example; when the prior store is writing a smaller region than the load is reading", + "MetricThreshold": "tma_store_fwd_blk > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric roughly estimates fraction of cycles when the memory subsystem had loads blocked since they could not forward data from earlier (in program order) overlapping stores. To streamline memory operations in the pipeline; a load can avoid waiting for memory if a prior in-flight store is writing the data that the load wants to read (store forwarding process). However; in some cases the load may be blocked for a significant time pending the store forward. For example; when the prior store is writing a smaller region than the load is reading.", "ScaleUnit": "100%" }, { @@ -962,8 +960,8 @@ "MetricExpr": "(L2_RQSTS.RFO_HIT * 9 * (1 - MEM_UOPS_RETIRED.LOCK_LOADS / MEM_UOPS_RETIRED.ALL_STORES) + (1 - MEM_UOPS_RETIRED.LOCK_LOADS / MEM_UOPS_RETIRED.ALL_STORES) * min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO)) / tma_info_thread_clks", "MetricGroup": "BvML;LockCont;MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_issueSL;tma_store_bound_group", "MetricName": "tma_store_latency", - "MetricThreshold": "tma_store_latency > 0.1 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", - "PublicDescription": "This metric estimates fraction of cycles the CPU spent handling L1D store misses. Store accesses usually less impact out-of-order core performance; however; holding resources for longer time can lead into undesired implications (e.g. contention on L1D fill-buffer entries - see FB_Full). Related metrics: tma_branch_resteers, tma_fb_full, tma_l3_hit_latency, tma_lock_latency", + "MetricThreshold": "tma_store_latency > 0.1 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric estimates fraction of cycles the CPU spent handling L1D store misses. Store accesses usually less impact out-of-order core performance; however; holding resources for longer time can lead into undesired implications (e.g. contention on L1D fill-buffer entries - see FB_Full). Related metrics: tma_fb_full, tma_lock_latency", "ScaleUnit": "100%" }, { diff --git a/tools/perf/pmu-events/arch/x86/haswellx/hsx-metrics.json b/tools/perf/pmu-events/arch/x86/haswellx/hsx-metrics.json index 1a05b74be575..8245a98ad4b9 100644 --- a/tools/perf/pmu-events/arch/x86/haswellx/hsx-metrics.json +++ b/tools/perf/pmu-events/arch/x86/haswellx/hsx-metrics.json @@ -276,12 +276,12 @@ "MetricExpr": "LD_BLOCKS_PARTIAL.ADDRESS_ALIAS / tma_info_thread_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group", "MetricName": "tma_4k_aliasing", - "MetricThreshold": "tma_4k_aliasing > 0.2 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", - "PublicDescription": "This metric estimates how often memory load accesses were aliased by preceding stores (in program order) with a 4K address offset. False match is possible; which incur a few cycles load re-issue. However; the short re-issue duration is often hidden by the out-of-order core and HW optimizations; hence a user may safely ignore a high value of this metric unless it manages to propagate up into parent nodes of the hierarchy (e.g. to L1_Bound)", + "MetricThreshold": "tma_4k_aliasing > 0.2 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric estimates how often memory load accesses were aliased by preceding stores (in program order) with a 4K address offset. False match is possible; which incur a few cycles load re-issue. However; the short re-issue duration is often hidden by the out-of-order core and HW optimizations; hence a user may safely ignore a high value of this metric unless it manages to propagate up into parent nodes of the hierarchy (e.g. to L1_Bound).", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution ports for ALU operations", + "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution ports for ALU operations.", "MetricConstraint": "NO_GROUP_EVENTS_NMI", "MetricExpr": "(UOPS_DISPATCHED_PORT.PORT_0 + UOPS_DISPATCHED_PORT.PORT_1 + UOPS_DISPATCHED_PORT.PORT_5 + UOPS_DISPATCHED_PORT.PORT_6) / tma_info_thread_slots", "MetricGroup": "TopdownL5;tma_L5_group;tma_ports_utilized_3m_group", @@ -294,8 +294,8 @@ "MetricExpr": "66 * OTHER_ASSISTS.ANY_WB_ASSIST / tma_info_thread_slots", "MetricGroup": "BvIO;TopdownL4;tma_L4_group;tma_microcode_sequencer_group", "MetricName": "tma_assists", - "MetricThreshold": "tma_assists > 0.1 & tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1", - "PublicDescription": "This metric estimates fraction of slots the CPU retired uops delivered by the Microcode_Sequencer as a result of Assists. Assists are long sequences of uops that are required in certain corner-cases for operations that cannot be handled natively by the execution pipeline. For example; when working with very small floating point values (so-called Denormals); the FP units are not set up to perform these operations natively. Instead; a sequence of instructions to perform the computation on the Denormals is injected into the pipeline. Since these microcode sequences might be dozens of uops long; Assists can be extremely deleterious to performance and they can be avoided in many cases. Sample with: OTHER_ASSISTS.ANY_WB_ASSIST", + "MetricThreshold": "tma_assists > 0.1 & (tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1)", + "PublicDescription": "This metric estimates fraction of slots the CPU retired uops delivered by the Microcode_Sequencer as a result of Assists. Assists are long sequences of uops that are required in certain corner-cases for operations that cannot be handled natively by the execution pipeline. For example; when working with very small floating point values (so-called Denormals); the FP units are not set up to perform these operations natively. Instead; a sequence of instructions to perform the computation on the Denormals is injected into the pipeline. Since these microcode sequences might be dozens of uops long; Assists can be extremely deleterious to performance and they can be avoided in many cases. Sample with: OTHER_ASSISTS.ANY", "ScaleUnit": "100%" }, { @@ -306,7 +306,7 @@ "MetricName": "tma_backend_bound", "MetricThreshold": "tma_backend_bound > 0.2", "MetricgroupNoGroup": "TopdownL1", - "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound", + "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound.", "ScaleUnit": "100%" }, { @@ -316,7 +316,7 @@ "MetricName": "tma_bad_speculation", "MetricThreshold": "tma_bad_speculation > 0.15", "MetricgroupNoGroup": "TopdownL1", - "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example", + "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.", "ScaleUnit": "100%" }, { @@ -327,7 +327,7 @@ "MetricName": "tma_branch_mispredicts", "MetricThreshold": "tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", "MetricgroupNoGroup": "TopdownL2", - "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction. These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: BR_MISP_RETIRED.ALL_BRANCHES", + "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction. These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_info_bad_spec_branch_misprediction_cost, tma_mispredicts_resteers", "ScaleUnit": "100%" }, { @@ -335,8 +335,8 @@ "MetricExpr": "12 * (BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT + BACLEARS.ANY) / tma_info_thread_clks", "MetricGroup": "FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group", "MetricName": "tma_branch_resteers", - "MetricThreshold": "tma_branch_resteers > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", - "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers. Branch Resteers estimates the Frontend delay in fetching operations from corrected path; following all sorts of miss-predicted branches. For example; branchy code with lots of miss-predictions might get categorized under Branch Resteers. Note the value of this node may overlap with its siblings. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_l3_hit_latency, tma_store_latency", + "MetricThreshold": "tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers. Branch Resteers estimates the Frontend delay in fetching operations from corrected path; following all sorts of miss-predicted branches. For example; branchy code with lots of miss-predictions might get categorized under Branch Resteers. Note the value of this node may overlap with its siblings. Sample with: BR_MISP_RETIRED.ALL_BRANCHES", "ScaleUnit": "100%" }, { @@ -345,8 +345,8 @@ "MetricExpr": "max(0, tma_microcode_sequencer - tma_assists)", "MetricGroup": "TopdownL4;tma_L4_group;tma_microcode_sequencer_group", "MetricName": "tma_cisc", - "MetricThreshold": "tma_cisc > 0.1 & tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1", - "PublicDescription": "This metric estimates fraction of cycles the CPU retired uops originated from CISC (complex instruction set computer) instruction. A CISC instruction has multiple uops that are required to perform the instruction's functionality as in the case of read-modify-write as an example. Since these instructions require multiple uops they may or may not imply sub-optimal use of machine resources", + "MetricThreshold": "tma_cisc > 0.1 & (tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1)", + "PublicDescription": "This metric estimates fraction of cycles the CPU retired uops originated from CISC (complex instruction set computer) instruction. A CISC instruction has multiple uops that are required to perform the instruction's functionality as in the case of read-modify-write as an example. Since these instructions require multiple uops they may or may not imply sub-optimal use of machine resources.", "ScaleUnit": "100%" }, { @@ -355,8 +355,8 @@ "MetricExpr": "(60 * (MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.L3_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_L3_MISS_RETIRED.LOCAL_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_HITM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_FWD))) + 43 * (MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.L3_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_L3_MISS_RETIRED.LOCAL_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_HITM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_FWD)))) / tma_info_thread_clks", "MetricGroup": "BvMS;DataSharing;LockCont;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group", "MetricName": "tma_contested_accesses", - "MetricThreshold": "tma_contested_accesses > 0.05 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", - "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses. Contested accesses occur when data written by one Logical Processor are read by another Logical Processor on a different Physical Core. Examples of contested accesses include synchronizations such as locks; true data sharing such as modified locked variables; and false sharing. Sample with: MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM, MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS. Related metrics: tma_data_sharing, tma_false_sharing, tma_machine_clears, tma_remote_cache", + "MetricThreshold": "tma_contested_accesses > 0.05 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses. Contested accesses occur when data written by one Logical Processor are read by another Logical Processor on a different Physical Core. Examples of contested accesses include synchronizations such as locks; true data sharing such as modified locked variables; and false sharing. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM_PS;MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS_PS. Related metrics: tma_data_sharing, tma_false_sharing, tma_machine_clears, tma_remote_cache", "ScaleUnit": "100%" }, { @@ -367,7 +367,7 @@ "MetricName": "tma_core_bound", "MetricThreshold": "tma_core_bound > 0.1 & tma_backend_bound > 0.2", "MetricgroupNoGroup": "TopdownL2", - "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck. Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations)", + "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck. Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations).", "ScaleUnit": "100%" }, { @@ -376,8 +376,8 @@ "MetricExpr": "43 * (MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.L3_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_L3_MISS_RETIRED.LOCAL_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_HITM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_FWD))) / tma_info_thread_clks", "MetricGroup": "BvMS;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group", "MetricName": "tma_data_sharing", - "MetricThreshold": "tma_data_sharing > 0.05 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", - "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses. Data shared by multiple Logical Processors (even just read shared) may cause increased access latency due to cache coherency. Excessive data sharing can drastically harm multithreaded performance. Sample with: MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT. Related metrics: tma_contested_accesses, tma_false_sharing, tma_machine_clears, tma_remote_cache", + "MetricThreshold": "tma_data_sharing > 0.05 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses. Data shared by multiple Logical Processors (even just read shared) may cause increased access latency due to cache coherency. Excessive data sharing can drastically harm multithreaded performance. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_HIT_PS. Related metrics: tma_contested_accesses, tma_false_sharing, tma_machine_clears, tma_remote_cache", "ScaleUnit": "100%" }, { @@ -385,8 +385,8 @@ "MetricExpr": "10 * ARITH.DIVIDER_UOPS / tma_info_core_core_clks", "MetricGroup": "BvCB;TopdownL3;tma_L3_group;tma_core_bound_group", "MetricName": "tma_divider", - "MetricThreshold": "tma_divider > 0.2 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", - "PublicDescription": "This metric represents fraction of cycles where the Divider unit was active. Divide and square root instructions are performed by the Divider unit and can take considerably longer latency than integer or Floating Point addition; subtraction; or multiplication. Sample with: ARITH.DIVIDER_UOPS", + "MetricThreshold": "tma_divider > 0.2 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)", + "PublicDescription": "This metric represents fraction of cycles where the Divider unit was active. Divide and square root instructions are performed by the Divider unit and can take considerably longer latency than integer or Floating Point addition; subtraction; or multiplication. Sample with: ARITH.DIVIDER_ACTIVE", "ScaleUnit": "100%" }, { @@ -395,8 +395,8 @@ "MetricExpr": "(1 - MEM_LOAD_UOPS_RETIRED.L3_HIT / (MEM_LOAD_UOPS_RETIRED.L3_HIT + 7 * MEM_LOAD_UOPS_RETIRED.L3_MISS)) * CYCLE_ACTIVITY.STALLS_L2_PENDING / tma_info_thread_clks", "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_dram_bound", - "MetricThreshold": "tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", - "PublicDescription": "This metric estimates how often the CPU was stalled on accesses to external memory (DRAM) by loads. Better caching can improve the latency and increase performance. Sample with: MEM_LOAD_UOPS_RETIRED.L3_MISS", + "MetricThreshold": "tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", + "PublicDescription": "This metric estimates how often the CPU was stalled on accesses to external memory (DRAM) by loads. Better caching can improve the latency and increase performance. Sample with: MEM_LOAD_UOPS_RETIRED.L3_MISS_PS", "ScaleUnit": "100%" }, { @@ -405,7 +405,7 @@ "MetricGroup": "DSB;FetchBW;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group", "MetricName": "tma_dsb", "MetricThreshold": "tma_dsb > 0.15 & tma_fetch_bandwidth > 0.2", - "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to DSB (decoded uop cache) fetch pipeline. For example; inefficient utilization of the DSB cache structure or bank conflict when reading from it; are categorized here", + "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to DSB (decoded uop cache) fetch pipeline. For example; inefficient utilization of the DSB cache structure or bank conflict when reading from it; are categorized here.", "ScaleUnit": "100%" }, { @@ -413,7 +413,7 @@ "MetricExpr": "DSB2MITE_SWITCHES.PENALTY_CYCLES / tma_info_thread_clks", "MetricGroup": "DSBmiss;FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueFB", "MetricName": "tma_dsb_switches", - "MetricThreshold": "tma_dsb_switches > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricThreshold": "tma_dsb_switches > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines. The DSB (decoded i-cache) is a Uop Cache where the front-end directly delivers Uops (micro operations) avoiding heavy x86 decoding. The DSB pipeline has shorter latency and delivered higher bandwidth than the MITE (legacy instruction decode pipeline). Switching between the two pipelines can cause penalties hence this metric measures the exposed penalty. Related metrics: tma_fetch_bandwidth, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp", "ScaleUnit": "100%" }, @@ -422,8 +422,8 @@ "MetricExpr": "(8 * DTLB_LOAD_MISSES.STLB_HIT + DTLB_LOAD_MISSES.WALK_DURATION) / tma_info_thread_clks", "MetricGroup": "BvMT;MemoryTLB;TopdownL4;tma_L4_group;tma_issueTLB;tma_l1_bound_group", "MetricName": "tma_dtlb_load", - "MetricThreshold": "tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", - "PublicDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses. TLBs (Translation Look-aside Buffers) are processor caches for recently used entries out of the Page Tables that are used to map virtual- to physical-addresses by the operating system. This metric approximates the potential delay of demand loads missing the first-level data TLB (assuming worst case scenario with back to back misses to different pages). This includes hitting in the second-level TLB (STLB) as well as performing a hardware page walk on an STLB miss. Sample with: MEM_UOPS_RETIRED.STLB_MISS_LOADS. Related metrics: tma_dtlb_store", + "MetricThreshold": "tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses. TLBs (Translation Look-aside Buffers) are processor caches for recently used entries out of the Page Tables that are used to map virtual- to physical-addresses by the operating system. This metric approximates the potential delay of demand loads missing the first-level data TLB (assuming worst case scenario with back to back misses to different pages). This includes hitting in the second-level TLB (STLB) as well as performing a hardware page walk on an STLB miss. Sample with: MEM_UOPS_RETIRED.STLB_MISS_LOADS_PS. Related metrics: tma_dtlb_store", "ScaleUnit": "100%" }, { @@ -431,8 +431,8 @@ "MetricExpr": "(8 * DTLB_STORE_MISSES.STLB_HIT + DTLB_STORE_MISSES.WALK_DURATION) / tma_info_thread_clks", "MetricGroup": "BvMT;MemoryTLB;TopdownL4;tma_L4_group;tma_issueTLB;tma_store_bound_group", "MetricName": "tma_dtlb_store", - "MetricThreshold": "tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", - "PublicDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses. As with ordinary data caching; focus on improving data locality and reducing working-set size to reduce DTLB overhead. Additionally; consider using profile-guided optimization (PGO) to collocate frequently-used data on the same page. Try using larger page sizes for large amounts of frequently-used data. Sample with: MEM_UOPS_RETIRED.STLB_MISS_STORES. Related metrics: tma_dtlb_load", + "MetricThreshold": "tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses. As with ordinary data caching; focus on improving data locality and reducing working-set size to reduce DTLB overhead. Additionally; consider using profile-guided optimization (PGO) to collocate frequently-used data on the same page. Try using larger page sizes for large amounts of frequently-used data. Sample with: MEM_UOPS_RETIRED.STLB_MISS_STORES_PS. Related metrics: tma_dtlb_load", "ScaleUnit": "100%" }, { @@ -440,18 +440,18 @@ "MetricExpr": "(200 * OFFCORE_RESPONSE.DEMAND_RFO.LLC_MISS.REMOTE_HITM + 60 * OFFCORE_RESPONSE.DEMAND_RFO.LLC_HIT.HITM_OTHER_CORE) / tma_info_thread_clks", "MetricGroup": "BvMS;DataSharing;LockCont;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_store_bound_group", "MetricName": "tma_false_sharing", - "MetricThreshold": "tma_false_sharing > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", - "PublicDescription": "This metric roughly estimates how often CPU was handling synchronizations due to False Sharing. False Sharing is a multithreading hiccup; where multiple Logical Processors contend on different data-elements mapped into the same cache line. Sample with: MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM, MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_HITM, OFFCORE_RESPONSE.DEMAND_RFO.LLC_HIT.HITM_OTHER_CORE, OFFCORE_RESPONSE.DEMAND_RFO.LLC_MISS.REMOTE_HITM. Related metrics: tma_contested_accesses, tma_data_sharing, tma_machine_clears, tma_remote_cache", + "MetricThreshold": "tma_false_sharing > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric roughly estimates how often CPU was handling synchronizations due to False Sharing. False Sharing is a multithreading hiccup; where multiple Logical Processors contend on different data-elements mapped into the same cache line. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM_PS;OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.SNOOP_HITM. Related metrics: tma_contested_accesses, tma_data_sharing, tma_machine_clears, tma_remote_cache", "ScaleUnit": "100%" }, { "BriefDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed", "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "tma_info_memory_load_miss_real_latency * cpu@L1D_PEND_MISS.REQUEST_FB_FULL\\,cmask\\=0x1@ / tma_info_thread_clks", + "MetricExpr": "tma_info_memory_load_miss_real_latency * cpu@L1D_PEND_MISS.REQUEST_FB_FULL\\,cmask\\=1@ / tma_info_thread_clks", "MetricGroup": "BvMB;MemoryBW;TopdownL4;tma_L4_group;tma_issueBW;tma_issueSL;tma_issueSmSt;tma_l1_bound_group", "MetricName": "tma_fb_full", "MetricThreshold": "tma_fb_full > 0.3", - "PublicDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed. The higher the metric value; the deeper the memory hierarchy level the misses are satisfied from (metric values >1 are valid). Often it hints on approaching bandwidth limits (to L2 cache; L3 cache or external memory). Related metrics: tma_info_system_dram_bw_use, tma_mem_bandwidth, tma_sq_full, tma_store_latency", + "PublicDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed. The higher the metric value; the deeper the memory hierarchy level the misses are satisfied from (metric values >1 are valid). Often it hints on approaching bandwidth limits (to L2 cache; L3 cache or external memory). Related metrics: tma_info_system_dram_bw_use, tma_mem_bandwidth, tma_sq_full, tma_store_latency, tma_streaming_stores", "ScaleUnit": "100%" }, { @@ -481,33 +481,33 @@ "MetricName": "tma_frontend_bound", "MetricThreshold": "tma_frontend_bound > 0.15", "MetricgroupNoGroup": "TopdownL1", - "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound", + "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound.", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations , instructions that require two or more uops or micro-coded sequences", + "BriefDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences", "MetricExpr": "tma_microcode_sequencer", "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_heavy_operations", "MetricThreshold": "tma_heavy_operations > 0.1", "MetricgroupNoGroup": "TopdownL2", - "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations , instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences.([ICL+] Note this may overcount due to approximation using indirect events; [ADL+])", + "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences.([ICL+] Note this may overcount due to approximation using indirect events; [ADL+])", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to instruction cache misses", + "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to instruction cache misses.", "MetricExpr": "ICACHE.IFDATA_STALL / tma_info_thread_clks", "MetricGroup": "BigFootprint;BvBC;FetchLat;IcMiss;TopdownL3;tma_L3_group;tma_fetch_latency_group", "MetricName": "tma_icache_misses", - "MetricThreshold": "tma_icache_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricThreshold": "tma_icache_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", "ScaleUnit": "100%" }, { - "BriefDescription": "Instructions per retired Mispredicts for indirect CALL or JMP branches (lower number means higher occurrence rate)", + "BriefDescription": "Instructions per retired Mispredicts for indirect CALL or JMP branches (lower number means higher occurrence rate).", "MetricExpr": "tma_info_inst_mix_instructions / (UOPS_RETIRED.RETIRE_SLOTS / UOPS_ISSUED.ANY * BR_MISP_EXEC.INDIRECT)", "MetricGroup": "Bad;BrMispredicts", "MetricName": "tma_info_bad_spec_ipmisp_indirect", - "MetricThreshold": "tma_info_bad_spec_ipmisp_indirect < 1000" + "MetricThreshold": "tma_info_bad_spec_ipmisp_indirect < 1e3" }, { "BriefDescription": "Number of Instructions per non-speculative Branch Misprediction (JEClear) (lower number means higher occurrence rate)", @@ -518,7 +518,7 @@ }, { "BriefDescription": "Core actual clocks when any Logical Processor is active on the Physical Core", - "MetricExpr": "(CPU_CLK_UNHALTED.THREAD_ANY / 2 if #SMT_on else tma_info_thread_clks)", + "MetricExpr": "(CPU_CLK_UNHALTED.THREAD / 2 * (1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK) if #core_wide < 1 else (CPU_CLK_UNHALTED.THREAD_ANY / 2 if #SMT_on else tma_info_thread_clks))", "MetricGroup": "SMT", "MetricName": "tma_info_core_core_clks" }, @@ -530,7 +530,7 @@ }, { "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is execution) per thread (logical-processor)", - "MetricExpr": "(UOPS_EXECUTED.CORE / 2 / (cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x1@ / 2 if #SMT_on else cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x1@) if #SMT_on else UOPS_EXECUTED.CORE / (cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x1@ / 2 if #SMT_on else cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x1@))", + "MetricExpr": "(UOPS_EXECUTED.CORE / 2 / (cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ / 2 if #SMT_on else cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@) if #SMT_on else UOPS_EXECUTED.CORE / (cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ / 2 if #SMT_on else cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@))", "MetricGroup": "Backend;Cor;Pipeline;PortsUtil", "MetricName": "tma_info_core_ilp" }, @@ -555,7 +555,7 @@ "MetricName": "tma_info_frontend_tbpc" }, { - "BriefDescription": "Branch instructions per taken branch", + "BriefDescription": "Branch instructions per taken branch.", "MetricExpr": "BR_INST_RETIRED.ALL_BRANCHES / BR_INST_RETIRED.NEAR_TAKEN", "MetricGroup": "Branches;Fed;PGO", "MetricName": "tma_info_inst_mix_bptkbranch" @@ -600,7 +600,7 @@ "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_TAKEN", "MetricGroup": "Branches;Fed;FetchBW;Frontend;PGO;tma_issueFB", "MetricName": "tma_info_inst_mix_iptb", - "MetricThreshold": "tma_info_inst_mix_iptb < 4 * 2 + 1", + "MetricThreshold": "tma_info_inst_mix_iptb < 9", "PublicDescription": "Instructions per taken branch. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_frontend_dsb_coverage, tma_lcp" }, { @@ -704,8 +704,8 @@ "MetricThreshold": "tma_info_memory_tlb_page_walks_utilization > 0.5" }, { - "BriefDescription": "Average number of Uops retired in cycles where at least one uop has retired", - "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / cpu@UOPS_RETIRED.RETIRE_SLOTS\\,cmask\\=0x1@", + "BriefDescription": "Average number of Uops retired in cycles where at least one uop has retired.", + "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / cpu@UOPS_RETIRED.RETIRE_SLOTS\\,cmask\\=1@", "MetricGroup": "Pipeline;Ret", "MetricName": "tma_info_pipeline_retire" }, @@ -739,14 +739,13 @@ "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.FAR_BRANCH:u", "MetricGroup": "Branches;OS", "MetricName": "tma_info_system_ipfarbranch", - "MetricThreshold": "tma_info_system_ipfarbranch < 1000000" + "MetricThreshold": "tma_info_system_ipfarbranch < 1e6" }, { "BriefDescription": "Cycles Per Instruction for the Operating System (OS) Kernel mode", "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P:k / INST_RETIRED.ANY_P:k", "MetricGroup": "OS", - "MetricName": "tma_info_system_kernel_cpi", - "ScaleUnit": "1per_instr" + "MetricName": "tma_info_system_kernel_cpi" }, { "BriefDescription": "Fraction of cycles spent in the Operating System (OS) Kernel mode", @@ -757,14 +756,14 @@ }, { "BriefDescription": "Average number of parallel data read requests to external memory", - "MetricExpr": "cbox@UNC_C_TOR_OCCUPANCY.MISS_OPCODE\\,filter_opc\\=0x182@ / cbox@UNC_C_TOR_OCCUPANCY.MISS_OPCODE\\,filter_opc\\=0x182@", + "MetricExpr": "UNC_C_TOR_OCCUPANCY.MISS_OPCODE@filter_opc\\=0x182@ / UNC_C_TOR_OCCUPANCY.MISS_OPCODE@filter_opc\\=0x182\\,thresh\\=1@", "MetricGroup": "Mem;MemoryBW;SoC", "MetricName": "tma_info_system_mem_parallel_reads", "PublicDescription": "Average number of parallel data read requests to external memory. Accounts for demand loads and L1/L2 prefetches" }, { "BriefDescription": "Average latency of data read request to external memory (in nanoseconds)", - "MetricExpr": "1e9 * (cbox@UNC_C_TOR_OCCUPANCY.MISS_OPCODE\\,filter_opc\\=0x182@ / cbox@UNC_C_TOR_INSERTS.MISS_OPCODE\\,filter_opc\\=0x182@) / (tma_info_system_socket_clks / tma_info_system_time)", + "MetricExpr": "1e9 * (UNC_C_TOR_OCCUPANCY.MISS_OPCODE@filter_opc\\=0x182@ / UNC_C_TOR_INSERTS.MISS_OPCODE@filter_opc\\=0x182@) / (tma_info_system_socket_clks / tma_info_system_time)", "MetricGroup": "Mem;MemoryLat;SoC", "MetricName": "tma_info_system_mem_read_latency", "PublicDescription": "Average latency of data read request to external memory (in nanoseconds). Accounts for demand loads and L1/L2 prefetches. ([RKL+]memory-controller only)" @@ -814,7 +813,7 @@ "MetricName": "tma_info_system_uncore_frequency" }, { - "BriefDescription": "Per-Logical Processor actual clocks when the Logical Processor is active", + "BriefDescription": "Per-Logical Processor actual clocks when the Logical Processor is active.", "MetricExpr": "CPU_CLK_UNHALTED.THREAD", "MetricGroup": "Pipeline", "MetricName": "tma_info_thread_clks" @@ -823,8 +822,7 @@ "BriefDescription": "Cycles Per Instruction (per Logical Processor)", "MetricExpr": "1 / tma_info_thread_ipc", "MetricGroup": "Mem;Pipeline", - "MetricName": "tma_info_thread_cpi", - "ScaleUnit": "1per_instr" + "MetricName": "tma_info_thread_cpi" }, { "BriefDescription": "Instructions Per Cycle (per Logical Processor)", @@ -850,14 +848,14 @@ "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / BR_INST_RETIRED.NEAR_TAKEN", "MetricGroup": "Branches;Fed;FetchBW", "MetricName": "tma_info_thread_uptb", - "MetricThreshold": "tma_info_thread_uptb < 4 * 1.5" + "MetricThreshold": "tma_info_thread_uptb < 6" }, { "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to Instruction TLB (ITLB) misses", "MetricExpr": "(14 * ITLB_MISSES.STLB_HIT + ITLB_MISSES.WALK_DURATION) / tma_info_thread_clks", "MetricGroup": "BigFootprint;BvBC;FetchLat;MemoryTLB;TopdownL3;tma_L3_group;tma_fetch_latency_group", "MetricName": "tma_itlb_misses", - "MetricThreshold": "tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricThreshold": "tma_itlb_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Instruction TLB (ITLB) misses. Sample with: ITLB_MISSES.WALK_COMPLETED", "ScaleUnit": "100%" }, @@ -866,8 +864,8 @@ "MetricExpr": "max((min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.STALLS_LDM_PENDING) - CYCLE_ACTIVITY.STALLS_L1D_PENDING) / tma_info_thread_clks, 0)", "MetricGroup": "CacheHits;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_issueL1;tma_issueMC;tma_memory_bound_group", "MetricName": "tma_l1_bound", - "MetricThreshold": "tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", - "PublicDescription": "This metric estimates how often the CPU was stalled without loads missing the L1 Data (L1D) cache. The L1D cache typically has the shortest latency. However; in certain cases like loads blocked on older stores; a load might suffer due to high latency even though it is being satisfied by the L1D. Another example is loads who miss in the TLB. These cases are characterized by execution unit stalls; while some non-completed demand load lives in the machine without having that demand load missing the L1 cache. Sample with: MEM_LOAD_UOPS_RETIRED.L1_HIT. Related metrics: tma_machine_clears, tma_microcode_sequencer, tma_ms_switches, tma_ports_utilized_1", + "MetricThreshold": "tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", + "PublicDescription": "This metric estimates how often the CPU was stalled without loads missing the L1 Data (L1D) cache. The L1D cache typically has the shortest latency. However; in certain cases like loads blocked on older stores; a load might suffer due to high latency even though it is being satisfied by the L1D. Another example is loads who miss in the TLB. These cases are characterized by execution unit stalls; while some non-completed demand load lives in the machine without having that demand load missing the L1 cache. Sample with: MEM_LOAD_UOPS_RETIRED.L1_HIT_PS. Related metrics: tma_clears_resteers, tma_machine_clears, tma_microcode_sequencer, tma_ms_switches, tma_ports_utilized_1", "ScaleUnit": "100%" }, { @@ -875,8 +873,8 @@ "MetricExpr": "(CYCLE_ACTIVITY.STALLS_L1D_PENDING - CYCLE_ACTIVITY.STALLS_L2_PENDING) / tma_info_thread_clks", "MetricGroup": "BvML;CacheHits;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_l2_bound", - "MetricThreshold": "tma_l2_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", - "PublicDescription": "This metric estimates how often the CPU was stalled due to L2 cache accesses by loads. Avoiding cache misses (i.e. L1 misses/L2 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_UOPS_RETIRED.L2_HIT", + "MetricThreshold": "tma_l2_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", + "PublicDescription": "This metric estimates how often the CPU was stalled due to L2 cache accesses by loads. Avoiding cache misses (i.e. L1 misses/L2 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_UOPS_RETIRED.L2_HIT_PS", "ScaleUnit": "100%" }, { @@ -885,8 +883,8 @@ "MetricExpr": "MEM_LOAD_UOPS_RETIRED.L3_HIT / (MEM_LOAD_UOPS_RETIRED.L3_HIT + 7 * MEM_LOAD_UOPS_RETIRED.L3_MISS) * CYCLE_ACTIVITY.STALLS_L2_PENDING / tma_info_thread_clks", "MetricGroup": "CacheHits;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_l3_bound", - "MetricThreshold": "tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", - "PublicDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core. Avoiding cache misses (i.e. L2 misses/L3 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_UOPS_RETIRED.L3_HIT", + "MetricThreshold": "tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", + "PublicDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core. Avoiding cache misses (i.e. L2 misses/L3 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_UOPS_RETIRED.L3_HIT_PS", "ScaleUnit": "100%" }, { @@ -895,8 +893,8 @@ "MetricExpr": "41 * (MEM_LOAD_UOPS_RETIRED.L3_HIT * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.L3_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_L3_MISS_RETIRED.LOCAL_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_HITM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_FWD))) / tma_info_thread_clks", "MetricGroup": "BvML;MemoryLat;TopdownL4;tma_L4_group;tma_issueLat;tma_l3_bound_group", "MetricName": "tma_l3_hit_latency", - "MetricThreshold": "tma_l3_hit_latency > 0.1 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", - "PublicDescription": "This metric estimates fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited). Avoiding private cache misses (i.e. L2 misses/L3 hits) will improve the latency; reduce contention with sibling physical cores and increase performance. Note the value of this node may overlap with its siblings. Sample with: MEM_LOAD_UOPS_RETIRED.L3_HIT. Related metrics: tma_branch_resteers, tma_mem_latency, tma_store_latency", + "MetricThreshold": "tma_l3_hit_latency > 0.1 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric estimates fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited). Avoiding private cache misses (i.e. L2 misses/L3 hits) will improve the latency; reduce contention with sibling physical cores and increase performance. Note the value of this node may overlap with its siblings. Sample with: MEM_LOAD_UOPS_RETIRED.L3_HIT_PS. Related metrics: tma_mem_latency", "ScaleUnit": "100%" }, { @@ -904,18 +902,18 @@ "MetricExpr": "ILD_STALL.LCP / tma_info_thread_clks", "MetricGroup": "FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueFB", "MetricName": "tma_lcp", - "MetricThreshold": "tma_lcp > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", - "PublicDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs). Using proper compiler flags or Intel Compiler by default will certainly avoid this. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb", + "MetricThreshold": "tma_lcp > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", + "PublicDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs). Using proper compiler flags or Intel Compiler by default will certainly avoid this. #Link: Optimization Guide about LCP BKMs. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations , instructions that require no more than one uop (micro-operation)", + "BriefDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation)", "MetricExpr": "tma_retiring - tma_heavy_operations", "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_light_operations", "MetricThreshold": "tma_light_operations > 0.6", "MetricgroupNoGroup": "TopdownL2", - "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations , instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized code running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. ([ICL+] Note this may undercount due to approximation using indirect events; [ADL+] .). Sample with: INST_RETIRED.PREC_DIST", + "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized code running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. ([ICL+] Note this may undercount due to approximation using indirect events; [ADL+] .). Sample with: INST_RETIRED.PREC_DIST", "ScaleUnit": "100%" }, { @@ -933,8 +931,8 @@ "MetricExpr": "200 * (MEM_LOAD_UOPS_L3_MISS_RETIRED.LOCAL_DRAM * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.L3_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_L3_MISS_RETIRED.LOCAL_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_HITM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_FWD))) / tma_info_thread_clks", "MetricGroup": "Server;TopdownL5;tma_L5_group;tma_mem_latency_group", "MetricName": "tma_local_mem", - "MetricThreshold": "tma_local_mem > 0.1 & tma_mem_latency > 0.1 & tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", - "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from local memory. Caching will improve the latency and increase performance. Sample with: MEM_LOAD_UOPS_L3_MISS_RETIRED.LOCAL_DRAM", + "MetricThreshold": "tma_local_mem > 0.1 & (tma_mem_latency > 0.1 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))", + "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from local memory. Caching will improve the latency and increase performance. Sample with: MEM_LOAD_UOPS_L3_MISS_RETIRED.LOCAL_DRAM_PS", "ScaleUnit": "100%" }, { @@ -943,8 +941,8 @@ "MetricExpr": "MEM_UOPS_RETIRED.LOCK_LOADS / MEM_UOPS_RETIRED.ALL_STORES * min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO) / tma_info_thread_clks", "MetricGroup": "LockCont;Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_l1_bound_group", "MetricName": "tma_lock_latency", - "MetricThreshold": "tma_lock_latency > 0.2 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", - "PublicDescription": "This metric represents fraction of cycles the CPU spent handling cache misses due to lock operations. Due to the microarchitecture handling of locks; they are classified as L1_Bound regardless of what memory source satisfied them. Sample with: MEM_UOPS_RETIRED.LOCK_LOADS. Related metrics: tma_store_latency", + "MetricThreshold": "tma_lock_latency > 0.2 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric represents fraction of cycles the CPU spent handling cache misses due to lock operations. Due to the microarchitecture handling of locks; they are classified as L1_Bound regardless of what memory source satisfied them. Sample with: MEM_UOPS_RETIRED.LOCK_LOADS_PS. Related metrics: tma_store_latency", "ScaleUnit": "100%" }, { @@ -955,15 +953,15 @@ "MetricName": "tma_machine_clears", "MetricThreshold": "tma_machine_clears > 0.1 & tma_bad_speculation > 0.15", "MetricgroupNoGroup": "TopdownL2", - "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears. These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT. Related metrics: tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_l1_bound, tma_microcode_sequencer, tma_ms_switches, tma_remote_cache", + "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears. These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT. Related metrics: tma_clears_resteers, tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_l1_bound, tma_microcode_sequencer, tma_ms_switches, tma_remote_cache", "ScaleUnit": "100%" }, { "BriefDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory - DRAM ([SPR-HBM] and/or HBM)", - "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, cpu@OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD\\,cmask\\=0x6@) / tma_info_thread_clks", + "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, cpu@OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD\\,cmask\\=6@) / tma_info_thread_clks", "MetricGroup": "BvMB;MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueBW", "MetricName": "tma_mem_bandwidth", - "MetricThreshold": "tma_mem_bandwidth > 0.2 & tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_mem_bandwidth > 0.2 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", "PublicDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory - DRAM ([SPR-HBM] and/or HBM). The underlying heuristic assumes that a similar off-core traffic is generated by all IA cores. This metric does not aggregate non-data-read requests by this logical processor; requests from other IA Logical Processors/Physical Cores/sockets; or other non-IA devices like GPU; hence the maximum external memory bandwidth limits may or may not be approached when this metric is flagged (see Uncore counters for that). Related metrics: tma_fb_full, tma_info_system_dram_bw_use, tma_sq_full", "ScaleUnit": "100%" }, @@ -972,19 +970,19 @@ "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD) / tma_info_thread_clks - tma_mem_bandwidth", "MetricGroup": "BvML;MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueLat", "MetricName": "tma_mem_latency", - "MetricThreshold": "tma_mem_latency > 0.1 & tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_mem_latency > 0.1 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", "PublicDescription": "This metric estimates fraction of cycles where the performance was likely hurt due to latency from external memory - DRAM ([SPR-HBM] and/or HBM). This metric does not aggregate requests from other Logical Processors/Physical Cores/sockets (see Uncore counters for that). Related metrics: tma_l3_hit_latency", "ScaleUnit": "100%" }, { "BriefDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck", "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "(min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.STALLS_LDM_PENDING) + RESOURCE_STALLS.SB) / (min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.CYCLES_NO_EXECUTE) + (cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x1@ - (cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x3@ if tma_info_thread_ipc > 1.8 else cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x2@)) / 2 - (RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else 0) + RESOURCE_STALLS.SB if #SMT_on else min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.CYCLES_NO_EXECUTE) + cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x1@ - (cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x3@ if tma_info_thread_ipc > 1.8 else cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x2@) - (RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else 0) + RESOURCE_STALLS.SB) * tma_backend_bound", + "MetricExpr": "((min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.STALLS_LDM_PENDING) + RESOURCE_STALLS.SB) / (min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.CYCLES_NO_EXECUTE) + (cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ - (cpu@UOPS_EXECUTED.CORE\\,cmask\\=3@ if tma_info_thread_ipc > 1.8 else cpu@UOPS_EXECUTED.CORE\\,cmask\\=2@)) / 2 - (RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else 0) + RESOURCE_STALLS.SB) if #SMT_on else min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.CYCLES_NO_EXECUTE) + cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ - (cpu@UOPS_EXECUTED.CORE\\,cmask\\=3@ if tma_info_thread_ipc > 1.8 else cpu@UOPS_EXECUTED.CORE\\,cmask\\=2@) - (RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else 0) + RESOURCE_STALLS.SB) * tma_backend_bound", "MetricGroup": "Backend;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_memory_bound", "MetricThreshold": "tma_memory_bound > 0.2 & tma_backend_bound > 0.2", "MetricgroupNoGroup": "TopdownL2", - "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck. Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two)", + "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck. Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two).", "ScaleUnit": "100%" }, { @@ -993,7 +991,7 @@ "MetricGroup": "MicroSeq;TopdownL3;tma_L3_group;tma_heavy_operations_group;tma_issueMC;tma_issueMS", "MetricName": "tma_microcode_sequencer", "MetricThreshold": "tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1", - "PublicDescription": "This metric represents fraction of slots the CPU was retiring uops fetched by the Microcode Sequencer (MS) unit. The MS is used for CISC instructions not supported by the default decoders (like repeat move strings; or CPUID); or by microcode assists used to address some operation modes (like in Floating Point assists). These cases can often be avoided. Sample with: IDQ.MS_UOPS. Related metrics: tma_l1_bound, tma_machine_clears, tma_ms_switches", + "PublicDescription": "This metric represents fraction of slots the CPU was retiring uops fetched by the Microcode Sequencer (MS) unit. The MS is used for CISC instructions not supported by the default decoders (like repeat move strings; or CPUID); or by microcode assists used to address some operation modes (like in Floating Point assists). These cases can often be avoided. Sample with: IDQ.MS_UOPS. Related metrics: tma_clears_resteers, tma_l1_bound, tma_machine_clears, tma_ms_switches", "ScaleUnit": "100%" }, { @@ -1002,7 +1000,7 @@ "MetricGroup": "DSBmiss;FetchBW;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group", "MetricName": "tma_mite", "MetricThreshold": "tma_mite > 0.1 & tma_fetch_bandwidth > 0.2", - "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to the MITE pipeline (the legacy decode pipeline). This pipeline is used for code that was not pre-cached in the DSB or LSD. For example; inefficiencies due to asymmetric decoders; use of long immediate or LCP can manifest as MITE fetch bandwidth bottleneck", + "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to the MITE pipeline (the legacy decode pipeline). This pipeline is used for code that was not pre-cached in the DSB or LSD. For example; inefficiencies due to asymmetric decoders; use of long immediate or LCP can manifest as MITE fetch bandwidth bottleneck.", "ScaleUnit": "100%" }, { @@ -1010,8 +1008,8 @@ "MetricExpr": "2 * IDQ.MS_SWITCHES / tma_info_thread_clks", "MetricGroup": "FetchLat;MicroSeq;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueMC;tma_issueMS;tma_issueMV;tma_issueSO", "MetricName": "tma_ms_switches", - "MetricThreshold": "tma_ms_switches > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", - "PublicDescription": "This metric estimates the fraction of cycles when the CPU was stalled due to switches of uop delivery to the Microcode Sequencer (MS). Commonly used instructions are optimized for delivery by the DSB (decoded i-cache) or MITE (legacy instruction decode) pipelines. Certain operations cannot be handled natively by the execution pipeline; and must be performed by microcode (small programs injected into the execution stream). Switching to the MS too often can negatively impact performance. The MS is designated to deliver long uop flows required by CISC instructions like CPUID; or uncommon conditions like Floating Point Assists when dealing with Denormals. Sample with: IDQ.MS_SWITCHES. Related metrics: tma_l1_bound, tma_machine_clears, tma_microcode_sequencer", + "MetricThreshold": "tma_ms_switches > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", + "PublicDescription": "This metric estimates the fraction of cycles when the CPU was stalled due to switches of uop delivery to the Microcode Sequencer (MS). Commonly used instructions are optimized for delivery by the DSB (decoded i-cache) or MITE (legacy instruction decode) pipelines. Certain operations cannot be handled natively by the execution pipeline; and must be performed by microcode (small programs injected into the execution stream). Switching to the MS too often can negatively impact performance. The MS is designated to deliver long uop flows required by CISC instructions like CPUID; or uncommon conditions like Floating Point Assists when dealing with Denormals. Sample with: IDQ.MS_SWITCHES. Related metrics: tma_clears_resteers, tma_l1_bound, tma_machine_clears, tma_microcode_sequencer, tma_mixing_vectors, tma_serializing_operation", "ScaleUnit": "100%" }, { @@ -1020,7 +1018,7 @@ "MetricGroup": "Compute;TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P", "MetricName": "tma_port_0", "MetricThreshold": "tma_port_0 > 0.6", - "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 0 ([SNB+] ALU; [HSW+] ALU and 2nd branch). Sample with: UOPS_DISPATCHED_PORT.PORT_0. Related metrics: tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", + "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 0 ([SNB+] ALU; [HSW+] ALU and 2nd branch). Sample with: UOPS_DISPATCHED.PORT_0. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%" }, { @@ -1029,7 +1027,7 @@ "MetricGroup": "TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P", "MetricName": "tma_port_1", "MetricThreshold": "tma_port_1 > 0.6", - "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 1 (ALU). Sample with: UOPS_DISPATCHED_PORT.PORT_1. Related metrics: tma_port_0, tma_port_5, tma_port_6, tma_ports_utilized_2", + "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 1 (ALU). Sample with: UOPS_DISPATCHED.PORT_1. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_5, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%" }, { @@ -1065,7 +1063,7 @@ "MetricGroup": "TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P", "MetricName": "tma_port_5", "MetricThreshold": "tma_port_5 > 0.6", - "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 5 ([SNB+] Branches and ALU; [HSW+] ALU). Sample with: UOPS_DISPATCHED_PORT.PORT_5. Related metrics: tma_port_0, tma_port_1, tma_port_6, tma_ports_utilized_2", + "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 5 ([SNB+] Branches and ALU; [HSW+] ALU). Sample with: UOPS_DISPATCHED.PORT_5. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%" }, { @@ -1074,7 +1072,7 @@ "MetricGroup": "TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P", "MetricName": "tma_port_6", "MetricThreshold": "tma_port_6 > 0.6", - "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 6 ([HSW+] Primary Branch and simple ALU). Sample with: UOPS_DISPATCHED_PORT.PORT_1. Related metrics: tma_port_0, tma_port_1, tma_port_5, tma_ports_utilized_2", + "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 6 ([HSW+] Primary Branch and simple ALU). Sample with: UOPS_DISPATCHED.PORT_1. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_ports_utilized_2", "ScaleUnit": "100%" }, { @@ -1089,46 +1087,46 @@ { "BriefDescription": "This metric estimates fraction of cycles the CPU performance was potentially limited due to Core computation issues (non divider-related)", "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "((min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.CYCLES_NO_EXECUTE) + (cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x1@ - (cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x3@ if tma_info_thread_ipc > 1.8 else cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x2@)) / 2 - (RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else 0) + RESOURCE_STALLS.SB if #SMT_on else min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.CYCLES_NO_EXECUTE) + cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x1@ - (cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x3@ if tma_info_thread_ipc > 1.8 else cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x2@) - (RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else 0) + RESOURCE_STALLS.SB) - RESOURCE_STALLS.SB - min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.STALLS_LDM_PENDING)) / tma_info_thread_clks", + "MetricExpr": "(min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.CYCLES_NO_EXECUTE) + (cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ - (cpu@UOPS_EXECUTED.CORE\\,cmask\\=3@ if tma_info_thread_ipc > 1.8 else cpu@UOPS_EXECUTED.CORE\\,cmask\\=2@)) / 2 - (RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else 0) + RESOURCE_STALLS.SB if #SMT_on else min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.CYCLES_NO_EXECUTE) + cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ - (cpu@UOPS_EXECUTED.CORE\\,cmask\\=3@ if tma_info_thread_ipc > 1.8 else cpu@UOPS_EXECUTED.CORE\\,cmask\\=2@) - (RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else 0) + RESOURCE_STALLS.SB - RESOURCE_STALLS.SB - min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.STALLS_LDM_PENDING)) / tma_info_thread_clks", "MetricGroup": "PortsUtil;TopdownL3;tma_L3_group;tma_core_bound_group", "MetricName": "tma_ports_utilization", - "MetricThreshold": "tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", - "PublicDescription": "This metric estimates fraction of cycles the CPU performance was potentially limited due to Core computation issues (non divider-related). Two distinct categories can be attributed into this metric: (1) heavy data-dependency among contiguous instructions would manifest in this metric - such cases are often referred to as low Instruction Level Parallelism (ILP). (2) Contention on some hardware execution unit other than Divider. For example; when there are too many multiply operations", + "MetricThreshold": "tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)", + "PublicDescription": "This metric estimates fraction of cycles the CPU performance was potentially limited due to Core computation issues (non divider-related). Two distinct categories can be attributed into this metric: (1) heavy data-dependency among contiguous instructions would manifest in this metric - such cases are often referred to as low Instruction Level Parallelism (ILP). (2) Contention on some hardware execution unit other than Divider. For example; when there are too many multiply operations.", "ScaleUnit": "100%" }, { "BriefDescription": "This metric represents fraction of cycles CPU executed no uops on any execution port (Logical Processor cycles since ICL, Physical Core cycles otherwise)", - "MetricExpr": "(cpu@UOPS_EXECUTED.CORE\\,inv\\=0x1\\,cmask\\=0x1@ / 2 if #SMT_on else min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.CYCLES_NO_EXECUTE) - (RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else 0)) / tma_info_core_core_clks", + "MetricExpr": "(cpu@UOPS_EXECUTED.CORE\\,inv\\,cmask\\=1@ / 2 if #SMT_on else (min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.CYCLES_NO_EXECUTE) - (RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else 0)) / tma_info_core_core_clks)", "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group", "MetricName": "tma_ports_utilized_0", - "MetricThreshold": "tma_ports_utilized_0 > 0.2 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", - "PublicDescription": "This metric represents fraction of cycles CPU executed no uops on any execution port (Logical Processor cycles since ICL, Physical Core cycles otherwise). Long-latency instructions like divides may contribute to this metric", + "MetricThreshold": "tma_ports_utilized_0 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric represents fraction of cycles CPU executed no uops on any execution port (Logical Processor cycles since ICL, Physical Core cycles otherwise). Long-latency instructions like divides may contribute to this metric.", "ScaleUnit": "100%" }, { "BriefDescription": "This metric represents fraction of cycles where the CPU executed total of 1 uop per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise)", - "MetricExpr": "((cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x1@ - cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x2@) / 2 if #SMT_on else cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x1@ - cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x2@) / tma_info_core_core_clks", + "MetricExpr": "((cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ - cpu@UOPS_EXECUTED.CORE\\,cmask\\=2@) / 2 if #SMT_on else (cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ - cpu@UOPS_EXECUTED.CORE\\,cmask\\=2@) / tma_info_core_core_clks)", "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_issueL1;tma_ports_utilization_group", "MetricName": "tma_ports_utilized_1", - "MetricThreshold": "tma_ports_utilized_1 > 0.2 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_ports_utilized_1 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", "PublicDescription": "This metric represents fraction of cycles where the CPU executed total of 1 uop per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise). This can be due to heavy data-dependency among software instructions; or over oversubscribing a particular hardware resource. In some other cases with high 1_Port_Utilized and L1_Bound; this metric can point to L1 data-cache latency bottleneck that may not necessarily manifest with complete execution starvation (due to the short L1 latency e.g. walking a linked list) - looking at the assembly can be helpful. Related metrics: tma_l1_bound", "ScaleUnit": "100%" }, { "BriefDescription": "This metric represents fraction of cycles CPU executed total of 2 uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise)", - "MetricExpr": "((cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x2@ - cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x3@) / 2 if #SMT_on else cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x2@ - cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x3@) / tma_info_core_core_clks", + "MetricExpr": "((cpu@UOPS_EXECUTED.CORE\\,cmask\\=2@ - cpu@UOPS_EXECUTED.CORE\\,cmask\\=3@) / 2 if #SMT_on else (cpu@UOPS_EXECUTED.CORE\\,cmask\\=2@ - cpu@UOPS_EXECUTED.CORE\\,cmask\\=3@) / tma_info_core_core_clks)", "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_issue2P;tma_ports_utilization_group", "MetricName": "tma_ports_utilized_2", - "MetricThreshold": "tma_ports_utilized_2 > 0.15 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", - "PublicDescription": "This metric represents fraction of cycles CPU executed total of 2 uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise). Loop Vectorization -most compilers feature auto-Vectorization options today- reduces pressure on the execution ports as multiple elements are calculated with same uop. Related metrics: tma_port_0, tma_port_1, tma_port_5, tma_port_6", + "MetricThreshold": "tma_ports_utilized_2 > 0.15 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric represents fraction of cycles CPU executed total of 2 uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise). Loop Vectorization -most compilers feature auto-Vectorization options today- reduces pressure on the execution ports as multiple elements are calculated with same uop. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of cycles CPU executed total of 3 or more uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise)", - "MetricExpr": "(cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x3@ / 2 if #SMT_on else cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x3@) / tma_info_core_core_clks", + "BriefDescription": "This metric represents fraction of cycles CPU executed total of 3 or more uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise).", + "MetricExpr": "(cpu@UOPS_EXECUTED.CORE\\,cmask\\=3@ / 2 if #SMT_on else cpu@UOPS_EXECUTED.CORE\\,cmask\\=3@) / tma_info_core_core_clks", "MetricGroup": "BvCB;PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group", "MetricName": "tma_ports_utilized_3m", - "MetricThreshold": "tma_ports_utilized_3m > 0.4 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_ports_utilized_3m > 0.4 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", "ScaleUnit": "100%" }, { @@ -1137,8 +1135,8 @@ "MetricExpr": "(200 * (MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_HITM * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.L3_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_L3_MISS_RETIRED.LOCAL_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_HITM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_FWD))) + 180 * (MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_FWD * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.L3_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_L3_MISS_RETIRED.LOCAL_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_HITM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_FWD)))) / tma_info_thread_clks", "MetricGroup": "Offcore;Server;Snoop;TopdownL5;tma_L5_group;tma_issueSyncxn;tma_mem_latency_group", "MetricName": "tma_remote_cache", - "MetricThreshold": "tma_remote_cache > 0.05 & tma_mem_latency > 0.1 & tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", - "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from remote cache in other sockets including synchronizations issues. This is caused often due to non-optimal NUMA allocations. Sample with: MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_HITM, MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_FWD. Related metrics: tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_machine_clears", + "MetricThreshold": "tma_remote_cache > 0.05 & (tma_mem_latency > 0.1 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))", + "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from remote cache in other sockets including synchronizations issues. This is caused often due to non-optimal NUMA allocations. #link to NUMA article. Sample with: MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_HITM_PS;MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_FWD_PS. Related metrics: tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_machine_clears", "ScaleUnit": "100%" }, { @@ -1146,8 +1144,8 @@ "MetricExpr": "310 * (MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_DRAM * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.L3_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_L3_MISS_RETIRED.LOCAL_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_HITM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_FWD))) / tma_info_thread_clks", "MetricGroup": "Server;Snoop;TopdownL5;tma_L5_group;tma_mem_latency_group", "MetricName": "tma_remote_mem", - "MetricThreshold": "tma_remote_mem > 0.1 & tma_mem_latency > 0.1 & tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", - "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from remote memory. This is caused often due to non-optimal NUMA allocations. Sample with: MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_DRAM", + "MetricThreshold": "tma_remote_mem > 0.1 & (tma_mem_latency > 0.1 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))", + "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from remote memory. This is caused often due to non-optimal NUMA allocations. #link to NUMA article. Sample with: MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_DRAM_PS", "ScaleUnit": "100%" }, { @@ -1167,7 +1165,7 @@ "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group", "MetricName": "tma_split_loads", "MetricThreshold": "tma_split_loads > 0.3", - "PublicDescription": "This metric estimates fraction of cycles handling memory load split accesses - load that cross 64-byte cache line boundary. Sample with: MEM_UOPS_RETIRED.SPLIT_LOADS", + "PublicDescription": "This metric estimates fraction of cycles handling memory load split accesses - load that cross 64-byte cache line boundary. Sample with: MEM_UOPS_RETIRED.SPLIT_LOADS_PS", "ScaleUnit": "100%" }, { @@ -1175,8 +1173,8 @@ "MetricExpr": "2 * MEM_UOPS_RETIRED.SPLIT_STORES / tma_info_core_core_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_issueSpSt;tma_store_bound_group", "MetricName": "tma_split_stores", - "MetricThreshold": "tma_split_stores > 0.2 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", - "PublicDescription": "This metric represents rate of split store accesses. Consider aligning your data to the 64-byte cache line granularity. Sample with: MEM_UOPS_RETIRED.SPLIT_STORES. Related metrics: tma_port_4", + "MetricThreshold": "tma_split_stores > 0.2 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric represents rate of split store accesses. Consider aligning your data to the 64-byte cache line granularity. Sample with: MEM_UOPS_RETIRED.SPLIT_STORES_PS. Related metrics: tma_port_4", "ScaleUnit": "100%" }, { @@ -1184,7 +1182,7 @@ "MetricExpr": "(OFFCORE_REQUESTS_BUFFER.SQ_FULL / 2 if #SMT_on else OFFCORE_REQUESTS_BUFFER.SQ_FULL) / tma_info_core_core_clks", "MetricGroup": "BvMB;MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_issueBW;tma_l3_bound_group", "MetricName": "tma_sq_full", - "MetricThreshold": "tma_sq_full > 0.3 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_sq_full > 0.3 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", "PublicDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors). Related metrics: tma_fb_full, tma_info_system_dram_bw_use, tma_mem_bandwidth", "ScaleUnit": "100%" }, @@ -1193,8 +1191,8 @@ "MetricExpr": "RESOURCE_STALLS.SB / tma_info_thread_clks", "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_store_bound", - "MetricThreshold": "tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", - "PublicDescription": "This metric estimates how often CPU was stalled due to RFO store memory accesses; RFO store issue a read-for-ownership request before the write. Even though store accesses do not typically stall out-of-order CPUs; there are few cases where stores can lead to actual stalls. This metric will be flagged should RFO stores be a bottleneck. Sample with: MEM_UOPS_RETIRED.ALL_STORES", + "MetricThreshold": "tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", + "PublicDescription": "This metric estimates how often CPU was stalled due to RFO store memory accesses; RFO store issue a read-for-ownership request before the write. Even though store accesses do not typically stall out-of-order CPUs; there are few cases where stores can lead to actual stalls. This metric will be flagged should RFO stores be a bottleneck. Sample with: MEM_UOPS_RETIRED.ALL_STORES_PS", "ScaleUnit": "100%" }, { @@ -1202,8 +1200,8 @@ "MetricExpr": "13 * LD_BLOCKS.STORE_FORWARD / tma_info_thread_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group", "MetricName": "tma_store_fwd_blk", - "MetricThreshold": "tma_store_fwd_blk > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", - "PublicDescription": "This metric roughly estimates fraction of cycles when the memory subsystem had loads blocked since they could not forward data from earlier (in program order) overlapping stores. To streamline memory operations in the pipeline; a load can avoid waiting for memory if a prior in-flight store is writing the data that the load wants to read (store forwarding process). However; in some cases the load may be blocked for a significant time pending the store forward. For example; when the prior store is writing a smaller region than the load is reading", + "MetricThreshold": "tma_store_fwd_blk > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric roughly estimates fraction of cycles when the memory subsystem had loads blocked since they could not forward data from earlier (in program order) overlapping stores. To streamline memory operations in the pipeline; a load can avoid waiting for memory if a prior in-flight store is writing the data that the load wants to read (store forwarding process). However; in some cases the load may be blocked for a significant time pending the store forward. For example; when the prior store is writing a smaller region than the load is reading.", "ScaleUnit": "100%" }, { @@ -1212,8 +1210,8 @@ "MetricExpr": "(L2_RQSTS.RFO_HIT * 9 * (1 - MEM_UOPS_RETIRED.LOCK_LOADS / MEM_UOPS_RETIRED.ALL_STORES) + (1 - MEM_UOPS_RETIRED.LOCK_LOADS / MEM_UOPS_RETIRED.ALL_STORES) * min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO)) / tma_info_thread_clks", "MetricGroup": "BvML;LockCont;MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_issueSL;tma_store_bound_group", "MetricName": "tma_store_latency", - "MetricThreshold": "tma_store_latency > 0.1 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", - "PublicDescription": "This metric estimates fraction of cycles the CPU spent handling L1D store misses. Store accesses usually less impact out-of-order core performance; however; holding resources for longer time can lead into undesired implications (e.g. contention on L1D fill-buffer entries - see FB_Full). Related metrics: tma_branch_resteers, tma_fb_full, tma_l3_hit_latency, tma_lock_latency", + "MetricThreshold": "tma_store_latency > 0.1 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric estimates fraction of cycles the CPU spent handling L1D store misses. Store accesses usually less impact out-of-order core performance; however; holding resources for longer time can lead into undesired implications (e.g. contention on L1D fill-buffer entries - see FB_Full). Related metrics: tma_fb_full, tma_lock_latency", "ScaleUnit": "100%" }, { diff --git a/tools/perf/pmu-events/arch/x86/icelake/cache.json b/tools/perf/pmu-events/arch/x86/icelake/cache.json index 015f70f157d1..e7bb2ca6f183 100644 --- a/tools/perf/pmu-events/arch/x86/icelake/cache.json +++ b/tools/perf/pmu-events/arch/x86/icelake/cache.json @@ -446,6 +446,16 @@ "UMask": "0x20" }, { + "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that have any type of response.", + "Counter": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OCR.DEMAND_CODE_RD.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x10004", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that hit a cacheline in the L3 where a snoop was sent or not.", "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -506,6 +516,16 @@ "UMask": "0x1" }, { + "BriefDescription": "Counts demand data reads that have any type of response.", + "Counter": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OCR.DEMAND_DATA_RD.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x10001", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { "BriefDescription": "Counts demand data reads that hit a cacheline in the L3 where a snoop was sent or not.", "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -566,6 +586,16 @@ "UMask": "0x1" }, { + "BriefDescription": "Counts demand reads for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that have any type of response.", + "Counter": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OCR.DEMAND_RFO.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x10002", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { "BriefDescription": "Counts demand reads for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that hit a cacheline in the L3 where a snoop was sent or not.", "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -626,6 +656,16 @@ "UMask": "0x1" }, { + "BriefDescription": "Counts L1 data cache prefetch requests and software prefetches (except PREFETCHW) that have any type of response.", + "Counter": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OCR.HWPF_L1D_AND_SWPF.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x10400", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { "BriefDescription": "Counts L1 data cache prefetch requests and software prefetches (except PREFETCHW) that hit a cacheline in the L3 where a snoop was sent or not.", "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -656,6 +696,16 @@ "UMask": "0x1" }, { + "BriefDescription": "Counts hardware prefetch data reads (which bring data to L2) that have any type of response.", + "Counter": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OCR.HWPF_L2_DATA_RD.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x10010", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { "BriefDescription": "Counts hardware prefetch data reads (which bring data to L2) that hit a cacheline in the L3 where a snoop was sent or not.", "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -716,6 +766,16 @@ "UMask": "0x1" }, { + "BriefDescription": "Counts hardware prefetch RFOs (which bring data to L2) that have any type of response.", + "Counter": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OCR.HWPF_L2_RFO.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x10020", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { "BriefDescription": "Counts hardware prefetch RFOs (which bring data to L2) that hit a cacheline in the L3 where a snoop was sent or not.", "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", diff --git a/tools/perf/pmu-events/arch/x86/icelake/icl-metrics.json b/tools/perf/pmu-events/arch/x86/icelake/icl-metrics.json index 63e28a03dc60..c5bfdb2f288b 100644 --- a/tools/perf/pmu-events/arch/x86/icelake/icl-metrics.json +++ b/tools/perf/pmu-events/arch/x86/icelake/icl-metrics.json @@ -89,12 +89,12 @@ "MetricExpr": "LD_BLOCKS_PARTIAL.ADDRESS_ALIAS / tma_info_thread_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group", "MetricName": "tma_4k_aliasing", - "MetricThreshold": "tma_4k_aliasing > 0.2 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", - "PublicDescription": "This metric estimates how often memory load accesses were aliased by preceding stores (in program order) with a 4K address offset. False match is possible; which incur a few cycles load re-issue. However; the short re-issue duration is often hidden by the out-of-order core and HW optimizations; hence a user may safely ignore a high value of this metric unless it manages to propagate up into parent nodes of the hierarchy (e.g. to L1_Bound)", + "MetricThreshold": "tma_4k_aliasing > 0.2 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric estimates how often memory load accesses were aliased by preceding stores (in program order) with a 4K address offset. False match is possible; which incur a few cycles load re-issue. However; the short re-issue duration is often hidden by the out-of-order core and HW optimizations; hence a user may safely ignore a high value of this metric unless it manages to propagate up into parent nodes of the hierarchy (e.g. to L1_Bound).", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution ports for ALU operations", + "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution ports for ALU operations.", "MetricExpr": "(UOPS_DISPATCHED.PORT_0 + UOPS_DISPATCHED.PORT_1 + UOPS_DISPATCHED.PORT_5 + UOPS_DISPATCHED.PORT_6) / (4 * tma_info_core_core_clks)", "MetricGroup": "TopdownL5;tma_L5_group;tma_ports_utilized_3m_group", "MetricName": "tma_alu_op_utilization", @@ -106,7 +106,7 @@ "MetricExpr": "34 * ASSISTS.ANY / tma_info_thread_slots", "MetricGroup": "BvIO;TopdownL4;tma_L4_group;tma_microcode_sequencer_group", "MetricName": "tma_assists", - "MetricThreshold": "tma_assists > 0.1 & tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1", + "MetricThreshold": "tma_assists > 0.1 & (tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1)", "PublicDescription": "This metric estimates fraction of slots the CPU retired uops delivered by the Microcode_Sequencer as a result of Assists. Assists are long sequences of uops that are required in certain corner-cases for operations that cannot be handled natively by the execution pipeline. For example; when working with very small floating point values (so-called Denormals); the FP units are not set up to perform these operations natively. Instead; a sequence of instructions to perform the computation on the Denormals is injected into the pipeline. Since these microcode sequences might be dozens of uops long; Assists can be extremely deleterious to performance and they can be avoided in many cases. Sample with: ASSISTS.ANY", "ScaleUnit": "100%" }, @@ -129,12 +129,12 @@ "MetricName": "tma_bad_speculation", "MetricThreshold": "tma_bad_speculation > 0.15", "MetricgroupNoGroup": "TopdownL1;Default", - "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example", + "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.", "ScaleUnit": "100%" }, { "BriefDescription": "Total pipeline cost of instruction fetch related bottlenecks by large code footprint programs (i-side cache; TLB and BTB misses)", - "MetricExpr": "100 * tma_fetch_latency * (tma_itlb_misses + tma_icache_misses + tma_unknown_branches) / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches)", + "MetricExpr": "100 * tma_fetch_latency * (tma_itlb_misses + tma_icache_misses + tma_unknown_branches) / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches)", "MetricGroup": "BigFootprint;BvBC;Fed;Frontend;IcMiss;MemoryTLB", "MetricName": "tma_bottleneck_big_code", "MetricThreshold": "tma_bottleneck_big_code > 20" @@ -149,7 +149,7 @@ }, { "BriefDescription": "Total pipeline cost of external Memory- or Cache-Bandwidth related bottlenecks", - "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_mem_bandwidth / (tma_mem_bandwidth + tma_mem_latency)) + tma_memory_bound * (tma_l3_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_sq_full / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_memory_bound * (tma_l1_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_fb_full / (tma_dtlb_load + tma_store_fwd_blk + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_4k_aliasing + tma_fb_full)))", + "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_mem_bandwidth / (tma_mem_bandwidth + tma_mem_latency)) + tma_memory_bound * (tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_sq_full / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_fb_full / (tma_4k_aliasing + tma_dtlb_load + tma_fb_full + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)))", "MetricGroup": "BvMB;Mem;MemoryBW;Offcore;tma_issueBW", "MetricName": "tma_bottleneck_cache_memory_bandwidth", "MetricThreshold": "tma_bottleneck_cache_memory_bandwidth > 20", @@ -157,7 +157,7 @@ }, { "BriefDescription": "Total pipeline cost of external Memory- or Cache-Latency related bottlenecks", - "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_mem_latency / (tma_mem_bandwidth + tma_mem_latency)) + tma_memory_bound * (tma_l3_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_l3_hit_latency / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_memory_bound * tma_l2_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound) + tma_memory_bound * (tma_l1_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_l1_latency_dependency / (tma_dtlb_load + tma_store_fwd_blk + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_4k_aliasing + tma_fb_full)) + tma_memory_bound * (tma_l1_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_lock_latency / (tma_dtlb_load + tma_store_fwd_blk + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_4k_aliasing + tma_fb_full)) + tma_memory_bound * (tma_l1_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_split_loads / (tma_dtlb_load + tma_store_fwd_blk + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_4k_aliasing + tma_fb_full)) + tma_memory_bound * (tma_store_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_split_stores / (tma_store_latency + tma_false_sharing + tma_split_stores + tma_streaming_stores + tma_dtlb_store)) + tma_memory_bound * (tma_store_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_store_latency / (tma_store_latency + tma_false_sharing + tma_split_stores + tma_streaming_stores + tma_dtlb_store)))", + "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_mem_latency / (tma_mem_bandwidth + tma_mem_latency)) + tma_memory_bound * (tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_l3_hit_latency / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_memory_bound * tma_l2_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) + tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_l1_latency_dependency / (tma_4k_aliasing + tma_dtlb_load + tma_fb_full + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_lock_latency / (tma_4k_aliasing + tma_dtlb_load + tma_fb_full + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_split_loads / (tma_4k_aliasing + tma_dtlb_load + tma_fb_full + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_memory_bound * (tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_split_stores / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency + tma_streaming_stores)) + tma_memory_bound * (tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_store_latency / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency + tma_streaming_stores)))", "MetricGroup": "BvML;Mem;MemoryLat;Offcore;tma_issueLat", "MetricName": "tma_bottleneck_cache_memory_latency", "MetricThreshold": "tma_bottleneck_cache_memory_latency > 20", @@ -165,22 +165,22 @@ }, { "BriefDescription": "Total pipeline cost when the execution is compute-bound - an estimation", - "MetricExpr": "100 * (tma_core_bound * tma_divider / (tma_divider + tma_serializing_operation + tma_ports_utilization) + tma_core_bound * (tma_ports_utilization / (tma_divider + tma_serializing_operation + tma_ports_utilization)) * (tma_ports_utilized_3m / (tma_ports_utilized_0 + tma_ports_utilized_1 + tma_ports_utilized_2 + tma_ports_utilized_3m)))", + "MetricExpr": "100 * (tma_core_bound * tma_divider / (tma_divider + tma_ports_utilization + tma_serializing_operation) + tma_core_bound * (tma_ports_utilization / (tma_divider + tma_ports_utilization + tma_serializing_operation)) * (tma_ports_utilized_3m / (tma_ports_utilized_0 + tma_ports_utilized_1 + tma_ports_utilized_2 + tma_ports_utilized_3m)))", "MetricGroup": "BvCB;Cor;tma_issueComp", "MetricName": "tma_bottleneck_compute_bound_est", "MetricThreshold": "tma_bottleneck_compute_bound_est > 20", - "PublicDescription": "Total pipeline cost when the execution is compute-bound - an estimation. Covers Core Bound when High ILP as well as when long-latency execution units are busy" + "PublicDescription": "Total pipeline cost when the execution is compute-bound - an estimation. Covers Core Bound when High ILP as well as when long-latency execution units are busy. Related metrics: " }, { "BriefDescription": "Total pipeline cost of instruction fetch bandwidth related bottlenecks (when the front-end could not sustain operations delivery to the back-end)", - "MetricExpr": "100 * (tma_frontend_bound - (1 - 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts) * tma_fetch_latency * tma_mispredicts_resteers / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches) - tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * (tma_fetch_latency * (tma_ms_switches + tma_branch_resteers * (tma_clears_resteers + 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts * tma_mispredicts_resteers) / (tma_mispredicts_resteers + tma_clears_resteers + tma_unknown_branches)) / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches) + tma_fetch_bandwidth * tma_ms / (tma_mite + tma_dsb + tma_lsd + tma_ms))) - tma_bottleneck_big_code", + "MetricExpr": "100 * (tma_frontend_bound - (1 - 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts) * tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) - tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * (tma_fetch_latency * (tma_ms_switches + tma_branch_resteers * (tma_clears_resteers + 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts * tma_mispredicts_resteers) / (tma_clears_resteers + tma_mispredicts_resteers + tma_unknown_branches)) / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) + tma_fetch_bandwidth * tma_ms / (tma_dsb + tma_lsd + tma_mite + tma_ms))) - tma_bottleneck_big_code", "MetricGroup": "BvFB;Fed;FetchBW;Frontend", "MetricName": "tma_bottleneck_instruction_fetch_bw", "MetricThreshold": "tma_bottleneck_instruction_fetch_bw > 20" }, { "BriefDescription": "Total pipeline cost of irregular execution (e.g", - "MetricExpr": "100 * (tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * (tma_fetch_latency * (tma_ms_switches + tma_branch_resteers * (tma_clears_resteers + 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts * tma_mispredicts_resteers) / (tma_mispredicts_resteers + tma_clears_resteers + tma_unknown_branches)) / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches) + tma_fetch_bandwidth * tma_ms / (tma_mite + tma_dsb + tma_lsd + tma_ms)) + 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts * tma_branch_mispredicts + tma_machine_clears * tma_other_nukes / tma_other_nukes + tma_core_bound * (tma_serializing_operation + tma_core_bound * RS_EVENTS.EMPTY_CYCLES / tma_info_thread_clks * tma_ports_utilized_0) / (tma_divider + tma_serializing_operation + tma_ports_utilization) + tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * tma_heavy_operations)", + "MetricExpr": "100 * (tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * (tma_fetch_latency * (tma_ms_switches + tma_branch_resteers * (tma_clears_resteers + 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts * tma_mispredicts_resteers) / (tma_clears_resteers + tma_mispredicts_resteers + tma_unknown_branches)) / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) + tma_fetch_bandwidth * tma_ms / (tma_dsb + tma_lsd + tma_mite + tma_ms)) + 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts * tma_branch_mispredicts + tma_machine_clears * tma_other_nukes / tma_other_nukes + tma_core_bound * (tma_serializing_operation + tma_core_bound * RS_EVENTS.EMPTY_CYCLES / tma_info_thread_clks * tma_ports_utilized_0) / (tma_divider + tma_ports_utilization + tma_serializing_operation) + tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * tma_heavy_operations)", "MetricGroup": "Bad;BvIO;Cor;Ret;tma_issueMS", "MetricName": "tma_bottleneck_irregular_overhead", "MetricThreshold": "tma_bottleneck_irregular_overhead > 10", @@ -188,7 +188,7 @@ }, { "BriefDescription": "Total pipeline cost of Memory Address Translation related bottlenecks (data-side TLBs)", - "MetricExpr": "100 * (tma_memory_bound * (tma_l1_bound / max(tma_memory_bound, tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_dtlb_load / max(tma_l1_bound, tma_dtlb_load + tma_store_fwd_blk + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_4k_aliasing + tma_fb_full)) + tma_memory_bound * (tma_store_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_dtlb_store / (tma_store_latency + tma_false_sharing + tma_split_stores + tma_streaming_stores + tma_dtlb_store)))", + "MetricExpr": "100 * (tma_memory_bound * (tma_l1_bound / max(tma_memory_bound, tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_dtlb_load / max(tma_l1_bound, tma_4k_aliasing + tma_dtlb_load + tma_fb_full + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_memory_bound * (tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_dtlb_store / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency + tma_streaming_stores)))", "MetricGroup": "BvMT;Mem;MemoryTLB;Offcore;tma_issueTLB", "MetricName": "tma_bottleneck_memory_data_tlbs", "MetricThreshold": "tma_bottleneck_memory_data_tlbs > 20", @@ -196,15 +196,15 @@ }, { "BriefDescription": "Total pipeline cost of Memory Synchronization related bottlenecks (data transfers and coherency updates across processors)", - "MetricExpr": "100 * (tma_memory_bound * (tma_l3_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound) * (tma_contested_accesses + tma_data_sharing) / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full) + tma_store_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound) * tma_false_sharing / (tma_store_latency + tma_false_sharing + tma_split_stores + tma_streaming_stores + tma_dtlb_store - tma_store_latency)) + tma_machine_clears * (1 - tma_other_nukes / tma_other_nukes))", + "MetricExpr": "100 * (tma_memory_bound * (tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_contested_accesses + tma_data_sharing) / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full) + tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * tma_false_sharing / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency + tma_streaming_stores - tma_store_latency)) + tma_machine_clears * (1 - tma_other_nukes / tma_other_nukes))", "MetricGroup": "BvMS;LockCont;Mem;Offcore;tma_issueSyncxn", "MetricName": "tma_bottleneck_memory_synchronization", "MetricThreshold": "tma_bottleneck_memory_synchronization > 10", - "PublicDescription": "Total pipeline cost of Memory Synchronization related bottlenecks (data transfers and coherency updates across processors). Related metrics: tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_machine_clears" + "PublicDescription": "Total pipeline cost of Memory Synchronization related bottlenecks (data transfers and coherency updates across processors). Related metrics: tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_machine_clears, tma_remote_cache" }, { "BriefDescription": "Total pipeline cost of Branch Misprediction related bottlenecks", - "MetricExpr": "100 * (1 - 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts) * (tma_branch_mispredicts + tma_fetch_latency * tma_mispredicts_resteers / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches))", + "MetricExpr": "100 * (1 - 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts) * (tma_branch_mispredicts + tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches))", "MetricGroup": "Bad;BadSpec;BrMispredicts;BvMP;tma_issueBM", "MetricName": "tma_bottleneck_mispredictions", "MetricThreshold": "tma_bottleneck_mispredictions > 20", @@ -216,17 +216,17 @@ "MetricGroup": "BvOB;Cor;Offcore", "MetricName": "tma_bottleneck_other_bottlenecks", "MetricThreshold": "tma_bottleneck_other_bottlenecks > 20", - "PublicDescription": "Total pipeline cost of remaining bottlenecks in the back-end. Examples include data-dependencies (Core Bound when Low ILP) and other unlisted memory-related stalls" + "PublicDescription": "Total pipeline cost of remaining bottlenecks in the back-end. Examples include data-dependencies (Core Bound when Low ILP) and other unlisted memory-related stalls." }, { - "BriefDescription": "Total pipeline cost of \"useful operations\" - the portion of Retiring category not covered by Branching_Overhead nor Irregular_Overhead", + "BriefDescription": "Total pipeline cost of \"useful operations\" - the portion of Retiring category not covered by Branching_Overhead nor Irregular_Overhead.", "MetricExpr": "100 * (tma_retiring - (BR_INST_RETIRED.ALL_BRANCHES + 2 * BR_INST_RETIRED.NEAR_CALL + INST_RETIRED.NOP) / tma_info_thread_slots - tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * tma_heavy_operations)", "MetricGroup": "BvUW;Ret", "MetricName": "tma_bottleneck_useful_work", "MetricThreshold": "tma_bottleneck_useful_work > 20" }, { - "BriefDescription": "This metric represents fraction of slots where the CPU was retiring branch instructions", + "BriefDescription": "This metric represents fraction of slots where the CPU was retiring branch instructions.", "MetricExpr": "tma_light_operations * BR_INST_RETIRED.ALL_BRANCHES / (tma_retiring * tma_info_thread_slots)", "MetricGroup": "Branches;BvBO;Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group", "MetricName": "tma_branch_instructions", @@ -248,8 +248,8 @@ "MetricExpr": "INT_MISC.CLEAR_RESTEER_CYCLES / tma_info_thread_clks + tma_unknown_branches", "MetricGroup": "FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group", "MetricName": "tma_branch_resteers", - "MetricThreshold": "tma_branch_resteers > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", - "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers. Branch Resteers estimates the Frontend delay in fetching operations from corrected path; following all sorts of miss-predicted branches. For example; branchy code with lots of miss-predictions might get categorized under Branch Resteers. Note the value of this node may overlap with its siblings. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_l3_hit_latency, tma_store_latency", + "MetricThreshold": "tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers. Branch Resteers estimates the Frontend delay in fetching operations from corrected path; following all sorts of miss-predicted branches. For example; branchy code with lots of miss-predictions might get categorized under Branch Resteers. Note the value of this node may overlap with its siblings. Sample with: BR_MISP_RETIRED.ALL_BRANCHES", "ScaleUnit": "100%" }, { @@ -257,8 +257,8 @@ "MetricExpr": "max(0, tma_microcode_sequencer - tma_assists)", "MetricGroup": "TopdownL4;tma_L4_group;tma_microcode_sequencer_group", "MetricName": "tma_cisc", - "MetricThreshold": "tma_cisc > 0.1 & tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1", - "PublicDescription": "This metric estimates fraction of cycles the CPU retired uops originated from CISC (complex instruction set computer) instruction. A CISC instruction has multiple uops that are required to perform the instruction's functionality as in the case of read-modify-write as an example. Since these instructions require multiple uops they may or may not imply sub-optimal use of machine resources", + "MetricThreshold": "tma_cisc > 0.1 & (tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1)", + "PublicDescription": "This metric estimates fraction of cycles the CPU retired uops originated from CISC (complex instruction set computer) instruction. A CISC instruction has multiple uops that are required to perform the instruction's functionality as in the case of read-modify-write as an example. Since these instructions require multiple uops they may or may not imply sub-optimal use of machine resources.", "ScaleUnit": "100%" }, { @@ -266,24 +266,24 @@ "MetricExpr": "(1 - BR_MISP_RETIRED.ALL_BRANCHES / (BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT)) * INT_MISC.CLEAR_RESTEER_CYCLES / tma_info_thread_clks", "MetricGroup": "BadSpec;MachineClears;TopdownL4;tma_L4_group;tma_branch_resteers_group;tma_issueMC", "MetricName": "tma_clears_resteers", - "MetricThreshold": "tma_clears_resteers > 0.05 & tma_branch_resteers > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricThreshold": "tma_clears_resteers > 0.05 & (tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))", "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Machine Clears. Sample with: INT_MISC.CLEAR_RESTEER_CYCLES. Related metrics: tma_l1_bound, tma_machine_clears, tma_microcode_sequencer, tma_ms_switches", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates fraction of cycles the CPU was stalled due to instruction cache misses that hit in the L2 cache", + "BriefDescription": "This metric estimates fraction of cycles the CPU was stalled due to instruction cache misses that hit in the L2 cache.", "MetricExpr": "max(0, tma_icache_misses - tma_code_l2_miss)", "MetricGroup": "FetchLat;IcMiss;Offcore;TopdownL4;tma_L4_group;tma_icache_misses_group", "MetricName": "tma_code_l2_hit", - "MetricThreshold": "tma_code_l2_hit > 0.05 & tma_icache_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricThreshold": "tma_code_l2_hit > 0.05 & (tma_icache_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates fraction of cycles the CPU was stalled due to instruction cache misses that miss in the L2 cache", + "BriefDescription": "This metric estimates fraction of cycles the CPU was stalled due to instruction cache misses that miss in the L2 cache.", "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_CODE_RD / tma_info_thread_clks", "MetricGroup": "FetchLat;IcMiss;Offcore;TopdownL4;tma_L4_group;tma_icache_misses_group", "MetricName": "tma_code_l2_miss", - "MetricThreshold": "tma_code_l2_miss > 0.05 & tma_icache_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricThreshold": "tma_code_l2_miss > 0.05 & (tma_icache_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))", "ScaleUnit": "100%" }, { @@ -291,7 +291,7 @@ "MetricExpr": "max(0, tma_itlb_misses - tma_code_stlb_miss)", "MetricGroup": "FetchLat;MemoryTLB;TopdownL4;tma_L4_group;tma_itlb_misses_group", "MetricName": "tma_code_stlb_hit", - "MetricThreshold": "tma_code_stlb_hit > 0.05 & tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricThreshold": "tma_code_stlb_hit > 0.05 & (tma_itlb_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))", "ScaleUnit": "100%" }, { @@ -299,33 +299,33 @@ "MetricExpr": "ITLB_MISSES.WALK_ACTIVE / tma_info_thread_clks", "MetricGroup": "FetchLat;MemoryTLB;TopdownL4;tma_L4_group;tma_itlb_misses_group", "MetricName": "tma_code_stlb_miss", - "MetricThreshold": "tma_code_stlb_miss > 0.05 & tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricThreshold": "tma_code_stlb_miss > 0.05 & (tma_itlb_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 2 or 4 MB pages for (instruction) code accesses", + "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 2 or 4 MB pages for (instruction) code accesses.", "MetricExpr": "tma_code_stlb_miss * ITLB_MISSES.WALK_COMPLETED_2M_4M / (ITLB_MISSES.WALK_COMPLETED_4K + ITLB_MISSES.WALK_COMPLETED_2M_4M)", "MetricGroup": "FetchLat;MemoryTLB;TopdownL5;tma_L5_group;tma_code_stlb_miss_group", "MetricName": "tma_code_stlb_miss_2m", - "MetricThreshold": "tma_code_stlb_miss_2m > 0.05 & tma_code_stlb_miss > 0.05 & tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricThreshold": "tma_code_stlb_miss_2m > 0.05 & (tma_code_stlb_miss > 0.05 & (tma_itlb_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)))", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 4 KB pages for (instruction) code accesses", + "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 4 KB pages for (instruction) code accesses.", "MetricExpr": "tma_code_stlb_miss * ITLB_MISSES.WALK_COMPLETED_4K / (ITLB_MISSES.WALK_COMPLETED_4K + ITLB_MISSES.WALK_COMPLETED_2M_4M)", "MetricGroup": "FetchLat;MemoryTLB;TopdownL5;tma_L5_group;tma_code_stlb_miss_group", "MetricName": "tma_code_stlb_miss_4k", - "MetricThreshold": "tma_code_stlb_miss_4k > 0.05 & tma_code_stlb_miss > 0.05 & tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricThreshold": "tma_code_stlb_miss_4k > 0.05 & (tma_code_stlb_miss > 0.05 & (tma_itlb_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)))", "ScaleUnit": "100%" }, { "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses", "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "((32.5 * tma_info_system_core_frequency - 3.5 * tma_info_system_core_frequency) * MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM + (27 * tma_info_system_core_frequency - 3.5 * tma_info_system_core_frequency) * MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks", + "MetricExpr": "(29 * tma_info_system_core_frequency * MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM + 23.5 * tma_info_system_core_frequency * MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks", "MetricGroup": "BvMS;DataSharing;LockCont;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group", "MetricName": "tma_contested_accesses", - "MetricThreshold": "tma_contested_accesses > 0.05 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", - "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses. Contested accesses occur when data written by one Logical Processor are read by another Logical Processor on a different Physical Core. Examples of contested accesses include synchronizations such as locks; true data sharing such as modified locked variables; and false sharing. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM, MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS. Related metrics: tma_bottleneck_memory_synchronization, tma_data_sharing, tma_false_sharing, tma_machine_clears", + "MetricThreshold": "tma_contested_accesses > 0.05 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses. Contested accesses occur when data written by one Logical Processor are read by another Logical Processor on a different Physical Core. Examples of contested accesses include synchronizations such as locks; true data sharing such as modified locked variables; and false sharing. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM_PS;MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS_PS. Related metrics: tma_bottleneck_memory_synchronization, tma_data_sharing, tma_false_sharing, tma_machine_clears, tma_remote_cache", "ScaleUnit": "100%" }, { @@ -335,25 +335,25 @@ "MetricName": "tma_core_bound", "MetricThreshold": "tma_core_bound > 0.1 & tma_backend_bound > 0.2", "MetricgroupNoGroup": "TopdownL2", - "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck. Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations)", + "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck. Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations).", "ScaleUnit": "100%" }, { "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses", "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "(27 * tma_info_system_core_frequency - 3.5 * tma_info_system_core_frequency) * MEM_LOAD_L3_HIT_RETIRED.XSNP_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks", + "MetricExpr": "23.5 * tma_info_system_core_frequency * MEM_LOAD_L3_HIT_RETIRED.XSNP_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks", "MetricGroup": "BvMS;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group", "MetricName": "tma_data_sharing", - "MetricThreshold": "tma_data_sharing > 0.05 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", - "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses. Data shared by multiple Logical Processors (even just read shared) may cause increased access latency due to cache coherency. Excessive data sharing can drastically harm multithreaded performance. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_HIT. Related metrics: tma_bottleneck_memory_synchronization, tma_contested_accesses, tma_false_sharing, tma_machine_clears", + "MetricThreshold": "tma_data_sharing > 0.05 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses. Data shared by multiple Logical Processors (even just read shared) may cause increased access latency due to cache coherency. Excessive data sharing can drastically harm multithreaded performance. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_HIT_PS. Related metrics: tma_bottleneck_memory_synchronization, tma_contested_accesses, tma_false_sharing, tma_machine_clears, tma_remote_cache", "ScaleUnit": "100%" }, { "BriefDescription": "This metric represents fraction of cycles where decoder-0 was the only active decoder", - "MetricExpr": "(cpu@INST_DECODED.DECODERS\\,cmask\\=0x1@ - cpu@INST_DECODED.DECODERS\\,cmask\\=0x2@) / tma_info_core_core_clks / 2", + "MetricExpr": "(cpu@INST_DECODED.DECODERS\\,cmask\\=1@ - cpu@INST_DECODED.DECODERS\\,cmask\\=2@) / tma_info_core_core_clks / 2", "MetricGroup": "DSBmiss;FetchBW;TopdownL4;tma_L4_group;tma_issueD0;tma_mite_group", "MetricName": "tma_decoder0_alone", - "MetricThreshold": "tma_decoder0_alone > 0.1 & tma_mite > 0.1 & tma_fetch_bandwidth > 0.2", + "MetricThreshold": "tma_decoder0_alone > 0.1 & (tma_mite > 0.1 & tma_fetch_bandwidth > 0.2)", "PublicDescription": "This metric represents fraction of cycles where decoder-0 was the only active decoder. Related metrics: tma_few_uops_instructions", "ScaleUnit": "100%" }, @@ -362,7 +362,7 @@ "MetricExpr": "ARITH.DIVIDER_ACTIVE / tma_info_thread_clks", "MetricGroup": "BvCB;TopdownL3;tma_L3_group;tma_core_bound_group", "MetricName": "tma_divider", - "MetricThreshold": "tma_divider > 0.2 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_divider > 0.2 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)", "PublicDescription": "This metric represents fraction of cycles where the Divider unit was active. Divide and square root instructions are performed by the Divider unit and can take considerably longer latency than integer or Floating Point addition; subtraction; or multiplication. Sample with: ARITH.DIVIDER_ACTIVE", "ScaleUnit": "100%" }, @@ -372,7 +372,7 @@ "MetricExpr": "CYCLE_ACTIVITY.STALLS_L3_MISS / tma_info_thread_clks + (CYCLE_ACTIVITY.STALLS_L1D_MISS - CYCLE_ACTIVITY.STALLS_L2_MISS) / tma_info_thread_clks - tma_l2_bound", "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_dram_bound", - "MetricThreshold": "tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", "PublicDescription": "This metric estimates how often the CPU was stalled on accesses to external memory (DRAM) by loads. Better caching can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L3_MISS", "ScaleUnit": "100%" }, @@ -382,7 +382,7 @@ "MetricGroup": "DSB;FetchBW;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group", "MetricName": "tma_dsb", "MetricThreshold": "tma_dsb > 0.15 & tma_fetch_bandwidth > 0.2", - "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to DSB (decoded uop cache) fetch pipeline. For example; inefficient utilization of the DSB cache structure or bank conflict when reading from it; are categorized here", + "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to DSB (decoded uop cache) fetch pipeline. For example; inefficient utilization of the DSB cache structure or bank conflict when reading from it; are categorized here.", "ScaleUnit": "100%" }, { @@ -390,26 +390,26 @@ "MetricExpr": "DSB2MITE_SWITCHES.PENALTY_CYCLES / tma_info_thread_clks", "MetricGroup": "DSBmiss;FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueFB", "MetricName": "tma_dsb_switches", - "MetricThreshold": "tma_dsb_switches > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", - "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines. The DSB (decoded i-cache) is a Uop Cache where the front-end directly delivers Uops (micro operations) avoiding heavy x86 decoding. The DSB pipeline has shorter latency and delivered higher bandwidth than the MITE (legacy instruction decode pipeline). Switching between the two pipelines can cause penalties hence this metric measures the exposed penalty. Sample with: FRONTEND_RETIRED.DSB_MISS. Related metrics: tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp", + "MetricThreshold": "tma_dsb_switches > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines. The DSB (decoded i-cache) is a Uop Cache where the front-end directly delivers Uops (micro operations) avoiding heavy x86 decoding. The DSB pipeline has shorter latency and delivered higher bandwidth than the MITE (legacy instruction decode pipeline). Switching between the two pipelines can cause penalties hence this metric measures the exposed penalty. Sample with: FRONTEND_RETIRED.DSB_MISS_PS. Related metrics: tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp", "ScaleUnit": "100%" }, { "BriefDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses", - "MetricExpr": "min(7 * cpu@DTLB_LOAD_MISSES.STLB_HIT\\,cmask\\=0x1@ + DTLB_LOAD_MISSES.WALK_ACTIVE, max(CYCLE_ACTIVITY.CYCLES_MEM_ANY - CYCLE_ACTIVITY.CYCLES_L1D_MISS, 0)) / tma_info_thread_clks", + "MetricExpr": "min(7 * cpu@DTLB_LOAD_MISSES.STLB_HIT\\,cmask\\=1@ + DTLB_LOAD_MISSES.WALK_ACTIVE, max(CYCLE_ACTIVITY.CYCLES_MEM_ANY - CYCLE_ACTIVITY.CYCLES_L1D_MISS, 0)) / tma_info_thread_clks", "MetricGroup": "BvMT;MemoryTLB;TopdownL4;tma_L4_group;tma_issueTLB;tma_l1_bound_group", "MetricName": "tma_dtlb_load", - "MetricThreshold": "tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", - "PublicDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses. TLBs (Translation Look-aside Buffers) are processor caches for recently used entries out of the Page Tables that are used to map virtual- to physical-addresses by the operating system. This metric approximates the potential delay of demand loads missing the first-level data TLB (assuming worst case scenario with back to back misses to different pages). This includes hitting in the second-level TLB (STLB) as well as performing a hardware page walk on an STLB miss. Sample with: MEM_INST_RETIRED.STLB_MISS_LOADS. Related metrics: tma_bottleneck_memory_data_tlbs, tma_dtlb_store", + "MetricThreshold": "tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses. TLBs (Translation Look-aside Buffers) are processor caches for recently used entries out of the Page Tables that are used to map virtual- to physical-addresses by the operating system. This metric approximates the potential delay of demand loads missing the first-level data TLB (assuming worst case scenario with back to back misses to different pages). This includes hitting in the second-level TLB (STLB) as well as performing a hardware page walk on an STLB miss. Sample with: MEM_INST_RETIRED.STLB_MISS_LOADS_PS. Related metrics: tma_bottleneck_memory_data_tlbs, tma_dtlb_store", "ScaleUnit": "100%" }, { "BriefDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses", - "MetricExpr": "(7 * cpu@DTLB_STORE_MISSES.STLB_HIT\\,cmask\\=0x1@ + DTLB_STORE_MISSES.WALK_ACTIVE) / tma_info_core_core_clks", + "MetricExpr": "(7 * cpu@DTLB_STORE_MISSES.STLB_HIT\\,cmask\\=1@ + DTLB_STORE_MISSES.WALK_ACTIVE) / tma_info_core_core_clks", "MetricGroup": "BvMT;MemoryTLB;TopdownL4;tma_L4_group;tma_issueTLB;tma_store_bound_group", "MetricName": "tma_dtlb_store", - "MetricThreshold": "tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", - "PublicDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses. As with ordinary data caching; focus on improving data locality and reducing working-set size to reduce DTLB overhead. Additionally; consider using profile-guided optimization (PGO) to collocate frequently-used data on the same page. Try using larger page sizes for large amounts of frequently-used data. Sample with: MEM_INST_RETIRED.STLB_MISS_STORES. Related metrics: tma_bottleneck_memory_data_tlbs, tma_dtlb_load", + "MetricThreshold": "tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses. As with ordinary data caching; focus on improving data locality and reducing working-set size to reduce DTLB overhead. Additionally; consider using profile-guided optimization (PGO) to collocate frequently-used data on the same page. Try using larger page sizes for large amounts of frequently-used data. Sample with: MEM_INST_RETIRED.STLB_MISS_STORES_PS. Related metrics: tma_bottleneck_memory_data_tlbs, tma_dtlb_load", "ScaleUnit": "100%" }, { @@ -417,8 +417,8 @@ "MetricExpr": "32.5 * tma_info_system_core_frequency * OCR.DEMAND_RFO.L3_HIT.SNOOP_HITM / tma_info_thread_clks", "MetricGroup": "BvMS;DataSharing;LockCont;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_store_bound_group", "MetricName": "tma_false_sharing", - "MetricThreshold": "tma_false_sharing > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", - "PublicDescription": "This metric roughly estimates how often CPU was handling synchronizations due to False Sharing. False Sharing is a multithreading hiccup; where multiple Logical Processors contend on different data-elements mapped into the same cache line. Sample with: OCR.DEMAND_RFO.L3_HIT.SNOOP_HITM. Related metrics: tma_bottleneck_memory_synchronization, tma_contested_accesses, tma_data_sharing, tma_machine_clears", + "MetricThreshold": "tma_false_sharing > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric roughly estimates how often CPU was handling synchronizations due to False Sharing. False Sharing is a multithreading hiccup; where multiple Logical Processors contend on different data-elements mapped into the same cache line. Sample with: OCR.DEMAND_RFO.L3_HIT.SNOOP_HITM. Related metrics: tma_bottleneck_memory_synchronization, tma_contested_accesses, tma_data_sharing, tma_machine_clears, tma_remote_cache", "ScaleUnit": "100%" }, { @@ -437,7 +437,7 @@ "MetricName": "tma_fetch_bandwidth", "MetricThreshold": "tma_fetch_bandwidth > 0.2", "MetricgroupNoGroup": "TopdownL2", - "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues. For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Sample with: FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1, FRONTEND_RETIRED.LATENCY_GE_1, FRONTEND_RETIRED.LATENCY_GE_2. Related metrics: tma_dsb_switches, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp", + "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues. For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Sample with: FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1;FRONTEND_RETIRED.LATENCY_GE_1;FRONTEND_RETIRED.LATENCY_GE_2. Related metrics: tma_dsb_switches, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp", "ScaleUnit": "100%" }, { @@ -447,7 +447,7 @@ "MetricName": "tma_fetch_latency", "MetricThreshold": "tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", "MetricgroupNoGroup": "TopdownL2", - "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues. For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: FRONTEND_RETIRED.LATENCY_GE_16, FRONTEND_RETIRED.LATENCY_GE_8", + "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues. For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: FRONTEND_RETIRED.LATENCY_GE_16_PS;FRONTEND_RETIRED.LATENCY_GE_8_PS", "ScaleUnit": "100%" }, { @@ -465,7 +465,7 @@ "MetricGroup": "HPC;TopdownL3;tma_L3_group;tma_light_operations_group", "MetricName": "tma_fp_arith", "MetricThreshold": "tma_fp_arith > 0.2 & tma_light_operations > 0.6", - "PublicDescription": "This metric represents overall arithmetic floating-point (FP) operations fraction the CPU has executed (retired). Note this metric's value may exceed its parent due to use of \"Uops\" CountDomain and FMA double-counting", + "PublicDescription": "This metric represents overall arithmetic floating-point (FP) operations fraction the CPU has executed (retired). Note this metric's value may exceed its parent due to use of \"Uops\" CountDomain and FMA double-counting.", "ScaleUnit": "100%" }, { @@ -474,15 +474,15 @@ "MetricGroup": "HPC;TopdownL5;tma_L5_group;tma_assists_group", "MetricName": "tma_fp_assists", "MetricThreshold": "tma_fp_assists > 0.1", - "PublicDescription": "This metric roughly estimates fraction of slots the CPU retired uops as a result of handing Floating Point (FP) Assists. FP Assist may apply when working with very small floating point values (so-called Denormals)", + "PublicDescription": "This metric roughly estimates fraction of slots the CPU retired uops as a result of handing Floating Point (FP) Assists. FP Assist may apply when working with very small floating point values (so-called Denormals).", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of cycles where the Floating-Point Divider unit was active", + "BriefDescription": "This metric represents fraction of cycles where the Floating-Point Divider unit was active.", "MetricExpr": "ARITH.FP_DIVIDER_ACTIVE / tma_info_thread_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_divider_group", "MetricName": "tma_fp_divider", - "MetricThreshold": "tma_fp_divider > 0.2 & tma_divider > 0.2 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_fp_divider > 0.2 & (tma_divider > 0.2 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", "ScaleUnit": "100%" }, { @@ -490,7 +490,7 @@ "MetricExpr": "FP_ARITH_INST_RETIRED.SCALAR / (tma_retiring * tma_info_thread_slots)", "MetricGroup": "Compute;Flops;TopdownL4;tma_L4_group;tma_fp_arith_group;tma_issue2P", "MetricName": "tma_fp_scalar", - "MetricThreshold": "tma_fp_scalar > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6", + "MetricThreshold": "tma_fp_scalar > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6)", "PublicDescription": "This metric approximates arithmetic floating-point (FP) scalar uops fraction the CPU has retired. May overcount due to FMA double counting. Related metrics: tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%" }, @@ -499,7 +499,7 @@ "MetricExpr": "FP_ARITH_INST_RETIRED.VECTOR / (tma_retiring * tma_info_thread_slots)", "MetricGroup": "Compute;Flops;TopdownL4;tma_L4_group;tma_fp_arith_group;tma_issue2P", "MetricName": "tma_fp_vector", - "MetricThreshold": "tma_fp_vector > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6", + "MetricThreshold": "tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6)", "PublicDescription": "This metric approximates arithmetic floating-point (FP) vector uops fraction the CPU has retired aggregated across all vector widths. May overcount due to FMA double counting. Related metrics: tma_fp_scalar, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%" }, @@ -508,7 +508,7 @@ "MetricExpr": "(FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE) / (tma_retiring * tma_info_thread_slots)", "MetricGroup": "Compute;Flops;TopdownL5;tma_L5_group;tma_fp_vector_group;tma_issue2P", "MetricName": "tma_fp_vector_128b", - "MetricThreshold": "tma_fp_vector_128b > 0.1 & tma_fp_vector > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6", + "MetricThreshold": "tma_fp_vector_128b > 0.1 & (tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6))", "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 128-bit wide vectors. May overcount due to FMA double counting prior to LNL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%" }, @@ -517,7 +517,7 @@ "MetricExpr": "(FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE) / (tma_retiring * tma_info_thread_slots)", "MetricGroup": "Compute;Flops;TopdownL5;tma_L5_group;tma_fp_vector_group;tma_issue2P", "MetricName": "tma_fp_vector_256b", - "MetricThreshold": "tma_fp_vector_256b > 0.1 & tma_fp_vector > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6", + "MetricThreshold": "tma_fp_vector_256b > 0.1 & (tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6))", "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 256-bit wide vectors. May overcount due to FMA double counting prior to LNL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%" }, @@ -526,7 +526,7 @@ "MetricExpr": "(FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE) / (tma_retiring * tma_info_thread_slots)", "MetricGroup": "Compute;Flops;TopdownL5;tma_L5_group;tma_fp_vector_group;tma_issue2P", "MetricName": "tma_fp_vector_512b", - "MetricThreshold": "tma_fp_vector_512b > 0.1 & tma_fp_vector > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6", + "MetricThreshold": "tma_fp_vector_512b > 0.1 & (tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6))", "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 512-bit wide vectors. May overcount due to FMA double counting. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%" }, @@ -538,17 +538,17 @@ "MetricName": "tma_frontend_bound", "MetricThreshold": "tma_frontend_bound > 0.15", "MetricgroupNoGroup": "TopdownL1;Default", - "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound. Sample with: FRONTEND_RETIRED.LATENCY_GE_4", + "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound. Sample with: FRONTEND_RETIRED.LATENCY_GE_4_PS", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations , instructions that require two or more uops or micro-coded sequences", - "MetricExpr": "tma_microcode_sequencer + tma_retiring * (UOPS_DECODED.DEC0 - cpu@UOPS_DECODED.DEC0\\,cmask\\=0x1@) / IDQ.MITE_UOPS", + "BriefDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences", + "MetricExpr": "tma_microcode_sequencer + tma_retiring * (UOPS_DECODED.DEC0 - cpu@UOPS_DECODED.DEC0\\,cmask\\=1@) / IDQ.MITE_UOPS", "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_heavy_operations", "MetricThreshold": "tma_heavy_operations > 0.1", "MetricgroupNoGroup": "TopdownL2", - "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations , instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences.([ICL+] Note this may overcount due to approximation using indirect events; [ADL+])", + "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences.([ICL+] Note this may overcount due to approximation using indirect events; [ADL+])", "ScaleUnit": "100%" }, { @@ -556,8 +556,8 @@ "MetricExpr": "ICACHE_DATA.STALLS / tma_info_thread_clks", "MetricGroup": "BigFootprint;BvBC;FetchLat;IcMiss;TopdownL3;tma_L3_group;tma_fetch_latency_group", "MetricName": "tma_icache_misses", - "MetricThreshold": "tma_icache_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", - "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to instruction cache misses. Sample with: FRONTEND_RETIRED.L2_MISS, FRONTEND_RETIRED.L1I_MISS", + "MetricThreshold": "tma_icache_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to instruction cache misses. Sample with: FRONTEND_RETIRED.L2_MISS_PS;FRONTEND_RETIRED.L1I_MISS_PS", "ScaleUnit": "100%" }, { @@ -569,28 +569,28 @@ "PublicDescription": "Branch Misprediction Cost: Cycles representing fraction of TMA slots wasted per non-speculative branch misprediction (retired JEClear). Related metrics: tma_bottleneck_mispredictions, tma_branch_mispredicts, tma_mispredicts_resteers" }, { - "BriefDescription": "Instructions per retired Mispredicts for conditional non-taken branches (lower number means higher occurrence rate)", + "BriefDescription": "Instructions per retired Mispredicts for conditional non-taken branches (lower number means higher occurrence rate).", "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.COND_NTAKEN", "MetricGroup": "Bad;BrMispredicts", "MetricName": "tma_info_bad_spec_ipmisp_cond_ntaken", "MetricThreshold": "tma_info_bad_spec_ipmisp_cond_ntaken < 200" }, { - "BriefDescription": "Instructions per retired Mispredicts for conditional taken branches (lower number means higher occurrence rate)", + "BriefDescription": "Instructions per retired Mispredicts for conditional taken branches (lower number means higher occurrence rate).", "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.COND_TAKEN", "MetricGroup": "Bad;BrMispredicts", "MetricName": "tma_info_bad_spec_ipmisp_cond_taken", "MetricThreshold": "tma_info_bad_spec_ipmisp_cond_taken < 200" }, { - "BriefDescription": "Instructions per retired Mispredicts for indirect CALL or JMP branches (lower number means higher occurrence rate)", + "BriefDescription": "Instructions per retired Mispredicts for indirect CALL or JMP branches (lower number means higher occurrence rate).", "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.INDIRECT", "MetricGroup": "Bad;BrMispredicts", "MetricName": "tma_info_bad_spec_ipmisp_indirect", - "MetricThreshold": "tma_info_bad_spec_ipmisp_indirect < 1000" + "MetricThreshold": "tma_info_bad_spec_ipmisp_indirect < 1e3" }, { - "BriefDescription": "Instructions per retired Mispredicts for return branches (lower number means higher occurrence rate)", + "BriefDescription": "Instructions per retired Mispredicts for return branches (lower number means higher occurrence rate).", "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.RET", "MetricGroup": "Bad;BrMispredicts", "MetricName": "tma_info_bad_spec_ipmisp_ret", @@ -619,7 +619,7 @@ }, { "BriefDescription": "Total pipeline cost of DSB (uop cache) hits - subset of the Instruction_Fetch_BW Bottleneck", - "MetricExpr": "100 * (tma_frontend_bound * (tma_fetch_bandwidth / (tma_fetch_latency + tma_fetch_bandwidth)) * (tma_dsb / (tma_mite + tma_dsb + tma_lsd + tma_ms)))", + "MetricExpr": "100 * (tma_frontend_bound * (tma_fetch_bandwidth / (tma_fetch_bandwidth + tma_fetch_latency)) * (tma_dsb / (tma_dsb + tma_lsd + tma_mite + tma_ms)))", "MetricGroup": "DSB;Fed;FetchBW;tma_issueFB", "MetricName": "tma_info_botlnk_l2_dsb_bandwidth", "MetricThreshold": "tma_info_botlnk_l2_dsb_bandwidth > 10", @@ -628,7 +628,7 @@ { "BriefDescription": "Total pipeline cost of DSB (uop cache) misses - subset of the Instruction_Fetch_BW Bottleneck", "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "100 * (tma_fetch_latency * tma_dsb_switches / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches) + tma_fetch_bandwidth * tma_mite / (tma_mite + tma_dsb + tma_lsd + tma_ms))", + "MetricExpr": "100 * (tma_fetch_latency * tma_dsb_switches / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) + tma_fetch_bandwidth * tma_mite / (tma_dsb + tma_lsd + tma_mite + tma_ms))", "MetricGroup": "DSBmiss;Fed;tma_issueFB", "MetricName": "tma_info_botlnk_l2_dsb_misses", "MetricThreshold": "tma_info_botlnk_l2_dsb_misses > 10", @@ -637,10 +637,11 @@ { "BriefDescription": "Total pipeline cost of Instruction Cache misses - subset of the Big_Code Bottleneck", "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "100 * (tma_fetch_latency * tma_icache_misses / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches))", + "MetricExpr": "100 * (tma_fetch_latency * tma_icache_misses / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches))", "MetricGroup": "Fed;FetchLat;IcMiss;tma_issueFL", "MetricName": "tma_info_botlnk_l2_ic_misses", - "MetricThreshold": "tma_info_botlnk_l2_ic_misses > 5" + "MetricThreshold": "tma_info_botlnk_l2_ic_misses > 5", + "PublicDescription": "Total pipeline cost of Instruction Cache misses - subset of the Big_Code Bottleneck. Related metrics: " }, { "BriefDescription": "Fraction of branches that are CALL or RET", @@ -701,11 +702,11 @@ "MetricExpr": "(FP_ARITH_INST_RETIRED.SCALAR + FP_ARITH_INST_RETIRED.VECTOR) / (2 * tma_info_core_core_clks)", "MetricGroup": "Cor;Flops;HPC", "MetricName": "tma_info_core_fp_arith_utilization", - "PublicDescription": "Actual per-core usage of the Floating Point non-X87 execution units (regardless of precision or vector-width). Values > 1 are possible due to ([BDW+] Fused-Multiply Add (FMA) counting - common; [ADL+] use all of ADD/MUL/FMA in Scalar or 128/256-bit vectors - less common)" + "PublicDescription": "Actual per-core usage of the Floating Point non-X87 execution units (regardless of precision or vector-width). Values > 1 are possible due to ([BDW+] Fused-Multiply Add (FMA) counting - common; [ADL+] use all of ADD/MUL/FMA in Scalar or 128/256-bit vectors - less common)." }, { "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is execution) per thread (logical-processor)", - "MetricExpr": "UOPS_EXECUTED.THREAD / cpu@UOPS_EXECUTED.THREAD\\,cmask\\=0x1@", + "MetricExpr": "UOPS_EXECUTED.THREAD / cpu@UOPS_EXECUTED.THREAD\\,cmask\\=1@", "MetricGroup": "Backend;Cor;Pipeline;PortsUtil", "MetricName": "tma_info_core_ilp" }, @@ -718,20 +719,20 @@ "PublicDescription": "Fraction of Uops delivered by the DSB (aka Decoded ICache; or Uop Cache). Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_inst_mix_iptb, tma_lcp" }, { - "BriefDescription": "Average number of cycles of a switch from the DSB fetch-unit to MITE fetch unit - see DSB_Switches tree node for details", - "MetricExpr": "DSB2MITE_SWITCHES.PENALTY_CYCLES / cpu@DSB2MITE_SWITCHES.PENALTY_CYCLES\\,cmask\\=0x1\\,edge\\=0x1@", + "BriefDescription": "Average number of cycles of a switch from the DSB fetch-unit to MITE fetch unit - see DSB_Switches tree node for details.", + "MetricExpr": "DSB2MITE_SWITCHES.PENALTY_CYCLES / cpu@DSB2MITE_SWITCHES.PENALTY_CYCLES\\,cmask\\=1\\,edge@", "MetricGroup": "DSBmiss", "MetricName": "tma_info_frontend_dsb_switch_cost" }, { "BriefDescription": "Average number of Uops issued by front-end when it issued something", - "MetricExpr": "UOPS_ISSUED.ANY / cpu@UOPS_ISSUED.ANY\\,cmask\\=0x1@", + "MetricExpr": "UOPS_ISSUED.ANY / cpu@UOPS_ISSUED.ANY\\,cmask\\=1@", "MetricGroup": "Fed;FetchBW", "MetricName": "tma_info_frontend_fetch_upc" }, { "BriefDescription": "Average Latency for L1 instruction cache misses", - "MetricExpr": "ICACHE_16B.IFDATA_STALL / cpu@ICACHE_16B.IFDATA_STALL\\,cmask\\=0x1\\,edge\\=0x1@", + "MetricExpr": "ICACHE_16B.IFDATA_STALL / cpu@ICACHE_16B.IFDATA_STALL\\,cmask\\=1\\,edge@", "MetricGroup": "Fed;FetchLat;IcMiss", "MetricName": "tma_info_frontend_icache_miss_latency" }, @@ -773,7 +774,7 @@ "MetricName": "tma_info_frontend_tbpc" }, { - "BriefDescription": "Branch instructions per taken branch", + "BriefDescription": "Branch instructions per taken branch.", "MetricExpr": "BR_INST_RETIRED.ALL_BRANCHES / BR_INST_RETIRED.NEAR_TAKEN", "MetricGroup": "Branches;Fed;PGO", "MetricName": "tma_info_inst_mix_bptkbranch" @@ -791,7 +792,7 @@ "MetricGroup": "Flops;InsType", "MetricName": "tma_info_inst_mix_iparith", "MetricThreshold": "tma_info_inst_mix_iparith < 10", - "PublicDescription": "Instructions per FP Arithmetic instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting. Approximated prior to BDW" + "PublicDescription": "Instructions per FP Arithmetic instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting. Approximated prior to BDW." }, { "BriefDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number means higher occurrence rate)", @@ -799,7 +800,7 @@ "MetricGroup": "Flops;FpVector;InsType", "MetricName": "tma_info_inst_mix_iparith_avx128", "MetricThreshold": "tma_info_inst_mix_iparith_avx128 < 10", - "PublicDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting" + "PublicDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting." }, { "BriefDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means higher occurrence rate)", @@ -807,7 +808,7 @@ "MetricGroup": "Flops;FpVector;InsType", "MetricName": "tma_info_inst_mix_iparith_avx256", "MetricThreshold": "tma_info_inst_mix_iparith_avx256 < 10", - "PublicDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting" + "PublicDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting." }, { "BriefDescription": "Instructions per FP Arithmetic AVX 512-bit instruction (lower number means higher occurrence rate)", @@ -815,7 +816,7 @@ "MetricGroup": "Flops;FpVector;InsType", "MetricName": "tma_info_inst_mix_iparith_avx512", "MetricThreshold": "tma_info_inst_mix_iparith_avx512 < 10", - "PublicDescription": "Instructions per FP Arithmetic AVX 512-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting" + "PublicDescription": "Instructions per FP Arithmetic AVX 512-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting." }, { "BriefDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction (lower number means higher occurrence rate)", @@ -823,7 +824,7 @@ "MetricGroup": "Flops;FpScalar;InsType", "MetricName": "tma_info_inst_mix_iparith_scalar_dp", "MetricThreshold": "tma_info_inst_mix_iparith_scalar_dp < 10", - "PublicDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting" + "PublicDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting." }, { "BriefDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction (lower number means higher occurrence rate)", @@ -831,7 +832,7 @@ "MetricGroup": "Flops;FpScalar;InsType", "MetricName": "tma_info_inst_mix_iparith_scalar_sp", "MetricThreshold": "tma_info_inst_mix_iparith_scalar_sp < 10", - "PublicDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting" + "PublicDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting." }, { "BriefDescription": "Instructions per Branch (lower number means higher occurrence rate)", @@ -886,7 +887,7 @@ "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_TAKEN", "MetricGroup": "Branches;Fed;FetchBW;Frontend;PGO;tma_issueFB", "MetricName": "tma_info_inst_mix_iptb", - "MetricThreshold": "tma_info_inst_mix_iptb < 5 * 2 + 1", + "MetricThreshold": "tma_info_inst_mix_iptb < 11", "PublicDescription": "Instructions per taken branch. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_lcp" }, { @@ -1005,7 +1006,7 @@ }, { "BriefDescription": "Average Parallel L2 cache miss demand Loads", - "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD / cpu@OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD\\,cmask\\=0x1@", + "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD / cpu@OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD\\,cmask\\=1@", "MetricGroup": "Memory_BW;Offcore", "MetricName": "tma_info_memory_latency_load_l2_mlp" }, @@ -1067,8 +1068,8 @@ "MetricName": "tma_info_memory_tlb_store_stlb_mpki" }, { - "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is execution) per core", - "MetricExpr": "UOPS_EXECUTED.THREAD / (UOPS_EXECUTED.CORE_CYCLES_GE_1 / 2 if #SMT_on else cpu@UOPS_EXECUTED.THREAD\\,cmask\\=0x1@)", + "BriefDescription": "", + "MetricExpr": "UOPS_EXECUTED.THREAD / (UOPS_EXECUTED.CORE_CYCLES_GE_1 / 2 if #SMT_on else cpu@UOPS_EXECUTED.THREAD\\,cmask\\=1@)", "MetricGroup": "Cor;Pipeline;PortsUtil;SMT", "MetricName": "tma_info_pipeline_execute" }, @@ -1095,12 +1096,12 @@ "MetricExpr": "INST_RETIRED.ANY / ASSISTS.ANY", "MetricGroup": "MicroSeq;Pipeline;Ret;Retire", "MetricName": "tma_info_pipeline_ipassist", - "MetricThreshold": "tma_info_pipeline_ipassist < 100000", + "MetricThreshold": "tma_info_pipeline_ipassist < 100e3", "PublicDescription": "Instructions per a microcode Assist invocation. See Assists tree node for details (lower number means higher occurrence rate)" }, { - "BriefDescription": "Average number of Uops retired in cycles where at least one uop has retired", - "MetricExpr": "tma_retiring * tma_info_thread_slots / cpu@UOPS_RETIRED.SLOTS\\,cmask\\=0x1@", + "BriefDescription": "Average number of Uops retired in cycles where at least one uop has retired.", + "MetricExpr": "tma_retiring * tma_info_thread_slots / cpu@UOPS_RETIRED.SLOTS\\,cmask\\=1@", "MetricGroup": "Pipeline;Ret", "MetricName": "tma_info_pipeline_retire" }, @@ -1141,14 +1142,13 @@ "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.FAR_BRANCH:u", "MetricGroup": "Branches;OS", "MetricName": "tma_info_system_ipfarbranch", - "MetricThreshold": "tma_info_system_ipfarbranch < 1000000" + "MetricThreshold": "tma_info_system_ipfarbranch < 1e6" }, { "BriefDescription": "Cycles Per Instruction for the Operating System (OS) Kernel mode", "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P:k / INST_RETIRED.ANY_P:k", "MetricGroup": "OS", - "MetricName": "tma_info_system_kernel_cpi", - "ScaleUnit": "1per_instr" + "MetricName": "tma_info_system_kernel_cpi" }, { "BriefDescription": "Fraction of cycles spent in the Operating System (OS) Kernel mode", @@ -1175,7 +1175,7 @@ "MetricExpr": "CORE_POWER.LVL0_TURBO_LICENSE / tma_info_core_core_clks", "MetricGroup": "Power", "MetricName": "tma_info_system_power_license0_utilization", - "PublicDescription": "Fraction of Core cycles where the core was running with power-delivery for baseline license level 0. This includes non-AVX codes, SSE, AVX 128-bit, and low-current AVX 256-bit codes" + "PublicDescription": "Fraction of Core cycles where the core was running with power-delivery for baseline license level 0. This includes non-AVX codes, SSE, AVX 128-bit, and low-current AVX 256-bit codes." }, { "BriefDescription": "Fraction of Core cycles where the core was running with power-delivery for license level 1", @@ -1183,7 +1183,7 @@ "MetricGroup": "Power", "MetricName": "tma_info_system_power_license1_utilization", "MetricThreshold": "tma_info_system_power_license1_utilization > 0.5", - "PublicDescription": "Fraction of Core cycles where the core was running with power-delivery for license level 1. This includes high current AVX 256-bit instructions as well as low current AVX 512-bit instructions" + "PublicDescription": "Fraction of Core cycles where the core was running with power-delivery for license level 1. This includes high current AVX 256-bit instructions as well as low current AVX 512-bit instructions." }, { "BriefDescription": "Fraction of Core cycles where the core was running with power-delivery for license level 2 (introduced in SKX)", @@ -1191,7 +1191,7 @@ "MetricGroup": "Power", "MetricName": "tma_info_system_power_license2_utilization", "MetricThreshold": "tma_info_system_power_license2_utilization > 0.5", - "PublicDescription": "Fraction of Core cycles where the core was running with power-delivery for license level 2 (introduced in SKX). This includes high current AVX 512-bit instructions" + "PublicDescription": "Fraction of Core cycles where the core was running with power-delivery for license level 2 (introduced in SKX). This includes high current AVX 512-bit instructions." }, { "BriefDescription": "Fraction of cycles where both hardware Logical Processors were active", @@ -1219,7 +1219,7 @@ "MetricName": "tma_info_system_turbo_utilization" }, { - "BriefDescription": "Per-Logical Processor actual clocks when the Logical Processor is active", + "BriefDescription": "Per-Logical Processor actual clocks when the Logical Processor is active.", "MetricExpr": "CPU_CLK_UNHALTED.THREAD", "MetricGroup": "Pipeline", "MetricName": "tma_info_thread_clks" @@ -1228,15 +1228,14 @@ "BriefDescription": "Cycles Per Instruction (per Logical Processor)", "MetricExpr": "1 / tma_info_thread_ipc", "MetricGroup": "Mem;Pipeline", - "MetricName": "tma_info_thread_cpi", - "ScaleUnit": "1per_instr" + "MetricName": "tma_info_thread_cpi" }, { "BriefDescription": "The ratio of Executed- by Issued-Uops", "MetricExpr": "UOPS_EXECUTED.THREAD / UOPS_ISSUED.ANY", "MetricGroup": "Cor;Pipeline", "MetricName": "tma_info_thread_execute_per_issue", - "PublicDescription": "The ratio of Executed- by Issued-Uops. Ratio > 1 suggests high rate of uop micro-fusions. Ratio < 1 suggest high rate of \"execute\" at rename stage" + "PublicDescription": "The ratio of Executed- by Issued-Uops. Ratio > 1 suggests high rate of uop micro-fusions. Ratio < 1 suggest high rate of \"execute\" at rename stage." }, { "BriefDescription": "Instructions Per Cycle (per Logical Processor)", @@ -1246,13 +1245,13 @@ }, { "BriefDescription": "Total issue-pipeline slots (per-Physical Core till ICL; per-Logical Processor ICL onward)", - "MetricExpr": "slots", + "MetricExpr": "TOPDOWN.SLOTS", "MetricGroup": "TmaL1;tma_L1_group", "MetricName": "tma_info_thread_slots" }, { "BriefDescription": "Fraction of Physical Core issue-slots utilized by this Logical Processor", - "MetricExpr": "(tma_info_thread_slots / (slots / 2) if #SMT_on else 1)", + "MetricExpr": "(tma_info_thread_slots / (TOPDOWN.SLOTS / 2) if #SMT_on else 1)", "MetricGroup": "SMT;TmaL1;tma_L1_group", "MetricName": "tma_info_thread_slots_utilization" }, @@ -1268,14 +1267,14 @@ "MetricExpr": "tma_retiring * tma_info_thread_slots / BR_INST_RETIRED.NEAR_TAKEN", "MetricGroup": "Branches;Fed;FetchBW", "MetricName": "tma_info_thread_uptb", - "MetricThreshold": "tma_info_thread_uptb < 5 * 1.5" + "MetricThreshold": "tma_info_thread_uptb < 7.5" }, { - "BriefDescription": "This metric represents fraction of cycles where the Integer Divider unit was active", + "BriefDescription": "This metric represents fraction of cycles where the Integer Divider unit was active.", "MetricExpr": "tma_divider - tma_fp_divider", "MetricGroup": "TopdownL4;tma_L4_group;tma_divider_group", "MetricName": "tma_int_divider", - "MetricThreshold": "tma_int_divider > 0.2 & tma_divider > 0.2 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_int_divider > 0.2 & (tma_divider > 0.2 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", "ScaleUnit": "100%" }, { @@ -1283,8 +1282,8 @@ "MetricExpr": "ICACHE_TAG.STALLS / tma_info_thread_clks", "MetricGroup": "BigFootprint;BvBC;FetchLat;MemoryTLB;TopdownL3;tma_L3_group;tma_fetch_latency_group", "MetricName": "tma_itlb_misses", - "MetricThreshold": "tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", - "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Instruction TLB (ITLB) misses. Sample with: FRONTEND_RETIRED.STLB_MISS, FRONTEND_RETIRED.ITLB_MISS", + "MetricThreshold": "tma_itlb_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Instruction TLB (ITLB) misses. Sample with: FRONTEND_RETIRED.STLB_MISS_PS;FRONTEND_RETIRED.ITLB_MISS_PS", "ScaleUnit": "100%" }, { @@ -1292,7 +1291,7 @@ "MetricExpr": "max((CYCLE_ACTIVITY.STALLS_MEM_ANY - CYCLE_ACTIVITY.STALLS_L1D_MISS) / tma_info_thread_clks, 0)", "MetricGroup": "CacheHits;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_issueL1;tma_issueMC;tma_memory_bound_group", "MetricName": "tma_l1_bound", - "MetricThreshold": "tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", "PublicDescription": "This metric estimates how often the CPU was stalled without loads missing the L1 Data (L1D) cache. The L1D cache typically has the shortest latency. However; in certain cases like loads blocked on older stores; a load might suffer due to high latency even though it is being satisfied by the L1D. Another example is loads who miss in the TLB. These cases are characterized by execution unit stalls; while some non-completed demand load lives in the machine without having that demand load missing the L1 cache. Sample with: MEM_LOAD_RETIRED.L1_HIT. Related metrics: tma_clears_resteers, tma_machine_clears, tma_microcode_sequencer, tma_ms_switches, tma_ports_utilized_1", "ScaleUnit": "100%" }, @@ -1301,7 +1300,7 @@ "MetricExpr": "min(2 * (MEM_INST_RETIRED.ALL_LOADS - MEM_LOAD_RETIRED.FB_HIT - MEM_LOAD_RETIRED.L1_MISS) * 20 / 100, max(CYCLE_ACTIVITY.CYCLES_MEM_ANY - CYCLE_ACTIVITY.CYCLES_L1D_MISS, 0)) / tma_info_thread_clks", "MetricGroup": "BvML;MemoryLat;TopdownL4;tma_L4_group;tma_l1_bound_group", "MetricName": "tma_l1_latency_dependency", - "MetricThreshold": "tma_l1_latency_dependency > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_l1_latency_dependency > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", "PublicDescription": "This metric([SKL+] roughly; [LNL]) estimates fraction of cycles with demand load accesses that hit the L1D cache. The short latency of the L1D cache may be exposed in pointer-chasing memory access patterns as an example. Sample with: MEM_LOAD_RETIRED.L1_HIT", "ScaleUnit": "100%" }, @@ -1311,7 +1310,7 @@ "MetricExpr": "MEM_LOAD_RETIRED.L2_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) / (MEM_LOAD_RETIRED.L2_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) + L1D_PEND_MISS.FB_FULL_PERIODS) * ((CYCLE_ACTIVITY.STALLS_L1D_MISS - CYCLE_ACTIVITY.STALLS_L2_MISS) / tma_info_thread_clks)", "MetricGroup": "BvML;CacheHits;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_l2_bound", - "MetricThreshold": "tma_l2_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_l2_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", "PublicDescription": "This metric estimates how often the CPU was stalled due to L2 cache accesses by loads. Avoiding cache misses (i.e. L1 misses/L2 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L2_HIT", "ScaleUnit": "100%" }, @@ -1320,7 +1319,7 @@ "MetricExpr": "3.5 * tma_info_system_core_frequency * MEM_LOAD_RETIRED.L2_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks", "MetricGroup": "MemoryLat;TopdownL4;tma_L4_group;tma_l2_bound_group", "MetricName": "tma_l2_hit_latency", - "MetricThreshold": "tma_l2_hit_latency > 0.05 & tma_l2_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_l2_hit_latency > 0.05 & (tma_l2_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", "PublicDescription": "This metric represents fraction of cycles with demand load accesses that hit the L2 cache under unloaded scenarios (possibly L2 latency limited). Avoiding L1 cache misses (i.e. L1 misses/L2 hits) will improve the latency. Sample with: MEM_LOAD_RETIRED.L2_HIT", "ScaleUnit": "100%" }, @@ -1330,17 +1329,17 @@ "MetricExpr": "(CYCLE_ACTIVITY.STALLS_L2_MISS - CYCLE_ACTIVITY.STALLS_L3_MISS) / tma_info_thread_clks", "MetricGroup": "CacheHits;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_l3_bound", - "MetricThreshold": "tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", - "PublicDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core. Avoiding cache misses (i.e. L2 misses/L3 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L3_HIT", + "MetricThreshold": "tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", + "PublicDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core. Avoiding cache misses (i.e. L2 misses/L3 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L3_HIT_PS", "ScaleUnit": "100%" }, { "BriefDescription": "This metric estimates fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited)", - "MetricExpr": "(12.5 * tma_info_system_core_frequency - 3.5 * tma_info_system_core_frequency) * (MEM_LOAD_RETIRED.L3_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2)) / tma_info_thread_clks", + "MetricExpr": "9 * tma_info_system_core_frequency * (MEM_LOAD_RETIRED.L3_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2)) / tma_info_thread_clks", "MetricGroup": "BvML;MemoryLat;TopdownL4;tma_L4_group;tma_issueLat;tma_l3_bound_group", "MetricName": "tma_l3_hit_latency", - "MetricThreshold": "tma_l3_hit_latency > 0.1 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", - "PublicDescription": "This metric estimates fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited). Avoiding private cache misses (i.e. L2 misses/L3 hits) will improve the latency; reduce contention with sibling physical cores and increase performance. Note the value of this node may overlap with its siblings. Sample with: MEM_LOAD_RETIRED.L3_HIT. Related metrics: tma_bottleneck_cache_memory_latency, tma_branch_resteers, tma_mem_latency, tma_store_latency", + "MetricThreshold": "tma_l3_hit_latency > 0.1 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric estimates fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited). Avoiding private cache misses (i.e. L2 misses/L3 hits) will improve the latency; reduce contention with sibling physical cores and increase performance. Note the value of this node may overlap with its siblings. Sample with: MEM_LOAD_RETIRED.L3_HIT_PS. Related metrics: tma_bottleneck_cache_memory_latency, tma_mem_latency", "ScaleUnit": "100%" }, { @@ -1348,18 +1347,18 @@ "MetricExpr": "DECODE.LCP / tma_info_thread_clks", "MetricGroup": "FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueFB", "MetricName": "tma_lcp", - "MetricThreshold": "tma_lcp > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", - "PublicDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs). Using proper compiler flags or Intel Compiler by default will certainly avoid this. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb", + "MetricThreshold": "tma_lcp > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", + "PublicDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs). Using proper compiler flags or Intel Compiler by default will certainly avoid this. #Link: Optimization Guide about LCP BKMs. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations , instructions that require no more than one uop (micro-operation)", + "BriefDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation)", "MetricExpr": "max(0, tma_retiring - tma_heavy_operations)", "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_light_operations", "MetricThreshold": "tma_light_operations > 0.6", "MetricgroupNoGroup": "TopdownL2", - "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations , instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized code running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. ([ICL+] Note this may undercount due to approximation using indirect events; [ADL+] .). Sample with: INST_RETIRED.PREC_DIST", + "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized code running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. ([ICL+] Note this may undercount due to approximation using indirect events; [ADL+] .). Sample with: INST_RETIRED.PREC_DIST", "ScaleUnit": "100%" }, { @@ -1376,7 +1375,7 @@ "MetricExpr": "tma_dtlb_load - tma_load_stlb_miss", "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_load_group", "MetricName": "tma_load_stlb_hit", - "MetricThreshold": "tma_load_stlb_hit > 0.05 & tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_load_stlb_hit > 0.05 & (tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))", "ScaleUnit": "100%" }, { @@ -1384,31 +1383,31 @@ "MetricExpr": "DTLB_LOAD_MISSES.WALK_ACTIVE / tma_info_thread_clks", "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_load_group", "MetricName": "tma_load_stlb_miss", - "MetricThreshold": "tma_load_stlb_miss > 0.05 & tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_load_stlb_miss > 0.05 & (tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 1 GB pages for data load accesses", + "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 1 GB pages for data load accesses.", "MetricExpr": "tma_load_stlb_miss * DTLB_LOAD_MISSES.WALK_COMPLETED_1G / (DTLB_LOAD_MISSES.WALK_COMPLETED_4K + DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M + DTLB_LOAD_MISSES.WALK_COMPLETED_1G)", "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_load_stlb_miss_group", "MetricName": "tma_load_stlb_miss_1g", - "MetricThreshold": "tma_load_stlb_miss_1g > 0.05 & tma_load_stlb_miss > 0.05 & tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_load_stlb_miss_1g > 0.05 & (tma_load_stlb_miss > 0.05 & (tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))))", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 2 or 4 MB pages for data load accesses", + "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 2 or 4 MB pages for data load accesses.", "MetricExpr": "tma_load_stlb_miss * DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M / (DTLB_LOAD_MISSES.WALK_COMPLETED_4K + DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M + DTLB_LOAD_MISSES.WALK_COMPLETED_1G)", "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_load_stlb_miss_group", "MetricName": "tma_load_stlb_miss_2m", - "MetricThreshold": "tma_load_stlb_miss_2m > 0.05 & tma_load_stlb_miss > 0.05 & tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_load_stlb_miss_2m > 0.05 & (tma_load_stlb_miss > 0.05 & (tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))))", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 4 KB pages for data load accesses", + "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 4 KB pages for data load accesses.", "MetricExpr": "tma_load_stlb_miss * DTLB_LOAD_MISSES.WALK_COMPLETED_4K / (DTLB_LOAD_MISSES.WALK_COMPLETED_4K + DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M + DTLB_LOAD_MISSES.WALK_COMPLETED_1G)", "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_load_stlb_miss_group", "MetricName": "tma_load_stlb_miss_4k", - "MetricThreshold": "tma_load_stlb_miss_4k > 0.05 & tma_load_stlb_miss > 0.05 & tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_load_stlb_miss_4k > 0.05 & (tma_load_stlb_miss > 0.05 & (tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))))", "ScaleUnit": "100%" }, { @@ -1417,7 +1416,7 @@ "MetricExpr": "(16 * max(0, MEM_INST_RETIRED.LOCK_LOADS - L2_RQSTS.ALL_RFO) + MEM_INST_RETIRED.LOCK_LOADS / MEM_INST_RETIRED.ALL_STORES * (10 * L2_RQSTS.RFO_HIT + min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO))) / tma_info_thread_clks", "MetricGroup": "LockCont;Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_l1_bound_group", "MetricName": "tma_lock_latency", - "MetricThreshold": "tma_lock_latency > 0.2 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_lock_latency > 0.2 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", "PublicDescription": "This metric represents fraction of cycles the CPU spent handling cache misses due to lock operations. Due to the microarchitecture handling of locks; they are classified as L1_Bound regardless of what memory source satisfied them. Sample with: MEM_INST_RETIRED.LOCK_LOADS. Related metrics: tma_store_latency", "ScaleUnit": "100%" }, @@ -1427,7 +1426,7 @@ "MetricGroup": "FetchBW;LSD;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group", "MetricName": "tma_lsd", "MetricThreshold": "tma_lsd > 0.15 & tma_fetch_bandwidth > 0.2", - "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to LSD (Loop Stream Detector) unit. LSD typically does well sustaining Uop supply. However; in some rare cases; optimal uop-delivery could not be reached for small loops whose size (in terms of number of uops) does not suit well the LSD structure", + "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to LSD (Loop Stream Detector) unit. LSD typically does well sustaining Uop supply. However; in some rare cases; optimal uop-delivery could not be reached for small loops whose size (in terms of number of uops) does not suit well the LSD structure.", "ScaleUnit": "100%" }, { @@ -1437,15 +1436,15 @@ "MetricName": "tma_machine_clears", "MetricThreshold": "tma_machine_clears > 0.1 & tma_bad_speculation > 0.15", "MetricgroupNoGroup": "TopdownL2", - "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears. These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT. Related metrics: tma_bottleneck_memory_synchronization, tma_clears_resteers, tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_l1_bound, tma_microcode_sequencer, tma_ms_switches", + "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears. These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT. Related metrics: tma_bottleneck_memory_synchronization, tma_clears_resteers, tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_l1_bound, tma_microcode_sequencer, tma_ms_switches, tma_remote_cache", "ScaleUnit": "100%" }, { "BriefDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory - DRAM ([SPR-HBM] and/or HBM)", - "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, cpu@OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD\\,cmask\\=0x4@) / tma_info_thread_clks", + "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, cpu@OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD\\,cmask\\=4@) / tma_info_thread_clks", "MetricGroup": "BvMB;MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueBW", "MetricName": "tma_mem_bandwidth", - "MetricThreshold": "tma_mem_bandwidth > 0.2 & tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_mem_bandwidth > 0.2 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", "PublicDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory - DRAM ([SPR-HBM] and/or HBM). The underlying heuristic assumes that a similar off-core traffic is generated by all IA cores. This metric does not aggregate non-data-read requests by this logical processor; requests from other IA Logical Processors/Physical Cores/sockets; or other non-IA devices like GPU; hence the maximum external memory bandwidth limits may or may not be approached when this metric is flagged (see Uncore counters for that). Related metrics: tma_bottleneck_cache_memory_bandwidth, tma_fb_full, tma_info_system_dram_bw_use, tma_sq_full", "ScaleUnit": "100%" }, @@ -1454,7 +1453,7 @@ "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD) / tma_info_thread_clks - tma_mem_bandwidth", "MetricGroup": "BvML;MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueLat", "MetricName": "tma_mem_latency", - "MetricThreshold": "tma_mem_latency > 0.1 & tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_mem_latency > 0.1 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", "PublicDescription": "This metric estimates fraction of cycles where the performance was likely hurt due to latency from external memory - DRAM ([SPR-HBM] and/or HBM). This metric does not aggregate requests from other Logical Processors/Physical Cores/sockets (see Uncore counters for that). Related metrics: tma_bottleneck_cache_memory_latency, tma_l3_hit_latency", "ScaleUnit": "100%" }, @@ -1465,11 +1464,11 @@ "MetricName": "tma_memory_bound", "MetricThreshold": "tma_memory_bound > 0.2 & tma_backend_bound > 0.2", "MetricgroupNoGroup": "TopdownL2", - "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck. Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two)", + "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck. Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two).", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of slots where the CPU was retiring memory operations , uops for memory load or store accesses", + "BriefDescription": "This metric represents fraction of slots where the CPU was retiring memory operations -- uops for memory load or store accesses.", "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "tma_light_operations * MEM_INST_RETIRED.ANY / INST_RETIRED.ANY", "MetricGroup": "Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group", @@ -1491,7 +1490,7 @@ "MetricExpr": "BR_MISP_RETIRED.ALL_BRANCHES / (BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT) * INT_MISC.CLEAR_RESTEER_CYCLES / tma_info_thread_clks", "MetricGroup": "BadSpec;BrMispredicts;BvMP;TopdownL4;tma_L4_group;tma_branch_resteers_group;tma_issueBM", "MetricName": "tma_mispredicts_resteers", - "MetricThreshold": "tma_mispredicts_resteers > 0.05 & tma_branch_resteers > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricThreshold": "tma_mispredicts_resteers > 0.05 & (tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))", "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Branch Misprediction at execution stage. Sample with: INT_MISC.CLEAR_RESTEER_CYCLES. Related metrics: tma_bottleneck_mispredictions, tma_branch_mispredicts, tma_info_bad_spec_branch_misprediction_cost", "ScaleUnit": "100%" }, @@ -1506,24 +1505,24 @@ }, { "BriefDescription": "This metric represents fraction of cycles where (only) 4 uops were delivered by the MITE pipeline", - "MetricExpr": "(cpu@IDQ.MITE_UOPS\\,cmask\\=0x4@ - cpu@IDQ.MITE_UOPS\\,cmask\\=0x5@) / tma_info_thread_clks", + "MetricExpr": "(cpu@IDQ.MITE_UOPS\\,cmask\\=4@ - cpu@IDQ.MITE_UOPS\\,cmask\\=5@) / tma_info_thread_clks", "MetricGroup": "DSBmiss;FetchBW;TopdownL4;tma_L4_group;tma_mite_group", "MetricName": "tma_mite_4wide", - "MetricThreshold": "tma_mite_4wide > 0.05 & tma_mite > 0.1 & tma_fetch_bandwidth > 0.2", + "MetricThreshold": "tma_mite_4wide > 0.05 & (tma_mite > 0.1 & tma_fetch_bandwidth > 0.2)", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates penalty in terms of percentage of([SKL+] injected blend uops out of all Uops Issued , the Count Domain; [ADL+] cycles)", + "BriefDescription": "This metric estimates penalty in terms of percentage of([SKL+] injected blend uops out of all Uops Issued -- the Count Domain; [ADL+] cycles)", "MetricExpr": "UOPS_ISSUED.VECTOR_WIDTH_MISMATCH / UOPS_ISSUED.ANY", "MetricGroup": "TopdownL5;tma_L5_group;tma_issueMV;tma_ports_utilized_0_group", "MetricName": "tma_mixing_vectors", "MetricThreshold": "tma_mixing_vectors > 0.05", - "PublicDescription": "This metric estimates penalty in terms of percentage of([SKL+] injected blend uops out of all Uops Issued , the Count Domain; [ADL+] cycles). Usually a Mixing_Vectors over 5% is worth investigating. Read more in Appendix B1 of the Optimizations Guide for this topic. Related metrics: tma_ms_switches", + "PublicDescription": "This metric estimates penalty in terms of percentage of([SKL+] injected blend uops out of all Uops Issued -- the Count Domain; [ADL+] cycles). Usually a Mixing_Vectors over 5% is worth investigating. Read more in Appendix B1 of the Optimizations Guide for this topic. Related metrics: tma_ms_switches", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to the Microcode Sequencer (MS) unit - see Microcode_Sequencer node for details", - "MetricExpr": "cpu@IDQ.MS_UOPS\\,cmask\\=0x1@ / tma_info_core_core_clks / 2", + "BriefDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to the Microcode Sequencer (MS) unit - see Microcode_Sequencer node for details.", + "MetricExpr": "cpu@IDQ.MS_UOPS\\,cmask\\=1@ / tma_info_core_core_clks / 2", "MetricGroup": "MicroSeq;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group", "MetricName": "tma_ms", "MetricThreshold": "tma_ms > 0.05 & tma_fetch_bandwidth > 0.2", @@ -1534,7 +1533,7 @@ "MetricExpr": "3 * IDQ.MS_SWITCHES / tma_info_thread_clks", "MetricGroup": "FetchLat;MicroSeq;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueMC;tma_issueMS;tma_issueMV;tma_issueSO", "MetricName": "tma_ms_switches", - "MetricThreshold": "tma_ms_switches > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricThreshold": "tma_ms_switches > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", "PublicDescription": "This metric estimates the fraction of cycles when the CPU was stalled due to switches of uop delivery to the Microcode Sequencer (MS). Commonly used instructions are optimized for delivery by the DSB (decoded i-cache) or MITE (legacy instruction decode) pipelines. Certain operations cannot be handled natively by the execution pipeline; and must be performed by microcode (small programs injected into the execution stream). Switching to the MS too often can negatively impact performance. The MS is designated to deliver long uop flows required by CISC instructions like CPUID; or uncommon conditions like Floating Point Assists when dealing with Denormals. Sample with: IDQ.MS_SWITCHES. Related metrics: tma_bottleneck_irregular_overhead, tma_clears_resteers, tma_l1_bound, tma_machine_clears, tma_microcode_sequencer, tma_mixing_vectors, tma_serializing_operation", "ScaleUnit": "100%" }, @@ -1543,7 +1542,7 @@ "MetricExpr": "tma_light_operations * INST_RETIRED.NOP / (tma_retiring * tma_info_thread_slots)", "MetricGroup": "BvBO;Pipeline;TopdownL4;tma_L4_group;tma_other_light_ops_group", "MetricName": "tma_nop_instructions", - "MetricThreshold": "tma_nop_instructions > 0.1 & tma_other_light_ops > 0.3 & tma_light_operations > 0.6", + "MetricThreshold": "tma_nop_instructions > 0.1 & (tma_other_light_ops > 0.3 & tma_light_operations > 0.6)", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring NOP (no op) instructions. Compilers often use NOPs for certain address alignments - e.g. start address of a function or loop body. Sample with: INST_RETIRED.NOP", "ScaleUnit": "100%" }, @@ -1558,19 +1557,19 @@ "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates fraction of slots the CPU was stalled due to other cases of misprediction (non-retired x86 branches or other types)", + "BriefDescription": "This metric estimates fraction of slots the CPU was stalled due to other cases of misprediction (non-retired x86 branches or other types).", "MetricExpr": "max(tma_branch_mispredicts * (1 - BR_MISP_RETIRED.ALL_BRANCHES / (INT_MISC.CLEARS_COUNT - MACHINE_CLEARS.COUNT)), 0.0001)", "MetricGroup": "BrMispredicts;BvIO;TopdownL3;tma_L3_group;tma_branch_mispredicts_group", "MetricName": "tma_other_mispredicts", - "MetricThreshold": "tma_other_mispredicts > 0.05 & tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", + "MetricThreshold": "tma_other_mispredicts > 0.05 & (tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15)", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of slots the CPU has wasted due to Nukes (Machine Clears) not related to memory ordering", + "BriefDescription": "This metric represents fraction of slots the CPU has wasted due to Nukes (Machine Clears) not related to memory ordering.", "MetricExpr": "max(tma_machine_clears * (1 - MACHINE_CLEARS.MEMORY_ORDERING / MACHINE_CLEARS.COUNT), 0.0001)", "MetricGroup": "BvIO;Machine_Clears;TopdownL3;tma_L3_group;tma_machine_clears_group", "MetricName": "tma_other_nukes", - "MetricThreshold": "tma_other_nukes > 0.05 & tma_machine_clears > 0.1 & tma_bad_speculation > 0.15", + "MetricThreshold": "tma_other_nukes > 0.05 & (tma_machine_clears > 0.1 & tma_bad_speculation > 0.15)", "ScaleUnit": "100%" }, { @@ -1614,8 +1613,8 @@ "MetricExpr": "((tma_ports_utilized_0 * tma_info_thread_clks + (EXE_ACTIVITY.1_PORTS_UTIL + tma_retiring * EXE_ACTIVITY.2_PORTS_UTIL)) / tma_info_thread_clks if ARITH.DIVIDER_ACTIVE < CYCLE_ACTIVITY.STALLS_TOTAL - CYCLE_ACTIVITY.STALLS_MEM_ANY else (EXE_ACTIVITY.1_PORTS_UTIL + tma_retiring * EXE_ACTIVITY.2_PORTS_UTIL) / tma_info_thread_clks)", "MetricGroup": "PortsUtil;TopdownL3;tma_L3_group;tma_core_bound_group", "MetricName": "tma_ports_utilization", - "MetricThreshold": "tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", - "PublicDescription": "This metric estimates fraction of cycles the CPU performance was potentially limited due to Core computation issues (non divider-related). Two distinct categories can be attributed into this metric: (1) heavy data-dependency among contiguous instructions would manifest in this metric - such cases are often referred to as low Instruction Level Parallelism (ILP). (2) Contention on some hardware execution unit other than Divider. For example; when there are too many multiply operations", + "MetricThreshold": "tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)", + "PublicDescription": "This metric estimates fraction of cycles the CPU performance was potentially limited due to Core computation issues (non divider-related). Two distinct categories can be attributed into this metric: (1) heavy data-dependency among contiguous instructions would manifest in this metric - such cases are often referred to as low Instruction Level Parallelism (ILP). (2) Contention on some hardware execution unit other than Divider. For example; when there are too many multiply operations.", "ScaleUnit": "100%" }, { @@ -1623,8 +1622,8 @@ "MetricExpr": "cpu@EXE_ACTIVITY.3_PORTS_UTIL\\,umask\\=0x80@ / tma_info_thread_clks", "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group", "MetricName": "tma_ports_utilized_0", - "MetricThreshold": "tma_ports_utilized_0 > 0.2 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", - "PublicDescription": "This metric represents fraction of cycles CPU executed no uops on any execution port (Logical Processor cycles since ICL, Physical Core cycles otherwise). Long-latency instructions like divides may contribute to this metric", + "MetricThreshold": "tma_ports_utilized_0 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric represents fraction of cycles CPU executed no uops on any execution port (Logical Processor cycles since ICL, Physical Core cycles otherwise). Long-latency instructions like divides may contribute to this metric.", "ScaleUnit": "100%" }, { @@ -1632,7 +1631,7 @@ "MetricExpr": "EXE_ACTIVITY.1_PORTS_UTIL / tma_info_thread_clks", "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_issueL1;tma_ports_utilization_group", "MetricName": "tma_ports_utilized_1", - "MetricThreshold": "tma_ports_utilized_1 > 0.2 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_ports_utilized_1 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", "PublicDescription": "This metric represents fraction of cycles where the CPU executed total of 1 uop per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise). This can be due to heavy data-dependency among software instructions; or over oversubscribing a particular hardware resource. In some other cases with high 1_Port_Utilized and L1_Bound; this metric can point to L1 data-cache latency bottleneck that may not necessarily manifest with complete execution starvation (due to the short L1 latency e.g. walking a linked list) - looking at the assembly can be helpful. Sample with: EXE_ACTIVITY.1_PORTS_UTIL. Related metrics: tma_l1_bound", "ScaleUnit": "100%" }, @@ -1641,7 +1640,7 @@ "MetricExpr": "EXE_ACTIVITY.2_PORTS_UTIL / tma_info_thread_clks", "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_issue2P;tma_ports_utilization_group", "MetricName": "tma_ports_utilized_2", - "MetricThreshold": "tma_ports_utilized_2 > 0.15 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_ports_utilized_2 > 0.15 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", "PublicDescription": "This metric represents fraction of cycles CPU executed total of 2 uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise). Loop Vectorization -most compilers feature auto-Vectorization options today- reduces pressure on the execution ports as multiple elements are calculated with same uop. Sample with: EXE_ACTIVITY.2_PORTS_UTIL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6", "ScaleUnit": "100%" }, @@ -1650,14 +1649,14 @@ "MetricExpr": "UOPS_EXECUTED.CYCLES_GE_3 / tma_info_thread_clks", "MetricGroup": "BvCB;PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group", "MetricName": "tma_ports_utilized_3m", - "MetricThreshold": "tma_ports_utilized_3m > 0.4 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_ports_utilized_3m > 0.4 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", "PublicDescription": "This metric represents fraction of cycles CPU executed total of 3 or more uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise). Sample with: UOPS_EXECUTED.CYCLES_GE_3", "ScaleUnit": "100%" }, { "BriefDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired", "DefaultMetricgroupName": "TopdownL1", - "MetricExpr": "topdown\\-retiring / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * slots", + "MetricExpr": "topdown\\-retiring / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * tma_info_thread_slots", "MetricGroup": "BvUW;Default;TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_retiring", "MetricThreshold": "tma_retiring > 0.7 | tma_heavy_operations > 0.1", @@ -1670,7 +1669,7 @@ "MetricExpr": "RESOURCE_STALLS.SCOREBOARD / tma_info_thread_clks", "MetricGroup": "BvIO;PortsUtil;TopdownL3;tma_L3_group;tma_core_bound_group;tma_issueSO", "MetricName": "tma_serializing_operation", - "MetricThreshold": "tma_serializing_operation > 0.1 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_serializing_operation > 0.1 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)", "PublicDescription": "This metric represents fraction of cycles the CPU issue-pipeline was stalled due to serializing operations. Instructions like CPUID; WRMSR or LFENCE serialize the out-of-order execution which may limit performance. Sample with: RESOURCE_STALLS.SCOREBOARD. Related metrics: tma_ms_switches", "ScaleUnit": "100%" }, @@ -1679,7 +1678,7 @@ "MetricExpr": "140 * MISC_RETIRED.PAUSE_INST / tma_info_thread_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_serializing_operation_group", "MetricName": "tma_slow_pause", - "MetricThreshold": "tma_slow_pause > 0.05 & tma_serializing_operation > 0.1 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_slow_pause > 0.05 & (tma_serializing_operation > 0.1 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to PAUSE Instructions. Sample with: MISC_RETIRED.PAUSE_INST", "ScaleUnit": "100%" }, @@ -1689,7 +1688,7 @@ "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group", "MetricName": "tma_split_loads", "MetricThreshold": "tma_split_loads > 0.3", - "PublicDescription": "This metric estimates fraction of cycles handling memory load split accesses - load that cross 64-byte cache line boundary. Sample with: MEM_INST_RETIRED.SPLIT_LOADS", + "PublicDescription": "This metric estimates fraction of cycles handling memory load split accesses - load that cross 64-byte cache line boundary. Sample with: MEM_INST_RETIRED.SPLIT_LOADS_PS", "ScaleUnit": "100%" }, { @@ -1698,8 +1697,8 @@ "MetricExpr": "MEM_INST_RETIRED.SPLIT_STORES / tma_info_core_core_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_issueSpSt;tma_store_bound_group", "MetricName": "tma_split_stores", - "MetricThreshold": "tma_split_stores > 0.2 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", - "PublicDescription": "This metric represents rate of split store accesses. Consider aligning your data to the 64-byte cache line granularity. Sample with: MEM_INST_RETIRED.SPLIT_STORES", + "MetricThreshold": "tma_split_stores > 0.2 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric represents rate of split store accesses. Consider aligning your data to the 64-byte cache line granularity. Sample with: MEM_INST_RETIRED.SPLIT_STORES_PS. Related metrics: tma_port_4", "ScaleUnit": "100%" }, { @@ -1707,7 +1706,7 @@ "MetricExpr": "L1D_PEND_MISS.L2_STALL / tma_info_thread_clks", "MetricGroup": "BvMB;MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_issueBW;tma_l3_bound_group", "MetricName": "tma_sq_full", - "MetricThreshold": "tma_sq_full > 0.3 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_sq_full > 0.3 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", "PublicDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors). Related metrics: tma_bottleneck_cache_memory_bandwidth, tma_fb_full, tma_info_system_dram_bw_use, tma_mem_bandwidth", "ScaleUnit": "100%" }, @@ -1716,8 +1715,8 @@ "MetricExpr": "EXE_ACTIVITY.BOUND_ON_STORES / tma_info_thread_clks", "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_store_bound", - "MetricThreshold": "tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", - "PublicDescription": "This metric estimates how often CPU was stalled due to RFO store memory accesses; RFO store issue a read-for-ownership request before the write. Even though store accesses do not typically stall out-of-order CPUs; there are few cases where stores can lead to actual stalls. This metric will be flagged should RFO stores be a bottleneck. Sample with: MEM_INST_RETIRED.ALL_STORES", + "MetricThreshold": "tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", + "PublicDescription": "This metric estimates how often CPU was stalled due to RFO store memory accesses; RFO store issue a read-for-ownership request before the write. Even though store accesses do not typically stall out-of-order CPUs; there are few cases where stores can lead to actual stalls. This metric will be flagged should RFO stores be a bottleneck. Sample with: MEM_INST_RETIRED.ALL_STORES_PS", "ScaleUnit": "100%" }, { @@ -1726,8 +1725,8 @@ "MetricExpr": "13 * LD_BLOCKS.STORE_FORWARD / tma_info_thread_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group", "MetricName": "tma_store_fwd_blk", - "MetricThreshold": "tma_store_fwd_blk > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", - "PublicDescription": "This metric roughly estimates fraction of cycles when the memory subsystem had loads blocked since they could not forward data from earlier (in program order) overlapping stores. To streamline memory operations in the pipeline; a load can avoid waiting for memory if a prior in-flight store is writing the data that the load wants to read (store forwarding process). However; in some cases the load may be blocked for a significant time pending the store forward. For example; when the prior store is writing a smaller region than the load is reading", + "MetricThreshold": "tma_store_fwd_blk > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric roughly estimates fraction of cycles when the memory subsystem had loads blocked since they could not forward data from earlier (in program order) overlapping stores. To streamline memory operations in the pipeline; a load can avoid waiting for memory if a prior in-flight store is writing the data that the load wants to read (store forwarding process). However; in some cases the load may be blocked for a significant time pending the store forward. For example; when the prior store is writing a smaller region than the load is reading.", "ScaleUnit": "100%" }, { @@ -1735,8 +1734,8 @@ "MetricExpr": "(L2_RQSTS.RFO_HIT * 10 * (1 - MEM_INST_RETIRED.LOCK_LOADS / MEM_INST_RETIRED.ALL_STORES) + (1 - MEM_INST_RETIRED.LOCK_LOADS / MEM_INST_RETIRED.ALL_STORES) * min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO)) / tma_info_thread_clks", "MetricGroup": "BvML;LockCont;MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_issueSL;tma_store_bound_group", "MetricName": "tma_store_latency", - "MetricThreshold": "tma_store_latency > 0.1 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", - "PublicDescription": "This metric estimates fraction of cycles the CPU spent handling L1D store misses. Store accesses usually less impact out-of-order core performance; however; holding resources for longer time can lead into undesired implications (e.g. contention on L1D fill-buffer entries - see FB_Full). Related metrics: tma_branch_resteers, tma_fb_full, tma_l3_hit_latency, tma_lock_latency", + "MetricThreshold": "tma_store_latency > 0.1 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric estimates fraction of cycles the CPU spent handling L1D store misses. Store accesses usually less impact out-of-order core performance; however; holding resources for longer time can lead into undesired implications (e.g. contention on L1D fill-buffer entries - see FB_Full). Related metrics: tma_fb_full, tma_lock_latency", "ScaleUnit": "100%" }, { @@ -1753,7 +1752,7 @@ "MetricExpr": "tma_dtlb_store - tma_store_stlb_miss", "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_store_group", "MetricName": "tma_store_stlb_hit", - "MetricThreshold": "tma_store_stlb_hit > 0.05 & tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_store_stlb_hit > 0.05 & (tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))", "ScaleUnit": "100%" }, { @@ -1761,31 +1760,31 @@ "MetricExpr": "DTLB_STORE_MISSES.WALK_ACTIVE / tma_info_core_core_clks", "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_store_group", "MetricName": "tma_store_stlb_miss", - "MetricThreshold": "tma_store_stlb_miss > 0.05 & tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_store_stlb_miss > 0.05 & (tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 1 GB pages for data store accesses", + "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 1 GB pages for data store accesses.", "MetricExpr": "tma_store_stlb_miss * DTLB_STORE_MISSES.WALK_COMPLETED_1G / (DTLB_STORE_MISSES.WALK_COMPLETED_4K + DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M + DTLB_STORE_MISSES.WALK_COMPLETED_1G)", "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_store_stlb_miss_group", "MetricName": "tma_store_stlb_miss_1g", - "MetricThreshold": "tma_store_stlb_miss_1g > 0.05 & tma_store_stlb_miss > 0.05 & tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_store_stlb_miss_1g > 0.05 & (tma_store_stlb_miss > 0.05 & (tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))))", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 2 or 4 MB pages for data store accesses", + "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 2 or 4 MB pages for data store accesses.", "MetricExpr": "tma_store_stlb_miss * DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M / (DTLB_STORE_MISSES.WALK_COMPLETED_4K + DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M + DTLB_STORE_MISSES.WALK_COMPLETED_1G)", "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_store_stlb_miss_group", "MetricName": "tma_store_stlb_miss_2m", - "MetricThreshold": "tma_store_stlb_miss_2m > 0.05 & tma_store_stlb_miss > 0.05 & tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_store_stlb_miss_2m > 0.05 & (tma_store_stlb_miss > 0.05 & (tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))))", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 4 KB pages for data store accesses", + "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 4 KB pages for data store accesses.", "MetricExpr": "tma_store_stlb_miss * DTLB_STORE_MISSES.WALK_COMPLETED_4K / (DTLB_STORE_MISSES.WALK_COMPLETED_4K + DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M + DTLB_STORE_MISSES.WALK_COMPLETED_1G)", "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_store_stlb_miss_group", "MetricName": "tma_store_stlb_miss_4k", - "MetricThreshold": "tma_store_stlb_miss_4k > 0.05 & tma_store_stlb_miss > 0.05 & tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_store_stlb_miss_4k > 0.05 & (tma_store_stlb_miss > 0.05 & (tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))))", "ScaleUnit": "100%" }, { @@ -1793,7 +1792,7 @@ "MetricExpr": "9 * OCR.STREAMING_WR.ANY_RESPONSE / tma_info_thread_clks", "MetricGroup": "MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_issueSmSt;tma_store_bound_group", "MetricName": "tma_streaming_stores", - "MetricThreshold": "tma_streaming_stores > 0.2 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_streaming_stores > 0.2 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", "PublicDescription": "This metric estimates how often CPU was stalled due to Streaming store memory accesses; Streaming store optimize out a read request required by RFO stores. Even though store accesses do not typically stall out-of-order CPUs; there are few cases where stores can lead to actual stalls. This metric will be flagged should Streaming stores be a bottleneck. Sample with: OCR.STREAMING_WR.ANY_RESPONSE. Related metrics: tma_fb_full", "ScaleUnit": "100%" }, @@ -1802,7 +1801,7 @@ "MetricExpr": "10 * BACLEARS.ANY / tma_info_thread_clks", "MetricGroup": "BigFootprint;BvBC;FetchLat;TopdownL4;tma_L4_group;tma_branch_resteers_group", "MetricName": "tma_unknown_branches", - "MetricThreshold": "tma_unknown_branches > 0.05 & tma_branch_resteers > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricThreshold": "tma_unknown_branches > 0.05 & (tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))", "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to new branch address clears. These are fetched branches the Branch Prediction Unit was unable to recognize (e.g. first time the branch is fetched or hitting BTB capacity limit) hence called Unknown Branches. Sample with: BACLEARS.ANY", "ScaleUnit": "100%" }, @@ -1811,8 +1810,8 @@ "MetricExpr": "tma_retiring * UOPS_EXECUTED.X87 / UOPS_EXECUTED.THREAD", "MetricGroup": "Compute;TopdownL4;tma_L4_group;tma_fp_arith_group", "MetricName": "tma_x87_use", - "MetricThreshold": "tma_x87_use > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6", - "PublicDescription": "This metric serves as an approximation of legacy x87 usage. It accounts for instructions beyond X87 FP arithmetic operations; hence may be used as a thermometer to avoid X87 high usage and preferably upgrade to modern ISA. See Tip under Tuning Hint", + "MetricThreshold": "tma_x87_use > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6)", + "PublicDescription": "This metric serves as an approximation of legacy x87 usage. It accounts for instructions beyond X87 FP arithmetic operations; hence may be used as a thermometer to avoid X87 high usage and preferably upgrade to modern ISA. See Tip under Tuning Hint.", "ScaleUnit": "100%" }, { diff --git a/tools/perf/pmu-events/arch/x86/icelake/memory.json b/tools/perf/pmu-events/arch/x86/icelake/memory.json index abaf3f4f9d63..1455aaac37b1 100644 --- a/tools/perf/pmu-events/arch/x86/icelake/memory.json +++ b/tools/perf/pmu-events/arch/x86/icelake/memory.json @@ -177,6 +177,16 @@ "UMask": "0x1" }, { + "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that DRAM supplied the request.", + "Counter": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OCR.DEMAND_CODE_RD.DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x184000004", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that was not supplied by the L3 cache.", "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -187,6 +197,26 @@ "UMask": "0x1" }, { + "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that DRAM supplied the request.", + "Counter": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OCR.DEMAND_CODE_RD.LOCAL_DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x184000004", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts demand data reads that DRAM supplied the request.", + "Counter": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OCR.DEMAND_DATA_RD.DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x184000001", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { "BriefDescription": "Counts demand data reads that was not supplied by the L3 cache.", "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -197,6 +227,26 @@ "UMask": "0x1" }, { + "BriefDescription": "Counts demand data reads that DRAM supplied the request.", + "Counter": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OCR.DEMAND_DATA_RD.LOCAL_DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x184000001", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts demand reads for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that DRAM supplied the request.", + "Counter": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OCR.DEMAND_RFO.DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x184000002", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { "BriefDescription": "Counts demand reads for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that was not supplied by the L3 cache.", "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -207,6 +257,26 @@ "UMask": "0x1" }, { + "BriefDescription": "Counts demand reads for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that DRAM supplied the request.", + "Counter": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OCR.DEMAND_RFO.LOCAL_DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x184000002", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts L1 data cache prefetch requests and software prefetches (except PREFETCHW) that DRAM supplied the request.", + "Counter": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OCR.HWPF_L1D_AND_SWPF.DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x184000400", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { "BriefDescription": "Counts L1 data cache prefetch requests and software prefetches (except PREFETCHW) that was not supplied by the L3 cache.", "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -217,6 +287,26 @@ "UMask": "0x1" }, { + "BriefDescription": "Counts L1 data cache prefetch requests and software prefetches (except PREFETCHW) that DRAM supplied the request.", + "Counter": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OCR.HWPF_L1D_AND_SWPF.LOCAL_DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x184000400", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts hardware prefetch data reads (which bring data to L2) that DRAM supplied the request.", + "Counter": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OCR.HWPF_L2_DATA_RD.DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x184000010", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { "BriefDescription": "Counts hardware prefetch data reads (which bring data to L2) that was not supplied by the L3 cache.", "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -227,6 +317,26 @@ "UMask": "0x1" }, { + "BriefDescription": "Counts hardware prefetch data reads (which bring data to L2) that DRAM supplied the request.", + "Counter": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OCR.HWPF_L2_DATA_RD.LOCAL_DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x184000010", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts hardware prefetch RFOs (which bring data to L2) that DRAM supplied the request.", + "Counter": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OCR.HWPF_L2_RFO.DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x184000020", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { "BriefDescription": "Counts hardware prefetch RFOs (which bring data to L2) that was not supplied by the L3 cache.", "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -237,6 +347,26 @@ "UMask": "0x1" }, { + "BriefDescription": "Counts hardware prefetch RFOs (which bring data to L2) that DRAM supplied the request.", + "Counter": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OCR.HWPF_L2_RFO.LOCAL_DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x184000020", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts miscellaneous requests, such as I/O and un-cacheable accesses that DRAM supplied the request.", + "Counter": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OCR.OTHER.DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x184008000", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { "BriefDescription": "Counts miscellaneous requests, such as I/O and un-cacheable accesses that was not supplied by the L3 cache.", "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -247,6 +377,26 @@ "UMask": "0x1" }, { + "BriefDescription": "Counts miscellaneous requests, such as I/O and un-cacheable accesses that DRAM supplied the request.", + "Counter": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OCR.OTHER.LOCAL_DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x184008000", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts streaming stores that DRAM supplied the request.", + "Counter": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OCR.STREAMING_WR.DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x184000800", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { "BriefDescription": "Counts streaming stores that was not supplied by the L3 cache.", "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -257,6 +407,16 @@ "UMask": "0x1" }, { + "BriefDescription": "Counts streaming stores that DRAM supplied the request.", + "Counter": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OCR.STREAMING_WR.LOCAL_DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x184000800", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { "BriefDescription": "Counts demand data read requests that miss the L3 cache.", "Counter": "0,1,2,3", "EventCode": "0xb0", diff --git a/tools/perf/pmu-events/arch/x86/icelake/other.json b/tools/perf/pmu-events/arch/x86/icelake/other.json index a96b2a989d3f..141cd30a30af 100644 --- a/tools/perf/pmu-events/arch/x86/icelake/other.json +++ b/tools/perf/pmu-events/arch/x86/icelake/other.json @@ -27,186 +27,6 @@ "UMask": "0x20" }, { - "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that have any type of response.", - "Counter": "0,1,2,3", - "EventCode": "0xB7, 0xBB", - "EventName": "OCR.DEMAND_CODE_RD.ANY_RESPONSE", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x10004", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that DRAM supplied the request.", - "Counter": "0,1,2,3", - "EventCode": "0xB7, 0xBB", - "EventName": "OCR.DEMAND_CODE_RD.DRAM", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x184000004", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that DRAM supplied the request.", - "Counter": "0,1,2,3", - "EventCode": "0xB7, 0xBB", - "EventName": "OCR.DEMAND_CODE_RD.LOCAL_DRAM", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x184000004", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts demand data reads that have any type of response.", - "Counter": "0,1,2,3", - "EventCode": "0xB7, 0xBB", - "EventName": "OCR.DEMAND_DATA_RD.ANY_RESPONSE", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x10001", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts demand data reads that DRAM supplied the request.", - "Counter": "0,1,2,3", - "EventCode": "0xB7, 0xBB", - "EventName": "OCR.DEMAND_DATA_RD.DRAM", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x184000001", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts demand data reads that DRAM supplied the request.", - "Counter": "0,1,2,3", - "EventCode": "0xB7, 0xBB", - "EventName": "OCR.DEMAND_DATA_RD.LOCAL_DRAM", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x184000001", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts demand reads for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that have any type of response.", - "Counter": "0,1,2,3", - "EventCode": "0xB7, 0xBB", - "EventName": "OCR.DEMAND_RFO.ANY_RESPONSE", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x10002", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts demand reads for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that DRAM supplied the request.", - "Counter": "0,1,2,3", - "EventCode": "0xB7, 0xBB", - "EventName": "OCR.DEMAND_RFO.DRAM", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x184000002", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts demand reads for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that DRAM supplied the request.", - "Counter": "0,1,2,3", - "EventCode": "0xB7, 0xBB", - "EventName": "OCR.DEMAND_RFO.LOCAL_DRAM", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x184000002", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts L1 data cache prefetch requests and software prefetches (except PREFETCHW) that have any type of response.", - "Counter": "0,1,2,3", - "EventCode": "0xB7, 0xBB", - "EventName": "OCR.HWPF_L1D_AND_SWPF.ANY_RESPONSE", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x10400", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts L1 data cache prefetch requests and software prefetches (except PREFETCHW) that DRAM supplied the request.", - "Counter": "0,1,2,3", - "EventCode": "0xB7, 0xBB", - "EventName": "OCR.HWPF_L1D_AND_SWPF.DRAM", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x184000400", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts L1 data cache prefetch requests and software prefetches (except PREFETCHW) that DRAM supplied the request.", - "Counter": "0,1,2,3", - "EventCode": "0xB7, 0xBB", - "EventName": "OCR.HWPF_L1D_AND_SWPF.LOCAL_DRAM", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x184000400", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts hardware prefetch data reads (which bring data to L2) that have any type of response.", - "Counter": "0,1,2,3", - "EventCode": "0xB7, 0xBB", - "EventName": "OCR.HWPF_L2_DATA_RD.ANY_RESPONSE", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x10010", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts hardware prefetch data reads (which bring data to L2) that DRAM supplied the request.", - "Counter": "0,1,2,3", - "EventCode": "0xB7, 0xBB", - "EventName": "OCR.HWPF_L2_DATA_RD.DRAM", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x184000010", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts hardware prefetch data reads (which bring data to L2) that DRAM supplied the request.", - "Counter": "0,1,2,3", - "EventCode": "0xB7, 0xBB", - "EventName": "OCR.HWPF_L2_DATA_RD.LOCAL_DRAM", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x184000010", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts hardware prefetch RFOs (which bring data to L2) that have any type of response.", - "Counter": "0,1,2,3", - "EventCode": "0xB7, 0xBB", - "EventName": "OCR.HWPF_L2_RFO.ANY_RESPONSE", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x10020", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts hardware prefetch RFOs (which bring data to L2) that DRAM supplied the request.", - "Counter": "0,1,2,3", - "EventCode": "0xB7, 0xBB", - "EventName": "OCR.HWPF_L2_RFO.DRAM", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x184000020", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts hardware prefetch RFOs (which bring data to L2) that DRAM supplied the request.", - "Counter": "0,1,2,3", - "EventCode": "0xB7, 0xBB", - "EventName": "OCR.HWPF_L2_RFO.LOCAL_DRAM", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x184000020", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { "BriefDescription": "Counts miscellaneous requests, such as I/O and un-cacheable accesses that have any type of response.", "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -217,26 +37,6 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts miscellaneous requests, such as I/O and un-cacheable accesses that DRAM supplied the request.", - "Counter": "0,1,2,3", - "EventCode": "0xB7, 0xBB", - "EventName": "OCR.OTHER.DRAM", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x184008000", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts miscellaneous requests, such as I/O and un-cacheable accesses that DRAM supplied the request.", - "Counter": "0,1,2,3", - "EventCode": "0xB7, 0xBB", - "EventName": "OCR.OTHER.LOCAL_DRAM", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x184008000", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { "BriefDescription": "Counts streaming stores that have any type of response.", "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -245,25 +45,5 @@ "MSRValue": "0x10800", "SampleAfterValue": "100003", "UMask": "0x1" - }, - { - "BriefDescription": "Counts streaming stores that DRAM supplied the request.", - "Counter": "0,1,2,3", - "EventCode": "0xB7, 0xBB", - "EventName": "OCR.STREAMING_WR.DRAM", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x184000800", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts streaming stores that DRAM supplied the request.", - "Counter": "0,1,2,3", - "EventCode": "0xB7, 0xBB", - "EventName": "OCR.STREAMING_WR.LOCAL_DRAM", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x184000800", - "SampleAfterValue": "100003", - "UMask": "0x1" } ] diff --git a/tools/perf/pmu-events/arch/x86/icelakex/cache.json b/tools/perf/pmu-events/arch/x86/icelakex/cache.json index e8ab6ef2cd50..e46fd6f91d6b 100644 --- a/tools/perf/pmu-events/arch/x86/icelakex/cache.json +++ b/tools/perf/pmu-events/arch/x86/icelakex/cache.json @@ -1,5 +1,68 @@ [ { + "BriefDescription": "Hit snoop reply with data, line invalidated.", + "Counter": "0,1,2,3", + "EventCode": "0xef", + "EventName": "CORE_SNOOP_RESPONSE.I_FWD_FE", + "PublicDescription": "Counts responses to snoops indicating the line will now be (I)nvalidated: removed from this core's cache, after the data is forwarded back to the requestor and indicating the data was found unmodified in the (FE) Forward or Exclusive State in this cores caches cache. A single snoop response from the core counts on all hyperthreads of the core.", + "SampleAfterValue": "1000003", + "UMask": "0x20" + }, + { + "BriefDescription": "HitM snoop reply with data, line invalidated.", + "Counter": "0,1,2,3", + "EventCode": "0xef", + "EventName": "CORE_SNOOP_RESPONSE.I_FWD_M", + "PublicDescription": "Counts responses to snoops indicating the line will now be (I)nvalidated: removed from this core's caches, after the data is forwarded back to the requestor, and indicating the data was found modified(M) in this cores caches cache (aka HitM response). A single snoop response from the core counts on all hyperthreads of the core.", + "SampleAfterValue": "1000003", + "UMask": "0x10" + }, + { + "BriefDescription": "Hit snoop reply without sending the data, line invalidated.", + "Counter": "0,1,2,3", + "EventCode": "0xef", + "EventName": "CORE_SNOOP_RESPONSE.I_HIT_FSE", + "PublicDescription": "Counts responses to snoops indicating the line will now be (I)nvalidated in this core's caches without being forwarded back to the requestor. The line was in Forward, Shared or Exclusive (FSE) state in this cores caches. A single snoop response from the core counts on all hyperthreads of the core.", + "SampleAfterValue": "1000003", + "UMask": "0x2" + }, + { + "BriefDescription": "Line not found snoop reply", + "Counter": "0,1,2,3", + "EventCode": "0xef", + "EventName": "CORE_SNOOP_RESPONSE.MISS", + "PublicDescription": "Counts responses to snoops indicating that the data was not found (IHitI) in this core's caches. A single snoop response from the core counts on all hyperthreads of the Core.", + "SampleAfterValue": "1000003", + "UMask": "0x1" + }, + { + "BriefDescription": "Hit snoop reply with data, line kept in Shared state.", + "Counter": "0,1,2,3", + "EventCode": "0xef", + "EventName": "CORE_SNOOP_RESPONSE.S_FWD_FE", + "PublicDescription": "Counts responses to snoops indicating the line may be kept on this core in the (S)hared state, after the data is forwarded back to the requestor, initially the data was found in the cache in the (FS) Forward or Shared state. A single snoop response from the core counts on all hyperthreads of the core.", + "SampleAfterValue": "1000003", + "UMask": "0x40" + }, + { + "BriefDescription": "HitM snoop reply with data, line kept in Shared state", + "Counter": "0,1,2,3", + "EventCode": "0xef", + "EventName": "CORE_SNOOP_RESPONSE.S_FWD_M", + "PublicDescription": "Counts responses to snoops indicating the line may be kept on this core in the (S)hared state, after the data is forwarded back to the requestor, initially the data was found in the cache in the (M)odified state. A single snoop response from the core counts on all hyperthreads of the core.", + "SampleAfterValue": "1000003", + "UMask": "0x8" + }, + { + "BriefDescription": "Hit snoop reply without sending the data, line kept in Shared state.", + "Counter": "0,1,2,3", + "EventCode": "0xef", + "EventName": "CORE_SNOOP_RESPONSE.S_HIT_FSE", + "PublicDescription": "Counts responses to snoops indicating the line was kept on this core in the (S)hared state, and that the data was found unmodified but not forwarded back to the requestor, initially the data was found in the cache in the (FSE) Forward, Shared state or Exclusive state. A single snoop response from the core counts on all hyperthreads of the core.", + "SampleAfterValue": "1000003", + "UMask": "0x4" + }, + { "BriefDescription": "Counts the number of cache lines replaced in L1 data cache.", "Counter": "0,1,2,3", "EventCode": "0x51", @@ -507,6 +570,16 @@ "UMask": "0x80" }, { + "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that have any type of response.", + "Counter": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OCR.DEMAND_CODE_RD.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x10004", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that hit in the L3 or were snooped from another core's caches on the same socket.", "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -547,6 +620,16 @@ "UMask": "0x1" }, { + "BriefDescription": "Counts demand data reads that have any type of response.", + "Counter": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OCR.DEMAND_DATA_RD.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x10001", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { "BriefDescription": "Counts demand data reads that hit in the L3 or were snooped from another core's caches on the same socket.", "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -587,6 +670,26 @@ "UMask": "0x1" }, { + "BriefDescription": "Counts demand data reads that were supplied by PMM attached to this socket, unless in Sub NUMA Cluster(SNC) Mode. In SNC Mode counts only those PMM accesses that are controlled by the close SNC Cluster.", + "Counter": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OCR.DEMAND_DATA_RD.LOCAL_PMM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x100400001", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts demand data reads that were supplied by PMM.", + "Counter": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OCR.DEMAND_DATA_RD.PMM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x703C00001", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { "BriefDescription": "Counts demand data reads that were supplied by a cache on a remote socket where a snoop hit a modified line in another core's caches which forwarded the data.", "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -607,6 +710,16 @@ "UMask": "0x1" }, { + "BriefDescription": "Counts demand data reads that were supplied by PMM attached to another socket.", + "Counter": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OCR.DEMAND_DATA_RD.REMOTE_PMM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x703000001", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { "BriefDescription": "Counts demand data reads that hit a modified line in a distant L3 Cache or were snooped from a distant core's L1/L2 caches on this socket when the system is in SNC (sub-NUMA cluster) mode.", "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -627,6 +740,26 @@ "UMask": "0x1" }, { + "BriefDescription": "Counts demand data reads that were supplied by PMM on a distant memory controller of this socket when the system is in SNC (sub-NUMA cluster) mode.", + "Counter": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OCR.DEMAND_DATA_RD.SNC_PMM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x700800001", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts demand reads for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that have any type of response.", + "Counter": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OCR.DEMAND_RFO.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x3F3FFC0002", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { "BriefDescription": "Counts demand reads for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that hit in the L3 or were snooped from another core's caches on the same socket.", "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -647,6 +780,36 @@ "UMask": "0x1" }, { + "BriefDescription": "Counts demand reads for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that were supplied by PMM attached to this socket, unless in Sub NUMA Cluster(SNC) Mode. In SNC Mode counts only those PMM accesses that are controlled by the close SNC Cluster.", + "Counter": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OCR.DEMAND_RFO.LOCAL_PMM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x100400002", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts demand reads for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that were supplied by PMM.", + "Counter": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OCR.DEMAND_RFO.PMM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x703C00002", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts demand reads for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that were supplied by PMM attached to another socket.", + "Counter": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OCR.DEMAND_RFO.REMOTE_PMM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x703000002", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { "BriefDescription": "Counts demand reads for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that hit a modified line in a distant L3 Cache or were snooped from a distant core's L1/L2 caches on this socket when the system is in SNC (sub-NUMA cluster) mode.", "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -667,6 +830,16 @@ "UMask": "0x1" }, { + "BriefDescription": "Counts demand reads for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that were supplied by PMM on a distant memory controller of this socket when the system is in SNC (sub-NUMA cluster) mode.", + "Counter": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OCR.DEMAND_RFO.SNC_PMM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x700800002", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { "BriefDescription": "Counts L1 data cache prefetch requests and software prefetches (except PREFETCHW) that hit in the L3 or were snooped from another core's caches on the same socket.", "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -677,6 +850,26 @@ "UMask": "0x1" }, { + "BriefDescription": "Counts hardware prefetch (which bring data to L2) that have any type of response.", + "Counter": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OCR.HWPF_L2.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x10070", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts hardware prefetches to the L3 only that have any type of response.", + "Counter": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OCR.HWPF_L3.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x12380", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { "BriefDescription": "Counts hardware prefetches to the L3 only that hit in the L3 or were snooped from another core's caches on the same socket.", "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -687,6 +880,26 @@ "UMask": "0x1" }, { + "BriefDescription": "Counts hardware prefetches to the L3 only that were not supplied by the local socket's L1, L2, or L3 caches and the cacheline was homed in a remote socket.", + "Counter": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OCR.HWPF_L3.REMOTE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x90002380", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts full cacheline writes (ItoM) that were not supplied by the local socket's L1, L2, or L3 caches and the cacheline was homed in a remote socket.", + "Counter": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OCR.ITOM.REMOTE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x90000002", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { "BriefDescription": "Counts hardware and software prefetches to all cache levels that hit in the L3 or were snooped from another core's caches on the same socket.", "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -697,6 +910,16 @@ "UMask": "0x1" }, { + "BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that have any type of response.", + "Counter": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OCR.READS_TO_CORE.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x3F3FFC0477", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { "BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that hit in the L3 or were snooped from another core's caches on the same socket.", "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -737,6 +960,36 @@ "UMask": "0x1" }, { + "BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by PMM attached to this socket, unless in Sub NUMA Cluster(SNC) Mode. In SNC Mode counts only those PMM accesses that are controlled by the close SNC Cluster.", + "Counter": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OCR.READS_TO_CORE.LOCAL_PMM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x100400477", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by PMM attached to this socket, whether or not in Sub NUMA Cluster(SNC) Mode. In SNC Mode counts PMM accesses that are controlled by the close or distant SNC Cluster.", + "Counter": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OCR.READS_TO_CORE.LOCAL_SOCKET_PMM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x700C00477", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were not supplied by the local socket's L1, L2, or L3 caches and were supplied by a remote socket.", + "Counter": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OCR.READS_TO_CORE.REMOTE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x3F33000477", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { "BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by a cache on a remote socket where a snoop was sent and data was returned (Modified or Not Modified).", "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -767,6 +1020,16 @@ "UMask": "0x1" }, { + "BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by PMM attached to another socket.", + "Counter": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OCR.READS_TO_CORE.REMOTE_PMM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x703000477", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { "BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that hit a modified line in a distant L3 Cache or were snooped from a distant core's L1/L2 caches on this socket when the system is in SNC (sub-NUMA cluster) mode.", "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -787,6 +1050,16 @@ "UMask": "0x1" }, { + "BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by PMM on a distant memory controller of this socket when the system is in SNC (sub-NUMA cluster) mode.", + "Counter": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OCR.READS_TO_CORE.SNC_PMM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x700800477", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { "BriefDescription": "Counts streaming stores that hit in the L3 or were snooped from another core's caches on the same socket.", "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", diff --git a/tools/perf/pmu-events/arch/x86/icelakex/icx-metrics.json b/tools/perf/pmu-events/arch/x86/icelakex/icx-metrics.json index 7bee03e532e4..a886a0cfee07 100644 --- a/tools/perf/pmu-events/arch/x86/icelakex/icx-metrics.json +++ b/tools/perf/pmu-events/arch/x86/icelakex/icx-metrics.json @@ -335,12 +335,12 @@ "MetricExpr": "LD_BLOCKS_PARTIAL.ADDRESS_ALIAS / tma_info_thread_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group", "MetricName": "tma_4k_aliasing", - "MetricThreshold": "tma_4k_aliasing > 0.2 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", - "PublicDescription": "This metric estimates how often memory load accesses were aliased by preceding stores (in program order) with a 4K address offset. False match is possible; which incur a few cycles load re-issue. However; the short re-issue duration is often hidden by the out-of-order core and HW optimizations; hence a user may safely ignore a high value of this metric unless it manages to propagate up into parent nodes of the hierarchy (e.g. to L1_Bound)", + "MetricThreshold": "tma_4k_aliasing > 0.2 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric estimates how often memory load accesses were aliased by preceding stores (in program order) with a 4K address offset. False match is possible; which incur a few cycles load re-issue. However; the short re-issue duration is often hidden by the out-of-order core and HW optimizations; hence a user may safely ignore a high value of this metric unless it manages to propagate up into parent nodes of the hierarchy (e.g. to L1_Bound).", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution ports for ALU operations", + "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution ports for ALU operations.", "MetricExpr": "(UOPS_DISPATCHED.PORT_0 + UOPS_DISPATCHED.PORT_1 + UOPS_DISPATCHED.PORT_5 + UOPS_DISPATCHED.PORT_6) / (4 * tma_info_core_core_clks)", "MetricGroup": "TopdownL5;tma_L5_group;tma_ports_utilized_3m_group", "MetricName": "tma_alu_op_utilization", @@ -352,7 +352,7 @@ "MetricExpr": "34 * ASSISTS.ANY / tma_info_thread_slots", "MetricGroup": "BvIO;TopdownL4;tma_L4_group;tma_microcode_sequencer_group", "MetricName": "tma_assists", - "MetricThreshold": "tma_assists > 0.1 & tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1", + "MetricThreshold": "tma_assists > 0.1 & (tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1)", "PublicDescription": "This metric estimates fraction of slots the CPU retired uops delivered by the Microcode_Sequencer as a result of Assists. Assists are long sequences of uops that are required in certain corner-cases for operations that cannot be handled natively by the execution pipeline. For example; when working with very small floating point values (so-called Denormals); the FP units are not set up to perform these operations natively. Instead; a sequence of instructions to perform the computation on the Denormals is injected into the pipeline. Since these microcode sequences might be dozens of uops long; Assists can be extremely deleterious to performance and they can be avoided in many cases. Sample with: ASSISTS.ANY", "ScaleUnit": "100%" }, @@ -375,12 +375,12 @@ "MetricName": "tma_bad_speculation", "MetricThreshold": "tma_bad_speculation > 0.15", "MetricgroupNoGroup": "TopdownL1;Default", - "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example", + "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.", "ScaleUnit": "100%" }, { "BriefDescription": "Total pipeline cost of instruction fetch related bottlenecks by large code footprint programs (i-side cache; TLB and BTB misses)", - "MetricExpr": "100 * tma_fetch_latency * (tma_itlb_misses + tma_icache_misses + tma_unknown_branches) / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches)", + "MetricExpr": "100 * tma_fetch_latency * (tma_itlb_misses + tma_icache_misses + tma_unknown_branches) / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches)", "MetricGroup": "BigFootprint;BvBC;Fed;Frontend;IcMiss;MemoryTLB", "MetricName": "tma_bottleneck_big_code", "MetricThreshold": "tma_bottleneck_big_code > 20" @@ -395,7 +395,7 @@ }, { "BriefDescription": "Total pipeline cost of external Memory- or Cache-Bandwidth related bottlenecks", - "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_mem_bandwidth / (tma_mem_bandwidth + tma_mem_latency)) + tma_memory_bound * (tma_l3_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_sq_full / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_memory_bound * (tma_l1_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_fb_full / (tma_dtlb_load + tma_store_fwd_blk + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_4k_aliasing + tma_fb_full)))", + "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_mem_bandwidth / (tma_mem_bandwidth + tma_mem_latency)) + tma_memory_bound * (tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_sq_full / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_fb_full / (tma_4k_aliasing + tma_dtlb_load + tma_fb_full + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)))", "MetricGroup": "BvMB;Mem;MemoryBW;Offcore;tma_issueBW", "MetricName": "tma_bottleneck_cache_memory_bandwidth", "MetricThreshold": "tma_bottleneck_cache_memory_bandwidth > 20", @@ -403,7 +403,7 @@ }, { "BriefDescription": "Total pipeline cost of external Memory- or Cache-Latency related bottlenecks", - "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_mem_latency / (tma_mem_bandwidth + tma_mem_latency)) + tma_memory_bound * (tma_l3_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_l3_hit_latency / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_memory_bound * tma_l2_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound) + tma_memory_bound * (tma_l1_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_l1_latency_dependency / (tma_dtlb_load + tma_store_fwd_blk + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_4k_aliasing + tma_fb_full)) + tma_memory_bound * (tma_l1_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_lock_latency / (tma_dtlb_load + tma_store_fwd_blk + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_4k_aliasing + tma_fb_full)) + tma_memory_bound * (tma_l1_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_split_loads / (tma_dtlb_load + tma_store_fwd_blk + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_4k_aliasing + tma_fb_full)) + tma_memory_bound * (tma_store_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_split_stores / (tma_store_latency + tma_false_sharing + tma_split_stores + tma_streaming_stores + tma_dtlb_store)) + tma_memory_bound * (tma_store_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_store_latency / (tma_store_latency + tma_false_sharing + tma_split_stores + tma_streaming_stores + tma_dtlb_store)))", + "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_mem_latency / (tma_mem_bandwidth + tma_mem_latency)) + tma_memory_bound * (tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_l3_hit_latency / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_memory_bound * tma_l2_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) + tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_l1_latency_dependency / (tma_4k_aliasing + tma_dtlb_load + tma_fb_full + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_lock_latency / (tma_4k_aliasing + tma_dtlb_load + tma_fb_full + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_split_loads / (tma_4k_aliasing + tma_dtlb_load + tma_fb_full + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_memory_bound * (tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_split_stores / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency + tma_streaming_stores)) + tma_memory_bound * (tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_store_latency / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency + tma_streaming_stores)))", "MetricGroup": "BvML;Mem;MemoryLat;Offcore;tma_issueLat", "MetricName": "tma_bottleneck_cache_memory_latency", "MetricThreshold": "tma_bottleneck_cache_memory_latency > 20", @@ -411,22 +411,22 @@ }, { "BriefDescription": "Total pipeline cost when the execution is compute-bound - an estimation", - "MetricExpr": "100 * (tma_core_bound * tma_divider / (tma_divider + tma_serializing_operation + tma_ports_utilization) + tma_core_bound * (tma_ports_utilization / (tma_divider + tma_serializing_operation + tma_ports_utilization)) * (tma_ports_utilized_3m / (tma_ports_utilized_0 + tma_ports_utilized_1 + tma_ports_utilized_2 + tma_ports_utilized_3m)))", + "MetricExpr": "100 * (tma_core_bound * tma_divider / (tma_divider + tma_ports_utilization + tma_serializing_operation) + tma_core_bound * (tma_ports_utilization / (tma_divider + tma_ports_utilization + tma_serializing_operation)) * (tma_ports_utilized_3m / (tma_ports_utilized_0 + tma_ports_utilized_1 + tma_ports_utilized_2 + tma_ports_utilized_3m)))", "MetricGroup": "BvCB;Cor;tma_issueComp", "MetricName": "tma_bottleneck_compute_bound_est", "MetricThreshold": "tma_bottleneck_compute_bound_est > 20", - "PublicDescription": "Total pipeline cost when the execution is compute-bound - an estimation. Covers Core Bound when High ILP as well as when long-latency execution units are busy" + "PublicDescription": "Total pipeline cost when the execution is compute-bound - an estimation. Covers Core Bound when High ILP as well as when long-latency execution units are busy. Related metrics: " }, { "BriefDescription": "Total pipeline cost of instruction fetch bandwidth related bottlenecks (when the front-end could not sustain operations delivery to the back-end)", - "MetricExpr": "100 * (tma_frontend_bound - (1 - 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts) * tma_fetch_latency * tma_mispredicts_resteers / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches) - tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * (tma_fetch_latency * (tma_ms_switches + tma_branch_resteers * (tma_clears_resteers + 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts * tma_mispredicts_resteers) / (tma_mispredicts_resteers + tma_clears_resteers + tma_unknown_branches)) / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches) + tma_fetch_bandwidth * tma_ms / (tma_mite + tma_dsb + tma_ms))) - tma_bottleneck_big_code", + "MetricExpr": "100 * (tma_frontend_bound - (1 - 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts) * tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) - tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * (tma_fetch_latency * (tma_ms_switches + tma_branch_resteers * (tma_clears_resteers + 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts * tma_mispredicts_resteers) / (tma_clears_resteers + tma_mispredicts_resteers + tma_unknown_branches)) / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) + tma_fetch_bandwidth * tma_ms / (tma_dsb + tma_mite + tma_ms))) - tma_bottleneck_big_code", "MetricGroup": "BvFB;Fed;FetchBW;Frontend", "MetricName": "tma_bottleneck_instruction_fetch_bw", "MetricThreshold": "tma_bottleneck_instruction_fetch_bw > 20" }, { "BriefDescription": "Total pipeline cost of irregular execution (e.g", - "MetricExpr": "100 * (tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * (tma_fetch_latency * (tma_ms_switches + tma_branch_resteers * (tma_clears_resteers + 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts * tma_mispredicts_resteers) / (tma_mispredicts_resteers + tma_clears_resteers + tma_unknown_branches)) / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches) + tma_fetch_bandwidth * tma_ms / (tma_mite + tma_dsb + tma_ms)) + 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts * tma_branch_mispredicts + tma_machine_clears * tma_other_nukes / tma_other_nukes + tma_core_bound * (tma_serializing_operation + tma_core_bound * RS_EVENTS.EMPTY_CYCLES / tma_info_thread_clks * tma_ports_utilized_0) / (tma_divider + tma_serializing_operation + tma_ports_utilization) + tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * tma_heavy_operations)", + "MetricExpr": "100 * (tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * (tma_fetch_latency * (tma_ms_switches + tma_branch_resteers * (tma_clears_resteers + 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts * tma_mispredicts_resteers) / (tma_clears_resteers + tma_mispredicts_resteers + tma_unknown_branches)) / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) + tma_fetch_bandwidth * tma_ms / (tma_dsb + tma_mite + tma_ms)) + 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts * tma_branch_mispredicts + tma_machine_clears * tma_other_nukes / tma_other_nukes + tma_core_bound * (tma_serializing_operation + tma_core_bound * RS_EVENTS.EMPTY_CYCLES / tma_info_thread_clks * tma_ports_utilized_0) / (tma_divider + tma_ports_utilization + tma_serializing_operation) + tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * tma_heavy_operations)", "MetricGroup": "Bad;BvIO;Cor;Ret;tma_issueMS", "MetricName": "tma_bottleneck_irregular_overhead", "MetricThreshold": "tma_bottleneck_irregular_overhead > 10", @@ -434,7 +434,7 @@ }, { "BriefDescription": "Total pipeline cost of Memory Address Translation related bottlenecks (data-side TLBs)", - "MetricExpr": "100 * (tma_memory_bound * (tma_l1_bound / max(tma_memory_bound, tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_dtlb_load / max(tma_l1_bound, tma_dtlb_load + tma_store_fwd_blk + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_4k_aliasing + tma_fb_full)) + tma_memory_bound * (tma_store_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_dtlb_store / (tma_store_latency + tma_false_sharing + tma_split_stores + tma_streaming_stores + tma_dtlb_store)))", + "MetricExpr": "100 * (tma_memory_bound * (tma_l1_bound / max(tma_memory_bound, tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_dtlb_load / max(tma_l1_bound, tma_4k_aliasing + tma_dtlb_load + tma_fb_full + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_memory_bound * (tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_dtlb_store / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency + tma_streaming_stores)))", "MetricGroup": "BvMT;Mem;MemoryTLB;Offcore;tma_issueTLB", "MetricName": "tma_bottleneck_memory_data_tlbs", "MetricThreshold": "tma_bottleneck_memory_data_tlbs > 20", @@ -442,7 +442,7 @@ }, { "BriefDescription": "Total pipeline cost of Memory Synchronization related bottlenecks (data transfers and coherency updates across processors)", - "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound) * (tma_mem_latency / (tma_mem_bandwidth + tma_mem_latency)) * tma_remote_cache / (tma_local_mem + tma_remote_mem + tma_remote_cache) + tma_l3_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound) * (tma_contested_accesses + tma_data_sharing) / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full) + tma_store_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound) * tma_false_sharing / (tma_store_latency + tma_false_sharing + tma_split_stores + tma_streaming_stores + tma_dtlb_store - tma_store_latency)) + tma_machine_clears * (1 - tma_other_nukes / tma_other_nukes))", + "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_mem_latency / (tma_mem_bandwidth + tma_mem_latency)) * tma_remote_cache / (tma_local_mem + tma_remote_cache + tma_remote_mem) + tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_contested_accesses + tma_data_sharing) / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full) + tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * tma_false_sharing / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency + tma_streaming_stores - tma_store_latency)) + tma_machine_clears * (1 - tma_other_nukes / tma_other_nukes))", "MetricGroup": "BvMS;LockCont;Mem;Offcore;tma_issueSyncxn", "MetricName": "tma_bottleneck_memory_synchronization", "MetricThreshold": "tma_bottleneck_memory_synchronization > 10", @@ -450,7 +450,7 @@ }, { "BriefDescription": "Total pipeline cost of Branch Misprediction related bottlenecks", - "MetricExpr": "100 * (1 - 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts) * (tma_branch_mispredicts + tma_fetch_latency * tma_mispredicts_resteers / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches))", + "MetricExpr": "100 * (1 - 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts) * (tma_branch_mispredicts + tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches))", "MetricGroup": "Bad;BadSpec;BrMispredicts;BvMP;tma_issueBM", "MetricName": "tma_bottleneck_mispredictions", "MetricThreshold": "tma_bottleneck_mispredictions > 20", @@ -462,17 +462,17 @@ "MetricGroup": "BvOB;Cor;Offcore", "MetricName": "tma_bottleneck_other_bottlenecks", "MetricThreshold": "tma_bottleneck_other_bottlenecks > 20", - "PublicDescription": "Total pipeline cost of remaining bottlenecks in the back-end. Examples include data-dependencies (Core Bound when Low ILP) and other unlisted memory-related stalls" + "PublicDescription": "Total pipeline cost of remaining bottlenecks in the back-end. Examples include data-dependencies (Core Bound when Low ILP) and other unlisted memory-related stalls." }, { - "BriefDescription": "Total pipeline cost of \"useful operations\" - the portion of Retiring category not covered by Branching_Overhead nor Irregular_Overhead", + "BriefDescription": "Total pipeline cost of \"useful operations\" - the portion of Retiring category not covered by Branching_Overhead nor Irregular_Overhead.", "MetricExpr": "100 * (tma_retiring - (BR_INST_RETIRED.ALL_BRANCHES + 2 * BR_INST_RETIRED.NEAR_CALL + INST_RETIRED.NOP) / tma_info_thread_slots - tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * tma_heavy_operations)", "MetricGroup": "BvUW;Ret", "MetricName": "tma_bottleneck_useful_work", "MetricThreshold": "tma_bottleneck_useful_work > 20" }, { - "BriefDescription": "This metric represents fraction of slots where the CPU was retiring branch instructions", + "BriefDescription": "This metric represents fraction of slots where the CPU was retiring branch instructions.", "MetricExpr": "tma_light_operations * BR_INST_RETIRED.ALL_BRANCHES / (tma_retiring * tma_info_thread_slots)", "MetricGroup": "Branches;BvBO;Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group", "MetricName": "tma_branch_instructions", @@ -494,8 +494,8 @@ "MetricExpr": "INT_MISC.CLEAR_RESTEER_CYCLES / tma_info_thread_clks + tma_unknown_branches", "MetricGroup": "FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group", "MetricName": "tma_branch_resteers", - "MetricThreshold": "tma_branch_resteers > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", - "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers. Branch Resteers estimates the Frontend delay in fetching operations from corrected path; following all sorts of miss-predicted branches. For example; branchy code with lots of miss-predictions might get categorized under Branch Resteers. Note the value of this node may overlap with its siblings. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_l3_hit_latency, tma_store_latency", + "MetricThreshold": "tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers. Branch Resteers estimates the Frontend delay in fetching operations from corrected path; following all sorts of miss-predicted branches. For example; branchy code with lots of miss-predictions might get categorized under Branch Resteers. Note the value of this node may overlap with its siblings. Sample with: BR_MISP_RETIRED.ALL_BRANCHES", "ScaleUnit": "100%" }, { @@ -503,8 +503,8 @@ "MetricExpr": "max(0, tma_microcode_sequencer - tma_assists)", "MetricGroup": "TopdownL4;tma_L4_group;tma_microcode_sequencer_group", "MetricName": "tma_cisc", - "MetricThreshold": "tma_cisc > 0.1 & tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1", - "PublicDescription": "This metric estimates fraction of cycles the CPU retired uops originated from CISC (complex instruction set computer) instruction. A CISC instruction has multiple uops that are required to perform the instruction's functionality as in the case of read-modify-write as an example. Since these instructions require multiple uops they may or may not imply sub-optimal use of machine resources", + "MetricThreshold": "tma_cisc > 0.1 & (tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1)", + "PublicDescription": "This metric estimates fraction of cycles the CPU retired uops originated from CISC (complex instruction set computer) instruction. A CISC instruction has multiple uops that are required to perform the instruction's functionality as in the case of read-modify-write as an example. Since these instructions require multiple uops they may or may not imply sub-optimal use of machine resources.", "ScaleUnit": "100%" }, { @@ -512,24 +512,24 @@ "MetricExpr": "(1 - BR_MISP_RETIRED.ALL_BRANCHES / (BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT)) * INT_MISC.CLEAR_RESTEER_CYCLES / tma_info_thread_clks", "MetricGroup": "BadSpec;MachineClears;TopdownL4;tma_L4_group;tma_branch_resteers_group;tma_issueMC", "MetricName": "tma_clears_resteers", - "MetricThreshold": "tma_clears_resteers > 0.05 & tma_branch_resteers > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricThreshold": "tma_clears_resteers > 0.05 & (tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))", "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Machine Clears. Sample with: INT_MISC.CLEAR_RESTEER_CYCLES. Related metrics: tma_l1_bound, tma_machine_clears, tma_microcode_sequencer, tma_ms_switches", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates fraction of cycles the CPU was stalled due to instruction cache misses that hit in the L2 cache", + "BriefDescription": "This metric estimates fraction of cycles the CPU was stalled due to instruction cache misses that hit in the L2 cache.", "MetricExpr": "max(0, tma_icache_misses - tma_code_l2_miss)", "MetricGroup": "FetchLat;IcMiss;Offcore;TopdownL4;tma_L4_group;tma_icache_misses_group", "MetricName": "tma_code_l2_hit", - "MetricThreshold": "tma_code_l2_hit > 0.05 & tma_icache_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricThreshold": "tma_code_l2_hit > 0.05 & (tma_icache_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates fraction of cycles the CPU was stalled due to instruction cache misses that miss in the L2 cache", + "BriefDescription": "This metric estimates fraction of cycles the CPU was stalled due to instruction cache misses that miss in the L2 cache.", "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_CODE_RD / tma_info_thread_clks", "MetricGroup": "FetchLat;IcMiss;Offcore;TopdownL4;tma_L4_group;tma_icache_misses_group", "MetricName": "tma_code_l2_miss", - "MetricThreshold": "tma_code_l2_miss > 0.05 & tma_icache_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricThreshold": "tma_code_l2_miss > 0.05 & (tma_icache_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))", "ScaleUnit": "100%" }, { @@ -537,7 +537,7 @@ "MetricExpr": "max(0, tma_itlb_misses - tma_code_stlb_miss)", "MetricGroup": "FetchLat;MemoryTLB;TopdownL4;tma_L4_group;tma_itlb_misses_group", "MetricName": "tma_code_stlb_hit", - "MetricThreshold": "tma_code_stlb_hit > 0.05 & tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricThreshold": "tma_code_stlb_hit > 0.05 & (tma_itlb_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))", "ScaleUnit": "100%" }, { @@ -545,33 +545,33 @@ "MetricExpr": "ITLB_MISSES.WALK_ACTIVE / tma_info_thread_clks", "MetricGroup": "FetchLat;MemoryTLB;TopdownL4;tma_L4_group;tma_itlb_misses_group", "MetricName": "tma_code_stlb_miss", - "MetricThreshold": "tma_code_stlb_miss > 0.05 & tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricThreshold": "tma_code_stlb_miss > 0.05 & (tma_itlb_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 2 or 4 MB pages for (instruction) code accesses", + "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 2 or 4 MB pages for (instruction) code accesses.", "MetricExpr": "tma_code_stlb_miss * ITLB_MISSES.WALK_COMPLETED_2M_4M / (ITLB_MISSES.WALK_COMPLETED_4K + ITLB_MISSES.WALK_COMPLETED_2M_4M)", "MetricGroup": "FetchLat;MemoryTLB;TopdownL5;tma_L5_group;tma_code_stlb_miss_group", "MetricName": "tma_code_stlb_miss_2m", - "MetricThreshold": "tma_code_stlb_miss_2m > 0.05 & tma_code_stlb_miss > 0.05 & tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricThreshold": "tma_code_stlb_miss_2m > 0.05 & (tma_code_stlb_miss > 0.05 & (tma_itlb_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)))", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 4 KB pages for (instruction) code accesses", + "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 4 KB pages for (instruction) code accesses.", "MetricExpr": "tma_code_stlb_miss * ITLB_MISSES.WALK_COMPLETED_4K / (ITLB_MISSES.WALK_COMPLETED_4K + ITLB_MISSES.WALK_COMPLETED_2M_4M)", "MetricGroup": "FetchLat;MemoryTLB;TopdownL5;tma_L5_group;tma_code_stlb_miss_group", "MetricName": "tma_code_stlb_miss_4k", - "MetricThreshold": "tma_code_stlb_miss_4k > 0.05 & tma_code_stlb_miss > 0.05 & tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricThreshold": "tma_code_stlb_miss_4k > 0.05 & (tma_code_stlb_miss > 0.05 & (tma_itlb_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)))", "ScaleUnit": "100%" }, { "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses", "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "((48 * tma_info_system_core_frequency - 4 * tma_info_system_core_frequency) * (MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM * (OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM / (OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM + OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD))) + (47.5 * tma_info_system_core_frequency - 4 * tma_info_system_core_frequency) * MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks", + "MetricExpr": "(44 * tma_info_system_core_frequency * (MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM * (OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM / (OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM + OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD))) + 43.5 * tma_info_system_core_frequency * MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks", "MetricGroup": "BvMS;DataSharing;LockCont;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group", "MetricName": "tma_contested_accesses", - "MetricThreshold": "tma_contested_accesses > 0.05 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", - "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses. Contested accesses occur when data written by one Logical Processor are read by another Logical Processor on a different Physical Core. Examples of contested accesses include synchronizations such as locks; true data sharing such as modified locked variables; and false sharing. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM, MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS. Related metrics: tma_bottleneck_memory_synchronization, tma_data_sharing, tma_false_sharing, tma_machine_clears, tma_remote_cache", + "MetricThreshold": "tma_contested_accesses > 0.05 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses. Contested accesses occur when data written by one Logical Processor are read by another Logical Processor on a different Physical Core. Examples of contested accesses include synchronizations such as locks; true data sharing such as modified locked variables; and false sharing. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM_PS;MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS_PS. Related metrics: tma_bottleneck_memory_synchronization, tma_data_sharing, tma_false_sharing, tma_machine_clears, tma_remote_cache", "ScaleUnit": "100%" }, { @@ -581,25 +581,25 @@ "MetricName": "tma_core_bound", "MetricThreshold": "tma_core_bound > 0.1 & tma_backend_bound > 0.2", "MetricgroupNoGroup": "TopdownL2", - "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck. Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations)", + "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck. Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations).", "ScaleUnit": "100%" }, { "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses", "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "(47.5 * tma_info_system_core_frequency - 4 * tma_info_system_core_frequency) * (MEM_LOAD_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM * (1 - OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM / (OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM + OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD))) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks", + "MetricExpr": "43.5 * tma_info_system_core_frequency * (MEM_LOAD_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM * (1 - OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM / (OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM + OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD))) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks", "MetricGroup": "BvMS;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group", "MetricName": "tma_data_sharing", - "MetricThreshold": "tma_data_sharing > 0.05 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", - "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses. Data shared by multiple Logical Processors (even just read shared) may cause increased access latency due to cache coherency. Excessive data sharing can drastically harm multithreaded performance. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_HIT. Related metrics: tma_bottleneck_memory_synchronization, tma_contested_accesses, tma_false_sharing, tma_machine_clears, tma_remote_cache", + "MetricThreshold": "tma_data_sharing > 0.05 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses. Data shared by multiple Logical Processors (even just read shared) may cause increased access latency due to cache coherency. Excessive data sharing can drastically harm multithreaded performance. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_HIT_PS. Related metrics: tma_bottleneck_memory_synchronization, tma_contested_accesses, tma_false_sharing, tma_machine_clears, tma_remote_cache", "ScaleUnit": "100%" }, { "BriefDescription": "This metric represents fraction of cycles where decoder-0 was the only active decoder", - "MetricExpr": "(cpu@INST_DECODED.DECODERS\\,cmask\\=0x1@ - cpu@INST_DECODED.DECODERS\\,cmask\\=0x2@) / tma_info_core_core_clks / 2", + "MetricExpr": "(cpu@INST_DECODED.DECODERS\\,cmask\\=1@ - cpu@INST_DECODED.DECODERS\\,cmask\\=2@) / tma_info_core_core_clks / 2", "MetricGroup": "DSBmiss;FetchBW;TopdownL4;tma_L4_group;tma_issueD0;tma_mite_group", "MetricName": "tma_decoder0_alone", - "MetricThreshold": "tma_decoder0_alone > 0.1 & tma_mite > 0.1 & tma_fetch_bandwidth > 0.2", + "MetricThreshold": "tma_decoder0_alone > 0.1 & (tma_mite > 0.1 & tma_fetch_bandwidth > 0.2)", "PublicDescription": "This metric represents fraction of cycles where decoder-0 was the only active decoder. Related metrics: tma_few_uops_instructions", "ScaleUnit": "100%" }, @@ -608,7 +608,7 @@ "MetricExpr": "ARITH.DIVIDER_ACTIVE / tma_info_thread_clks", "MetricGroup": "BvCB;TopdownL3;tma_L3_group;tma_core_bound_group", "MetricName": "tma_divider", - "MetricThreshold": "tma_divider > 0.2 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_divider > 0.2 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)", "PublicDescription": "This metric represents fraction of cycles where the Divider unit was active. Divide and square root instructions are performed by the Divider unit and can take considerably longer latency than integer or Floating Point addition; subtraction; or multiplication. Sample with: ARITH.DIVIDER_ACTIVE", "ScaleUnit": "100%" }, @@ -618,7 +618,7 @@ "MetricExpr": "CYCLE_ACTIVITY.STALLS_L3_MISS / tma_info_thread_clks + (CYCLE_ACTIVITY.STALLS_L1D_MISS - CYCLE_ACTIVITY.STALLS_L2_MISS) / tma_info_thread_clks - tma_l2_bound", "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_dram_bound", - "MetricThreshold": "tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", "PublicDescription": "This metric estimates how often the CPU was stalled on accesses to external memory (DRAM) by loads. Better caching can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L3_MISS", "ScaleUnit": "100%" }, @@ -628,7 +628,7 @@ "MetricGroup": "DSB;FetchBW;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group", "MetricName": "tma_dsb", "MetricThreshold": "tma_dsb > 0.15 & tma_fetch_bandwidth > 0.2", - "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to DSB (decoded uop cache) fetch pipeline. For example; inefficient utilization of the DSB cache structure or bank conflict when reading from it; are categorized here", + "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to DSB (decoded uop cache) fetch pipeline. For example; inefficient utilization of the DSB cache structure or bank conflict when reading from it; are categorized here.", "ScaleUnit": "100%" }, { @@ -636,34 +636,34 @@ "MetricExpr": "DSB2MITE_SWITCHES.PENALTY_CYCLES / tma_info_thread_clks", "MetricGroup": "DSBmiss;FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueFB", "MetricName": "tma_dsb_switches", - "MetricThreshold": "tma_dsb_switches > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", - "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines. The DSB (decoded i-cache) is a Uop Cache where the front-end directly delivers Uops (micro operations) avoiding heavy x86 decoding. The DSB pipeline has shorter latency and delivered higher bandwidth than the MITE (legacy instruction decode pipeline). Switching between the two pipelines can cause penalties hence this metric measures the exposed penalty. Sample with: FRONTEND_RETIRED.DSB_MISS. Related metrics: tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp", + "MetricThreshold": "tma_dsb_switches > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines. The DSB (decoded i-cache) is a Uop Cache where the front-end directly delivers Uops (micro operations) avoiding heavy x86 decoding. The DSB pipeline has shorter latency and delivered higher bandwidth than the MITE (legacy instruction decode pipeline). Switching between the two pipelines can cause penalties hence this metric measures the exposed penalty. Sample with: FRONTEND_RETIRED.DSB_MISS_PS. Related metrics: tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp", "ScaleUnit": "100%" }, { "BriefDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses", - "MetricExpr": "min(7 * cpu@DTLB_LOAD_MISSES.STLB_HIT\\,cmask\\=0x1@ + DTLB_LOAD_MISSES.WALK_ACTIVE, max(CYCLE_ACTIVITY.CYCLES_MEM_ANY - CYCLE_ACTIVITY.CYCLES_L1D_MISS, 0)) / tma_info_thread_clks", + "MetricExpr": "min(7 * cpu@DTLB_LOAD_MISSES.STLB_HIT\\,cmask\\=1@ + DTLB_LOAD_MISSES.WALK_ACTIVE, max(CYCLE_ACTIVITY.CYCLES_MEM_ANY - CYCLE_ACTIVITY.CYCLES_L1D_MISS, 0)) / tma_info_thread_clks", "MetricGroup": "BvMT;MemoryTLB;TopdownL4;tma_L4_group;tma_issueTLB;tma_l1_bound_group", "MetricName": "tma_dtlb_load", - "MetricThreshold": "tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", - "PublicDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses. TLBs (Translation Look-aside Buffers) are processor caches for recently used entries out of the Page Tables that are used to map virtual- to physical-addresses by the operating system. This metric approximates the potential delay of demand loads missing the first-level data TLB (assuming worst case scenario with back to back misses to different pages). This includes hitting in the second-level TLB (STLB) as well as performing a hardware page walk on an STLB miss. Sample with: MEM_INST_RETIRED.STLB_MISS_LOADS. Related metrics: tma_bottleneck_memory_data_tlbs, tma_dtlb_store", + "MetricThreshold": "tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses. TLBs (Translation Look-aside Buffers) are processor caches for recently used entries out of the Page Tables that are used to map virtual- to physical-addresses by the operating system. This metric approximates the potential delay of demand loads missing the first-level data TLB (assuming worst case scenario with back to back misses to different pages). This includes hitting in the second-level TLB (STLB) as well as performing a hardware page walk on an STLB miss. Sample with: MEM_INST_RETIRED.STLB_MISS_LOADS_PS. Related metrics: tma_bottleneck_memory_data_tlbs, tma_dtlb_store", "ScaleUnit": "100%" }, { "BriefDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses", - "MetricExpr": "(7 * cpu@DTLB_STORE_MISSES.STLB_HIT\\,cmask\\=0x1@ + DTLB_STORE_MISSES.WALK_ACTIVE) / tma_info_core_core_clks", + "MetricExpr": "(7 * cpu@DTLB_STORE_MISSES.STLB_HIT\\,cmask\\=1@ + DTLB_STORE_MISSES.WALK_ACTIVE) / tma_info_core_core_clks", "MetricGroup": "BvMT;MemoryTLB;TopdownL4;tma_L4_group;tma_issueTLB;tma_store_bound_group", "MetricName": "tma_dtlb_store", - "MetricThreshold": "tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", - "PublicDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses. As with ordinary data caching; focus on improving data locality and reducing working-set size to reduce DTLB overhead. Additionally; consider using profile-guided optimization (PGO) to collocate frequently-used data on the same page. Try using larger page sizes for large amounts of frequently-used data. Sample with: MEM_INST_RETIRED.STLB_MISS_STORES. Related metrics: tma_bottleneck_memory_data_tlbs, tma_dtlb_load", + "MetricThreshold": "tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses. As with ordinary data caching; focus on improving data locality and reducing working-set size to reduce DTLB overhead. Additionally; consider using profile-guided optimization (PGO) to collocate frequently-used data on the same page. Try using larger page sizes for large amounts of frequently-used data. Sample with: MEM_INST_RETIRED.STLB_MISS_STORES_PS. Related metrics: tma_bottleneck_memory_data_tlbs, tma_dtlb_load", "ScaleUnit": "100%" }, { "BriefDescription": "This metric roughly estimates how often CPU was handling synchronizations due to False Sharing", - "MetricExpr": "(120 * tma_info_system_core_frequency * cpu@OCR.DEMAND_RFO.L3_MISS\\,offcore_rsp\\=0x103b800002@ + 48 * tma_info_system_core_frequency * OCR.DEMAND_RFO.L3_HIT.SNOOP_HITM) / tma_info_thread_clks", + "MetricExpr": "(120 * tma_info_system_core_frequency * OCR.DEMAND_RFO.L3_MISS@offcore_rsp\\=0x103b800002@ + 48 * tma_info_system_core_frequency * OCR.DEMAND_RFO.L3_HIT.SNOOP_HITM) / tma_info_thread_clks", "MetricGroup": "BvMS;DataSharing;LockCont;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_store_bound_group", "MetricName": "tma_false_sharing", - "MetricThreshold": "tma_false_sharing > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_false_sharing > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", "PublicDescription": "This metric roughly estimates how often CPU was handling synchronizations due to False Sharing. False Sharing is a multithreading hiccup; where multiple Logical Processors contend on different data-elements mapped into the same cache line. Sample with: OCR.DEMAND_RFO.L3_HIT.SNOOP_HITM. Related metrics: tma_bottleneck_memory_synchronization, tma_contested_accesses, tma_data_sharing, tma_machine_clears, tma_remote_cache", "ScaleUnit": "100%" }, @@ -683,7 +683,7 @@ "MetricName": "tma_fetch_bandwidth", "MetricThreshold": "tma_fetch_bandwidth > 0.2", "MetricgroupNoGroup": "TopdownL2", - "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues. For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Sample with: FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1, FRONTEND_RETIRED.LATENCY_GE_1, FRONTEND_RETIRED.LATENCY_GE_2. Related metrics: tma_dsb_switches, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp", + "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues. For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Sample with: FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1;FRONTEND_RETIRED.LATENCY_GE_1;FRONTEND_RETIRED.LATENCY_GE_2. Related metrics: tma_dsb_switches, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp", "ScaleUnit": "100%" }, { @@ -693,7 +693,7 @@ "MetricName": "tma_fetch_latency", "MetricThreshold": "tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", "MetricgroupNoGroup": "TopdownL2", - "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues. For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: FRONTEND_RETIRED.LATENCY_GE_16, FRONTEND_RETIRED.LATENCY_GE_8", + "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues. For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: FRONTEND_RETIRED.LATENCY_GE_16_PS;FRONTEND_RETIRED.LATENCY_GE_8_PS", "ScaleUnit": "100%" }, { @@ -711,7 +711,7 @@ "MetricGroup": "HPC;TopdownL3;tma_L3_group;tma_light_operations_group", "MetricName": "tma_fp_arith", "MetricThreshold": "tma_fp_arith > 0.2 & tma_light_operations > 0.6", - "PublicDescription": "This metric represents overall arithmetic floating-point (FP) operations fraction the CPU has executed (retired). Note this metric's value may exceed its parent due to use of \"Uops\" CountDomain and FMA double-counting", + "PublicDescription": "This metric represents overall arithmetic floating-point (FP) operations fraction the CPU has executed (retired). Note this metric's value may exceed its parent due to use of \"Uops\" CountDomain and FMA double-counting.", "ScaleUnit": "100%" }, { @@ -720,15 +720,15 @@ "MetricGroup": "HPC;TopdownL5;tma_L5_group;tma_assists_group", "MetricName": "tma_fp_assists", "MetricThreshold": "tma_fp_assists > 0.1", - "PublicDescription": "This metric roughly estimates fraction of slots the CPU retired uops as a result of handing Floating Point (FP) Assists. FP Assist may apply when working with very small floating point values (so-called Denormals)", + "PublicDescription": "This metric roughly estimates fraction of slots the CPU retired uops as a result of handing Floating Point (FP) Assists. FP Assist may apply when working with very small floating point values (so-called Denormals).", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of cycles where the Floating-Point Divider unit was active", + "BriefDescription": "This metric represents fraction of cycles where the Floating-Point Divider unit was active.", "MetricExpr": "ARITH.FP_DIVIDER_ACTIVE / tma_info_thread_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_divider_group", "MetricName": "tma_fp_divider", - "MetricThreshold": "tma_fp_divider > 0.2 & tma_divider > 0.2 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_fp_divider > 0.2 & (tma_divider > 0.2 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", "ScaleUnit": "100%" }, { @@ -736,7 +736,7 @@ "MetricExpr": "FP_ARITH_INST_RETIRED.SCALAR / (tma_retiring * tma_info_thread_slots)", "MetricGroup": "Compute;Flops;TopdownL4;tma_L4_group;tma_fp_arith_group;tma_issue2P", "MetricName": "tma_fp_scalar", - "MetricThreshold": "tma_fp_scalar > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6", + "MetricThreshold": "tma_fp_scalar > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6)", "PublicDescription": "This metric approximates arithmetic floating-point (FP) scalar uops fraction the CPU has retired. May overcount due to FMA double counting. Related metrics: tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%" }, @@ -745,7 +745,7 @@ "MetricExpr": "FP_ARITH_INST_RETIRED.VECTOR / (tma_retiring * tma_info_thread_slots)", "MetricGroup": "Compute;Flops;TopdownL4;tma_L4_group;tma_fp_arith_group;tma_issue2P", "MetricName": "tma_fp_vector", - "MetricThreshold": "tma_fp_vector > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6", + "MetricThreshold": "tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6)", "PublicDescription": "This metric approximates arithmetic floating-point (FP) vector uops fraction the CPU has retired aggregated across all vector widths. May overcount due to FMA double counting. Related metrics: tma_fp_scalar, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%" }, @@ -754,7 +754,7 @@ "MetricExpr": "(FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE) / (tma_retiring * tma_info_thread_slots)", "MetricGroup": "Compute;Flops;TopdownL5;tma_L5_group;tma_fp_vector_group;tma_issue2P", "MetricName": "tma_fp_vector_128b", - "MetricThreshold": "tma_fp_vector_128b > 0.1 & tma_fp_vector > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6", + "MetricThreshold": "tma_fp_vector_128b > 0.1 & (tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6))", "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 128-bit wide vectors. May overcount due to FMA double counting prior to LNL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%" }, @@ -763,7 +763,7 @@ "MetricExpr": "(FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE) / (tma_retiring * tma_info_thread_slots)", "MetricGroup": "Compute;Flops;TopdownL5;tma_L5_group;tma_fp_vector_group;tma_issue2P", "MetricName": "tma_fp_vector_256b", - "MetricThreshold": "tma_fp_vector_256b > 0.1 & tma_fp_vector > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6", + "MetricThreshold": "tma_fp_vector_256b > 0.1 & (tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6))", "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 256-bit wide vectors. May overcount due to FMA double counting prior to LNL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%" }, @@ -772,7 +772,7 @@ "MetricExpr": "(FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE) / (tma_retiring * tma_info_thread_slots)", "MetricGroup": "Compute;Flops;TopdownL5;tma_L5_group;tma_fp_vector_group;tma_issue2P", "MetricName": "tma_fp_vector_512b", - "MetricThreshold": "tma_fp_vector_512b > 0.1 & tma_fp_vector > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6", + "MetricThreshold": "tma_fp_vector_512b > 0.1 & (tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6))", "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 512-bit wide vectors. May overcount due to FMA double counting. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%" }, @@ -784,17 +784,17 @@ "MetricName": "tma_frontend_bound", "MetricThreshold": "tma_frontend_bound > 0.15", "MetricgroupNoGroup": "TopdownL1;Default", - "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound. Sample with: FRONTEND_RETIRED.LATENCY_GE_4", + "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound. Sample with: FRONTEND_RETIRED.LATENCY_GE_4_PS", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations , instructions that require two or more uops or micro-coded sequences", - "MetricExpr": "tma_microcode_sequencer + tma_retiring * (UOPS_DECODED.DEC0 - cpu@UOPS_DECODED.DEC0\\,cmask\\=0x1@) / IDQ.MITE_UOPS", + "BriefDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences", + "MetricExpr": "tma_microcode_sequencer + tma_retiring * (UOPS_DECODED.DEC0 - cpu@UOPS_DECODED.DEC0\\,cmask\\=1@) / IDQ.MITE_UOPS", "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_heavy_operations", "MetricThreshold": "tma_heavy_operations > 0.1", "MetricgroupNoGroup": "TopdownL2", - "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations , instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences.([ICL+] Note this may overcount due to approximation using indirect events; [ADL+])", + "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences.([ICL+] Note this may overcount due to approximation using indirect events; [ADL+])", "ScaleUnit": "100%" }, { @@ -802,8 +802,8 @@ "MetricExpr": "ICACHE_DATA.STALLS / tma_info_thread_clks", "MetricGroup": "BigFootprint;BvBC;FetchLat;IcMiss;TopdownL3;tma_L3_group;tma_fetch_latency_group", "MetricName": "tma_icache_misses", - "MetricThreshold": "tma_icache_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", - "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to instruction cache misses. Sample with: FRONTEND_RETIRED.L2_MISS, FRONTEND_RETIRED.L1I_MISS", + "MetricThreshold": "tma_icache_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to instruction cache misses. Sample with: FRONTEND_RETIRED.L2_MISS_PS;FRONTEND_RETIRED.L1I_MISS_PS", "ScaleUnit": "100%" }, { @@ -815,28 +815,28 @@ "PublicDescription": "Branch Misprediction Cost: Cycles representing fraction of TMA slots wasted per non-speculative branch misprediction (retired JEClear). Related metrics: tma_bottleneck_mispredictions, tma_branch_mispredicts, tma_mispredicts_resteers" }, { - "BriefDescription": "Instructions per retired Mispredicts for conditional non-taken branches (lower number means higher occurrence rate)", + "BriefDescription": "Instructions per retired Mispredicts for conditional non-taken branches (lower number means higher occurrence rate).", "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.COND_NTAKEN", "MetricGroup": "Bad;BrMispredicts", "MetricName": "tma_info_bad_spec_ipmisp_cond_ntaken", "MetricThreshold": "tma_info_bad_spec_ipmisp_cond_ntaken < 200" }, { - "BriefDescription": "Instructions per retired Mispredicts for conditional taken branches (lower number means higher occurrence rate)", + "BriefDescription": "Instructions per retired Mispredicts for conditional taken branches (lower number means higher occurrence rate).", "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.COND_TAKEN", "MetricGroup": "Bad;BrMispredicts", "MetricName": "tma_info_bad_spec_ipmisp_cond_taken", "MetricThreshold": "tma_info_bad_spec_ipmisp_cond_taken < 200" }, { - "BriefDescription": "Instructions per retired Mispredicts for indirect CALL or JMP branches (lower number means higher occurrence rate)", + "BriefDescription": "Instructions per retired Mispredicts for indirect CALL or JMP branches (lower number means higher occurrence rate).", "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.INDIRECT", "MetricGroup": "Bad;BrMispredicts", "MetricName": "tma_info_bad_spec_ipmisp_indirect", - "MetricThreshold": "tma_info_bad_spec_ipmisp_indirect < 1000" + "MetricThreshold": "tma_info_bad_spec_ipmisp_indirect < 1e3" }, { - "BriefDescription": "Instructions per retired Mispredicts for return branches (lower number means higher occurrence rate)", + "BriefDescription": "Instructions per retired Mispredicts for return branches (lower number means higher occurrence rate).", "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.RET", "MetricGroup": "Bad;BrMispredicts", "MetricName": "tma_info_bad_spec_ipmisp_ret", @@ -865,7 +865,7 @@ }, { "BriefDescription": "Total pipeline cost of DSB (uop cache) hits - subset of the Instruction_Fetch_BW Bottleneck", - "MetricExpr": "100 * (tma_frontend_bound * (tma_fetch_bandwidth / (tma_fetch_latency + tma_fetch_bandwidth)) * (tma_dsb / (tma_mite + tma_dsb + tma_ms)))", + "MetricExpr": "100 * (tma_frontend_bound * (tma_fetch_bandwidth / (tma_fetch_bandwidth + tma_fetch_latency)) * (tma_dsb / (tma_dsb + tma_mite + tma_ms)))", "MetricGroup": "DSB;Fed;FetchBW;tma_issueFB", "MetricName": "tma_info_botlnk_l2_dsb_bandwidth", "MetricThreshold": "tma_info_botlnk_l2_dsb_bandwidth > 10", @@ -874,7 +874,7 @@ { "BriefDescription": "Total pipeline cost of DSB (uop cache) misses - subset of the Instruction_Fetch_BW Bottleneck", "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "100 * (tma_fetch_latency * tma_dsb_switches / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches) + tma_fetch_bandwidth * tma_mite / (tma_mite + tma_dsb + tma_ms))", + "MetricExpr": "100 * (tma_fetch_latency * tma_dsb_switches / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) + tma_fetch_bandwidth * tma_mite / (tma_dsb + tma_mite + tma_ms))", "MetricGroup": "DSBmiss;Fed;tma_issueFB", "MetricName": "tma_info_botlnk_l2_dsb_misses", "MetricThreshold": "tma_info_botlnk_l2_dsb_misses > 10", @@ -883,10 +883,11 @@ { "BriefDescription": "Total pipeline cost of Instruction Cache misses - subset of the Big_Code Bottleneck", "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "100 * (tma_fetch_latency * tma_icache_misses / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches))", + "MetricExpr": "100 * (tma_fetch_latency * tma_icache_misses / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches))", "MetricGroup": "Fed;FetchLat;IcMiss;tma_issueFL", "MetricName": "tma_info_botlnk_l2_ic_misses", - "MetricThreshold": "tma_info_botlnk_l2_ic_misses > 5" + "MetricThreshold": "tma_info_botlnk_l2_ic_misses > 5", + "PublicDescription": "Total pipeline cost of Instruction Cache misses - subset of the Big_Code Bottleneck. Related metrics: " }, { "BriefDescription": "Fraction of branches that are CALL or RET", @@ -947,11 +948,11 @@ "MetricExpr": "(FP_ARITH_INST_RETIRED.SCALAR + FP_ARITH_INST_RETIRED.VECTOR) / (2 * tma_info_core_core_clks)", "MetricGroup": "Cor;Flops;HPC", "MetricName": "tma_info_core_fp_arith_utilization", - "PublicDescription": "Actual per-core usage of the Floating Point non-X87 execution units (regardless of precision or vector-width). Values > 1 are possible due to ([BDW+] Fused-Multiply Add (FMA) counting - common; [ADL+] use all of ADD/MUL/FMA in Scalar or 128/256-bit vectors - less common)" + "PublicDescription": "Actual per-core usage of the Floating Point non-X87 execution units (regardless of precision or vector-width). Values > 1 are possible due to ([BDW+] Fused-Multiply Add (FMA) counting - common; [ADL+] use all of ADD/MUL/FMA in Scalar or 128/256-bit vectors - less common)." }, { "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is execution) per thread (logical-processor)", - "MetricExpr": "UOPS_EXECUTED.THREAD / cpu@UOPS_EXECUTED.THREAD\\,cmask\\=0x1@", + "MetricExpr": "UOPS_EXECUTED.THREAD / cpu@UOPS_EXECUTED.THREAD\\,cmask\\=1@", "MetricGroup": "Backend;Cor;Pipeline;PortsUtil", "MetricName": "tma_info_core_ilp" }, @@ -964,20 +965,20 @@ "PublicDescription": "Fraction of Uops delivered by the DSB (aka Decoded ICache; or Uop Cache). Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_inst_mix_iptb, tma_lcp" }, { - "BriefDescription": "Average number of cycles of a switch from the DSB fetch-unit to MITE fetch unit - see DSB_Switches tree node for details", - "MetricExpr": "DSB2MITE_SWITCHES.PENALTY_CYCLES / cpu@DSB2MITE_SWITCHES.PENALTY_CYCLES\\,cmask\\=0x1\\,edge\\=0x1@", + "BriefDescription": "Average number of cycles of a switch from the DSB fetch-unit to MITE fetch unit - see DSB_Switches tree node for details.", + "MetricExpr": "DSB2MITE_SWITCHES.PENALTY_CYCLES / cpu@DSB2MITE_SWITCHES.PENALTY_CYCLES\\,cmask\\=1\\,edge@", "MetricGroup": "DSBmiss", "MetricName": "tma_info_frontend_dsb_switch_cost" }, { "BriefDescription": "Average number of Uops issued by front-end when it issued something", - "MetricExpr": "UOPS_ISSUED.ANY / cpu@UOPS_ISSUED.ANY\\,cmask\\=0x1@", + "MetricExpr": "UOPS_ISSUED.ANY / cpu@UOPS_ISSUED.ANY\\,cmask\\=1@", "MetricGroup": "Fed;FetchBW", "MetricName": "tma_info_frontend_fetch_upc" }, { "BriefDescription": "Average Latency for L1 instruction cache misses", - "MetricExpr": "ICACHE_16B.IFDATA_STALL / cpu@ICACHE_16B.IFDATA_STALL\\,cmask\\=0x1\\,edge\\=0x1@", + "MetricExpr": "ICACHE_16B.IFDATA_STALL / cpu@ICACHE_16B.IFDATA_STALL\\,cmask\\=1\\,edge@", "MetricGroup": "Fed;FetchLat;IcMiss", "MetricName": "tma_info_frontend_icache_miss_latency" }, @@ -1013,7 +1014,7 @@ "MetricName": "tma_info_frontend_tbpc" }, { - "BriefDescription": "Branch instructions per taken branch", + "BriefDescription": "Branch instructions per taken branch.", "MetricExpr": "BR_INST_RETIRED.ALL_BRANCHES / BR_INST_RETIRED.NEAR_TAKEN", "MetricGroup": "Branches;Fed;PGO", "MetricName": "tma_info_inst_mix_bptkbranch" @@ -1031,7 +1032,7 @@ "MetricGroup": "Flops;InsType", "MetricName": "tma_info_inst_mix_iparith", "MetricThreshold": "tma_info_inst_mix_iparith < 10", - "PublicDescription": "Instructions per FP Arithmetic instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting. Approximated prior to BDW" + "PublicDescription": "Instructions per FP Arithmetic instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting. Approximated prior to BDW." }, { "BriefDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number means higher occurrence rate)", @@ -1039,7 +1040,7 @@ "MetricGroup": "Flops;FpVector;InsType", "MetricName": "tma_info_inst_mix_iparith_avx128", "MetricThreshold": "tma_info_inst_mix_iparith_avx128 < 10", - "PublicDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting" + "PublicDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting." }, { "BriefDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means higher occurrence rate)", @@ -1047,7 +1048,7 @@ "MetricGroup": "Flops;FpVector;InsType", "MetricName": "tma_info_inst_mix_iparith_avx256", "MetricThreshold": "tma_info_inst_mix_iparith_avx256 < 10", - "PublicDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting" + "PublicDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting." }, { "BriefDescription": "Instructions per FP Arithmetic AVX 512-bit instruction (lower number means higher occurrence rate)", @@ -1055,7 +1056,7 @@ "MetricGroup": "Flops;FpVector;InsType", "MetricName": "tma_info_inst_mix_iparith_avx512", "MetricThreshold": "tma_info_inst_mix_iparith_avx512 < 10", - "PublicDescription": "Instructions per FP Arithmetic AVX 512-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting" + "PublicDescription": "Instructions per FP Arithmetic AVX 512-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting." }, { "BriefDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction (lower number means higher occurrence rate)", @@ -1063,7 +1064,7 @@ "MetricGroup": "Flops;FpScalar;InsType", "MetricName": "tma_info_inst_mix_iparith_scalar_dp", "MetricThreshold": "tma_info_inst_mix_iparith_scalar_dp < 10", - "PublicDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting" + "PublicDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting." }, { "BriefDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction (lower number means higher occurrence rate)", @@ -1071,7 +1072,7 @@ "MetricGroup": "Flops;FpScalar;InsType", "MetricName": "tma_info_inst_mix_iparith_scalar_sp", "MetricThreshold": "tma_info_inst_mix_iparith_scalar_sp < 10", - "PublicDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting" + "PublicDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting." }, { "BriefDescription": "Instructions per Branch (lower number means higher occurrence rate)", @@ -1126,7 +1127,7 @@ "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_TAKEN", "MetricGroup": "Branches;Fed;FetchBW;Frontend;PGO;tma_issueFB", "MetricName": "tma_info_inst_mix_iptb", - "MetricThreshold": "tma_info_inst_mix_iptb < 5 * 2 + 1", + "MetricThreshold": "tma_info_inst_mix_iptb < 11", "PublicDescription": "Instructions per taken branch. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_lcp" }, { @@ -1257,7 +1258,7 @@ }, { "BriefDescription": "Average Parallel L2 cache miss demand Loads", - "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD / cpu@OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD\\,cmask\\=0x1@", + "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD / cpu@OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD\\,cmask\\=1@", "MetricGroup": "Memory_BW;Offcore", "MetricName": "tma_info_memory_latency_load_l2_mlp" }, @@ -1319,8 +1320,8 @@ "MetricName": "tma_info_memory_tlb_store_stlb_mpki" }, { - "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is execution) per core", - "MetricExpr": "UOPS_EXECUTED.THREAD / (UOPS_EXECUTED.CORE_CYCLES_GE_1 / 2 if #SMT_on else cpu@UOPS_EXECUTED.THREAD\\,cmask\\=0x1@)", + "BriefDescription": "", + "MetricExpr": "UOPS_EXECUTED.THREAD / (UOPS_EXECUTED.CORE_CYCLES_GE_1 / 2 if #SMT_on else cpu@UOPS_EXECUTED.THREAD\\,cmask\\=1@)", "MetricGroup": "Cor;Pipeline;PortsUtil;SMT", "MetricName": "tma_info_pipeline_execute" }, @@ -1341,12 +1342,12 @@ "MetricExpr": "INST_RETIRED.ANY / ASSISTS.ANY", "MetricGroup": "MicroSeq;Pipeline;Ret;Retire", "MetricName": "tma_info_pipeline_ipassist", - "MetricThreshold": "tma_info_pipeline_ipassist < 100000", + "MetricThreshold": "tma_info_pipeline_ipassist < 100e3", "PublicDescription": "Instructions per a microcode Assist invocation. See Assists tree node for details (lower number means higher occurrence rate)" }, { - "BriefDescription": "Average number of Uops retired in cycles where at least one uop has retired", - "MetricExpr": "tma_retiring * tma_info_thread_slots / cpu@UOPS_RETIRED.SLOTS\\,cmask\\=0x1@", + "BriefDescription": "Average number of Uops retired in cycles where at least one uop has retired.", + "MetricExpr": "tma_retiring * tma_info_thread_slots / cpu@UOPS_RETIRED.SLOTS\\,cmask\\=1@", "MetricGroup": "Pipeline;Ret", "MetricName": "tma_info_pipeline_retire" }, @@ -1401,14 +1402,13 @@ "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.FAR_BRANCH:u", "MetricGroup": "Branches;OS", "MetricName": "tma_info_system_ipfarbranch", - "MetricThreshold": "tma_info_system_ipfarbranch < 1000000" + "MetricThreshold": "tma_info_system_ipfarbranch < 1e6" }, { "BriefDescription": "Cycles Per Instruction for the Operating System (OS) Kernel mode", "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P:k / INST_RETIRED.ANY_P:k", "MetricGroup": "OS", - "MetricName": "tma_info_system_kernel_cpi", - "ScaleUnit": "1per_instr" + "MetricName": "tma_info_system_kernel_cpi" }, { "BriefDescription": "Fraction of cycles spent in the Operating System (OS) Kernel mode", @@ -1429,11 +1429,11 @@ "MetricExpr": "UNC_CHA_RxC_IRQ1_REJECT.PA_MATCH / UNC_CHA_CLOCKTICKS", "MetricGroup": "LockCont;MemOffcore;Server;SoC", "MetricName": "tma_info_system_mem_irq_duplicate_address", - "MetricThreshold": "(tma_info_system_mem_irq_duplicate_address > 0.1)" + "MetricThreshold": "tma_info_system_mem_irq_duplicate_address > 0.1" }, { "BriefDescription": "Average number of parallel data read requests to external memory", - "MetricExpr": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD / cha@UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD\\,thresh\\=0x1@", + "MetricExpr": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD / UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD@thresh\\=1@", "MetricGroup": "Mem;MemoryBW;SoC", "MetricName": "tma_info_system_mem_parallel_reads", "PublicDescription": "Average number of parallel data read requests to external memory. Accounts for demand loads and L1/L2 prefetches" @@ -1463,7 +1463,7 @@ "MetricExpr": "CORE_POWER.LVL0_TURBO_LICENSE / tma_info_core_core_clks", "MetricGroup": "Power", "MetricName": "tma_info_system_power_license0_utilization", - "PublicDescription": "Fraction of Core cycles where the core was running with power-delivery for baseline license level 0. This includes non-AVX codes, SSE, AVX 128-bit, and low-current AVX 256-bit codes" + "PublicDescription": "Fraction of Core cycles where the core was running with power-delivery for baseline license level 0. This includes non-AVX codes, SSE, AVX 128-bit, and low-current AVX 256-bit codes." }, { "BriefDescription": "Fraction of Core cycles where the core was running with power-delivery for license level 1", @@ -1471,7 +1471,7 @@ "MetricGroup": "Power", "MetricName": "tma_info_system_power_license1_utilization", "MetricThreshold": "tma_info_system_power_license1_utilization > 0.5", - "PublicDescription": "Fraction of Core cycles where the core was running with power-delivery for license level 1. This includes high current AVX 256-bit instructions as well as low current AVX 512-bit instructions" + "PublicDescription": "Fraction of Core cycles where the core was running with power-delivery for license level 1. This includes high current AVX 256-bit instructions as well as low current AVX 512-bit instructions." }, { "BriefDescription": "Fraction of Core cycles where the core was running with power-delivery for license level 2 (introduced in SKX)", @@ -1479,7 +1479,7 @@ "MetricGroup": "Power", "MetricName": "tma_info_system_power_license2_utilization", "MetricThreshold": "tma_info_system_power_license2_utilization > 0.5", - "PublicDescription": "Fraction of Core cycles where the core was running with power-delivery for license level 2 (introduced in SKX). This includes high current AVX 512-bit instructions" + "PublicDescription": "Fraction of Core cycles where the core was running with power-delivery for license level 2 (introduced in SKX). This includes high current AVX 512-bit instructions." }, { "BriefDescription": "Fraction of cycles where both hardware Logical Processors were active", @@ -1513,7 +1513,7 @@ "MetricName": "tma_info_system_uncore_frequency" }, { - "BriefDescription": "Per-Logical Processor actual clocks when the Logical Processor is active", + "BriefDescription": "Per-Logical Processor actual clocks when the Logical Processor is active.", "MetricExpr": "CPU_CLK_UNHALTED.THREAD", "MetricGroup": "Pipeline", "MetricName": "tma_info_thread_clks" @@ -1522,15 +1522,14 @@ "BriefDescription": "Cycles Per Instruction (per Logical Processor)", "MetricExpr": "1 / tma_info_thread_ipc", "MetricGroup": "Mem;Pipeline", - "MetricName": "tma_info_thread_cpi", - "ScaleUnit": "1per_instr" + "MetricName": "tma_info_thread_cpi" }, { "BriefDescription": "The ratio of Executed- by Issued-Uops", "MetricExpr": "UOPS_EXECUTED.THREAD / UOPS_ISSUED.ANY", "MetricGroup": "Cor;Pipeline", "MetricName": "tma_info_thread_execute_per_issue", - "PublicDescription": "The ratio of Executed- by Issued-Uops. Ratio > 1 suggests high rate of uop micro-fusions. Ratio < 1 suggest high rate of \"execute\" at rename stage" + "PublicDescription": "The ratio of Executed- by Issued-Uops. Ratio > 1 suggests high rate of uop micro-fusions. Ratio < 1 suggest high rate of \"execute\" at rename stage." }, { "BriefDescription": "Instructions Per Cycle (per Logical Processor)", @@ -1540,13 +1539,13 @@ }, { "BriefDescription": "Total issue-pipeline slots (per-Physical Core till ICL; per-Logical Processor ICL onward)", - "MetricExpr": "slots", + "MetricExpr": "TOPDOWN.SLOTS", "MetricGroup": "TmaL1;tma_L1_group", "MetricName": "tma_info_thread_slots" }, { "BriefDescription": "Fraction of Physical Core issue-slots utilized by this Logical Processor", - "MetricExpr": "(tma_info_thread_slots / (slots / 2) if #SMT_on else 1)", + "MetricExpr": "(tma_info_thread_slots / (TOPDOWN.SLOTS / 2) if #SMT_on else 1)", "MetricGroup": "SMT;TmaL1;tma_L1_group", "MetricName": "tma_info_thread_slots_utilization" }, @@ -1562,14 +1561,14 @@ "MetricExpr": "tma_retiring * tma_info_thread_slots / BR_INST_RETIRED.NEAR_TAKEN", "MetricGroup": "Branches;Fed;FetchBW", "MetricName": "tma_info_thread_uptb", - "MetricThreshold": "tma_info_thread_uptb < 5 * 1.5" + "MetricThreshold": "tma_info_thread_uptb < 7.5" }, { - "BriefDescription": "This metric represents fraction of cycles where the Integer Divider unit was active", + "BriefDescription": "This metric represents fraction of cycles where the Integer Divider unit was active.", "MetricExpr": "tma_divider - tma_fp_divider", "MetricGroup": "TopdownL4;tma_L4_group;tma_divider_group", "MetricName": "tma_int_divider", - "MetricThreshold": "tma_int_divider > 0.2 & tma_divider > 0.2 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_int_divider > 0.2 & (tma_divider > 0.2 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", "ScaleUnit": "100%" }, { @@ -1577,8 +1576,8 @@ "MetricExpr": "ICACHE_TAG.STALLS / tma_info_thread_clks", "MetricGroup": "BigFootprint;BvBC;FetchLat;MemoryTLB;TopdownL3;tma_L3_group;tma_fetch_latency_group", "MetricName": "tma_itlb_misses", - "MetricThreshold": "tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", - "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Instruction TLB (ITLB) misses. Sample with: FRONTEND_RETIRED.STLB_MISS, FRONTEND_RETIRED.ITLB_MISS", + "MetricThreshold": "tma_itlb_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Instruction TLB (ITLB) misses. Sample with: FRONTEND_RETIRED.STLB_MISS_PS;FRONTEND_RETIRED.ITLB_MISS_PS", "ScaleUnit": "100%" }, { @@ -1586,7 +1585,7 @@ "MetricExpr": "max((CYCLE_ACTIVITY.STALLS_MEM_ANY - CYCLE_ACTIVITY.STALLS_L1D_MISS) / tma_info_thread_clks, 0)", "MetricGroup": "CacheHits;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_issueL1;tma_issueMC;tma_memory_bound_group", "MetricName": "tma_l1_bound", - "MetricThreshold": "tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", "PublicDescription": "This metric estimates how often the CPU was stalled without loads missing the L1 Data (L1D) cache. The L1D cache typically has the shortest latency. However; in certain cases like loads blocked on older stores; a load might suffer due to high latency even though it is being satisfied by the L1D. Another example is loads who miss in the TLB. These cases are characterized by execution unit stalls; while some non-completed demand load lives in the machine without having that demand load missing the L1 cache. Sample with: MEM_LOAD_RETIRED.L1_HIT. Related metrics: tma_clears_resteers, tma_machine_clears, tma_microcode_sequencer, tma_ms_switches, tma_ports_utilized_1", "ScaleUnit": "100%" }, @@ -1595,7 +1594,7 @@ "MetricExpr": "min(2 * (MEM_INST_RETIRED.ALL_LOADS - MEM_LOAD_RETIRED.FB_HIT - MEM_LOAD_RETIRED.L1_MISS) * 20 / 100, max(CYCLE_ACTIVITY.CYCLES_MEM_ANY - CYCLE_ACTIVITY.CYCLES_L1D_MISS, 0)) / tma_info_thread_clks", "MetricGroup": "BvML;MemoryLat;TopdownL4;tma_L4_group;tma_l1_bound_group", "MetricName": "tma_l1_latency_dependency", - "MetricThreshold": "tma_l1_latency_dependency > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_l1_latency_dependency > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", "PublicDescription": "This metric([SKL+] roughly; [LNL]) estimates fraction of cycles with demand load accesses that hit the L1D cache. The short latency of the L1D cache may be exposed in pointer-chasing memory access patterns as an example. Sample with: MEM_LOAD_RETIRED.L1_HIT", "ScaleUnit": "100%" }, @@ -1605,7 +1604,7 @@ "MetricExpr": "MEM_LOAD_RETIRED.L2_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) / (MEM_LOAD_RETIRED.L2_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) + L1D_PEND_MISS.FB_FULL_PERIODS) * ((CYCLE_ACTIVITY.STALLS_L1D_MISS - CYCLE_ACTIVITY.STALLS_L2_MISS) / tma_info_thread_clks)", "MetricGroup": "BvML;CacheHits;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_l2_bound", - "MetricThreshold": "tma_l2_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_l2_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", "PublicDescription": "This metric estimates how often the CPU was stalled due to L2 cache accesses by loads. Avoiding cache misses (i.e. L1 misses/L2 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L2_HIT", "ScaleUnit": "100%" }, @@ -1614,7 +1613,7 @@ "MetricExpr": "4 * tma_info_system_core_frequency * MEM_LOAD_RETIRED.L2_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks", "MetricGroup": "MemoryLat;TopdownL4;tma_L4_group;tma_l2_bound_group", "MetricName": "tma_l2_hit_latency", - "MetricThreshold": "tma_l2_hit_latency > 0.05 & tma_l2_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_l2_hit_latency > 0.05 & (tma_l2_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", "PublicDescription": "This metric represents fraction of cycles with demand load accesses that hit the L2 cache under unloaded scenarios (possibly L2 latency limited). Avoiding L1 cache misses (i.e. L1 misses/L2 hits) will improve the latency. Sample with: MEM_LOAD_RETIRED.L2_HIT", "ScaleUnit": "100%" }, @@ -1624,17 +1623,17 @@ "MetricExpr": "(CYCLE_ACTIVITY.STALLS_L2_MISS - CYCLE_ACTIVITY.STALLS_L3_MISS) / tma_info_thread_clks", "MetricGroup": "CacheHits;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_l3_bound", - "MetricThreshold": "tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", - "PublicDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core. Avoiding cache misses (i.e. L2 misses/L3 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L3_HIT", + "MetricThreshold": "tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", + "PublicDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core. Avoiding cache misses (i.e. L2 misses/L3 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L3_HIT_PS", "ScaleUnit": "100%" }, { "BriefDescription": "This metric estimates fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited)", - "MetricExpr": "(23 * tma_info_system_core_frequency - 4 * tma_info_system_core_frequency) * (MEM_LOAD_RETIRED.L3_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2)) / tma_info_thread_clks", + "MetricExpr": "19 * tma_info_system_core_frequency * (MEM_LOAD_RETIRED.L3_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2)) / tma_info_thread_clks", "MetricGroup": "BvML;MemoryLat;TopdownL4;tma_L4_group;tma_issueLat;tma_l3_bound_group", "MetricName": "tma_l3_hit_latency", - "MetricThreshold": "tma_l3_hit_latency > 0.1 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", - "PublicDescription": "This metric estimates fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited). Avoiding private cache misses (i.e. L2 misses/L3 hits) will improve the latency; reduce contention with sibling physical cores and increase performance. Note the value of this node may overlap with its siblings. Sample with: MEM_LOAD_RETIRED.L3_HIT. Related metrics: tma_bottleneck_cache_memory_latency, tma_branch_resteers, tma_mem_latency, tma_store_latency", + "MetricThreshold": "tma_l3_hit_latency > 0.1 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric estimates fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited). Avoiding private cache misses (i.e. L2 misses/L3 hits) will improve the latency; reduce contention with sibling physical cores and increase performance. Note the value of this node may overlap with its siblings. Sample with: MEM_LOAD_RETIRED.L3_HIT_PS. Related metrics: tma_bottleneck_cache_memory_latency, tma_mem_latency", "ScaleUnit": "100%" }, { @@ -1642,18 +1641,18 @@ "MetricExpr": "DECODE.LCP / tma_info_thread_clks", "MetricGroup": "FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueFB", "MetricName": "tma_lcp", - "MetricThreshold": "tma_lcp > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", - "PublicDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs). Using proper compiler flags or Intel Compiler by default will certainly avoid this. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb", + "MetricThreshold": "tma_lcp > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", + "PublicDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs). Using proper compiler flags or Intel Compiler by default will certainly avoid this. #Link: Optimization Guide about LCP BKMs. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations , instructions that require no more than one uop (micro-operation)", + "BriefDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation)", "MetricExpr": "max(0, tma_retiring - tma_heavy_operations)", "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_light_operations", "MetricThreshold": "tma_light_operations > 0.6", "MetricgroupNoGroup": "TopdownL2", - "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations , instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized code running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. ([ICL+] Note this may undercount due to approximation using indirect events; [ADL+] .). Sample with: INST_RETIRED.PREC_DIST", + "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized code running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. ([ICL+] Note this may undercount due to approximation using indirect events; [ADL+] .). Sample with: INST_RETIRED.PREC_DIST", "ScaleUnit": "100%" }, { @@ -1670,7 +1669,7 @@ "MetricExpr": "tma_dtlb_load - tma_load_stlb_miss", "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_load_group", "MetricName": "tma_load_stlb_hit", - "MetricThreshold": "tma_load_stlb_hit > 0.05 & tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_load_stlb_hit > 0.05 & (tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))", "ScaleUnit": "100%" }, { @@ -1678,39 +1677,39 @@ "MetricExpr": "DTLB_LOAD_MISSES.WALK_ACTIVE / tma_info_thread_clks", "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_load_group", "MetricName": "tma_load_stlb_miss", - "MetricThreshold": "tma_load_stlb_miss > 0.05 & tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_load_stlb_miss > 0.05 & (tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 1 GB pages for data load accesses", + "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 1 GB pages for data load accesses.", "MetricExpr": "tma_load_stlb_miss * DTLB_LOAD_MISSES.WALK_COMPLETED_1G / (DTLB_LOAD_MISSES.WALK_COMPLETED_4K + DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M + DTLB_LOAD_MISSES.WALK_COMPLETED_1G)", "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_load_stlb_miss_group", "MetricName": "tma_load_stlb_miss_1g", - "MetricThreshold": "tma_load_stlb_miss_1g > 0.05 & tma_load_stlb_miss > 0.05 & tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_load_stlb_miss_1g > 0.05 & (tma_load_stlb_miss > 0.05 & (tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))))", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 2 or 4 MB pages for data load accesses", + "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 2 or 4 MB pages for data load accesses.", "MetricExpr": "tma_load_stlb_miss * DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M / (DTLB_LOAD_MISSES.WALK_COMPLETED_4K + DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M + DTLB_LOAD_MISSES.WALK_COMPLETED_1G)", "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_load_stlb_miss_group", "MetricName": "tma_load_stlb_miss_2m", - "MetricThreshold": "tma_load_stlb_miss_2m > 0.05 & tma_load_stlb_miss > 0.05 & tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_load_stlb_miss_2m > 0.05 & (tma_load_stlb_miss > 0.05 & (tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))))", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 4 KB pages for data load accesses", + "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 4 KB pages for data load accesses.", "MetricExpr": "tma_load_stlb_miss * DTLB_LOAD_MISSES.WALK_COMPLETED_4K / (DTLB_LOAD_MISSES.WALK_COMPLETED_4K + DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M + DTLB_LOAD_MISSES.WALK_COMPLETED_1G)", "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_load_stlb_miss_group", "MetricName": "tma_load_stlb_miss_4k", - "MetricThreshold": "tma_load_stlb_miss_4k > 0.05 & tma_load_stlb_miss > 0.05 & tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_load_stlb_miss_4k > 0.05 & (tma_load_stlb_miss > 0.05 & (tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))))", "ScaleUnit": "100%" }, { "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from local memory", - "MetricExpr": "(66.5 * tma_info_system_core_frequency - 23 * tma_info_system_core_frequency) * MEM_LOAD_L3_MISS_RETIRED.LOCAL_DRAM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks", + "MetricExpr": "43.5 * tma_info_system_core_frequency * MEM_LOAD_L3_MISS_RETIRED.LOCAL_DRAM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks", "MetricGroup": "Server;TopdownL5;tma_L5_group;tma_mem_latency_group", "MetricName": "tma_local_mem", - "MetricThreshold": "tma_local_mem > 0.1 & tma_mem_latency > 0.1 & tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_local_mem > 0.1 & (tma_mem_latency > 0.1 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))", "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from local memory. Caching will improve the latency and increase performance. Sample with: MEM_LOAD_L3_MISS_RETIRED.LOCAL_DRAM", "ScaleUnit": "100%" }, @@ -1720,7 +1719,7 @@ "MetricExpr": "(16 * max(0, MEM_INST_RETIRED.LOCK_LOADS - L2_RQSTS.ALL_RFO) + MEM_INST_RETIRED.LOCK_LOADS / MEM_INST_RETIRED.ALL_STORES * (10 * L2_RQSTS.RFO_HIT + min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO))) / tma_info_thread_clks", "MetricGroup": "LockCont;Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_l1_bound_group", "MetricName": "tma_lock_latency", - "MetricThreshold": "tma_lock_latency > 0.2 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_lock_latency > 0.2 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", "PublicDescription": "This metric represents fraction of cycles the CPU spent handling cache misses due to lock operations. Due to the microarchitecture handling of locks; they are classified as L1_Bound regardless of what memory source satisfied them. Sample with: MEM_INST_RETIRED.LOCK_LOADS. Related metrics: tma_store_latency", "ScaleUnit": "100%" }, @@ -1736,10 +1735,10 @@ }, { "BriefDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory - DRAM ([SPR-HBM] and/or HBM)", - "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, cpu@OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD\\,cmask\\=0x4@) / tma_info_thread_clks", + "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, cpu@OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD\\,cmask\\=4@) / tma_info_thread_clks", "MetricGroup": "BvMB;MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueBW", "MetricName": "tma_mem_bandwidth", - "MetricThreshold": "tma_mem_bandwidth > 0.2 & tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_mem_bandwidth > 0.2 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", "PublicDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory - DRAM ([SPR-HBM] and/or HBM). The underlying heuristic assumes that a similar off-core traffic is generated by all IA cores. This metric does not aggregate non-data-read requests by this logical processor; requests from other IA Logical Processors/Physical Cores/sockets; or other non-IA devices like GPU; hence the maximum external memory bandwidth limits may or may not be approached when this metric is flagged (see Uncore counters for that). Related metrics: tma_bottleneck_cache_memory_bandwidth, tma_fb_full, tma_info_system_dram_bw_use, tma_sq_full", "ScaleUnit": "100%" }, @@ -1748,7 +1747,7 @@ "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD) / tma_info_thread_clks - tma_mem_bandwidth", "MetricGroup": "BvML;MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueLat", "MetricName": "tma_mem_latency", - "MetricThreshold": "tma_mem_latency > 0.1 & tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_mem_latency > 0.1 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", "PublicDescription": "This metric estimates fraction of cycles where the performance was likely hurt due to latency from external memory - DRAM ([SPR-HBM] and/or HBM). This metric does not aggregate requests from other Logical Processors/Physical Cores/sockets (see Uncore counters for that). Related metrics: tma_bottleneck_cache_memory_latency, tma_l3_hit_latency", "ScaleUnit": "100%" }, @@ -1759,11 +1758,11 @@ "MetricName": "tma_memory_bound", "MetricThreshold": "tma_memory_bound > 0.2 & tma_backend_bound > 0.2", "MetricgroupNoGroup": "TopdownL2", - "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck. Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two)", + "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck. Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two).", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of slots where the CPU was retiring memory operations , uops for memory load or store accesses", + "BriefDescription": "This metric represents fraction of slots where the CPU was retiring memory operations -- uops for memory load or store accesses.", "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "tma_light_operations * MEM_INST_RETIRED.ANY / INST_RETIRED.ANY", "MetricGroup": "Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group", @@ -1785,7 +1784,7 @@ "MetricExpr": "BR_MISP_RETIRED.ALL_BRANCHES / (BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT) * INT_MISC.CLEAR_RESTEER_CYCLES / tma_info_thread_clks", "MetricGroup": "BadSpec;BrMispredicts;BvMP;TopdownL4;tma_L4_group;tma_branch_resteers_group;tma_issueBM", "MetricName": "tma_mispredicts_resteers", - "MetricThreshold": "tma_mispredicts_resteers > 0.05 & tma_branch_resteers > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricThreshold": "tma_mispredicts_resteers > 0.05 & (tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))", "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Branch Misprediction at execution stage. Sample with: INT_MISC.CLEAR_RESTEER_CYCLES. Related metrics: tma_bottleneck_mispredictions, tma_branch_mispredicts, tma_info_bad_spec_branch_misprediction_cost", "ScaleUnit": "100%" }, @@ -1800,24 +1799,24 @@ }, { "BriefDescription": "This metric represents fraction of cycles where (only) 4 uops were delivered by the MITE pipeline", - "MetricExpr": "(cpu@IDQ.MITE_UOPS\\,cmask\\=0x4@ - cpu@IDQ.MITE_UOPS\\,cmask\\=0x5@) / tma_info_thread_clks", + "MetricExpr": "(cpu@IDQ.MITE_UOPS\\,cmask\\=4@ - cpu@IDQ.MITE_UOPS\\,cmask\\=5@) / tma_info_thread_clks", "MetricGroup": "DSBmiss;FetchBW;TopdownL4;tma_L4_group;tma_mite_group", "MetricName": "tma_mite_4wide", - "MetricThreshold": "tma_mite_4wide > 0.05 & tma_mite > 0.1 & tma_fetch_bandwidth > 0.2", + "MetricThreshold": "tma_mite_4wide > 0.05 & (tma_mite > 0.1 & tma_fetch_bandwidth > 0.2)", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates penalty in terms of percentage of([SKL+] injected blend uops out of all Uops Issued , the Count Domain; [ADL+] cycles)", + "BriefDescription": "This metric estimates penalty in terms of percentage of([SKL+] injected blend uops out of all Uops Issued -- the Count Domain; [ADL+] cycles)", "MetricExpr": "UOPS_ISSUED.VECTOR_WIDTH_MISMATCH / UOPS_ISSUED.ANY", "MetricGroup": "TopdownL5;tma_L5_group;tma_issueMV;tma_ports_utilized_0_group", "MetricName": "tma_mixing_vectors", "MetricThreshold": "tma_mixing_vectors > 0.05", - "PublicDescription": "This metric estimates penalty in terms of percentage of([SKL+] injected blend uops out of all Uops Issued , the Count Domain; [ADL+] cycles). Usually a Mixing_Vectors over 5% is worth investigating. Read more in Appendix B1 of the Optimizations Guide for this topic. Related metrics: tma_ms_switches", + "PublicDescription": "This metric estimates penalty in terms of percentage of([SKL+] injected blend uops out of all Uops Issued -- the Count Domain; [ADL+] cycles). Usually a Mixing_Vectors over 5% is worth investigating. Read more in Appendix B1 of the Optimizations Guide for this topic. Related metrics: tma_ms_switches", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to the Microcode Sequencer (MS) unit - see Microcode_Sequencer node for details", - "MetricExpr": "cpu@IDQ.MS_UOPS\\,cmask\\=0x1@ / tma_info_core_core_clks / 2", + "BriefDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to the Microcode Sequencer (MS) unit - see Microcode_Sequencer node for details.", + "MetricExpr": "cpu@IDQ.MS_UOPS\\,cmask\\=1@ / tma_info_core_core_clks / 2", "MetricGroup": "MicroSeq;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group", "MetricName": "tma_ms", "MetricThreshold": "tma_ms > 0.05 & tma_fetch_bandwidth > 0.2", @@ -1828,7 +1827,7 @@ "MetricExpr": "3 * IDQ.MS_SWITCHES / tma_info_thread_clks", "MetricGroup": "FetchLat;MicroSeq;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueMC;tma_issueMS;tma_issueMV;tma_issueSO", "MetricName": "tma_ms_switches", - "MetricThreshold": "tma_ms_switches > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricThreshold": "tma_ms_switches > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", "PublicDescription": "This metric estimates the fraction of cycles when the CPU was stalled due to switches of uop delivery to the Microcode Sequencer (MS). Commonly used instructions are optimized for delivery by the DSB (decoded i-cache) or MITE (legacy instruction decode) pipelines. Certain operations cannot be handled natively by the execution pipeline; and must be performed by microcode (small programs injected into the execution stream). Switching to the MS too often can negatively impact performance. The MS is designated to deliver long uop flows required by CISC instructions like CPUID; or uncommon conditions like Floating Point Assists when dealing with Denormals. Sample with: IDQ.MS_SWITCHES. Related metrics: tma_bottleneck_irregular_overhead, tma_clears_resteers, tma_l1_bound, tma_machine_clears, tma_microcode_sequencer, tma_mixing_vectors, tma_serializing_operation", "ScaleUnit": "100%" }, @@ -1837,7 +1836,7 @@ "MetricExpr": "tma_light_operations * INST_RETIRED.NOP / (tma_retiring * tma_info_thread_slots)", "MetricGroup": "BvBO;Pipeline;TopdownL4;tma_L4_group;tma_other_light_ops_group", "MetricName": "tma_nop_instructions", - "MetricThreshold": "tma_nop_instructions > 0.1 & tma_other_light_ops > 0.3 & tma_light_operations > 0.6", + "MetricThreshold": "tma_nop_instructions > 0.1 & (tma_other_light_ops > 0.3 & tma_light_operations > 0.6)", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring NOP (no op) instructions. Compilers often use NOPs for certain address alignments - e.g. start address of a function or loop body. Sample with: INST_RETIRED.NOP", "ScaleUnit": "100%" }, @@ -1852,19 +1851,19 @@ "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates fraction of slots the CPU was stalled due to other cases of misprediction (non-retired x86 branches or other types)", + "BriefDescription": "This metric estimates fraction of slots the CPU was stalled due to other cases of misprediction (non-retired x86 branches or other types).", "MetricExpr": "max(tma_branch_mispredicts * (1 - BR_MISP_RETIRED.ALL_BRANCHES / (INT_MISC.CLEARS_COUNT - MACHINE_CLEARS.COUNT)), 0.0001)", "MetricGroup": "BrMispredicts;BvIO;TopdownL3;tma_L3_group;tma_branch_mispredicts_group", "MetricName": "tma_other_mispredicts", - "MetricThreshold": "tma_other_mispredicts > 0.05 & tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", + "MetricThreshold": "tma_other_mispredicts > 0.05 & (tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15)", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of slots the CPU has wasted due to Nukes (Machine Clears) not related to memory ordering", + "BriefDescription": "This metric represents fraction of slots the CPU has wasted due to Nukes (Machine Clears) not related to memory ordering.", "MetricExpr": "max(tma_machine_clears * (1 - MACHINE_CLEARS.MEMORY_ORDERING / MACHINE_CLEARS.COUNT), 0.0001)", "MetricGroup": "BvIO;Machine_Clears;TopdownL3;tma_L3_group;tma_machine_clears_group", "MetricName": "tma_other_nukes", - "MetricThreshold": "tma_other_nukes > 0.05 & tma_machine_clears > 0.1 & tma_bad_speculation > 0.15", + "MetricThreshold": "tma_other_nukes > 0.05 & (tma_machine_clears > 0.1 & tma_bad_speculation > 0.15)", "ScaleUnit": "100%" }, { @@ -1908,8 +1907,8 @@ "MetricExpr": "((tma_ports_utilized_0 * tma_info_thread_clks + (EXE_ACTIVITY.1_PORTS_UTIL + tma_retiring * EXE_ACTIVITY.2_PORTS_UTIL)) / tma_info_thread_clks if ARITH.DIVIDER_ACTIVE < CYCLE_ACTIVITY.STALLS_TOTAL - CYCLE_ACTIVITY.STALLS_MEM_ANY else (EXE_ACTIVITY.1_PORTS_UTIL + tma_retiring * EXE_ACTIVITY.2_PORTS_UTIL) / tma_info_thread_clks)", "MetricGroup": "PortsUtil;TopdownL3;tma_L3_group;tma_core_bound_group", "MetricName": "tma_ports_utilization", - "MetricThreshold": "tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", - "PublicDescription": "This metric estimates fraction of cycles the CPU performance was potentially limited due to Core computation issues (non divider-related). Two distinct categories can be attributed into this metric: (1) heavy data-dependency among contiguous instructions would manifest in this metric - such cases are often referred to as low Instruction Level Parallelism (ILP). (2) Contention on some hardware execution unit other than Divider. For example; when there are too many multiply operations", + "MetricThreshold": "tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)", + "PublicDescription": "This metric estimates fraction of cycles the CPU performance was potentially limited due to Core computation issues (non divider-related). Two distinct categories can be attributed into this metric: (1) heavy data-dependency among contiguous instructions would manifest in this metric - such cases are often referred to as low Instruction Level Parallelism (ILP). (2) Contention on some hardware execution unit other than Divider. For example; when there are too many multiply operations.", "ScaleUnit": "100%" }, { @@ -1917,8 +1916,8 @@ "MetricExpr": "cpu@EXE_ACTIVITY.3_PORTS_UTIL\\,umask\\=0x80@ / tma_info_thread_clks", "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group", "MetricName": "tma_ports_utilized_0", - "MetricThreshold": "tma_ports_utilized_0 > 0.2 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", - "PublicDescription": "This metric represents fraction of cycles CPU executed no uops on any execution port (Logical Processor cycles since ICL, Physical Core cycles otherwise). Long-latency instructions like divides may contribute to this metric", + "MetricThreshold": "tma_ports_utilized_0 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric represents fraction of cycles CPU executed no uops on any execution port (Logical Processor cycles since ICL, Physical Core cycles otherwise). Long-latency instructions like divides may contribute to this metric.", "ScaleUnit": "100%" }, { @@ -1926,7 +1925,7 @@ "MetricExpr": "EXE_ACTIVITY.1_PORTS_UTIL / tma_info_thread_clks", "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_issueL1;tma_ports_utilization_group", "MetricName": "tma_ports_utilized_1", - "MetricThreshold": "tma_ports_utilized_1 > 0.2 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_ports_utilized_1 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", "PublicDescription": "This metric represents fraction of cycles where the CPU executed total of 1 uop per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise). This can be due to heavy data-dependency among software instructions; or over oversubscribing a particular hardware resource. In some other cases with high 1_Port_Utilized and L1_Bound; this metric can point to L1 data-cache latency bottleneck that may not necessarily manifest with complete execution starvation (due to the short L1 latency e.g. walking a linked list) - looking at the assembly can be helpful. Sample with: EXE_ACTIVITY.1_PORTS_UTIL. Related metrics: tma_l1_bound", "ScaleUnit": "100%" }, @@ -1935,7 +1934,7 @@ "MetricExpr": "EXE_ACTIVITY.2_PORTS_UTIL / tma_info_thread_clks", "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_issue2P;tma_ports_utilization_group", "MetricName": "tma_ports_utilized_2", - "MetricThreshold": "tma_ports_utilized_2 > 0.15 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_ports_utilized_2 > 0.15 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", "PublicDescription": "This metric represents fraction of cycles CPU executed total of 2 uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise). Loop Vectorization -most compilers feature auto-Vectorization options today- reduces pressure on the execution ports as multiple elements are calculated with same uop. Sample with: EXE_ACTIVITY.2_PORTS_UTIL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6", "ScaleUnit": "100%" }, @@ -1944,32 +1943,32 @@ "MetricExpr": "UOPS_EXECUTED.CYCLES_GE_3 / tma_info_thread_clks", "MetricGroup": "BvCB;PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group", "MetricName": "tma_ports_utilized_3m", - "MetricThreshold": "tma_ports_utilized_3m > 0.4 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_ports_utilized_3m > 0.4 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", "PublicDescription": "This metric represents fraction of cycles CPU executed total of 3 or more uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise). Sample with: UOPS_EXECUTED.CYCLES_GE_3", "ScaleUnit": "100%" }, { "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from remote cache in other sockets including synchronizations issues", - "MetricExpr": "((120 * tma_info_system_core_frequency - 23 * tma_info_system_core_frequency) * MEM_LOAD_L3_MISS_RETIRED.REMOTE_HITM + (120 * tma_info_system_core_frequency - 23 * tma_info_system_core_frequency) * MEM_LOAD_L3_MISS_RETIRED.REMOTE_FWD) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks", + "MetricExpr": "(97 * tma_info_system_core_frequency * MEM_LOAD_L3_MISS_RETIRED.REMOTE_HITM + 97 * tma_info_system_core_frequency * MEM_LOAD_L3_MISS_RETIRED.REMOTE_FWD) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks", "MetricGroup": "Offcore;Server;Snoop;TopdownL5;tma_L5_group;tma_issueSyncxn;tma_mem_latency_group", "MetricName": "tma_remote_cache", - "MetricThreshold": "tma_remote_cache > 0.05 & tma_mem_latency > 0.1 & tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", - "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from remote cache in other sockets including synchronizations issues. This is caused often due to non-optimal NUMA allocations. Sample with: MEM_LOAD_L3_MISS_RETIRED.REMOTE_HITM, MEM_LOAD_L3_MISS_RETIRED.REMOTE_FWD. Related metrics: tma_bottleneck_memory_synchronization, tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_machine_clears", + "MetricThreshold": "tma_remote_cache > 0.05 & (tma_mem_latency > 0.1 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))", + "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from remote cache in other sockets including synchronizations issues. This is caused often due to non-optimal NUMA allocations. #link to NUMA article. Sample with: MEM_LOAD_L3_MISS_RETIRED.REMOTE_HITM_PS;MEM_LOAD_L3_MISS_RETIRED.REMOTE_FWD_PS. Related metrics: tma_bottleneck_memory_synchronization, tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_machine_clears", "ScaleUnit": "100%" }, { "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from remote memory", - "MetricExpr": "(131 * tma_info_system_core_frequency - 23 * tma_info_system_core_frequency) * MEM_LOAD_L3_MISS_RETIRED.REMOTE_DRAM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks", + "MetricExpr": "108 * tma_info_system_core_frequency * MEM_LOAD_L3_MISS_RETIRED.REMOTE_DRAM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks", "MetricGroup": "Server;Snoop;TopdownL5;tma_L5_group;tma_mem_latency_group", "MetricName": "tma_remote_mem", - "MetricThreshold": "tma_remote_mem > 0.1 & tma_mem_latency > 0.1 & tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", - "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from remote memory. This is caused often due to non-optimal NUMA allocations. Sample with: MEM_LOAD_L3_MISS_RETIRED.REMOTE_DRAM", + "MetricThreshold": "tma_remote_mem > 0.1 & (tma_mem_latency > 0.1 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))", + "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from remote memory. This is caused often due to non-optimal NUMA allocations. #link to NUMA article. Sample with: MEM_LOAD_L3_MISS_RETIRED.REMOTE_DRAM_PS", "ScaleUnit": "100%" }, { "BriefDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired", "DefaultMetricgroupName": "TopdownL1", - "MetricExpr": "topdown\\-retiring / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * slots", + "MetricExpr": "topdown\\-retiring / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * tma_info_thread_slots", "MetricGroup": "BvUW;Default;TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_retiring", "MetricThreshold": "tma_retiring > 0.7 | tma_heavy_operations > 0.1", @@ -1982,7 +1981,7 @@ "MetricExpr": "RESOURCE_STALLS.SCOREBOARD / tma_info_thread_clks", "MetricGroup": "BvIO;PortsUtil;TopdownL3;tma_L3_group;tma_core_bound_group;tma_issueSO", "MetricName": "tma_serializing_operation", - "MetricThreshold": "tma_serializing_operation > 0.1 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_serializing_operation > 0.1 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)", "PublicDescription": "This metric represents fraction of cycles the CPU issue-pipeline was stalled due to serializing operations. Instructions like CPUID; WRMSR or LFENCE serialize the out-of-order execution which may limit performance. Sample with: RESOURCE_STALLS.SCOREBOARD. Related metrics: tma_ms_switches", "ScaleUnit": "100%" }, @@ -1991,7 +1990,7 @@ "MetricExpr": "37 * MISC_RETIRED.PAUSE_INST / tma_info_thread_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_serializing_operation_group", "MetricName": "tma_slow_pause", - "MetricThreshold": "tma_slow_pause > 0.05 & tma_serializing_operation > 0.1 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_slow_pause > 0.05 & (tma_serializing_operation > 0.1 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to PAUSE Instructions. Sample with: MISC_RETIRED.PAUSE_INST", "ScaleUnit": "100%" }, @@ -2001,7 +2000,7 @@ "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group", "MetricName": "tma_split_loads", "MetricThreshold": "tma_split_loads > 0.3", - "PublicDescription": "This metric estimates fraction of cycles handling memory load split accesses - load that cross 64-byte cache line boundary. Sample with: MEM_INST_RETIRED.SPLIT_LOADS", + "PublicDescription": "This metric estimates fraction of cycles handling memory load split accesses - load that cross 64-byte cache line boundary. Sample with: MEM_INST_RETIRED.SPLIT_LOADS_PS", "ScaleUnit": "100%" }, { @@ -2010,8 +2009,8 @@ "MetricExpr": "MEM_INST_RETIRED.SPLIT_STORES / tma_info_core_core_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_issueSpSt;tma_store_bound_group", "MetricName": "tma_split_stores", - "MetricThreshold": "tma_split_stores > 0.2 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", - "PublicDescription": "This metric represents rate of split store accesses. Consider aligning your data to the 64-byte cache line granularity. Sample with: MEM_INST_RETIRED.SPLIT_STORES", + "MetricThreshold": "tma_split_stores > 0.2 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric represents rate of split store accesses. Consider aligning your data to the 64-byte cache line granularity. Sample with: MEM_INST_RETIRED.SPLIT_STORES_PS. Related metrics: tma_port_4", "ScaleUnit": "100%" }, { @@ -2019,7 +2018,7 @@ "MetricExpr": "L1D_PEND_MISS.L2_STALL / tma_info_thread_clks", "MetricGroup": "BvMB;MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_issueBW;tma_l3_bound_group", "MetricName": "tma_sq_full", - "MetricThreshold": "tma_sq_full > 0.3 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_sq_full > 0.3 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", "PublicDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors). Related metrics: tma_bottleneck_cache_memory_bandwidth, tma_fb_full, tma_info_system_dram_bw_use, tma_mem_bandwidth", "ScaleUnit": "100%" }, @@ -2028,8 +2027,8 @@ "MetricExpr": "EXE_ACTIVITY.BOUND_ON_STORES / tma_info_thread_clks", "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_store_bound", - "MetricThreshold": "tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", - "PublicDescription": "This metric estimates how often CPU was stalled due to RFO store memory accesses; RFO store issue a read-for-ownership request before the write. Even though store accesses do not typically stall out-of-order CPUs; there are few cases where stores can lead to actual stalls. This metric will be flagged should RFO stores be a bottleneck. Sample with: MEM_INST_RETIRED.ALL_STORES", + "MetricThreshold": "tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", + "PublicDescription": "This metric estimates how often CPU was stalled due to RFO store memory accesses; RFO store issue a read-for-ownership request before the write. Even though store accesses do not typically stall out-of-order CPUs; there are few cases where stores can lead to actual stalls. This metric will be flagged should RFO stores be a bottleneck. Sample with: MEM_INST_RETIRED.ALL_STORES_PS", "ScaleUnit": "100%" }, { @@ -2038,8 +2037,8 @@ "MetricExpr": "13 * LD_BLOCKS.STORE_FORWARD / tma_info_thread_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group", "MetricName": "tma_store_fwd_blk", - "MetricThreshold": "tma_store_fwd_blk > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", - "PublicDescription": "This metric roughly estimates fraction of cycles when the memory subsystem had loads blocked since they could not forward data from earlier (in program order) overlapping stores. To streamline memory operations in the pipeline; a load can avoid waiting for memory if a prior in-flight store is writing the data that the load wants to read (store forwarding process). However; in some cases the load may be blocked for a significant time pending the store forward. For example; when the prior store is writing a smaller region than the load is reading", + "MetricThreshold": "tma_store_fwd_blk > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric roughly estimates fraction of cycles when the memory subsystem had loads blocked since they could not forward data from earlier (in program order) overlapping stores. To streamline memory operations in the pipeline; a load can avoid waiting for memory if a prior in-flight store is writing the data that the load wants to read (store forwarding process). However; in some cases the load may be blocked for a significant time pending the store forward. For example; when the prior store is writing a smaller region than the load is reading.", "ScaleUnit": "100%" }, { @@ -2047,8 +2046,8 @@ "MetricExpr": "(L2_RQSTS.RFO_HIT * 10 * (1 - MEM_INST_RETIRED.LOCK_LOADS / MEM_INST_RETIRED.ALL_STORES) + (1 - MEM_INST_RETIRED.LOCK_LOADS / MEM_INST_RETIRED.ALL_STORES) * min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO)) / tma_info_thread_clks", "MetricGroup": "BvML;LockCont;MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_issueSL;tma_store_bound_group", "MetricName": "tma_store_latency", - "MetricThreshold": "tma_store_latency > 0.1 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", - "PublicDescription": "This metric estimates fraction of cycles the CPU spent handling L1D store misses. Store accesses usually less impact out-of-order core performance; however; holding resources for longer time can lead into undesired implications (e.g. contention on L1D fill-buffer entries - see FB_Full). Related metrics: tma_branch_resteers, tma_fb_full, tma_l3_hit_latency, tma_lock_latency", + "MetricThreshold": "tma_store_latency > 0.1 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric estimates fraction of cycles the CPU spent handling L1D store misses. Store accesses usually less impact out-of-order core performance; however; holding resources for longer time can lead into undesired implications (e.g. contention on L1D fill-buffer entries - see FB_Full). Related metrics: tma_fb_full, tma_lock_latency", "ScaleUnit": "100%" }, { @@ -2065,7 +2064,7 @@ "MetricExpr": "tma_dtlb_store - tma_store_stlb_miss", "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_store_group", "MetricName": "tma_store_stlb_hit", - "MetricThreshold": "tma_store_stlb_hit > 0.05 & tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_store_stlb_hit > 0.05 & (tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))", "ScaleUnit": "100%" }, { @@ -2073,31 +2072,31 @@ "MetricExpr": "DTLB_STORE_MISSES.WALK_ACTIVE / tma_info_core_core_clks", "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_store_group", "MetricName": "tma_store_stlb_miss", - "MetricThreshold": "tma_store_stlb_miss > 0.05 & tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_store_stlb_miss > 0.05 & (tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 1 GB pages for data store accesses", + "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 1 GB pages for data store accesses.", "MetricExpr": "tma_store_stlb_miss * DTLB_STORE_MISSES.WALK_COMPLETED_1G / (DTLB_STORE_MISSES.WALK_COMPLETED_4K + DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M + DTLB_STORE_MISSES.WALK_COMPLETED_1G)", "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_store_stlb_miss_group", "MetricName": "tma_store_stlb_miss_1g", - "MetricThreshold": "tma_store_stlb_miss_1g > 0.05 & tma_store_stlb_miss > 0.05 & tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_store_stlb_miss_1g > 0.05 & (tma_store_stlb_miss > 0.05 & (tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))))", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 2 or 4 MB pages for data store accesses", + "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 2 or 4 MB pages for data store accesses.", "MetricExpr": "tma_store_stlb_miss * DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M / (DTLB_STORE_MISSES.WALK_COMPLETED_4K + DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M + DTLB_STORE_MISSES.WALK_COMPLETED_1G)", "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_store_stlb_miss_group", "MetricName": "tma_store_stlb_miss_2m", - "MetricThreshold": "tma_store_stlb_miss_2m > 0.05 & tma_store_stlb_miss > 0.05 & tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_store_stlb_miss_2m > 0.05 & (tma_store_stlb_miss > 0.05 & (tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))))", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 4 KB pages for data store accesses", + "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 4 KB pages for data store accesses.", "MetricExpr": "tma_store_stlb_miss * DTLB_STORE_MISSES.WALK_COMPLETED_4K / (DTLB_STORE_MISSES.WALK_COMPLETED_4K + DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M + DTLB_STORE_MISSES.WALK_COMPLETED_1G)", "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_store_stlb_miss_group", "MetricName": "tma_store_stlb_miss_4k", - "MetricThreshold": "tma_store_stlb_miss_4k > 0.05 & tma_store_stlb_miss > 0.05 & tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_store_stlb_miss_4k > 0.05 & (tma_store_stlb_miss > 0.05 & (tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))))", "ScaleUnit": "100%" }, { @@ -2105,7 +2104,7 @@ "MetricExpr": "9 * OCR.STREAMING_WR.ANY_RESPONSE / tma_info_thread_clks", "MetricGroup": "MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_issueSmSt;tma_store_bound_group", "MetricName": "tma_streaming_stores", - "MetricThreshold": "tma_streaming_stores > 0.2 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_streaming_stores > 0.2 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", "PublicDescription": "This metric estimates how often CPU was stalled due to Streaming store memory accesses; Streaming store optimize out a read request required by RFO stores. Even though store accesses do not typically stall out-of-order CPUs; there are few cases where stores can lead to actual stalls. This metric will be flagged should Streaming stores be a bottleneck. Sample with: OCR.STREAMING_WR.ANY_RESPONSE. Related metrics: tma_fb_full", "ScaleUnit": "100%" }, @@ -2114,7 +2113,7 @@ "MetricExpr": "10 * BACLEARS.ANY / tma_info_thread_clks", "MetricGroup": "BigFootprint;BvBC;FetchLat;TopdownL4;tma_L4_group;tma_branch_resteers_group", "MetricName": "tma_unknown_branches", - "MetricThreshold": "tma_unknown_branches > 0.05 & tma_branch_resteers > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricThreshold": "tma_unknown_branches > 0.05 & (tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))", "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to new branch address clears. These are fetched branches the Branch Prediction Unit was unable to recognize (e.g. first time the branch is fetched or hitting BTB capacity limit) hence called Unknown Branches. Sample with: BACLEARS.ANY", "ScaleUnit": "100%" }, @@ -2123,8 +2122,8 @@ "MetricExpr": "tma_retiring * UOPS_EXECUTED.X87 / UOPS_EXECUTED.THREAD", "MetricGroup": "Compute;TopdownL4;tma_L4_group;tma_fp_arith_group", "MetricName": "tma_x87_use", - "MetricThreshold": "tma_x87_use > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6", - "PublicDescription": "This metric serves as an approximation of legacy x87 usage. It accounts for instructions beyond X87 FP arithmetic operations; hence may be used as a thermometer to avoid X87 high usage and preferably upgrade to modern ISA. See Tip under Tuning Hint", + "MetricThreshold": "tma_x87_use > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6)", + "PublicDescription": "This metric serves as an approximation of legacy x87 usage. It accounts for instructions beyond X87 FP arithmetic operations; hence may be used as a thermometer to avoid X87 high usage and preferably upgrade to modern ISA. See Tip under Tuning Hint.", "ScaleUnit": "100%" }, { diff --git a/tools/perf/pmu-events/arch/x86/icelakex/memory.json b/tools/perf/pmu-events/arch/x86/icelakex/memory.json index ec9577cce3ac..ca7f68f67463 100644 --- a/tools/perf/pmu-events/arch/x86/icelakex/memory.json +++ b/tools/perf/pmu-events/arch/x86/icelakex/memory.json @@ -114,6 +114,16 @@ "UMask": "0x1" }, { + "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were supplied by DRAM.", + "Counter": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OCR.DEMAND_CODE_RD.DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x73C000004", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were not supplied by the local socket's L1, L2, or L3 caches.", "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -134,6 +144,36 @@ "UMask": "0x1" }, { + "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were supplied by DRAM attached to this socket, unless in Sub NUMA Cluster(SNC) Mode. In SNC Mode counts only those DRAM accesses that are controlled by the close SNC Cluster.", + "Counter": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OCR.DEMAND_CODE_RD.LOCAL_DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x104000004", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were supplied by DRAM on a distant memory controller of this socket when the system is in SNC (sub-NUMA cluster) mode.", + "Counter": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OCR.DEMAND_CODE_RD.SNC_DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x708000004", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts demand data reads that were supplied by DRAM.", + "Counter": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OCR.DEMAND_DATA_RD.DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x73C000001", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { "BriefDescription": "Counts demand data reads that were not supplied by the local socket's L1, L2, or L3 caches.", "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -154,6 +194,46 @@ "UMask": "0x1" }, { + "BriefDescription": "Counts demand data reads that were supplied by DRAM attached to this socket, unless in Sub NUMA Cluster(SNC) Mode. In SNC Mode counts only those DRAM accesses that are controlled by the close SNC Cluster.", + "Counter": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OCR.DEMAND_DATA_RD.LOCAL_DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x104000001", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts demand data reads that were supplied by DRAM attached to another socket.", + "Counter": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OCR.DEMAND_DATA_RD.REMOTE_DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x730000001", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts demand data reads that were supplied by DRAM on a distant memory controller of this socket when the system is in SNC (sub-NUMA cluster) mode.", + "Counter": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OCR.DEMAND_DATA_RD.SNC_DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x708000001", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts demand reads for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that were supplied by DRAM.", + "Counter": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OCR.DEMAND_RFO.DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x73C000002", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { "BriefDescription": "Counts demand reads for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that were not supplied by the local socket's L1, L2, or L3 caches.", "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -174,6 +254,36 @@ "UMask": "0x1" }, { + "BriefDescription": "Counts demand reads for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that were supplied by DRAM attached to this socket, unless in Sub NUMA Cluster(SNC) Mode. In SNC Mode counts only those DRAM accesses that are controlled by the close SNC Cluster.", + "Counter": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OCR.DEMAND_RFO.LOCAL_DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x104000002", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts demand reads for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that were supplied by DRAM on a distant memory controller of this socket when the system is in SNC (sub-NUMA cluster) mode.", + "Counter": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OCR.DEMAND_RFO.SNC_DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x708000002", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts L1 data cache prefetch requests and software prefetches (except PREFETCHW) that were supplied by DRAM.", + "Counter": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OCR.HWPF_L1D_AND_SWPF.DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x73C000400", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { "BriefDescription": "Counts L1 data cache prefetch requests and software prefetches (except PREFETCHW) that were not supplied by the local socket's L1, L2, or L3 caches.", "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -194,6 +304,16 @@ "UMask": "0x1" }, { + "BriefDescription": "Counts L1 data cache prefetch requests and software prefetches (except PREFETCHW) that were supplied by DRAM attached to this socket, unless in Sub NUMA Cluster(SNC) Mode. In SNC Mode counts only those DRAM accesses that are controlled by the close SNC Cluster.", + "Counter": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OCR.HWPF_L1D_AND_SWPF.LOCAL_DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x104000400", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { "BriefDescription": "Counts hardware prefetches to the L3 only that missed the local socket's L1, L2, and L3 caches.", "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -254,6 +374,16 @@ "UMask": "0x1" }, { + "BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by DRAM.", + "Counter": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OCR.READS_TO_CORE.DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x73C000477", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { "BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were not supplied by the local socket's L1, L2, or L3 caches.", "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -284,6 +414,56 @@ "UMask": "0x1" }, { + "BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by DRAM attached to this socket, unless in Sub NUMA Cluster(SNC) Mode. In SNC Mode counts only those DRAM accesses that are controlled by the close SNC Cluster.", + "Counter": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OCR.READS_TO_CORE.LOCAL_DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x104000477", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by DRAM attached to this socket, whether or not in Sub NUMA Cluster(SNC) Mode. In SNC Mode counts DRAM accesses that are controlled by the close or distant SNC Cluster.", + "Counter": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OCR.READS_TO_CORE.LOCAL_SOCKET_DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x70C000477", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by DRAM attached to another socket.", + "Counter": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OCR.READS_TO_CORE.REMOTE_DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x730000477", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by DRAM or PMM attached to another socket.", + "Counter": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OCR.READS_TO_CORE.REMOTE_MEMORY", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x731800477", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by DRAM on a distant memory controller of this socket when the system is in SNC (sub-NUMA cluster) mode.", + "Counter": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OCR.READS_TO_CORE.SNC_DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x708000477", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { "BriefDescription": "Counts streaming stores that missed the local socket's L1, L2, and L3 caches.", "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -304,6 +484,16 @@ "UMask": "0x1" }, { + "BriefDescription": "Counts Demand RFOs, ItoM's, PREFECTHW's, Hardware RFO Prefetches to the L1/L2 and Streaming stores that likely resulted in a store to Memory (DRAM or PMM)", + "Counter": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OCR.WRITE_ESTIMATE.MEMORY", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0xFBFF80822", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { "BriefDescription": "Counts demand data read requests that miss the L3 cache.", "Counter": "0,1,2,3", "EventCode": "0xb0", diff --git a/tools/perf/pmu-events/arch/x86/icelakex/other.json b/tools/perf/pmu-events/arch/x86/icelakex/other.json index 05b348d9c838..141cd30a30af 100644 --- a/tools/perf/pmu-events/arch/x86/icelakex/other.json +++ b/tools/perf/pmu-events/arch/x86/icelakex/other.json @@ -27,339 +27,6 @@ "UMask": "0x20" }, { - "BriefDescription": "Hit snoop reply with data, line invalidated.", - "Counter": "0,1,2,3", - "EventCode": "0xef", - "EventName": "CORE_SNOOP_RESPONSE.I_FWD_FE", - "PublicDescription": "Counts responses to snoops indicating the line will now be (I)nvalidated: removed from this core's cache, after the data is forwarded back to the requestor and indicating the data was found unmodified in the (FE) Forward or Exclusive State in this cores caches cache. A single snoop response from the core counts on all hyperthreads of the core.", - "SampleAfterValue": "1000003", - "UMask": "0x20" - }, - { - "BriefDescription": "HitM snoop reply with data, line invalidated.", - "Counter": "0,1,2,3", - "EventCode": "0xef", - "EventName": "CORE_SNOOP_RESPONSE.I_FWD_M", - "PublicDescription": "Counts responses to snoops indicating the line will now be (I)nvalidated: removed from this core's caches, after the data is forwarded back to the requestor, and indicating the data was found modified(M) in this cores caches cache (aka HitM response). A single snoop response from the core counts on all hyperthreads of the core.", - "SampleAfterValue": "1000003", - "UMask": "0x10" - }, - { - "BriefDescription": "Hit snoop reply without sending the data, line invalidated.", - "Counter": "0,1,2,3", - "EventCode": "0xef", - "EventName": "CORE_SNOOP_RESPONSE.I_HIT_FSE", - "PublicDescription": "Counts responses to snoops indicating the line will now be (I)nvalidated in this core's caches without being forwarded back to the requestor. The line was in Forward, Shared or Exclusive (FSE) state in this cores caches. A single snoop response from the core counts on all hyperthreads of the core.", - "SampleAfterValue": "1000003", - "UMask": "0x2" - }, - { - "BriefDescription": "Line not found snoop reply", - "Counter": "0,1,2,3", - "EventCode": "0xef", - "EventName": "CORE_SNOOP_RESPONSE.MISS", - "PublicDescription": "Counts responses to snoops indicating that the data was not found (IHitI) in this core's caches. A single snoop response from the core counts on all hyperthreads of the Core.", - "SampleAfterValue": "1000003", - "UMask": "0x1" - }, - { - "BriefDescription": "Hit snoop reply with data, line kept in Shared state.", - "Counter": "0,1,2,3", - "EventCode": "0xef", - "EventName": "CORE_SNOOP_RESPONSE.S_FWD_FE", - "PublicDescription": "Counts responses to snoops indicating the line may be kept on this core in the (S)hared state, after the data is forwarded back to the requestor, initially the data was found in the cache in the (FS) Forward or Shared state. A single snoop response from the core counts on all hyperthreads of the core.", - "SampleAfterValue": "1000003", - "UMask": "0x40" - }, - { - "BriefDescription": "HitM snoop reply with data, line kept in Shared state", - "Counter": "0,1,2,3", - "EventCode": "0xef", - "EventName": "CORE_SNOOP_RESPONSE.S_FWD_M", - "PublicDescription": "Counts responses to snoops indicating the line may be kept on this core in the (S)hared state, after the data is forwarded back to the requestor, initially the data was found in the cache in the (M)odified state. A single snoop response from the core counts on all hyperthreads of the core.", - "SampleAfterValue": "1000003", - "UMask": "0x8" - }, - { - "BriefDescription": "Hit snoop reply without sending the data, line kept in Shared state.", - "Counter": "0,1,2,3", - "EventCode": "0xef", - "EventName": "CORE_SNOOP_RESPONSE.S_HIT_FSE", - "PublicDescription": "Counts responses to snoops indicating the line was kept on this core in the (S)hared state, and that the data was found unmodified but not forwarded back to the requestor, initially the data was found in the cache in the (FSE) Forward, Shared state or Exclusive state. A single snoop response from the core counts on all hyperthreads of the core.", - "SampleAfterValue": "1000003", - "UMask": "0x4" - }, - { - "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that have any type of response.", - "Counter": "0,1,2,3", - "EventCode": "0xB7, 0xBB", - "EventName": "OCR.DEMAND_CODE_RD.ANY_RESPONSE", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x10004", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were supplied by DRAM.", - "Counter": "0,1,2,3", - "EventCode": "0xB7, 0xBB", - "EventName": "OCR.DEMAND_CODE_RD.DRAM", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x73C000004", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were supplied by DRAM attached to this socket, unless in Sub NUMA Cluster(SNC) Mode. In SNC Mode counts only those DRAM accesses that are controlled by the close SNC Cluster.", - "Counter": "0,1,2,3", - "EventCode": "0xB7, 0xBB", - "EventName": "OCR.DEMAND_CODE_RD.LOCAL_DRAM", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x104000004", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were supplied by DRAM on a distant memory controller of this socket when the system is in SNC (sub-NUMA cluster) mode.", - "Counter": "0,1,2,3", - "EventCode": "0xB7, 0xBB", - "EventName": "OCR.DEMAND_CODE_RD.SNC_DRAM", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x708000004", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts demand data reads that have any type of response.", - "Counter": "0,1,2,3", - "EventCode": "0xB7, 0xBB", - "EventName": "OCR.DEMAND_DATA_RD.ANY_RESPONSE", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x10001", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts demand data reads that were supplied by DRAM.", - "Counter": "0,1,2,3", - "EventCode": "0xB7, 0xBB", - "EventName": "OCR.DEMAND_DATA_RD.DRAM", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x73C000001", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts demand data reads that were supplied by DRAM attached to this socket, unless in Sub NUMA Cluster(SNC) Mode. In SNC Mode counts only those DRAM accesses that are controlled by the close SNC Cluster.", - "Counter": "0,1,2,3", - "EventCode": "0xB7, 0xBB", - "EventName": "OCR.DEMAND_DATA_RD.LOCAL_DRAM", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x104000001", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts demand data reads that were supplied by PMM attached to this socket, unless in Sub NUMA Cluster(SNC) Mode. In SNC Mode counts only those PMM accesses that are controlled by the close SNC Cluster.", - "Counter": "0,1,2,3", - "EventCode": "0xB7, 0xBB", - "EventName": "OCR.DEMAND_DATA_RD.LOCAL_PMM", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x100400001", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts demand data reads that were supplied by PMM.", - "Counter": "0,1,2,3", - "EventCode": "0xB7, 0xBB", - "EventName": "OCR.DEMAND_DATA_RD.PMM", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x703C00001", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts demand data reads that were supplied by DRAM attached to another socket.", - "Counter": "0,1,2,3", - "EventCode": "0xB7, 0xBB", - "EventName": "OCR.DEMAND_DATA_RD.REMOTE_DRAM", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x730000001", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts demand data reads that were supplied by PMM attached to another socket.", - "Counter": "0,1,2,3", - "EventCode": "0xB7, 0xBB", - "EventName": "OCR.DEMAND_DATA_RD.REMOTE_PMM", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x703000001", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts demand data reads that were supplied by DRAM on a distant memory controller of this socket when the system is in SNC (sub-NUMA cluster) mode.", - "Counter": "0,1,2,3", - "EventCode": "0xB7, 0xBB", - "EventName": "OCR.DEMAND_DATA_RD.SNC_DRAM", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x708000001", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts demand data reads that were supplied by PMM on a distant memory controller of this socket when the system is in SNC (sub-NUMA cluster) mode.", - "Counter": "0,1,2,3", - "EventCode": "0xB7, 0xBB", - "EventName": "OCR.DEMAND_DATA_RD.SNC_PMM", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x700800001", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts demand reads for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that have any type of response.", - "Counter": "0,1,2,3", - "EventCode": "0xB7, 0xBB", - "EventName": "OCR.DEMAND_RFO.ANY_RESPONSE", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x3F3FFC0002", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts demand reads for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that were supplied by DRAM.", - "Counter": "0,1,2,3", - "EventCode": "0xB7, 0xBB", - "EventName": "OCR.DEMAND_RFO.DRAM", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x73C000002", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts demand reads for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that were supplied by DRAM attached to this socket, unless in Sub NUMA Cluster(SNC) Mode. In SNC Mode counts only those DRAM accesses that are controlled by the close SNC Cluster.", - "Counter": "0,1,2,3", - "EventCode": "0xB7, 0xBB", - "EventName": "OCR.DEMAND_RFO.LOCAL_DRAM", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x104000002", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts demand reads for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that were supplied by PMM attached to this socket, unless in Sub NUMA Cluster(SNC) Mode. In SNC Mode counts only those PMM accesses that are controlled by the close SNC Cluster.", - "Counter": "0,1,2,3", - "EventCode": "0xB7, 0xBB", - "EventName": "OCR.DEMAND_RFO.LOCAL_PMM", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x100400002", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts demand reads for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that were supplied by PMM.", - "Counter": "0,1,2,3", - "EventCode": "0xB7, 0xBB", - "EventName": "OCR.DEMAND_RFO.PMM", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x703C00002", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts demand reads for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that were supplied by PMM attached to another socket.", - "Counter": "0,1,2,3", - "EventCode": "0xB7, 0xBB", - "EventName": "OCR.DEMAND_RFO.REMOTE_PMM", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x703000002", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts demand reads for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that were supplied by DRAM on a distant memory controller of this socket when the system is in SNC (sub-NUMA cluster) mode.", - "Counter": "0,1,2,3", - "EventCode": "0xB7, 0xBB", - "EventName": "OCR.DEMAND_RFO.SNC_DRAM", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x708000002", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts demand reads for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that were supplied by PMM on a distant memory controller of this socket when the system is in SNC (sub-NUMA cluster) mode.", - "Counter": "0,1,2,3", - "EventCode": "0xB7, 0xBB", - "EventName": "OCR.DEMAND_RFO.SNC_PMM", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x700800002", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts L1 data cache prefetch requests and software prefetches (except PREFETCHW) that were supplied by DRAM.", - "Counter": "0,1,2,3", - "EventCode": "0xB7, 0xBB", - "EventName": "OCR.HWPF_L1D_AND_SWPF.DRAM", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x73C000400", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts L1 data cache prefetch requests and software prefetches (except PREFETCHW) that were supplied by DRAM attached to this socket, unless in Sub NUMA Cluster(SNC) Mode. In SNC Mode counts only those DRAM accesses that are controlled by the close SNC Cluster.", - "Counter": "0,1,2,3", - "EventCode": "0xB7, 0xBB", - "EventName": "OCR.HWPF_L1D_AND_SWPF.LOCAL_DRAM", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x104000400", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts hardware prefetch (which bring data to L2) that have any type of response.", - "Counter": "0,1,2,3", - "EventCode": "0xB7, 0xBB", - "EventName": "OCR.HWPF_L2.ANY_RESPONSE", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x10070", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts hardware prefetches to the L3 only that have any type of response.", - "Counter": "0,1,2,3", - "EventCode": "0xB7, 0xBB", - "EventName": "OCR.HWPF_L3.ANY_RESPONSE", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x12380", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts hardware prefetches to the L3 only that were not supplied by the local socket's L1, L2, or L3 caches and the cacheline was homed in a remote socket.", - "Counter": "0,1,2,3", - "EventCode": "0xB7, 0xBB", - "EventName": "OCR.HWPF_L3.REMOTE", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x90002380", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts full cacheline writes (ItoM) that were not supplied by the local socket's L1, L2, or L3 caches and the cacheline was homed in a remote socket.", - "Counter": "0,1,2,3", - "EventCode": "0xB7, 0xBB", - "EventName": "OCR.ITOM.REMOTE", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x90000002", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { "BriefDescription": "Counts miscellaneous requests, such as I/O and un-cacheable accesses that have any type of response.", "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -370,126 +37,6 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that have any type of response.", - "Counter": "0,1,2,3", - "EventCode": "0xB7, 0xBB", - "EventName": "OCR.READS_TO_CORE.ANY_RESPONSE", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x3F3FFC0477", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by DRAM.", - "Counter": "0,1,2,3", - "EventCode": "0xB7, 0xBB", - "EventName": "OCR.READS_TO_CORE.DRAM", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x73C000477", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by DRAM attached to this socket, unless in Sub NUMA Cluster(SNC) Mode. In SNC Mode counts only those DRAM accesses that are controlled by the close SNC Cluster.", - "Counter": "0,1,2,3", - "EventCode": "0xB7, 0xBB", - "EventName": "OCR.READS_TO_CORE.LOCAL_DRAM", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x104000477", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by PMM attached to this socket, unless in Sub NUMA Cluster(SNC) Mode. In SNC Mode counts only those PMM accesses that are controlled by the close SNC Cluster.", - "Counter": "0,1,2,3", - "EventCode": "0xB7, 0xBB", - "EventName": "OCR.READS_TO_CORE.LOCAL_PMM", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x100400477", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by DRAM attached to this socket, whether or not in Sub NUMA Cluster(SNC) Mode. In SNC Mode counts DRAM accesses that are controlled by the close or distant SNC Cluster.", - "Counter": "0,1,2,3", - "EventCode": "0xB7, 0xBB", - "EventName": "OCR.READS_TO_CORE.LOCAL_SOCKET_DRAM", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x70C000477", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by PMM attached to this socket, whether or not in Sub NUMA Cluster(SNC) Mode. In SNC Mode counts PMM accesses that are controlled by the close or distant SNC Cluster.", - "Counter": "0,1,2,3", - "EventCode": "0xB7, 0xBB", - "EventName": "OCR.READS_TO_CORE.LOCAL_SOCKET_PMM", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x700C00477", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were not supplied by the local socket's L1, L2, or L3 caches and were supplied by a remote socket.", - "Counter": "0,1,2,3", - "EventCode": "0xB7, 0xBB", - "EventName": "OCR.READS_TO_CORE.REMOTE", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x3F33000477", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by DRAM attached to another socket.", - "Counter": "0,1,2,3", - "EventCode": "0xB7, 0xBB", - "EventName": "OCR.READS_TO_CORE.REMOTE_DRAM", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x730000477", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by DRAM or PMM attached to another socket.", - "Counter": "0,1,2,3", - "EventCode": "0xB7, 0xBB", - "EventName": "OCR.READS_TO_CORE.REMOTE_MEMORY", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x731800477", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by PMM attached to another socket.", - "Counter": "0,1,2,3", - "EventCode": "0xB7, 0xBB", - "EventName": "OCR.READS_TO_CORE.REMOTE_PMM", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x703000477", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by DRAM on a distant memory controller of this socket when the system is in SNC (sub-NUMA cluster) mode.", - "Counter": "0,1,2,3", - "EventCode": "0xB7, 0xBB", - "EventName": "OCR.READS_TO_CORE.SNC_DRAM", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x708000477", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by PMM on a distant memory controller of this socket when the system is in SNC (sub-NUMA cluster) mode.", - "Counter": "0,1,2,3", - "EventCode": "0xB7, 0xBB", - "EventName": "OCR.READS_TO_CORE.SNC_PMM", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x700800477", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { "BriefDescription": "Counts streaming stores that have any type of response.", "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -498,15 +45,5 @@ "MSRValue": "0x10800", "SampleAfterValue": "100003", "UMask": "0x1" - }, - { - "BriefDescription": "Counts Demand RFOs, ItoM's, PREFECTHW's, Hardware RFO Prefetches to the L1/L2 and Streaming stores that likely resulted in a store to Memory (DRAM or PMM)", - "Counter": "0,1,2,3", - "EventCode": "0xB7, 0xBB", - "EventName": "OCR.WRITE_ESTIMATE.MEMORY", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0xFBFF80822", - "SampleAfterValue": "100003", - "UMask": "0x1" } ] diff --git a/tools/perf/pmu-events/arch/x86/ivybridge/ivb-metrics.json b/tools/perf/pmu-events/arch/x86/ivybridge/ivb-metrics.json index 77d37db98b70..de651ff9f846 100644 --- a/tools/perf/pmu-events/arch/x86/ivybridge/ivb-metrics.json +++ b/tools/perf/pmu-events/arch/x86/ivybridge/ivb-metrics.json @@ -151,7 +151,7 @@ "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses", "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "(60 * (MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_HITM * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.LLC_HIT + MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_RETIRED.LLC_MISS))) + 43 * (MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_MISS * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.LLC_HIT + MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_RETIRED.LLC_MISS)))) / tma_info_thread_clks", - "MetricGroup": "BvMS;DataSharing;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group", + "MetricGroup": "BvMS;DataSharing;LockCont;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group", "MetricName": "tma_contested_accesses", "MetricThreshold": "tma_contested_accesses > 0.05 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses. Contested accesses occur when data written by one Logical Processor are read by another Logical Processor on a different Physical Core. Examples of contested accesses include synchronizations such as locks; true data sharing such as modified locked variables; and false sharing. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM_PS;MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS_PS. Related metrics: tma_data_sharing, tma_false_sharing, tma_machine_clears, tma_remote_cache", @@ -184,7 +184,7 @@ "MetricGroup": "BvCB;TopdownL3;tma_L3_group;tma_core_bound_group", "MetricName": "tma_divider", "MetricThreshold": "tma_divider > 0.2 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)", - "PublicDescription": "This metric represents fraction of cycles where the Divider unit was active. Divide and square root instructions are performed by the Divider unit and can take considerably longer latency than integer or Floating Point addition; subtraction; or multiplication. Sample with: ARITH.DIVIDER_UOPS", + "PublicDescription": "This metric represents fraction of cycles where the Divider unit was active. Divide and square root instructions are performed by the Divider unit and can take considerably longer latency than integer or Floating Point addition; subtraction; or multiplication. Sample with: ARITH.DIVIDER_ACTIVE", "ScaleUnit": "100%" }, { @@ -236,7 +236,7 @@ { "BriefDescription": "This metric roughly estimates how often CPU was handling synchronizations due to False Sharing", "MetricExpr": "60 * OFFCORE_RESPONSE.DEMAND_RFO.LLC_HIT.HITM_OTHER_CORE / tma_info_thread_clks", - "MetricGroup": "BvMS;DataSharing;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_store_bound_group", + "MetricGroup": "BvMS;DataSharing;LockCont;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_store_bound_group", "MetricName": "tma_false_sharing", "MetricThreshold": "tma_false_sharing > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", "PublicDescription": "This metric roughly estimates how often CPU was handling synchronizations due to False Sharing. False Sharing is a multithreading hiccup; where multiple Logical Processors contend on different data-elements mapped into the same cache line. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM_PS;OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.SNOOP_HITM. Related metrics: tma_contested_accesses, tma_data_sharing, tma_machine_clears, tma_remote_cache", @@ -246,7 +246,7 @@ "BriefDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed", "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "tma_info_memory_load_miss_real_latency * cpu@L1D_PEND_MISS.FB_FULL\\,cmask\\=1@ / tma_info_thread_clks", - "MetricGroup": "BvMS;MemoryBW;TopdownL4;tma_L4_group;tma_issueBW;tma_issueSL;tma_issueSmSt;tma_l1_bound_group", + "MetricGroup": "BvMB;MemoryBW;TopdownL4;tma_L4_group;tma_issueBW;tma_issueSL;tma_issueSmSt;tma_l1_bound_group", "MetricName": "tma_fb_full", "MetricThreshold": "tma_fb_full > 0.3", "PublicDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed. The higher the metric value; the deeper the memory hierarchy level the misses are satisfied from (metric values >1 are valid). Often it hints on approaching bandwidth limits (to L2 cache; L3 cache or external memory). Related metrics: tma_info_system_dram_bw_use, tma_mem_bandwidth, tma_sq_full, tma_store_latency, tma_streaming_stores", @@ -305,7 +305,7 @@ "MetricGroup": "Compute;Flops;TopdownL5;tma_L5_group;tma_fp_vector_group;tma_issue2P", "MetricName": "tma_fp_vector_128b", "MetricThreshold": "tma_fp_vector_128b > 0.1 & (tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6))", - "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 128-bit wide vectors. May overcount due to FMA double counting. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", + "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 128-bit wide vectors. May overcount due to FMA double counting prior to LNL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%" }, { @@ -314,7 +314,7 @@ "MetricGroup": "Compute;Flops;TopdownL5;tma_L5_group;tma_fp_vector_group;tma_issue2P", "MetricName": "tma_fp_vector_256b", "MetricThreshold": "tma_fp_vector_256b > 0.1 & (tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6))", - "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 256-bit wide vectors. May overcount due to FMA double counting. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", + "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 256-bit wide vectors. May overcount due to FMA double counting prior to LNL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%" }, { @@ -334,7 +334,7 @@ "MetricName": "tma_heavy_operations", "MetricThreshold": "tma_heavy_operations > 0.1", "MetricgroupNoGroup": "TopdownL2", - "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences. ([ICL+] Note this may overcount due to approximation using indirect events; [ADL+] .)", + "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences.([ICL+] Note this may overcount due to approximation using indirect events; [ADL+])", "ScaleUnit": "100%" }, { @@ -346,7 +346,7 @@ "ScaleUnit": "100%" }, { - "BriefDescription": "Instructions per retired mispredicts for indirect CALL or JMP branches (lower number means higher occurrence rate).", + "BriefDescription": "Instructions per retired Mispredicts for indirect CALL or JMP branches (lower number means higher occurrence rate).", "MetricExpr": "tma_info_inst_mix_instructions / (UOPS_RETIRED.RETIRE_SLOTS / UOPS_ISSUED.ANY * BR_MISP_EXEC.INDIRECT)", "MetricGroup": "Bad;BrMispredicts", "MetricName": "tma_info_bad_spec_ipmisp_indirect", @@ -398,6 +398,12 @@ "MetricName": "tma_info_frontend_ipunknown_branch" }, { + "BriefDescription": "Taken Branches retired Per Cycle", + "MetricExpr": "BR_INST_RETIRED.NEAR_TAKEN / tma_info_thread_clks", + "MetricGroup": "Branches;FetchBW", + "MetricName": "tma_info_frontend_tbpc" + }, + { "BriefDescription": "Branch instructions per taken branch.", "MetricExpr": "BR_INST_RETIRED.ALL_BRANCHES / BR_INST_RETIRED.NEAR_TAKEN", "MetricGroup": "Branches;Fed;PGO", @@ -474,7 +480,7 @@ }, { "BriefDescription": "Average per-thread data fill bandwidth to the L1 data cache [GB / sec]", - "MetricExpr": "64 * L1D.REPLACEMENT / 1e9 / duration_time", + "MetricExpr": "64 * L1D.REPLACEMENT / 1e9 / tma_info_system_time", "MetricGroup": "Mem;MemoryBW", "MetricName": "tma_info_memory_l1d_cache_fill_bw" }, @@ -486,7 +492,7 @@ }, { "BriefDescription": "Average per-thread data fill bandwidth to the L2 cache [GB / sec]", - "MetricExpr": "64 * L2_LINES_IN.ALL / 1e9 / duration_time", + "MetricExpr": "64 * L2_LINES_IN.ALL / 1e9 / tma_info_system_time", "MetricGroup": "Mem;MemoryBW", "MetricName": "tma_info_memory_l2_cache_fill_bw" }, @@ -504,7 +510,7 @@ }, { "BriefDescription": "Average per-thread data fill bandwidth to the L3 cache [GB / sec]", - "MetricExpr": "64 * LONGEST_LAT_CACHE.MISS / 1e9 / duration_time", + "MetricExpr": "64 * LONGEST_LAT_CACHE.MISS / 1e9 / tma_info_system_time", "MetricGroup": "Mem;MemoryBW", "MetricName": "tma_info_memory_l3_cache_fill_bw" }, @@ -523,7 +529,7 @@ { "BriefDescription": "Average Latency for L2 cache miss demand Loads", "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD / OFFCORE_REQUESTS.DEMAND_DATA_RD", - "MetricGroup": "Memory_Lat;Offcore", + "MetricGroup": "LockCont;Memory_Lat;Offcore", "MetricName": "tma_info_memory_latency_load_l2_miss_latency" }, { @@ -555,7 +561,7 @@ "MetricThreshold": "tma_info_memory_tlb_page_walks_utilization > 0.5" }, { - "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is execution) per core", + "BriefDescription": "", "MetricExpr": "UOPS_EXECUTED.THREAD / (cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ / 2 if #SMT_on else UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC)", "MetricGroup": "Cor;Pipeline;PortsUtil;SMT", "MetricName": "tma_info_pipeline_execute" @@ -568,7 +574,7 @@ }, { "BriefDescription": "Measured Average Core Frequency for unhalted processors [GHz]", - "MetricExpr": "tma_info_system_turbo_utilization * TSC / 1e9 / duration_time", + "MetricExpr": "tma_info_system_turbo_utilization * TSC / 1e9 / tma_info_system_time", "MetricGroup": "Power;Summary", "MetricName": "tma_info_system_core_frequency" }, @@ -586,14 +592,14 @@ }, { "BriefDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]", - "MetricExpr": "64 * (UNC_ARB_TRK_REQUESTS.ALL + UNC_ARB_COH_TRK_REQUESTS.ALL) / 1e6 / duration_time / 1e3", + "MetricExpr": "64 * (UNC_ARB_TRK_REQUESTS.ALL + UNC_ARB_COH_TRK_REQUESTS.ALL) / 1e6 / tma_info_system_time / 1e3", "MetricGroup": "HPC;MemOffcore;MemoryBW;SoC;tma_issueBW", "MetricName": "tma_info_system_dram_bw_use", "PublicDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]. Related metrics: tma_fb_full, tma_mem_bandwidth, tma_sq_full" }, { "BriefDescription": "Giga Floating Point Operations Per Second", - "MetricExpr": "(FP_COMP_OPS_EXE.SSE_SCALAR_SINGLE + FP_COMP_OPS_EXE.SSE_SCALAR_DOUBLE + 2 * FP_COMP_OPS_EXE.SSE_PACKED_DOUBLE + 4 * (FP_COMP_OPS_EXE.SSE_PACKED_SINGLE + SIMD_FP_256.PACKED_DOUBLE) + 8 * SIMD_FP_256.PACKED_SINGLE) / 1e9 / duration_time", + "MetricExpr": "(FP_COMP_OPS_EXE.SSE_SCALAR_SINGLE + FP_COMP_OPS_EXE.SSE_SCALAR_DOUBLE + 2 * FP_COMP_OPS_EXE.SSE_PACKED_DOUBLE + 4 * (FP_COMP_OPS_EXE.SSE_PACKED_SINGLE + SIMD_FP_256.PACKED_DOUBLE) + 8 * SIMD_FP_256.PACKED_SINGLE) / 1e9 / tma_info_system_time", "MetricGroup": "Cor;Flops;HPC", "MetricName": "tma_info_system_gflops", "PublicDescription": "Giga Floating Point Operations Per Second. Aggregate across all supported options of: FP precisions, scalar and vector instructions, vector-width" @@ -619,6 +625,19 @@ "MetricThreshold": "tma_info_system_kernel_utilization > 0.05" }, { + "BriefDescription": "PerfMon Event Multiplexing accuracy indicator", + "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P / CPU_CLK_UNHALTED.THREAD", + "MetricGroup": "Summary", + "MetricName": "tma_info_system_mux", + "MetricThreshold": "tma_info_system_mux > 1.1 | tma_info_system_mux < 0.9" + }, + { + "BriefDescription": "Total package Power in Watts", + "MetricExpr": "power@energy\\-pkg@ * 15.6 / (tma_info_system_time * 1e6)", + "MetricGroup": "Power;SoC", + "MetricName": "tma_info_system_power" + }, + { "BriefDescription": "Fraction of cycles where both hardware Logical Processors were active", "MetricExpr": "(1 - CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / (CPU_CLK_UNHALTED.REF_XCLK_ANY / 2) if #SMT_on else 0)", "MetricGroup": "SMT", @@ -631,6 +650,13 @@ "MetricName": "tma_info_system_socket_clks" }, { + "BriefDescription": "Run duration time in seconds", + "MetricExpr": "duration_time", + "MetricGroup": "Summary", + "MetricName": "tma_info_system_time", + "MetricThreshold": "tma_info_system_time < 1" + }, + { "BriefDescription": "Average Frequency Utilization relative nominal frequency", "MetricExpr": "tma_info_thread_clks / CPU_CLK_UNHALTED.REF_TSC", "MetricGroup": "Power", @@ -691,12 +717,12 @@ "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates how often the CPU was stalled without loads missing the L1 data cache", + "BriefDescription": "This metric estimates how often the CPU was stalled without loads missing the L1 Data (L1D) cache", "MetricExpr": "max((min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.STALLS_LDM_PENDING) - CYCLE_ACTIVITY.STALLS_L1D_PENDING) / tma_info_thread_clks, 0)", "MetricGroup": "CacheHits;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_issueL1;tma_issueMC;tma_memory_bound_group", "MetricName": "tma_l1_bound", "MetricThreshold": "tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", - "PublicDescription": "This metric estimates how often the CPU was stalled without loads missing the L1 data cache. The L1 data cache typically has the shortest latency. However; in certain cases like loads blocked on older stores; a load might suffer due to high latency even though it is being satisfied by the L1. Another example is loads who miss in the TLB. These cases are characterized by execution unit stalls; while some non-completed demand load lives in the machine without having that demand load missing the L1 cache. Sample with: MEM_LOAD_UOPS_RETIRED.L1_HIT_PS;MEM_LOAD_UOPS_RETIRED.HIT_LFB_PS. Related metrics: tma_clears_resteers, tma_machine_clears, tma_microcode_sequencer, tma_ms_switches, tma_ports_utilized_1", + "PublicDescription": "This metric estimates how often the CPU was stalled without loads missing the L1 Data (L1D) cache. The L1D cache typically has the shortest latency. However; in certain cases like loads blocked on older stores; a load might suffer due to high latency even though it is being satisfied by the L1D. Another example is loads who miss in the TLB. These cases are characterized by execution unit stalls; while some non-completed demand load lives in the machine without having that demand load missing the L1 cache. Sample with: MEM_LOAD_UOPS_RETIRED.L1_HIT_PS. Related metrics: tma_clears_resteers, tma_machine_clears, tma_microcode_sequencer, tma_ms_switches, tma_ports_utilized_1", "ScaleUnit": "100%" }, { @@ -761,7 +787,7 @@ "BriefDescription": "This metric represents fraction of cycles the CPU spent handling cache misses due to lock operations", "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "MEM_UOPS_RETIRED.LOCK_LOADS / MEM_UOPS_RETIRED.ALL_STORES * min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO) / tma_info_thread_clks", - "MetricGroup": "Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_l1_bound_group", + "MetricGroup": "LockCont;Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_l1_bound_group", "MetricName": "tma_lock_latency", "MetricThreshold": "tma_lock_latency > 0.2 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", "PublicDescription": "This metric represents fraction of cycles the CPU spent handling cache misses due to lock operations. Due to the microarchitecture handling of locks; they are classified as L1_Bound regardless of what memory source satisfied them. Sample with: MEM_UOPS_RETIRED.LOCK_LOADS_PS. Related metrics: tma_store_latency", @@ -781,7 +807,7 @@ { "BriefDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory - DRAM ([SPR-HBM] and/or HBM)", "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, cpu@OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD\\,cmask\\=6@) / tma_info_thread_clks", - "MetricGroup": "BvMS;MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueBW", + "MetricGroup": "BvMB;MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueBW", "MetricName": "tma_mem_bandwidth", "MetricThreshold": "tma_mem_bandwidth > 0.2 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", "PublicDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory - DRAM ([SPR-HBM] and/or HBM). The underlying heuristic assumes that a similar off-core traffic is generated by all IA cores. This metric does not aggregate non-data-read requests by this logical processor; requests from other IA Logical Processors/Physical Cores/sockets; or other non-IA devices like GPU; hence the maximum external memory bandwidth limits may or may not be approached when this metric is flagged (see Uncore counters for that). Related metrics: tma_fb_full, tma_info_system_dram_bw_use, tma_sq_full", @@ -840,7 +866,7 @@ "MetricGroup": "Compute;TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P", "MetricName": "tma_port_0", "MetricThreshold": "tma_port_0 > 0.6", - "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 0 ([SNB+] ALU; [HSW+] ALU and 2nd branch). Sample with: UOPS_DISPATCHED_PORT.PORT_0. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", + "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 0 ([SNB+] ALU; [HSW+] ALU and 2nd branch). Sample with: UOPS_DISPATCHED.PORT_0. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%" }, { @@ -849,7 +875,7 @@ "MetricGroup": "TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P", "MetricName": "tma_port_1", "MetricThreshold": "tma_port_1 > 0.6", - "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 1 (ALU). Sample with: UOPS_DISPATCHED_PORT.PORT_1. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_5, tma_port_6, tma_ports_utilized_2", + "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 1 (ALU). Sample with: UOPS_DISPATCHED.PORT_1. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_5, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%" }, { @@ -949,7 +975,7 @@ "MetricExpr": "13 * LD_BLOCKS.NO_SR / tma_info_thread_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group", "MetricName": "tma_split_loads", - "MetricThreshold": "tma_split_loads > 0.2 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "MetricThreshold": "tma_split_loads > 0.3", "PublicDescription": "This metric estimates fraction of cycles handling memory load split accesses - load that cross 64-byte cache line boundary. Sample with: MEM_UOPS_RETIRED.SPLIT_LOADS_PS", "ScaleUnit": "100%" }, @@ -965,7 +991,7 @@ { "BriefDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors)", "MetricExpr": "(OFFCORE_REQUESTS_BUFFER.SQ_FULL / 2 if #SMT_on else OFFCORE_REQUESTS_BUFFER.SQ_FULL) / tma_info_core_core_clks", - "MetricGroup": "BvMS;MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_issueBW;tma_l3_bound_group", + "MetricGroup": "BvMB;MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_issueBW;tma_l3_bound_group", "MetricName": "tma_sq_full", "MetricThreshold": "tma_sq_full > 0.3 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", "PublicDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors). Related metrics: tma_fb_full, tma_info_system_dram_bw_use, tma_mem_bandwidth", @@ -993,7 +1019,7 @@ "BriefDescription": "This metric estimates fraction of cycles the CPU spent handling L1D store misses", "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "(L2_RQSTS.RFO_HIT * 9 * (1 - MEM_UOPS_RETIRED.LOCK_LOADS / MEM_UOPS_RETIRED.ALL_STORES) + (1 - MEM_UOPS_RETIRED.LOCK_LOADS / MEM_UOPS_RETIRED.ALL_STORES) * min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO)) / tma_info_thread_clks", - "MetricGroup": "BvML;MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_issueSL;tma_store_bound_group", + "MetricGroup": "BvML;LockCont;MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_issueSL;tma_store_bound_group", "MetricName": "tma_store_latency", "MetricThreshold": "tma_store_latency > 0.1 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", "PublicDescription": "This metric estimates fraction of cycles the CPU spent handling L1D store misses. Store accesses usually less impact out-of-order core performance; however; holding resources for longer time can lead into undesired implications (e.g. contention on L1D fill-buffer entries - see FB_Full). Related metrics: tma_fb_full, tma_lock_latency", diff --git a/tools/perf/pmu-events/arch/x86/ivybridge/metricgroups.json b/tools/perf/pmu-events/arch/x86/ivybridge/metricgroups.json index 4193c90c3459..0863375bdead 100644 --- a/tools/perf/pmu-events/arch/x86/ivybridge/metricgroups.json +++ b/tools/perf/pmu-events/arch/x86/ivybridge/metricgroups.json @@ -9,6 +9,7 @@ "BvCB": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", "BvFB": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", "BvIO": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "BvMB": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", "BvML": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", "BvMP": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", "BvMS": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", @@ -34,6 +35,7 @@ "InsType": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", "L2Evicts": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", "LSD": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "LockCont": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", "MachineClears": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", "Machine_Clears": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", "Mem": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", @@ -51,6 +53,7 @@ "Pipeline": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", "PortsUtil": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", "Power": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Prefetches": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", "Ret": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", "Retire": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", "SMT": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", @@ -78,6 +81,7 @@ "tma_bad_speculation_group": "Metrics contributing to tma_bad_speculation category", "tma_branch_resteers_group": "Metrics contributing to tma_branch_resteers category", "tma_core_bound_group": "Metrics contributing to tma_core_bound category", + "tma_divider_group": "Metrics contributing to tma_divider category", "tma_dram_bound_group": "Metrics contributing to tma_dram_bound category", "tma_dtlb_load_group": "Metrics contributing to tma_dtlb_load category", "tma_dtlb_store_group": "Metrics contributing to tma_dtlb_store category", @@ -103,6 +107,7 @@ "tma_issueSpSt": "Metrics related by the issue $issueSpSt", "tma_issueSyncxn": "Metrics related by the issue $issueSyncxn", "tma_issueTLB": "Metrics related by the issue $issueTLB", + "tma_itlb_misses_group": "Metrics contributing to tma_itlb_misses category", "tma_l1_bound_group": "Metrics contributing to tma_l1_bound category", "tma_l3_bound_group": "Metrics contributing to tma_l3_bound category", "tma_light_operations_group": "Metrics contributing to tma_light_operations category", diff --git a/tools/perf/pmu-events/arch/x86/ivytown/ivt-metrics.json b/tools/perf/pmu-events/arch/x86/ivytown/ivt-metrics.json index 8fe0512c938f..714d5e6d21e7 100644 --- a/tools/perf/pmu-events/arch/x86/ivytown/ivt-metrics.json +++ b/tools/perf/pmu-events/arch/x86/ivytown/ivt-metrics.json @@ -151,7 +151,7 @@ "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses", "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "(60 * (MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_HITM * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.LLC_HIT + MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_LLC_MISS_RETIRED.LOCAL_DRAM + MEM_LOAD_UOPS_LLC_MISS_RETIRED.REMOTE_DRAM + MEM_LOAD_UOPS_LLC_MISS_RETIRED.REMOTE_HITM + MEM_LOAD_UOPS_LLC_MISS_RETIRED.REMOTE_FWD))) + 43 * (MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_MISS * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.LLC_HIT + MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_LLC_MISS_RETIRED.LOCAL_DRAM + MEM_LOAD_UOPS_LLC_MISS_RETIRED.REMOTE_DRAM + MEM_LOAD_UOPS_LLC_MISS_RETIRED.REMOTE_HITM + MEM_LOAD_UOPS_LLC_MISS_RETIRED.REMOTE_FWD)))) / tma_info_thread_clks", - "MetricGroup": "BvMS;DataSharing;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group", + "MetricGroup": "BvMS;DataSharing;LockCont;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group", "MetricName": "tma_contested_accesses", "MetricThreshold": "tma_contested_accesses > 0.05 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses. Contested accesses occur when data written by one Logical Processor are read by another Logical Processor on a different Physical Core. Examples of contested accesses include synchronizations such as locks; true data sharing such as modified locked variables; and false sharing. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM_PS;MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS_PS. Related metrics: tma_data_sharing, tma_false_sharing, tma_machine_clears, tma_remote_cache", @@ -184,7 +184,7 @@ "MetricGroup": "BvCB;TopdownL3;tma_L3_group;tma_core_bound_group", "MetricName": "tma_divider", "MetricThreshold": "tma_divider > 0.2 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)", - "PublicDescription": "This metric represents fraction of cycles where the Divider unit was active. Divide and square root instructions are performed by the Divider unit and can take considerably longer latency than integer or Floating Point addition; subtraction; or multiplication. Sample with: ARITH.DIVIDER_UOPS", + "PublicDescription": "This metric represents fraction of cycles where the Divider unit was active. Divide and square root instructions are performed by the Divider unit and can take considerably longer latency than integer or Floating Point addition; subtraction; or multiplication. Sample with: ARITH.DIVIDER_ACTIVE", "ScaleUnit": "100%" }, { @@ -236,7 +236,7 @@ { "BriefDescription": "This metric roughly estimates how often CPU was handling synchronizations due to False Sharing", "MetricExpr": "(200 * OFFCORE_RESPONSE.DEMAND_RFO.LLC_MISS.REMOTE_HITM + 60 * OFFCORE_RESPONSE.DEMAND_RFO.LLC_HIT.HITM_OTHER_CORE) / tma_info_thread_clks", - "MetricGroup": "BvMS;DataSharing;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_store_bound_group", + "MetricGroup": "BvMS;DataSharing;LockCont;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_store_bound_group", "MetricName": "tma_false_sharing", "MetricThreshold": "tma_false_sharing > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", "PublicDescription": "This metric roughly estimates how often CPU was handling synchronizations due to False Sharing. False Sharing is a multithreading hiccup; where multiple Logical Processors contend on different data-elements mapped into the same cache line. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM_PS;OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.SNOOP_HITM. Related metrics: tma_contested_accesses, tma_data_sharing, tma_machine_clears, tma_remote_cache", @@ -246,7 +246,7 @@ "BriefDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed", "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "tma_info_memory_load_miss_real_latency * cpu@L1D_PEND_MISS.FB_FULL\\,cmask\\=1@ / tma_info_thread_clks", - "MetricGroup": "BvMS;MemoryBW;TopdownL4;tma_L4_group;tma_issueBW;tma_issueSL;tma_issueSmSt;tma_l1_bound_group", + "MetricGroup": "BvMB;MemoryBW;TopdownL4;tma_L4_group;tma_issueBW;tma_issueSL;tma_issueSmSt;tma_l1_bound_group", "MetricName": "tma_fb_full", "MetricThreshold": "tma_fb_full > 0.3", "PublicDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed. The higher the metric value; the deeper the memory hierarchy level the misses are satisfied from (metric values >1 are valid). Often it hints on approaching bandwidth limits (to L2 cache; L3 cache or external memory). Related metrics: tma_info_system_dram_bw_use, tma_mem_bandwidth, tma_sq_full, tma_store_latency, tma_streaming_stores", @@ -305,7 +305,7 @@ "MetricGroup": "Compute;Flops;TopdownL5;tma_L5_group;tma_fp_vector_group;tma_issue2P", "MetricName": "tma_fp_vector_128b", "MetricThreshold": "tma_fp_vector_128b > 0.1 & (tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6))", - "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 128-bit wide vectors. May overcount due to FMA double counting. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", + "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 128-bit wide vectors. May overcount due to FMA double counting prior to LNL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%" }, { @@ -314,7 +314,7 @@ "MetricGroup": "Compute;Flops;TopdownL5;tma_L5_group;tma_fp_vector_group;tma_issue2P", "MetricName": "tma_fp_vector_256b", "MetricThreshold": "tma_fp_vector_256b > 0.1 & (tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6))", - "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 256-bit wide vectors. May overcount due to FMA double counting. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", + "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 256-bit wide vectors. May overcount due to FMA double counting prior to LNL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%" }, { @@ -334,7 +334,7 @@ "MetricName": "tma_heavy_operations", "MetricThreshold": "tma_heavy_operations > 0.1", "MetricgroupNoGroup": "TopdownL2", - "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences. ([ICL+] Note this may overcount due to approximation using indirect events; [ADL+] .)", + "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences.([ICL+] Note this may overcount due to approximation using indirect events; [ADL+])", "ScaleUnit": "100%" }, { @@ -346,7 +346,7 @@ "ScaleUnit": "100%" }, { - "BriefDescription": "Instructions per retired mispredicts for indirect CALL or JMP branches (lower number means higher occurrence rate).", + "BriefDescription": "Instructions per retired Mispredicts for indirect CALL or JMP branches (lower number means higher occurrence rate).", "MetricExpr": "tma_info_inst_mix_instructions / (UOPS_RETIRED.RETIRE_SLOTS / UOPS_ISSUED.ANY * BR_MISP_EXEC.INDIRECT)", "MetricGroup": "Bad;BrMispredicts", "MetricName": "tma_info_bad_spec_ipmisp_indirect", @@ -398,6 +398,12 @@ "MetricName": "tma_info_frontend_ipunknown_branch" }, { + "BriefDescription": "Taken Branches retired Per Cycle", + "MetricExpr": "BR_INST_RETIRED.NEAR_TAKEN / tma_info_thread_clks", + "MetricGroup": "Branches;FetchBW", + "MetricName": "tma_info_frontend_tbpc" + }, + { "BriefDescription": "Branch instructions per taken branch.", "MetricExpr": "BR_INST_RETIRED.ALL_BRANCHES / BR_INST_RETIRED.NEAR_TAKEN", "MetricGroup": "Branches;Fed;PGO", @@ -474,7 +480,7 @@ }, { "BriefDescription": "Average per-thread data fill bandwidth to the L1 data cache [GB / sec]", - "MetricExpr": "64 * L1D.REPLACEMENT / 1e9 / duration_time", + "MetricExpr": "64 * L1D.REPLACEMENT / 1e9 / tma_info_system_time", "MetricGroup": "Mem;MemoryBW", "MetricName": "tma_info_memory_l1d_cache_fill_bw" }, @@ -486,7 +492,7 @@ }, { "BriefDescription": "Average per-thread data fill bandwidth to the L2 cache [GB / sec]", - "MetricExpr": "64 * L2_LINES_IN.ALL / 1e9 / duration_time", + "MetricExpr": "64 * L2_LINES_IN.ALL / 1e9 / tma_info_system_time", "MetricGroup": "Mem;MemoryBW", "MetricName": "tma_info_memory_l2_cache_fill_bw" }, @@ -504,7 +510,7 @@ }, { "BriefDescription": "Average per-thread data fill bandwidth to the L3 cache [GB / sec]", - "MetricExpr": "64 * LONGEST_LAT_CACHE.MISS / 1e9 / duration_time", + "MetricExpr": "64 * LONGEST_LAT_CACHE.MISS / 1e9 / tma_info_system_time", "MetricGroup": "Mem;MemoryBW", "MetricName": "tma_info_memory_l3_cache_fill_bw" }, @@ -523,7 +529,7 @@ { "BriefDescription": "Average Latency for L2 cache miss demand Loads", "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD / OFFCORE_REQUESTS.DEMAND_DATA_RD", - "MetricGroup": "Memory_Lat;Offcore", + "MetricGroup": "LockCont;Memory_Lat;Offcore", "MetricName": "tma_info_memory_latency_load_l2_miss_latency" }, { @@ -555,7 +561,7 @@ "MetricThreshold": "tma_info_memory_tlb_page_walks_utilization > 0.5" }, { - "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is execution) per core", + "BriefDescription": "", "MetricExpr": "UOPS_EXECUTED.THREAD / (cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ / 2 if #SMT_on else UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC)", "MetricGroup": "Cor;Pipeline;PortsUtil;SMT", "MetricName": "tma_info_pipeline_execute" @@ -568,7 +574,7 @@ }, { "BriefDescription": "Measured Average Core Frequency for unhalted processors [GHz]", - "MetricExpr": "tma_info_system_turbo_utilization * TSC / 1e9 / duration_time", + "MetricExpr": "tma_info_system_turbo_utilization * TSC / 1e9 / tma_info_system_time", "MetricGroup": "Power;Summary", "MetricName": "tma_info_system_core_frequency" }, @@ -586,14 +592,14 @@ }, { "BriefDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]", - "MetricExpr": "64 * (UNC_M_CAS_COUNT.RD + UNC_M_CAS_COUNT.WR) / 1e9 / duration_time", + "MetricExpr": "64 * (UNC_M_CAS_COUNT.RD + UNC_M_CAS_COUNT.WR) / 1e9 / tma_info_system_time", "MetricGroup": "HPC;MemOffcore;MemoryBW;SoC;tma_issueBW", "MetricName": "tma_info_system_dram_bw_use", "PublicDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]. Related metrics: tma_fb_full, tma_mem_bandwidth, tma_sq_full" }, { "BriefDescription": "Giga Floating Point Operations Per Second", - "MetricExpr": "(FP_COMP_OPS_EXE.SSE_SCALAR_SINGLE + FP_COMP_OPS_EXE.SSE_SCALAR_DOUBLE + 2 * FP_COMP_OPS_EXE.SSE_PACKED_DOUBLE + 4 * (FP_COMP_OPS_EXE.SSE_PACKED_SINGLE + SIMD_FP_256.PACKED_DOUBLE) + 8 * SIMD_FP_256.PACKED_SINGLE) / 1e9 / duration_time", + "MetricExpr": "(FP_COMP_OPS_EXE.SSE_SCALAR_SINGLE + FP_COMP_OPS_EXE.SSE_SCALAR_DOUBLE + 2 * FP_COMP_OPS_EXE.SSE_PACKED_DOUBLE + 4 * (FP_COMP_OPS_EXE.SSE_PACKED_SINGLE + SIMD_FP_256.PACKED_DOUBLE) + 8 * SIMD_FP_256.PACKED_SINGLE) / 1e9 / tma_info_system_time", "MetricGroup": "Cor;Flops;HPC", "MetricName": "tma_info_system_gflops", "PublicDescription": "Giga Floating Point Operations Per Second. Aggregate across all supported options of: FP precisions, scalar and vector instructions, vector-width" @@ -627,12 +633,25 @@ }, { "BriefDescription": "Average latency of data read request to external memory (in nanoseconds)", - "MetricExpr": "1e9 * (UNC_C_TOR_OCCUPANCY.MISS_OPCODE@filter_opc\\=0x182@ / UNC_C_TOR_INSERTS.MISS_OPCODE@filter_opc\\=0x182@) / (tma_info_system_socket_clks / duration_time)", + "MetricExpr": "1e9 * (UNC_C_TOR_OCCUPANCY.MISS_OPCODE@filter_opc\\=0x182@ / UNC_C_TOR_INSERTS.MISS_OPCODE@filter_opc\\=0x182@) / (tma_info_system_socket_clks / tma_info_system_time)", "MetricGroup": "Mem;MemoryLat;SoC", "MetricName": "tma_info_system_mem_read_latency", "PublicDescription": "Average latency of data read request to external memory (in nanoseconds). Accounts for demand loads and L1/L2 prefetches. ([RKL+]memory-controller only)" }, { + "BriefDescription": "PerfMon Event Multiplexing accuracy indicator", + "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P / CPU_CLK_UNHALTED.THREAD", + "MetricGroup": "Summary", + "MetricName": "tma_info_system_mux", + "MetricThreshold": "tma_info_system_mux > 1.1 | tma_info_system_mux < 0.9" + }, + { + "BriefDescription": "Total package Power in Watts", + "MetricExpr": "(power@energy\\-pkg@ + power@energy\\-ram@) * 15.6 / (duration_time * 1e6)", + "MetricGroup": "Power;SoC", + "MetricName": "tma_info_system_power" + }, + { "BriefDescription": "Fraction of cycles where both hardware Logical Processors were active", "MetricExpr": "(1 - CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / (CPU_CLK_UNHALTED.REF_XCLK_ANY / 2) if #SMT_on else 0)", "MetricGroup": "SMT", @@ -645,6 +664,13 @@ "MetricName": "tma_info_system_socket_clks" }, { + "BriefDescription": "Run duration time in seconds", + "MetricExpr": "duration_time", + "MetricGroup": "Summary", + "MetricName": "tma_info_system_time", + "MetricThreshold": "tma_info_system_time < 1" + }, + { "BriefDescription": "Average Frequency Utilization relative nominal frequency", "MetricExpr": "tma_info_thread_clks / CPU_CLK_UNHALTED.REF_TSC", "MetricGroup": "Power", @@ -652,7 +678,7 @@ }, { "BriefDescription": "Measured Average Uncore Frequency for the SoC [GHz]", - "MetricExpr": "tma_info_system_socket_clks / 1e9 / duration_time", + "MetricExpr": "tma_info_system_socket_clks / 1e9 / tma_info_system_time", "MetricGroup": "SoC", "MetricName": "tma_info_system_uncore_frequency" }, @@ -711,12 +737,12 @@ "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates how often the CPU was stalled without loads missing the L1 data cache", + "BriefDescription": "This metric estimates how often the CPU was stalled without loads missing the L1 Data (L1D) cache", "MetricExpr": "max((min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.STALLS_LDM_PENDING) - CYCLE_ACTIVITY.STALLS_L1D_PENDING) / tma_info_thread_clks, 0)", "MetricGroup": "CacheHits;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_issueL1;tma_issueMC;tma_memory_bound_group", "MetricName": "tma_l1_bound", "MetricThreshold": "tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", - "PublicDescription": "This metric estimates how often the CPU was stalled without loads missing the L1 data cache. The L1 data cache typically has the shortest latency. However; in certain cases like loads blocked on older stores; a load might suffer due to high latency even though it is being satisfied by the L1. Another example is loads who miss in the TLB. These cases are characterized by execution unit stalls; while some non-completed demand load lives in the machine without having that demand load missing the L1 cache. Sample with: MEM_LOAD_UOPS_RETIRED.L1_HIT_PS;MEM_LOAD_UOPS_RETIRED.HIT_LFB_PS. Related metrics: tma_clears_resteers, tma_machine_clears, tma_microcode_sequencer, tma_ms_switches, tma_ports_utilized_1", + "PublicDescription": "This metric estimates how often the CPU was stalled without loads missing the L1 Data (L1D) cache. The L1D cache typically has the shortest latency. However; in certain cases like loads blocked on older stores; a load might suffer due to high latency even though it is being satisfied by the L1D. Another example is loads who miss in the TLB. These cases are characterized by execution unit stalls; while some non-completed demand load lives in the machine without having that demand load missing the L1 cache. Sample with: MEM_LOAD_UOPS_RETIRED.L1_HIT_PS. Related metrics: tma_clears_resteers, tma_machine_clears, tma_microcode_sequencer, tma_ms_switches, tma_ports_utilized_1", "ScaleUnit": "100%" }, { @@ -790,7 +816,7 @@ "BriefDescription": "This metric represents fraction of cycles the CPU spent handling cache misses due to lock operations", "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "MEM_UOPS_RETIRED.LOCK_LOADS / MEM_UOPS_RETIRED.ALL_STORES * min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO) / tma_info_thread_clks", - "MetricGroup": "Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_l1_bound_group", + "MetricGroup": "LockCont;Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_l1_bound_group", "MetricName": "tma_lock_latency", "MetricThreshold": "tma_lock_latency > 0.2 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", "PublicDescription": "This metric represents fraction of cycles the CPU spent handling cache misses due to lock operations. Due to the microarchitecture handling of locks; they are classified as L1_Bound regardless of what memory source satisfied them. Sample with: MEM_UOPS_RETIRED.LOCK_LOADS_PS. Related metrics: tma_store_latency", @@ -810,7 +836,7 @@ { "BriefDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory - DRAM ([SPR-HBM] and/or HBM)", "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, cpu@OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD\\,cmask\\=6@) / tma_info_thread_clks", - "MetricGroup": "BvMS;MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueBW", + "MetricGroup": "BvMB;MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueBW", "MetricName": "tma_mem_bandwidth", "MetricThreshold": "tma_mem_bandwidth > 0.2 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", "PublicDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory - DRAM ([SPR-HBM] and/or HBM). The underlying heuristic assumes that a similar off-core traffic is generated by all IA cores. This metric does not aggregate non-data-read requests by this logical processor; requests from other IA Logical Processors/Physical Cores/sockets; or other non-IA devices like GPU; hence the maximum external memory bandwidth limits may or may not be approached when this metric is flagged (see Uncore counters for that). Related metrics: tma_fb_full, tma_info_system_dram_bw_use, tma_sq_full", @@ -869,7 +895,7 @@ "MetricGroup": "Compute;TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P", "MetricName": "tma_port_0", "MetricThreshold": "tma_port_0 > 0.6", - "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 0 ([SNB+] ALU; [HSW+] ALU and 2nd branch). Sample with: UOPS_DISPATCHED_PORT.PORT_0. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", + "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 0 ([SNB+] ALU; [HSW+] ALU and 2nd branch). Sample with: UOPS_DISPATCHED.PORT_0. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%" }, { @@ -878,7 +904,7 @@ "MetricGroup": "TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P", "MetricName": "tma_port_1", "MetricThreshold": "tma_port_1 > 0.6", - "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 1 (ALU). Sample with: UOPS_DISPATCHED_PORT.PORT_1. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_5, tma_port_6, tma_ports_utilized_2", + "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 1 (ALU). Sample with: UOPS_DISPATCHED.PORT_1. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_5, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%" }, { @@ -997,7 +1023,7 @@ "MetricExpr": "13 * LD_BLOCKS.NO_SR / tma_info_thread_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group", "MetricName": "tma_split_loads", - "MetricThreshold": "tma_split_loads > 0.2 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "MetricThreshold": "tma_split_loads > 0.3", "PublicDescription": "This metric estimates fraction of cycles handling memory load split accesses - load that cross 64-byte cache line boundary. Sample with: MEM_UOPS_RETIRED.SPLIT_LOADS_PS", "ScaleUnit": "100%" }, @@ -1013,7 +1039,7 @@ { "BriefDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors)", "MetricExpr": "(OFFCORE_REQUESTS_BUFFER.SQ_FULL / 2 if #SMT_on else OFFCORE_REQUESTS_BUFFER.SQ_FULL) / tma_info_core_core_clks", - "MetricGroup": "BvMS;MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_issueBW;tma_l3_bound_group", + "MetricGroup": "BvMB;MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_issueBW;tma_l3_bound_group", "MetricName": "tma_sq_full", "MetricThreshold": "tma_sq_full > 0.3 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", "PublicDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors). Related metrics: tma_fb_full, tma_info_system_dram_bw_use, tma_mem_bandwidth", @@ -1041,7 +1067,7 @@ "BriefDescription": "This metric estimates fraction of cycles the CPU spent handling L1D store misses", "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "(L2_RQSTS.RFO_HIT * 9 * (1 - MEM_UOPS_RETIRED.LOCK_LOADS / MEM_UOPS_RETIRED.ALL_STORES) + (1 - MEM_UOPS_RETIRED.LOCK_LOADS / MEM_UOPS_RETIRED.ALL_STORES) * min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO)) / tma_info_thread_clks", - "MetricGroup": "BvML;MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_issueSL;tma_store_bound_group", + "MetricGroup": "BvML;LockCont;MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_issueSL;tma_store_bound_group", "MetricName": "tma_store_latency", "MetricThreshold": "tma_store_latency > 0.1 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", "PublicDescription": "This metric estimates fraction of cycles the CPU spent handling L1D store misses. Store accesses usually less impact out-of-order core performance; however; holding resources for longer time can lead into undesired implications (e.g. contention on L1D fill-buffer entries - see FB_Full). Related metrics: tma_fb_full, tma_lock_latency", diff --git a/tools/perf/pmu-events/arch/x86/ivytown/metricgroups.json b/tools/perf/pmu-events/arch/x86/ivytown/metricgroups.json index 4193c90c3459..0863375bdead 100644 --- a/tools/perf/pmu-events/arch/x86/ivytown/metricgroups.json +++ b/tools/perf/pmu-events/arch/x86/ivytown/metricgroups.json @@ -9,6 +9,7 @@ "BvCB": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", "BvFB": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", "BvIO": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "BvMB": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", "BvML": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", "BvMP": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", "BvMS": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", @@ -34,6 +35,7 @@ "InsType": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", "L2Evicts": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", "LSD": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "LockCont": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", "MachineClears": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", "Machine_Clears": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", "Mem": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", @@ -51,6 +53,7 @@ "Pipeline": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", "PortsUtil": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", "Power": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Prefetches": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", "Ret": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", "Retire": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", "SMT": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", @@ -78,6 +81,7 @@ "tma_bad_speculation_group": "Metrics contributing to tma_bad_speculation category", "tma_branch_resteers_group": "Metrics contributing to tma_branch_resteers category", "tma_core_bound_group": "Metrics contributing to tma_core_bound category", + "tma_divider_group": "Metrics contributing to tma_divider category", "tma_dram_bound_group": "Metrics contributing to tma_dram_bound category", "tma_dtlb_load_group": "Metrics contributing to tma_dtlb_load category", "tma_dtlb_store_group": "Metrics contributing to tma_dtlb_store category", @@ -103,6 +107,7 @@ "tma_issueSpSt": "Metrics related by the issue $issueSpSt", "tma_issueSyncxn": "Metrics related by the issue $issueSyncxn", "tma_issueTLB": "Metrics related by the issue $issueTLB", + "tma_itlb_misses_group": "Metrics contributing to tma_itlb_misses category", "tma_l1_bound_group": "Metrics contributing to tma_l1_bound category", "tma_l3_bound_group": "Metrics contributing to tma_l3_bound category", "tma_light_operations_group": "Metrics contributing to tma_light_operations category", diff --git a/tools/perf/pmu-events/arch/x86/jaketown/frontend.json b/tools/perf/pmu-events/arch/x86/jaketown/frontend.json index 3cb468da7011..97e7760aeb26 100644 --- a/tools/perf/pmu-events/arch/x86/jaketown/frontend.json +++ b/tools/perf/pmu-events/arch/x86/jaketown/frontend.json @@ -278,5 +278,13 @@ "EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_LE_3_UOP_DELIV.CORE", "SampleAfterValue": "2000003", "UMask": "0x1" + }, + { + "BriefDescription": "Valid instructions written to IQ per cycle.", + "Counter": "0,1,2,3", + "EventCode": "0x17", + "EventName": "INSTS_WRITTEN_TO_IQ.INSTS", + "SampleAfterValue": "2000003", + "UMask": "0x1" } ] diff --git a/tools/perf/pmu-events/arch/x86/jaketown/jkt-metrics.json b/tools/perf/pmu-events/arch/x86/jaketown/jkt-metrics.json index f8c18741b360..6f636ea0f216 100644 --- a/tools/perf/pmu-events/arch/x86/jaketown/jkt-metrics.json +++ b/tools/perf/pmu-events/arch/x86/jaketown/jkt-metrics.json @@ -127,7 +127,7 @@ "MetricGroup": "BvCB;TopdownL3;tma_L3_group;tma_core_bound_group", "MetricName": "tma_divider", "MetricThreshold": "tma_divider > 0.2 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)", - "PublicDescription": "This metric represents fraction of cycles where the Divider unit was active. Divide and square root instructions are performed by the Divider unit and can take considerably longer latency than integer or Floating Point addition; subtraction; or multiplication. Sample with: ARITH.DIVIDER_UOPS", + "PublicDescription": "This metric represents fraction of cycles where the Divider unit was active. Divide and square root instructions are performed by the Divider unit and can take considerably longer latency than integer or Floating Point addition; subtraction; or multiplication. Sample with: ARITH.DIVIDER_ACTIVE", "ScaleUnit": "100%" }, { @@ -211,7 +211,7 @@ "MetricGroup": "Compute;Flops;TopdownL5;tma_L5_group;tma_fp_vector_group;tma_issue2P", "MetricName": "tma_fp_vector_128b", "MetricThreshold": "tma_fp_vector_128b > 0.1 & (tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6))", - "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 128-bit wide vectors. May overcount due to FMA double counting. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_6, tma_ports_utilized_2", + "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 128-bit wide vectors. May overcount due to FMA double counting prior to LNL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%" }, { @@ -220,7 +220,7 @@ "MetricGroup": "Compute;Flops;TopdownL5;tma_L5_group;tma_fp_vector_group;tma_issue2P", "MetricName": "tma_fp_vector_256b", "MetricThreshold": "tma_fp_vector_256b > 0.1 & (tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6))", - "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 256-bit wide vectors. May overcount due to FMA double counting. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_512b, tma_port_6, tma_ports_utilized_2", + "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 256-bit wide vectors. May overcount due to FMA double counting prior to LNL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_512b, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%" }, { @@ -240,7 +240,7 @@ "MetricName": "tma_heavy_operations", "MetricThreshold": "tma_heavy_operations > 0.1", "MetricgroupNoGroup": "TopdownL2", - "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences. ([ICL+] Note this may overcount due to approximation using indirect events; [ADL+] .)", + "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences.([ICL+] Note this may overcount due to approximation using indirect events; [ADL+])", "ScaleUnit": "100%" }, { @@ -276,6 +276,12 @@ "PublicDescription": "Fraction of Uops delivered by the DSB (aka Decoded ICache; or Uop Cache). Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_lcp" }, { + "BriefDescription": "Taken Branches retired Per Cycle", + "MetricExpr": "BR_INST_RETIRED.NEAR_TAKEN / tma_info_thread_clks", + "MetricGroup": "Branches;FetchBW", + "MetricName": "tma_info_frontend_tbpc" + }, + { "BriefDescription": "Total number of retired Instructions", "MetricExpr": "INST_RETIRED.ANY", "MetricGroup": "Summary;TmaL1;tma_L1_group", @@ -290,7 +296,7 @@ }, { "BriefDescription": "Measured Average Core Frequency for unhalted processors [GHz]", - "MetricExpr": "tma_info_system_turbo_utilization * TSC / 1e9 / duration_time", + "MetricExpr": "tma_info_system_turbo_utilization * TSC / 1e9 / tma_info_system_time", "MetricGroup": "Power;Summary", "MetricName": "tma_info_system_core_frequency" }, @@ -308,14 +314,14 @@ }, { "BriefDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]", - "MetricExpr": "64 * (UNC_M_CAS_COUNT.RD + UNC_M_CAS_COUNT.WR) / 1e9 / duration_time", + "MetricExpr": "64 * (UNC_M_CAS_COUNT.RD + UNC_M_CAS_COUNT.WR) / 1e9 / tma_info_system_time", "MetricGroup": "HPC;MemOffcore;MemoryBW;SoC;tma_issueBW", "MetricName": "tma_info_system_dram_bw_use", "PublicDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]. Related metrics: tma_mem_bandwidth" }, { "BriefDescription": "Giga Floating Point Operations Per Second", - "MetricExpr": "(FP_COMP_OPS_EXE.SSE_SCALAR_SINGLE + FP_COMP_OPS_EXE.SSE_SCALAR_DOUBLE + 2 * FP_COMP_OPS_EXE.SSE_PACKED_DOUBLE + 4 * (FP_COMP_OPS_EXE.SSE_PACKED_SINGLE + SIMD_FP_256.PACKED_DOUBLE) + 8 * SIMD_FP_256.PACKED_SINGLE) / 1e9 / duration_time", + "MetricExpr": "(FP_COMP_OPS_EXE.SSE_SCALAR_SINGLE + FP_COMP_OPS_EXE.SSE_SCALAR_DOUBLE + 2 * FP_COMP_OPS_EXE.SSE_PACKED_DOUBLE + 4 * (FP_COMP_OPS_EXE.SSE_PACKED_SINGLE + SIMD_FP_256.PACKED_DOUBLE) + 8 * SIMD_FP_256.PACKED_SINGLE) / 1e9 / tma_info_system_time", "MetricGroup": "Cor;Flops;HPC", "MetricName": "tma_info_system_gflops", "PublicDescription": "Giga Floating Point Operations Per Second. Aggregate across all supported options of: FP precisions, scalar and vector instructions, vector-width" @@ -349,12 +355,19 @@ }, { "BriefDescription": "Average latency of data read request to external memory (in nanoseconds)", - "MetricExpr": "1e9 * (UNC_C_TOR_OCCUPANCY.MISS_OPCODE@filter_opc\\=0x182@ / UNC_C_TOR_INSERTS.MISS_OPCODE@filter_opc\\=0x182@) / (tma_info_system_socket_clks / duration_time)", + "MetricExpr": "1e9 * (UNC_C_TOR_OCCUPANCY.MISS_OPCODE@filter_opc\\=0x182@ / UNC_C_TOR_INSERTS.MISS_OPCODE@filter_opc\\=0x182@) / (tma_info_system_socket_clks / tma_info_system_time)", "MetricGroup": "Mem;MemoryLat;SoC", "MetricName": "tma_info_system_mem_read_latency", "PublicDescription": "Average latency of data read request to external memory (in nanoseconds). Accounts for demand loads and L1/L2 prefetches. ([RKL+]memory-controller only)" }, { + "BriefDescription": "PerfMon Event Multiplexing accuracy indicator", + "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P / CPU_CLK_UNHALTED.THREAD", + "MetricGroup": "Summary", + "MetricName": "tma_info_system_mux", + "MetricThreshold": "tma_info_system_mux > 1.1 | tma_info_system_mux < 0.9" + }, + { "BriefDescription": "Fraction of cycles where both hardware Logical Processors were active", "MetricExpr": "(1 - CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / (CPU_CLK_UNHALTED.REF_XCLK_ANY / 2) if #SMT_on else 0)", "MetricGroup": "SMT", @@ -367,6 +380,13 @@ "MetricName": "tma_info_system_socket_clks" }, { + "BriefDescription": "Run duration time in seconds", + "MetricExpr": "duration_time", + "MetricGroup": "Summary", + "MetricName": "tma_info_system_time", + "MetricThreshold": "tma_info_system_time < 1" + }, + { "BriefDescription": "Average Frequency Utilization relative nominal frequency", "MetricExpr": "tma_info_thread_clks / CPU_CLK_UNHALTED.REF_TSC", "MetricGroup": "Power", @@ -374,7 +394,7 @@ }, { "BriefDescription": "Measured Average Uncore Frequency for the SoC [GHz]", - "MetricExpr": "tma_info_system_socket_clks / 1e9 / duration_time", + "MetricExpr": "tma_info_system_socket_clks / 1e9 / tma_info_system_time", "MetricGroup": "SoC", "MetricName": "tma_info_system_uncore_frequency" }, @@ -468,7 +488,7 @@ { "BriefDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory - DRAM ([SPR-HBM] and/or HBM)", "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, cpu@OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD\\,cmask\\=6@) / tma_info_thread_clks", - "MetricGroup": "BvMS;MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueBW", + "MetricGroup": "BvMB;MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueBW", "MetricName": "tma_mem_bandwidth", "MetricThreshold": "tma_mem_bandwidth > 0.2 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", "PublicDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory - DRAM ([SPR-HBM] and/or HBM). The underlying heuristic assumes that a similar off-core traffic is generated by all IA cores. This metric does not aggregate non-data-read requests by this logical processor; requests from other IA Logical Processors/Physical Cores/sockets; or other non-IA devices like GPU; hence the maximum external memory bandwidth limits may or may not be approached when this metric is flagged (see Uncore counters for that). Related metrics: tma_info_system_dram_bw_use", diff --git a/tools/perf/pmu-events/arch/x86/jaketown/metricgroups.json b/tools/perf/pmu-events/arch/x86/jaketown/metricgroups.json index 7dc7eb0d3dd3..eb8fbd14138a 100644 --- a/tools/perf/pmu-events/arch/x86/jaketown/metricgroups.json +++ b/tools/perf/pmu-events/arch/x86/jaketown/metricgroups.json @@ -9,6 +9,7 @@ "BvCB": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", "BvFB": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", "BvIO": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "BvMB": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", "BvML": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", "BvMP": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", "BvMS": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", @@ -33,6 +34,7 @@ "InsType": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", "L2Evicts": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", "LSD": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "LockCont": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", "MachineClears": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", "Machine_Clears": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", "Mem": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", @@ -48,6 +50,7 @@ "Pipeline": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", "PortsUtil": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", "Power": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Prefetches": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", "Ret": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", "Retire": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", "SMT": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", @@ -75,6 +78,7 @@ "tma_bad_speculation_group": "Metrics contributing to tma_bad_speculation category", "tma_branch_resteers_group": "Metrics contributing to tma_branch_resteers category", "tma_core_bound_group": "Metrics contributing to tma_core_bound category", + "tma_divider_group": "Metrics contributing to tma_divider category", "tma_dram_bound_group": "Metrics contributing to tma_dram_bound category", "tma_dtlb_load_group": "Metrics contributing to tma_dtlb_load category", "tma_dtlb_store_group": "Metrics contributing to tma_dtlb_store category", @@ -99,6 +103,7 @@ "tma_issueSmSt": "Metrics related by the issue $issueSmSt", "tma_issueSyncxn": "Metrics related by the issue $issueSyncxn", "tma_issueTLB": "Metrics related by the issue $issueTLB", + "tma_itlb_misses_group": "Metrics contributing to tma_itlb_misses category", "tma_l1_bound_group": "Metrics contributing to tma_l1_bound category", "tma_light_operations_group": "Metrics contributing to tma_light_operations category", "tma_machine_clears_group": "Metrics contributing to tma_machine_clears category", diff --git a/tools/perf/pmu-events/arch/x86/jaketown/other.json b/tools/perf/pmu-events/arch/x86/jaketown/other.json index 42692fa24b6c..970839a9c786 100644 --- a/tools/perf/pmu-events/arch/x86/jaketown/other.json +++ b/tools/perf/pmu-events/arch/x86/jaketown/other.json @@ -34,14 +34,6 @@ "UMask": "0x2" }, { - "BriefDescription": "Valid instructions written to IQ per cycle.", - "Counter": "0,1,2,3", - "EventCode": "0x17", - "EventName": "INSTS_WRITTEN_TO_IQ.INSTS", - "SampleAfterValue": "2000003", - "UMask": "0x1" - }, - { "BriefDescription": "Cycles when L1 and L2 are locked due to UC or split lock.", "Counter": "0,1,2,3", "EventCode": "0x63", diff --git a/tools/perf/pmu-events/arch/x86/lunarlake/cache.json b/tools/perf/pmu-events/arch/x86/lunarlake/cache.json index 15fb9921f4fc..b1a6bb867a1e 100644 --- a/tools/perf/pmu-events/arch/x86/lunarlake/cache.json +++ b/tools/perf/pmu-events/arch/x86/lunarlake/cache.json @@ -418,6 +418,51 @@ "Unit": "cpu_core" }, { + "BriefDescription": "Counts the number of LLC prefetches that were throttled due to Dynamic Prefetch Throttling. The throttle requestor/source could be from the uncore/SOC or the Dead Block Predictor. Counts on a per core basis.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x29", + "EventName": "LLC_PREFETCHES_THROTTLED.DPT", + "SampleAfterValue": "1000003", + "UMask": "0x1", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of LLC prefetches throttled due to Demand Throttle Prefetcher. DTP Global Triggered with no Local Override. Counts on a per core basis.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x29", + "EventName": "LLC_PREFETCHES_THROTTLED.DTP", + "SampleAfterValue": "1000003", + "UMask": "0x2", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of LLC prefetches not throttled by DTP due to local override. These prefetches may still be throttled due to another throttler mechanism. Counts on a per core basis.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x29", + "EventName": "LLC_PREFETCHES_THROTTLED.DTP_OVERRIDE", + "SampleAfterValue": "1000003", + "UMask": "0x4", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of LLC prefetches throttled due to LLC hit rate in <insert knob name here>. Counts on a per core basis.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x29", + "EventName": "LLC_PREFETCHES_THROTTLED.HIT_RATE", + "SampleAfterValue": "1000003", + "UMask": "0x10", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of LLC prefetches throttled due to exceeding the XQ threshold set by either XQ_THRESOLD_DTP or LLC_XQ_THRESHOLD. Counts on a per core basis.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x29", + "EventName": "LLC_PREFETCHES_THROTTLED.XQ_THRESH", + "SampleAfterValue": "1000003", + "UMask": "0x8", + "Unit": "cpu_atom" + }, + { "BriefDescription": "Cycles when L1D is locked", "Counter": "0,1,2,3,4,5,6,7,8,9", "EventCode": "0x42", @@ -547,7 +592,7 @@ "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_INST_RETIRED.ALL_LOADS", - "PublicDescription": "Counts Instructions with at least one architecturally visible load retired.", + "PublicDescription": "Counts Instructions with at least one architecturally visible load retired. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x81", "Unit": "cpu_core" @@ -558,7 +603,7 @@ "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_INST_RETIRED.ALL_STORES", - "PublicDescription": "Counts all retired store instructions.", + "PublicDescription": "Counts all retired store instructions. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x82", "Unit": "cpu_core" @@ -568,7 +613,7 @@ "Counter": "0,1,2,3", "EventCode": "0xd0", "EventName": "MEM_INST_RETIRED.ALL_SWPF", - "PublicDescription": "Counts all retired software prefetch instructions.", + "PublicDescription": "Counts all retired software prefetch instructions. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x84", "Unit": "cpu_core" @@ -579,7 +624,7 @@ "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_INST_RETIRED.ANY", - "PublicDescription": "Counts all retired memory instructions - loads and stores.", + "PublicDescription": "Counts all retired memory instructions - loads and stores. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x87", "Unit": "cpu_core" @@ -590,7 +635,7 @@ "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_INST_RETIRED.LOCK_LOADS", - "PublicDescription": "Counts retired load instructions with locked access.", + "PublicDescription": "Counts retired load instructions with locked access. Available PDIST counters: 0", "SampleAfterValue": "100007", "UMask": "0x21", "Unit": "cpu_core" @@ -601,7 +646,7 @@ "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_INST_RETIRED.SPLIT_LOADS", - "PublicDescription": "Counts retired load instructions that split across a cacheline boundary.", + "PublicDescription": "Counts retired load instructions that split across a cacheline boundary. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x41", "Unit": "cpu_core" @@ -612,7 +657,7 @@ "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_INST_RETIRED.SPLIT_STORES", - "PublicDescription": "Counts retired store instructions that split across a cacheline boundary.", + "PublicDescription": "Counts retired store instructions that split across a cacheline boundary. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x42", "Unit": "cpu_core" @@ -623,7 +668,7 @@ "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_INST_RETIRED.STLB_HIT_LOADS", - "PublicDescription": "Number of retired load instructions with a clean hit in the 2nd-level TLB (STLB).", + "PublicDescription": "Number of retired load instructions with a clean hit in the 2nd-level TLB (STLB). Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x9", "Unit": "cpu_core" @@ -634,7 +679,7 @@ "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_INST_RETIRED.STLB_HIT_STORES", - "PublicDescription": "Number of retired store instructions that hit in the 2nd-level TLB (STLB).", + "PublicDescription": "Number of retired store instructions that hit in the 2nd-level TLB (STLB). Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0xa", "Unit": "cpu_core" @@ -645,7 +690,7 @@ "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_INST_RETIRED.STLB_MISS_LOADS", - "PublicDescription": "Number of retired load instructions that (start a) miss in the 2nd-level TLB (STLB).", + "PublicDescription": "Number of retired load instructions that (start a) miss in the 2nd-level TLB (STLB). Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x11", "Unit": "cpu_core" @@ -656,7 +701,7 @@ "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_INST_RETIRED.STLB_MISS_STORES", - "PublicDescription": "Number of retired store instructions that (start a) miss in the 2nd-level TLB (STLB).", + "PublicDescription": "Number of retired store instructions that (start a) miss in the 2nd-level TLB (STLB). Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x12", "Unit": "cpu_core" @@ -667,7 +712,7 @@ "Data_LA": "1", "EventCode": "0xd2", "EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD", - "PublicDescription": "Counts retired load instructions whose data sources were a cross-core Snoop hits and forwards data from an in on-package core cache (induced by NI$)", + "PublicDescription": "Counts retired load instructions whose data sources were a cross-core Snoop hits and forwards data from an in on-package core cache (induced by NI$) Available PDIST counters: 0", "SampleAfterValue": "20011", "UMask": "0x10", "Unit": "cpu_core" @@ -678,7 +723,7 @@ "Data_LA": "1", "EventCode": "0xd2", "EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM", - "PublicDescription": "Counts retired load instructions whose data sources were HitM responses from shared L3, Hit-with-FWD is normally excluded.", + "PublicDescription": "Counts retired load instructions whose data sources were HitM responses from shared L3, Hit-with-FWD is normally excluded. Available PDIST counters: 0", "SampleAfterValue": "20011", "UMask": "0x4", "Unit": "cpu_core" @@ -689,7 +734,7 @@ "Data_LA": "1", "EventCode": "0xd2", "EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS", - "PublicDescription": "Counts the retired load instructions whose data sources were L3 hit and cross-core snoop missed in on-pkg core cache.", + "PublicDescription": "Counts the retired load instructions whose data sources were L3 hit and cross-core snoop missed in on-pkg core cache. Available PDIST counters: 0", "SampleAfterValue": "20011", "UMask": "0x1", "Unit": "cpu_core" @@ -700,7 +745,7 @@ "Data_LA": "1", "EventCode": "0xd2", "EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_NO_FWD", - "PublicDescription": "Counts retired load instructions whose data sources were L3 and cross-core snoop hits in on-pkg core cache.", + "PublicDescription": "Counts retired load instructions whose data sources were L3 and cross-core snoop hits in on-pkg core cache. Available PDIST counters: 0", "SampleAfterValue": "20011", "UMask": "0x2", "Unit": "cpu_core" @@ -711,6 +756,7 @@ "Data_LA": "1", "EventCode": "0xd3", "EventName": "MEM_LOAD_L3_MISS_RETIRED.MEMSIDE_CACHE", + "PublicDescription": "Retired load instructions which data source is memory side cache. Available PDIST counters: 0", "SampleAfterValue": "100007", "Unit": "cpu_core" }, @@ -720,7 +766,7 @@ "Data_LA": "1", "EventCode": "0xd4", "EventName": "MEM_LOAD_MISC_RETIRED.UC", - "PublicDescription": "Retired instructions with at least one load to uncacheable memory-type, or at least one cache-line split locked access (Bus Lock).", + "PublicDescription": "Retired instructions with at least one load to uncacheable memory-type, or at least one cache-line split locked access (Bus Lock). Available PDIST counters: 0", "SampleAfterValue": "100007", "UMask": "0x4", "Unit": "cpu_core" @@ -731,7 +777,7 @@ "Data_LA": "1", "EventCode": "0xd1", "EventName": "MEM_LOAD_RETIRED.FB_HIT", - "PublicDescription": "Counts retired load instructions with at least one uop was load missed in L1 but hit FB (Fill Buffers) due to preceding miss to the same cache line with data not ready.", + "PublicDescription": "Counts retired load instructions with at least one uop was load missed in L1 but hit FB (Fill Buffers) due to preceding miss to the same cache line with data not ready. Available PDIST counters: 0", "SampleAfterValue": "100007", "UMask": "0x40", "Unit": "cpu_core" @@ -742,7 +788,7 @@ "Data_LA": "1", "EventCode": "0xd1", "EventName": "MEM_LOAD_RETIRED.L1_HIT", - "PublicDescription": "Counts retired load instructions with at least one uop that hit in the L1 data cache. This event includes all SW prefetches and lock instructions regardless of the data source.", + "PublicDescription": "Counts retired load instructions with at least one uop that hit in the L1 data cache. This event includes all SW prefetches and lock instructions regardless of the data source. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x1", "Unit": "cpu_core" @@ -752,6 +798,7 @@ "Counter": "0,1,2,3", "EventCode": "0xd1", "EventName": "MEM_LOAD_RETIRED.L1_HIT_L1", + "PublicDescription": "Counts retired load instructions with at least one uop that hit in the Level 1 of the L1 data cache. Available PDIST counters: 0", "SampleAfterValue": "1000003", "Unit": "cpu_core" }, @@ -761,7 +808,7 @@ "Data_LA": "1", "EventCode": "0xd1", "EventName": "MEM_LOAD_RETIRED.L1_MISS", - "PublicDescription": "Counts retired load instructions with at least one uop that missed in the L1 cache.", + "PublicDescription": "Counts retired load instructions with at least one uop that missed in the L1 cache. Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0x8", "Unit": "cpu_core" @@ -772,7 +819,7 @@ "Data_LA": "1", "EventCode": "0xd1", "EventName": "MEM_LOAD_RETIRED.L2_HIT", - "PublicDescription": "Counts retired load instructions with L2 cache hits as data sources.", + "PublicDescription": "Counts retired load instructions with L2 cache hits as data sources. Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0x2", "Unit": "cpu_core" @@ -783,7 +830,7 @@ "Data_LA": "1", "EventCode": "0xd1", "EventName": "MEM_LOAD_RETIRED.L2_MISS", - "PublicDescription": "Counts retired load instructions missed L2 cache as data sources.", + "PublicDescription": "Counts retired load instructions missed L2 cache as data sources. Available PDIST counters: 0", "SampleAfterValue": "100021", "UMask": "0x10", "Unit": "cpu_core" @@ -794,7 +841,7 @@ "Data_LA": "1", "EventCode": "0xd1", "EventName": "MEM_LOAD_RETIRED.L3_HIT", - "PublicDescription": "Counts retired load instructions with at least one uop that hit in the L3 cache.", + "PublicDescription": "Counts retired load instructions with at least one uop that hit in the L3 cache. Available PDIST counters: 0", "SampleAfterValue": "100021", "UMask": "0x4", "Unit": "cpu_core" @@ -805,7 +852,7 @@ "Data_LA": "1", "EventCode": "0xd1", "EventName": "MEM_LOAD_RETIRED.L3_MISS", - "PublicDescription": "Counts retired load instructions with at least one uop that missed in the L3 cache.", + "PublicDescription": "Counts retired load instructions with at least one uop that missed in the L3 cache. Available PDIST counters: 0", "SampleAfterValue": "50021", "UMask": "0x20", "Unit": "cpu_core" @@ -1184,23 +1231,85 @@ "Unit": "cpu_core" }, { + "BriefDescription": "Counts writebacks of modified cachelines that have any type of response.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xB7", + "EventName": "OCR.COREWB_M.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x10008", + "PublicDescription": "Counts writebacks of modified cachelines that have any type of response. Available PDIST counters: 0", + "SampleAfterValue": "100003", + "UMask": "0x1", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts writebacks of non-modified cachelines that have any type of response.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xB7", + "EventName": "OCR.COREWB_NONM.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x11000", + "PublicDescription": "Counts writebacks of non-modified cachelines that have any type of response. Available PDIST counters: 0", + "SampleAfterValue": "100003", + "UMask": "0x1", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that have any type of response.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xB7", + "EventName": "OCR.DEMAND_CODE_RD.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x10004", + "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that have any type of response. Available PDIST counters: 0", + "SampleAfterValue": "100003", + "UMask": "0x1", + "Unit": "cpu_atom" + }, + { "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were supplied by mem side cache.", "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xB7", "EventName": "OCR.DEMAND_CODE_RD.MEMSIDE_CACHE", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x11F80000004", + "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were supplied by mem side cache. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1", "Unit": "cpu_atom" }, { + "BriefDescription": "Counts demand data reads that have any type of response.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xB7", + "EventName": "OCR.DEMAND_DATA_RD.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x10001", + "PublicDescription": "Counts demand data reads that have any type of response. Available PDIST counters: 0", + "SampleAfterValue": "100003", + "UMask": "0x1", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts demand data reads that have any type of response.", + "Counter": "0,1,2,3", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.DEMAND_DATA_RD.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x10001", + "PublicDescription": "Counts demand data reads that have any type of response. Available PDIST counters: 0", + "SampleAfterValue": "100003", + "UMask": "0x1", + "Unit": "cpu_core" + }, + { "BriefDescription": "Counts demand data reads that were supplied by the L3 cache where a snoop hit in another cores caches, data forwarding is required as the data is modified.", "Counter": "0,1,2,3", "EventCode": "0x2A,0x2B", "EventName": "OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x40001E00001", + "PublicDescription": "Counts demand data reads that were supplied by the L3 cache where a snoop hit in another cores caches, data forwarding is required as the data is modified. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1", "Unit": "cpu_core" @@ -1212,6 +1321,7 @@ "EventName": "OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x20001E00001", + "PublicDescription": "Counts demand data reads that were supplied by the L3 cache where a snoop hit in another cores caches which forwarded the unmodified data to the requesting core. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1", "Unit": "cpu_core" @@ -1223,17 +1333,43 @@ "EventName": "OCR.DEMAND_DATA_RD.MEMSIDE_CACHE", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x11F80000001", + "PublicDescription": "Counts demand data reads that were supplied by mem side cache. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1", "Unit": "cpu_atom" }, { + "BriefDescription": "Counts demand read for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that have any type of response.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xB7", + "EventName": "OCR.DEMAND_RFO.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x10002", + "PublicDescription": "Counts demand read for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that have any type of response. Available PDIST counters: 0", + "SampleAfterValue": "100003", + "UMask": "0x1", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts demand read for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that have any type of response.", + "Counter": "0,1,2,3", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.DEMAND_RFO.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x10002", + "PublicDescription": "Counts demand read for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that have any type of response. Available PDIST counters: 0", + "SampleAfterValue": "100003", + "UMask": "0x1", + "Unit": "cpu_core" + }, + { "BriefDescription": "Counts demand read for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that were supplied by the L3 cache where a snoop hit in another cores caches, data forwarding is required as the data is modified.", "Counter": "0,1,2,3", "EventCode": "0x2A,0x2B", "EventName": "OCR.DEMAND_RFO.L3_HIT.SNOOP_HITM", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x40001E00002", + "PublicDescription": "Counts demand read for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that were supplied by the L3 cache where a snoop hit in another cores caches, data forwarding is required as the data is modified. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1", "Unit": "cpu_core" diff --git a/tools/perf/pmu-events/arch/x86/lunarlake/frontend.json b/tools/perf/pmu-events/arch/x86/lunarlake/frontend.json index 07bd38a1904e..e2facc4086e9 100644 --- a/tools/perf/pmu-events/arch/x86/lunarlake/frontend.json +++ b/tools/perf/pmu-events/arch/x86/lunarlake/frontend.json @@ -108,7 +108,7 @@ "EventName": "FRONTEND_RETIRED.ANY_ANT", "MSRIndex": "0x3F7", "MSRValue": "0x9", - "PublicDescription": "Always Not Taken (ANT) conditional retired branches (no BTB entry and not mispredicted)", + "PublicDescription": "Always Not Taken (ANT) conditional retired branches (no BTB entry and not mispredicted) Available PDIST counters: 0", "SampleAfterValue": "100007", "UMask": "0x3", "Unit": "cpu_core" @@ -120,7 +120,7 @@ "EventName": "FRONTEND_RETIRED.ANY_DSB_MISS", "MSRIndex": "0x3F7", "MSRValue": "0x1", - "PublicDescription": "Counts retired Instructions that experienced DSB (Decode stream buffer i.e. the decoded instruction-cache) miss.", + "PublicDescription": "Counts retired Instructions that experienced DSB (Decode stream buffer i.e. the decoded instruction-cache) miss. Available PDIST counters: 0", "SampleAfterValue": "100007", "UMask": "0x3", "Unit": "cpu_core" @@ -169,7 +169,7 @@ "EventName": "FRONTEND_RETIRED.DSB_MISS", "MSRIndex": "0x3F7", "MSRValue": "0x11", - "PublicDescription": "Number of retired Instructions that experienced a critical DSB (Decode stream buffer i.e. the decoded instruction-cache) miss. Critical means stalls were exposed to the back-end as a result of the DSB miss.", + "PublicDescription": "Number of retired Instructions that experienced a critical DSB (Decode stream buffer i.e. the decoded instruction-cache) miss. Critical means stalls were exposed to the back-end as a result of the DSB miss. Available PDIST counters: 0", "SampleAfterValue": "100007", "UMask": "0x3", "Unit": "cpu_core" @@ -199,7 +199,7 @@ "EventName": "FRONTEND_RETIRED.ITLB_MISS", "MSRIndex": "0x3F7", "MSRValue": "0x14", - "PublicDescription": "Counts retired Instructions that experienced iTLB (Instruction TLB) true miss.", + "PublicDescription": "Counts retired Instructions that experienced iTLB (Instruction TLB) true miss. Available PDIST counters: 0", "SampleAfterValue": "100007", "UMask": "0x3", "Unit": "cpu_core" @@ -211,7 +211,7 @@ "EventName": "FRONTEND_RETIRED.L1I_MISS", "MSRIndex": "0x3F7", "MSRValue": "0x12", - "PublicDescription": "Counts retired Instructions who experienced Instruction L1 Cache true miss.", + "PublicDescription": "Counts retired Instructions who experienced Instruction L1 Cache true miss. Available PDIST counters: 0", "SampleAfterValue": "100007", "UMask": "0x3", "Unit": "cpu_core" @@ -223,7 +223,7 @@ "EventName": "FRONTEND_RETIRED.L2_MISS", "MSRIndex": "0x3F7", "MSRValue": "0x13", - "PublicDescription": "Counts retired Instructions who experienced Instruction L2 Cache true miss.", + "PublicDescription": "Counts retired Instructions who experienced Instruction L2 Cache true miss. Available PDIST counters: 0", "SampleAfterValue": "100007", "UMask": "0x3", "Unit": "cpu_core" @@ -235,7 +235,7 @@ "EventName": "FRONTEND_RETIRED.LATENCY_GE_128", "MSRIndex": "0x3F7", "MSRValue": "0x608006", - "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 128 cycles which was not interrupted by a back-end stall.", + "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 128 cycles which was not interrupted by a back-end stall. Available PDIST counters: 0", "SampleAfterValue": "100007", "UMask": "0x3", "Unit": "cpu_core" @@ -247,7 +247,7 @@ "EventName": "FRONTEND_RETIRED.LATENCY_GE_16", "MSRIndex": "0x3F7", "MSRValue": "0x601006", - "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 16 cycles. During this period the front-end delivered no uops.", + "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 16 cycles. During this period the front-end delivered no uops. Available PDIST counters: 0", "SampleAfterValue": "100007", "UMask": "0x3", "Unit": "cpu_core" @@ -259,7 +259,7 @@ "EventName": "FRONTEND_RETIRED.LATENCY_GE_2", "MSRIndex": "0x3F7", "MSRValue": "0x600206", - "PublicDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of at least 2 cycles which was not interrupted by a back-end stall.", + "PublicDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of at least 2 cycles which was not interrupted by a back-end stall. Available PDIST counters: 0", "SampleAfterValue": "100007", "UMask": "0x3", "Unit": "cpu_core" @@ -271,7 +271,7 @@ "EventName": "FRONTEND_RETIRED.LATENCY_GE_256", "MSRIndex": "0x3F7", "MSRValue": "0x610006", - "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 256 cycles which was not interrupted by a back-end stall.", + "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 256 cycles which was not interrupted by a back-end stall. Available PDIST counters: 0", "SampleAfterValue": "100007", "UMask": "0x3", "Unit": "cpu_core" @@ -283,7 +283,7 @@ "EventName": "FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1", "MSRIndex": "0x3F7", "MSRValue": "0x100206", - "PublicDescription": "Counts retired instructions that are delivered to the back-end after the front-end had at least 1 bubble-slot for a period of 2 cycles. A bubble-slot is an empty issue-pipeline slot while there was no RAT stall.", + "PublicDescription": "Counts retired instructions that are delivered to the back-end after the front-end had at least 1 bubble-slot for a period of 2 cycles. A bubble-slot is an empty issue-pipeline slot while there was no RAT stall. Available PDIST counters: 0", "SampleAfterValue": "100007", "UMask": "0x3", "Unit": "cpu_core" @@ -295,7 +295,7 @@ "EventName": "FRONTEND_RETIRED.LATENCY_GE_32", "MSRIndex": "0x3F7", "MSRValue": "0x602006", - "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 32 cycles. During this period the front-end delivered no uops.", + "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 32 cycles. During this period the front-end delivered no uops. Available PDIST counters: 0", "SampleAfterValue": "100007", "UMask": "0x3", "Unit": "cpu_core" @@ -307,7 +307,7 @@ "EventName": "FRONTEND_RETIRED.LATENCY_GE_4", "MSRIndex": "0x3F7", "MSRValue": "0x600406", - "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 4 cycles which was not interrupted by a back-end stall.", + "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 4 cycles which was not interrupted by a back-end stall. Available PDIST counters: 0", "SampleAfterValue": "100007", "UMask": "0x3", "Unit": "cpu_core" @@ -319,7 +319,7 @@ "EventName": "FRONTEND_RETIRED.LATENCY_GE_512", "MSRIndex": "0x3F7", "MSRValue": "0x620006", - "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 512 cycles which was not interrupted by a back-end stall.", + "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 512 cycles which was not interrupted by a back-end stall. Available PDIST counters: 0", "SampleAfterValue": "100007", "UMask": "0x3", "Unit": "cpu_core" @@ -331,7 +331,7 @@ "EventName": "FRONTEND_RETIRED.LATENCY_GE_64", "MSRIndex": "0x3F7", "MSRValue": "0x604006", - "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 64 cycles which was not interrupted by a back-end stall.", + "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 64 cycles which was not interrupted by a back-end stall. Available PDIST counters: 0", "SampleAfterValue": "100007", "UMask": "0x3", "Unit": "cpu_core" @@ -343,7 +343,7 @@ "EventName": "FRONTEND_RETIRED.LATENCY_GE_8", "MSRIndex": "0x3F7", "MSRValue": "0x600806", - "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 8 cycles. During this period the front-end delivered no uops.", + "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 8 cycles. During this period the front-end delivered no uops. Available PDIST counters: 0", "SampleAfterValue": "100007", "UMask": "0x3", "Unit": "cpu_core" @@ -355,7 +355,7 @@ "EventName": "FRONTEND_RETIRED.MISP_ANT", "MSRIndex": "0x3F7", "MSRValue": "0x9", - "PublicDescription": "ANT retired branches that got just mispredicted", + "PublicDescription": "ANT retired branches that got just mispredicted Available PDIST counters: 0", "SampleAfterValue": "100007", "UMask": "0x2", "Unit": "cpu_core" @@ -367,6 +367,7 @@ "EventName": "FRONTEND_RETIRED.MS_FLOWS", "MSRIndex": "0x3F7", "MSRValue": "0x8", + "PublicDescription": "Counts flows delivered by the Microcode Sequencer Available PDIST counters: 0", "SampleAfterValue": "100007", "UMask": "0x3", "Unit": "cpu_core" @@ -396,7 +397,7 @@ "EventName": "FRONTEND_RETIRED.STLB_MISS", "MSRIndex": "0x3F7", "MSRValue": "0x15", - "PublicDescription": "Counts retired Instructions that experienced STLB (2nd level TLB) true miss.", + "PublicDescription": "Counts retired Instructions that experienced STLB (2nd level TLB) true miss. Available PDIST counters: 0", "SampleAfterValue": "100007", "UMask": "0x3", "Unit": "cpu_core" @@ -408,7 +409,7 @@ "EventName": "FRONTEND_RETIRED.UNKNOWN_BRANCH", "MSRIndex": "0x3F7", "MSRValue": "0x17", - "PublicDescription": "Number retired branch instructions that caused the front-end to be resteered when it finds the instruction in a fetch line. This is called Unknown Branch which occurs for the first time a branch instruction is fetched or when the branch is not tracked by the BPU (Branch Prediction Unit) anymore.", + "PublicDescription": "Number retired branch instructions that caused the front-end to be resteered when it finds the instruction in a fetch line. This is called Unknown Branch which occurs for the first time a branch instruction is fetched or when the branch is not tracked by the BPU (Branch Prediction Unit) anymore. Available PDIST counters: 0", "SampleAfterValue": "100007", "UMask": "0x3", "Unit": "cpu_core" diff --git a/tools/perf/pmu-events/arch/x86/lunarlake/lnl-metrics.json b/tools/perf/pmu-events/arch/x86/lunarlake/lnl-metrics.json index e748f839c4bd..3c740962e63e 100644 --- a/tools/perf/pmu-events/arch/x86/lunarlake/lnl-metrics.json +++ b/tools/perf/pmu-events/arch/x86/lunarlake/lnl-metrics.json @@ -89,7 +89,7 @@ "MetricExpr": "tma_core_bound", "MetricGroup": "TopdownL3;tma_L3_group;tma_core_bound_group", "MetricName": "tma_allocation_restriction", - "MetricThreshold": "(tma_allocation_restriction >0.10) & ((tma_core_bound >0.10) & ((tma_backend_bound >0.10)))", + "MetricThreshold": "tma_allocation_restriction > 0.1 & (tma_core_bound > 0.1 & tma_backend_bound > 0.1)", "ScaleUnit": "100%", "Unit": "cpu_atom" }, @@ -99,7 +99,7 @@ "MetricExpr": "cpu_atom@TOPDOWN_BE_BOUND.ALL_P@ / (8 * cpu_atom@CPU_CLK_UNHALTED.CORE@)", "MetricGroup": "Default;TopdownL1;tma_L1_group", "MetricName": "tma_backend_bound", - "MetricThreshold": "(tma_backend_bound >0.10)", + "MetricThreshold": "tma_backend_bound > 0.1", "MetricgroupNoGroup": "TopdownL1;Default", "PublicDescription": "Counts the total number of issue slots that were not consumed by the backend due to backend stalls. Note that uops must be available for consumption in order for this event to count. If a uop is not available (IQ is empty), this event will not count", "ScaleUnit": "100%", @@ -111,7 +111,7 @@ "MetricExpr": "cpu_atom@TOPDOWN_BAD_SPECULATION.ALL_P@ / (8 * cpu_atom@CPU_CLK_UNHALTED.CORE@)", "MetricGroup": "Default;TopdownL1;tma_L1_group", "MetricName": "tma_bad_speculation", - "MetricThreshold": "(tma_bad_speculation >0.15)", + "MetricThreshold": "tma_bad_speculation > 0.15", "MetricgroupNoGroup": "TopdownL1;Default", "PublicDescription": "Counts the total number of issue slots that were not consumed by the backend because allocation is stalled due to a mispredicted jump or a machine clear. Only issue slots wasted due to fast nukes such as memory ordering nukes are counted. Other nukes are not accounted for. Counts all issue slots blocked during this recovery window including relevant microcode flows and while uops are not yet available in the instruction queue (IQ). Also includes the issue slots that were consumed by the backend but were thrown away because they were younger than the mispredict or machine clear.", "ScaleUnit": "100%", @@ -122,7 +122,7 @@ "MetricExpr": "cpu_atom@TOPDOWN_FE_BOUND.BRANCH_DETECT@ / (8 * cpu_atom@CPU_CLK_UNHALTED.CORE@)", "MetricGroup": "TopdownL3;tma_L3_group;tma_ifetch_latency_group", "MetricName": "tma_branch_detect", - "MetricThreshold": "(tma_branch_detect >0.05) & ((tma_ifetch_latency >0.15) & ((tma_frontend_bound >0.20)))", + "MetricThreshold": "tma_branch_detect > 0.05 & (tma_ifetch_latency > 0.15 & tma_frontend_bound > 0.2)", "PublicDescription": "Counts the number of issue slots that were not delivered by the frontend due to BACLEARS, which occurs when the Branch Target Buffer (BTB) prediction or lack thereof, was corrected by a later branch predictor in the frontend. Includes BACLEARS due to all branch types including conditional and unconditional jumps, returns, and indirect branches.", "ScaleUnit": "100%", "Unit": "cpu_atom" @@ -132,7 +132,7 @@ "MetricExpr": "cpu_atom@TOPDOWN_BAD_SPECULATION.MISPREDICT@ / (8 * cpu_atom@CPU_CLK_UNHALTED.CORE@)", "MetricGroup": "TopdownL2;tma_L2_group;tma_bad_speculation_group", "MetricName": "tma_branch_mispredicts", - "MetricThreshold": "(tma_branch_mispredicts >0.05) & ((tma_bad_speculation >0.15))", + "MetricThreshold": "tma_branch_mispredicts > 0.05 & tma_bad_speculation > 0.15", "MetricgroupNoGroup": "TopdownL2", "ScaleUnit": "100%", "Unit": "cpu_atom" @@ -142,7 +142,7 @@ "MetricExpr": "cpu_atom@TOPDOWN_FE_BOUND.BRANCH_RESTEER@ / (8 * cpu_atom@CPU_CLK_UNHALTED.CORE@)", "MetricGroup": "TopdownL3;tma_L3_group;tma_ifetch_latency_group", "MetricName": "tma_branch_resteer", - "MetricThreshold": "(tma_branch_resteer >0.05) & ((tma_ifetch_latency >0.15) & ((tma_frontend_bound >0.20)))", + "MetricThreshold": "tma_branch_resteer > 0.05 & (tma_ifetch_latency > 0.15 & tma_frontend_bound > 0.2)", "ScaleUnit": "100%", "Unit": "cpu_atom" }, @@ -151,7 +151,7 @@ "MetricExpr": "cpu_atom@TOPDOWN_FE_BOUND.CISC@ / (8 * cpu_atom@CPU_CLK_UNHALTED.CORE@)", "MetricGroup": "TopdownL3;tma_L3_group;tma_ifetch_bandwidth_group", "MetricName": "tma_cisc", - "MetricThreshold": "(tma_cisc >0.05) & ((tma_ifetch_bandwidth >0.10) & ((tma_frontend_bound >0.20)))", + "MetricThreshold": "tma_cisc > 0.05 & (tma_ifetch_bandwidth > 0.1 & tma_frontend_bound > 0.2)", "ScaleUnit": "100%", "Unit": "cpu_atom" }, @@ -160,7 +160,7 @@ "MetricExpr": "cpu_atom@TOPDOWN_BE_BOUND.ALLOC_RESTRICTIONS@ / (8 * cpu_atom@CPU_CLK_UNHALTED.CORE@)", "MetricGroup": "TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_core_bound", - "MetricThreshold": "(tma_core_bound >0.10) & ((tma_backend_bound >0.10))", + "MetricThreshold": "tma_core_bound > 0.1 & tma_backend_bound > 0.1", "MetricgroupNoGroup": "TopdownL2", "ScaleUnit": "100%", "Unit": "cpu_atom" @@ -170,7 +170,7 @@ "MetricExpr": "cpu_atom@TOPDOWN_FE_BOUND.DECODE@ / (8 * cpu_atom@CPU_CLK_UNHALTED.CORE@)", "MetricGroup": "TopdownL3;tma_L3_group;tma_ifetch_bandwidth_group", "MetricName": "tma_decode", - "MetricThreshold": "(tma_decode >0.05) & ((tma_ifetch_bandwidth >0.10) & ((tma_frontend_bound >0.20)))", + "MetricThreshold": "tma_decode > 0.05 & (tma_ifetch_bandwidth > 0.1 & tma_frontend_bound > 0.2)", "ScaleUnit": "100%", "Unit": "cpu_atom" }, @@ -179,7 +179,7 @@ "MetricExpr": "cpu_atom@TOPDOWN_BAD_SPECULATION.FASTNUKE@ / (8 * cpu_atom@CPU_CLK_UNHALTED.CORE@)", "MetricGroup": "TopdownL3;tma_L3_group;tma_machine_clears_group", "MetricName": "tma_fast_nuke", - "MetricThreshold": "(tma_fast_nuke >0.05) & ((tma_machine_clears >0.05) & ((tma_bad_speculation >0.15)))", + "MetricThreshold": "tma_fast_nuke > 0.05 & (tma_machine_clears > 0.05 & tma_bad_speculation > 0.15)", "ScaleUnit": "100%", "Unit": "cpu_atom" }, @@ -189,7 +189,7 @@ "MetricExpr": "cpu_atom@TOPDOWN_FE_BOUND.ALL@ / (8 * cpu_atom@CPU_CLK_UNHALTED.CORE@)", "MetricGroup": "Default;TopdownL1;tma_L1_group", "MetricName": "tma_frontend_bound", - "MetricThreshold": "(tma_frontend_bound >0.20)", + "MetricThreshold": "tma_frontend_bound > 0.2", "MetricgroupNoGroup": "TopdownL1;Default", "ScaleUnit": "100%", "Unit": "cpu_atom" @@ -199,7 +199,7 @@ "MetricExpr": "cpu_atom@TOPDOWN_FE_BOUND.ICACHE@ / (8 * cpu_atom@CPU_CLK_UNHALTED.CORE@)", "MetricGroup": "TopdownL3;tma_L3_group;tma_ifetch_latency_group", "MetricName": "tma_icache_misses", - "MetricThreshold": "(tma_icache_misses >0.05) & ((tma_ifetch_latency >0.15) & ((tma_frontend_bound >0.20)))", + "MetricThreshold": "tma_icache_misses > 0.05 & (tma_ifetch_latency > 0.15 & tma_frontend_bound > 0.2)", "ScaleUnit": "100%", "Unit": "cpu_atom" }, @@ -208,7 +208,7 @@ "MetricExpr": "cpu_atom@TOPDOWN_FE_BOUND.FRONTEND_BANDWIDTH@ / (8 * cpu_atom@CPU_CLK_UNHALTED.CORE@)", "MetricGroup": "TopdownL2;tma_L2_group;tma_frontend_bound_group", "MetricName": "tma_ifetch_bandwidth", - "MetricThreshold": "(tma_ifetch_bandwidth >0.10) & ((tma_frontend_bound >0.20))", + "MetricThreshold": "tma_ifetch_bandwidth > 0.1 & tma_frontend_bound > 0.2", "MetricgroupNoGroup": "TopdownL2", "ScaleUnit": "100%", "Unit": "cpu_atom" @@ -218,7 +218,7 @@ "MetricExpr": "cpu_atom@TOPDOWN_FE_BOUND.FRONTEND_LATENCY@ / (8 * cpu_atom@CPU_CLK_UNHALTED.CORE@)", "MetricGroup": "TopdownL2;tma_L2_group;tma_frontend_bound_group", "MetricName": "tma_ifetch_latency", - "MetricThreshold": "(tma_ifetch_latency >0.15) & ((tma_frontend_bound >0.20))", + "MetricThreshold": "tma_ifetch_latency > 0.15 & tma_frontend_bound > 0.2", "MetricgroupNoGroup": "TopdownL2", "ScaleUnit": "100%", "Unit": "cpu_atom" @@ -578,7 +578,7 @@ "BriefDescription": "PerfMon Event Multiplexing accuracy indicator", "MetricExpr": "cpu_atom@CPU_CLK_UNHALTED.CORE_P@ / cpu_atom@CPU_CLK_UNHALTED.CORE@", "MetricName": "tma_info_system_mux", - "MetricThreshold": "((tma_info_system_mux > 1.1)|(tma_info_system_mux < 0.9))", + "MetricThreshold": "tma_info_system_mux > 1.1 | tma_info_system_mux < 0.9", "Unit": "cpu_atom" }, { @@ -617,7 +617,7 @@ "MetricExpr": "cpu_atom@TOPDOWN_FE_BOUND.ITLB_MISS@ / (8 * cpu_atom@CPU_CLK_UNHALTED.CORE@)", "MetricGroup": "TopdownL3;tma_L3_group;tma_ifetch_latency_group", "MetricName": "tma_itlb_misses", - "MetricThreshold": "(tma_itlb_misses >0.05) & ((tma_ifetch_latency >0.15) & ((tma_frontend_bound >0.20)))", + "MetricThreshold": "tma_itlb_misses > 0.05 & (tma_ifetch_latency > 0.15 & tma_frontend_bound > 0.2)", "ScaleUnit": "100%", "Unit": "cpu_atom" }, @@ -626,7 +626,7 @@ "MetricExpr": "cpu_atom@TOPDOWN_BAD_SPECULATION.MACHINE_CLEARS@ / (8 * cpu_atom@CPU_CLK_UNHALTED.CORE@)", "MetricGroup": "TopdownL2;tma_L2_group;tma_bad_speculation_group", "MetricName": "tma_machine_clears", - "MetricThreshold": "(tma_machine_clears >0.05) & ((tma_bad_speculation >0.15))", + "MetricThreshold": "tma_machine_clears > 0.05 & tma_bad_speculation > 0.15", "MetricgroupNoGroup": "TopdownL2", "ScaleUnit": "100%", "Unit": "cpu_atom" @@ -636,7 +636,7 @@ "MetricExpr": "cpu_atom@TOPDOWN_BE_BOUND.MEM_SCHEDULER@ / (8 * cpu_atom@CPU_CLK_UNHALTED.CORE@)", "MetricGroup": "TopdownL3;tma_L3_group;tma_resource_bound_group", "MetricName": "tma_mem_scheduler", - "MetricThreshold": "(tma_mem_scheduler >0.10) & ((tma_resource_bound >0.20) & ((tma_backend_bound >0.10)))", + "MetricThreshold": "tma_mem_scheduler > 0.1 & (tma_resource_bound > 0.2 & tma_backend_bound > 0.1)", "ScaleUnit": "100%", "Unit": "cpu_atom" }, @@ -645,7 +645,7 @@ "MetricExpr": "cpu_atom@TOPDOWN_BE_BOUND.NON_MEM_SCHEDULER@ / (8 * cpu_atom@CPU_CLK_UNHALTED.CORE@)", "MetricGroup": "TopdownL3;tma_L3_group;tma_resource_bound_group", "MetricName": "tma_non_mem_scheduler", - "MetricThreshold": "(tma_non_mem_scheduler >0.10) & ((tma_resource_bound >0.20) & ((tma_backend_bound >0.10)))", + "MetricThreshold": "tma_non_mem_scheduler > 0.1 & (tma_resource_bound > 0.2 & tma_backend_bound > 0.1)", "ScaleUnit": "100%", "Unit": "cpu_atom" }, @@ -654,7 +654,7 @@ "MetricExpr": "cpu_atom@TOPDOWN_BAD_SPECULATION.NUKE@ / (8 * cpu_atom@CPU_CLK_UNHALTED.CORE@)", "MetricGroup": "TopdownL3;tma_L3_group;tma_machine_clears_group", "MetricName": "tma_nuke", - "MetricThreshold": "(tma_nuke >0.05) & ((tma_machine_clears >0.05) & ((tma_bad_speculation >0.15)))", + "MetricThreshold": "tma_nuke > 0.05 & (tma_machine_clears > 0.05 & tma_bad_speculation > 0.15)", "ScaleUnit": "100%", "Unit": "cpu_atom" }, @@ -663,7 +663,7 @@ "MetricExpr": "cpu_atom@TOPDOWN_FE_BOUND.OTHER@ / (8 * cpu_atom@CPU_CLK_UNHALTED.CORE@)", "MetricGroup": "TopdownL3;tma_L3_group;tma_ifetch_bandwidth_group", "MetricName": "tma_other_fb", - "MetricThreshold": "(tma_other_fb >0.05) & ((tma_ifetch_bandwidth >0.10) & ((tma_frontend_bound >0.20)))", + "MetricThreshold": "tma_other_fb > 0.05 & (tma_ifetch_bandwidth > 0.1 & tma_frontend_bound > 0.2)", "ScaleUnit": "100%", "Unit": "cpu_atom" }, @@ -672,7 +672,7 @@ "MetricExpr": "cpu_atom@TOPDOWN_FE_BOUND.PREDECODE@ / (8 * cpu_atom@CPU_CLK_UNHALTED.CORE@)", "MetricGroup": "TopdownL3;tma_L3_group;tma_ifetch_bandwidth_group", "MetricName": "tma_predecode", - "MetricThreshold": "(tma_predecode >0.05) & ((tma_ifetch_bandwidth >0.10) & ((tma_frontend_bound >0.20)))", + "MetricThreshold": "tma_predecode > 0.05 & (tma_ifetch_bandwidth > 0.1 & tma_frontend_bound > 0.2)", "ScaleUnit": "100%", "Unit": "cpu_atom" }, @@ -681,7 +681,7 @@ "MetricExpr": "cpu_atom@TOPDOWN_BE_BOUND.REGISTER@ / (8 * cpu_atom@CPU_CLK_UNHALTED.CORE@)", "MetricGroup": "TopdownL3;tma_L3_group;tma_resource_bound_group", "MetricName": "tma_register", - "MetricThreshold": "(tma_register >0.10) & ((tma_resource_bound >0.20) & ((tma_backend_bound >0.10)))", + "MetricThreshold": "tma_register > 0.1 & (tma_resource_bound > 0.2 & tma_backend_bound > 0.1)", "ScaleUnit": "100%", "Unit": "cpu_atom" }, @@ -690,7 +690,7 @@ "MetricExpr": "cpu_atom@TOPDOWN_BE_BOUND.REORDER_BUFFER@ / (8 * cpu_atom@CPU_CLK_UNHALTED.CORE@)", "MetricGroup": "TopdownL3;tma_L3_group;tma_resource_bound_group", "MetricName": "tma_reorder_buffer", - "MetricThreshold": "(tma_reorder_buffer >0.10) & ((tma_resource_bound >0.20) & ((tma_backend_bound >0.10)))", + "MetricThreshold": "tma_reorder_buffer > 0.1 & (tma_resource_bound > 0.2 & tma_backend_bound > 0.1)", "ScaleUnit": "100%", "Unit": "cpu_atom" }, @@ -699,7 +699,7 @@ "MetricExpr": "tma_backend_bound - tma_core_bound", "MetricGroup": "TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_resource_bound", - "MetricThreshold": "(tma_resource_bound >0.20) & ((tma_backend_bound >0.10))", + "MetricThreshold": "tma_resource_bound > 0.2 & tma_backend_bound > 0.1", "MetricgroupNoGroup": "TopdownL2", "ScaleUnit": "100%", "Unit": "cpu_atom" @@ -710,7 +710,7 @@ "MetricExpr": "cpu_atom@TOPDOWN_RETIRING.ALL@ / (8 * cpu_atom@CPU_CLK_UNHALTED.CORE@)", "MetricGroup": "Default;TopdownL1;tma_L1_group", "MetricName": "tma_retiring", - "MetricThreshold": "(tma_retiring >0.75)", + "MetricThreshold": "tma_retiring > 0.75", "MetricgroupNoGroup": "TopdownL1;Default", "ScaleUnit": "100%", "Unit": "cpu_atom" @@ -720,12 +720,12 @@ "MetricExpr": "cpu_atom@TOPDOWN_BE_BOUND.SERIALIZATION@ / (8 * cpu_atom@CPU_CLK_UNHALTED.CORE@)", "MetricGroup": "TopdownL3;tma_L3_group;tma_resource_bound_group", "MetricName": "tma_serialization", - "MetricThreshold": "(tma_serialization >0.10) & ((tma_resource_bound >0.20) & ((tma_backend_bound >0.10)))", + "MetricThreshold": "tma_serialization > 0.1 & (tma_resource_bound > 0.2 & tma_backend_bound > 0.1)", "ScaleUnit": "100%", "Unit": "cpu_atom" }, { - "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution ports for ALU operations", + "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution ports for ALU operations.", "MetricExpr": "cpu_core@UOPS_DISPATCHED.ALU@ / (6 * tma_info_thread_clks)", "MetricGroup": "TopdownL5;tma_L5_group;tma_ports_utilized_3m_group", "MetricName": "tma_alu_op_utilization", @@ -738,13 +738,13 @@ "MetricExpr": "78 * cpu_core@ASSISTS.ANY@ / tma_info_thread_slots", "MetricGroup": "BvIO;TopdownL4;tma_L4_group;tma_microcode_sequencer_group", "MetricName": "tma_assists", - "MetricThreshold": "tma_assists > 0.1 & tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1", + "MetricThreshold": "tma_assists > 0.1 & (tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1)", "PublicDescription": "This metric estimates fraction of slots the CPU retired uops delivered by the Microcode_Sequencer as a result of Assists. Assists are long sequences of uops that are required in certain corner-cases for operations that cannot be handled natively by the execution pipeline. For example; when working with very small floating point values (so-called Denormals); the FP units are not set up to perform these operations natively. Instead; a sequence of instructions to perform the computation on the Denormals is injected into the pipeline. Since these microcode sequences might be dozens of uops long; Assists can be extremely deleterious to performance and they can be avoided in many cases. Sample with: ASSISTS.ANY", "ScaleUnit": "100%", "Unit": "cpu_core" }, { - "BriefDescription": "This metric estimates fraction of slots the CPU retired uops as a result of handing SSE to AVX* or AVX* to SSE transition Assists", + "BriefDescription": "This metric estimates fraction of slots the CPU retired uops as a result of handing SSE to AVX* or AVX* to SSE transition Assists.", "MetricExpr": "63 * cpu_core@ASSISTS.SSE_AVX_MIX@ / tma_info_thread_slots", "MetricGroup": "HPC;TopdownL5;tma_L5_group;tma_assists_group", "MetricName": "tma_avx_assists", @@ -755,7 +755,7 @@ { "BriefDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend", "DefaultMetricgroupName": "TopdownL1", - "MetricExpr": "topdown\\-be\\-bound / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * slots", + "MetricExpr": "cpu_core@topdown\\-be\\-bound@ / (cpu_core@topdown\\-fe\\-bound@ + cpu_core@topdown\\-bad\\-spec@ + cpu_core@topdown\\-retiring@ + cpu_core@topdown\\-be\\-bound@) + 0 * tma_info_thread_slots", "MetricGroup": "BvOB;Default;TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_backend_bound", "MetricThreshold": "tma_backend_bound > 0.2", @@ -767,18 +767,18 @@ { "BriefDescription": "This category represents fraction of slots wasted due to incorrect speculations", "DefaultMetricgroupName": "TopdownL1", - "MetricExpr": "topdown\\-bad\\-spec / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * slots", + "MetricExpr": "cpu_core@topdown\\-bad\\-spec@ / (cpu_core@topdown\\-fe\\-bound@ + cpu_core@topdown\\-bad\\-spec@ + cpu_core@topdown\\-retiring@ + cpu_core@topdown\\-be\\-bound@) + 0 * tma_info_thread_slots", "MetricGroup": "Default;TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_bad_speculation", "MetricThreshold": "tma_bad_speculation > 0.15", "MetricgroupNoGroup": "TopdownL1;Default", - "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example", + "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.", "ScaleUnit": "100%", "Unit": "cpu_core" }, { "BriefDescription": "Total pipeline cost of instruction fetch related bottlenecks by large code footprint programs (i-side cache; TLB and BTB misses)", - "MetricExpr": "100 * tma_fetch_latency * (tma_itlb_misses + tma_icache_misses + tma_unknown_branches) / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches)", + "MetricExpr": "100 * tma_fetch_latency * (tma_itlb_misses + tma_icache_misses + tma_unknown_branches) / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches)", "MetricGroup": "BigFootprint;BvBC;Fed;Frontend;IcMiss;MemoryTLB", "MetricName": "tma_bottleneck_big_code", "MetricThreshold": "tma_bottleneck_big_code > 20", @@ -795,16 +795,16 @@ }, { "BriefDescription": "Total pipeline cost of external Memory- or Cache-Bandwidth related bottlenecks", - "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_mem_bandwidth / (tma_mem_bandwidth + tma_mem_latency)) + tma_memory_bound * (tma_l3_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_sq_full / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_memory_bound * (tma_l1_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_fb_full / (tma_dtlb_load + tma_store_fwd_blk + tma_l1_latency_dependency + tma_l1_latency_capacity + tma_lock_latency + tma_split_loads + tma_fb_full)))", + "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_mem_bandwidth / (tma_mem_bandwidth + tma_mem_latency)) + tma_memory_bound * (tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_sq_full / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_fb_full / (tma_dtlb_load + tma_fb_full + tma_l1_latency_capacity + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)))", "MetricGroup": "BvMB;Mem;MemoryBW;Offcore;tma_issueBW", "MetricName": "tma_bottleneck_cache_memory_bandwidth", "MetricThreshold": "tma_bottleneck_cache_memory_bandwidth > 20", - "PublicDescription": "Total pipeline cost of external Memory- or Cache-Bandwidth related bottlenecks. Related metrics: tma_fb_full, tma_mem_bandwidth, tma_sq_full", + "PublicDescription": "Total pipeline cost of external Memory- or Cache-Bandwidth related bottlenecks. Related metrics: tma_fb_full, tma_info_system_dram_bw_use, tma_mem_bandwidth, tma_sq_full", "Unit": "cpu_core" }, { "BriefDescription": "Total pipeline cost of external Memory- or Cache-Latency related bottlenecks", - "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_mem_latency / (tma_mem_bandwidth + tma_mem_latency)) + tma_memory_bound * (tma_l3_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_l3_hit_latency / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_memory_bound * tma_l2_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound) + tma_memory_bound * (tma_l1_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_l1_latency_dependency / (tma_dtlb_load + tma_store_fwd_blk + tma_l1_latency_dependency + tma_l1_latency_capacity + tma_lock_latency + tma_split_loads + tma_fb_full)) + tma_memory_bound * (tma_l1_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_l1_latency_capacity / (tma_dtlb_load + tma_store_fwd_blk + tma_l1_latency_dependency + tma_l1_latency_capacity + tma_lock_latency + tma_split_loads + tma_fb_full)) + tma_memory_bound * (tma_l1_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_lock_latency / (tma_dtlb_load + tma_store_fwd_blk + tma_l1_latency_dependency + tma_l1_latency_capacity + tma_lock_latency + tma_split_loads + tma_fb_full)) + tma_memory_bound * (tma_l1_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_split_loads / (tma_dtlb_load + tma_store_fwd_blk + tma_l1_latency_dependency + tma_l1_latency_capacity + tma_lock_latency + tma_split_loads + tma_fb_full)) + tma_memory_bound * (tma_store_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_split_stores / (tma_store_latency + tma_false_sharing + tma_split_stores + tma_streaming_stores + tma_dtlb_store)) + tma_memory_bound * (tma_store_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_store_latency / (tma_store_latency + tma_false_sharing + tma_split_stores + tma_streaming_stores + tma_dtlb_store)))", + "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_mem_latency / (tma_mem_bandwidth + tma_mem_latency)) + tma_memory_bound * (tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_l3_hit_latency / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_memory_bound * tma_l2_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) + tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_l1_latency_dependency / (tma_dtlb_load + tma_fb_full + tma_l1_latency_capacity + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_l1_latency_capacity / (tma_dtlb_load + tma_fb_full + tma_l1_latency_capacity + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_lock_latency / (tma_dtlb_load + tma_fb_full + tma_l1_latency_capacity + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_split_loads / (tma_dtlb_load + tma_fb_full + tma_l1_latency_capacity + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_memory_bound * (tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_split_stores / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency + tma_streaming_stores)) + tma_memory_bound * (tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_store_latency / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency + tma_streaming_stores)))", "MetricGroup": "BvML;Mem;MemoryLat;Offcore;tma_issueLat", "MetricName": "tma_bottleneck_cache_memory_latency", "MetricThreshold": "tma_bottleneck_cache_memory_latency > 20", @@ -813,16 +813,16 @@ }, { "BriefDescription": "Total pipeline cost when the execution is compute-bound - an estimation", - "MetricExpr": "100 * (tma_core_bound * tma_divider / (tma_divider + tma_serializing_operation + tma_ports_utilization) + tma_core_bound * (tma_ports_utilization / (tma_divider + tma_serializing_operation + tma_ports_utilization)) * (tma_ports_utilized_3m / (tma_ports_utilized_0 + tma_ports_utilized_1 + tma_ports_utilized_2 + tma_ports_utilized_3m)))", + "MetricExpr": "100 * (tma_core_bound * tma_divider / (tma_divider + tma_ports_utilization + tma_serializing_operation) + tma_core_bound * (tma_ports_utilization / (tma_divider + tma_ports_utilization + tma_serializing_operation)) * (tma_ports_utilized_3m / (tma_ports_utilized_0 + tma_ports_utilized_1 + tma_ports_utilized_2 + tma_ports_utilized_3m)))", "MetricGroup": "BvCB;Cor;tma_issueComp", "MetricName": "tma_bottleneck_compute_bound_est", "MetricThreshold": "tma_bottleneck_compute_bound_est > 20", - "PublicDescription": "Total pipeline cost when the execution is compute-bound - an estimation. Covers Core Bound when High ILP as well as when long-latency execution units are busy", + "PublicDescription": "Total pipeline cost when the execution is compute-bound - an estimation. Covers Core Bound when High ILP as well as when long-latency execution units are busy. Related metrics: ", "Unit": "cpu_core" }, { "BriefDescription": "Total pipeline cost of instruction fetch bandwidth related bottlenecks (when the front-end could not sustain operations delivery to the back-end)", - "MetricExpr": "100 * (tma_frontend_bound - (1 - 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts) * tma_fetch_latency * tma_mispredicts_resteers / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches) - (1 - cpu_core@INST_RETIRED.REP_ITERATION@ / cpu_core@UOPS_RETIRED.MS\\,cmask\\=0x1@) * (tma_fetch_latency * (tma_ms_switches + tma_branch_resteers * (tma_clears_resteers + tma_mispredicts_resteers * tma_other_mispredicts / tma_branch_mispredicts) / (tma_mispredicts_resteers + tma_clears_resteers + tma_unknown_branches)) / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches) + tma_fetch_bandwidth * tma_ms / (tma_mite + tma_dsb + tma_lsd + tma_ms))) - tma_bottleneck_big_code", + "MetricExpr": "100 * (tma_frontend_bound - (1 - 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts) * tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) - (1 - cpu_core@INST_RETIRED.REP_ITERATION@ / cpu_core@UOPS_RETIRED.MS\\,cmask\\=1@) * (tma_fetch_latency * (tma_ms_switches + tma_branch_resteers * (tma_clears_resteers + tma_mispredicts_resteers * tma_other_mispredicts / tma_branch_mispredicts) / (tma_clears_resteers + tma_mispredicts_resteers + tma_unknown_branches)) / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) + tma_fetch_bandwidth * tma_ms / (tma_dsb + tma_lsd + tma_mite + tma_ms))) - tma_bottleneck_big_code", "MetricGroup": "BvFB;Fed;FetchBW;Frontend", "MetricName": "tma_bottleneck_instruction_fetch_bw", "MetricThreshold": "tma_bottleneck_instruction_fetch_bw > 20", @@ -830,7 +830,7 @@ }, { "BriefDescription": "Total pipeline cost of irregular execution (e.g", - "MetricExpr": "100 * ((1 - cpu_core@INST_RETIRED.REP_ITERATION@ / cpu_core@UOPS_RETIRED.MS\\,cmask\\=0x1@) * (tma_fetch_latency * (tma_ms_switches + tma_branch_resteers * (tma_clears_resteers + tma_mispredicts_resteers * tma_other_mispredicts / tma_branch_mispredicts) / (tma_mispredicts_resteers + tma_clears_resteers + tma_unknown_branches)) / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches) + tma_fetch_bandwidth * tma_ms / (tma_mite + tma_dsb + tma_lsd + tma_ms)) + 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts * tma_branch_mispredicts + tma_machine_clears * tma_other_nukes / tma_other_nukes + tma_core_bound * (tma_serializing_operation + cpu_core@RS.EMPTY_RESOURCE@ / tma_info_thread_clks * tma_ports_utilized_0) / (tma_divider + tma_serializing_operation + tma_ports_utilization) + tma_microcode_sequencer / (tma_microcode_sequencer + tma_few_uops_instructions) * (tma_assists / tma_microcode_sequencer) * tma_heavy_operations)", + "MetricExpr": "100 * ((1 - cpu_core@INST_RETIRED.REP_ITERATION@ / cpu_core@UOPS_RETIRED.MS\\,cmask\\=1@) * (tma_fetch_latency * (tma_ms_switches + tma_branch_resteers * (tma_clears_resteers + tma_mispredicts_resteers * tma_other_mispredicts / tma_branch_mispredicts) / (tma_clears_resteers + tma_mispredicts_resteers + tma_unknown_branches)) / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) + tma_fetch_bandwidth * tma_ms / (tma_dsb + tma_lsd + tma_mite + tma_ms)) + 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts * tma_branch_mispredicts + tma_machine_clears * tma_other_nukes / tma_other_nukes + tma_core_bound * (tma_serializing_operation + cpu_core@RS.EMPTY_RESOURCE@ / tma_info_thread_clks * tma_ports_utilized_0) / (tma_divider + tma_ports_utilization + tma_serializing_operation) + tma_microcode_sequencer / (tma_microcode_sequencer + tma_few_uops_instructions) * (tma_assists / tma_microcode_sequencer) * tma_heavy_operations)", "MetricGroup": "Bad;BvIO;Cor;Ret;tma_issueMS", "MetricName": "tma_bottleneck_irregular_overhead", "MetricThreshold": "tma_bottleneck_irregular_overhead > 10", @@ -839,7 +839,7 @@ }, { "BriefDescription": "Total pipeline cost of Memory Address Translation related bottlenecks (data-side TLBs)", - "MetricExpr": "100 * (tma_memory_bound * (tma_l1_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_dtlb_load / (tma_dtlb_load + tma_store_fwd_blk + tma_l1_latency_dependency + tma_l1_latency_capacity + tma_lock_latency + tma_split_loads + tma_fb_full)) + tma_memory_bound * (tma_store_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_dtlb_store / (tma_store_latency + tma_false_sharing + tma_split_stores + tma_streaming_stores + tma_dtlb_store)))", + "MetricExpr": "100 * (tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_dtlb_load / (tma_dtlb_load + tma_fb_full + tma_l1_latency_capacity + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_memory_bound * (tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_dtlb_store / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency + tma_streaming_stores)))", "MetricGroup": "BvMT;Mem;MemoryTLB;Offcore;tma_issueTLB", "MetricName": "tma_bottleneck_memory_data_tlbs", "MetricThreshold": "tma_bottleneck_memory_data_tlbs > 20", @@ -848,16 +848,16 @@ }, { "BriefDescription": "Total pipeline cost of Memory Synchronization related bottlenecks (data transfers and coherency updates across processors)", - "MetricExpr": "100 * (tma_memory_bound * (tma_l3_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound) * (tma_contested_accesses + tma_data_sharing) / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full) + tma_store_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound) * tma_false_sharing / (tma_store_latency + tma_false_sharing + tma_split_stores + tma_streaming_stores + tma_dtlb_store - tma_store_latency)) + tma_machine_clears * (1 - tma_other_nukes / tma_other_nukes))", + "MetricExpr": "100 * (tma_memory_bound * (tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_contested_accesses + tma_data_sharing) / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full) + tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * tma_false_sharing / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency + tma_streaming_stores - tma_store_latency)) + tma_machine_clears * (1 - tma_other_nukes / tma_other_nukes))", "MetricGroup": "BvMS;LockCont;Mem;Offcore;tma_issueSyncxn", "MetricName": "tma_bottleneck_memory_synchronization", "MetricThreshold": "tma_bottleneck_memory_synchronization > 10", - "PublicDescription": "Total pipeline cost of Memory Synchronization related bottlenecks (data transfers and coherency updates across processors). Related metrics: tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_machine_clears", + "PublicDescription": "Total pipeline cost of Memory Synchronization related bottlenecks (data transfers and coherency updates across processors). Related metrics: tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_machine_clears, tma_remote_cache", "Unit": "cpu_core" }, { "BriefDescription": "Total pipeline cost of Branch Misprediction related bottlenecks", - "MetricExpr": "100 * (1 - 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts) * (tma_branch_mispredicts + tma_fetch_latency * tma_mispredicts_resteers / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches))", + "MetricExpr": "100 * (1 - 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts) * (tma_branch_mispredicts + tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches))", "MetricGroup": "Bad;BadSpec;BrMispredicts;BvMP;tma_issueBM", "MetricName": "tma_bottleneck_mispredictions", "MetricThreshold": "tma_bottleneck_mispredictions > 20", @@ -870,11 +870,11 @@ "MetricGroup": "BvOB;Cor;Offcore", "MetricName": "tma_bottleneck_other_bottlenecks", "MetricThreshold": "tma_bottleneck_other_bottlenecks > 20", - "PublicDescription": "Total pipeline cost of remaining bottlenecks in the back-end. Examples include data-dependencies (Core Bound when Low ILP) and other unlisted memory-related stalls", + "PublicDescription": "Total pipeline cost of remaining bottlenecks in the back-end. Examples include data-dependencies (Core Bound when Low ILP) and other unlisted memory-related stalls.", "Unit": "cpu_core" }, { - "BriefDescription": "Total pipeline cost of \"useful operations\" - the portion of Retiring category not covered by Branching_Overhead nor Irregular_Overhead", + "BriefDescription": "Total pipeline cost of \"useful operations\" - the portion of Retiring category not covered by Branching_Overhead nor Irregular_Overhead.", "MetricExpr": "100 * (tma_retiring - (cpu_core@BR_INST_RETIRED.ALL_BRANCHES@ + 2 * cpu_core@BR_INST_RETIRED.NEAR_CALL@ + cpu_core@INST_RETIRED.NOP@) / tma_info_thread_slots - tma_microcode_sequencer / (tma_microcode_sequencer + tma_few_uops_instructions) * (tma_assists / tma_microcode_sequencer) * tma_heavy_operations)", "MetricGroup": "BvUW;Ret", "MetricName": "tma_bottleneck_useful_work", @@ -883,7 +883,7 @@ }, { "BriefDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction", - "MetricExpr": "topdown\\-br\\-mispredict / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * slots", + "MetricExpr": "cpu_core@topdown\\-br\\-mispredict@ / (cpu_core@topdown\\-fe\\-bound@ + cpu_core@topdown\\-bad\\-spec@ + cpu_core@topdown\\-retiring@ + cpu_core@topdown\\-be\\-bound@) + 0 * tma_info_thread_slots", "MetricGroup": "BadSpec;BrMispredicts;BvMP;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueBM", "MetricName": "tma_branch_mispredicts", "MetricThreshold": "tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", @@ -897,26 +897,26 @@ "MetricExpr": "cpu_core@INT_MISC.CLEAR_RESTEER_CYCLES@ / tma_info_thread_clks + tma_unknown_branches", "MetricGroup": "FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group", "MetricName": "tma_branch_resteers", - "MetricThreshold": "tma_branch_resteers > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", - "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers. Branch Resteers estimates the Frontend delay in fetching operations from corrected path; following all sorts of miss-predicted branches. For example; branchy code with lots of miss-predictions might get categorized under Branch Resteers. Note the value of this node may overlap with its siblings. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_l3_hit_latency, tma_store_latency", + "MetricThreshold": "tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers. Branch Resteers estimates the Frontend delay in fetching operations from corrected path; following all sorts of miss-predicted branches. For example; branchy code with lots of miss-predictions might get categorized under Branch Resteers. Note the value of this node may overlap with its siblings. Sample with: BR_MISP_RETIRED.ALL_BRANCHES", "ScaleUnit": "100%", "Unit": "cpu_core" }, { - "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due staying in C0.1 power-performance optimized state (Faster wakeup time; Smaller power savings)", + "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due staying in C0.1 power-performance optimized state (Faster wakeup time; Smaller power savings).", "MetricExpr": "cpu_core@CPU_CLK_UNHALTED.C01@ / tma_info_thread_clks", "MetricGroup": "C0Wait;TopdownL4;tma_L4_group;tma_serializing_operation_group", "MetricName": "tma_c01_wait", - "MetricThreshold": "tma_c01_wait > 0.05 & tma_serializing_operation > 0.1 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_c01_wait > 0.05 & (tma_serializing_operation > 0.1 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", "ScaleUnit": "100%", "Unit": "cpu_core" }, { - "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due staying in C0.2 power-performance optimized state (Slower wakeup time; Larger power savings)", + "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due staying in C0.2 power-performance optimized state (Slower wakeup time; Larger power savings).", "MetricExpr": "cpu_core@CPU_CLK_UNHALTED.C02@ / tma_info_thread_clks", "MetricGroup": "C0Wait;TopdownL4;tma_L4_group;tma_serializing_operation_group", "MetricName": "tma_c02_wait", - "MetricThreshold": "tma_c02_wait > 0.05 & tma_serializing_operation > 0.1 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_c02_wait > 0.05 & (tma_serializing_operation > 0.1 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -925,8 +925,8 @@ "MetricExpr": "max(0, tma_microcode_sequencer - tma_assists)", "MetricGroup": "TopdownL4;tma_L4_group;tma_microcode_sequencer_group", "MetricName": "tma_cisc", - "MetricThreshold": "tma_cisc > 0.1 & tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1", - "PublicDescription": "This metric estimates fraction of cycles the CPU retired uops originated from CISC (complex instruction set computer) instruction. A CISC instruction has multiple uops that are required to perform the instruction's functionality as in the case of read-modify-write as an example. Since these instructions require multiple uops they may or may not imply sub-optimal use of machine resources", + "MetricThreshold": "tma_cisc > 0.1 & (tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1)", + "PublicDescription": "This metric estimates fraction of cycles the CPU retired uops originated from CISC (complex instruction set computer) instruction. A CISC instruction has multiple uops that are required to perform the instruction's functionality as in the case of read-modify-write as an example. Since these instructions require multiple uops they may or may not imply sub-optimal use of machine resources.", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -935,99 +935,100 @@ "MetricExpr": "(1 - tma_branch_mispredicts / tma_bad_speculation) * cpu_core@INT_MISC.CLEAR_RESTEER_CYCLES@ / tma_info_thread_clks", "MetricGroup": "BadSpec;MachineClears;TopdownL4;tma_L4_group;tma_branch_resteers_group;tma_issueMC", "MetricName": "tma_clears_resteers", - "MetricThreshold": "tma_clears_resteers > 0.05 & tma_branch_resteers > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricThreshold": "tma_clears_resteers > 0.05 & (tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))", "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Machine Clears. Sample with: INT_MISC.CLEAR_RESTEER_CYCLES. Related metrics: tma_l1_bound, tma_machine_clears, tma_microcode_sequencer, tma_ms_switches", "ScaleUnit": "100%", "Unit": "cpu_core" }, { - "BriefDescription": "This metric estimates fraction of cycles the CPU was stalled due to instruction cache misses that hit in the L2 cache", - "MetricExpr": "max(0, cpu_core@FRONTEND_RETIRED.L1I_MISS@ * cpu_core@frontend_retired.l1i_miss@R / tma_info_thread_clks - tma_code_l2_miss)", + "BriefDescription": "This metric estimates fraction of cycles the CPU was stalled due to instruction cache misses that hit in the L2 cache.", + "MetricExpr": "max(0, cpu_core@FRONTEND_RETIRED.L1I_MISS@ * cpu_core@FRONTEND_RETIRED.L1I_MISS@R / tma_info_thread_clks - tma_code_l2_miss)", "MetricGroup": "FetchLat;IcMiss;Offcore;TopdownL4;tma_L4_group;tma_icache_misses_group", "MetricName": "tma_code_l2_hit", - "MetricThreshold": "tma_code_l2_hit > 0.05 & tma_icache_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricThreshold": "tma_code_l2_hit > 0.05 & (tma_icache_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))", "ScaleUnit": "100%", "Unit": "cpu_core" }, { - "BriefDescription": "This metric estimates fraction of cycles the CPU was stalled due to instruction cache misses that miss in the L2 cache", - "MetricExpr": "cpu_core@FRONTEND_RETIRED.L2_MISS@ * cpu_core@frontend_retired.l2_miss@R / tma_info_thread_clks", + "BriefDescription": "This metric estimates fraction of cycles the CPU was stalled due to instruction cache misses that miss in the L2 cache.", + "MetricExpr": "cpu_core@FRONTEND_RETIRED.L2_MISS@ * cpu_core@FRONTEND_RETIRED.L2_MISS@R / tma_info_thread_clks", "MetricGroup": "FetchLat;IcMiss;Offcore;TopdownL4;tma_L4_group;tma_icache_misses_group", "MetricName": "tma_code_l2_miss", - "MetricThreshold": "tma_code_l2_miss > 0.05 & tma_icache_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricThreshold": "tma_code_l2_miss > 0.05 & (tma_icache_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))", "ScaleUnit": "100%", "Unit": "cpu_core" }, { "BriefDescription": "This metric roughly estimates the fraction of cycles where the (first level) ITLB was missed by instructions fetches, that later on hit in second-level TLB (STLB)", - "MetricExpr": "max(0, cpu_core@FRONTEND_RETIRED.ITLB_MISS@ * cpu_core@frontend_retired.itlb_miss@R / tma_info_thread_clks - tma_code_stlb_miss)", + "MetricExpr": "max(0, cpu_core@FRONTEND_RETIRED.ITLB_MISS@ * cpu_core@FRONTEND_RETIRED.ITLB_MISS@R / tma_info_thread_clks - tma_code_stlb_miss)", "MetricGroup": "FetchLat;MemoryTLB;TopdownL4;tma_L4_group;tma_itlb_misses_group", "MetricName": "tma_code_stlb_hit", - "MetricThreshold": "tma_code_stlb_hit > 0.05 & tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricThreshold": "tma_code_stlb_hit > 0.05 & (tma_itlb_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))", "ScaleUnit": "100%", "Unit": "cpu_core" }, { "BriefDescription": "This metric estimates the fraction of cycles where the Second-level TLB (STLB) was missed by instruction fetches, performing a hardware page walk", - "MetricExpr": "cpu_core@FRONTEND_RETIRED.STLB_MISS@ * cpu_core@frontend_retired.stlb_miss@R / tma_info_thread_clks", + "MetricExpr": "cpu_core@FRONTEND_RETIRED.STLB_MISS@ * cpu_core@FRONTEND_RETIRED.STLB_MISS@R / tma_info_thread_clks", "MetricGroup": "FetchLat;MemoryTLB;TopdownL4;tma_L4_group;tma_itlb_misses_group", "MetricName": "tma_code_stlb_miss", - "MetricThreshold": "tma_code_stlb_miss > 0.05 & tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricThreshold": "tma_code_stlb_miss > 0.05 & (tma_itlb_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))", "ScaleUnit": "100%", "Unit": "cpu_core" }, { - "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 2 or 4 MB pages for (instruction) code accesses", + "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 2 or 4 MB pages for (instruction) code accesses.", "MetricExpr": "cpu_core@ITLB_MISSES.WALK_ACTIVE@ / tma_info_thread_clks * cpu_core@ITLB_MISSES.WALK_COMPLETED_2M_4M@ / (cpu_core@ITLB_MISSES.WALK_COMPLETED_4K@ + cpu_core@ITLB_MISSES.WALK_COMPLETED_2M_4M@)", "MetricGroup": "FetchLat;MemoryTLB;TopdownL5;tma_L5_group;tma_code_stlb_miss_group", "MetricName": "tma_code_stlb_miss_2m", - "MetricThreshold": "tma_code_stlb_miss_2m > 0.05 & tma_code_stlb_miss > 0.05 & tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricThreshold": "tma_code_stlb_miss_2m > 0.05 & (tma_code_stlb_miss > 0.05 & (tma_itlb_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)))", "ScaleUnit": "100%", "Unit": "cpu_core" }, { - "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 4 KB pages for (instruction) code accesses", + "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 4 KB pages for (instruction) code accesses.", "MetricExpr": "cpu_core@ITLB_MISSES.WALK_ACTIVE@ / tma_info_thread_clks * cpu_core@ITLB_MISSES.WALK_COMPLETED_4K@ / (cpu_core@ITLB_MISSES.WALK_COMPLETED_4K@ + cpu_core@ITLB_MISSES.WALK_COMPLETED_2M_4M@)", "MetricGroup": "FetchLat;MemoryTLB;TopdownL5;tma_L5_group;tma_code_stlb_miss_group", "MetricName": "tma_code_stlb_miss_4k", - "MetricThreshold": "tma_code_stlb_miss_4k > 0.05 & tma_code_stlb_miss > 0.05 & tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricThreshold": "tma_code_stlb_miss_4k > 0.05 & (tma_code_stlb_miss > 0.05 & (tma_itlb_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)))", "ScaleUnit": "100%", "Unit": "cpu_core" }, { - "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to retired misprediction by non-taken conditional branches", - "MetricExpr": "cpu_core@BR_MISP_RETIRED.COND_NTAKEN_COST@ * cpu_core@br_misp_retired.cond_ntaken_cost@R / tma_info_thread_clks", + "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to retired misprediction by non-taken conditional branches.", + "MetricExpr": "cpu_core@BR_MISP_RETIRED.COND_NTAKEN_COST@ * cpu_core@BR_MISP_RETIRED.COND_NTAKEN_COST@R / tma_info_thread_clks", "MetricGroup": "BrMispredicts;TopdownL3;tma_L3_group;tma_branch_mispredicts_group", "MetricName": "tma_cond_nt_mispredicts", - "MetricThreshold": "tma_cond_nt_mispredicts > 0.05 & tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", + "MetricThreshold": "tma_cond_nt_mispredicts > 0.05 & (tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15)", "ScaleUnit": "100%", "Unit": "cpu_core" }, { - "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to misprediction by backward-taken conditional branches", - "MetricExpr": "cpu_core@BR_MISP_RETIRED.COND_TAKEN_BWD_COST@ * cpu_core@br_misp_retired.cond_taken_bwd_cost@R / tma_info_thread_clks", + "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to misprediction by backward-taken conditional branches.", + "MetricExpr": "cpu_core@BR_MISP_RETIRED.COND_TAKEN_BWD_COST@ * cpu_core@BR_MISP_RETIRED.COND_TAKEN_BWD_COST@R / tma_info_thread_clks", "MetricGroup": "BrMispredicts;TopdownL3;tma_L3_group;tma_branch_mispredicts_group", "MetricName": "tma_cond_tk_bwd_mispredicts", - "MetricThreshold": "tma_cond_tk_bwd_mispredicts > 0.05 & tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", + "MetricThreshold": "tma_cond_tk_bwd_mispredicts > 0.05 & (tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15)", "ScaleUnit": "100%", "Unit": "cpu_core" }, { - "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to misprediction by forward-taken conditional branches", - "MetricExpr": "cpu_core@BR_MISP_RETIRED.COND_TAKEN_FWD_COST@ * cpu_core@br_misp_retired.cond_taken_fwd_cost@R / tma_info_thread_clks", + "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to misprediction by forward-taken conditional branches.", + "MetricExpr": "cpu_core@BR_MISP_RETIRED.COND_TAKEN_FWD_COST@ * cpu_core@BR_MISP_RETIRED.COND_TAKEN_FWD_COST@R / tma_info_thread_clks", "MetricGroup": "BrMispredicts;TopdownL3;tma_L3_group;tma_branch_mispredicts_group", "MetricName": "tma_cond_tk_fwd_mispredicts", - "MetricThreshold": "tma_cond_tk_fwd_mispredicts > 0.05 & tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", + "MetricThreshold": "tma_cond_tk_fwd_mispredicts > 0.05 & (tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15)", "ScaleUnit": "100%", "Unit": "cpu_core" }, { "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses", - "MetricExpr": "((min(cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS@ * cpu_core@mem_load_l3_hit_retired.xsnp_miss@R, cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS@ * (27 * tma_info_system_core_frequency) - 3 * tma_info_system_core_frequency) if 0 < cpu_core@mem_load_l3_hit_retired.xsnp_miss@R else cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS@ * (27 * tma_info_system_core_frequency) - 3 * tma_info_system_core_frequency) + (min(cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM@ * cpu_core@mem_load_l3_hit_retired.xsnp_hitm@R, cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM@ * (28 * tma_info_system_core_frequency) - 3 * tma_info_system_core_frequency) if 0 < cpu_core@mem_load_l3_hit_retired.xsnp_hitm@R else cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM@ * (28 * tma_info_system_core_frequency) - 3 * tma_info_system_core_frequency)) * (1 + cpu_core@MEM_LOAD_RETIRED.FB_HIT@ / cpu_core@MEM_LOAD_RETIRED.L1_MISS@ / 2) / tma_info_thread_clks", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "(cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS@ * min(cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS@R, 24 * tma_info_system_core_frequency) + cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM@ * min(cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM@R, 25 * tma_info_system_core_frequency)) * (1 + cpu_core@MEM_LOAD_RETIRED.FB_HIT@ / cpu_core@MEM_LOAD_RETIRED.L1_MISS@ / 2) / tma_info_thread_clks", "MetricGroup": "BvMS;DataSharing;LockCont;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group", "MetricName": "tma_contested_accesses", - "MetricThreshold": "tma_contested_accesses > 0.05 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", - "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses. Contested accesses occur when data written by one Logical Processor are read by another Logical Processor on a different Physical Core. Examples of contested accesses include synchronizations such as locks; true data sharing such as modified locked variables; and false sharing. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD, MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS. Related metrics: tma_bottleneck_memory_synchronization, tma_data_sharing, tma_false_sharing, tma_machine_clears", + "MetricThreshold": "tma_contested_accesses > 0.05 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses. Contested accesses occur when data written by one Logical Processor are read by another Logical Processor on a different Physical Core. Examples of contested accesses include synchronizations such as locks; true data sharing such as modified locked variables; and false sharing. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD;MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS. Related metrics: tma_bottleneck_memory_synchronization, tma_data_sharing, tma_false_sharing, tma_machine_clears, tma_remote_cache", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -1038,17 +1039,18 @@ "MetricName": "tma_core_bound", "MetricThreshold": "tma_core_bound > 0.1 & tma_backend_bound > 0.2", "MetricgroupNoGroup": "TopdownL2", - "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck. Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations)", + "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck. Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations).", "ScaleUnit": "100%", "Unit": "cpu_core" }, { "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses", - "MetricExpr": "((min(cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_NO_FWD@ * cpu_core@mem_load_l3_hit_retired.xsnp_no_fwd@R, cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_NO_FWD@ * (27 * tma_info_system_core_frequency) - 3 * tma_info_system_core_frequency) if 0 < cpu_core@mem_load_l3_hit_retired.xsnp_no_fwd@R else cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_NO_FWD@ * (27 * tma_info_system_core_frequency) - 3 * tma_info_system_core_frequency) + (min(cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD@ * cpu_core@mem_load_l3_hit_retired.xsnp_fwd@R, cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD@ * (28 * tma_info_system_core_frequency) - 3 * tma_info_system_core_frequency) if 0 < cpu_core@mem_load_l3_hit_retired.xsnp_fwd@R else cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD@ * (28 * tma_info_system_core_frequency) - 3 * tma_info_system_core_frequency)) * (1 + cpu_core@MEM_LOAD_RETIRED.FB_HIT@ / cpu_core@MEM_LOAD_RETIRED.L1_MISS@ / 2) / tma_info_thread_clks", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "(cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_NO_FWD@ * min(cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_NO_FWD@R, 24 * tma_info_system_core_frequency) + cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD@ * min(cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD@R, 25 * tma_info_system_core_frequency)) * (1 + cpu_core@MEM_LOAD_RETIRED.FB_HIT@ / cpu_core@MEM_LOAD_RETIRED.L1_MISS@ / 2) / tma_info_thread_clks", "MetricGroup": "BvMS;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group", "MetricName": "tma_data_sharing", - "MetricThreshold": "tma_data_sharing > 0.05 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", - "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses. Data shared by multiple Logical Processors (even just read shared) may cause increased access latency due to cache coherency. Excessive data sharing can drastically harm multithreaded performance. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_NO_FWD. Related metrics: tma_bottleneck_memory_synchronization, tma_contested_accesses, tma_false_sharing, tma_machine_clears", + "MetricThreshold": "tma_data_sharing > 0.05 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses. Data shared by multiple Logical Processors (even just read shared) may cause increased access latency due to cache coherency. Excessive data sharing can drastically harm multithreaded performance. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_NO_FWD. Related metrics: tma_bottleneck_memory_synchronization, tma_contested_accesses, tma_false_sharing, tma_machine_clears, tma_remote_cache", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -1057,7 +1059,7 @@ "MetricExpr": "cpu_core@ARITH.DIV_ACTIVE@ / tma_info_thread_clks", "MetricGroup": "BvCB;TopdownL3;tma_L3_group;tma_core_bound_group", "MetricName": "tma_divider", - "MetricThreshold": "tma_divider > 0.2 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_divider > 0.2 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)", "PublicDescription": "This metric represents fraction of cycles where the Divider unit was active. Divide and square root instructions are performed by the Divider unit and can take considerably longer latency than integer or Floating Point addition; subtraction; or multiplication. Sample with: ARITH.DIV_ACTIVE", "ScaleUnit": "100%", "Unit": "cpu_core" @@ -1067,7 +1069,7 @@ "MetricExpr": "cpu_core@MEMORY_STALLS.MEM@ / tma_info_thread_clks", "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_dram_bound", - "MetricThreshold": "tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", "PublicDescription": "This metric estimates how often the CPU was stalled on accesses to external memory (DRAM) by loads. Better caching can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L3_MISS", "ScaleUnit": "100%", "Unit": "cpu_core" @@ -1078,7 +1080,7 @@ "MetricGroup": "DSB;FetchBW;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group", "MetricName": "tma_dsb", "MetricThreshold": "tma_dsb > 0.15 & tma_fetch_bandwidth > 0.2", - "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to DSB (decoded uop cache) fetch pipeline. For example; inefficient utilization of the DSB cache structure or bank conflict when reading from it; are categorized here", + "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to DSB (decoded uop cache) fetch pipeline. For example; inefficient utilization of the DSB cache structure or bank conflict when reading from it; are categorized here.", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -1087,28 +1089,28 @@ "MetricExpr": "cpu_core@DSB2MITE_SWITCHES.PENALTY_CYCLES@ / tma_info_thread_clks", "MetricGroup": "DSBmiss;FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueFB", "MetricName": "tma_dsb_switches", - "MetricThreshold": "tma_dsb_switches > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", - "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines. The DSB (decoded i-cache) is a Uop Cache where the front-end directly delivers Uops (micro operations) avoiding heavy x86 decoding. The DSB pipeline has shorter latency and delivered higher bandwidth than the MITE (legacy instruction decode pipeline). Switching between the two pipelines can cause penalties hence this metric measures the exposed penalty. Sample with: FRONTEND_RETIRED.DSB_MISS. Related metrics: tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp", + "MetricThreshold": "tma_dsb_switches > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines. The DSB (decoded i-cache) is a Uop Cache where the front-end directly delivers Uops (micro operations) avoiding heavy x86 decoding. The DSB pipeline has shorter latency and delivered higher bandwidth than the MITE (legacy instruction decode pipeline). Switching between the two pipelines can cause penalties hence this metric measures the exposed penalty. Sample with: FRONTEND_RETIRED.DSB_MISS_PS. Related metrics: tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp", "ScaleUnit": "100%", "Unit": "cpu_core" }, { "BriefDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses", - "MetricExpr": "(min(cpu_core@MEM_INST_RETIRED.STLB_HIT_LOADS@ * cpu_core@mem_inst_retired.stlb_hit_loads@R, cpu_core@MEM_INST_RETIRED.STLB_HIT_LOADS@ * 7) if 0 < cpu_core@mem_inst_retired.stlb_hit_loads@R else cpu_core@MEM_INST_RETIRED.STLB_HIT_LOADS@ * 7) / tma_info_thread_clks + tma_load_stlb_miss", + "MetricExpr": "cpu_core@MEM_INST_RETIRED.STLB_HIT_LOADS@ * min(cpu_core@MEM_INST_RETIRED.STLB_HIT_LOADS@R, 7) / tma_info_thread_clks + tma_load_stlb_miss", "MetricGroup": "BvMT;MemoryTLB;TopdownL4;tma_L4_group;tma_issueTLB;tma_l1_bound_group", "MetricName": "tma_dtlb_load", - "MetricThreshold": "tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", - "PublicDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses. TLBs (Translation Look-aside Buffers) are processor caches for recently used entries out of the Page Tables that are used to map virtual- to physical-addresses by the operating system. This metric approximates the potential delay of demand loads missing the first-level data TLB (assuming worst case scenario with back to back misses to different pages). This includes hitting in the second-level TLB (STLB) as well as performing a hardware page walk on an STLB miss. Sample with: MEM_INST_RETIRED.STLB_MISS_LOADS. Related metrics: tma_bottleneck_memory_data_tlbs, tma_dtlb_store", + "MetricThreshold": "tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses. TLBs (Translation Look-aside Buffers) are processor caches for recently used entries out of the Page Tables that are used to map virtual- to physical-addresses by the operating system. This metric approximates the potential delay of demand loads missing the first-level data TLB (assuming worst case scenario with back to back misses to different pages). This includes hitting in the second-level TLB (STLB) as well as performing a hardware page walk on an STLB miss. Sample with: MEM_INST_RETIRED.STLB_MISS_LOADS_PS. Related metrics: tma_bottleneck_memory_data_tlbs, tma_dtlb_store", "ScaleUnit": "100%", "Unit": "cpu_core" }, { "BriefDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses", - "MetricExpr": "(min(cpu_core@MEM_INST_RETIRED.STLB_HIT_STORES@ * cpu_core@mem_inst_retired.stlb_hit_stores@R, cpu_core@MEM_INST_RETIRED.STLB_HIT_STORES@ * 7) if 0 < cpu_core@mem_inst_retired.stlb_hit_stores@R else cpu_core@MEM_INST_RETIRED.STLB_HIT_STORES@ * 7) / tma_info_thread_clks + tma_store_stlb_miss", + "MetricExpr": "cpu_core@MEM_INST_RETIRED.STLB_HIT_STORES@ * min(cpu_core@MEM_INST_RETIRED.STLB_HIT_STORES@R, 7) / tma_info_thread_clks + tma_store_stlb_miss", "MetricGroup": "BvMT;MemoryTLB;TopdownL4;tma_L4_group;tma_issueTLB;tma_store_bound_group", "MetricName": "tma_dtlb_store", - "MetricThreshold": "tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", - "PublicDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses. As with ordinary data caching; focus on improving data locality and reducing working-set size to reduce DTLB overhead. Additionally; consider using profile-guided optimization (PGO) to collocate frequently-used data on the same page. Try using larger page sizes for large amounts of frequently-used data. Sample with: MEM_INST_RETIRED.STLB_MISS_STORES. Related metrics: tma_bottleneck_memory_data_tlbs, tma_dtlb_load", + "MetricThreshold": "tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses. As with ordinary data caching; focus on improving data locality and reducing working-set size to reduce DTLB overhead. Additionally; consider using profile-guided optimization (PGO) to collocate frequently-used data on the same page. Try using larger page sizes for large amounts of frequently-used data. Sample with: MEM_INST_RETIRED.STLB_MISS_STORES_PS. Related metrics: tma_bottleneck_memory_data_tlbs, tma_dtlb_load", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -1117,8 +1119,8 @@ "MetricExpr": "28 * tma_info_system_core_frequency * cpu_core@OCR.DEMAND_RFO.L3_HIT.SNOOP_HITM@ / tma_info_thread_clks", "MetricGroup": "BvMS;DataSharing;LockCont;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_store_bound_group", "MetricName": "tma_false_sharing", - "MetricThreshold": "tma_false_sharing > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", - "PublicDescription": "This metric roughly estimates how often CPU was handling synchronizations due to False Sharing. False Sharing is a multithreading hiccup; where multiple Logical Processors contend on different data-elements mapped into the same cache line. Sample with: OCR.DEMAND_RFO.L3_HIT.SNOOP_HITM. Related metrics: tma_bottleneck_memory_synchronization, tma_contested_accesses, tma_data_sharing, tma_machine_clears", + "MetricThreshold": "tma_false_sharing > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric roughly estimates how often CPU was handling synchronizations due to False Sharing. False Sharing is a multithreading hiccup; where multiple Logical Processors contend on different data-elements mapped into the same cache line. Sample with: OCR.DEMAND_RFO.L3_HIT.SNOOP_HITM. Related metrics: tma_bottleneck_memory_synchronization, tma_contested_accesses, tma_data_sharing, tma_machine_clears, tma_remote_cache", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -1128,7 +1130,7 @@ "MetricGroup": "BvMB;MemoryBW;TopdownL4;tma_L4_group;tma_issueBW;tma_issueSL;tma_issueSmSt;tma_l1_bound_group", "MetricName": "tma_fb_full", "MetricThreshold": "tma_fb_full > 0.3", - "PublicDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed. The higher the metric value; the deeper the memory hierarchy level the misses are satisfied from (metric values >1 are valid). Often it hints on approaching bandwidth limits (to L2 cache; L3 cache or external memory). Related metrics: tma_bottleneck_cache_memory_bandwidth, tma_mem_bandwidth, tma_sq_full, tma_store_latency, tma_streaming_stores", + "PublicDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed. The higher the metric value; the deeper the memory hierarchy level the misses are satisfied from (metric values >1 are valid). Often it hints on approaching bandwidth limits (to L2 cache; L3 cache or external memory). Related metrics: tma_bottleneck_cache_memory_bandwidth, tma_info_system_dram_bw_use, tma_mem_bandwidth, tma_sq_full, tma_store_latency, tma_streaming_stores", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -1145,12 +1147,12 @@ }, { "BriefDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues", - "MetricExpr": "topdown\\-fetch\\-lat / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * slots", + "MetricExpr": "cpu_core@topdown\\-fetch\\-lat@ / (cpu_core@topdown\\-fe\\-bound@ + cpu_core@topdown\\-bad\\-spec@ + cpu_core@topdown\\-retiring@ + cpu_core@topdown\\-be\\-bound@) + 0 * tma_info_thread_slots", "MetricGroup": "Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group", "MetricName": "tma_fetch_latency", "MetricThreshold": "tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", "MetricgroupNoGroup": "TopdownL2", - "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues. For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: FRONTEND_RETIRED.LATENCY_GE_16, FRONTEND_RETIRED.LATENCY_GE_8", + "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues. For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: FRONTEND_RETIRED.LATENCY_GE_16_PS;FRONTEND_RETIRED.LATENCY_GE_8_PS", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -1160,7 +1162,7 @@ "MetricGroup": "TopdownL3;tma_L3_group;tma_heavy_operations_group;tma_issueD0", "MetricName": "tma_few_uops_instructions", "MetricThreshold": "tma_few_uops_instructions > 0.05 & tma_heavy_operations > 0.1", - "PublicDescription": "This metric represents fraction of slots where the CPU was retiring instructions that that are decoder into two or more uops. This highly-correlates with the number of uops in such instructions", + "PublicDescription": "This metric represents fraction of slots where the CPU was retiring instructions that that are decoder into two or more uops. This highly-correlates with the number of uops in such instructions. Related metrics: tma_decoder0_alone", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -1170,7 +1172,7 @@ "MetricGroup": "HPC;TopdownL3;tma_L3_group;tma_light_operations_group", "MetricName": "tma_fp_arith", "MetricThreshold": "tma_fp_arith > 0.2 & tma_light_operations > 0.6", - "PublicDescription": "This metric represents overall arithmetic floating-point (FP) operations fraction the CPU has executed (retired). Note this metric's value may exceed its parent due to use of \"Uops\" CountDomain and FMA double-counting", + "PublicDescription": "This metric represents overall arithmetic floating-point (FP) operations fraction the CPU has executed (retired). Note this metric's value may exceed its parent due to use of \"Uops\" CountDomain and FMA double-counting.", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -1180,16 +1182,16 @@ "MetricGroup": "HPC;TopdownL5;tma_L5_group;tma_assists_group", "MetricName": "tma_fp_assists", "MetricThreshold": "tma_fp_assists > 0.1", - "PublicDescription": "This metric roughly estimates fraction of slots the CPU retired uops as a result of handing Floating Point (FP) Assists. FP Assist may apply when working with very small floating point values (so-called Denormals)", + "PublicDescription": "This metric roughly estimates fraction of slots the CPU retired uops as a result of handing Floating Point (FP) Assists. FP Assist may apply when working with very small floating point values (so-called Denormals).", "ScaleUnit": "100%", "Unit": "cpu_core" }, { - "BriefDescription": "This metric represents fraction of cycles where the Floating-Point Divider unit was active", + "BriefDescription": "This metric represents fraction of cycles where the Floating-Point Divider unit was active.", "MetricExpr": "cpu_core@ARITH.FPDIV_ACTIVE@ / tma_info_thread_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_divider_group", "MetricName": "tma_fp_divider", - "MetricThreshold": "tma_fp_divider > 0.2 & tma_divider > 0.2 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_fp_divider > 0.2 & (tma_divider > 0.2 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -1198,8 +1200,8 @@ "MetricExpr": "cpu_core@FP_ARITH_INST_RETIRED.SCALAR@ / (tma_retiring * tma_info_thread_slots)", "MetricGroup": "Compute;Flops;TopdownL4;tma_L4_group;tma_fp_arith_group;tma_issue2P", "MetricName": "tma_fp_scalar", - "MetricThreshold": "tma_fp_scalar > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6", - "PublicDescription": "This metric approximates arithmetic floating-point (FP) scalar uops fraction the CPU has retired. May overcount due to FMA double counting. Related metrics: tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_int_vector_128b, tma_int_vector_256b, tma_ports_utilized_2", + "MetricThreshold": "tma_fp_scalar > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6)", + "PublicDescription": "This metric approximates arithmetic floating-point (FP) scalar uops fraction the CPU has retired. May overcount due to FMA double counting. Related metrics: tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -1208,8 +1210,8 @@ "MetricExpr": "cpu_core@FP_ARITH_INST_RETIRED.VECTOR@ / (tma_retiring * tma_info_thread_slots)", "MetricGroup": "Compute;Flops;TopdownL4;tma_L4_group;tma_fp_arith_group;tma_issue2P", "MetricName": "tma_fp_vector", - "MetricThreshold": "tma_fp_vector > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6", - "PublicDescription": "This metric approximates arithmetic floating-point (FP) vector uops fraction the CPU has retired aggregated across all vector widths. May overcount due to FMA double counting. Related metrics: tma_fp_scalar, tma_fp_vector_128b, tma_fp_vector_256b, tma_int_vector_128b, tma_int_vector_256b, tma_ports_utilized_2", + "MetricThreshold": "tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6)", + "PublicDescription": "This metric approximates arithmetic floating-point (FP) vector uops fraction the CPU has retired aggregated across all vector widths. May overcount due to FMA double counting. Related metrics: tma_fp_scalar, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -1218,8 +1220,8 @@ "MetricExpr": "(cpu_core@FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE@ + cpu_core@FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE@) / (tma_retiring * tma_info_thread_slots)", "MetricGroup": "Compute;Flops;TopdownL5;tma_L5_group;tma_fp_vector_group;tma_issue2P", "MetricName": "tma_fp_vector_128b", - "MetricThreshold": "tma_fp_vector_128b > 0.1 & tma_fp_vector > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6", - "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 128-bit wide vectors. May overcount due to FMA double counting prior to LNL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_256b, tma_int_vector_128b, tma_int_vector_256b, tma_ports_utilized_2", + "MetricThreshold": "tma_fp_vector_128b > 0.1 & (tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6))", + "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 128-bit wide vectors. May overcount due to FMA double counting prior to LNL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -1228,41 +1230,41 @@ "MetricExpr": "cpu_core@FP_ARITH_INST_RETIRED.VECTOR\\,umask\\=0x30@ / (tma_retiring * tma_info_thread_slots)", "MetricGroup": "Compute;Flops;TopdownL5;tma_L5_group;tma_fp_vector_group;tma_issue2P", "MetricName": "tma_fp_vector_256b", - "MetricThreshold": "tma_fp_vector_256b > 0.1 & tma_fp_vector > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6", - "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 256-bit wide vectors. May overcount due to FMA double counting prior to LNL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_int_vector_128b, tma_int_vector_256b, tma_ports_utilized_2", + "MetricThreshold": "tma_fp_vector_256b > 0.1 & (tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6))", + "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 256-bit wide vectors. May overcount due to FMA double counting prior to LNL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%", "Unit": "cpu_core" }, { "BriefDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend", "DefaultMetricgroupName": "TopdownL1", - "MetricExpr": "topdown\\-fe\\-bound / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * slots", + "MetricExpr": "cpu_core@topdown\\-fe\\-bound@ / (cpu_core@topdown\\-fe\\-bound@ + cpu_core@topdown\\-bad\\-spec@ + cpu_core@topdown\\-retiring@ + cpu_core@topdown\\-be\\-bound@) + 0 * tma_info_thread_slots", "MetricGroup": "BvFB;BvIO;Default;PGO;TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_frontend_bound", "MetricThreshold": "tma_frontend_bound > 0.15", "MetricgroupNoGroup": "TopdownL1;Default", - "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound", + "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound.", "ScaleUnit": "100%", "Unit": "cpu_core" }, { - "BriefDescription": "This metric represents fraction of slots where the CPU was retiring fused instructions , where one uop can represent multiple contiguous instructions", + "BriefDescription": "This metric represents fraction of slots where the CPU was retiring fused instructions -- where one uop can represent multiple contiguous instructions", "MetricExpr": "tma_light_operations * cpu_core@INST_RETIRED.MACRO_FUSED@ / (tma_retiring * tma_info_thread_slots)", "MetricGroup": "Branches;BvBO;Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group", "MetricName": "tma_fused_instructions", "MetricThreshold": "tma_fused_instructions > 0.1 & tma_light_operations > 0.6", - "PublicDescription": "This metric represents fraction of slots where the CPU was retiring fused instructions , where one uop can represent multiple contiguous instructions. CMP+JCC or DEC+JCC are common examples of legacy fusions. {([MTL] Note new MOV+OP and Load+OP fusions appear under Other_Light_Ops in MTL!)}", + "PublicDescription": "This metric represents fraction of slots where the CPU was retiring fused instructions -- where one uop can represent multiple contiguous instructions. CMP+JCC or DEC+JCC are common examples of legacy fusions. {([MTL] Note new MOV+OP and Load+OP fusions appear under Other_Light_Ops in MTL!)}", "ScaleUnit": "100%", "Unit": "cpu_core" }, { - "BriefDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations , instructions that require two or more uops or micro-coded sequences", - "MetricExpr": "topdown\\-heavy\\-ops / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * slots", + "BriefDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences", + "MetricExpr": "cpu_core@topdown\\-heavy\\-ops@ / (cpu_core@topdown\\-fe\\-bound@ + cpu_core@topdown\\-bad\\-spec@ + cpu_core@topdown\\-retiring@ + cpu_core@topdown\\-be\\-bound@) + 0 * tma_info_thread_slots", "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_heavy_operations", "MetricThreshold": "tma_heavy_operations > 0.1", "MetricgroupNoGroup": "TopdownL2", - "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations , instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences.([ICL+] Note this may overcount due to approximation using indirect events; [ADL+]). Sample with: UOPS_RETIRED.HEAVY", + "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences.([ICL+] Note this may overcount due to approximation using indirect events; [ADL+]). Sample with: UOPS_RETIRED.HEAVY", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -1271,26 +1273,26 @@ "MetricExpr": "cpu_core@ICACHE_DATA.STALLS@ / tma_info_thread_clks", "MetricGroup": "BigFootprint;BvBC;FetchLat;IcMiss;TopdownL3;tma_L3_group;tma_fetch_latency_group", "MetricName": "tma_icache_misses", - "MetricThreshold": "tma_icache_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", - "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to instruction cache misses. Sample with: FRONTEND_RETIRED.L2_MISS, FRONTEND_RETIRED.L1I_MISS", + "MetricThreshold": "tma_icache_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to instruction cache misses. Sample with: FRONTEND_RETIRED.L2_MISS_PS;FRONTEND_RETIRED.L1I_MISS_PS", "ScaleUnit": "100%", "Unit": "cpu_core" }, { - "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to retired misprediction by indirect CALL instructions", - "MetricExpr": "cpu_core@BR_MISP_RETIRED.INDIRECT_CALL_COST@ * cpu_core@br_misp_retired.indirect_call_cost@R / tma_info_thread_clks", + "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to retired misprediction by indirect CALL instructions.", + "MetricExpr": "cpu_core@BR_MISP_RETIRED.INDIRECT_CALL_COST@ * cpu_core@BR_MISP_RETIRED.INDIRECT_CALL_COST@R / tma_info_thread_clks", "MetricGroup": "BrMispredicts;TopdownL3;tma_L3_group;tma_branch_mispredicts_group", "MetricName": "tma_ind_call_mispredicts", - "MetricThreshold": "tma_ind_call_mispredicts > 0.05 & tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", + "MetricThreshold": "tma_ind_call_mispredicts > 0.05 & (tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15)", "ScaleUnit": "100%", "Unit": "cpu_core" }, { - "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to retired misprediction by indirect JMP instructions", - "MetricExpr": "max((cpu_core@BR_MISP_RETIRED.INDIRECT_COST@ * cpu_core@br_misp_retired.indirect_cost@R - cpu_core@BR_MISP_RETIRED.INDIRECT_CALL_COST@ * cpu_core@br_misp_retired.indirect_call_cost@R) / tma_info_thread_clks, 0)", + "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to retired misprediction by indirect JMP instructions.", + "MetricExpr": "max((cpu_core@BR_MISP_RETIRED.INDIRECT_COST@ * cpu_core@BR_MISP_RETIRED.INDIRECT_COST@R - cpu_core@BR_MISP_RETIRED.INDIRECT_CALL_COST@ * cpu_core@BR_MISP_RETIRED.INDIRECT_CALL_COST@R) / tma_info_thread_clks, 0)", "MetricGroup": "BrMispredicts;TopdownL3;tma_L3_group;tma_branch_mispredicts_group", "MetricName": "tma_ind_jump_mispredicts", - "MetricThreshold": "tma_ind_jump_mispredicts > 0.05 & tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", + "MetricThreshold": "tma_ind_jump_mispredicts > 0.05 & (tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15)", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -1303,7 +1305,7 @@ "Unit": "cpu_core" }, { - "BriefDescription": "Instructions per retired Mispredicts for conditional non-taken branches (lower number means higher occurrence rate)", + "BriefDescription": "Instructions per retired Mispredicts for conditional non-taken branches (lower number means higher occurrence rate).", "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / cpu_core@BR_MISP_RETIRED.COND_NTAKEN@", "MetricGroup": "Bad;BrMispredicts", "MetricName": "tma_info_bad_spec_ipmisp_cond_ntaken", @@ -1311,29 +1313,29 @@ "Unit": "cpu_core" }, { - "BriefDescription": "Instructions per retired Mispredicts for conditional backward-taken branches (lower number means higher occurrence rate)", + "BriefDescription": "Instructions per retired Mispredicts for conditional backward-taken branches (lower number means higher occurrence rate).", "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / cpu_core@BR_MISP_RETIRED.COND_TAKEN_BWD@", "MetricGroup": "Bad;BrMispredicts", "MetricName": "tma_info_bad_spec_ipmisp_cond_taken_bwd", "Unit": "cpu_core" }, { - "BriefDescription": "Instructions per retired Mispredicts for conditional forward-taken branches (lower number means higher occurrence rate)", + "BriefDescription": "Instructions per retired Mispredicts for conditional forward-taken branches (lower number means higher occurrence rate).", "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / cpu_core@BR_MISP_RETIRED.COND_TAKEN_FWD@", "MetricGroup": "Bad;BrMispredicts", "MetricName": "tma_info_bad_spec_ipmisp_cond_taken_fwd", "Unit": "cpu_core" }, { - "BriefDescription": "Instructions per retired Mispredicts for indirect CALL or JMP branches (lower number means higher occurrence rate)", + "BriefDescription": "Instructions per retired Mispredicts for indirect CALL or JMP branches (lower number means higher occurrence rate).", "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / cpu_core@BR_MISP_RETIRED.INDIRECT@", "MetricGroup": "Bad;BrMispredicts", "MetricName": "tma_info_bad_spec_ipmisp_indirect", - "MetricThreshold": "tma_info_bad_spec_ipmisp_indirect < 1000", + "MetricThreshold": "tma_info_bad_spec_ipmisp_indirect < 1e3", "Unit": "cpu_core" }, { - "BriefDescription": "Instructions per retired Mispredicts for return branches (lower number means higher occurrence rate)", + "BriefDescription": "Instructions per retired Mispredicts for return branches (lower number means higher occurrence rate).", "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / cpu_core@BR_MISP_RETIRED.RET@", "MetricGroup": "Bad;BrMispredicts", "MetricName": "tma_info_bad_spec_ipmisp_ret", @@ -1357,7 +1359,7 @@ }, { "BriefDescription": "Total pipeline cost of DSB (uop cache) hits - subset of the Instruction_Fetch_BW Bottleneck", - "MetricExpr": "100 * (tma_frontend_bound * (tma_fetch_bandwidth / (tma_fetch_latency + tma_fetch_bandwidth)) * (tma_dsb / (tma_mite + tma_dsb + tma_lsd + tma_ms)))", + "MetricExpr": "100 * (tma_frontend_bound * (tma_fetch_bandwidth / (tma_fetch_bandwidth + tma_fetch_latency)) * (tma_dsb / (tma_dsb + tma_lsd + tma_mite + tma_ms)))", "MetricGroup": "DSB;Fed;FetchBW;tma_issueFB", "MetricName": "tma_info_botlnk_l2_dsb_bandwidth", "MetricThreshold": "tma_info_botlnk_l2_dsb_bandwidth > 10", @@ -1366,7 +1368,7 @@ }, { "BriefDescription": "Total pipeline cost of DSB (uop cache) misses - subset of the Instruction_Fetch_BW Bottleneck", - "MetricExpr": "100 * (tma_fetch_latency * tma_dsb_switches / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches) + tma_fetch_bandwidth * tma_mite / (tma_mite + tma_dsb + tma_lsd + tma_ms))", + "MetricExpr": "100 * (tma_fetch_latency * tma_dsb_switches / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) + tma_fetch_bandwidth * tma_mite / (tma_dsb + tma_lsd + tma_mite + tma_ms))", "MetricGroup": "DSBmiss;Fed;tma_issueFB", "MetricName": "tma_info_botlnk_l2_dsb_misses", "MetricThreshold": "tma_info_botlnk_l2_dsb_misses > 10", @@ -1375,10 +1377,11 @@ }, { "BriefDescription": "Total pipeline cost of Instruction Cache misses - subset of the Big_Code Bottleneck", - "MetricExpr": "100 * (tma_fetch_latency * tma_icache_misses / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches))", + "MetricExpr": "100 * (tma_fetch_latency * tma_icache_misses / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches))", "MetricGroup": "Fed;FetchLat;IcMiss;tma_issueFL", "MetricName": "tma_info_botlnk_l2_ic_misses", "MetricThreshold": "tma_info_botlnk_l2_ic_misses > 5", + "PublicDescription": "Total pipeline cost of Instruction Cache misses - subset of the Big_Code Bottleneck. Related metrics: ", "Unit": "cpu_core" }, { @@ -1444,12 +1447,12 @@ "MetricExpr": "(cpu_core@FP_ARITH_DISPATCHED.V0@ + cpu_core@FP_ARITH_DISPATCHED.V1@ + cpu_core@FP_ARITH_DISPATCHED.V2@ + cpu_core@FP_ARITH_DISPATCHED.V3@) / (4 * tma_info_thread_clks)", "MetricGroup": "Cor;Flops;HPC", "MetricName": "tma_info_core_fp_arith_utilization", - "PublicDescription": "Actual per-core usage of the Floating Point non-X87 execution units (regardless of precision or vector-width). Values > 1 are possible due to ([BDW+] Fused-Multiply Add (FMA) counting - common; [ADL+] use all of ADD/MUL/FMA in Scalar or 128/256-bit vectors - less common)", + "PublicDescription": "Actual per-core usage of the Floating Point non-X87 execution units (regardless of precision or vector-width). Values > 1 are possible due to ([BDW+] Fused-Multiply Add (FMA) counting - common; [ADL+] use all of ADD/MUL/FMA in Scalar or 128/256-bit vectors - less common).", "Unit": "cpu_core" }, { "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is execution) per thread (logical-processor)", - "MetricExpr": "cpu_core@UOPS_EXECUTED.THREAD@ / cpu_core@UOPS_EXECUTED.THREAD\\,cmask\\=0x1@", + "MetricExpr": "cpu_core@UOPS_EXECUTED.THREAD@ / cpu_core@UOPS_EXECUTED.THREAD\\,cmask\\=1@", "MetricGroup": "Backend;Cor;Pipeline;PortsUtil", "MetricName": "tma_info_core_ilp", "Unit": "cpu_core" @@ -1464,15 +1467,15 @@ "Unit": "cpu_core" }, { - "BriefDescription": "Average number of cycles of a switch from the DSB fetch-unit to MITE fetch unit - see DSB_Switches tree node for details", - "MetricExpr": "cpu_core@DSB2MITE_SWITCHES.PENALTY_CYCLES@ / cpu_core@DSB2MITE_SWITCHES.PENALTY_CYCLES\\,cmask\\=0x1\\,edge\\=0x1@", + "BriefDescription": "Average number of cycles of a switch from the DSB fetch-unit to MITE fetch unit - see DSB_Switches tree node for details.", + "MetricExpr": "cpu_core@DSB2MITE_SWITCHES.PENALTY_CYCLES@ / cpu_core@DSB2MITE_SWITCHES.PENALTY_CYCLES\\,cmask\\=1\\,edge@", "MetricGroup": "DSBmiss", "MetricName": "tma_info_frontend_dsb_switch_cost", "Unit": "cpu_core" }, { "BriefDescription": "This metric represents fraction of cycles the CPU retirement was stalled likely due to retired DSB misses", - "MetricExpr": "cpu_core@FRONTEND_RETIRED.ANY_DSB_MISS@ * cpu_core@frontend_retired.any_dsb_miss@R / tma_info_thread_clks", + "MetricExpr": "cpu_core@FRONTEND_RETIRED.ANY_DSB_MISS@ * cpu_core@FRONTEND_RETIRED.ANY_DSB_MISS@R / tma_info_thread_clks", "MetricGroup": "DSBmiss;Fed;FetchLat", "MetricName": "tma_info_frontend_dsb_switches_ret", "MetricThreshold": "tma_info_frontend_dsb_switches_ret > 0.05", @@ -1480,7 +1483,7 @@ }, { "BriefDescription": "Average number of Uops issued by front-end when it issued something", - "MetricExpr": "cpu_core@UOPS_ISSUED.ANY@ / cpu_core@UOPS_ISSUED.ANY\\,cmask\\=0x1@", + "MetricExpr": "cpu_core@UOPS_ISSUED.ANY@ / cpu_core@UOPS_ISSUED.ANY\\,cmask\\=1@", "MetricGroup": "Fed;FetchBW", "MetricName": "tma_info_frontend_fetch_upc", "Unit": "cpu_core" @@ -1530,7 +1533,7 @@ }, { "BriefDescription": "This metric represents fraction of cycles the CPU retirement was stalled likely due to retired operations that invoke the Microcode Sequencer", - "MetricExpr": "cpu_core@FRONTEND_RETIRED.MS_FLOWS@ * cpu_core@frontend_retired.ms_flows@R / tma_info_thread_clks", + "MetricExpr": "cpu_core@FRONTEND_RETIRED.MS_FLOWS@ * cpu_core@FRONTEND_RETIRED.MS_FLOWS@R / tma_info_thread_clks", "MetricGroup": "Fed;FetchLat;MicroSeq", "MetricName": "tma_info_frontend_ms_latency_ret", "MetricThreshold": "tma_info_frontend_ms_latency_ret > 0.05", @@ -1545,21 +1548,21 @@ }, { "BriefDescription": "Average number of cycles the front-end was delayed due to an Unknown Branch detection", - "MetricExpr": "cpu_core@INT_MISC.UNKNOWN_BRANCH_CYCLES@ / cpu_core@INT_MISC.UNKNOWN_BRANCH_CYCLES\\,cmask\\=0x1\\,edge\\=0x1@", + "MetricExpr": "cpu_core@INT_MISC.UNKNOWN_BRANCH_CYCLES@ / cpu_core@INT_MISC.UNKNOWN_BRANCH_CYCLES\\,cmask\\=1\\,edge@", "MetricGroup": "Fed", "MetricName": "tma_info_frontend_unknown_branch_cost", - "PublicDescription": "Average number of cycles the front-end was delayed due to an Unknown Branch detection. See Unknown_Branches node", + "PublicDescription": "Average number of cycles the front-end was delayed due to an Unknown Branch detection. See Unknown_Branches node.", "Unit": "cpu_core" }, { "BriefDescription": "This metric represents fraction of cycles the CPU retirement was stalled likely due to retired branches who got branch address clears", - "MetricExpr": "cpu_core@FRONTEND_RETIRED.UNKNOWN_BRANCH@ * cpu_core@frontend_retired.unknown_branch@R / tma_info_thread_clks", + "MetricExpr": "cpu_core@FRONTEND_RETIRED.UNKNOWN_BRANCH@ * cpu_core@FRONTEND_RETIRED.UNKNOWN_BRANCH@R / tma_info_thread_clks", "MetricGroup": "Fed;FetchLat", "MetricName": "tma_info_frontend_unknown_branches_ret", "Unit": "cpu_core" }, { - "BriefDescription": "Branch instructions per taken branch", + "BriefDescription": "Branch instructions per taken branch.", "MetricExpr": "cpu_core@BR_INST_RETIRED.ALL_BRANCHES@ / cpu_core@BR_INST_RETIRED.NEAR_TAKEN@", "MetricGroup": "Branches;Fed;PGO", "MetricName": "tma_info_inst_mix_bptkbranch", @@ -1579,7 +1582,7 @@ "MetricGroup": "Flops;InsType", "MetricName": "tma_info_inst_mix_iparith", "MetricThreshold": "tma_info_inst_mix_iparith < 10", - "PublicDescription": "Instructions per FP Arithmetic instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting. Approximated prior to BDW", + "PublicDescription": "Instructions per FP Arithmetic instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting. Approximated prior to BDW.", "Unit": "cpu_core" }, { @@ -1588,7 +1591,7 @@ "MetricGroup": "Flops;FpVector;InsType", "MetricName": "tma_info_inst_mix_iparith_avx128", "MetricThreshold": "tma_info_inst_mix_iparith_avx128 < 10", - "PublicDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting", + "PublicDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting.", "Unit": "cpu_core" }, { @@ -1597,7 +1600,7 @@ "MetricGroup": "Flops;FpVector;InsType", "MetricName": "tma_info_inst_mix_iparith_avx256", "MetricThreshold": "tma_info_inst_mix_iparith_avx256 < 10", - "PublicDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting", + "PublicDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting.", "Unit": "cpu_core" }, { @@ -1606,7 +1609,7 @@ "MetricGroup": "Flops;FpScalar;InsType", "MetricName": "tma_info_inst_mix_iparith_scalar_dp", "MetricThreshold": "tma_info_inst_mix_iparith_scalar_dp < 10", - "PublicDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting", + "PublicDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting.", "Unit": "cpu_core" }, { @@ -1615,7 +1618,7 @@ "MetricGroup": "Flops;FpScalar;InsType", "MetricName": "tma_info_inst_mix_iparith_scalar_sp", "MetricThreshold": "tma_info_inst_mix_iparith_scalar_sp < 10", - "PublicDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting", + "PublicDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting.", "Unit": "cpu_core" }, { @@ -1678,7 +1681,7 @@ "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / cpu_core@BR_INST_RETIRED.NEAR_TAKEN@", "MetricGroup": "Branches;Fed;FetchBW;Frontend;PGO;tma_issueFB", "MetricName": "tma_info_inst_mix_iptb", - "MetricThreshold": "tma_info_inst_mix_iptb < 8 * 2 + 1", + "MetricThreshold": "tma_info_inst_mix_iptb < 17", "PublicDescription": "Instructions per taken branch. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_lcp", "Unit": "cpu_core" }, @@ -1803,7 +1806,7 @@ }, { "BriefDescription": "Average Parallel L2 cache miss demand Loads", - "MetricExpr": "cpu_core@OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD@ / cpu_core@OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD\\,cmask\\=0x1@", + "MetricExpr": "cpu_core@OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD@ / cpu_core@OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD\\,cmask\\=1@", "MetricGroup": "Memory_BW;Offcore", "MetricName": "tma_info_memory_latency_load_l2_mlp", "Unit": "cpu_core" @@ -1861,7 +1864,7 @@ }, { "BriefDescription": "This metric represents fraction of cycles the CPU retirement was stalled likely due to STLB misses by demand loads", - "MetricExpr": "cpu_core@MEM_INST_RETIRED.STLB_MISS_LOADS@ * cpu_core@mem_inst_retired.stlb_miss_loads@R / tma_info_thread_clks", + "MetricExpr": "cpu_core@MEM_INST_RETIRED.STLB_MISS_LOADS@ * cpu_core@MEM_INST_RETIRED.STLB_MISS_LOADS@R / tma_info_thread_clks", "MetricGroup": "Mem;MemoryTLB", "MetricName": "tma_info_memory_tlb_load_stlb_miss_ret", "MetricThreshold": "tma_info_memory_tlb_load_stlb_miss_ret > 0.05", @@ -1884,7 +1887,7 @@ }, { "BriefDescription": "This metric represents fraction of cycles the CPU retirement was stalled likely due to STLB misses by demand stores", - "MetricExpr": "cpu_core@MEM_INST_RETIRED.STLB_MISS_STORES@ * cpu_core@mem_inst_retired.stlb_miss_stores@R / tma_info_thread_clks", + "MetricExpr": "cpu_core@MEM_INST_RETIRED.STLB_MISS_STORES@ * cpu_core@MEM_INST_RETIRED.STLB_MISS_STORES@R / tma_info_thread_clks", "MetricGroup": "Mem;MemoryTLB", "MetricName": "tma_info_memory_tlb_store_stlb_miss_ret", "MetricThreshold": "tma_info_memory_tlb_store_stlb_miss_ret > 0.05", @@ -1923,20 +1926,20 @@ "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / cpu_core@ASSISTS.ANY@", "MetricGroup": "MicroSeq;Pipeline;Ret;Retire", "MetricName": "tma_info_pipeline_ipassist", - "MetricThreshold": "tma_info_pipeline_ipassist < 100000", + "MetricThreshold": "tma_info_pipeline_ipassist < 100e3", "PublicDescription": "Instructions per a microcode Assist invocation. See Assists tree node for details (lower number means higher occurrence rate)", "Unit": "cpu_core" }, { - "BriefDescription": "Average number of Uops retired in cycles where at least one uop has retired", - "MetricExpr": "tma_retiring * tma_info_thread_slots / cpu_core@UOPS_RETIRED.SLOTS\\,cmask\\=0x1@", + "BriefDescription": "Average number of Uops retired in cycles where at least one uop has retired.", + "MetricExpr": "tma_retiring * tma_info_thread_slots / cpu_core@UOPS_RETIRED.SLOTS\\,cmask\\=1@", "MetricGroup": "Pipeline;Ret", "MetricName": "tma_info_pipeline_retire", "Unit": "cpu_core" }, { "BriefDescription": "Estimated fraction of retirement-cycles dealing with repeat instructions", - "MetricExpr": "cpu_core@INST_RETIRED.REP_ITERATION@ / cpu_core@UOPS_RETIRED.SLOTS\\,cmask\\=0x1@", + "MetricExpr": "cpu_core@INST_RETIRED.REP_ITERATION@ / cpu_core@UOPS_RETIRED.SLOTS\\,cmask\\=1@", "MetricGroup": "MicroSeq;Pipeline;Ret", "MetricName": "tma_info_pipeline_strings_cycles", "MetricThreshold": "tma_info_pipeline_strings_cycles > 0.1", @@ -1981,23 +1984,22 @@ }, { "BriefDescription": "Instructions per Far Branch ( Far Branches apply upon transition from application to operating system, handling interrupts, exceptions) [lower number means higher occurrence rate]", - "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / BR_INST_RETIRED.FAR_BRANCH:u", + "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / cpu_core@BR_INST_RETIRED.FAR_BRANCH@u", "MetricGroup": "Branches;OS", "MetricName": "tma_info_system_ipfarbranch", - "MetricThreshold": "tma_info_system_ipfarbranch < 1000000", + "MetricThreshold": "tma_info_system_ipfarbranch < 1e6", "Unit": "cpu_core" }, { "BriefDescription": "Cycles Per Instruction for the Operating System (OS) Kernel mode", - "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P:k / INST_RETIRED.ANY_P:k", + "MetricExpr": "cpu_core@CPU_CLK_UNHALTED.THREAD_P@k / cpu_core@INST_RETIRED.ANY_P@k", "MetricGroup": "OS", "MetricName": "tma_info_system_kernel_cpi", - "ScaleUnit": "1per_instr", "Unit": "cpu_core" }, { "BriefDescription": "Fraction of cycles spent in the Operating System (OS) Kernel mode", - "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P:k / cpu_core@CPU_CLK_UNHALTED.THREAD@", + "MetricExpr": "cpu_core@CPU_CLK_UNHALTED.THREAD_P@k / cpu_core@CPU_CLK_UNHALTED.THREAD@", "MetricGroup": "OS", "MetricName": "tma_info_system_kernel_utilization", "MetricThreshold": "tma_info_system_kernel_utilization > 0.05", @@ -2034,7 +2036,7 @@ "Unit": "cpu_core" }, { - "BriefDescription": "Per-Logical Processor actual clocks when the Logical Processor is active", + "BriefDescription": "Per-Logical Processor actual clocks when the Logical Processor is active.", "MetricExpr": "cpu_core@CPU_CLK_UNHALTED.THREAD@", "MetricGroup": "Pipeline", "MetricName": "tma_info_thread_clks", @@ -2045,7 +2047,6 @@ "MetricExpr": "1 / tma_info_thread_ipc", "MetricGroup": "Mem;Pipeline", "MetricName": "tma_info_thread_cpi", - "ScaleUnit": "1per_instr", "Unit": "cpu_core" }, { @@ -2053,7 +2054,7 @@ "MetricExpr": "cpu_core@UOPS_EXECUTED.THREAD@ / cpu_core@UOPS_ISSUED.ANY@", "MetricGroup": "Cor;Pipeline", "MetricName": "tma_info_thread_execute_per_issue", - "PublicDescription": "The ratio of Executed- by Issued-Uops. Ratio > 1 suggests high rate of uop micro-fusions. Ratio < 1 suggest high rate of \"execute\" at rename stage", + "PublicDescription": "The ratio of Executed- by Issued-Uops. Ratio > 1 suggests high rate of uop micro-fusions. Ratio < 1 suggest high rate of \"execute\" at rename stage.", "Unit": "cpu_core" }, { @@ -2065,7 +2066,7 @@ }, { "BriefDescription": "Total issue-pipeline slots (per-Physical Core till ICL; per-Logical Processor ICL onward)", - "MetricExpr": "slots", + "MetricExpr": "cpu_core@TOPDOWN.SLOTS@", "MetricGroup": "TmaL1;tma_L1_group", "MetricName": "tma_info_thread_slots", "Unit": "cpu_core" @@ -2083,15 +2084,15 @@ "MetricExpr": "tma_retiring * tma_info_thread_slots / cpu_core@BR_INST_RETIRED.NEAR_TAKEN@", "MetricGroup": "Branches;Fed;FetchBW", "MetricName": "tma_info_thread_uptb", - "MetricThreshold": "tma_info_thread_uptb < 8 * 1.5", + "MetricThreshold": "tma_info_thread_uptb < 12", "Unit": "cpu_core" }, { - "BriefDescription": "This metric represents fraction of cycles where the Integer Divider unit was active", + "BriefDescription": "This metric represents fraction of cycles where the Integer Divider unit was active.", "MetricExpr": "tma_divider - tma_fp_divider", "MetricGroup": "TopdownL4;tma_L4_group;tma_divider_group", "MetricName": "tma_int_divider", - "MetricThreshold": "tma_int_divider > 0.2 & tma_divider > 0.2 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_int_divider > 0.2 & (tma_divider > 0.2 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -2101,7 +2102,7 @@ "MetricGroup": "Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group", "MetricName": "tma_int_operations", "MetricThreshold": "tma_int_operations > 0.1 & tma_light_operations > 0.6", - "PublicDescription": "This metric represents overall Integer (Int) select operations fraction the CPU has executed (retired). Vector/Matrix Int operations and shuffles are counted. Note this metric's value may exceed its parent due to use of \"Uops\" CountDomain", + "PublicDescription": "This metric represents overall Integer (Int) select operations fraction the CPU has executed (retired). Vector/Matrix Int operations and shuffles are counted. Note this metric's value may exceed its parent due to use of \"Uops\" CountDomain.", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -2110,8 +2111,8 @@ "MetricExpr": "cpu_core@INT_VEC_RETIRED.128BIT@ / (tma_retiring * tma_info_thread_slots)", "MetricGroup": "Compute;IntVector;Pipeline;TopdownL4;tma_L4_group;tma_int_operations_group;tma_issue2P", "MetricName": "tma_int_vector_128b", - "MetricThreshold": "tma_int_vector_128b > 0.1 & tma_int_operations > 0.1 & tma_light_operations > 0.6", - "PublicDescription": "This metric represents 128-bit vector Integer ADD/SUB/SAD or VNNI (Vector Neural Network Instructions) uops fraction the CPU has retired. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_int_vector_256b, tma_ports_utilized_2", + "MetricThreshold": "tma_int_vector_128b > 0.1 & (tma_int_operations > 0.1 & tma_light_operations > 0.6)", + "PublicDescription": "This metric represents 128-bit vector Integer ADD/SUB/SAD or VNNI (Vector Neural Network Instructions) uops fraction the CPU has retired. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -2120,8 +2121,8 @@ "MetricExpr": "cpu_core@INT_VEC_RETIRED.256BIT@ / (tma_retiring * tma_info_thread_slots)", "MetricGroup": "Compute;IntVector;Pipeline;TopdownL4;tma_L4_group;tma_int_operations_group;tma_issue2P", "MetricName": "tma_int_vector_256b", - "MetricThreshold": "tma_int_vector_256b > 0.1 & tma_int_operations > 0.1 & tma_light_operations > 0.6", - "PublicDescription": "This metric represents 256-bit vector Integer ADD/SUB/SAD/MUL or VNNI (Vector Neural Network Instructions) uops fraction the CPU has retired. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_int_vector_128b, tma_ports_utilized_2", + "MetricThreshold": "tma_int_vector_256b > 0.1 & (tma_int_operations > 0.1 & tma_light_operations > 0.6)", + "PublicDescription": "This metric represents 256-bit vector Integer ADD/SUB/SAD/MUL or VNNI (Vector Neural Network Instructions) uops fraction the CPU has retired. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -2130,8 +2131,8 @@ "MetricExpr": "cpu_core@ICACHE_TAG.STALLS@ / tma_info_thread_clks", "MetricGroup": "BigFootprint;BvBC;FetchLat;MemoryTLB;TopdownL3;tma_L3_group;tma_fetch_latency_group", "MetricName": "tma_itlb_misses", - "MetricThreshold": "tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", - "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Instruction TLB (ITLB) misses. Sample with: FRONTEND_RETIRED.STLB_MISS, FRONTEND_RETIRED.ITLB_MISS", + "MetricThreshold": "tma_itlb_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Instruction TLB (ITLB) misses. Sample with: FRONTEND_RETIRED.STLB_MISS_PS;FRONTEND_RETIRED.ITLB_MISS_PS", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -2140,17 +2141,17 @@ "MetricExpr": "cpu_core@MEMORY_STALLS.L1@ / tma_info_thread_clks", "MetricGroup": "CacheHits;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_issueL1;tma_issueMC;tma_memory_bound_group", "MetricName": "tma_l1_bound", - "MetricThreshold": "tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", "PublicDescription": "This metric estimates how often the CPU was stalled without loads missing the L1 Data (L1D) cache. The L1D cache typically has the shortest latency. However; in certain cases like loads blocked on older stores; a load might suffer due to high latency even though it is being satisfied by the L1D. Another example is loads who miss in the TLB. These cases are characterized by execution unit stalls; while some non-completed demand load lives in the machine without having that demand load missing the L1 cache. Sample with: MEM_LOAD_RETIRED.L1_HIT. Related metrics: tma_clears_resteers, tma_machine_clears, tma_microcode_sequencer, tma_ms_switches, tma_ports_utilized_1", "ScaleUnit": "100%", "Unit": "cpu_core" }, { - "BriefDescription": "This metric estimates fraction of cycles with demand load accesses that hit Level 1 after missing Level 0 within the L1D cache", - "MetricExpr": "(min(cpu_core@MEM_LOAD_RETIRED.L1_HIT_L1@ * cpu_core@mem_load_retired.l1_hit_l1@R, cpu_core@MEM_LOAD_RETIRED.L1_HIT_L1@ * 9) if 0 < cpu_core@mem_load_retired.l1_hit_l1@R else cpu_core@MEM_LOAD_RETIRED.L1_HIT_L1@ * 9) / tma_info_thread_clks", + "BriefDescription": "This metric estimates fraction of cycles with demand load accesses that hit Level 1 after missing Level 0 within the L1D cache.", + "MetricExpr": "cpu_core@MEM_LOAD_RETIRED.L1_HIT_L1@ * min(cpu_core@MEM_LOAD_RETIRED.L1_HIT_L1@R, 9) / tma_info_thread_clks", "MetricGroup": "BvML;MemoryLat;TopdownL4;tma_L4_group;tma_l1_bound_group", "MetricName": "tma_l1_latency_capacity", - "MetricThreshold": "tma_l1_latency_capacity > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_l1_latency_capacity > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -2159,8 +2160,8 @@ "MetricExpr": "4 * cpu_core@DEPENDENT_LOADS.ANY@ / tma_info_thread_clks", "MetricGroup": "BvML;MemoryLat;TopdownL4;tma_L4_group;tma_l1_bound_group", "MetricName": "tma_l1_latency_dependency", - "MetricThreshold": "tma_l1_latency_dependency > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", - "PublicDescription": "This metric([SKL+] roughly; [LNL]) estimates fraction of cycles with demand load accesses that hit the L1D cache. The short latency of the L1D cache may be exposed in pointer-chasing memory access patterns as an example. Sample with: DEPENDENT_LOADS.ANY", + "MetricThreshold": "tma_l1_latency_dependency > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric([SKL+] roughly; [LNL]) estimates fraction of cycles with demand load accesses that hit the L1D cache. The short latency of the L1D cache may be exposed in pointer-chasing memory access patterns as an example. Sample with: MEM_LOAD_UOPS_RETIRED.L1_HIT_PS", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -2169,17 +2170,18 @@ "MetricExpr": "cpu_core@MEMORY_STALLS.L2@ / tma_info_thread_clks", "MetricGroup": "BvML;CacheHits;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_l2_bound", - "MetricThreshold": "tma_l2_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_l2_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", "PublicDescription": "This metric estimates how often the CPU was stalled due to L2 cache accesses by loads. Avoiding cache misses (i.e. L1 misses/L2 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L2_HIT", "ScaleUnit": "100%", "Unit": "cpu_core" }, { "BriefDescription": "This metric represents fraction of cycles with demand load accesses that hit the L2 cache under unloaded scenarios (possibly L2 latency limited)", - "MetricExpr": "(min(cpu_core@MEM_LOAD_RETIRED.L2_HIT@ * cpu_core@mem_load_retired.l2_hit@R, cpu_core@MEM_LOAD_RETIRED.L2_HIT@ * (3 * tma_info_system_core_frequency)) if 0 < cpu_core@mem_load_retired.l2_hit@R else cpu_core@MEM_LOAD_RETIRED.L2_HIT@ * (3 * tma_info_system_core_frequency)) * (1 + cpu_core@MEM_LOAD_RETIRED.FB_HIT@ / cpu_core@MEM_LOAD_RETIRED.L1_MISS@ / 2) / tma_info_thread_clks", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "cpu_core@MEM_LOAD_RETIRED.L2_HIT@ * min(cpu_core@MEM_LOAD_RETIRED.L2_HIT@R, 3 * tma_info_system_core_frequency) * (1 + cpu_core@MEM_LOAD_RETIRED.FB_HIT@ / cpu_core@MEM_LOAD_RETIRED.L1_MISS@ / 2) / tma_info_thread_clks", "MetricGroup": "MemoryLat;TopdownL4;tma_L4_group;tma_l2_bound_group", "MetricName": "tma_l2_hit_latency", - "MetricThreshold": "tma_l2_hit_latency > 0.05 & tma_l2_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_l2_hit_latency > 0.05 & (tma_l2_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", "PublicDescription": "This metric represents fraction of cycles with demand load accesses that hit the L2 cache under unloaded scenarios (possibly L2 latency limited). Avoiding L1 cache misses (i.e. L1 misses/L2 hits) will improve the latency. Sample with: MEM_LOAD_RETIRED.L2_HIT", "ScaleUnit": "100%", "Unit": "cpu_core" @@ -2189,18 +2191,19 @@ "MetricExpr": "cpu_core@MEMORY_STALLS.L3@ / tma_info_thread_clks", "MetricGroup": "CacheHits;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_l3_bound", - "MetricThreshold": "tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", - "PublicDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core. Avoiding cache misses (i.e. L2 misses/L3 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L3_HIT", + "MetricThreshold": "tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", + "PublicDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core. Avoiding cache misses (i.e. L2 misses/L3 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L3_HIT_PS", "ScaleUnit": "100%", "Unit": "cpu_core" }, { "BriefDescription": "This metric estimates fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited)", - "MetricExpr": "(min(cpu_core@MEM_LOAD_RETIRED.L3_HIT@ * cpu_core@mem_load_retired.l3_hit@R, cpu_core@MEM_LOAD_RETIRED.L3_HIT@ * (12 * tma_info_system_core_frequency) - 3 * tma_info_system_core_frequency) if 0 < cpu_core@mem_load_retired.l3_hit@R else cpu_core@MEM_LOAD_RETIRED.L3_HIT@ * (12 * tma_info_system_core_frequency) - 3 * tma_info_system_core_frequency) * (1 + cpu_core@MEM_LOAD_RETIRED.FB_HIT@ / cpu_core@MEM_LOAD_RETIRED.L1_MISS@ / 2) / tma_info_thread_clks", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "cpu_core@MEM_LOAD_RETIRED.L3_HIT@ * min(cpu_core@MEM_LOAD_RETIRED.L3_HIT@R, 9 * tma_info_system_core_frequency) * (1 + cpu_core@MEM_LOAD_RETIRED.FB_HIT@ / cpu_core@MEM_LOAD_RETIRED.L1_MISS@ / 2) / tma_info_thread_clks", "MetricGroup": "BvML;MemoryLat;TopdownL4;tma_L4_group;tma_issueLat;tma_l3_bound_group", "MetricName": "tma_l3_hit_latency", - "MetricThreshold": "tma_l3_hit_latency > 0.1 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", - "PublicDescription": "This metric estimates fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited). Avoiding private cache misses (i.e. L2 misses/L3 hits) will improve the latency; reduce contention with sibling physical cores and increase performance. Note the value of this node may overlap with its siblings. Sample with: MEM_LOAD_RETIRED.L3_HIT. Related metrics: tma_bottleneck_cache_memory_latency, tma_branch_resteers, tma_mem_latency, tma_store_latency", + "MetricThreshold": "tma_l3_hit_latency > 0.1 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric estimates fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited). Avoiding private cache misses (i.e. L2 misses/L3 hits) will improve the latency; reduce contention with sibling physical cores and increase performance. Note the value of this node may overlap with its siblings. Sample with: MEM_LOAD_RETIRED.L3_HIT_PS. Related metrics: tma_bottleneck_cache_memory_latency, tma_mem_latency", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -2209,19 +2212,19 @@ "MetricExpr": "cpu_core@DECODE.LCP@ / tma_info_thread_clks", "MetricGroup": "FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueFB", "MetricName": "tma_lcp", - "MetricThreshold": "tma_lcp > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", - "PublicDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs). Using proper compiler flags or Intel Compiler by default will certainly avoid this. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb", + "MetricThreshold": "tma_lcp > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", + "PublicDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs). Using proper compiler flags or Intel Compiler by default will certainly avoid this. #Link: Optimization Guide about LCP BKMs. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb", "ScaleUnit": "100%", "Unit": "cpu_core" }, { - "BriefDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations , instructions that require no more than one uop (micro-operation)", + "BriefDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation)", "MetricExpr": "max(0, tma_retiring - tma_heavy_operations)", "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_light_operations", "MetricThreshold": "tma_light_operations > 0.6", "MetricgroupNoGroup": "TopdownL2", - "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations , instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized code running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. ([ICL+] Note this may undercount due to approximation using indirect events; [ADL+] .). Sample with: INST_RETIRED.PREC_DIST", + "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized code running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. ([ICL+] Note this may undercount due to approximation using indirect events; [ADL+] .). Sample with: INST_RETIRED.PREC_DIST", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -2231,7 +2234,7 @@ "MetricGroup": "TopdownL5;tma_L5_group;tma_ports_utilized_3m_group", "MetricName": "tma_load_op_utilization", "MetricThreshold": "tma_load_op_utilization > 0.6", - "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port for Load operations. Sample with: UOPS_DISPATCHED.LOAD", + "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port for Load operations. Sample with: UOPS_DISPATCHED.PORT_2_3", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -2240,7 +2243,7 @@ "MetricExpr": "max(0, tma_dtlb_load - tma_load_stlb_miss)", "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_load_group", "MetricName": "tma_load_stlb_hit", - "MetricThreshold": "tma_load_stlb_hit > 0.05 & tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_load_stlb_hit > 0.05 & (tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -2249,43 +2252,43 @@ "MetricExpr": "cpu_core@DTLB_LOAD_MISSES.WALK_ACTIVE@ / tma_info_thread_clks", "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_load_group", "MetricName": "tma_load_stlb_miss", - "MetricThreshold": "tma_load_stlb_miss > 0.05 & tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_load_stlb_miss > 0.05 & (tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))", "ScaleUnit": "100%", "Unit": "cpu_core" }, { - "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 1 GB pages for data load accesses", + "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 1 GB pages for data load accesses.", "MetricExpr": "tma_load_stlb_miss * cpu_core@DTLB_LOAD_MISSES.WALK_COMPLETED_1G@ / (cpu_core@DTLB_LOAD_MISSES.WALK_COMPLETED_4K@ + cpu_core@DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M@ + cpu_core@DTLB_LOAD_MISSES.WALK_COMPLETED_1G@)", "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_load_stlb_miss_group", "MetricName": "tma_load_stlb_miss_1g", - "MetricThreshold": "tma_load_stlb_miss_1g > 0.05 & tma_load_stlb_miss > 0.05 & tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_load_stlb_miss_1g > 0.05 & (tma_load_stlb_miss > 0.05 & (tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))))", "ScaleUnit": "100%", "Unit": "cpu_core" }, { - "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 2 or 4 MB pages for data load accesses", + "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 2 or 4 MB pages for data load accesses.", "MetricExpr": "tma_load_stlb_miss * cpu_core@DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M@ / (cpu_core@DTLB_LOAD_MISSES.WALK_COMPLETED_4K@ + cpu_core@DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M@ + cpu_core@DTLB_LOAD_MISSES.WALK_COMPLETED_1G@)", "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_load_stlb_miss_group", "MetricName": "tma_load_stlb_miss_2m", - "MetricThreshold": "tma_load_stlb_miss_2m > 0.05 & tma_load_stlb_miss > 0.05 & tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_load_stlb_miss_2m > 0.05 & (tma_load_stlb_miss > 0.05 & (tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))))", "ScaleUnit": "100%", "Unit": "cpu_core" }, { - "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 4 KB pages for data load accesses", + "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 4 KB pages for data load accesses.", "MetricExpr": "tma_load_stlb_miss * cpu_core@DTLB_LOAD_MISSES.WALK_COMPLETED_4K@ / (cpu_core@DTLB_LOAD_MISSES.WALK_COMPLETED_4K@ + cpu_core@DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M@ + cpu_core@DTLB_LOAD_MISSES.WALK_COMPLETED_1G@)", "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_load_stlb_miss_group", "MetricName": "tma_load_stlb_miss_4k", - "MetricThreshold": "tma_load_stlb_miss_4k > 0.05 & tma_load_stlb_miss > 0.05 & tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_load_stlb_miss_4k > 0.05 & (tma_load_stlb_miss > 0.05 & (tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))))", "ScaleUnit": "100%", "Unit": "cpu_core" }, { "BriefDescription": "This metric represents fraction of cycles the CPU spent handling cache misses due to lock operations", - "MetricExpr": "cpu_core@MEM_INST_RETIRED.LOCK_LOADS@ * cpu_core@mem_inst_retired.lock_loads@R / tma_info_thread_clks", + "MetricExpr": "cpu_core@MEM_INST_RETIRED.LOCK_LOADS@ * cpu_core@MEM_INST_RETIRED.LOCK_LOADS@R / tma_info_thread_clks", "MetricGroup": "LockCont;Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_l1_bound_group", "MetricName": "tma_lock_latency", - "MetricThreshold": "tma_lock_latency > 0.2 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_lock_latency > 0.2 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", "PublicDescription": "This metric represents fraction of cycles the CPU spent handling cache misses due to lock operations. Due to the microarchitecture handling of locks; they are classified as L1_Bound regardless of what memory source satisfied them. Sample with: MEM_INST_RETIRED.LOCK_LOADS. Related metrics: tma_store_latency", "ScaleUnit": "100%", "Unit": "cpu_core" @@ -2296,7 +2299,7 @@ "MetricGroup": "FetchBW;LSD;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group", "MetricName": "tma_lsd", "MetricThreshold": "tma_lsd > 0.15 & tma_fetch_bandwidth > 0.2", - "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to LSD (Loop Stream Detector) unit. LSD typically does well sustaining Uop supply. However; in some rare cases; optimal uop-delivery could not be reached for small loops whose size (in terms of number of uops) does not suit well the LSD structure", + "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to LSD (Loop Stream Detector) unit. LSD typically does well sustaining Uop supply. However; in some rare cases; optimal uop-delivery could not be reached for small loops whose size (in terms of number of uops) does not suit well the LSD structure.", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -2307,17 +2310,17 @@ "MetricName": "tma_machine_clears", "MetricThreshold": "tma_machine_clears > 0.1 & tma_bad_speculation > 0.15", "MetricgroupNoGroup": "TopdownL2", - "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears. These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT. Related metrics: tma_bottleneck_memory_synchronization, tma_clears_resteers, tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_l1_bound, tma_microcode_sequencer, tma_ms_switches", + "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears. These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT. Related metrics: tma_bottleneck_memory_synchronization, tma_clears_resteers, tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_l1_bound, tma_microcode_sequencer, tma_ms_switches, tma_remote_cache", "ScaleUnit": "100%", "Unit": "cpu_core" }, { "BriefDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory - DRAM ([SPR-HBM] and/or HBM)", - "MetricExpr": "min(cpu_core@CPU_CLK_UNHALTED.THREAD@, cpu_core@OFFCORE_REQUESTS_OUTSTANDING.DATA_RD\\,cmask\\=0x4@) / tma_info_thread_clks", + "MetricExpr": "min(cpu_core@CPU_CLK_UNHALTED.THREAD@, cpu_core@OFFCORE_REQUESTS_OUTSTANDING.DATA_RD\\,cmask\\=4@) / tma_info_thread_clks", "MetricGroup": "BvMB;MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueBW", "MetricName": "tma_mem_bandwidth", - "MetricThreshold": "tma_mem_bandwidth > 0.2 & tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", - "PublicDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory - DRAM ([SPR-HBM] and/or HBM). The underlying heuristic assumes that a similar off-core traffic is generated by all IA cores. This metric does not aggregate non-data-read requests by this logical processor; requests from other IA Logical Processors/Physical Cores/sockets; or other non-IA devices like GPU; hence the maximum external memory bandwidth limits may or may not be approached when this metric is flagged (see Uncore counters for that). Related metrics: tma_bottleneck_cache_memory_bandwidth, tma_fb_full, tma_sq_full", + "MetricThreshold": "tma_mem_bandwidth > 0.2 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory - DRAM ([SPR-HBM] and/or HBM). The underlying heuristic assumes that a similar off-core traffic is generated by all IA cores. This metric does not aggregate non-data-read requests by this logical processor; requests from other IA Logical Processors/Physical Cores/sockets; or other non-IA devices like GPU; hence the maximum external memory bandwidth limits may or may not be approached when this metric is flagged (see Uncore counters for that). Related metrics: tma_bottleneck_cache_memory_bandwidth, tma_fb_full, tma_info_system_dram_bw_use, tma_sq_full", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -2326,34 +2329,34 @@ "MetricExpr": "min(cpu_core@CPU_CLK_UNHALTED.THREAD@, cpu_core@OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD@) / tma_info_thread_clks - tma_mem_bandwidth", "MetricGroup": "BvML;MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueLat", "MetricName": "tma_mem_latency", - "MetricThreshold": "tma_mem_latency > 0.1 & tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_mem_latency > 0.1 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", "PublicDescription": "This metric estimates fraction of cycles where the performance was likely hurt due to latency from external memory - DRAM ([SPR-HBM] and/or HBM). This metric does not aggregate requests from other Logical Processors/Physical Cores/sockets (see Uncore counters for that). Related metrics: tma_bottleneck_cache_memory_latency, tma_l3_hit_latency", "ScaleUnit": "100%", "Unit": "cpu_core" }, { "BriefDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck", - "MetricExpr": "topdown\\-mem\\-bound / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * slots", + "MetricExpr": "cpu_core@topdown\\-mem\\-bound@ / (cpu_core@topdown\\-fe\\-bound@ + cpu_core@topdown\\-bad\\-spec@ + cpu_core@topdown\\-retiring@ + cpu_core@topdown\\-be\\-bound@) + 0 * tma_info_thread_slots", "MetricGroup": "Backend;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_memory_bound", "MetricThreshold": "tma_memory_bound > 0.2 & tma_backend_bound > 0.2", "MetricgroupNoGroup": "TopdownL2", - "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck. Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two)", + "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck. Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two).", "ScaleUnit": "100%", "Unit": "cpu_core" }, { - "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to LFENCE Instructions", + "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to LFENCE Instructions.", "MetricConstraint": "NO_GROUP_EVENTS_NMI", "MetricExpr": "13 * cpu_core@MISC2_RETIRED.LFENCE@ / tma_info_thread_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_serializing_operation_group", "MetricName": "tma_memory_fence", - "MetricThreshold": "tma_memory_fence > 0.05 & tma_serializing_operation > 0.1 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_memory_fence > 0.05 & (tma_serializing_operation > 0.1 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", "ScaleUnit": "100%", "Unit": "cpu_core" }, { - "BriefDescription": "This metric represents fraction of slots where the CPU was retiring memory operations , uops for memory load or store accesses", + "BriefDescription": "This metric represents fraction of slots where the CPU was retiring memory operations -- uops for memory load or store accesses.", "MetricExpr": "tma_light_operations * cpu_core@MEM_UOP_RETIRED.ANY@ / (tma_retiring * tma_info_thread_slots)", "MetricGroup": "Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group", "MetricName": "tma_memory_operations", @@ -2376,14 +2379,14 @@ "MetricExpr": "tma_branch_mispredicts / tma_bad_speculation * cpu_core@INT_MISC.CLEAR_RESTEER_CYCLES@ / tma_info_thread_clks", "MetricGroup": "BadSpec;BrMispredicts;BvMP;TopdownL4;tma_L4_group;tma_branch_resteers_group;tma_issueBM", "MetricName": "tma_mispredicts_resteers", - "MetricThreshold": "tma_mispredicts_resteers > 0.05 & tma_branch_resteers > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricThreshold": "tma_mispredicts_resteers > 0.05 & (tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))", "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Branch Misprediction at execution stage. Sample with: INT_MISC.CLEAR_RESTEER_CYCLES. Related metrics: tma_bottleneck_mispredictions, tma_branch_mispredicts, tma_info_bad_spec_branch_misprediction_cost", "ScaleUnit": "100%", "Unit": "cpu_core" }, { "BriefDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to the MITE pipeline (the legacy decode pipeline)", - "MetricExpr": "(cpu_core@IDQ.MITE_UOPS\\,cmask\\=0x8\\,inv\\=0x1@ / tma_info_thread_clks + cpu_core@IDQ.MITE_UOPS@ / (cpu_core@IDQ.DSB_UOPS@ + cpu_core@IDQ.MITE_UOPS@) * (cpu_core@IDQ_BUBBLES.CYCLES_0_UOPS_DELIV.CORE@ - cpu_core@IDQ_BUBBLES.FETCH_LATENCY@)) / tma_info_thread_clks", + "MetricExpr": "(cpu_core@IDQ.MITE_UOPS\\,cmask\\=0x8\\,inv\\=0x1@ / 2 + cpu_core@IDQ.MITE_UOPS@ / (cpu_core@IDQ.DSB_UOPS@ + cpu_core@IDQ.MITE_UOPS@) * (cpu_core@IDQ_BUBBLES.CYCLES_0_UOPS_DELIV.CORE@ - cpu_core@IDQ_BUBBLES.FETCH_LATENCY@)) / tma_info_thread_clks", "MetricGroup": "DSBmiss;FetchBW;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group", "MetricName": "tma_mite", "MetricThreshold": "tma_mite > 0.1 & tma_fetch_bandwidth > 0.2", @@ -2392,17 +2395,17 @@ "Unit": "cpu_core" }, { - "BriefDescription": "This metric estimates penalty in terms of percentage of([SKL+] injected blend uops out of all Uops Issued , the Count Domain; [ADL+] cycles)", + "BriefDescription": "This metric estimates penalty in terms of percentage of([SKL+] injected blend uops out of all Uops Issued -- the Count Domain; [ADL+] cycles)", "MetricExpr": "160 * cpu_core@ASSISTS.SSE_AVX_MIX@ / tma_info_thread_clks", "MetricGroup": "TopdownL5;tma_L5_group;tma_issueMV;tma_ports_utilized_0_group", "MetricName": "tma_mixing_vectors", "MetricThreshold": "tma_mixing_vectors > 0.05", - "PublicDescription": "This metric estimates penalty in terms of percentage of([SKL+] injected blend uops out of all Uops Issued , the Count Domain; [ADL+] cycles). Usually a Mixing_Vectors over 5% is worth investigating. Read more in Appendix B1 of the Optimizations Guide for this topic. Related metrics: tma_ms_switches", + "PublicDescription": "This metric estimates penalty in terms of percentage of([SKL+] injected blend uops out of all Uops Issued -- the Count Domain; [ADL+] cycles). Usually a Mixing_Vectors over 5% is worth investigating. Read more in Appendix B1 of the Optimizations Guide for this topic. Related metrics: tma_ms_switches", "ScaleUnit": "100%", "Unit": "cpu_core" }, { - "BriefDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to the Microcode Sequencer (MS) unit - see Microcode_Sequencer node for details", + "BriefDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to the Microcode Sequencer (MS) unit - see Microcode_Sequencer node for details.", "MetricExpr": "cpu_core@IDQ.MS_CYCLES_ANY@ / tma_info_thread_clks", "MetricGroup": "MicroSeq;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group", "MetricName": "tma_ms", @@ -2415,7 +2418,7 @@ "MetricExpr": "3 * cpu_core@IDQ.MS_SWITCHES@ / tma_info_thread_clks", "MetricGroup": "FetchLat;MicroSeq;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueMC;tma_issueMS;tma_issueMV;tma_issueSO", "MetricName": "tma_ms_switches", - "MetricThreshold": "tma_ms_switches > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricThreshold": "tma_ms_switches > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", "PublicDescription": "This metric estimates the fraction of cycles when the CPU was stalled due to switches of uop delivery to the Microcode Sequencer (MS). Commonly used instructions are optimized for delivery by the DSB (decoded i-cache) or MITE (legacy instruction decode) pipelines. Certain operations cannot be handled natively by the execution pipeline; and must be performed by microcode (small programs injected into the execution stream). Switching to the MS too often can negatively impact performance. The MS is designated to deliver long uop flows required by CISC instructions like CPUID; or uncommon conditions like Floating Point Assists when dealing with Denormals. Sample with: IDQ.MS_SWITCHES. Related metrics: tma_bottleneck_irregular_overhead, tma_clears_resteers, tma_l1_bound, tma_machine_clears, tma_microcode_sequencer, tma_mixing_vectors, tma_serializing_operation", "ScaleUnit": "100%", "Unit": "cpu_core" @@ -2426,7 +2429,7 @@ "MetricGroup": "Branches;BvBO;Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group", "MetricName": "tma_non_fused_branches", "MetricThreshold": "tma_non_fused_branches > 0.1 & tma_light_operations > 0.6", - "PublicDescription": "This metric represents fraction of slots where the CPU was retiring branch instructions that were not fused. Non-conditional branches like direct JMP or CALL would count here. Can be used to examine fusible conditional jumps that were not fused", + "PublicDescription": "This metric represents fraction of slots where the CPU was retiring branch instructions that were not fused. Non-conditional branches like direct JMP or CALL would count here. Can be used to examine fusible conditional jumps that were not fused.", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -2435,7 +2438,7 @@ "MetricExpr": "tma_light_operations * cpu_core@INST_RETIRED.NOP@ / (tma_retiring * tma_info_thread_slots)", "MetricGroup": "BvBO;Pipeline;TopdownL4;tma_L4_group;tma_other_light_ops_group", "MetricName": "tma_nop_instructions", - "MetricThreshold": "tma_nop_instructions > 0.1 & tma_other_light_ops > 0.3 & tma_light_operations > 0.6", + "MetricThreshold": "tma_nop_instructions > 0.1 & (tma_other_light_ops > 0.3 & tma_light_operations > 0.6)", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring NOP (no op) instructions. Compilers often use NOPs for certain address alignments - e.g. start address of a function or loop body. Sample with: INST_RETIRED.NOP", "ScaleUnit": "100%", "Unit": "cpu_core" @@ -2451,20 +2454,20 @@ "Unit": "cpu_core" }, { - "BriefDescription": "This metric estimates fraction of slots the CPU was stalled due to other cases of misprediction (non-retired x86 branches or other types)", + "BriefDescription": "This metric estimates fraction of slots the CPU was stalled due to other cases of misprediction (non-retired x86 branches or other types).", "MetricExpr": "max(tma_branch_mispredicts * (1 - cpu_core@BR_MISP_RETIRED.ALL_BRANCHES@ / (cpu_core@INT_MISC.CLEARS_COUNT@ - cpu_core@MACHINE_CLEARS.COUNT@)), 0.0001)", "MetricGroup": "BrMispredicts;BvIO;TopdownL3;tma_L3_group;tma_branch_mispredicts_group", "MetricName": "tma_other_mispredicts", - "MetricThreshold": "tma_other_mispredicts > 0.05 & tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", + "MetricThreshold": "tma_other_mispredicts > 0.05 & (tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15)", "ScaleUnit": "100%", "Unit": "cpu_core" }, { - "BriefDescription": "This metric represents fraction of slots the CPU has wasted due to Nukes (Machine Clears) not related to memory ordering", + "BriefDescription": "This metric represents fraction of slots the CPU has wasted due to Nukes (Machine Clears) not related to memory ordering.", "MetricExpr": "max(tma_machine_clears * (1 - cpu_core@MACHINE_CLEARS.MEMORY_ORDERING@ / cpu_core@MACHINE_CLEARS.COUNT@), 0.0001)", "MetricGroup": "BvIO;Machine_Clears;TopdownL3;tma_L3_group;tma_machine_clears_group", "MetricName": "tma_other_nukes", - "MetricThreshold": "tma_other_nukes > 0.05 & tma_machine_clears > 0.1 & tma_bad_speculation > 0.15", + "MetricThreshold": "tma_other_nukes > 0.05 & (tma_machine_clears > 0.1 & tma_bad_speculation > 0.15)", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -2474,7 +2477,7 @@ "MetricGroup": "TopdownL5;tma_L5_group;tma_assists_group", "MetricName": "tma_page_faults", "MetricThreshold": "tma_page_faults > 0.05", - "PublicDescription": "This metric roughly estimates fraction of slots the CPU retired uops as a result of handing Page Faults. A Page Fault may apply on first application access to a memory page. Note operating system handling of page faults accounts for the majority of its cost", + "PublicDescription": "This metric roughly estimates fraction of slots the CPU retired uops as a result of handing Page Faults. A Page Fault may apply on first application access to a memory page. Note operating system handling of page faults accounts for the majority of its cost.", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -2483,8 +2486,8 @@ "MetricExpr": "((cpu_core@EXE_ACTIVITY.EXE_BOUND_0_PORTS@ + (cpu_core@EXE_ACTIVITY.1_PORTS_UTIL@ + tma_retiring * cpu_core@EXE_ACTIVITY.2_3_PORTS_UTIL@)) / tma_info_thread_clks if cpu_core@ARITH.DIV_ACTIVE@ < cpu_core@CYCLE_ACTIVITY.STALLS_TOTAL@ - cpu_core@EXE_ACTIVITY.BOUND_ON_LOADS@ else (cpu_core@EXE_ACTIVITY.1_PORTS_UTIL@ + tma_retiring * cpu_core@EXE_ACTIVITY.2_3_PORTS_UTIL@) / tma_info_thread_clks)", "MetricGroup": "PortsUtil;TopdownL3;tma_L3_group;tma_core_bound_group", "MetricName": "tma_ports_utilization", - "MetricThreshold": "tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", - "PublicDescription": "This metric estimates fraction of cycles the CPU performance was potentially limited due to Core computation issues (non divider-related). Two distinct categories can be attributed into this metric: (1) heavy data-dependency among contiguous instructions would manifest in this metric - such cases are often referred to as low Instruction Level Parallelism (ILP). (2) Contention on some hardware execution unit other than Divider. For example; when there are too many multiply operations", + "MetricThreshold": "tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)", + "PublicDescription": "This metric estimates fraction of cycles the CPU performance was potentially limited due to Core computation issues (non divider-related). Two distinct categories can be attributed into this metric: (1) heavy data-dependency among contiguous instructions would manifest in this metric - such cases are often referred to as low Instruction Level Parallelism (ILP). (2) Contention on some hardware execution unit other than Divider. For example; when there are too many multiply operations.", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -2493,8 +2496,8 @@ "MetricExpr": "cpu_core@EXE_ACTIVITY.EXE_BOUND_0_PORTS@ / tma_info_thread_clks", "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group", "MetricName": "tma_ports_utilized_0", - "MetricThreshold": "tma_ports_utilized_0 > 0.2 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", - "PublicDescription": "This metric represents fraction of cycles CPU executed no uops on any execution port (Logical Processor cycles since ICL, Physical Core cycles otherwise). Long-latency instructions like divides may contribute to this metric", + "MetricThreshold": "tma_ports_utilized_0 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric represents fraction of cycles CPU executed no uops on any execution port (Logical Processor cycles since ICL, Physical Core cycles otherwise). Long-latency instructions like divides may contribute to this metric.", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -2503,7 +2506,7 @@ "MetricExpr": "cpu_core@EXE_ACTIVITY.1_PORTS_UTIL@ / tma_info_thread_clks", "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_issueL1;tma_ports_utilization_group", "MetricName": "tma_ports_utilized_1", - "MetricThreshold": "tma_ports_utilized_1 > 0.2 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_ports_utilized_1 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", "PublicDescription": "This metric represents fraction of cycles where the CPU executed total of 1 uop per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise). This can be due to heavy data-dependency among software instructions; or over oversubscribing a particular hardware resource. In some other cases with high 1_Port_Utilized and L1_Bound; this metric can point to L1 data-cache latency bottleneck that may not necessarily manifest with complete execution starvation (due to the short L1 latency e.g. walking a linked list) - looking at the assembly can be helpful. Sample with: EXE_ACTIVITY.1_PORTS_UTIL. Related metrics: tma_l1_bound", "ScaleUnit": "100%", "Unit": "cpu_core" @@ -2514,8 +2517,8 @@ "MetricExpr": "cpu_core@EXE_ACTIVITY.2_PORTS_UTIL@ / tma_info_thread_clks", "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_issue2P;tma_ports_utilization_group", "MetricName": "tma_ports_utilized_2", - "MetricThreshold": "tma_ports_utilized_2 > 0.15 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", - "PublicDescription": "This metric represents fraction of cycles CPU executed total of 2 uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise). Loop Vectorization -most compilers feature auto-Vectorization options today- reduces pressure on the execution ports as multiple elements are calculated with same uop. Sample with: EXE_ACTIVITY.2_PORTS_UTIL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_int_vector_128b, tma_int_vector_256b", + "MetricThreshold": "tma_ports_utilized_2 > 0.15 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric represents fraction of cycles CPU executed total of 2 uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise). Loop Vectorization -most compilers feature auto-Vectorization options today- reduces pressure on the execution ports as multiple elements are calculated with same uop. Sample with: EXE_ACTIVITY.2_PORTS_UTIL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_port_6", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -2525,24 +2528,24 @@ "MetricExpr": "cpu_core@UOPS_EXECUTED.CYCLES_GE_3@ / tma_info_thread_clks", "MetricGroup": "BvCB;PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group", "MetricName": "tma_ports_utilized_3m", - "MetricThreshold": "tma_ports_utilized_3m > 0.4 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_ports_utilized_3m > 0.4 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", "PublicDescription": "This metric represents fraction of cycles CPU executed total of 3 or more uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise). Sample with: UOPS_EXECUTED.CYCLES_GE_3", "ScaleUnit": "100%", "Unit": "cpu_core" }, { - "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to retired misprediction by (indirect) RET instructions", - "MetricExpr": "cpu_core@BR_MISP_RETIRED.RET_COST@ * cpu_core@br_misp_retired.ret_cost@R / tma_info_thread_clks", + "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to retired misprediction by (indirect) RET instructions.", + "MetricExpr": "cpu_core@BR_MISP_RETIRED.RET_COST@ * cpu_core@BR_MISP_RETIRED.RET_COST@R / tma_info_thread_clks", "MetricGroup": "BrMispredicts;TopdownL3;tma_L3_group;tma_branch_mispredicts_group", "MetricName": "tma_ret_mispredicts", - "MetricThreshold": "tma_ret_mispredicts > 0.05 & tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", + "MetricThreshold": "tma_ret_mispredicts > 0.05 & (tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15)", "ScaleUnit": "100%", "Unit": "cpu_core" }, { "BriefDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired", "DefaultMetricgroupName": "TopdownL1", - "MetricExpr": "topdown\\-retiring / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * slots", + "MetricExpr": "cpu_core@topdown\\-retiring@ / (cpu_core@topdown\\-fe\\-bound@ + cpu_core@topdown\\-bad\\-spec@ + cpu_core@topdown\\-retiring@ + cpu_core@topdown\\-be\\-bound@) + 0 * tma_info_thread_slots", "MetricGroup": "BvUW;Default;TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_retiring", "MetricThreshold": "tma_retiring > 0.7 | tma_heavy_operations > 0.1", @@ -2556,8 +2559,8 @@ "MetricExpr": "(cpu_core@BE_STALLS.SCOREBOARD@ + cpu_core@CPU_CLK_UNHALTED.C02@) / tma_info_thread_clks", "MetricGroup": "BvIO;PortsUtil;TopdownL3;tma_L3_group;tma_core_bound_group;tma_issueSO", "MetricName": "tma_serializing_operation", - "MetricThreshold": "tma_serializing_operation > 0.1 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", - "PublicDescription": "This metric represents fraction of cycles the CPU issue-pipeline was stalled due to serializing operations. Instructions like CPUID; WRMSR or LFENCE serialize the out-of-order execution which may limit performance. Sample with: BE_STALLS.SCOREBOARD. Related metrics: tma_ms_switches", + "MetricThreshold": "tma_serializing_operation > 0.1 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)", + "PublicDescription": "This metric represents fraction of cycles the CPU issue-pipeline was stalled due to serializing operations. Instructions like CPUID; WRMSR or LFENCE serialize the out-of-order execution which may limit performance. Sample with: PARTIAL_RAT_STALLS.SCOREBOARD. Related metrics: tma_ms_switches", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -2566,8 +2569,8 @@ "MetricExpr": "tma_light_operations * cpu_core@INT_VEC_RETIRED.SHUFFLES@ / (tma_retiring * tma_info_thread_slots)", "MetricGroup": "HPC;Pipeline;TopdownL4;tma_L4_group;tma_other_light_ops_group", "MetricName": "tma_shuffles_256b", - "MetricThreshold": "tma_shuffles_256b > 0.1 & tma_other_light_ops > 0.3 & tma_light_operations > 0.6", - "PublicDescription": "This metric represents fraction of slots where the CPU was retiring Shuffle operations of 256-bit vector size (FP or Integer). Shuffles may incur slow cross \"vector lane\" data transfers", + "MetricThreshold": "tma_shuffles_256b > 0.1 & (tma_other_light_ops > 0.3 & tma_light_operations > 0.6)", + "PublicDescription": "This metric represents fraction of slots where the CPU was retiring Shuffle operations of 256-bit vector size (FP or Integer). Shuffles may incur slow cross \"vector lane\" data transfers.", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -2577,28 +2580,28 @@ "MetricExpr": "cpu_core@CPU_CLK_UNHALTED.PAUSE@ / tma_info_thread_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_serializing_operation_group", "MetricName": "tma_slow_pause", - "MetricThreshold": "tma_slow_pause > 0.05 & tma_serializing_operation > 0.1 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_slow_pause > 0.05 & (tma_serializing_operation > 0.1 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to PAUSE Instructions. Sample with: CPU_CLK_UNHALTED.PAUSE_INST", "ScaleUnit": "100%", "Unit": "cpu_core" }, { "BriefDescription": "This metric estimates fraction of cycles handling memory load split accesses - load that cross 64-byte cache line boundary", - "MetricExpr": "(min(cpu_core@MEM_INST_RETIRED.SPLIT_LOADS@ * cpu_core@mem_inst_retired.split_loads@R, cpu_core@MEM_INST_RETIRED.SPLIT_LOADS@ * tma_info_memory_load_miss_real_latency) if 0 < cpu_core@mem_inst_retired.split_loads@R else cpu_core@MEM_INST_RETIRED.SPLIT_LOADS@ * tma_info_memory_load_miss_real_latency) / tma_info_thread_clks", + "MetricExpr": "cpu_core@MEM_INST_RETIRED.SPLIT_LOADS@ * min(cpu_core@MEM_INST_RETIRED.SPLIT_LOADS@R, tma_info_memory_load_miss_real_latency) / tma_info_thread_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group", "MetricName": "tma_split_loads", "MetricThreshold": "tma_split_loads > 0.3", - "PublicDescription": "This metric estimates fraction of cycles handling memory load split accesses - load that cross 64-byte cache line boundary. Sample with: MEM_INST_RETIRED.SPLIT_LOADS", + "PublicDescription": "This metric estimates fraction of cycles handling memory load split accesses - load that cross 64-byte cache line boundary. Sample with: MEM_INST_RETIRED.SPLIT_LOADS_PS", "ScaleUnit": "100%", "Unit": "cpu_core" }, { "BriefDescription": "This metric represents rate of split store accesses", - "MetricExpr": "(min(cpu_core@MEM_INST_RETIRED.SPLIT_STORES@ * cpu_core@mem_inst_retired.split_stores@R, cpu_core@MEM_INST_RETIRED.SPLIT_STORES@) if 0 < cpu_core@mem_inst_retired.split_stores@R else cpu_core@MEM_INST_RETIRED.SPLIT_STORES@) / tma_info_thread_clks", + "MetricExpr": "cpu_core@MEM_INST_RETIRED.SPLIT_STORES@ * min(cpu_core@MEM_INST_RETIRED.SPLIT_STORES@R, 1) / tma_info_thread_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_issueSpSt;tma_store_bound_group", "MetricName": "tma_split_stores", - "MetricThreshold": "tma_split_stores > 0.2 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", - "PublicDescription": "This metric represents rate of split store accesses. Consider aligning your data to the 64-byte cache line granularity. Sample with: MEM_INST_RETIRED.SPLIT_STORES", + "MetricThreshold": "tma_split_stores > 0.2 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric represents rate of split store accesses. Consider aligning your data to the 64-byte cache line granularity. Sample with: MEM_INST_RETIRED.SPLIT_STORES_PS. Related metrics: tma_port_4", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -2607,8 +2610,8 @@ "MetricExpr": "(cpu_core@XQ.FULL@ + cpu_core@L1D_MISS.L2_STALLS@) / tma_info_thread_clks", "MetricGroup": "BvMB;MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_issueBW;tma_l3_bound_group", "MetricName": "tma_sq_full", - "MetricThreshold": "tma_sq_full > 0.3 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", - "PublicDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors). Related metrics: tma_bottleneck_cache_memory_bandwidth, tma_fb_full, tma_mem_bandwidth", + "MetricThreshold": "tma_sq_full > 0.3 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors). Related metrics: tma_bottleneck_cache_memory_bandwidth, tma_fb_full, tma_info_system_dram_bw_use, tma_mem_bandwidth", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -2617,8 +2620,8 @@ "MetricExpr": "cpu_core@EXE_ACTIVITY.BOUND_ON_STORES@ / tma_info_thread_clks", "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_store_bound", - "MetricThreshold": "tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", - "PublicDescription": "This metric estimates how often CPU was stalled due to RFO store memory accesses; RFO store issue a read-for-ownership request before the write. Even though store accesses do not typically stall out-of-order CPUs; there are few cases where stores can lead to actual stalls. This metric will be flagged should RFO stores be a bottleneck. Sample with: MEM_INST_RETIRED.ALL_STORES", + "MetricThreshold": "tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", + "PublicDescription": "This metric estimates how often CPU was stalled due to RFO store memory accesses; RFO store issue a read-for-ownership request before the write. Even though store accesses do not typically stall out-of-order CPUs; there are few cases where stores can lead to actual stalls. This metric will be flagged should RFO stores be a bottleneck. Sample with: MEM_INST_RETIRED.ALL_STORES_PS", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -2627,8 +2630,8 @@ "MetricExpr": "13 * cpu_core@LD_BLOCKS.STORE_FORWARD@ / tma_info_thread_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group", "MetricName": "tma_store_fwd_blk", - "MetricThreshold": "tma_store_fwd_blk > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", - "PublicDescription": "This metric roughly estimates fraction of cycles when the memory subsystem had loads blocked since they could not forward data from earlier (in program order) overlapping stores. To streamline memory operations in the pipeline; a load can avoid waiting for memory if a prior in-flight store is writing the data that the load wants to read (store forwarding process). However; in some cases the load may be blocked for a significant time pending the store forward. For example; when the prior store is writing a smaller region than the load is reading", + "MetricThreshold": "tma_store_fwd_blk > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric roughly estimates fraction of cycles when the memory subsystem had loads blocked since they could not forward data from earlier (in program order) overlapping stores. To streamline memory operations in the pipeline; a load can avoid waiting for memory if a prior in-flight store is writing the data that the load wants to read (store forwarding process). However; in some cases the load may be blocked for a significant time pending the store forward. For example; when the prior store is writing a smaller region than the load is reading.", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -2637,8 +2640,8 @@ "MetricExpr": "(cpu_core@MEM_STORE_RETIRED.L2_HIT@ * 10 * (1 - cpu_core@MEM_INST_RETIRED.LOCK_LOADS@ / cpu_core@MEM_INST_RETIRED.ALL_STORES@) + (1 - cpu_core@MEM_INST_RETIRED.LOCK_LOADS@ / cpu_core@MEM_INST_RETIRED.ALL_STORES@) * min(cpu_core@CPU_CLK_UNHALTED.THREAD@, cpu_core@OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO@)) / tma_info_thread_clks", "MetricGroup": "BvML;LockCont;MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_issueSL;tma_store_bound_group", "MetricName": "tma_store_latency", - "MetricThreshold": "tma_store_latency > 0.1 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", - "PublicDescription": "This metric estimates fraction of cycles the CPU spent handling L1D store misses. Store accesses usually less impact out-of-order core performance; however; holding resources for longer time can lead into undesired implications (e.g. contention on L1D fill-buffer entries - see FB_Full). Related metrics: tma_branch_resteers, tma_fb_full, tma_l3_hit_latency, tma_lock_latency", + "MetricThreshold": "tma_store_latency > 0.1 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric estimates fraction of cycles the CPU spent handling L1D store misses. Store accesses usually less impact out-of-order core performance; however; holding resources for longer time can lead into undesired implications (e.g. contention on L1D fill-buffer entries - see FB_Full). Related metrics: tma_fb_full, tma_lock_latency", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -2648,7 +2651,6 @@ "MetricGroup": "TopdownL5;tma_L5_group;tma_ports_utilized_3m_group", "MetricName": "tma_store_op_utilization", "MetricThreshold": "tma_store_op_utilization > 0.6", - "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port for Store operations. Sample with: UOPS_DISPATCHED.STD, UOPS_DISPATCHED.STA", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -2657,7 +2659,7 @@ "MetricExpr": "max(0, tma_dtlb_store - tma_store_stlb_miss)", "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_store_group", "MetricName": "tma_store_stlb_hit", - "MetricThreshold": "tma_store_stlb_hit > 0.05 & tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_store_stlb_hit > 0.05 & (tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -2666,34 +2668,34 @@ "MetricExpr": "cpu_core@DTLB_STORE_MISSES.WALK_ACTIVE@ / tma_info_thread_clks", "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_store_group", "MetricName": "tma_store_stlb_miss", - "MetricThreshold": "tma_store_stlb_miss > 0.05 & tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_store_stlb_miss > 0.05 & (tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))", "ScaleUnit": "100%", "Unit": "cpu_core" }, { - "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 1 GB pages for data store accesses", + "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 1 GB pages for data store accesses.", "MetricExpr": "tma_store_stlb_miss * cpu_core@DTLB_STORE_MISSES.WALK_COMPLETED_1G@ / (cpu_core@DTLB_STORE_MISSES.WALK_COMPLETED_4K@ + cpu_core@DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M@ + cpu_core@DTLB_STORE_MISSES.WALK_COMPLETED_1G@)", "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_store_stlb_miss_group", "MetricName": "tma_store_stlb_miss_1g", - "MetricThreshold": "tma_store_stlb_miss_1g > 0.05 & tma_store_stlb_miss > 0.05 & tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_store_stlb_miss_1g > 0.05 & (tma_store_stlb_miss > 0.05 & (tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))))", "ScaleUnit": "100%", "Unit": "cpu_core" }, { - "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 2 or 4 MB pages for data store accesses", + "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 2 or 4 MB pages for data store accesses.", "MetricExpr": "tma_store_stlb_miss * cpu_core@DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M@ / (cpu_core@DTLB_STORE_MISSES.WALK_COMPLETED_4K@ + cpu_core@DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M@ + cpu_core@DTLB_STORE_MISSES.WALK_COMPLETED_1G@)", "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_store_stlb_miss_group", "MetricName": "tma_store_stlb_miss_2m", - "MetricThreshold": "tma_store_stlb_miss_2m > 0.05 & tma_store_stlb_miss > 0.05 & tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_store_stlb_miss_2m > 0.05 & (tma_store_stlb_miss > 0.05 & (tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))))", "ScaleUnit": "100%", "Unit": "cpu_core" }, { - "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 4 KB pages for data store accesses", + "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 4 KB pages for data store accesses.", "MetricExpr": "tma_store_stlb_miss * cpu_core@DTLB_STORE_MISSES.WALK_COMPLETED_4K@ / (cpu_core@DTLB_STORE_MISSES.WALK_COMPLETED_4K@ + cpu_core@DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M@ + cpu_core@DTLB_STORE_MISSES.WALK_COMPLETED_1G@)", "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_store_stlb_miss_group", "MetricName": "tma_store_stlb_miss_4k", - "MetricThreshold": "tma_store_stlb_miss_4k > 0.05 & tma_store_stlb_miss > 0.05 & tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_store_stlb_miss_4k > 0.05 & (tma_store_stlb_miss > 0.05 & (tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))))", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -2702,7 +2704,7 @@ "MetricExpr": "9 * cpu_core@OCR.STREAMING_WR.ANY_RESPONSE@ / tma_info_thread_clks", "MetricGroup": "MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_issueSmSt;tma_store_bound_group", "MetricName": "tma_streaming_stores", - "MetricThreshold": "tma_streaming_stores > 0.2 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_streaming_stores > 0.2 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", "PublicDescription": "This metric estimates how often CPU was stalled due to Streaming store memory accesses; Streaming store optimize out a read request required by RFO stores. Even though store accesses do not typically stall out-of-order CPUs; there are few cases where stores can lead to actual stalls. This metric will be flagged should Streaming stores be a bottleneck. Sample with: OCR.STREAMING_WR.ANY_RESPONSE. Related metrics: tma_fb_full", "ScaleUnit": "100%", "Unit": "cpu_core" @@ -2712,7 +2714,7 @@ "MetricExpr": "cpu_core@INT_MISC.UNKNOWN_BRANCH_CYCLES@ / tma_info_thread_clks", "MetricGroup": "BigFootprint;BvBC;FetchLat;TopdownL4;tma_L4_group;tma_branch_resteers_group", "MetricName": "tma_unknown_branches", - "MetricThreshold": "tma_unknown_branches > 0.05 & tma_branch_resteers > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricThreshold": "tma_unknown_branches > 0.05 & (tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))", "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to new branch address clears. These are fetched branches the Branch Prediction Unit was unable to recognize (e.g. first time the branch is fetched or hitting BTB capacity limit) hence called Unknown Branches. Sample with: FRONTEND_RETIRED.UNKNOWN_BRANCH", "ScaleUnit": "100%", "Unit": "cpu_core" @@ -2722,8 +2724,8 @@ "MetricExpr": "tma_retiring * cpu_core@UOPS_EXECUTED.X87@ / cpu_core@UOPS_EXECUTED.THREAD@", "MetricGroup": "Compute;TopdownL4;tma_L4_group;tma_fp_arith_group", "MetricName": "tma_x87_use", - "MetricThreshold": "tma_x87_use > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6", - "PublicDescription": "This metric serves as an approximation of legacy x87 usage. It accounts for instructions beyond X87 FP arithmetic operations; hence may be used as a thermometer to avoid X87 high usage and preferably upgrade to modern ISA. See Tip under Tuning Hint", + "MetricThreshold": "tma_x87_use > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6)", + "PublicDescription": "This metric serves as an approximation of legacy x87 usage. It accounts for instructions beyond X87 FP arithmetic operations; hence may be used as a thermometer to avoid X87 high usage and preferably upgrade to modern ISA. See Tip under Tuning Hint.", "ScaleUnit": "100%", "Unit": "cpu_core" } diff --git a/tools/perf/pmu-events/arch/x86/lunarlake/memory.json b/tools/perf/pmu-events/arch/x86/lunarlake/memory.json index 60daff922a89..8021a1c7dd3b 100644 --- a/tools/perf/pmu-events/arch/x86/lunarlake/memory.json +++ b/tools/perf/pmu-events/arch/x86/lunarlake/memory.json @@ -163,7 +163,7 @@ "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_1024", "MSRIndex": "0x3F6", "MSRValue": "0x400", - "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 1024 cycles. Reported latency may be longer than just the memory latency.", + "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 1024 cycles. Reported latency may be longer than just the memory latency. Available PDIST counters: 0", "SampleAfterValue": "53", "UMask": "0x1", "Unit": "cpu_core" @@ -176,7 +176,7 @@ "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_128", "MSRIndex": "0x3F6", "MSRValue": "0x80", - "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 128 cycles. Reported latency may be longer than just the memory latency.", + "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 128 cycles. Reported latency may be longer than just the memory latency. Available PDIST counters: 0", "SampleAfterValue": "1009", "UMask": "0x1", "Unit": "cpu_core" @@ -189,7 +189,7 @@ "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_16", "MSRIndex": "0x3F6", "MSRValue": "0x10", - "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 16 cycles. Reported latency may be longer than just the memory latency.", + "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 16 cycles. Reported latency may be longer than just the memory latency. Available PDIST counters: 0", "SampleAfterValue": "20011", "UMask": "0x1", "Unit": "cpu_core" @@ -202,7 +202,7 @@ "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_2048", "MSRIndex": "0x3F6", "MSRValue": "0x800", - "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 2048 cycles. Reported latency may be longer than just the memory latency.", + "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 2048 cycles. Reported latency may be longer than just the memory latency. Available PDIST counters: 0", "SampleAfterValue": "23", "UMask": "0x1", "Unit": "cpu_core" @@ -215,7 +215,7 @@ "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_256", "MSRIndex": "0x3F6", "MSRValue": "0x100", - "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 256 cycles. Reported latency may be longer than just the memory latency.", + "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 256 cycles. Reported latency may be longer than just the memory latency. Available PDIST counters: 0", "SampleAfterValue": "503", "UMask": "0x1", "Unit": "cpu_core" @@ -228,7 +228,7 @@ "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_32", "MSRIndex": "0x3F6", "MSRValue": "0x20", - "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 32 cycles. Reported latency may be longer than just the memory latency.", + "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 32 cycles. Reported latency may be longer than just the memory latency. Available PDIST counters: 0", "SampleAfterValue": "100007", "UMask": "0x1", "Unit": "cpu_core" @@ -241,7 +241,7 @@ "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_4", "MSRIndex": "0x3F6", "MSRValue": "0x4", - "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 4 cycles. Reported latency may be longer than just the memory latency.", + "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 4 cycles. Reported latency may be longer than just the memory latency. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1", "Unit": "cpu_core" @@ -254,7 +254,7 @@ "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_512", "MSRIndex": "0x3F6", "MSRValue": "0x200", - "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 512 cycles. Reported latency may be longer than just the memory latency.", + "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 512 cycles. Reported latency may be longer than just the memory latency. Available PDIST counters: 0", "SampleAfterValue": "101", "UMask": "0x1", "Unit": "cpu_core" @@ -267,7 +267,7 @@ "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_64", "MSRIndex": "0x3F6", "MSRValue": "0x40", - "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 64 cycles. Reported latency may be longer than just the memory latency.", + "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 64 cycles. Reported latency may be longer than just the memory latency. Available PDIST counters: 0", "SampleAfterValue": "2003", "UMask": "0x1", "Unit": "cpu_core" @@ -280,7 +280,7 @@ "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_8", "MSRIndex": "0x3F6", "MSRValue": "0x8", - "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 8 cycles. Reported latency may be longer than just the memory latency.", + "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 8 cycles. Reported latency may be longer than just the memory latency. Available PDIST counters: 0", "SampleAfterValue": "50021", "UMask": "0x1", "Unit": "cpu_core" @@ -291,7 +291,7 @@ "Data_LA": "1", "EventCode": "0xcd", "EventName": "MEM_TRANS_RETIRED.STORE_SAMPLE", - "PublicDescription": "Counts Retired memory accesses with at least 1 store operation. This PEBS event is the precisely-distributed (PDist) trigger covering all stores uops for sampling by the PEBS Store Latency Facility. The facility is described in Intel SDM Volume 3 section 19.9.8", + "PublicDescription": "Counts Retired memory accesses with at least 1 store operation. This PEBS event is the precisely-distributed (PDist) trigger covering all stores uops for sampling by the PEBS Store Latency Facility. The facility is described in Intel SDM Volume 3 section 19.9.8 Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x2", "Unit": "cpu_core" @@ -315,23 +315,61 @@ "Unit": "cpu_atom" }, { + "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were supplied by DRAM.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xB7", + "EventName": "OCR.DEMAND_CODE_RD.DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x1FBC000004", + "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were supplied by DRAM. Available PDIST counters: 0", + "SampleAfterValue": "100003", + "UMask": "0x1", + "Unit": "cpu_atom" + }, + { "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were not supplied by the L3 cache and were supplied by the system memory (DRAM, MSC, or MMIO).", "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xB7", "EventName": "OCR.DEMAND_CODE_RD.L3_MISS", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x13FBFC00004", + "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were not supplied by the L3 cache and were supplied by the system memory (DRAM, MSC, or MMIO). Available PDIST counters: 0", + "SampleAfterValue": "100003", + "UMask": "0x1", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts demand data reads that were supplied by DRAM.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xB7", + "EventName": "OCR.DEMAND_DATA_RD.DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x1FBC000001", + "PublicDescription": "Counts demand data reads that were supplied by DRAM. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1", "Unit": "cpu_atom" }, { + "BriefDescription": "Counts demand data reads that were supplied by DRAM.", + "Counter": "0,1,2,3", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.DEMAND_DATA_RD.DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x1E780000001", + "PublicDescription": "Counts demand data reads that were supplied by DRAM. Available PDIST counters: 0", + "SampleAfterValue": "100003", + "UMask": "0x1", + "Unit": "cpu_core" + }, + { "BriefDescription": "Counts demand data reads that were not supplied by the L3 cache and were supplied by the system memory (DRAM, MSC, or MMIO).", "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xB7", "EventName": "OCR.DEMAND_DATA_RD.L3_MISS", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x13FBFC00001", + "PublicDescription": "Counts demand data reads that were not supplied by the L3 cache and were supplied by the system memory (DRAM, MSC, or MMIO). Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1", "Unit": "cpu_atom" @@ -343,17 +381,31 @@ "EventName": "OCR.DEMAND_DATA_RD.L3_MISS", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x9E7FA000001", + "PublicDescription": "Counts demand data reads that were not supplied by the L3 cache and were supplied by the system memory (DRAM, MSC, or MMIO). Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1", "Unit": "cpu_core" }, { + "BriefDescription": "Counts demand read for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that were supplied by DRAM.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xB7", + "EventName": "OCR.DEMAND_RFO.DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x1FBC000002", + "PublicDescription": "Counts demand read for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that were supplied by DRAM. Available PDIST counters: 0", + "SampleAfterValue": "100003", + "UMask": "0x1", + "Unit": "cpu_atom" + }, + { "BriefDescription": "Counts demand read for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that were not supplied by the L3 cache and were supplied by the system memory (DRAM, MSC, or MMIO).", "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xB7", "EventName": "OCR.DEMAND_RFO.L3_MISS", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x13FBFC00002", + "PublicDescription": "Counts demand read for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that were not supplied by the L3 cache and were supplied by the system memory (DRAM, MSC, or MMIO). Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1", "Unit": "cpu_atom" @@ -365,6 +417,7 @@ "EventName": "OCR.DEMAND_RFO.L3_MISS", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x9E7FA000002", + "PublicDescription": "Counts demand read for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that were not supplied by the L3 cache and were supplied by the system memory (DRAM, MSC, or MMIO). Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1", "Unit": "cpu_core" diff --git a/tools/perf/pmu-events/arch/x86/lunarlake/other.json b/tools/perf/pmu-events/arch/x86/lunarlake/other.json index 667707d4fe37..59949f9541d8 100644 --- a/tools/perf/pmu-events/arch/x86/lunarlake/other.json +++ b/tools/perf/pmu-events/arch/x86/lunarlake/other.json @@ -19,15 +19,6 @@ "Unit": "cpu_core" }, { - "BriefDescription": "Counts cycles where the pipeline is stalled due to serializing operations.", - "Counter": "0,1,2,3,4,5,6,7,8,9", - "EventCode": "0xa2", - "EventName": "BE_STALLS.SCOREBOARD", - "SampleAfterValue": "100003", - "UMask": "0x2", - "Unit": "cpu_core" - }, - { "BriefDescription": "Counts the number of unhalted cycles a Core is blocked due to a lock In Progress issued by another core", "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0x63", @@ -66,15 +57,6 @@ "Unit": "cpu_atom" }, { - "BriefDescription": "Count number of times a load is depending on another load that had just write back its data or in previous or 2 cycles back. This event supports in-direct dependency through a single uop.", - "Counter": "0,1,2,3,4,5,6,7,8,9", - "EventCode": "0x02", - "EventName": "DEPENDENT_LOADS.ANY", - "SampleAfterValue": "1000003", - "UMask": "0x7", - "Unit": "cpu_core" - }, - { "BriefDescription": "Counts the number of cycles the L2 Prefetchers are at throttle level 0", "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0x32", @@ -120,297 +102,13 @@ "Unit": "cpu_atom" }, { - "BriefDescription": "Counts the number of uops executed on all Integer ports.", - "Counter": "0,1,2,3,4,5,6,7", - "EventCode": "0xb3", - "EventName": "INT_UOPS_EXECUTED.ALL", - "SampleAfterValue": "1000003", - "UMask": "0xff", - "Unit": "cpu_atom" - }, - { - "BriefDescription": "Counts the number of uops executed on a load port.", - "Counter": "0,1,2,3,4,5,6,7", - "EventCode": "0xb3", - "EventName": "INT_UOPS_EXECUTED.LD", - "PublicDescription": "Counts the number of uops executed on a load port. This event counts for integer uops even if the destination is FP/vector", - "SampleAfterValue": "1000003", - "UMask": "0x1", - "Unit": "cpu_atom" - }, - { - "BriefDescription": "Counts the number of uops executed on integer port 0.", - "Counter": "0,1,2,3,4,5,6,7", - "EventCode": "0xb3", - "EventName": "INT_UOPS_EXECUTED.P0", - "SampleAfterValue": "1000003", - "UMask": "0x8", - "Unit": "cpu_atom" - }, - { - "BriefDescription": "Counts the number of uops executed on integer port 1.", - "Counter": "0,1,2,3,4,5,6,7", - "EventCode": "0xb3", - "EventName": "INT_UOPS_EXECUTED.P1", - "SampleAfterValue": "1000003", - "UMask": "0x10", - "Unit": "cpu_atom" - }, - { - "BriefDescription": "Counts the number of uops executed on integer port 2.", - "Counter": "0,1,2,3,4,5,6,7", - "EventCode": "0xb3", - "EventName": "INT_UOPS_EXECUTED.P2", - "SampleAfterValue": "1000003", - "UMask": "0x20", - "Unit": "cpu_atom" - }, - { - "BriefDescription": "Counts the number of uops executed on integer port 3.", - "Counter": "0,1,2,3,4,5,6,7", - "EventCode": "0xb3", - "EventName": "INT_UOPS_EXECUTED.P3", - "SampleAfterValue": "1000003", - "UMask": "0x40", - "Unit": "cpu_atom" - }, - { - "BriefDescription": "Counts the number of uops executed on integer port 0,1, 2, 3.", - "Counter": "0,1,2,3,4,5,6,7", - "EventCode": "0xb3", - "EventName": "INT_UOPS_EXECUTED.PRIMARY", - "SampleAfterValue": "1000003", - "UMask": "0x78", - "Unit": "cpu_atom" - }, - { - "BriefDescription": "Counts the number of uops executed on a Store address port.", - "Counter": "0,1,2,3,4,5,6,7", - "EventCode": "0xb3", - "EventName": "INT_UOPS_EXECUTED.STA", - "PublicDescription": "Counts the number of uops executed on a Store address port. This event counts integer uops even if the data source is FP/vector", - "SampleAfterValue": "1000003", - "UMask": "0x2", - "Unit": "cpu_atom" - }, - { - "BriefDescription": "Counts the number of uops executed on an integer store data and jump port.", - "Counter": "0,1,2,3,4,5,6,7", - "EventCode": "0xb3", - "EventName": "INT_UOPS_EXECUTED.STD_JMP", - "SampleAfterValue": "1000003", - "UMask": "0x4", - "Unit": "cpu_atom" - }, - { - "BriefDescription": "Counts the number of LLC prefetches that were throttled due to Dynamic Prefetch Throttling. The throttle requestor/source could be from the uncore/SOC or the Dead Block Predictor. Counts on a per core basis.", - "Counter": "0,1,2,3,4,5,6,7", - "EventCode": "0x29", - "EventName": "LLC_PREFETCHES_THROTTLED.DPT", - "SampleAfterValue": "1000003", - "UMask": "0x1", - "Unit": "cpu_atom" - }, - { - "BriefDescription": "Counts the number of LLC prefetches throttled due to Demand Throttle Prefetcher. DTP Global Triggered with no Local Override. Counts on a per core basis.", - "Counter": "0,1,2,3,4,5,6,7", - "EventCode": "0x29", - "EventName": "LLC_PREFETCHES_THROTTLED.DTP", - "SampleAfterValue": "1000003", - "UMask": "0x2", - "Unit": "cpu_atom" - }, - { - "BriefDescription": "Counts the number of LLC prefetches not throttled by DTP due to local override. These prefetches may still be throttled due to another throttler mechanism. Counts on a per core basis.", - "Counter": "0,1,2,3,4,5,6,7", - "EventCode": "0x29", - "EventName": "LLC_PREFETCHES_THROTTLED.DTP_OVERRIDE", - "SampleAfterValue": "1000003", - "UMask": "0x4", - "Unit": "cpu_atom" - }, - { - "BriefDescription": "Counts the number of LLC prefetches throttled due to LLC hit rate in <insert knob name here>. Counts on a per core basis.", - "Counter": "0,1,2,3,4,5,6,7", - "EventCode": "0x29", - "EventName": "LLC_PREFETCHES_THROTTLED.HIT_RATE", - "SampleAfterValue": "1000003", - "UMask": "0x10", - "Unit": "cpu_atom" - }, - { - "BriefDescription": "Counts the number of LLC prefetches throttled due to exceeding the XQ threshold set by either XQ_THRESOLD_DTP or LLC_XQ_THRESHOLD. Counts on a per core basis.", - "Counter": "0,1,2,3,4,5,6,7", - "EventCode": "0x29", - "EventName": "LLC_PREFETCHES_THROTTLED.XQ_THRESH", - "SampleAfterValue": "1000003", - "UMask": "0x8", - "Unit": "cpu_atom" - }, - { - "BriefDescription": "Counts cycles where no execution is happening due to loads waiting for L1 cache (that is: no execution & load in flight & no load missed L1 cache)", - "Counter": "0,1,2,3,4,5,6,7,8,9", - "EventCode": "0x46", - "EventName": "MEMORY_STALLS.L1", - "SampleAfterValue": "1000003", - "UMask": "0x1", - "Unit": "cpu_core" - }, - { - "BriefDescription": "Counts cycles where no execution is happening due to loads waiting for L2 cache (that is: no execution & load in flight & load missed L1 & no load missed L2 cache)", - "Counter": "0,1,2,3,4,5,6,7,8,9", - "EventCode": "0x46", - "EventName": "MEMORY_STALLS.L2", - "SampleAfterValue": "1000003", - "UMask": "0x2", - "Unit": "cpu_core" - }, - { - "BriefDescription": "Counts cycles where no execution is happening due to loads waiting for L3 cache (that is: no execution & load in flight & load missed L1 & load missed L2 cache & no load missed L3 Cache)", - "Counter": "0,1,2,3,4,5,6,7,8,9", - "EventCode": "0x46", - "EventName": "MEMORY_STALLS.L3", - "SampleAfterValue": "1000003", - "UMask": "0x4", - "Unit": "cpu_core" - }, - { - "BriefDescription": "Counts cycles where no execution is happening due to loads waiting for Memory (that is: no execution & load in flight & a load missed L3 cache)", - "Counter": "0,1,2,3,4,5,6,7,8,9", - "EventCode": "0x46", - "EventName": "MEMORY_STALLS.MEM", - "SampleAfterValue": "1000003", - "UMask": "0x8", - "Unit": "cpu_core" - }, - { "BriefDescription": "Counts all requests that have any type of response.", "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xB7", "EventName": "OCR.ALL_REQUESTS.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0xFF0000001DFFF", - "SampleAfterValue": "100003", - "UMask": "0x1", - "Unit": "cpu_atom" - }, - { - "BriefDescription": "Counts writebacks of modified cachelines that have any type of response.", - "Counter": "0,1,2,3,4,5,6,7", - "EventCode": "0xB7", - "EventName": "OCR.COREWB_M.ANY_RESPONSE", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x10008", - "SampleAfterValue": "100003", - "UMask": "0x1", - "Unit": "cpu_atom" - }, - { - "BriefDescription": "Counts writebacks of non-modified cachelines that have any type of response.", - "Counter": "0,1,2,3,4,5,6,7", - "EventCode": "0xB7", - "EventName": "OCR.COREWB_NONM.ANY_RESPONSE", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x11000", - "SampleAfterValue": "100003", - "UMask": "0x1", - "Unit": "cpu_atom" - }, - { - "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that have any type of response.", - "Counter": "0,1,2,3,4,5,6,7", - "EventCode": "0xB7", - "EventName": "OCR.DEMAND_CODE_RD.ANY_RESPONSE", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x10004", - "SampleAfterValue": "100003", - "UMask": "0x1", - "Unit": "cpu_atom" - }, - { - "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were supplied by DRAM.", - "Counter": "0,1,2,3,4,5,6,7", - "EventCode": "0xB7", - "EventName": "OCR.DEMAND_CODE_RD.DRAM", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x1FBC000004", - "SampleAfterValue": "100003", - "UMask": "0x1", - "Unit": "cpu_atom" - }, - { - "BriefDescription": "Counts demand data reads that have any type of response.", - "Counter": "0,1,2,3,4,5,6,7", - "EventCode": "0xB7", - "EventName": "OCR.DEMAND_DATA_RD.ANY_RESPONSE", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x10001", - "SampleAfterValue": "100003", - "UMask": "0x1", - "Unit": "cpu_atom" - }, - { - "BriefDescription": "Counts demand data reads that have any type of response.", - "Counter": "0,1,2,3", - "EventCode": "0x2A,0x2B", - "EventName": "OCR.DEMAND_DATA_RD.ANY_RESPONSE", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x10001", - "SampleAfterValue": "100003", - "UMask": "0x1", - "Unit": "cpu_core" - }, - { - "BriefDescription": "Counts demand data reads that were supplied by DRAM.", - "Counter": "0,1,2,3,4,5,6,7", - "EventCode": "0xB7", - "EventName": "OCR.DEMAND_DATA_RD.DRAM", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x1FBC000001", - "SampleAfterValue": "100003", - "UMask": "0x1", - "Unit": "cpu_atom" - }, - { - "BriefDescription": "Counts demand data reads that were supplied by DRAM.", - "Counter": "0,1,2,3", - "EventCode": "0x2A,0x2B", - "EventName": "OCR.DEMAND_DATA_RD.DRAM", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x1E780000001", - "SampleAfterValue": "100003", - "UMask": "0x1", - "Unit": "cpu_core" - }, - { - "BriefDescription": "Counts demand read for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that have any type of response.", - "Counter": "0,1,2,3,4,5,6,7", - "EventCode": "0xB7", - "EventName": "OCR.DEMAND_RFO.ANY_RESPONSE", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x10002", - "SampleAfterValue": "100003", - "UMask": "0x1", - "Unit": "cpu_atom" - }, - { - "BriefDescription": "Counts demand read for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that have any type of response.", - "Counter": "0,1,2,3", - "EventCode": "0x2A,0x2B", - "EventName": "OCR.DEMAND_RFO.ANY_RESPONSE", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x10002", - "SampleAfterValue": "100003", - "UMask": "0x1", - "Unit": "cpu_core" - }, - { - "BriefDescription": "Counts demand read for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that were supplied by DRAM.", - "Counter": "0,1,2,3,4,5,6,7", - "EventCode": "0xB7", - "EventName": "OCR.DEMAND_RFO.DRAM", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x1FBC000002", + "PublicDescription": "Counts all requests that have any type of response. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1", "Unit": "cpu_atom" @@ -422,6 +120,7 @@ "EventName": "OCR.FULL_STREAMING_WR.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x800000010000", + "PublicDescription": "Counts full streaming stores (64 bytes, WCiLF) that have any type of response. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1", "Unit": "cpu_atom" @@ -433,6 +132,7 @@ "EventName": "OCR.PARTIAL_STREAMING_WR.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x400000010000", + "PublicDescription": "Counts partial streaming stores (less than 64 bytes, WCiL) that have any type of response. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1", "Unit": "cpu_atom" @@ -444,6 +144,7 @@ "EventName": "OCR.STREAMING_WR.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x10800", + "PublicDescription": "Counts streaming stores that have any type of response. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1", "Unit": "cpu_atom" @@ -455,61 +156,12 @@ "EventName": "OCR.STREAMING_WR.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x10800", + "PublicDescription": "Counts streaming stores that have any type of response. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1", "Unit": "cpu_core" }, { - "BriefDescription": "Cycles when Reservation Station (RS) is empty for the thread.", - "Counter": "0,1,2,3,4,5,6,7,8,9", - "EventCode": "0xa5", - "EventName": "RS.EMPTY", - "PublicDescription": "Counts cycles during which the reservation station (RS) is empty for this logical processor. This is usually caused when the front-end pipeline runs into starvation periods (e.g. branch mispredictions or i-cache misses)", - "SampleAfterValue": "1000003", - "UMask": "0x7", - "Unit": "cpu_core" - }, - { - "BriefDescription": "Counts end of periods where the Reservation Station (RS) was empty.", - "Counter": "0,1,2,3,4,5,6,7,8,9", - "CounterMask": "1", - "EdgeDetect": "1", - "EventCode": "0xa5", - "EventName": "RS.EMPTY_COUNT", - "Invert": "1", - "PublicDescription": "Counts end of periods where the Reservation Station (RS) was empty. Could be useful to closely sample on front-end latency issues (see the FRONTEND_RETIRED event of designated precise events)", - "SampleAfterValue": "100003", - "UMask": "0x7", - "Unit": "cpu_core" - }, - { - "BriefDescription": "Cycles when RS was empty and a resource allocation stall is asserted", - "Counter": "0,1,2,3,4,5,6,7,8,9", - "EventCode": "0xa5", - "EventName": "RS.EMPTY_RESOURCE", - "SampleAfterValue": "1000003", - "UMask": "0x1", - "Unit": "cpu_core" - }, - { - "BriefDescription": "Counts the number of issue slots in a UMWAIT or TPAUSE instruction where no uop issues due to the instruction putting the CPU into the C0.1 activity state.", - "Counter": "0,1,2,3,4,5,6,7", - "EventCode": "0x75", - "EventName": "SERIALIZATION.C01_MS_SCB", - "SampleAfterValue": "1000003", - "UMask": "0x4", - "Unit": "cpu_atom" - }, - { - "BriefDescription": "Counts the number issue slots not consumed due to a color request for an FCW or MXCSR control register when all 4 colors (copies) are already in use", - "Counter": "0,1,2,3,4,5,6,7", - "EventCode": "0x75", - "EventName": "SERIALIZATION.COLOR_STALLS", - "SampleAfterValue": "1000003", - "UMask": "0x8", - "Unit": "cpu_atom" - }, - { "BriefDescription": "Cycles the uncore cannot take further requests", "Counter": "0,1,2,3,4,5,6,7,8,9", "CounterMask": "1", diff --git a/tools/perf/pmu-events/arch/x86/lunarlake/pipeline.json b/tools/perf/pmu-events/arch/x86/lunarlake/pipeline.json index f4ec7a884937..4875047fb65c 100644 --- a/tools/perf/pmu-events/arch/x86/lunarlake/pipeline.json +++ b/tools/perf/pmu-events/arch/x86/lunarlake/pipeline.json @@ -88,6 +88,15 @@ "Unit": "cpu_core" }, { + "BriefDescription": "Counts cycles where the pipeline is stalled due to serializing operations.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xa2", + "EventName": "BE_STALLS.SCOREBOARD", + "SampleAfterValue": "100003", + "UMask": "0x2", + "Unit": "cpu_core" + }, + { "BriefDescription": "Counts the total number of branch instructions retired for all branch types.", "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc4", @@ -101,7 +110,7 @@ "Counter": "0,1,2,3,4,5,6,7,8,9", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.ALL_BRANCHES", - "PublicDescription": "Counts all branch instructions retired.", + "PublicDescription": "Counts all branch instructions retired. Available PDIST counters: 0", "SampleAfterValue": "400009", "Unit": "cpu_core" }, @@ -119,7 +128,7 @@ "Counter": "0,1,2,3,4,5,6,7,8,9", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.COND", - "PublicDescription": "Counts conditional branch instructions retired.", + "PublicDescription": "Counts conditional branch instructions retired. Available PDIST counters: 0", "SampleAfterValue": "400009", "UMask": "0x111", "Unit": "cpu_core" @@ -138,7 +147,7 @@ "Counter": "0,1,2,3,4,5,6,7,8,9", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.COND_NTAKEN", - "PublicDescription": "Counts not taken branch instructions retired.", + "PublicDescription": "Counts not taken branch instructions retired. Available PDIST counters: 0", "SampleAfterValue": "400009", "UMask": "0x10", "Unit": "cpu_core" @@ -157,7 +166,7 @@ "Counter": "0,1,2,3,4,5,6,7,8,9", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.COND_TAKEN", - "PublicDescription": "Counts taken conditional branch instructions retired.", + "PublicDescription": "Counts taken conditional branch instructions retired. Available PDIST counters: 0", "SampleAfterValue": "400009", "UMask": "0x101", "Unit": "cpu_core" @@ -167,7 +176,7 @@ "Counter": "0,1,2,3,4,5,6,7,8,9", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.COND_TAKEN_BWD", - "PublicDescription": "Counts taken backward conditional branch instructions retired.", + "PublicDescription": "Counts taken backward conditional branch instructions retired. Available PDIST counters: 0", "SampleAfterValue": "400009", "UMask": "0x1", "Unit": "cpu_core" @@ -177,7 +186,7 @@ "Counter": "0,1,2,3,4,5,6,7,8,9", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.COND_TAKEN_FWD", - "PublicDescription": "Counts taken forward conditional branch instructions retired.", + "PublicDescription": "Counts taken forward conditional branch instructions retired. Available PDIST counters: 0", "SampleAfterValue": "400009", "UMask": "0x102", "Unit": "cpu_core" @@ -196,7 +205,7 @@ "Counter": "0,1,2,3,4,5,6,7,8,9", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.FAR_BRANCH", - "PublicDescription": "Counts far branch instructions retired.", + "PublicDescription": "Counts far branch instructions retired. Available PDIST counters: 0", "SampleAfterValue": "100007", "UMask": "0x40", "Unit": "cpu_core" @@ -215,7 +224,7 @@ "Counter": "0,1,2,3,4,5,6,7,8,9", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.INDIRECT", - "PublicDescription": "Counts near indirect branch instructions retired excluding returns. TSX abort is an indirect branch.", + "PublicDescription": "Counts near indirect branch instructions retired excluding returns. TSX abort is an indirect branch. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x80", "Unit": "cpu_core" @@ -252,7 +261,7 @@ "Counter": "0,1,2,3,4,5,6,7,8,9", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.NEAR_CALL", - "PublicDescription": "Counts both direct and indirect near call instructions retired.", + "PublicDescription": "Counts both direct and indirect near call instructions retired. Available PDIST counters: 0", "SampleAfterValue": "100007", "UMask": "0x2", "Unit": "cpu_core" @@ -271,7 +280,7 @@ "Counter": "0,1,2,3,4,5,6,7,8,9", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.NEAR_RETURN", - "PublicDescription": "Counts return instructions retired.", + "PublicDescription": "Counts return instructions retired. Available PDIST counters: 0", "SampleAfterValue": "100007", "UMask": "0x8", "Unit": "cpu_core" @@ -290,7 +299,7 @@ "Counter": "0,1,2,3,4,5,6,7,8,9", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.NEAR_TAKEN", - "PublicDescription": "Counts taken branch instructions retired.", + "PublicDescription": "Counts taken branch instructions retired. Available PDIST counters: 0", "SampleAfterValue": "400009", "UMask": "0x20", "Unit": "cpu_core" @@ -318,7 +327,7 @@ "Counter": "0,1,2,3,4,5,6,7,8,9", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.ALL_BRANCHES", - "PublicDescription": "Counts all the retired branch instructions that were mispredicted by the processor. A branch misprediction occurs when the processor incorrectly predicts the destination of the branch. When the misprediction is discovered at execution, all the instructions executed in the wrong (speculative) path must be discarded, and the processor must start fetching from the correct path.", + "PublicDescription": "Counts all the retired branch instructions that were mispredicted by the processor. A branch misprediction occurs when the processor incorrectly predicts the destination of the branch. When the misprediction is discovered at execution, all the instructions executed in the wrong (speculative) path must be discarded, and the processor must start fetching from the correct path. Available PDIST counters: 0", "SampleAfterValue": "400009", "Unit": "cpu_core" }, @@ -327,6 +336,7 @@ "Counter": "0,1,2,3,4,5,6,7,8,9", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.ALL_BRANCHES_COST", + "PublicDescription": "All mispredicted branch instructions retired. This precise event may be used to get the misprediction cost via the Retire_Latency field of PEBS. It fires on the instruction that immediately follows the mispredicted branch. Available PDIST counters: 0", "SampleAfterValue": "400009", "UMask": "0x44", "Unit": "cpu_core" @@ -345,7 +355,7 @@ "Counter": "0,1,2,3,4,5,6,7,8,9", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.COND", - "PublicDescription": "Counts mispredicted conditional branch instructions retired.", + "PublicDescription": "Counts mispredicted conditional branch instructions retired. Available PDIST counters: 0", "SampleAfterValue": "400009", "UMask": "0x111", "Unit": "cpu_core" @@ -355,6 +365,7 @@ "Counter": "0,1,2,3,4,5,6,7,8,9", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.COND_COST", + "PublicDescription": "Mispredicted conditional branch instructions retired. This precise event may be used to get the misprediction cost via the Retire_Latency field of PEBS. It fires on the instruction that immediately follows the mispredicted branch. Available PDIST counters: 0", "SampleAfterValue": "400009", "UMask": "0x151", "Unit": "cpu_core" @@ -373,7 +384,7 @@ "Counter": "0,1,2,3,4,5,6,7,8,9", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.COND_NTAKEN", - "PublicDescription": "Counts the number of conditional branch instructions retired that were mispredicted and the branch direction was not taken.", + "PublicDescription": "Counts the number of conditional branch instructions retired that were mispredicted and the branch direction was not taken. Available PDIST counters: 0", "SampleAfterValue": "400009", "UMask": "0x10", "Unit": "cpu_core" @@ -383,6 +394,7 @@ "Counter": "0,1,2,3,4,5,6,7,8,9", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.COND_NTAKEN_COST", + "PublicDescription": "Mispredicted non-taken conditional branch instructions retired. This precise event may be used to get the misprediction cost via the Retire_Latency field of PEBS. It fires on the instruction that immediately follows the mispredicted branch. Available PDIST counters: 0", "SampleAfterValue": "400009", "UMask": "0x50", "Unit": "cpu_core" @@ -401,7 +413,7 @@ "Counter": "0,1,2,3,4,5,6,7,8,9", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.COND_TAKEN", - "PublicDescription": "Counts taken conditional mispredicted branch instructions retired.", + "PublicDescription": "Counts taken conditional mispredicted branch instructions retired. Available PDIST counters: 0", "SampleAfterValue": "400009", "UMask": "0x101", "Unit": "cpu_core" @@ -411,7 +423,7 @@ "Counter": "0,1,2,3,4,5,6,7,8,9", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.COND_TAKEN_BWD", - "PublicDescription": "Counts taken backward conditional mispredicted branch instructions retired.", + "PublicDescription": "Counts taken backward conditional mispredicted branch instructions retired. Available PDIST counters: 0", "SampleAfterValue": "400009", "UMask": "0x1", "Unit": "cpu_core" @@ -421,6 +433,7 @@ "Counter": "0,1,2,3,4,5,6,7,8,9", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.COND_TAKEN_BWD_COST", + "PublicDescription": "number of branch instructions retired that were mispredicted and taken backward. This precise event may be used to get the misprediction cost via the Retire_Latency field of PEBS. It fires on the instruction that immediately follows the mispredicted branch. Available PDIST counters: 0", "SampleAfterValue": "400009", "UMask": "0x8001", "Unit": "cpu_core" @@ -430,6 +443,7 @@ "Counter": "0,1,2,3,4,5,6,7,8,9", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.COND_TAKEN_COST", + "PublicDescription": "Mispredicted taken conditional branch instructions retired. This precise event may be used to get the misprediction cost via the Retire_Latency field of PEBS. It fires on the instruction that immediately follows the mispredicted branch. Available PDIST counters: 0", "SampleAfterValue": "400009", "UMask": "0x141", "Unit": "cpu_core" @@ -439,7 +453,7 @@ "Counter": "0,1,2,3,4,5,6,7,8,9", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.COND_TAKEN_FWD", - "PublicDescription": "Counts taken forward conditional mispredicted branch instructions retired.", + "PublicDescription": "Counts taken forward conditional mispredicted branch instructions retired. Available PDIST counters: 0", "SampleAfterValue": "400009", "Unit": "cpu_core" }, @@ -448,6 +462,7 @@ "Counter": "0,1,2,3,4,5,6,7,8,9", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.COND_TAKEN_FWD_COST", + "PublicDescription": "number of branch instructions retired that were mispredicted and taken forward. This precise event may be used to get the misprediction cost via the Retire_Latency field of PEBS. It fires on the instruction that immediately follows the mispredicted branch. Available PDIST counters: 0", "SampleAfterValue": "400009", "UMask": "0x8002", "Unit": "cpu_core" @@ -466,7 +481,7 @@ "Counter": "0,1,2,3,4,5,6,7,8,9", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.INDIRECT", - "PublicDescription": "Counts miss-predicted near indirect branch instructions retired excluding returns. TSX abort is an indirect branch.", + "PublicDescription": "Counts miss-predicted near indirect branch instructions retired excluding returns. TSX abort is an indirect branch. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x80", "Unit": "cpu_core" @@ -485,7 +500,7 @@ "Counter": "0,1,2,3,4,5,6,7,8,9", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.INDIRECT_CALL", - "PublicDescription": "Counts retired mispredicted indirect (near taken) CALL instructions, including both register and memory indirect.", + "PublicDescription": "Counts retired mispredicted indirect (near taken) CALL instructions, including both register and memory indirect. Available PDIST counters: 0", "SampleAfterValue": "400009", "UMask": "0x2", "Unit": "cpu_core" @@ -495,6 +510,7 @@ "Counter": "0,1,2,3,4,5,6,7,8,9", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.INDIRECT_CALL_COST", + "PublicDescription": "Mispredicted indirect CALL retired. This precise event may be used to get the misprediction cost via the Retire_Latency field of PEBS. It fires on the instruction that immediately follows the mispredicted branch. Available PDIST counters: 0", "SampleAfterValue": "400009", "UMask": "0x42", "Unit": "cpu_core" @@ -504,6 +520,7 @@ "Counter": "0,1,2,3,4,5,6,7,8,9", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.INDIRECT_COST", + "PublicDescription": "Mispredicted near indirect branch instructions retired (excluding returns). This precise event may be used to get the misprediction cost via the Retire_Latency field of PEBS. It fires on the instruction that immediately follows the mispredicted branch. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0xc0", "Unit": "cpu_core" @@ -531,7 +548,7 @@ "Counter": "0,1,2,3,4,5,6,7,8,9", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.NEAR_TAKEN", - "PublicDescription": "Counts number of near branch instructions retired that were mispredicted and taken.", + "PublicDescription": "Counts number of near branch instructions retired that were mispredicted and taken. Available PDIST counters: 0", "SampleAfterValue": "400009", "UMask": "0x20", "Unit": "cpu_core" @@ -541,6 +558,7 @@ "Counter": "0,1,2,3,4,5,6,7,8,9", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.NEAR_TAKEN_COST", + "PublicDescription": "Mispredicted taken near branch instructions retired. This precise event may be used to get the misprediction cost via the Retire_Latency field of PEBS. It fires on the instruction that immediately follows the mispredicted branch. Available PDIST counters: 0", "SampleAfterValue": "400009", "UMask": "0x60", "Unit": "cpu_core" @@ -550,7 +568,7 @@ "Counter": "0,1,2,3,4,5,6,7,8,9", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.RET", - "PublicDescription": "This is a non-precise version (that is, does not use PEBS) of the event that counts mispredicted return instructions retired.", + "PublicDescription": "This is a non-precise version (that is, does not use PEBS) of the event that counts mispredicted return instructions retired. Available PDIST counters: 0", "SampleAfterValue": "100007", "UMask": "0x8", "Unit": "cpu_core" @@ -569,6 +587,7 @@ "Counter": "0,1,2,3,4,5,6,7,8,9", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.RET_COST", + "PublicDescription": "Mispredicted ret instructions retired. This precise event may be used to get the misprediction cost via the Retire_Latency field of PEBS. It fires on the instruction that immediately follows the mispredicted branch. Available PDIST counters: 0", "SampleAfterValue": "100007", "UMask": "0x48", "Unit": "cpu_core" @@ -758,6 +777,15 @@ "Unit": "cpu_core" }, { + "BriefDescription": "Count number of times a load is depending on another load that had just write back its data or in previous or 2 cycles back. This event supports in-direct dependency through a single uop.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0x02", + "EventName": "DEPENDENT_LOADS.ANY", + "SampleAfterValue": "1000003", + "UMask": "0x7", + "Unit": "cpu_core" + }, + { "BriefDescription": "Cycles total of 1 uop is executed on all ports and Reservation Station was not empty.", "Counter": "0,1,2,3,4,5,6,7,8,9", "EventCode": "0xa6", @@ -851,6 +879,7 @@ "BriefDescription": "Fixed Counter: Counts the number of instructions retired.", "Counter": "Fixed counter 0", "EventName": "INST_RETIRED.ANY", + "PublicDescription": "Fixed Counter: Counts the number of instructions retired. Available PDIST counters: 32", "SampleAfterValue": "2000003", "UMask": "0x1", "Unit": "cpu_atom" @@ -859,7 +888,7 @@ "BriefDescription": "Number of instructions retired. Fixed Counter - architectural event", "Counter": "Fixed counter 0", "EventName": "INST_RETIRED.ANY", - "PublicDescription": "Counts the number of X86 instructions retired - an Architectural PerfMon event. Counting continues during hardware interrupts, traps, and inside interrupt handlers. Notes: INST_RETIRED.ANY is counted by a designated fixed counter freeing up programmable counters to count other events. INST_RETIRED.ANY_P is counted by a programmable counter.", + "PublicDescription": "Counts the number of X86 instructions retired - an Architectural PerfMon event. Counting continues during hardware interrupts, traps, and inside interrupt handlers. Notes: INST_RETIRED.ANY is counted by a designated fixed counter freeing up programmable counters to count other events. INST_RETIRED.ANY_P is counted by a programmable counter. Available PDIST counters: 32", "SampleAfterValue": "2000003", "UMask": "0x1", "Unit": "cpu_core" @@ -877,7 +906,7 @@ "Counter": "0,1,2,3,4,5,6,7,8,9", "EventCode": "0xc0", "EventName": "INST_RETIRED.ANY_P", - "PublicDescription": "Counts the number of X86 instructions retired - an Architectural PerfMon event. Counting continues during hardware interrupts, traps, and inside interrupt handlers. Notes: INST_RETIRED.ANY is counted by a designated fixed counter freeing up programmable counters to count other events. INST_RETIRED.ANY_P is counted by a programmable counter.", + "PublicDescription": "Counts the number of X86 instructions retired - an Architectural PerfMon event. Counting continues during hardware interrupts, traps, and inside interrupt handlers. Notes: INST_RETIRED.ANY is counted by a designated fixed counter freeing up programmable counters to count other events. INST_RETIRED.ANY_P is counted by a programmable counter. Available PDIST counters: 0", "SampleAfterValue": "2000003", "Unit": "cpu_core" }, @@ -886,6 +915,7 @@ "Counter": "0,1,2,3,4,5,6,7,8,9", "EventCode": "0xc0", "EventName": "INST_RETIRED.BR_FUSED", + "PublicDescription": "retired macro-fused uops when there is a branch in the macro-fused pair (the two instructions that got macro-fused count once in this pmon) Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x10", "Unit": "cpu_core" @@ -895,6 +925,7 @@ "Counter": "0,1,2,3,4,5,6,7,8,9", "EventCode": "0xc0", "EventName": "INST_RETIRED.MACRO_FUSED", + "PublicDescription": "INST_RETIRED.MACRO_FUSED Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x30", "Unit": "cpu_core" @@ -904,7 +935,7 @@ "Counter": "0,1,2,3,4,5,6,7,8,9", "EventCode": "0xc0", "EventName": "INST_RETIRED.NOP", - "PublicDescription": "Counts all retired NOP or ENDBR32/64 or PREFETCHIT0/1 instructions", + "PublicDescription": "Counts all retired NOP or ENDBR32/64 or PREFETCHIT0/1 instructions Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x2", "Unit": "cpu_core" @@ -913,7 +944,7 @@ "BriefDescription": "Precise instruction retired with PEBS precise-distribution", "Counter": "Fixed counter 0", "EventName": "INST_RETIRED.PREC_DIST", - "PublicDescription": "A version of INST_RETIRED that allows for a precise distribution of samples across instructions retired. It utilizes the Precise Distribution of Instructions Retired (PDIR++) feature to fix bias in how retired instructions get sampled. Use on Fixed Counter 0.", + "PublicDescription": "A version of INST_RETIRED that allows for a precise distribution of samples across instructions retired. It utilizes the Precise Distribution of Instructions Retired (PDIR++) feature to fix bias in how retired instructions get sampled. Use on Fixed Counter 0. Available PDIST counters: 32", "SampleAfterValue": "2000003", "UMask": "0x1", "Unit": "cpu_core" @@ -923,7 +954,7 @@ "Counter": "0,1,2,3,4,5,6,7,8,9", "EventCode": "0xc0", "EventName": "INST_RETIRED.REP_ITERATION", - "PublicDescription": "Number of iterations of Repeat (REP) string retired instructions such as MOVS, CMPS, and SCAS. Each has a byte, word, and doubleword version and string instructions can be repeated using a repetition prefix, REP, that allows their architectural execution to be repeated a number of times as specified by the RCX register. Note the number of iterations is implementation-dependent.", + "PublicDescription": "Number of iterations of Repeat (REP) string retired instructions such as MOVS, CMPS, and SCAS. Each has a byte, word, and doubleword version and string instructions can be repeated using a repetition prefix, REP, that allows their architectural execution to be repeated a number of times as specified by the RCX register. Note the number of iterations is implementation-dependent. Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x8", "Unit": "cpu_core" @@ -993,6 +1024,89 @@ "Unit": "cpu_core" }, { + "BriefDescription": "Counts the number of uops executed on all Integer ports.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xb3", + "EventName": "INT_UOPS_EXECUTED.ALL", + "SampleAfterValue": "1000003", + "UMask": "0xff", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of uops executed on a load port.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xb3", + "EventName": "INT_UOPS_EXECUTED.LD", + "PublicDescription": "Counts the number of uops executed on a load port. This event counts for integer uops even if the destination is FP/vector", + "SampleAfterValue": "1000003", + "UMask": "0x1", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of uops executed on integer port 0.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xb3", + "EventName": "INT_UOPS_EXECUTED.P0", + "SampleAfterValue": "1000003", + "UMask": "0x8", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of uops executed on integer port 1.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xb3", + "EventName": "INT_UOPS_EXECUTED.P1", + "SampleAfterValue": "1000003", + "UMask": "0x10", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of uops executed on integer port 2.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xb3", + "EventName": "INT_UOPS_EXECUTED.P2", + "SampleAfterValue": "1000003", + "UMask": "0x20", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of uops executed on integer port 3.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xb3", + "EventName": "INT_UOPS_EXECUTED.P3", + "SampleAfterValue": "1000003", + "UMask": "0x40", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of uops executed on integer port 0,1, 2, 3.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xb3", + "EventName": "INT_UOPS_EXECUTED.PRIMARY", + "SampleAfterValue": "1000003", + "UMask": "0x78", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of uops executed on a Store address port.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xb3", + "EventName": "INT_UOPS_EXECUTED.STA", + "PublicDescription": "Counts the number of uops executed on a Store address port. This event counts integer uops even if the data source is FP/vector", + "SampleAfterValue": "1000003", + "UMask": "0x2", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of uops executed on an integer store data and jump port.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xb3", + "EventName": "INT_UOPS_EXECUTED.STD_JMP", + "SampleAfterValue": "1000003", + "UMask": "0x4", + "Unit": "cpu_atom" + }, + { "BriefDescription": "Number of vector integer instructions retired of 128-bit vector-width.", "Counter": "0,1,2,3,4,5,6,7,8,9", "EventCode": "0xe7", @@ -1268,6 +1382,42 @@ "Unit": "cpu_core" }, { + "BriefDescription": "Counts cycles where no execution is happening due to loads waiting for L1 cache (that is: no execution & load in flight & no load missed L1 cache)", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0x46", + "EventName": "MEMORY_STALLS.L1", + "SampleAfterValue": "1000003", + "UMask": "0x1", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts cycles where no execution is happening due to loads waiting for L2 cache (that is: no execution & load in flight & load missed L1 & no load missed L2 cache)", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0x46", + "EventName": "MEMORY_STALLS.L2", + "SampleAfterValue": "1000003", + "UMask": "0x2", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts cycles where no execution is happening due to loads waiting for L3 cache (that is: no execution & load in flight & load missed L1 & load missed L2 cache & no load missed L3 Cache)", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0x46", + "EventName": "MEMORY_STALLS.L3", + "SampleAfterValue": "1000003", + "UMask": "0x4", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts cycles where no execution is happening due to loads waiting for Memory (that is: no execution & load in flight & a load missed L3 cache)", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0x46", + "EventName": "MEMORY_STALLS.MEM", + "SampleAfterValue": "1000003", + "UMask": "0x8", + "Unit": "cpu_core" + }, + { "BriefDescription": "LFENCE instructions retired", "Counter": "0,1,2,3,4,5,6,7,8,9", "EventCode": "0xe0", @@ -1291,6 +1441,7 @@ "Counter": "0,1,2,3,4,5,6,7,8,9", "EventCode": "0xe4", "EventName": "MISC_RETIRED.LBR_INSERTS", + "PublicDescription": "LBR record is inserted Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x1", "Unit": "cpu_core" @@ -1394,6 +1545,56 @@ "Unit": "cpu_atom" }, { + "BriefDescription": "Cycles when Reservation Station (RS) is empty for the thread.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xa5", + "EventName": "RS.EMPTY", + "PublicDescription": "Counts cycles during which the reservation station (RS) is empty for this logical processor. This is usually caused when the front-end pipeline runs into starvation periods (e.g. branch mispredictions or i-cache misses)", + "SampleAfterValue": "1000003", + "UMask": "0x7", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts end of periods where the Reservation Station (RS) was empty.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "CounterMask": "1", + "EdgeDetect": "1", + "EventCode": "0xa5", + "EventName": "RS.EMPTY_COUNT", + "Invert": "1", + "PublicDescription": "Counts end of periods where the Reservation Station (RS) was empty. Could be useful to closely sample on front-end latency issues (see the FRONTEND_RETIRED event of designated precise events)", + "SampleAfterValue": "100003", + "UMask": "0x7", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Cycles when RS was empty and a resource allocation stall is asserted", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xa5", + "EventName": "RS.EMPTY_RESOURCE", + "SampleAfterValue": "1000003", + "UMask": "0x1", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts the number of issue slots in a UMWAIT or TPAUSE instruction where no uop issues due to the instruction putting the CPU into the C0.1 activity state.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x75", + "EventName": "SERIALIZATION.C01_MS_SCB", + "SampleAfterValue": "1000003", + "UMask": "0x4", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number issue slots not consumed due to a color request for an FCW or MXCSR control register when all 4 colors (copies) are already in use", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x75", + "EventName": "SERIALIZATION.COLOR_STALLS", + "SampleAfterValue": "1000003", + "UMask": "0x8", + "Unit": "cpu_atom" + }, + { "BriefDescription": "Counts the number of issue slots not consumed by the backend due to a micro-sequencer (MS) scoreboard, which stalls the front-end from issuing from the UROM until a specified older uop retires.", "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0x75", diff --git a/tools/perf/pmu-events/arch/x86/mapfile.csv b/tools/perf/pmu-events/arch/x86/mapfile.csv index 56d5fc419acf..bde2f32423a1 100644 --- a/tools/perf/pmu-events/arch/x86/mapfile.csv +++ b/tools/perf/pmu-events/arch/x86/mapfile.csv @@ -1,7 +1,7 @@ Family-model,Version,Filename,EventType -GenuineIntel-6-(97|9A|B7|BA|BF),v1.28,alderlake,core -GenuineIntel-6-BE,v1.28,alderlaken,core -GenuineIntel-6-C[56],v1.07,arrowlake,core +GenuineIntel-6-(97|9A|B7|BA|BF),v1.29,alderlake,core +GenuineIntel-6-BE,v1.29,alderlaken,core +GenuineIntel-6-C[56],v1.08,arrowlake,core GenuineIntel-6-(1C|26|27|35|36),v5,bonnell,core GenuineIntel-6-(3D|47),v30,broadwell,core GenuineIntel-6-56,v12,broadwellde,core @@ -12,8 +12,8 @@ GenuineIntel-6-9[6C],v1.05,elkhartlake,core GenuineIntel-6-CF,v1.11,emeraldrapids,core GenuineIntel-6-5[CF],v13,goldmont,core GenuineIntel-6-7A,v1.01,goldmontplus,core -GenuineIntel-6-B6,v1.05,grandridge,core -GenuineIntel-6-A[DE],v1.06,graniterapids,core +GenuineIntel-6-B6,v1.07,grandridge,core +GenuineIntel-6-A[DE],v1.08,graniterapids,core GenuineIntel-6-(3C|45|46),v36,haswell,core GenuineIntel-6-3F,v29,haswellx,core GenuineIntel-6-7[DE],v1.24,icelake,core @@ -23,13 +23,13 @@ GenuineIntel-6-3E,v24,ivytown,core GenuineIntel-6-2D,v24,jaketown,core GenuineIntel-6-(57|85),v16,knightslanding,core GenuineIntel-6-BD,v1.11,lunarlake,core -GenuineIntel-6-(AA|AC|B5),v1.12,meteorlake,core +GenuineIntel-6-(AA|AC|B5),v1.13,meteorlake,core GenuineIntel-6-1[AEF],v4,nehalemep,core GenuineIntel-6-2E,v4,nehalemex,core GenuineIntel-6-A7,v1.04,rocketlake,core GenuineIntel-6-2A,v19,sandybridge,core GenuineIntel-6-8F,v1.25,sapphirerapids,core -GenuineIntel-6-AF,v1.08,sierraforest,core +GenuineIntel-6-AF,v1.09,sierraforest,core GenuineIntel-6-(37|4A|4C|4D|5A),v15,silvermont,core GenuineIntel-6-(4E|5E|8E|9E|A5|A6),v59,skylake,core GenuineIntel-6-55-[01234],v1.36,skylakex,core diff --git a/tools/perf/pmu-events/arch/x86/meteorlake/cache.json b/tools/perf/pmu-events/arch/x86/meteorlake/cache.json index ce351cd7caaf..c980bbee6146 100644 --- a/tools/perf/pmu-events/arch/x86/meteorlake/cache.json +++ b/tools/perf/pmu-events/arch/x86/meteorlake/cache.json @@ -1,9 +1,20 @@ [ { + "BriefDescription": "Counts the number of L1D cacheline (dirty) evictions caused by load misses, stores, and prefetches.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x51", + "EventName": "DL1.DIRTY_EVICTION", + "PublicDescription": "Counts the number of L1D cacheline (dirty) evictions caused by load misses, stores, and prefetches. Does not count evictions or dirty writebacks caused by snoops. Does not count a replacement unless a (dirty) line was written back.", + "SampleAfterValue": "200003", + "UMask": "0x1", + "Unit": "cpu_atom" + }, + { "BriefDescription": "L1D.HWPF_MISS", "Counter": "0,1,2,3", "EventCode": "0x51", "EventName": "L1D.HWPF_MISS", + "PublicDescription": "L1D.HWPF_MISS Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x20", "Unit": "cpu_core" @@ -13,7 +24,7 @@ "Counter": "0,1,2,3", "EventCode": "0x51", "EventName": "L1D.REPLACEMENT", - "PublicDescription": "Counts L1D data line replacements including opportunistic replacements, and replacements that require stall-for-replace or block-for-replace.", + "PublicDescription": "Counts L1D data line replacements including opportunistic replacements, and replacements that require stall-for-replace or block-for-replace. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1", "Unit": "cpu_core" @@ -23,7 +34,7 @@ "Counter": "0,1,2,3", "EventCode": "0x48", "EventName": "L1D_PEND_MISS.FB_FULL", - "PublicDescription": "Counts number of cycles a demand request has waited due to L1D Fill Buffer (FB) unavailability. Demand requests include cacheable/uncacheable demand load, store, lock or SW prefetch accesses.", + "PublicDescription": "Counts number of cycles a demand request has waited due to L1D Fill Buffer (FB) unavailability. Demand requests include cacheable/uncacheable demand load, store, lock or SW prefetch accesses. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x2", "Unit": "cpu_core" @@ -35,7 +46,7 @@ "EdgeDetect": "1", "EventCode": "0x48", "EventName": "L1D_PEND_MISS.FB_FULL_PERIODS", - "PublicDescription": "Counts number of phases a demand request has waited due to L1D Fill Buffer (FB) unavailability. Demand requests include cacheable/uncacheable demand load, store, lock or SW prefetch accesses.", + "PublicDescription": "Counts number of phases a demand request has waited due to L1D Fill Buffer (FB) unavailability. Demand requests include cacheable/uncacheable demand load, store, lock or SW prefetch accesses. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x2", "Unit": "cpu_core" @@ -45,7 +56,7 @@ "Counter": "0,1,2,3", "EventCode": "0x48", "EventName": "L1D_PEND_MISS.L2_STALLS", - "PublicDescription": "Counts number of cycles a demand request has waited due to L1D due to lack of L2 resources. Demand requests include cacheable/uncacheable demand load, store, lock or SW prefetch accesses.", + "PublicDescription": "Counts number of cycles a demand request has waited due to L1D due to lack of L2 resources. Demand requests include cacheable/uncacheable demand load, store, lock or SW prefetch accesses. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x4", "Unit": "cpu_core" @@ -55,7 +66,7 @@ "Counter": "0,1,2,3", "EventCode": "0x48", "EventName": "L1D_PEND_MISS.PENDING", - "PublicDescription": "Counts number of L1D misses that are outstanding in each cycle, that is each cycle the number of Fill Buffers (FB) outstanding required by Demand Reads. FB either is held by demand loads, or it is held by non-demand loads and gets hit at least once by demand. The valid outstanding interval is defined until the FB deallocation by one of the following ways: from FB allocation, if FB is allocated by demand from the demand Hit FB, if it is allocated by hardware or software prefetch. Note: In the L1D, a Demand Read contains cacheable or noncacheable demand loads, including ones causing cache-line splits and reads due to page walks resulted from any request type.", + "PublicDescription": "Counts number of L1D misses that are outstanding in each cycle, that is each cycle the number of Fill Buffers (FB) outstanding required by Demand Reads. FB either is held by demand loads, or it is held by non-demand loads and gets hit at least once by demand. The valid outstanding interval is defined until the FB deallocation by one of the following ways: from FB allocation, if FB is allocated by demand from the demand Hit FB, if it is allocated by hardware or software prefetch. Note: In the L1D, a Demand Read contains cacheable or noncacheable demand loads, including ones causing cache-line splits and reads due to page walks resulted from any request type. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x1", "Unit": "cpu_core" @@ -66,7 +77,7 @@ "CounterMask": "1", "EventCode": "0x48", "EventName": "L1D_PEND_MISS.PENDING_CYCLES", - "PublicDescription": "Counts duration of L1D miss outstanding in cycles.", + "PublicDescription": "Counts duration of L1D miss outstanding in cycles. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x1", "Unit": "cpu_core" @@ -76,27 +87,87 @@ "Counter": "0,1,2,3", "EventCode": "0x25", "EventName": "L2_LINES_IN.ALL", - "PublicDescription": "Counts the number of L2 cache lines filling the L2. Counting does not cover rejects.", + "PublicDescription": "Counts the number of L2 cache lines filling the L2. Counting does not cover rejects. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1f", "Unit": "cpu_core" }, { + "BriefDescription": "Counts the number of cache lines filled into the L2 cache that are in Exclusive state", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x25", + "EventName": "L2_LINES_IN.E", + "PublicDescription": "Counts the number of cache lines filled into the L2 cache that are in Exclusive state. Counts on a per core basis.", + "SampleAfterValue": "1000003", + "UMask": "0x4", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of cache lines filled into the L2 cache that are in Forward state", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x25", + "EventName": "L2_LINES_IN.F", + "PublicDescription": "Counts the number of cache lines filled into the L2 cache that are in Forward state. Counts on a per core basis.", + "SampleAfterValue": "1000003", + "UMask": "0x10", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of cache lines filled into the L2 cache that are in Modified state", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x25", + "EventName": "L2_LINES_IN.M", + "PublicDescription": "Counts the number of cache lines filled into the L2 cache that are in Modified state. Counts on a per core basis.", + "SampleAfterValue": "1000003", + "UMask": "0x8", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of cache lines filled into the L2 cache that are in Shared state", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x25", + "EventName": "L2_LINES_IN.S", + "PublicDescription": "Counts the number of cache lines filled into the L2 cache that are in Shared state. Counts on a per core basis.", + "SampleAfterValue": "1000003", + "UMask": "0x2", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of L2 cache lines that are evicted due to an L2 cache fill", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x26", + "EventName": "L2_LINES_OUT.NON_SILENT", + "PublicDescription": "Counts the number of L2 cache lines that are evicted due to an L2 cache fill. Increments on the core that brought the line in originally.", + "SampleAfterValue": "1000003", + "UMask": "0x2", + "Unit": "cpu_atom" + }, + { "BriefDescription": "Modified cache lines that are evicted by L2 cache when triggered by an L2 cache fill.", "Counter": "0,1,2,3", "EventCode": "0x26", "EventName": "L2_LINES_OUT.NON_SILENT", - "PublicDescription": "Counts the number of lines that are evicted by L2 cache when triggered by an L2 cache fill. Those lines are in Modified state. Modified lines are written back to L3", + "PublicDescription": "Counts the number of lines that are evicted by L2 cache when triggered by an L2 cache fill. Those lines are in Modified state. Modified lines are written back to L3 Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0x2", "Unit": "cpu_core" }, { + "BriefDescription": "Counts the number of L2 cache lines that are silently dropped due to an L2 cache fill", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x26", + "EventName": "L2_LINES_OUT.SILENT", + "PublicDescription": "Counts the number of L2 cache lines that are silently dropped due to an L2 cache fill. Increments on the core that brought the line in originally.", + "SampleAfterValue": "1000003", + "UMask": "0x1", + "Unit": "cpu_atom" + }, + { "BriefDescription": "Non-modified cache lines that are silently dropped by L2 cache.", "Counter": "0,1,2,3", "EventCode": "0x26", "EventName": "L2_LINES_OUT.SILENT", - "PublicDescription": "Counts the number of lines that are silently dropped by L2 cache. These lines are typically in Shared or Exclusive state. A non-threaded event.", + "PublicDescription": "Counts the number of lines that are silently dropped by L2 cache. These lines are typically in Shared or Exclusive state. A non-threaded event. Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0x1", "Unit": "cpu_core" @@ -106,7 +177,7 @@ "Counter": "0,1,2,3", "EventCode": "0x26", "EventName": "L2_LINES_OUT.USELESS_HWPF", - "PublicDescription": "Counts the number of cache lines that have been prefetched by the L2 hardware prefetcher but not used by demand access when evicted from the L2 cache", + "PublicDescription": "Counts the number of cache lines that have been prefetched by the L2 hardware prefetcher but not used by demand access when evicted from the L2 cache Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0x4", "Unit": "cpu_core" @@ -116,37 +187,64 @@ "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_REQUEST.ALL", - "PublicDescription": "Counts all requests that were hit or true misses in L2 cache. True-miss excludes misses that were merged with ongoing L2 misses. [This event is alias to L2_RQSTS.REFERENCES]", + "PublicDescription": "Counts all requests that were hit or true misses in L2 cache. True-miss excludes misses that were merged with ongoing L2 misses. [This event is alias to L2_RQSTS.REFERENCES] Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0xff", "Unit": "cpu_core" }, { + "BriefDescription": "Counts the number of L2 Cache Accesses that resulted in a Hit from a front door request only (does not include rejects or recycles), per core event", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x24", + "EventName": "L2_REQUEST.HIT", + "SampleAfterValue": "200003", + "UMask": "0x2", + "Unit": "cpu_atom" + }, + { "BriefDescription": "All requests that hit L2 cache. [This event is alias to L2_RQSTS.HIT]", "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_REQUEST.HIT", - "PublicDescription": "Counts all requests that hit L2 cache. [This event is alias to L2_RQSTS.HIT]", + "PublicDescription": "Counts all requests that hit L2 cache. [This event is alias to L2_RQSTS.HIT] Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0xdf", "Unit": "cpu_core" }, { + "BriefDescription": "Counts the number of total L2 Cache Accesses that resulted in a Miss from a front door request only (does not include rejects or recycles), per core event", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x24", + "EventName": "L2_REQUEST.MISS", + "SampleAfterValue": "200003", + "UMask": "0x1", + "Unit": "cpu_atom" + }, + { "BriefDescription": "Read requests with true-miss in L2 cache [This event is alias to L2_RQSTS.MISS]", "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_REQUEST.MISS", - "PublicDescription": "Counts read requests of any type with true-miss in the L2 cache. True-miss excludes L2 misses that were merged with ongoing L2 misses. [This event is alias to L2_RQSTS.MISS]", + "PublicDescription": "Counts read requests of any type with true-miss in the L2 cache. True-miss excludes L2 misses that were merged with ongoing L2 misses. [This event is alias to L2_RQSTS.MISS] Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0x3f", "Unit": "cpu_core" }, { + "BriefDescription": "Counts the number of L2 Cache Accesses that miss the L2 and get BBL reject short and long rejects (includes those counted in L2_reject_XQ.any), per core event", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x24", + "EventName": "L2_REQUEST.REJECTS", + "SampleAfterValue": "200003", + "UMask": "0x4", + "Unit": "cpu_atom" + }, + { "BriefDescription": "L2 code requests", "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_RQSTS.ALL_CODE_RD", - "PublicDescription": "Counts the total number of L2 code requests.", + "PublicDescription": "Counts the total number of L2 code requests. Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0xe4", "Unit": "cpu_core" @@ -156,7 +254,7 @@ "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_RQSTS.ALL_DEMAND_DATA_RD", - "PublicDescription": "Counts Demand Data Read requests accessing the L2 cache. These requests may hit or miss L2 cache. True-miss exclude misses that were merged with ongoing L2 misses. An access is counted once.", + "PublicDescription": "Counts Demand Data Read requests accessing the L2 cache. These requests may hit or miss L2 cache. True-miss exclude misses that were merged with ongoing L2 misses. An access is counted once. Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0xe1", "Unit": "cpu_core" @@ -166,7 +264,7 @@ "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_RQSTS.ALL_DEMAND_MISS", - "PublicDescription": "Counts demand requests that miss L2 cache.", + "PublicDescription": "Counts demand requests that miss L2 cache. Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0x27", "Unit": "cpu_core" @@ -176,7 +274,7 @@ "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_RQSTS.ALL_DEMAND_REFERENCES", - "PublicDescription": "Counts demand requests to L2 cache.", + "PublicDescription": "Counts demand requests to L2 cache. Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0xe7", "Unit": "cpu_core" @@ -186,6 +284,7 @@ "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_RQSTS.ALL_HWPF", + "PublicDescription": "L2_RQSTS.ALL_HWPF Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0xf0", "Unit": "cpu_core" @@ -195,7 +294,7 @@ "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_RQSTS.ALL_RFO", - "PublicDescription": "Counts the total number of RFO (read for ownership) requests to L2 cache. L2 RFO requests include both L1D demand RFO misses as well as L1D RFO prefetches.", + "PublicDescription": "Counts the total number of RFO (read for ownership) requests to L2 cache. L2 RFO requests include both L1D demand RFO misses as well as L1D RFO prefetches. Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0xe2", "Unit": "cpu_core" @@ -205,7 +304,7 @@ "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_RQSTS.CODE_RD_HIT", - "PublicDescription": "Counts L2 cache hits when fetching instructions, code reads.", + "PublicDescription": "Counts L2 cache hits when fetching instructions, code reads. Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0xc4", "Unit": "cpu_core" @@ -215,7 +314,7 @@ "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_RQSTS.CODE_RD_MISS", - "PublicDescription": "Counts L2 cache misses when fetching instructions.", + "PublicDescription": "Counts L2 cache misses when fetching instructions. Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0x24", "Unit": "cpu_core" @@ -225,7 +324,7 @@ "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_RQSTS.DEMAND_DATA_RD_HIT", - "PublicDescription": "Counts the number of demand Data Read requests initiated by load instructions that hit L2 cache.", + "PublicDescription": "Counts the number of demand Data Read requests initiated by load instructions that hit L2 cache. Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0xc1", "Unit": "cpu_core" @@ -235,7 +334,7 @@ "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_RQSTS.DEMAND_DATA_RD_MISS", - "PublicDescription": "Counts demand Data Read requests with true-miss in the L2 cache. True-miss excludes misses that were merged with ongoing L2 misses. An access is counted once.", + "PublicDescription": "Counts demand Data Read requests with true-miss in the L2 cache. True-miss excludes misses that were merged with ongoing L2 misses. An access is counted once. Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0x21", "Unit": "cpu_core" @@ -245,7 +344,7 @@ "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_RQSTS.HIT", - "PublicDescription": "Counts all requests that hit L2 cache. [This event is alias to L2_REQUEST.HIT]", + "PublicDescription": "Counts all requests that hit L2 cache. [This event is alias to L2_REQUEST.HIT] Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0xdf", "Unit": "cpu_core" @@ -255,6 +354,7 @@ "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_RQSTS.HWPF_MISS", + "PublicDescription": "L2_RQSTS.HWPF_MISS Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0x30", "Unit": "cpu_core" @@ -264,7 +364,7 @@ "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_RQSTS.MISS", - "PublicDescription": "Counts read requests of any type with true-miss in the L2 cache. True-miss excludes L2 misses that were merged with ongoing L2 misses. [This event is alias to L2_REQUEST.MISS]", + "PublicDescription": "Counts read requests of any type with true-miss in the L2 cache. True-miss excludes L2 misses that were merged with ongoing L2 misses. [This event is alias to L2_REQUEST.MISS] Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0x3f", "Unit": "cpu_core" @@ -274,7 +374,7 @@ "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_RQSTS.REFERENCES", - "PublicDescription": "Counts all requests that were hit or true misses in L2 cache. True-miss excludes misses that were merged with ongoing L2 misses. [This event is alias to L2_REQUEST.ALL]", + "PublicDescription": "Counts all requests that were hit or true misses in L2 cache. True-miss excludes misses that were merged with ongoing L2 misses. [This event is alias to L2_REQUEST.ALL] Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0xff", "Unit": "cpu_core" @@ -284,7 +384,7 @@ "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_RQSTS.RFO_HIT", - "PublicDescription": "Counts the RFO (Read-for-Ownership) requests that hit L2 cache.", + "PublicDescription": "Counts the RFO (Read-for-Ownership) requests that hit L2 cache. Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0xc2", "Unit": "cpu_core" @@ -294,7 +394,7 @@ "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_RQSTS.RFO_MISS", - "PublicDescription": "Counts the RFO (Read-for-Ownership) requests that miss L2 cache.", + "PublicDescription": "Counts the RFO (Read-for-Ownership) requests that miss L2 cache. Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0x22", "Unit": "cpu_core" @@ -304,7 +404,7 @@ "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_RQSTS.SWPF_HIT", - "PublicDescription": "Counts Software prefetch requests that hit the L2 cache. Accounts for PREFETCHNTA and PREFETCHT0/1/2 instructions when FB is not full.", + "PublicDescription": "Counts Software prefetch requests that hit the L2 cache. Accounts for PREFETCHNTA and PREFETCHT0/1/2 instructions when FB is not full. Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0xc8", "Unit": "cpu_core" @@ -314,7 +414,7 @@ "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_RQSTS.SWPF_MISS", - "PublicDescription": "Counts Software prefetch requests that miss the L2 cache. Accounts for PREFETCHNTA and PREFETCHT0/1/2 instructions when FB is not full.", + "PublicDescription": "Counts Software prefetch requests that miss the L2 cache. Accounts for PREFETCHNTA and PREFETCHT0/1/2 instructions when FB is not full. Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0x28", "Unit": "cpu_core" @@ -324,7 +424,7 @@ "Counter": "0,1,2,3", "EventCode": "0x23", "EventName": "L2_TRANS.L2_WB", - "PublicDescription": "Counts L2 writebacks that access L2 cache.", + "PublicDescription": "Counts L2 writebacks that access L2 cache. Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0x40", "Unit": "cpu_core" @@ -334,7 +434,7 @@ "Counter": "0,1,2,3", "EventCode": "0x42", "EventName": "LOCK_CYCLES.CACHE_LOCK_DURATION", - "PublicDescription": "This event counts the number of cycles when the L1D is locked. It is a superset of the 0x1 mask (BUS_LOCK_CLOCKS.BUS_LOCK_DURATION).", + "PublicDescription": "This event counts the number of cycles when the L1D is locked. It is a superset of the 0x1 mask (BUS_LOCK_CLOCKS.BUS_LOCK_DURATION). Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x2", "Unit": "cpu_core" @@ -354,7 +454,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0x2e", "EventName": "LONGEST_LAT_CACHE.MISS", - "PublicDescription": "Counts core-originated cacheable requests that miss the L3 cache (Longest Latency cache). Requests include data and code reads, Reads-for-Ownership (RFOs), speculative accesses and hardware prefetches to the L1 and L2. It does not include hardware prefetches to the L3, and may not count other types of requests to the L3.", + "PublicDescription": "Counts core-originated cacheable requests that miss the L3 cache (Longest Latency cache). Requests include data and code reads, Reads-for-Ownership (RFOs), speculative accesses and hardware prefetches to the L1 and L2. It does not include hardware prefetches to the L3, and may not count other types of requests to the L3. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x41", "Unit": "cpu_core" @@ -374,7 +474,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0x2e", "EventName": "LONGEST_LAT_CACHE.REFERENCE", - "PublicDescription": "Counts core-originated cacheable requests to the L3 cache (Longest Latency cache). Requests include data and code reads, Reads-for-Ownership (RFOs), speculative accesses and hardware prefetches to the L1 and L2. It does not include hardware prefetches to the L3, and may not count other types of requests to the L3.", + "PublicDescription": "Counts core-originated cacheable requests to the L3 cache (Longest Latency cache). Requests include data and code reads, Reads-for-Ownership (RFOs), speculative accesses and hardware prefetches to the L1 and L2. It does not include hardware prefetches to the L3, and may not count other types of requests to the L3. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x4f", "Unit": "cpu_core" @@ -399,6 +499,15 @@ "Unit": "cpu_atom" }, { + "BriefDescription": "Counts the number of cycles the core is stalled due to an instruction cache or TLB miss which missed in the L2 cache.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x35", + "EventName": "MEM_BOUND_STALLS_IFETCH.L2_MISS", + "SampleAfterValue": "1000003", + "UMask": "0x7e", + "Unit": "cpu_atom" + }, + { "BriefDescription": "Counts the number of unhalted cycles when the core is stalled due to an ICACHE or ITLB miss which hit in the LLC. If the core has access to an L3 cache, an LLC hit refers to an L3 cache hit, otherwise it counts zeros.", "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0x35", @@ -436,6 +545,15 @@ "Unit": "cpu_atom" }, { + "BriefDescription": "Counts the number of cycles the core is stalled due to a demand load which missed in the L2 cache.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x34", + "EventName": "MEM_BOUND_STALLS_LOAD.L2_MISS", + "SampleAfterValue": "1000003", + "UMask": "0x7e", + "Unit": "cpu_atom" + }, + { "BriefDescription": "Counts the number of unhalted cycles when the core is stalled due to a demand load miss which hit in the LLC. If the core has access to an L3 cache, an LLC hit refers to an L3 cache hit, otherwise it counts zeros.", "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0x34", @@ -454,12 +572,21 @@ "Unit": "cpu_atom" }, { + "BriefDescription": "Counts the number of unhalted cycles when the core is stalled to a store buffer full condition", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x34", + "EventName": "MEM_BOUND_STALLS_LOAD.SBFULL", + "SampleAfterValue": "1000003", + "UMask": "0x80", + "Unit": "cpu_atom" + }, + { "BriefDescription": "Retired load instructions.", "Counter": "0,1,2,3", "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_INST_RETIRED.ALL_LOADS", - "PublicDescription": "Counts all retired load instructions. This event accounts for SW prefetch instructions of PREFETCHNTA or PREFETCHT0/1/2 or PREFETCHW.", + "PublicDescription": "Counts all retired load instructions. This event accounts for SW prefetch instructions of PREFETCHNTA or PREFETCHT0/1/2 or PREFETCHW. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x81", "Unit": "cpu_core" @@ -470,7 +597,7 @@ "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_INST_RETIRED.ALL_STORES", - "PublicDescription": "Counts all retired store instructions.", + "PublicDescription": "Counts all retired store instructions. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x82", "Unit": "cpu_core" @@ -481,7 +608,7 @@ "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_INST_RETIRED.ANY", - "PublicDescription": "Counts all retired memory instructions - loads and stores.", + "PublicDescription": "Counts all retired memory instructions - loads and stores. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x83", "Unit": "cpu_core" @@ -492,7 +619,7 @@ "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_INST_RETIRED.LOCK_LOADS", - "PublicDescription": "Counts retired load instructions with locked access.", + "PublicDescription": "Counts retired load instructions with locked access. Available PDIST counters: 0", "SampleAfterValue": "100007", "UMask": "0x21", "Unit": "cpu_core" @@ -503,7 +630,7 @@ "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_INST_RETIRED.SPLIT_LOADS", - "PublicDescription": "Counts retired load instructions that split across a cacheline boundary.", + "PublicDescription": "Counts retired load instructions that split across a cacheline boundary. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x41", "Unit": "cpu_core" @@ -514,7 +641,7 @@ "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_INST_RETIRED.SPLIT_STORES", - "PublicDescription": "Counts retired store instructions that split across a cacheline boundary.", + "PublicDescription": "Counts retired store instructions that split across a cacheline boundary. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x42", "Unit": "cpu_core" @@ -525,7 +652,7 @@ "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_INST_RETIRED.STLB_HIT_LOADS", - "PublicDescription": "Number of retired load instructions with a clean hit in the 2nd-level TLB (STLB).", + "PublicDescription": "Number of retired load instructions with a clean hit in the 2nd-level TLB (STLB). Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x9", "Unit": "cpu_core" @@ -536,7 +663,7 @@ "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_INST_RETIRED.STLB_HIT_STORES", - "PublicDescription": "Number of retired store instructions that hit in the 2nd-level TLB (STLB).", + "PublicDescription": "Number of retired store instructions that hit in the 2nd-level TLB (STLB). Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0xa", "Unit": "cpu_core" @@ -547,7 +674,7 @@ "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_INST_RETIRED.STLB_MISS_LOADS", - "PublicDescription": "Number of retired load instructions that (start a) miss in the 2nd-level TLB (STLB).", + "PublicDescription": "Number of retired load instructions that (start a) miss in the 2nd-level TLB (STLB). Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x11", "Unit": "cpu_core" @@ -558,7 +685,7 @@ "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_INST_RETIRED.STLB_MISS_STORES", - "PublicDescription": "Number of retired store instructions that (start a) miss in the 2nd-level TLB (STLB).", + "PublicDescription": "Number of retired store instructions that (start a) miss in the 2nd-level TLB (STLB). Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x12", "Unit": "cpu_core" @@ -568,7 +695,7 @@ "Counter": "0,1,2,3", "EventCode": "0x43", "EventName": "MEM_LOAD_COMPLETED.L1_MISS_ANY", - "PublicDescription": "Number of completed demand load requests that missed the L1 data cache including shadow misses (FB hits, merge to an ongoing L1D miss)", + "PublicDescription": "Number of completed demand load requests that missed the L1 data cache including shadow misses (FB hits, merge to an ongoing L1D miss) Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0xfd", "Unit": "cpu_core" @@ -579,7 +706,7 @@ "Data_LA": "1", "EventCode": "0xd2", "EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD", - "PublicDescription": "Counts retired load instructions whose data sources were HitM responses from shared L3.", + "PublicDescription": "Counts retired load instructions whose data sources were HitM responses from shared L3. Available PDIST counters: 0", "SampleAfterValue": "20011", "UMask": "0x4", "Unit": "cpu_core" @@ -590,7 +717,7 @@ "Data_LA": "1", "EventCode": "0xd2", "EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS", - "PublicDescription": "Counts the retired load instructions whose data sources were L3 hit and cross-core snoop missed in on-pkg core cache.", + "PublicDescription": "Counts the retired load instructions whose data sources were L3 hit and cross-core snoop missed in on-pkg core cache. Available PDIST counters: 0", "SampleAfterValue": "20011", "UMask": "0x1", "Unit": "cpu_core" @@ -601,7 +728,7 @@ "Data_LA": "1", "EventCode": "0xd2", "EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_NONE", - "PublicDescription": "Counts retired load instructions whose data sources were hits in L3 without snoops required.", + "PublicDescription": "Counts retired load instructions whose data sources were hits in L3 without snoops required. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x8", "Unit": "cpu_core" @@ -612,7 +739,7 @@ "Data_LA": "1", "EventCode": "0xd2", "EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_NO_FWD", - "PublicDescription": "Counts retired load instructions whose data sources were L3 and cross-core snoop hits in on-pkg core cache.", + "PublicDescription": "Counts retired load instructions whose data sources were L3 and cross-core snoop hits in on-pkg core cache. Available PDIST counters: 0", "SampleAfterValue": "20011", "UMask": "0x2", "Unit": "cpu_core" @@ -623,7 +750,7 @@ "Data_LA": "1", "EventCode": "0xd3", "EventName": "MEM_LOAD_L3_MISS_RETIRED.LOCAL_DRAM", - "PublicDescription": "Retired load instructions which data sources missed L3 but serviced from local DRAM.", + "PublicDescription": "Retired load instructions which data sources missed L3 but serviced from local DRAM. Available PDIST counters: 0", "SampleAfterValue": "100007", "UMask": "0x1", "Unit": "cpu_core" @@ -634,7 +761,7 @@ "Data_LA": "1", "EventCode": "0xd4", "EventName": "MEM_LOAD_MISC_RETIRED.UC", - "PublicDescription": "Retired instructions with at least one load to uncacheable memory-type, or at least one cache-line split locked access (Bus Lock).", + "PublicDescription": "Retired instructions with at least one load to uncacheable memory-type, or at least one cache-line split locked access (Bus Lock). Available PDIST counters: 0", "SampleAfterValue": "100007", "UMask": "0x4", "Unit": "cpu_core" @@ -645,7 +772,7 @@ "Data_LA": "1", "EventCode": "0xd1", "EventName": "MEM_LOAD_RETIRED.FB_HIT", - "PublicDescription": "Counts retired load instructions with at least one uop was load missed in L1 but hit FB (Fill Buffers) due to preceding miss to the same cache line with data not ready.", + "PublicDescription": "Counts retired load instructions with at least one uop was load missed in L1 but hit FB (Fill Buffers) due to preceding miss to the same cache line with data not ready. Available PDIST counters: 0", "SampleAfterValue": "100007", "UMask": "0x40", "Unit": "cpu_core" @@ -656,7 +783,7 @@ "Data_LA": "1", "EventCode": "0xd1", "EventName": "MEM_LOAD_RETIRED.L1_HIT", - "PublicDescription": "Counts retired load instructions with at least one uop that hit in the L1 data cache. This event includes all SW prefetches and lock instructions regardless of the data source.", + "PublicDescription": "Counts retired load instructions with at least one uop that hit in the L1 data cache. This event includes all SW prefetches and lock instructions regardless of the data source. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x1", "Unit": "cpu_core" @@ -667,7 +794,7 @@ "Data_LA": "1", "EventCode": "0xd1", "EventName": "MEM_LOAD_RETIRED.L1_MISS", - "PublicDescription": "Counts retired load instructions with at least one uop that missed in the L1 cache.", + "PublicDescription": "Counts retired load instructions with at least one uop that missed in the L1 cache. Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0x8", "Unit": "cpu_core" @@ -678,7 +805,7 @@ "Data_LA": "1", "EventCode": "0xd1", "EventName": "MEM_LOAD_RETIRED.L2_HIT", - "PublicDescription": "Counts retired load instructions with L2 cache hits as data sources.", + "PublicDescription": "Counts retired load instructions with L2 cache hits as data sources. Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0x2", "Unit": "cpu_core" @@ -689,7 +816,7 @@ "Data_LA": "1", "EventCode": "0xd1", "EventName": "MEM_LOAD_RETIRED.L2_MISS", - "PublicDescription": "Counts retired load instructions missed L2 cache as data sources.", + "PublicDescription": "Counts retired load instructions missed L2 cache as data sources. Available PDIST counters: 0", "SampleAfterValue": "100021", "UMask": "0x10", "Unit": "cpu_core" @@ -700,7 +827,7 @@ "Data_LA": "1", "EventCode": "0xd1", "EventName": "MEM_LOAD_RETIRED.L3_HIT", - "PublicDescription": "Counts retired load instructions with at least one uop that hit in the L3 cache.", + "PublicDescription": "Counts retired load instructions with at least one uop that hit in the L3 cache. Available PDIST counters: 0", "SampleAfterValue": "100021", "UMask": "0x4", "Unit": "cpu_core" @@ -711,7 +838,7 @@ "Data_LA": "1", "EventCode": "0xd1", "EventName": "MEM_LOAD_RETIRED.L3_MISS", - "PublicDescription": "Counts retired load instructions with at least one uop that missed in the L3 cache.", + "PublicDescription": "Counts retired load instructions with at least one uop that missed in the L3 cache. Available PDIST counters: 0", "SampleAfterValue": "50021", "UMask": "0x20", "Unit": "cpu_core" @@ -820,6 +947,7 @@ "Counter": "0,1,2,3", "EventCode": "0x44", "EventName": "MEM_STORE_RETIRED.L2_HIT", + "PublicDescription": "MEM_STORE_RETIRED.L2_HIT Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0x1", "Unit": "cpu_core" @@ -1049,18 +1177,31 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xe5", "EventName": "MEM_UOP_RETIRED.ANY", - "PublicDescription": "Number of retired micro-operations (uops) for load or store memory accesses", + "PublicDescription": "Number of retired micro-operations (uops) for load or store memory accesses Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x3", "Unit": "cpu_core" }, { + "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that have any type of response.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xB7", + "EventName": "OCR.DEMAND_CODE_RD.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x10004", + "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that have any type of response. Available PDIST counters: 0", + "SampleAfterValue": "100003", + "UMask": "0x1", + "Unit": "cpu_atom" + }, + { "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were supplied by the L3 cache.", "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xB7", "EventName": "OCR.DEMAND_CODE_RD.L3_HIT", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x3F803C0004", + "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were supplied by the L3 cache. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1", "Unit": "cpu_atom" @@ -1072,6 +1213,7 @@ "EventName": "OCR.DEMAND_CODE_RD.L3_HIT.SNOOP_HITM", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x10003C0004", + "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were supplied by the L3 cache where a snoop was sent, the snoop hit, and modified data was forwarded. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1", "Unit": "cpu_atom" @@ -1083,6 +1225,7 @@ "EventName": "OCR.DEMAND_CODE_RD.L3_HIT.SNOOP_HIT_NO_FWD", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x4003C0004", + "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were supplied by the L3 cache where a snoop was sent, the snoop hit, but no data was forwarded. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1", "Unit": "cpu_atom" @@ -1094,17 +1237,43 @@ "EventName": "OCR.DEMAND_CODE_RD.L3_HIT.SNOOP_HIT_WITH_FWD", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x8003C0004", + "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were supplied by the L3 cache where a snoop was sent, the snoop hit, and non-modified data was forwarded. Available PDIST counters: 0", + "SampleAfterValue": "100003", + "UMask": "0x1", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts demand data reads that have any type of response.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xB7", + "EventName": "OCR.DEMAND_DATA_RD.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x10001", + "PublicDescription": "Counts demand data reads that have any type of response. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1", "Unit": "cpu_atom" }, { + "BriefDescription": "Counts demand data reads that have any type of response.", + "Counter": "0,1,2,3", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.DEMAND_DATA_RD.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x10001", + "PublicDescription": "Counts demand data reads that have any type of response. Available PDIST counters: 0", + "SampleAfterValue": "100003", + "UMask": "0x1", + "Unit": "cpu_core" + }, + { "BriefDescription": "Counts demand data reads that were supplied by the L3 cache.", "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xB7", "EventName": "OCR.DEMAND_DATA_RD.L3_HIT", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x3F803C0001", + "PublicDescription": "Counts demand data reads that were supplied by the L3 cache. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1", "Unit": "cpu_atom" @@ -1116,6 +1285,7 @@ "EventName": "OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x10003C0001", + "PublicDescription": "Counts demand data reads that were supplied by the L3 cache where a snoop was sent, the snoop hit, and modified data was forwarded. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1", "Unit": "cpu_atom" @@ -1127,6 +1297,7 @@ "EventName": "OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x10003C0001", + "PublicDescription": "Counts demand data reads that resulted in a snoop hit in another cores caches, data forwarding is required as the data is modified. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1", "Unit": "cpu_core" @@ -1138,6 +1309,7 @@ "EventName": "OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_NO_FWD", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x4003C0001", + "PublicDescription": "Counts demand data reads that were supplied by the L3 cache where a snoop was sent, the snoop hit, but no data was forwarded. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1", "Unit": "cpu_atom" @@ -1149,6 +1321,7 @@ "EventName": "OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x8003C0001", + "PublicDescription": "Counts demand data reads that were supplied by the L3 cache where a snoop was sent, the snoop hit, and non-modified data was forwarded. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1", "Unit": "cpu_atom" @@ -1160,6 +1333,31 @@ "EventName": "OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x8003C0001", + "PublicDescription": "Counts demand data reads that resulted in a snoop hit in another cores caches which forwarded the unmodified data to the requesting core. Available PDIST counters: 0", + "SampleAfterValue": "100003", + "UMask": "0x1", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that have any type of response.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xB7", + "EventName": "OCR.DEMAND_RFO.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x10002", + "PublicDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that have any type of response. Available PDIST counters: 0", + "SampleAfterValue": "100003", + "UMask": "0x1", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts demand read for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that have any type of response.", + "Counter": "0,1,2,3", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.DEMAND_RFO.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x10002", + "PublicDescription": "Counts demand read for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that have any type of response. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1", "Unit": "cpu_core" @@ -1171,6 +1369,7 @@ "EventName": "OCR.DEMAND_RFO.L3_HIT", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x3F803C0002", + "PublicDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that were supplied by the L3 cache. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1", "Unit": "cpu_atom" @@ -1182,6 +1381,7 @@ "EventName": "OCR.DEMAND_RFO.L3_HIT.SNOOP_HITM", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x10003C0002", + "PublicDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that were supplied by the L3 cache where a snoop was sent, the snoop hit, and modified data was forwarded. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1", "Unit": "cpu_atom" @@ -1193,6 +1393,7 @@ "EventName": "OCR.DEMAND_RFO.L3_HIT.SNOOP_HITM", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x10003C0002", + "PublicDescription": "Counts demand read for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that resulted in a snoop hit in another cores caches, data forwarding is required as the data is modified. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1", "Unit": "cpu_core" @@ -1202,7 +1403,7 @@ "Counter": "0,1,2,3", "EventCode": "0x21", "EventName": "OFFCORE_REQUESTS.ALL_REQUESTS", - "PublicDescription": "Counts memory transactions reached the super queue including requests initiated by the core, all L3 prefetches, page walks, etc..", + "PublicDescription": "Counts memory transactions reached the super queue including requests initiated by the core, all L3 prefetches, page walks, etc.. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x80", "Unit": "cpu_core" @@ -1212,7 +1413,7 @@ "Counter": "0,1,2,3", "EventCode": "0x21", "EventName": "OFFCORE_REQUESTS.DATA_RD", - "PublicDescription": "Counts the demand and prefetch data reads. All Core Data Reads include cacheable 'Demands' and L2 prefetchers (not L3 prefetchers). Counting also covers reads due to page walks resulted from any request type.", + "PublicDescription": "Counts the demand and prefetch data reads. All Core Data Reads include cacheable 'Demands' and L2 prefetchers (not L3 prefetchers). Counting also covers reads due to page walks resulted from any request type. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x8", "Unit": "cpu_core" @@ -1222,7 +1423,7 @@ "Counter": "0,1,2,3", "EventCode": "0x21", "EventName": "OFFCORE_REQUESTS.DEMAND_CODE_RD", - "PublicDescription": "Counts both cacheable and Non-Cacheable code read requests.", + "PublicDescription": "Counts both cacheable and Non-Cacheable code read requests. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x2", "Unit": "cpu_core" @@ -1232,7 +1433,7 @@ "Counter": "0,1,2,3", "EventCode": "0x21", "EventName": "OFFCORE_REQUESTS.DEMAND_DATA_RD", - "PublicDescription": "Counts the Demand Data Read requests sent to uncore. Use it in conjunction with OFFCORE_REQUESTS_OUTSTANDING to determine average latency in the uncore.", + "PublicDescription": "Counts the Demand Data Read requests sent to uncore. Use it in conjunction with OFFCORE_REQUESTS_OUTSTANDING to determine average latency in the uncore. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1", "Unit": "cpu_core" @@ -1242,7 +1443,7 @@ "Counter": "0,1,2,3", "EventCode": "0x21", "EventName": "OFFCORE_REQUESTS.DEMAND_RFO", - "PublicDescription": "Counts the demand RFO (read for ownership) requests including regular RFOs, locks, ItoM.", + "PublicDescription": "Counts the demand RFO (read for ownership) requests including regular RFOs, locks, ItoM. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x4", "Unit": "cpu_core" @@ -1253,7 +1454,7 @@ "CounterMask": "1", "EventCode": "0x20", "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD", - "PublicDescription": "Counts cycles when offcore outstanding cacheable Core Data Read transactions are present in the super queue. A transaction is considered to be in the Offcore outstanding state between L2 miss and transaction completion sent to requestor (SQ de-allocation). See corresponding Umask under OFFCORE_REQUESTS.", + "PublicDescription": "Counts cycles when offcore outstanding cacheable Core Data Read transactions are present in the super queue. A transaction is considered to be in the Offcore outstanding state between L2 miss and transaction completion sent to requestor (SQ de-allocation). See corresponding Umask under OFFCORE_REQUESTS. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x8", "Unit": "cpu_core" @@ -1264,7 +1465,7 @@ "CounterMask": "1", "EventCode": "0x20", "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_CODE_RD", - "PublicDescription": "Counts the number of offcore outstanding Code Reads transactions in the super queue every cycle. The 'Offcore outstanding' state of the transaction lasts from the L2 miss until the sending transaction completion to requestor (SQ deallocation). See the corresponding Umask under OFFCORE_REQUESTS.", + "PublicDescription": "Counts the number of offcore outstanding Code Reads transactions in the super queue every cycle. The 'Offcore outstanding' state of the transaction lasts from the L2 miss until the sending transaction completion to requestor (SQ deallocation). See the corresponding Umask under OFFCORE_REQUESTS. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x2", "Unit": "cpu_core" @@ -1275,6 +1476,7 @@ "CounterMask": "1", "EventCode": "0x20", "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_DATA_RD", + "PublicDescription": "Cycles where at least 1 outstanding demand data read request is pending. Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x1", "Unit": "cpu_core" @@ -1285,7 +1487,7 @@ "CounterMask": "1", "EventCode": "0x20", "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO", - "PublicDescription": "Counts the number of offcore outstanding demand rfo Reads transactions in the super queue every cycle. The 'Offcore outstanding' state of the transaction lasts from the L2 miss until the sending transaction completion to requestor (SQ deallocation). See the corresponding Umask under OFFCORE_REQUESTS.", + "PublicDescription": "Counts the number of offcore outstanding demand rfo Reads transactions in the super queue every cycle. The 'Offcore outstanding' state of the transaction lasts from the L2 miss until the sending transaction completion to requestor (SQ deallocation). See the corresponding Umask under OFFCORE_REQUESTS. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x4", "Unit": "cpu_core" @@ -1295,6 +1497,7 @@ "Counter": "0,1,2,3", "EventCode": "0x20", "EventName": "OFFCORE_REQUESTS_OUTSTANDING.DATA_RD", + "PublicDescription": "OFFCORE_REQUESTS_OUTSTANDING.DATA_RD Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x8", "Unit": "cpu_core" @@ -1304,7 +1507,7 @@ "Counter": "0,1,2,3", "EventCode": "0x20", "EventName": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_CODE_RD", - "PublicDescription": "Counts the number of offcore outstanding Code Reads transactions in the super queue every cycle. The 'Offcore outstanding' state of the transaction lasts from the L2 miss until the sending transaction completion to requestor (SQ deallocation). See the corresponding Umask under OFFCORE_REQUESTS.", + "PublicDescription": "Counts the number of offcore outstanding Code Reads transactions in the super queue every cycle. The 'Offcore outstanding' state of the transaction lasts from the L2 miss until the sending transaction completion to requestor (SQ deallocation). See the corresponding Umask under OFFCORE_REQUESTS. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x2", "Unit": "cpu_core" @@ -1314,7 +1517,7 @@ "Counter": "0,1,2,3", "EventCode": "0x20", "EventName": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD", - "PublicDescription": "For every cycle, increments by the number of outstanding demand data read requests pending. Requests are considered outstanding from the time they miss the core's L2 cache until the transaction completion message is sent to the requestor.", + "PublicDescription": "For every cycle, increments by the number of outstanding demand data read requests pending. Requests are considered outstanding from the time they miss the core's L2 cache until the transaction completion message is sent to the requestor. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x1", "Unit": "cpu_core" @@ -1324,7 +1527,7 @@ "Counter": "0,1,2,3", "EventCode": "0x20", "EventName": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_RFO", - "PublicDescription": "Counts the number of off-core outstanding read-for-ownership (RFO) store transactions every cycle. An RFO transaction is considered to be in the Off-core outstanding state between L2 cache miss and transaction completion.", + "PublicDescription": "Counts the number of off-core outstanding read-for-ownership (RFO) store transactions every cycle. An RFO transaction is considered to be in the Off-core outstanding state between L2 cache miss and transaction completion. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x4", "Unit": "cpu_core" @@ -1334,7 +1537,7 @@ "Counter": "0,1,2,3", "EventCode": "0x2c", "EventName": "SQ_MISC.BUS_LOCK", - "PublicDescription": "Counts the more expensive bus lock needed to enforce cache coherency for certain memory accesses that need to be done atomically. Can be created by issuing an atomic instruction (via the LOCK prefix) which causes a cache line split or accesses uncacheable memory.", + "PublicDescription": "Counts the more expensive bus lock needed to enforce cache coherency for certain memory accesses that need to be done atomically. Can be created by issuing an atomic instruction (via the LOCK prefix) which causes a cache line split or accesses uncacheable memory. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x10", "Unit": "cpu_core" @@ -1344,6 +1547,7 @@ "Counter": "0,1,2,3", "EventCode": "0x40", "EventName": "SW_PREFETCH_ACCESS.ANY", + "PublicDescription": "Counts the number of PREFETCHNTA, PREFETCHW, PREFETCHT0, PREFETCHT1 or PREFETCHT2 instructions executed. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0xf", "Unit": "cpu_core" @@ -1353,7 +1557,7 @@ "Counter": "0,1,2,3", "EventCode": "0x40", "EventName": "SW_PREFETCH_ACCESS.NTA", - "PublicDescription": "Counts the number of PREFETCHNTA instructions executed.", + "PublicDescription": "Counts the number of PREFETCHNTA instructions executed. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1", "Unit": "cpu_core" @@ -1363,7 +1567,7 @@ "Counter": "0,1,2,3", "EventCode": "0x40", "EventName": "SW_PREFETCH_ACCESS.PREFETCHW", - "PublicDescription": "Counts the number of PREFETCHW instructions executed.", + "PublicDescription": "Counts the number of PREFETCHW instructions executed. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x8", "Unit": "cpu_core" @@ -1373,7 +1577,7 @@ "Counter": "0,1,2,3", "EventCode": "0x40", "EventName": "SW_PREFETCH_ACCESS.T0", - "PublicDescription": "Counts the number of PREFETCHT0 instructions executed.", + "PublicDescription": "Counts the number of PREFETCHT0 instructions executed. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x2", "Unit": "cpu_core" @@ -1383,7 +1587,7 @@ "Counter": "0,1,2,3", "EventCode": "0x40", "EventName": "SW_PREFETCH_ACCESS.T1_T2", - "PublicDescription": "Counts the number of PREFETCHT1 or PREFETCHT2 instructions executed.", + "PublicDescription": "Counts the number of PREFETCHT1 or PREFETCHT2 instructions executed. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x4", "Unit": "cpu_core" diff --git a/tools/perf/pmu-events/arch/x86/meteorlake/floating-point.json b/tools/perf/pmu-events/arch/x86/meteorlake/floating-point.json index 28dc5e06ee31..ae9778aa755b 100644 --- a/tools/perf/pmu-events/arch/x86/meteorlake/floating-point.json +++ b/tools/perf/pmu-events/arch/x86/meteorlake/floating-point.json @@ -15,6 +15,7 @@ "CounterMask": "1", "EventCode": "0xb0", "EventName": "ARITH.FPDIV_ACTIVE", + "PublicDescription": "This event counts the cycles the floating point divider is busy. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x1", "Unit": "cpu_core" @@ -24,7 +25,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc1", "EventName": "ASSISTS.FP", - "PublicDescription": "Counts all microcode Floating Point assists.", + "PublicDescription": "Counts all microcode Floating Point assists. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x2", "Unit": "cpu_core" @@ -34,6 +35,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc1", "EventName": "ASSISTS.SSE_AVX_MIX", + "PublicDescription": "ASSISTS.SSE_AVX_MIX Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x10", "Unit": "cpu_core" @@ -43,6 +45,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xb3", "EventName": "FP_ARITH_DISPATCHED.PORT_0", + "PublicDescription": "FP_ARITH_DISPATCHED.PORT_0 [This event is alias to FP_ARITH_DISPATCHED.V0] Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x1", "Unit": "cpu_core" @@ -52,6 +55,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xb3", "EventName": "FP_ARITH_DISPATCHED.PORT_1", + "PublicDescription": "FP_ARITH_DISPATCHED.PORT_1 [This event is alias to FP_ARITH_DISPATCHED.V1] Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x2", "Unit": "cpu_core" @@ -61,6 +65,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xb3", "EventName": "FP_ARITH_DISPATCHED.PORT_5", + "PublicDescription": "FP_ARITH_DISPATCHED.PORT_5 [This event is alias to FP_ARITH_DISPATCHED.V2] Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x4", "Unit": "cpu_core" @@ -70,6 +75,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xb3", "EventName": "FP_ARITH_DISPATCHED.V0", + "PublicDescription": "FP_ARITH_DISPATCHED.V0 [This event is alias to FP_ARITH_DISPATCHED.PORT_0] Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x1", "Unit": "cpu_core" @@ -79,6 +85,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xb3", "EventName": "FP_ARITH_DISPATCHED.V1", + "PublicDescription": "FP_ARITH_DISPATCHED.V1 [This event is alias to FP_ARITH_DISPATCHED.PORT_1] Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x2", "Unit": "cpu_core" @@ -88,6 +95,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xb3", "EventName": "FP_ARITH_DISPATCHED.V2", + "PublicDescription": "FP_ARITH_DISPATCHED.V2 [This event is alias to FP_ARITH_DISPATCHED.PORT_5] Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x4", "Unit": "cpu_core" @@ -97,7 +105,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc7", "EventName": "FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE", - "PublicDescription": "Number of SSE/AVX computational 128-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 2 computation operations, one for each element. Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.", + "PublicDescription": "Number of SSE/AVX computational 128-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 2 computation operations, one for each element. Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x4", "Unit": "cpu_core" @@ -107,7 +115,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc7", "EventName": "FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE", - "PublicDescription": "Number of SSE/AVX computational 128-bit packed single precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 4 computation operations, one for each element. Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT RSQRT RCP DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.", + "PublicDescription": "Number of SSE/AVX computational 128-bit packed single precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 4 computation operations, one for each element. Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT RSQRT RCP DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x8", "Unit": "cpu_core" @@ -117,7 +125,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc7", "EventName": "FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE", - "PublicDescription": "Number of SSE/AVX computational 256-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 4 computation operations, one for each element. Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.", + "PublicDescription": "Number of SSE/AVX computational 256-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 4 computation operations, one for each element. Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x10", "Unit": "cpu_core" @@ -127,7 +135,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc7", "EventName": "FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE", - "PublicDescription": "Number of SSE/AVX computational 256-bit packed single precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 8 computation operations, one for each element. Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT RSQRT RCP DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.", + "PublicDescription": "Number of SSE/AVX computational 256-bit packed single precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 8 computation operations, one for each element. Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT RSQRT RCP DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x20", "Unit": "cpu_core" @@ -137,7 +145,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc7", "EventName": "FP_ARITH_INST_RETIRED.4_FLOPS", - "PublicDescription": "Number of SSE/AVX computational 128-bit packed single precision and 256-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 2 or/and 4 computation operations, one for each element. Applies to SSE* and AVX* packed single precision floating-point and packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX RCP14 RSQRT14 SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.", + "PublicDescription": "Number of SSE/AVX computational 128-bit packed single precision and 256-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 2 or/and 4 computation operations, one for each element. Applies to SSE* and AVX* packed single precision floating-point and packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX RCP14 RSQRT14 SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x18", "Unit": "cpu_core" @@ -147,7 +155,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc7", "EventName": "FP_ARITH_INST_RETIRED.SCALAR", - "PublicDescription": "Number of SSE/AVX computational scalar single precision and double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 1 computational operation. Applies to SSE* and AVX* scalar single precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT RSQRT RCP FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.", + "PublicDescription": "Number of SSE/AVX computational scalar single precision and double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 1 computational operation. Applies to SSE* and AVX* scalar single precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT RSQRT RCP FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x3", "Unit": "cpu_core" @@ -157,7 +165,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc7", "EventName": "FP_ARITH_INST_RETIRED.SCALAR_DOUBLE", - "PublicDescription": "Number of SSE/AVX computational scalar double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 1 computational operation. Applies to SSE* and AVX* scalar double precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.", + "PublicDescription": "Number of SSE/AVX computational scalar double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 1 computational operation. Applies to SSE* and AVX* scalar double precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1", "Unit": "cpu_core" @@ -167,7 +175,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc7", "EventName": "FP_ARITH_INST_RETIRED.SCALAR_SINGLE", - "PublicDescription": "Number of SSE/AVX computational scalar single precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 1 computational operation. Applies to SSE* and AVX* scalar single precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT RSQRT RCP FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.", + "PublicDescription": "Number of SSE/AVX computational scalar single precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 1 computational operation. Applies to SSE* and AVX* scalar single precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT RSQRT RCP FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x2", "Unit": "cpu_core" @@ -177,7 +185,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc7", "EventName": "FP_ARITH_INST_RETIRED.VECTOR", - "PublicDescription": "Number of any Vector retired FP arithmetic instructions. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.", + "PublicDescription": "Number of any Vector retired FP arithmetic instructions. The DAZ and FTZ flags in the MXCSR register need to be set when using these events. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0xfc", "Unit": "cpu_core" diff --git a/tools/perf/pmu-events/arch/x86/meteorlake/frontend.json b/tools/perf/pmu-events/arch/x86/meteorlake/frontend.json index a10614513c8d..509ce68c2ea6 100644 --- a/tools/perf/pmu-events/arch/x86/meteorlake/frontend.json +++ b/tools/perf/pmu-events/arch/x86/meteorlake/frontend.json @@ -14,7 +14,7 @@ "Counter": "0,1,2,3", "EventCode": "0x60", "EventName": "BACLEARS.ANY", - "PublicDescription": "Number of times the front-end is resteered when it finds a branch instruction in a fetch line. This is called Unknown Branch which occurs for the first time a branch instruction is fetched or when the branch is not tracked by the BPU (Branch Prediction Unit) anymore.", + "PublicDescription": "Number of times the front-end is resteered when it finds a branch instruction in a fetch line. This is called Unknown Branch which occurs for the first time a branch instruction is fetched or when the branch is not tracked by the BPU (Branch Prediction Unit) anymore. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1", "Unit": "cpu_core" @@ -24,7 +24,7 @@ "Counter": "0,1,2,3", "EventCode": "0x87", "EventName": "DECODE.LCP", - "PublicDescription": "Counts cycles that the Instruction Length decoder (ILD) stalls occurred due to dynamically changing prefix length of the decoded instruction (by operand size prefix instruction 0x66, address size prefix instruction 0x67 or REX.W for Intel64). Count is proportional to the number of prefixes in a 16B-line. This may result in a three-cycle penalty for each LCP (Length changing prefix) in a 16-byte chunk.", + "PublicDescription": "Counts cycles that the Instruction Length decoder (ILD) stalls occurred due to dynamically changing prefix length of the decoded instruction (by operand size prefix instruction 0x66, address size prefix instruction 0x67 or REX.W for Intel64). Count is proportional to the number of prefixes in a 16B-line. This may result in a three-cycle penalty for each LCP (Length changing prefix) in a 16-byte chunk. Available PDIST counters: 0", "SampleAfterValue": "500009", "UMask": "0x1", "Unit": "cpu_core" @@ -34,6 +34,7 @@ "Counter": "0,1,2,3", "EventCode": "0x87", "EventName": "DECODE.MS_BUSY", + "PublicDescription": "Cycles the Microcode Sequencer is busy. Available PDIST counters: 0", "SampleAfterValue": "500009", "UMask": "0x2", "Unit": "cpu_core" @@ -43,7 +44,7 @@ "Counter": "0,1,2,3", "EventCode": "0x61", "EventName": "DSB2MITE_SWITCHES.PENALTY_CYCLES", - "PublicDescription": "Decode Stream Buffer (DSB) is a Uop-cache that holds translations of previously fetched instructions that were decoded by the legacy x86 decode pipeline (MITE). This event counts fetch penalty cycles when a transition occurs from DSB to MITE.", + "PublicDescription": "Decode Stream Buffer (DSB) is a Uop-cache that holds translations of previously fetched instructions that were decoded by the legacy x86 decode pipeline (MITE). This event counts fetch penalty cycles when a transition occurs from DSB to MITE. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x2", "Unit": "cpu_core" @@ -55,7 +56,7 @@ "EventName": "FRONTEND_RETIRED.ANY_ANT", "MSRIndex": "0x3F7", "MSRValue": "0x9", - "PublicDescription": "Always Not Taken (ANT) conditional retired branches (no BTB entry and not mispredicted)", + "PublicDescription": "Always Not Taken (ANT) conditional retired branches (no BTB entry and not mispredicted) Available PDIST counters: 0", "SampleAfterValue": "100007", "UMask": "0x3", "Unit": "cpu_core" @@ -67,7 +68,7 @@ "EventName": "FRONTEND_RETIRED.ANY_DSB_MISS", "MSRIndex": "0x3F7", "MSRValue": "0x1", - "PublicDescription": "Counts retired Instructions that experienced DSB (Decode stream buffer i.e. the decoded instruction-cache) miss.", + "PublicDescription": "Counts retired Instructions that experienced DSB (Decode stream buffer i.e. the decoded instruction-cache) miss. Available PDIST counters: 0", "SampleAfterValue": "100007", "UMask": "0x3", "Unit": "cpu_core" @@ -79,7 +80,7 @@ "EventName": "FRONTEND_RETIRED.DSB_MISS", "MSRIndex": "0x3F7", "MSRValue": "0x11", - "PublicDescription": "Number of retired Instructions that experienced a critical DSB (Decode stream buffer i.e. the decoded instruction-cache) miss. Critical means stalls were exposed to the back-end as a result of the DSB miss.", + "PublicDescription": "Number of retired Instructions that experienced a critical DSB (Decode stream buffer i.e. the decoded instruction-cache) miss. Critical means stalls were exposed to the back-end as a result of the DSB miss. Available PDIST counters: 0", "SampleAfterValue": "100007", "UMask": "0x3", "Unit": "cpu_core" @@ -100,7 +101,7 @@ "EventName": "FRONTEND_RETIRED.ITLB_MISS", "MSRIndex": "0x3F7", "MSRValue": "0x14", - "PublicDescription": "Counts retired Instructions that experienced iTLB (Instruction TLB) true miss.", + "PublicDescription": "Counts retired Instructions that experienced iTLB (Instruction TLB) true miss. Available PDIST counters: 0", "SampleAfterValue": "100007", "UMask": "0x3", "Unit": "cpu_core" @@ -112,7 +113,7 @@ "EventName": "FRONTEND_RETIRED.L1I_MISS", "MSRIndex": "0x3F7", "MSRValue": "0x12", - "PublicDescription": "Counts retired Instructions who experienced Instruction L1 Cache true miss.", + "PublicDescription": "Counts retired Instructions who experienced Instruction L1 Cache true miss. Available PDIST counters: 0", "SampleAfterValue": "100007", "UMask": "0x3", "Unit": "cpu_core" @@ -124,7 +125,7 @@ "EventName": "FRONTEND_RETIRED.L2_MISS", "MSRIndex": "0x3F7", "MSRValue": "0x13", - "PublicDescription": "Counts retired Instructions who experienced Instruction L2 Cache true miss.", + "PublicDescription": "Counts retired Instructions who experienced Instruction L2 Cache true miss. Available PDIST counters: 0", "SampleAfterValue": "100007", "UMask": "0x3", "Unit": "cpu_core" @@ -136,7 +137,7 @@ "EventName": "FRONTEND_RETIRED.LATENCY_GE_1", "MSRIndex": "0x3F7", "MSRValue": "0x600106", - "PublicDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of at least 1 cycle which was not interrupted by a back-end stall.", + "PublicDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of at least 1 cycle which was not interrupted by a back-end stall. Available PDIST counters: 0", "SampleAfterValue": "100007", "UMask": "0x3", "Unit": "cpu_core" @@ -148,7 +149,7 @@ "EventName": "FRONTEND_RETIRED.LATENCY_GE_128", "MSRIndex": "0x3F7", "MSRValue": "0x608006", - "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 128 cycles which was not interrupted by a back-end stall.", + "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 128 cycles which was not interrupted by a back-end stall. Available PDIST counters: 0", "SampleAfterValue": "100007", "UMask": "0x3", "Unit": "cpu_core" @@ -160,7 +161,7 @@ "EventName": "FRONTEND_RETIRED.LATENCY_GE_16", "MSRIndex": "0x3F7", "MSRValue": "0x601006", - "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 16 cycles. During this period the front-end delivered no uops.", + "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 16 cycles. During this period the front-end delivered no uops. Available PDIST counters: 0", "SampleAfterValue": "100007", "UMask": "0x3", "Unit": "cpu_core" @@ -172,7 +173,7 @@ "EventName": "FRONTEND_RETIRED.LATENCY_GE_2", "MSRIndex": "0x3F7", "MSRValue": "0x600206", - "PublicDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of at least 2 cycles which was not interrupted by a back-end stall.", + "PublicDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of at least 2 cycles which was not interrupted by a back-end stall. Available PDIST counters: 0", "SampleAfterValue": "100007", "UMask": "0x3", "Unit": "cpu_core" @@ -184,7 +185,7 @@ "EventName": "FRONTEND_RETIRED.LATENCY_GE_256", "MSRIndex": "0x3F7", "MSRValue": "0x610006", - "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 256 cycles which was not interrupted by a back-end stall.", + "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 256 cycles which was not interrupted by a back-end stall. Available PDIST counters: 0", "SampleAfterValue": "100007", "UMask": "0x3", "Unit": "cpu_core" @@ -196,7 +197,7 @@ "EventName": "FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1", "MSRIndex": "0x3F7", "MSRValue": "0x100206", - "PublicDescription": "Counts retired instructions that are delivered to the back-end after the front-end had at least 1 bubble-slot for a period of 2 cycles. A bubble-slot is an empty issue-pipeline slot while there was no RAT stall.", + "PublicDescription": "Counts retired instructions that are delivered to the back-end after the front-end had at least 1 bubble-slot for a period of 2 cycles. A bubble-slot is an empty issue-pipeline slot while there was no RAT stall. Available PDIST counters: 0", "SampleAfterValue": "100007", "UMask": "0x3", "Unit": "cpu_core" @@ -208,7 +209,7 @@ "EventName": "FRONTEND_RETIRED.LATENCY_GE_32", "MSRIndex": "0x3F7", "MSRValue": "0x602006", - "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 32 cycles. During this period the front-end delivered no uops.", + "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 32 cycles. During this period the front-end delivered no uops. Available PDIST counters: 0", "SampleAfterValue": "100007", "UMask": "0x3", "Unit": "cpu_core" @@ -220,7 +221,7 @@ "EventName": "FRONTEND_RETIRED.LATENCY_GE_4", "MSRIndex": "0x3F7", "MSRValue": "0x600406", - "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 4 cycles which was not interrupted by a back-end stall.", + "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 4 cycles which was not interrupted by a back-end stall. Available PDIST counters: 0", "SampleAfterValue": "100007", "UMask": "0x3", "Unit": "cpu_core" @@ -232,7 +233,7 @@ "EventName": "FRONTEND_RETIRED.LATENCY_GE_512", "MSRIndex": "0x3F7", "MSRValue": "0x620006", - "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 512 cycles which was not interrupted by a back-end stall.", + "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 512 cycles which was not interrupted by a back-end stall. Available PDIST counters: 0", "SampleAfterValue": "100007", "UMask": "0x3", "Unit": "cpu_core" @@ -244,7 +245,7 @@ "EventName": "FRONTEND_RETIRED.LATENCY_GE_64", "MSRIndex": "0x3F7", "MSRValue": "0x604006", - "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 64 cycles which was not interrupted by a back-end stall.", + "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 64 cycles which was not interrupted by a back-end stall. Available PDIST counters: 0", "SampleAfterValue": "100007", "UMask": "0x3", "Unit": "cpu_core" @@ -256,7 +257,7 @@ "EventName": "FRONTEND_RETIRED.LATENCY_GE_8", "MSRIndex": "0x3F7", "MSRValue": "0x600806", - "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 8 cycles. During this period the front-end delivered no uops.", + "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 8 cycles. During this period the front-end delivered no uops. Available PDIST counters: 0", "SampleAfterValue": "100007", "UMask": "0x3", "Unit": "cpu_core" @@ -268,7 +269,7 @@ "EventName": "FRONTEND_RETIRED.MISP_ANT", "MSRIndex": "0x3F7", "MSRValue": "0x9", - "PublicDescription": "ANT retired branches that got just mispredicted", + "PublicDescription": "ANT retired branches that got just mispredicted Available PDIST counters: 0", "SampleAfterValue": "100007", "UMask": "0x2", "Unit": "cpu_core" @@ -280,6 +281,7 @@ "EventName": "FRONTEND_RETIRED.MS_FLOWS", "MSRIndex": "0x3F7", "MSRValue": "0x8", + "PublicDescription": "FRONTEND_RETIRED.MS_FLOWS Available PDIST counters: 0", "SampleAfterValue": "100007", "UMask": "0x3", "Unit": "cpu_core" @@ -291,7 +293,7 @@ "EventName": "FRONTEND_RETIRED.STLB_MISS", "MSRIndex": "0x3F7", "MSRValue": "0x15", - "PublicDescription": "Counts retired Instructions that experienced STLB (2nd level TLB) true miss.", + "PublicDescription": "Counts retired Instructions that experienced STLB (2nd level TLB) true miss. Available PDIST counters: 0", "SampleAfterValue": "100007", "UMask": "0x3", "Unit": "cpu_core" @@ -303,6 +305,7 @@ "EventName": "FRONTEND_RETIRED.UNKNOWN_BRANCH", "MSRIndex": "0x3F7", "MSRValue": "0x17", + "PublicDescription": "FRONTEND_RETIRED.UNKNOWN_BRANCH Available PDIST counters: 0", "SampleAfterValue": "100007", "UMask": "0x3", "Unit": "cpu_core" @@ -330,7 +333,7 @@ "Counter": "0,1,2,3", "EventCode": "0x80", "EventName": "ICACHE_DATA.STALLS", - "PublicDescription": "Counts cycles where a code line fetch is stalled due to an L1 instruction cache miss. The decode pipeline works at a 32 Byte granularity.", + "PublicDescription": "Counts cycles where a code line fetch is stalled due to an L1 instruction cache miss. The decode pipeline works at a 32 Byte granularity. Available PDIST counters: 0", "SampleAfterValue": "500009", "UMask": "0x4", "Unit": "cpu_core" @@ -342,6 +345,7 @@ "EdgeDetect": "1", "EventCode": "0x80", "EventName": "ICACHE_DATA.STALL_PERIODS", + "PublicDescription": "ICACHE_DATA.STALL_PERIODS Available PDIST counters: 0", "SampleAfterValue": "500009", "UMask": "0x4", "Unit": "cpu_core" @@ -351,7 +355,7 @@ "Counter": "0,1,2,3", "EventCode": "0x83", "EventName": "ICACHE_TAG.STALLS", - "PublicDescription": "Counts cycles where a code fetch is stalled due to L1 instruction cache tag miss.", + "PublicDescription": "Counts cycles where a code fetch is stalled due to L1 instruction cache tag miss. Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0x4", "Unit": "cpu_core" @@ -362,7 +366,7 @@ "CounterMask": "1", "EventCode": "0x79", "EventName": "IDQ.DSB_CYCLES_ANY", - "PublicDescription": "Counts the number of cycles uops were delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path.", + "PublicDescription": "Counts the number of cycles uops were delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path. Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x8", "Unit": "cpu_core" @@ -373,7 +377,7 @@ "CounterMask": "6", "EventCode": "0x79", "EventName": "IDQ.DSB_CYCLES_OK", - "PublicDescription": "Counts the number of cycles where optimal number of uops was delivered to the Instruction Decode Queue (IDQ) from the DSB (Decode Stream Buffer) path. Count includes uops that may 'bypass' the IDQ.", + "PublicDescription": "Counts the number of cycles where optimal number of uops was delivered to the Instruction Decode Queue (IDQ) from the DSB (Decode Stream Buffer) path. Count includes uops that may 'bypass' the IDQ. Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x8", "Unit": "cpu_core" @@ -383,7 +387,7 @@ "Counter": "0,1,2,3", "EventCode": "0x79", "EventName": "IDQ.DSB_UOPS", - "PublicDescription": "Counts the number of uops delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path.", + "PublicDescription": "Counts the number of uops delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path. Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x8", "Unit": "cpu_core" @@ -394,7 +398,7 @@ "CounterMask": "1", "EventCode": "0x79", "EventName": "IDQ.MITE_CYCLES_ANY", - "PublicDescription": "Counts the number of cycles uops were delivered to the Instruction Decode Queue (IDQ) from the MITE (legacy decode pipeline) path. During these cycles uops are not being delivered from the Decode Stream Buffer (DSB).", + "PublicDescription": "Counts the number of cycles uops were delivered to the Instruction Decode Queue (IDQ) from the MITE (legacy decode pipeline) path. During these cycles uops are not being delivered from the Decode Stream Buffer (DSB). Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x4", "Unit": "cpu_core" @@ -405,7 +409,7 @@ "CounterMask": "6", "EventCode": "0x79", "EventName": "IDQ.MITE_CYCLES_OK", - "PublicDescription": "Counts the number of cycles where optimal number of uops was delivered to the Instruction Decode Queue (IDQ) from the MITE (legacy decode pipeline) path. During these cycles uops are not being delivered from the Decode Stream Buffer (DSB).", + "PublicDescription": "Counts the number of cycles where optimal number of uops was delivered to the Instruction Decode Queue (IDQ) from the MITE (legacy decode pipeline) path. During these cycles uops are not being delivered from the Decode Stream Buffer (DSB). Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x4", "Unit": "cpu_core" @@ -415,7 +419,7 @@ "Counter": "0,1,2,3", "EventCode": "0x79", "EventName": "IDQ.MITE_UOPS", - "PublicDescription": "Counts the number of uops delivered to Instruction Decode Queue (IDQ) from the MITE path. This also means that uops are not being delivered from the Decode Stream Buffer (DSB).", + "PublicDescription": "Counts the number of uops delivered to Instruction Decode Queue (IDQ) from the MITE path. This also means that uops are not being delivered from the Decode Stream Buffer (DSB). Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x4", "Unit": "cpu_core" @@ -426,7 +430,7 @@ "CounterMask": "1", "EventCode": "0x79", "EventName": "IDQ.MS_CYCLES_ANY", - "PublicDescription": "Counts cycles during which uops are being delivered to Instruction Decode Queue (IDQ) while the Microcode Sequencer (MS) is busy. Uops maybe initiated by Decode Stream Buffer (DSB) or MITE.", + "PublicDescription": "Counts cycles during which uops are being delivered to Instruction Decode Queue (IDQ) while the Microcode Sequencer (MS) is busy. Uops maybe initiated by Decode Stream Buffer (DSB) or MITE. Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x20", "Unit": "cpu_core" @@ -438,7 +442,7 @@ "EdgeDetect": "1", "EventCode": "0x79", "EventName": "IDQ.MS_SWITCHES", - "PublicDescription": "Number of switches from DSB (Decode Stream Buffer) or MITE (legacy decode pipeline) to the Microcode Sequencer.", + "PublicDescription": "Number of switches from DSB (Decode Stream Buffer) or MITE (legacy decode pipeline) to the Microcode Sequencer. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x20", "Unit": "cpu_core" @@ -448,7 +452,7 @@ "Counter": "0,1,2,3", "EventCode": "0x79", "EventName": "IDQ.MS_UOPS", - "PublicDescription": "Counts the number of uops initiated by MITE or Decode Stream Buffer (DSB) and delivered to Instruction Decode Queue (IDQ) while the Microcode Sequencer (MS) is busy. Counting includes uops that may 'bypass' the IDQ.", + "PublicDescription": "Counts the number of uops initiated by MITE or Decode Stream Buffer (DSB) and delivered to Instruction Decode Queue (IDQ) while the Microcode Sequencer (MS) is busy. Counting includes uops that may 'bypass' the IDQ. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x20", "Unit": "cpu_core" @@ -458,7 +462,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0x9c", "EventName": "IDQ_BUBBLES.CORE", - "PublicDescription": "This event counts a subset of the Topdown Slots event that when no operation was delivered to the back-end pipeline due to instruction fetch limitations when the back-end could have accepted more operations. Common examples include instruction cache misses or x86 instruction decode limitations. The count may be distributed among unhalted logical processors (hyper-threads) who share the same physical core, in processors that support Intel Hyper-Threading Technology. Software can use this event as the numerator for the Frontend Bound metric (or top-level category) of the Top-down Microarchitecture Analysis method.", + "PublicDescription": "This event counts a subset of the Topdown Slots event that when no operation was delivered to the back-end pipeline due to instruction fetch limitations when the back-end could have accepted more operations. Common examples include instruction cache misses or x86 instruction decode limitations. The count may be distributed among unhalted logical processors (hyper-threads) who share the same physical core, in processors that support Intel Hyper-Threading Technology. Software can use this event as the numerator for the Frontend Bound metric (or top-level category) of the Top-down Microarchitecture Analysis method. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x1", "Unit": "cpu_core" @@ -469,7 +473,7 @@ "CounterMask": "6", "EventCode": "0x9c", "EventName": "IDQ_BUBBLES.CYCLES_0_UOPS_DELIV.CORE", - "PublicDescription": "Counts the number of cycles when no uops were delivered by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle. [This event is alias to IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE]", + "PublicDescription": "Counts the number of cycles when no uops were delivered by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle. [This event is alias to IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE] Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x1", "Unit": "cpu_core" @@ -481,7 +485,7 @@ "EventCode": "0x9c", "EventName": "IDQ_BUBBLES.CYCLES_FE_WAS_OK", "Invert": "1", - "PublicDescription": "Counts the number of cycles when the optimal number of uops were delivered by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle. [This event is alias to IDQ_UOPS_NOT_DELIVERED.CYCLES_FE_WAS_OK]", + "PublicDescription": "Counts the number of cycles when the optimal number of uops were delivered by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle. [This event is alias to IDQ_UOPS_NOT_DELIVERED.CYCLES_FE_WAS_OK] Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x1", "Unit": "cpu_core" @@ -491,7 +495,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0x9c", "EventName": "IDQ_UOPS_NOT_DELIVERED.CORE", - "PublicDescription": "Counts the number of uops not delivered to by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle.", + "PublicDescription": "Counts the number of uops not delivered to by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x1", "Unit": "cpu_core" @@ -502,7 +506,7 @@ "CounterMask": "6", "EventCode": "0x9c", "EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE", - "PublicDescription": "Counts the number of cycles when no uops were delivered by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle. [This event is alias to IDQ_BUBBLES.CYCLES_0_UOPS_DELIV.CORE]", + "PublicDescription": "Counts the number of cycles when no uops were delivered by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle. [This event is alias to IDQ_BUBBLES.CYCLES_0_UOPS_DELIV.CORE] Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x1", "Unit": "cpu_core" @@ -514,7 +518,7 @@ "EventCode": "0x9c", "EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_FE_WAS_OK", "Invert": "1", - "PublicDescription": "Counts the number of cycles when the optimal number of uops were delivered by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle. [This event is alias to IDQ_BUBBLES.CYCLES_FE_WAS_OK]", + "PublicDescription": "Counts the number of cycles when the optimal number of uops were delivered by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle. [This event is alias to IDQ_BUBBLES.CYCLES_FE_WAS_OK] Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x1", "Unit": "cpu_core" diff --git a/tools/perf/pmu-events/arch/x86/meteorlake/memory.json b/tools/perf/pmu-events/arch/x86/meteorlake/memory.json index e4481fbc1e13..17b94f810d5a 100644 --- a/tools/perf/pmu-events/arch/x86/meteorlake/memory.json +++ b/tools/perf/pmu-events/arch/x86/meteorlake/memory.json @@ -5,6 +5,7 @@ "CounterMask": "2", "EventCode": "0xa3", "EventName": "CYCLE_ACTIVITY.CYCLES_L3_MISS", + "PublicDescription": "Cycles while L3 cache miss demand load is outstanding. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x2", "Unit": "cpu_core" @@ -15,6 +16,7 @@ "CounterMask": "6", "EventCode": "0xa3", "EventName": "CYCLE_ACTIVITY.STALLS_L3_MISS", + "PublicDescription": "Execution stalls while L3 cache miss demand load is outstanding. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x6", "Unit": "cpu_core" @@ -88,7 +90,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc3", "EventName": "MACHINE_CLEARS.MEMORY_ORDERING", - "PublicDescription": "Counts the number of Machine Clears detected dye to memory ordering. Memory Ordering Machine Clears may apply when a memory read may not conform to the memory ordering rules of the x86 architecture", + "PublicDescription": "Counts the number of Machine Clears detected dye to memory ordering. Memory Ordering Machine Clears may apply when a memory read may not conform to the memory ordering rules of the x86 architecture Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x2", "Unit": "cpu_core" @@ -99,6 +101,7 @@ "CounterMask": "2", "EventCode": "0x47", "EventName": "MEMORY_ACTIVITY.CYCLES_L1D_MISS", + "PublicDescription": "Cycles while L1 cache miss demand load is outstanding. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x2", "Unit": "cpu_core" @@ -109,6 +112,7 @@ "CounterMask": "3", "EventCode": "0x47", "EventName": "MEMORY_ACTIVITY.STALLS_L1D_MISS", + "PublicDescription": "Execution stalls while L1 cache miss demand load is outstanding. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x3", "Unit": "cpu_core" @@ -119,7 +123,7 @@ "CounterMask": "5", "EventCode": "0x47", "EventName": "MEMORY_ACTIVITY.STALLS_L2_MISS", - "PublicDescription": "Execution stalls while L2 cache miss demand cacheable load request is outstanding (will not count for uncacheable demand requests e.g. bus lock).", + "PublicDescription": "Execution stalls while L2 cache miss demand cacheable load request is outstanding (will not count for uncacheable demand requests e.g. bus lock). Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x5", "Unit": "cpu_core" @@ -130,7 +134,7 @@ "CounterMask": "9", "EventCode": "0x47", "EventName": "MEMORY_ACTIVITY.STALLS_L3_MISS", - "PublicDescription": "Execution stalls while L3 cache miss demand cacheable load request is outstanding (will not count for uncacheable demand requests e.g. bus lock).", + "PublicDescription": "Execution stalls while L3 cache miss demand cacheable load request is outstanding (will not count for uncacheable demand requests e.g. bus lock). Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x9", "Unit": "cpu_core" @@ -143,7 +147,7 @@ "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_1024", "MSRIndex": "0x3F6", "MSRValue": "0x400", - "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 1024 cycles. Reported latency may be longer than just the memory latency.", + "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 1024 cycles. Reported latency may be longer than just the memory latency. Available PDIST counters: 0", "SampleAfterValue": "53", "UMask": "0x1", "Unit": "cpu_core" @@ -156,7 +160,7 @@ "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_128", "MSRIndex": "0x3F6", "MSRValue": "0x80", - "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 128 cycles. Reported latency may be longer than just the memory latency.", + "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 128 cycles. Reported latency may be longer than just the memory latency. Available PDIST counters: 0", "SampleAfterValue": "1009", "UMask": "0x1", "Unit": "cpu_core" @@ -169,7 +173,7 @@ "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_16", "MSRIndex": "0x3F6", "MSRValue": "0x10", - "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 16 cycles. Reported latency may be longer than just the memory latency.", + "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 16 cycles. Reported latency may be longer than just the memory latency. Available PDIST counters: 0", "SampleAfterValue": "20011", "UMask": "0x1", "Unit": "cpu_core" @@ -182,7 +186,7 @@ "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_2048", "MSRIndex": "0x3F6", "MSRValue": "0x800", - "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 2048 cycles. Reported latency may be longer than just the memory latency.", + "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 2048 cycles. Reported latency may be longer than just the memory latency. Available PDIST counters: 0", "SampleAfterValue": "23", "UMask": "0x1", "Unit": "cpu_core" @@ -195,7 +199,7 @@ "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_256", "MSRIndex": "0x3F6", "MSRValue": "0x100", - "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 256 cycles. Reported latency may be longer than just the memory latency.", + "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 256 cycles. Reported latency may be longer than just the memory latency. Available PDIST counters: 0", "SampleAfterValue": "503", "UMask": "0x1", "Unit": "cpu_core" @@ -208,7 +212,7 @@ "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_32", "MSRIndex": "0x3F6", "MSRValue": "0x20", - "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 32 cycles. Reported latency may be longer than just the memory latency.", + "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 32 cycles. Reported latency may be longer than just the memory latency. Available PDIST counters: 0", "SampleAfterValue": "100007", "UMask": "0x1", "Unit": "cpu_core" @@ -221,7 +225,7 @@ "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_4", "MSRIndex": "0x3F6", "MSRValue": "0x4", - "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 4 cycles. Reported latency may be longer than just the memory latency.", + "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 4 cycles. Reported latency may be longer than just the memory latency. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1", "Unit": "cpu_core" @@ -234,7 +238,7 @@ "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_512", "MSRIndex": "0x3F6", "MSRValue": "0x200", - "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 512 cycles. Reported latency may be longer than just the memory latency.", + "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 512 cycles. Reported latency may be longer than just the memory latency. Available PDIST counters: 0", "SampleAfterValue": "101", "UMask": "0x1", "Unit": "cpu_core" @@ -247,7 +251,7 @@ "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_64", "MSRIndex": "0x3F6", "MSRValue": "0x40", - "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 64 cycles. Reported latency may be longer than just the memory latency.", + "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 64 cycles. Reported latency may be longer than just the memory latency. Available PDIST counters: 0", "SampleAfterValue": "2003", "UMask": "0x1", "Unit": "cpu_core" @@ -260,7 +264,7 @@ "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_8", "MSRIndex": "0x3F6", "MSRValue": "0x8", - "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 8 cycles. Reported latency may be longer than just the memory latency.", + "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 8 cycles. Reported latency may be longer than just the memory latency. Available PDIST counters: 0", "SampleAfterValue": "50021", "UMask": "0x1", "Unit": "cpu_core" @@ -271,7 +275,7 @@ "Data_LA": "1", "EventCode": "0xcd", "EventName": "MEM_TRANS_RETIRED.STORE_SAMPLE", - "PublicDescription": "Counts Retired memory accesses with at least 1 store operation. This PEBS event is the precisely-distributed (PDist) trigger covering all stores uops for sampling by the PEBS Store Latency Facility. The facility is described in Intel SDM Volume 3 section 19.9.8", + "PublicDescription": "Counts Retired memory accesses with at least 1 store operation. This PEBS event is the precisely-distributed (PDist) trigger covering all stores uops for sampling by the PEBS Store Latency Facility. The facility is described in Intel SDM Volume 3 section 19.9.8 Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x2", "Unit": "cpu_core" @@ -295,23 +299,61 @@ "Unit": "cpu_atom" }, { + "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were supplied by DRAM.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xB7", + "EventName": "OCR.DEMAND_CODE_RD.DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x184000004", + "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were supplied by DRAM. Available PDIST counters: 0", + "SampleAfterValue": "100003", + "UMask": "0x1", + "Unit": "cpu_atom" + }, + { "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were not supplied by the L3 cache.", "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xB7", "EventName": "OCR.DEMAND_CODE_RD.L3_MISS", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x3FBFC00004", + "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were not supplied by the L3 cache. Available PDIST counters: 0", + "SampleAfterValue": "100003", + "UMask": "0x1", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts demand data reads that were supplied by DRAM.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xB7", + "EventName": "OCR.DEMAND_DATA_RD.DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x184000001", + "PublicDescription": "Counts demand data reads that were supplied by DRAM. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1", "Unit": "cpu_atom" }, { + "BriefDescription": "Counts demand data reads that were supplied by DRAM.", + "Counter": "0,1,2,3", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.DEMAND_DATA_RD.DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x184000001", + "PublicDescription": "Counts demand data reads that were supplied by DRAM. Available PDIST counters: 0", + "SampleAfterValue": "100003", + "UMask": "0x1", + "Unit": "cpu_core" + }, + { "BriefDescription": "Counts demand data reads that were not supplied by the L3 cache.", "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xB7", "EventName": "OCR.DEMAND_DATA_RD.L3_MISS", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x3FBFC00001", + "PublicDescription": "Counts demand data reads that were not supplied by the L3 cache. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1", "Unit": "cpu_atom" @@ -323,17 +365,31 @@ "EventName": "OCR.DEMAND_DATA_RD.L3_MISS", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x3FBFC00001", + "PublicDescription": "Counts demand data reads that were not supplied by the L3 cache. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1", "Unit": "cpu_core" }, { + "BriefDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that were supplied by DRAM.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xB7", + "EventName": "OCR.DEMAND_RFO.DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x184000002", + "PublicDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that were supplied by DRAM. Available PDIST counters: 0", + "SampleAfterValue": "100003", + "UMask": "0x1", + "Unit": "cpu_atom" + }, + { "BriefDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that were not supplied by the L3 cache.", "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xB7", "EventName": "OCR.DEMAND_RFO.L3_MISS", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x3FBFC00002", + "PublicDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that were not supplied by the L3 cache. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1", "Unit": "cpu_atom" @@ -345,6 +401,7 @@ "EventName": "OCR.DEMAND_RFO.L3_MISS", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x3FBFC00002", + "PublicDescription": "Counts demand read for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that were not supplied by the L3 cache. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1", "Unit": "cpu_core" @@ -354,6 +411,7 @@ "Counter": "0,1,2,3", "EventCode": "0x21", "EventName": "OFFCORE_REQUESTS.L3_MISS_DEMAND_DATA_RD", + "PublicDescription": "Counts demand data read requests that miss the L3 cache. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x10", "Unit": "cpu_core" @@ -364,7 +422,7 @@ "CounterMask": "1", "EventCode": "0x20", "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_L3_MISS_DEMAND_DATA_RD", - "PublicDescription": "Cycles with at least 1 Demand Data Read requests who miss L3 cache in the superQ.", + "PublicDescription": "Cycles with at least 1 Demand Data Read requests who miss L3 cache in the superQ. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x10", "Unit": "cpu_core" @@ -374,7 +432,7 @@ "Counter": "0,1,2,3", "EventCode": "0x20", "EventName": "OFFCORE_REQUESTS_OUTSTANDING.L3_MISS_DEMAND_DATA_RD", - "PublicDescription": "For every cycle, increments by the number of demand data read requests pending that are known to have missed the L3 cache. Note that this does not capture all elapsed cycles while requests are outstanding - only cycles from when the requests were known by the requesting core to have missed the L3 cache.", + "PublicDescription": "For every cycle, increments by the number of demand data read requests pending that are known to have missed the L3 cache. Note that this does not capture all elapsed cycles while requests are outstanding - only cycles from when the requests were known by the requesting core to have missed the L3 cache. Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x10", "Unit": "cpu_core" diff --git a/tools/perf/pmu-events/arch/x86/meteorlake/mtl-metrics.json b/tools/perf/pmu-events/arch/x86/meteorlake/mtl-metrics.json index 20c52630127e..0088be169f9b 100644 --- a/tools/perf/pmu-events/arch/x86/meteorlake/mtl-metrics.json +++ b/tools/perf/pmu-events/arch/x86/meteorlake/mtl-metrics.json @@ -75,7 +75,7 @@ "MetricExpr": "tma_core_bound", "MetricGroup": "TopdownL3;tma_L3_group;tma_core_bound_group", "MetricName": "tma_allocation_restriction", - "MetricThreshold": "(tma_allocation_restriction >0.10) & ((tma_core_bound >0.10) & ((tma_backend_bound >0.10)))", + "MetricThreshold": "tma_allocation_restriction > 0.1 & (tma_core_bound > 0.1 & tma_backend_bound > 0.1)", "ScaleUnit": "100%", "Unit": "cpu_atom" }, @@ -85,7 +85,7 @@ "MetricExpr": "cpu_atom@TOPDOWN_BE_BOUND.ALL_P@ / (6 * cpu_atom@CPU_CLK_UNHALTED.CORE@)", "MetricGroup": "Default;TopdownL1;tma_L1_group", "MetricName": "tma_backend_bound", - "MetricThreshold": "(tma_backend_bound >0.10)", + "MetricThreshold": "tma_backend_bound > 0.1", "MetricgroupNoGroup": "TopdownL1;Default", "PublicDescription": "Counts the total number of issue slots that were not consumed by the backend due to backend stalls. Note that uops must be available for consumption in order for this event to count. If a uop is not available (IQ is empty), this event will not count", "ScaleUnit": "100%", @@ -97,7 +97,7 @@ "MetricExpr": "cpu_atom@TOPDOWN_BAD_SPECULATION.ALL_P@ / (6 * cpu_atom@CPU_CLK_UNHALTED.CORE@)", "MetricGroup": "Default;TopdownL1;tma_L1_group", "MetricName": "tma_bad_speculation", - "MetricThreshold": "(tma_bad_speculation >0.15)", + "MetricThreshold": "tma_bad_speculation > 0.15", "MetricgroupNoGroup": "TopdownL1;Default", "PublicDescription": "Counts the total number of issue slots that were not consumed by the backend because allocation is stalled due to a mispredicted jump or a machine clear. Only issue slots wasted due to fast nukes such as memory ordering nukes are counted. Other nukes are not accounted for. Counts all issue slots blocked during this recovery window including relevant microcode flows and while uops are not yet available in the instruction queue (IQ). Also includes the issue slots that were consumed by the backend but were thrown away because they were younger than the mispredict or machine clear.", "ScaleUnit": "100%", @@ -108,7 +108,7 @@ "MetricExpr": "cpu_atom@TOPDOWN_FE_BOUND.BRANCH_DETECT@ / (6 * cpu_atom@CPU_CLK_UNHALTED.CORE@)", "MetricGroup": "TopdownL3;tma_L3_group;tma_ifetch_latency_group", "MetricName": "tma_branch_detect", - "MetricThreshold": "(tma_branch_detect >0.05) & ((tma_ifetch_latency >0.15) & ((tma_frontend_bound >0.20)))", + "MetricThreshold": "tma_branch_detect > 0.05 & (tma_ifetch_latency > 0.15 & tma_frontend_bound > 0.2)", "PublicDescription": "Counts the number of issue slots that were not delivered by the frontend due to BACLEARS, which occurs when the Branch Target Buffer (BTB) prediction or lack thereof, was corrected by a later branch predictor in the frontend. Includes BACLEARS due to all branch types including conditional and unconditional jumps, returns, and indirect branches.", "ScaleUnit": "100%", "Unit": "cpu_atom" @@ -118,7 +118,7 @@ "MetricExpr": "cpu_atom@TOPDOWN_BAD_SPECULATION.MISPREDICT@ / (6 * cpu_atom@CPU_CLK_UNHALTED.CORE@)", "MetricGroup": "TopdownL2;tma_L2_group;tma_bad_speculation_group", "MetricName": "tma_branch_mispredicts", - "MetricThreshold": "(tma_branch_mispredicts >0.05) & ((tma_bad_speculation >0.15))", + "MetricThreshold": "tma_branch_mispredicts > 0.05 & tma_bad_speculation > 0.15", "MetricgroupNoGroup": "TopdownL2", "ScaleUnit": "100%", "Unit": "cpu_atom" @@ -128,7 +128,7 @@ "MetricExpr": "cpu_atom@TOPDOWN_FE_BOUND.BRANCH_RESTEER@ / (6 * cpu_atom@CPU_CLK_UNHALTED.CORE@)", "MetricGroup": "TopdownL3;tma_L3_group;tma_ifetch_latency_group", "MetricName": "tma_branch_resteer", - "MetricThreshold": "(tma_branch_resteer >0.05) & ((tma_ifetch_latency >0.15) & ((tma_frontend_bound >0.20)))", + "MetricThreshold": "tma_branch_resteer > 0.05 & (tma_ifetch_latency > 0.15 & tma_frontend_bound > 0.2)", "ScaleUnit": "100%", "Unit": "cpu_atom" }, @@ -137,7 +137,7 @@ "MetricExpr": "cpu_atom@TOPDOWN_FE_BOUND.CISC@ / (6 * cpu_atom@CPU_CLK_UNHALTED.CORE@)", "MetricGroup": "TopdownL3;tma_L3_group;tma_ifetch_bandwidth_group", "MetricName": "tma_cisc", - "MetricThreshold": "(tma_cisc >0.05) & ((tma_ifetch_bandwidth >0.10) & ((tma_frontend_bound >0.20)))", + "MetricThreshold": "tma_cisc > 0.05 & (tma_ifetch_bandwidth > 0.1 & tma_frontend_bound > 0.2)", "ScaleUnit": "100%", "Unit": "cpu_atom" }, @@ -146,7 +146,7 @@ "MetricExpr": "cpu_atom@TOPDOWN_BE_BOUND.ALLOC_RESTRICTIONS@ / (6 * cpu_atom@CPU_CLK_UNHALTED.CORE@)", "MetricGroup": "TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_core_bound", - "MetricThreshold": "(tma_core_bound >0.10) & ((tma_backend_bound >0.10))", + "MetricThreshold": "tma_core_bound > 0.1 & tma_backend_bound > 0.1", "MetricgroupNoGroup": "TopdownL2", "ScaleUnit": "100%", "Unit": "cpu_atom" @@ -156,7 +156,7 @@ "MetricExpr": "cpu_atom@TOPDOWN_FE_BOUND.DECODE@ / (6 * cpu_atom@CPU_CLK_UNHALTED.CORE@)", "MetricGroup": "TopdownL3;tma_L3_group;tma_ifetch_bandwidth_group", "MetricName": "tma_decode", - "MetricThreshold": "(tma_decode >0.05) & ((tma_ifetch_bandwidth >0.10) & ((tma_frontend_bound >0.20)))", + "MetricThreshold": "tma_decode > 0.05 & (tma_ifetch_bandwidth > 0.1 & tma_frontend_bound > 0.2)", "ScaleUnit": "100%", "Unit": "cpu_atom" }, @@ -165,7 +165,7 @@ "MetricExpr": "cpu_atom@TOPDOWN_BAD_SPECULATION.FASTNUKE@ / (6 * cpu_atom@CPU_CLK_UNHALTED.CORE@)", "MetricGroup": "TopdownL3;tma_L3_group;tma_machine_clears_group", "MetricName": "tma_fast_nuke", - "MetricThreshold": "(tma_fast_nuke >0.05) & ((tma_machine_clears >0.05) & ((tma_bad_speculation >0.15)))", + "MetricThreshold": "tma_fast_nuke > 0.05 & (tma_machine_clears > 0.05 & tma_bad_speculation > 0.15)", "ScaleUnit": "100%", "Unit": "cpu_atom" }, @@ -175,7 +175,7 @@ "MetricExpr": "cpu_atom@TOPDOWN_FE_BOUND.ALL_P@ / (6 * cpu_atom@CPU_CLK_UNHALTED.CORE@)", "MetricGroup": "Default;TopdownL1;tma_L1_group", "MetricName": "tma_frontend_bound", - "MetricThreshold": "(tma_frontend_bound >0.20)", + "MetricThreshold": "tma_frontend_bound > 0.2", "MetricgroupNoGroup": "TopdownL1;Default", "ScaleUnit": "100%", "Unit": "cpu_atom" @@ -185,7 +185,7 @@ "MetricExpr": "cpu_atom@TOPDOWN_FE_BOUND.ICACHE@ / (6 * cpu_atom@CPU_CLK_UNHALTED.CORE@)", "MetricGroup": "TopdownL3;tma_L3_group;tma_ifetch_latency_group", "MetricName": "tma_icache_misses", - "MetricThreshold": "(tma_icache_misses >0.05) & ((tma_ifetch_latency >0.15) & ((tma_frontend_bound >0.20)))", + "MetricThreshold": "tma_icache_misses > 0.05 & (tma_ifetch_latency > 0.15 & tma_frontend_bound > 0.2)", "ScaleUnit": "100%", "Unit": "cpu_atom" }, @@ -194,7 +194,7 @@ "MetricExpr": "cpu_atom@TOPDOWN_FE_BOUND.FRONTEND_BANDWIDTH@ / (6 * cpu_atom@CPU_CLK_UNHALTED.CORE@)", "MetricGroup": "TopdownL2;tma_L2_group;tma_frontend_bound_group", "MetricName": "tma_ifetch_bandwidth", - "MetricThreshold": "(tma_ifetch_bandwidth >0.10) & ((tma_frontend_bound >0.20))", + "MetricThreshold": "tma_ifetch_bandwidth > 0.1 & tma_frontend_bound > 0.2", "MetricgroupNoGroup": "TopdownL2", "ScaleUnit": "100%", "Unit": "cpu_atom" @@ -204,7 +204,7 @@ "MetricExpr": "cpu_atom@TOPDOWN_FE_BOUND.FRONTEND_LATENCY@ / (6 * cpu_atom@CPU_CLK_UNHALTED.CORE@)", "MetricGroup": "TopdownL2;tma_L2_group;tma_frontend_bound_group", "MetricName": "tma_ifetch_latency", - "MetricThreshold": "(tma_ifetch_latency >0.15) & ((tma_frontend_bound >0.20))", + "MetricThreshold": "tma_ifetch_latency > 0.15 & tma_frontend_bound > 0.2", "MetricgroupNoGroup": "TopdownL2", "ScaleUnit": "100%", "Unit": "cpu_atom" @@ -564,7 +564,7 @@ "BriefDescription": "PerfMon Event Multiplexing accuracy indicator", "MetricExpr": "cpu_atom@CPU_CLK_UNHALTED.CORE_P@ / cpu_atom@CPU_CLK_UNHALTED.CORE@", "MetricName": "tma_info_system_mux", - "MetricThreshold": "((tma_info_system_mux > 1.1)|(tma_info_system_mux < 0.9))", + "MetricThreshold": "tma_info_system_mux > 1.1 | tma_info_system_mux < 0.9", "Unit": "cpu_atom" }, { @@ -603,7 +603,7 @@ "MetricExpr": "cpu_atom@TOPDOWN_FE_BOUND.ITLB_MISS@ / (6 * cpu_atom@CPU_CLK_UNHALTED.CORE@)", "MetricGroup": "TopdownL3;tma_L3_group;tma_ifetch_latency_group", "MetricName": "tma_itlb_misses", - "MetricThreshold": "(tma_itlb_misses >0.05) & ((tma_ifetch_latency >0.15) & ((tma_frontend_bound >0.20)))", + "MetricThreshold": "tma_itlb_misses > 0.05 & (tma_ifetch_latency > 0.15 & tma_frontend_bound > 0.2)", "ScaleUnit": "100%", "Unit": "cpu_atom" }, @@ -612,7 +612,7 @@ "MetricExpr": "cpu_atom@TOPDOWN_BAD_SPECULATION.MACHINE_CLEARS@ / (6 * cpu_atom@CPU_CLK_UNHALTED.CORE@)", "MetricGroup": "TopdownL2;tma_L2_group;tma_bad_speculation_group", "MetricName": "tma_machine_clears", - "MetricThreshold": "(tma_machine_clears >0.05) & ((tma_bad_speculation >0.15))", + "MetricThreshold": "tma_machine_clears > 0.05 & tma_bad_speculation > 0.15", "MetricgroupNoGroup": "TopdownL2", "ScaleUnit": "100%", "Unit": "cpu_atom" @@ -622,7 +622,7 @@ "MetricExpr": "cpu_atom@TOPDOWN_BE_BOUND.MEM_SCHEDULER@ / (6 * cpu_atom@CPU_CLK_UNHALTED.CORE@)", "MetricGroup": "TopdownL3;tma_L3_group;tma_resource_bound_group", "MetricName": "tma_mem_scheduler", - "MetricThreshold": "(tma_mem_scheduler >0.10) & ((tma_resource_bound >0.20) & ((tma_backend_bound >0.10)))", + "MetricThreshold": "tma_mem_scheduler > 0.1 & (tma_resource_bound > 0.2 & tma_backend_bound > 0.1)", "ScaleUnit": "100%", "Unit": "cpu_atom" }, @@ -631,7 +631,7 @@ "MetricExpr": "cpu_atom@TOPDOWN_BE_BOUND.NON_MEM_SCHEDULER@ / (6 * cpu_atom@CPU_CLK_UNHALTED.CORE@)", "MetricGroup": "TopdownL3;tma_L3_group;tma_resource_bound_group", "MetricName": "tma_non_mem_scheduler", - "MetricThreshold": "(tma_non_mem_scheduler >0.10) & ((tma_resource_bound >0.20) & ((tma_backend_bound >0.10)))", + "MetricThreshold": "tma_non_mem_scheduler > 0.1 & (tma_resource_bound > 0.2 & tma_backend_bound > 0.1)", "ScaleUnit": "100%", "Unit": "cpu_atom" }, @@ -640,7 +640,7 @@ "MetricExpr": "cpu_atom@TOPDOWN_BAD_SPECULATION.NUKE@ / (6 * cpu_atom@CPU_CLK_UNHALTED.CORE@)", "MetricGroup": "TopdownL3;tma_L3_group;tma_machine_clears_group", "MetricName": "tma_nuke", - "MetricThreshold": "(tma_nuke >0.05) & ((tma_machine_clears >0.05) & ((tma_bad_speculation >0.15)))", + "MetricThreshold": "tma_nuke > 0.05 & (tma_machine_clears > 0.05 & tma_bad_speculation > 0.15)", "ScaleUnit": "100%", "Unit": "cpu_atom" }, @@ -649,7 +649,7 @@ "MetricExpr": "cpu_atom@TOPDOWN_FE_BOUND.OTHER@ / (6 * cpu_atom@CPU_CLK_UNHALTED.CORE@)", "MetricGroup": "TopdownL3;tma_L3_group;tma_ifetch_bandwidth_group", "MetricName": "tma_other_fb", - "MetricThreshold": "(tma_other_fb >0.05) & ((tma_ifetch_bandwidth >0.10) & ((tma_frontend_bound >0.20)))", + "MetricThreshold": "tma_other_fb > 0.05 & (tma_ifetch_bandwidth > 0.1 & tma_frontend_bound > 0.2)", "ScaleUnit": "100%", "Unit": "cpu_atom" }, @@ -658,7 +658,7 @@ "MetricExpr": "cpu_atom@TOPDOWN_FE_BOUND.PREDECODE@ / (6 * cpu_atom@CPU_CLK_UNHALTED.CORE@)", "MetricGroup": "TopdownL3;tma_L3_group;tma_ifetch_bandwidth_group", "MetricName": "tma_predecode", - "MetricThreshold": "(tma_predecode >0.05) & ((tma_ifetch_bandwidth >0.10) & ((tma_frontend_bound >0.20)))", + "MetricThreshold": "tma_predecode > 0.05 & (tma_ifetch_bandwidth > 0.1 & tma_frontend_bound > 0.2)", "ScaleUnit": "100%", "Unit": "cpu_atom" }, @@ -667,7 +667,7 @@ "MetricExpr": "cpu_atom@TOPDOWN_BE_BOUND.REGISTER@ / (6 * cpu_atom@CPU_CLK_UNHALTED.CORE@)", "MetricGroup": "TopdownL3;tma_L3_group;tma_resource_bound_group", "MetricName": "tma_register", - "MetricThreshold": "(tma_register >0.10) & ((tma_resource_bound >0.20) & ((tma_backend_bound >0.10)))", + "MetricThreshold": "tma_register > 0.1 & (tma_resource_bound > 0.2 & tma_backend_bound > 0.1)", "ScaleUnit": "100%", "Unit": "cpu_atom" }, @@ -676,7 +676,7 @@ "MetricExpr": "cpu_atom@TOPDOWN_BE_BOUND.REORDER_BUFFER@ / (6 * cpu_atom@CPU_CLK_UNHALTED.CORE@)", "MetricGroup": "TopdownL3;tma_L3_group;tma_resource_bound_group", "MetricName": "tma_reorder_buffer", - "MetricThreshold": "(tma_reorder_buffer >0.10) & ((tma_resource_bound >0.20) & ((tma_backend_bound >0.10)))", + "MetricThreshold": "tma_reorder_buffer > 0.1 & (tma_resource_bound > 0.2 & tma_backend_bound > 0.1)", "ScaleUnit": "100%", "Unit": "cpu_atom" }, @@ -685,7 +685,7 @@ "MetricExpr": "tma_backend_bound - tma_core_bound", "MetricGroup": "TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_resource_bound", - "MetricThreshold": "(tma_resource_bound >0.20) & ((tma_backend_bound >0.10))", + "MetricThreshold": "tma_resource_bound > 0.2 & tma_backend_bound > 0.1", "MetricgroupNoGroup": "TopdownL2", "ScaleUnit": "100%", "Unit": "cpu_atom" @@ -696,7 +696,7 @@ "MetricExpr": "cpu_atom@TOPDOWN_RETIRING.ALL_P@ / (6 * cpu_atom@CPU_CLK_UNHALTED.CORE@)", "MetricGroup": "Default;TopdownL1;tma_L1_group", "MetricName": "tma_retiring", - "MetricThreshold": "(tma_retiring >0.75)", + "MetricThreshold": "tma_retiring > 0.75", "MetricgroupNoGroup": "TopdownL1;Default", "ScaleUnit": "100%", "Unit": "cpu_atom" @@ -706,7 +706,7 @@ "MetricExpr": "cpu_atom@TOPDOWN_BE_BOUND.SERIALIZATION@ / (6 * cpu_atom@CPU_CLK_UNHALTED.CORE@)", "MetricGroup": "TopdownL3;tma_L3_group;tma_resource_bound_group", "MetricName": "tma_serialization", - "MetricThreshold": "(tma_serialization >0.10) & ((tma_resource_bound >0.20) & ((tma_backend_bound >0.10)))", + "MetricThreshold": "tma_serialization > 0.1 & (tma_resource_bound > 0.2 & tma_backend_bound > 0.1)", "ScaleUnit": "100%", "Unit": "cpu_atom" }, @@ -718,7 +718,7 @@ "Unit": "cpu_core" }, { - "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution ports for ALU operations", + "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution ports for ALU operations.", "MetricExpr": "(cpu_core@UOPS_DISPATCHED.PORT_0@ + cpu_core@UOPS_DISPATCHED.PORT_1@ + cpu_core@UOPS_DISPATCHED.PORT_5_11@ + cpu_core@UOPS_DISPATCHED.PORT_6@) / (5 * tma_info_core_core_clks)", "MetricGroup": "TopdownL5;tma_L5_group;tma_ports_utilized_3m_group", "MetricName": "tma_alu_op_utilization", @@ -731,13 +731,13 @@ "MetricExpr": "78 * cpu_core@ASSISTS.ANY@ / tma_info_thread_slots", "MetricGroup": "BvIO;TopdownL4;tma_L4_group;tma_microcode_sequencer_group", "MetricName": "tma_assists", - "MetricThreshold": "tma_assists > 0.1 & tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1", + "MetricThreshold": "tma_assists > 0.1 & (tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1)", "PublicDescription": "This metric estimates fraction of slots the CPU retired uops delivered by the Microcode_Sequencer as a result of Assists. Assists are long sequences of uops that are required in certain corner-cases for operations that cannot be handled natively by the execution pipeline. For example; when working with very small floating point values (so-called Denormals); the FP units are not set up to perform these operations natively. Instead; a sequence of instructions to perform the computation on the Denormals is injected into the pipeline. Since these microcode sequences might be dozens of uops long; Assists can be extremely deleterious to performance and they can be avoided in many cases. Sample with: ASSISTS.ANY", "ScaleUnit": "100%", "Unit": "cpu_core" }, { - "BriefDescription": "This metric estimates fraction of slots the CPU retired uops as a result of handing SSE to AVX* or AVX* to SSE transition Assists", + "BriefDescription": "This metric estimates fraction of slots the CPU retired uops as a result of handing SSE to AVX* or AVX* to SSE transition Assists.", "MetricExpr": "63 * cpu_core@ASSISTS.SSE_AVX_MIX@ / tma_info_thread_slots", "MetricGroup": "HPC;TopdownL5;tma_L5_group;tma_assists_group", "MetricName": "tma_avx_assists", @@ -748,7 +748,7 @@ { "BriefDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend", "DefaultMetricgroupName": "TopdownL1", - "MetricExpr": "topdown\\-be\\-bound / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * slots", + "MetricExpr": "cpu_core@topdown\\-be\\-bound@ / (cpu_core@topdown\\-fe\\-bound@ + cpu_core@topdown\\-bad\\-spec@ + cpu_core@topdown\\-retiring@ + cpu_core@topdown\\-be\\-bound@) + 0 * tma_info_thread_slots", "MetricGroup": "BvOB;Default;TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_backend_bound", "MetricThreshold": "tma_backend_bound > 0.2", @@ -765,13 +765,13 @@ "MetricName": "tma_bad_speculation", "MetricThreshold": "tma_bad_speculation > 0.15", "MetricgroupNoGroup": "TopdownL1;Default", - "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example", + "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.", "ScaleUnit": "100%", "Unit": "cpu_core" }, { "BriefDescription": "Total pipeline cost of instruction fetch related bottlenecks by large code footprint programs (i-side cache; TLB and BTB misses)", - "MetricExpr": "100 * tma_fetch_latency * (tma_itlb_misses + tma_icache_misses + tma_unknown_branches) / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches)", + "MetricExpr": "100 * tma_fetch_latency * (tma_itlb_misses + tma_icache_misses + tma_unknown_branches) / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches)", "MetricGroup": "BigFootprint;BvBC;Fed;Frontend;IcMiss;MemoryTLB", "MetricName": "tma_bottleneck_big_code", "MetricThreshold": "tma_bottleneck_big_code > 20", @@ -788,16 +788,16 @@ }, { "BriefDescription": "Total pipeline cost of external Memory- or Cache-Bandwidth related bottlenecks", - "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_mem_bandwidth / (tma_mem_bandwidth + tma_mem_latency)) + tma_memory_bound * (tma_l3_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_sq_full / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_memory_bound * (tma_l1_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_fb_full / (tma_dtlb_load + tma_store_fwd_blk + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_fb_full)))", + "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_mem_bandwidth / (tma_mem_bandwidth + tma_mem_latency)) + tma_memory_bound * (tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_sq_full / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_fb_full / (tma_dtlb_load + tma_fb_full + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)))", "MetricGroup": "BvMB;Mem;MemoryBW;Offcore;tma_issueBW", "MetricName": "tma_bottleneck_cache_memory_bandwidth", "MetricThreshold": "tma_bottleneck_cache_memory_bandwidth > 20", - "PublicDescription": "Total pipeline cost of external Memory- or Cache-Bandwidth related bottlenecks. Related metrics: tma_fb_full, tma_mem_bandwidth, tma_sq_full", + "PublicDescription": "Total pipeline cost of external Memory- or Cache-Bandwidth related bottlenecks. Related metrics: tma_fb_full, tma_info_system_dram_bw_use, tma_mem_bandwidth, tma_sq_full", "Unit": "cpu_core" }, { "BriefDescription": "Total pipeline cost of external Memory- or Cache-Latency related bottlenecks", - "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_mem_latency / (tma_mem_bandwidth + tma_mem_latency)) + tma_memory_bound * (tma_l3_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_l3_hit_latency / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_memory_bound * tma_l2_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound) + tma_memory_bound * (tma_l1_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_l1_latency_dependency / (tma_dtlb_load + tma_store_fwd_blk + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_fb_full)) + tma_memory_bound * (tma_l1_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_lock_latency / (tma_dtlb_load + tma_store_fwd_blk + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_fb_full)) + tma_memory_bound * (tma_l1_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_split_loads / (tma_dtlb_load + tma_store_fwd_blk + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_fb_full)) + tma_memory_bound * (tma_store_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_split_stores / (tma_store_latency + tma_false_sharing + tma_split_stores + tma_streaming_stores + tma_dtlb_store)) + tma_memory_bound * (tma_store_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_store_latency / (tma_store_latency + tma_false_sharing + tma_split_stores + tma_streaming_stores + tma_dtlb_store)))", + "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_mem_latency / (tma_mem_bandwidth + tma_mem_latency)) + tma_memory_bound * (tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_l3_hit_latency / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_memory_bound * tma_l2_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) + tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_l1_latency_dependency / (tma_dtlb_load + tma_fb_full + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_lock_latency / (tma_dtlb_load + tma_fb_full + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_split_loads / (tma_dtlb_load + tma_fb_full + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_memory_bound * (tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_split_stores / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency + tma_streaming_stores)) + tma_memory_bound * (tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_store_latency / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency + tma_streaming_stores)))", "MetricGroup": "BvML;Mem;MemoryLat;Offcore;tma_issueLat", "MetricName": "tma_bottleneck_cache_memory_latency", "MetricThreshold": "tma_bottleneck_cache_memory_latency > 20", @@ -806,16 +806,16 @@ }, { "BriefDescription": "Total pipeline cost when the execution is compute-bound - an estimation", - "MetricExpr": "100 * (tma_core_bound * tma_divider / (tma_divider + tma_serializing_operation + tma_ports_utilization) + tma_core_bound * (tma_ports_utilization / (tma_divider + tma_serializing_operation + tma_ports_utilization)) * (tma_ports_utilized_3m / (tma_ports_utilized_0 + tma_ports_utilized_1 + tma_ports_utilized_2 + tma_ports_utilized_3m)))", + "MetricExpr": "100 * (tma_core_bound * tma_divider / (tma_divider + tma_ports_utilization + tma_serializing_operation) + tma_core_bound * (tma_ports_utilization / (tma_divider + tma_ports_utilization + tma_serializing_operation)) * (tma_ports_utilized_3m / (tma_ports_utilized_0 + tma_ports_utilized_1 + tma_ports_utilized_2 + tma_ports_utilized_3m)))", "MetricGroup": "BvCB;Cor;tma_issueComp", "MetricName": "tma_bottleneck_compute_bound_est", "MetricThreshold": "tma_bottleneck_compute_bound_est > 20", - "PublicDescription": "Total pipeline cost when the execution is compute-bound - an estimation. Covers Core Bound when High ILP as well as when long-latency execution units are busy", + "PublicDescription": "Total pipeline cost when the execution is compute-bound - an estimation. Covers Core Bound when High ILP as well as when long-latency execution units are busy. Related metrics: ", "Unit": "cpu_core" }, { "BriefDescription": "Total pipeline cost of instruction fetch bandwidth related bottlenecks (when the front-end could not sustain operations delivery to the back-end)", - "MetricExpr": "100 * (tma_frontend_bound - (1 - 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts) * tma_fetch_latency * tma_mispredicts_resteers / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches) - (1 - cpu_core@INST_RETIRED.REP_ITERATION@ / cpu_core@UOPS_RETIRED.MS\\,cmask\\=0x1@) * (tma_fetch_latency * (tma_ms_switches + tma_branch_resteers * (tma_clears_resteers + tma_mispredicts_resteers * tma_other_mispredicts / tma_branch_mispredicts) / (tma_mispredicts_resteers + tma_clears_resteers + tma_unknown_branches)) / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches) + tma_fetch_bandwidth * tma_ms / (tma_mite + tma_dsb + tma_lsd + tma_ms))) - tma_bottleneck_big_code", + "MetricExpr": "100 * (tma_frontend_bound - (1 - 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts) * tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) - (1 - cpu_core@INST_RETIRED.REP_ITERATION@ / cpu_core@UOPS_RETIRED.MS\\,cmask\\=1@) * (tma_fetch_latency * (tma_ms_switches + tma_branch_resteers * (tma_clears_resteers + tma_mispredicts_resteers * tma_other_mispredicts / tma_branch_mispredicts) / (tma_clears_resteers + tma_mispredicts_resteers + tma_unknown_branches)) / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) + tma_fetch_bandwidth * tma_ms / (tma_dsb + tma_lsd + tma_mite + tma_ms))) - tma_bottleneck_big_code", "MetricGroup": "BvFB;Fed;FetchBW;Frontend", "MetricName": "tma_bottleneck_instruction_fetch_bw", "MetricThreshold": "tma_bottleneck_instruction_fetch_bw > 20", @@ -823,7 +823,7 @@ }, { "BriefDescription": "Total pipeline cost of irregular execution (e.g", - "MetricExpr": "100 * ((1 - cpu_core@INST_RETIRED.REP_ITERATION@ / cpu_core@UOPS_RETIRED.MS\\,cmask\\=0x1@) * (tma_fetch_latency * (tma_ms_switches + tma_branch_resteers * (tma_clears_resteers + tma_mispredicts_resteers * tma_other_mispredicts / tma_branch_mispredicts) / (tma_mispredicts_resteers + tma_clears_resteers + tma_unknown_branches)) / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches) + tma_fetch_bandwidth * tma_ms / (tma_mite + tma_dsb + tma_lsd + tma_ms)) + 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts * tma_branch_mispredicts + tma_machine_clears * tma_other_nukes / tma_other_nukes + tma_core_bound * (tma_serializing_operation + cpu_core@RS.EMPTY_RESOURCE@ / tma_info_thread_clks * tma_ports_utilized_0) / (tma_divider + tma_serializing_operation + tma_ports_utilization) + tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * tma_heavy_operations)", + "MetricExpr": "100 * ((1 - cpu_core@INST_RETIRED.REP_ITERATION@ / cpu_core@UOPS_RETIRED.MS\\,cmask\\=1@) * (tma_fetch_latency * (tma_ms_switches + tma_branch_resteers * (tma_clears_resteers + tma_mispredicts_resteers * tma_other_mispredicts / tma_branch_mispredicts) / (tma_clears_resteers + tma_mispredicts_resteers + tma_unknown_branches)) / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) + tma_fetch_bandwidth * tma_ms / (tma_dsb + tma_lsd + tma_mite + tma_ms)) + 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts * tma_branch_mispredicts + tma_machine_clears * tma_other_nukes / tma_other_nukes + tma_core_bound * (tma_serializing_operation + cpu_core@RS.EMPTY_RESOURCE@ / tma_info_thread_clks * tma_ports_utilized_0) / (tma_divider + tma_ports_utilization + tma_serializing_operation) + tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * tma_heavy_operations)", "MetricGroup": "Bad;BvIO;Cor;Ret;tma_issueMS", "MetricName": "tma_bottleneck_irregular_overhead", "MetricThreshold": "tma_bottleneck_irregular_overhead > 10", @@ -832,7 +832,7 @@ }, { "BriefDescription": "Total pipeline cost of Memory Address Translation related bottlenecks (data-side TLBs)", - "MetricExpr": "100 * (tma_memory_bound * (tma_l1_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_dtlb_load / (tma_dtlb_load + tma_store_fwd_blk + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_fb_full)) + tma_memory_bound * (tma_store_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_dtlb_store / (tma_store_latency + tma_false_sharing + tma_split_stores + tma_streaming_stores + tma_dtlb_store)))", + "MetricExpr": "100 * (tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_dtlb_load / (tma_dtlb_load + tma_fb_full + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_memory_bound * (tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_dtlb_store / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency + tma_streaming_stores)))", "MetricGroup": "BvMT;Mem;MemoryTLB;Offcore;tma_issueTLB", "MetricName": "tma_bottleneck_memory_data_tlbs", "MetricThreshold": "tma_bottleneck_memory_data_tlbs > 20", @@ -841,16 +841,16 @@ }, { "BriefDescription": "Total pipeline cost of Memory Synchronization related bottlenecks (data transfers and coherency updates across processors)", - "MetricExpr": "100 * (tma_memory_bound * (tma_l3_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound) * (tma_contested_accesses + tma_data_sharing) / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full) + tma_store_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound) * tma_false_sharing / (tma_store_latency + tma_false_sharing + tma_split_stores + tma_streaming_stores + tma_dtlb_store - tma_store_latency)) + tma_machine_clears * (1 - tma_other_nukes / tma_other_nukes))", + "MetricExpr": "100 * (tma_memory_bound * (tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_contested_accesses + tma_data_sharing) / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full) + tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * tma_false_sharing / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency + tma_streaming_stores - tma_store_latency)) + tma_machine_clears * (1 - tma_other_nukes / tma_other_nukes))", "MetricGroup": "BvMS;LockCont;Mem;Offcore;tma_issueSyncxn", "MetricName": "tma_bottleneck_memory_synchronization", "MetricThreshold": "tma_bottleneck_memory_synchronization > 10", - "PublicDescription": "Total pipeline cost of Memory Synchronization related bottlenecks (data transfers and coherency updates across processors). Related metrics: tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_machine_clears", + "PublicDescription": "Total pipeline cost of Memory Synchronization related bottlenecks (data transfers and coherency updates across processors). Related metrics: tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_machine_clears, tma_remote_cache", "Unit": "cpu_core" }, { "BriefDescription": "Total pipeline cost of Branch Misprediction related bottlenecks", - "MetricExpr": "100 * (1 - 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts) * (tma_branch_mispredicts + tma_fetch_latency * tma_mispredicts_resteers / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches))", + "MetricExpr": "100 * (1 - 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts) * (tma_branch_mispredicts + tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches))", "MetricGroup": "Bad;BadSpec;BrMispredicts;BvMP;tma_issueBM", "MetricName": "tma_bottleneck_mispredictions", "MetricThreshold": "tma_bottleneck_mispredictions > 20", @@ -863,11 +863,11 @@ "MetricGroup": "BvOB;Cor;Offcore", "MetricName": "tma_bottleneck_other_bottlenecks", "MetricThreshold": "tma_bottleneck_other_bottlenecks > 20", - "PublicDescription": "Total pipeline cost of remaining bottlenecks in the back-end. Examples include data-dependencies (Core Bound when Low ILP) and other unlisted memory-related stalls", + "PublicDescription": "Total pipeline cost of remaining bottlenecks in the back-end. Examples include data-dependencies (Core Bound when Low ILP) and other unlisted memory-related stalls.", "Unit": "cpu_core" }, { - "BriefDescription": "Total pipeline cost of \"useful operations\" - the portion of Retiring category not covered by Branching_Overhead nor Irregular_Overhead", + "BriefDescription": "Total pipeline cost of \"useful operations\" - the portion of Retiring category not covered by Branching_Overhead nor Irregular_Overhead.", "MetricExpr": "100 * (tma_retiring - (cpu_core@BR_INST_RETIRED.ALL_BRANCHES@ + 2 * cpu_core@BR_INST_RETIRED.NEAR_CALL@ + cpu_core@INST_RETIRED.NOP@) / tma_info_thread_slots - tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * tma_heavy_operations)", "MetricGroup": "BvUW;Ret", "MetricName": "tma_bottleneck_useful_work", @@ -876,7 +876,7 @@ }, { "BriefDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction", - "MetricExpr": "topdown\\-br\\-mispredict / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * slots", + "MetricExpr": "cpu_core@topdown\\-br\\-mispredict@ / (cpu_core@topdown\\-fe\\-bound@ + cpu_core@topdown\\-bad\\-spec@ + cpu_core@topdown\\-retiring@ + cpu_core@topdown\\-be\\-bound@) + 0 * tma_info_thread_slots", "MetricGroup": "BadSpec;BrMispredicts;BvMP;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueBM", "MetricName": "tma_branch_mispredicts", "MetricThreshold": "tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", @@ -890,26 +890,26 @@ "MetricExpr": "cpu_core@INT_MISC.CLEAR_RESTEER_CYCLES@ / tma_info_thread_clks + tma_unknown_branches", "MetricGroup": "FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group", "MetricName": "tma_branch_resteers", - "MetricThreshold": "tma_branch_resteers > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", - "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers. Branch Resteers estimates the Frontend delay in fetching operations from corrected path; following all sorts of miss-predicted branches. For example; branchy code with lots of miss-predictions might get categorized under Branch Resteers. Note the value of this node may overlap with its siblings. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_l3_hit_latency, tma_store_latency", + "MetricThreshold": "tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers. Branch Resteers estimates the Frontend delay in fetching operations from corrected path; following all sorts of miss-predicted branches. For example; branchy code with lots of miss-predictions might get categorized under Branch Resteers. Note the value of this node may overlap with its siblings. Sample with: BR_MISP_RETIRED.ALL_BRANCHES", "ScaleUnit": "100%", "Unit": "cpu_core" }, { - "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due staying in C0.1 power-performance optimized state (Faster wakeup time; Smaller power savings)", + "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due staying in C0.1 power-performance optimized state (Faster wakeup time; Smaller power savings).", "MetricExpr": "cpu_core@CPU_CLK_UNHALTED.C01@ / tma_info_thread_clks", "MetricGroup": "C0Wait;TopdownL4;tma_L4_group;tma_serializing_operation_group", "MetricName": "tma_c01_wait", - "MetricThreshold": "tma_c01_wait > 0.05 & tma_serializing_operation > 0.1 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_c01_wait > 0.05 & (tma_serializing_operation > 0.1 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", "ScaleUnit": "100%", "Unit": "cpu_core" }, { - "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due staying in C0.2 power-performance optimized state (Slower wakeup time; Larger power savings)", + "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due staying in C0.2 power-performance optimized state (Slower wakeup time; Larger power savings).", "MetricExpr": "cpu_core@CPU_CLK_UNHALTED.C02@ / tma_info_thread_clks", "MetricGroup": "C0Wait;TopdownL4;tma_L4_group;tma_serializing_operation_group", "MetricName": "tma_c02_wait", - "MetricThreshold": "tma_c02_wait > 0.05 & tma_serializing_operation > 0.1 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_c02_wait > 0.05 & (tma_serializing_operation > 0.1 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -918,7 +918,7 @@ "MetricExpr": "max(0, tma_microcode_sequencer - tma_assists)", "MetricGroup": "TopdownL4;tma_L4_group;tma_microcode_sequencer_group", "MetricName": "tma_cisc", - "MetricThreshold": "tma_cisc > 0.1 & tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1", + "MetricThreshold": "tma_cisc > 0.1 & (tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1)", "PublicDescription": "This metric estimates fraction of cycles the CPU retired uops originated from CISC (complex instruction set computer) instruction. A CISC instruction has multiple uops that are required to perform the instruction's functionality as in the case of read-modify-write as an example. Since these instructions require multiple uops they may or may not imply sub-optimal use of machine resources. Sample with: FRONTEND_RETIRED.MS_FLOWS", "ScaleUnit": "100%", "Unit": "cpu_core" @@ -928,90 +928,91 @@ "MetricExpr": "(1 - tma_branch_mispredicts / tma_bad_speculation) * cpu_core@INT_MISC.CLEAR_RESTEER_CYCLES@ / tma_info_thread_clks", "MetricGroup": "BadSpec;MachineClears;TopdownL4;tma_L4_group;tma_branch_resteers_group;tma_issueMC", "MetricName": "tma_clears_resteers", - "MetricThreshold": "tma_clears_resteers > 0.05 & tma_branch_resteers > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricThreshold": "tma_clears_resteers > 0.05 & (tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))", "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Machine Clears. Sample with: INT_MISC.CLEAR_RESTEER_CYCLES. Related metrics: tma_l1_bound, tma_machine_clears, tma_microcode_sequencer, tma_ms_switches", "ScaleUnit": "100%", "Unit": "cpu_core" }, { - "BriefDescription": "This metric estimates fraction of cycles the CPU was stalled due to instruction cache misses that hit in the L2 cache", - "MetricExpr": "max(0, cpu_core@FRONTEND_RETIRED.L1I_MISS@ * cpu_core@frontend_retired.l1i_miss@R / tma_info_thread_clks - tma_code_l2_miss)", + "BriefDescription": "This metric estimates fraction of cycles the CPU was stalled due to instruction cache misses that hit in the L2 cache.", + "MetricExpr": "max(0, cpu_core@FRONTEND_RETIRED.L1I_MISS@ * cpu_core@FRONTEND_RETIRED.L1I_MISS@R / tma_info_thread_clks - tma_code_l2_miss)", "MetricGroup": "FetchLat;IcMiss;Offcore;TopdownL4;tma_L4_group;tma_icache_misses_group", "MetricName": "tma_code_l2_hit", - "MetricThreshold": "tma_code_l2_hit > 0.05 & tma_icache_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricThreshold": "tma_code_l2_hit > 0.05 & (tma_icache_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))", "ScaleUnit": "100%", "Unit": "cpu_core" }, { - "BriefDescription": "This metric estimates fraction of cycles the CPU was stalled due to instruction cache misses that miss in the L2 cache", - "MetricExpr": "cpu_core@FRONTEND_RETIRED.L2_MISS@ * cpu_core@frontend_retired.l2_miss@R / tma_info_thread_clks", + "BriefDescription": "This metric estimates fraction of cycles the CPU was stalled due to instruction cache misses that miss in the L2 cache.", + "MetricExpr": "cpu_core@FRONTEND_RETIRED.L2_MISS@ * cpu_core@FRONTEND_RETIRED.L2_MISS@R / tma_info_thread_clks", "MetricGroup": "FetchLat;IcMiss;Offcore;TopdownL4;tma_L4_group;tma_icache_misses_group", "MetricName": "tma_code_l2_miss", - "MetricThreshold": "tma_code_l2_miss > 0.05 & tma_icache_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricThreshold": "tma_code_l2_miss > 0.05 & (tma_icache_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))", "ScaleUnit": "100%", "Unit": "cpu_core" }, { "BriefDescription": "This metric roughly estimates the fraction of cycles where the (first level) ITLB was missed by instructions fetches, that later on hit in second-level TLB (STLB)", - "MetricExpr": "max(0, cpu_core@FRONTEND_RETIRED.ITLB_MISS@ * cpu_core@frontend_retired.itlb_miss@R / tma_info_thread_clks - tma_code_stlb_miss)", + "MetricExpr": "max(0, cpu_core@FRONTEND_RETIRED.ITLB_MISS@ * cpu_core@FRONTEND_RETIRED.ITLB_MISS@R / tma_info_thread_clks - tma_code_stlb_miss)", "MetricGroup": "FetchLat;MemoryTLB;TopdownL4;tma_L4_group;tma_itlb_misses_group", "MetricName": "tma_code_stlb_hit", - "MetricThreshold": "tma_code_stlb_hit > 0.05 & tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricThreshold": "tma_code_stlb_hit > 0.05 & (tma_itlb_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))", "ScaleUnit": "100%", "Unit": "cpu_core" }, { "BriefDescription": "This metric estimates the fraction of cycles where the Second-level TLB (STLB) was missed by instruction fetches, performing a hardware page walk", - "MetricExpr": "cpu_core@FRONTEND_RETIRED.STLB_MISS@ * cpu_core@frontend_retired.stlb_miss@R / tma_info_thread_clks", + "MetricExpr": "cpu_core@FRONTEND_RETIRED.STLB_MISS@ * cpu_core@FRONTEND_RETIRED.STLB_MISS@R / tma_info_thread_clks", "MetricGroup": "FetchLat;MemoryTLB;TopdownL4;tma_L4_group;tma_itlb_misses_group", "MetricName": "tma_code_stlb_miss", - "MetricThreshold": "tma_code_stlb_miss > 0.05 & tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricThreshold": "tma_code_stlb_miss > 0.05 & (tma_itlb_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))", "ScaleUnit": "100%", "Unit": "cpu_core" }, { - "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 2 or 4 MB pages for (instruction) code accesses", + "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 2 or 4 MB pages for (instruction) code accesses.", "MetricExpr": "cpu_core@ITLB_MISSES.WALK_ACTIVE@ / tma_info_thread_clks * cpu_core@ITLB_MISSES.WALK_COMPLETED_2M_4M@ / (cpu_core@ITLB_MISSES.WALK_COMPLETED_4K@ + cpu_core@ITLB_MISSES.WALK_COMPLETED_2M_4M@)", "MetricGroup": "FetchLat;MemoryTLB;TopdownL5;tma_L5_group;tma_code_stlb_miss_group", "MetricName": "tma_code_stlb_miss_2m", - "MetricThreshold": "tma_code_stlb_miss_2m > 0.05 & tma_code_stlb_miss > 0.05 & tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricThreshold": "tma_code_stlb_miss_2m > 0.05 & (tma_code_stlb_miss > 0.05 & (tma_itlb_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)))", "ScaleUnit": "100%", "Unit": "cpu_core" }, { - "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 4 KB pages for (instruction) code accesses", + "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 4 KB pages for (instruction) code accesses.", "MetricExpr": "cpu_core@ITLB_MISSES.WALK_ACTIVE@ / tma_info_thread_clks * cpu_core@ITLB_MISSES.WALK_COMPLETED_4K@ / (cpu_core@ITLB_MISSES.WALK_COMPLETED_4K@ + cpu_core@ITLB_MISSES.WALK_COMPLETED_2M_4M@)", "MetricGroup": "FetchLat;MemoryTLB;TopdownL5;tma_L5_group;tma_code_stlb_miss_group", "MetricName": "tma_code_stlb_miss_4k", - "MetricThreshold": "tma_code_stlb_miss_4k > 0.05 & tma_code_stlb_miss > 0.05 & tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricThreshold": "tma_code_stlb_miss_4k > 0.05 & (tma_code_stlb_miss > 0.05 & (tma_itlb_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)))", "ScaleUnit": "100%", "Unit": "cpu_core" }, { - "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to retired misprediction by non-taken conditional branches", - "MetricExpr": "cpu_core@BR_MISP_RETIRED.COND_NTAKEN_COST@ * cpu_core@br_misp_retired.cond_ntaken_cost@R / tma_info_thread_clks", + "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to retired misprediction by non-taken conditional branches.", + "MetricExpr": "cpu_core@BR_MISP_RETIRED.COND_NTAKEN_COST@ * cpu_core@BR_MISP_RETIRED.COND_NTAKEN_COST@R / tma_info_thread_clks", "MetricGroup": "BrMispredicts;TopdownL3;tma_L3_group;tma_branch_mispredicts_group", "MetricName": "tma_cond_nt_mispredicts", - "MetricThreshold": "tma_cond_nt_mispredicts > 0.05 & tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", + "MetricThreshold": "tma_cond_nt_mispredicts > 0.05 & (tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15)", "ScaleUnit": "100%", "Unit": "cpu_core" }, { - "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to misprediction by taken conditional branches", - "MetricExpr": "cpu_core@BR_MISP_RETIRED.COND_TAKEN_COST@ * cpu_core@br_misp_retired.cond_taken_cost@R / tma_info_thread_clks", + "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to misprediction by taken conditional branches.", + "MetricExpr": "cpu_core@BR_MISP_RETIRED.COND_TAKEN_COST@ * cpu_core@BR_MISP_RETIRED.COND_TAKEN_COST@R / tma_info_thread_clks", "MetricGroup": "BrMispredicts;TopdownL3;tma_L3_group;tma_branch_mispredicts_group", "MetricName": "tma_cond_tk_mispredicts", - "MetricThreshold": "tma_cond_tk_mispredicts > 0.05 & tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", + "MetricThreshold": "tma_cond_tk_mispredicts > 0.05 & (tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15)", "ScaleUnit": "100%", "Unit": "cpu_core" }, { "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses", - "MetricExpr": "((min(cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS@ * cpu_core@mem_load_l3_hit_retired.xsnp_miss@R, cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS@ * (27 * tma_info_system_core_frequency) - 3 * tma_info_system_core_frequency) if 0 < cpu_core@mem_load_l3_hit_retired.xsnp_miss@R else cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS@ * (27 * tma_info_system_core_frequency) - 3 * tma_info_system_core_frequency) + (min(cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD@ * cpu_core@mem_load_l3_hit_retired.xsnp_fwd@R, cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD@ * (28 * tma_info_system_core_frequency) - 3 * tma_info_system_core_frequency) if 0 < cpu_core@mem_load_l3_hit_retired.xsnp_fwd@R else cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD@ * (28 * tma_info_system_core_frequency) - 3 * tma_info_system_core_frequency) * (cpu_core@OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM@ / (cpu_core@OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM@ + cpu_core@OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD@))) * (1 + cpu_core@MEM_LOAD_RETIRED.FB_HIT@ / cpu_core@MEM_LOAD_RETIRED.L1_MISS@ / 2) / tma_info_thread_clks", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "(cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS@ * min(cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS@R, 24 * tma_info_system_core_frequency) + cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD@ * min(cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD@R, 25 * tma_info_system_core_frequency) * (cpu_core@OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM@ / (cpu_core@OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM@ + cpu_core@OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD@))) * (1 + cpu_core@MEM_LOAD_RETIRED.FB_HIT@ / cpu_core@MEM_LOAD_RETIRED.L1_MISS@ / 2) / tma_info_thread_clks", "MetricGroup": "BvMS;DataSharing;LockCont;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group", "MetricName": "tma_contested_accesses", - "MetricThreshold": "tma_contested_accesses > 0.05 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", - "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses. Contested accesses occur when data written by one Logical Processor are read by another Logical Processor on a different Physical Core. Examples of contested accesses include synchronizations such as locks; true data sharing such as modified locked variables; and false sharing. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD, MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS. Related metrics: tma_bottleneck_memory_synchronization, tma_data_sharing, tma_false_sharing, tma_machine_clears", + "MetricThreshold": "tma_contested_accesses > 0.05 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses. Contested accesses occur when data written by one Logical Processor are read by another Logical Processor on a different Physical Core. Examples of contested accesses include synchronizations such as locks; true data sharing such as modified locked variables; and false sharing. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD;MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS. Related metrics: tma_bottleneck_memory_synchronization, tma_data_sharing, tma_false_sharing, tma_machine_clears, tma_remote_cache", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -1022,26 +1023,27 @@ "MetricName": "tma_core_bound", "MetricThreshold": "tma_core_bound > 0.1 & tma_backend_bound > 0.2", "MetricgroupNoGroup": "TopdownL2", - "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck. Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations)", + "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck. Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations).", "ScaleUnit": "100%", "Unit": "cpu_core" }, { "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses", - "MetricExpr": "((min(cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_NO_FWD@ * cpu_core@mem_load_l3_hit_retired.xsnp_no_fwd@R, cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_NO_FWD@ * (27 * tma_info_system_core_frequency) - 3 * tma_info_system_core_frequency) if 0 < cpu_core@mem_load_l3_hit_retired.xsnp_no_fwd@R else cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_NO_FWD@ * (27 * tma_info_system_core_frequency) - 3 * tma_info_system_core_frequency) + (min(cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD@ * cpu_core@mem_load_l3_hit_retired.xsnp_fwd@R, cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD@ * (27 * tma_info_system_core_frequency) - 3 * tma_info_system_core_frequency) if 0 < cpu_core@mem_load_l3_hit_retired.xsnp_fwd@R else cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD@ * (27 * tma_info_system_core_frequency) - 3 * tma_info_system_core_frequency) * (1 - cpu_core@OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM@ / (cpu_core@OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM@ + cpu_core@OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD@))) * (1 + cpu_core@MEM_LOAD_RETIRED.FB_HIT@ / cpu_core@MEM_LOAD_RETIRED.L1_MISS@ / 2) / tma_info_thread_clks", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "(cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_NO_FWD@ * min(cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_NO_FWD@R, 24 * tma_info_system_core_frequency) + cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD@ * min(cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD@R, 24 * tma_info_system_core_frequency) * (1 - cpu_core@OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM@ / (cpu_core@OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM@ + cpu_core@OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD@))) * (1 + cpu_core@MEM_LOAD_RETIRED.FB_HIT@ / cpu_core@MEM_LOAD_RETIRED.L1_MISS@ / 2) / tma_info_thread_clks", "MetricGroup": "BvMS;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group", "MetricName": "tma_data_sharing", - "MetricThreshold": "tma_data_sharing > 0.05 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", - "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses. Data shared by multiple Logical Processors (even just read shared) may cause increased access latency due to cache coherency. Excessive data sharing can drastically harm multithreaded performance. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_NO_FWD. Related metrics: tma_bottleneck_memory_synchronization, tma_contested_accesses, tma_false_sharing, tma_machine_clears", + "MetricThreshold": "tma_data_sharing > 0.05 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses. Data shared by multiple Logical Processors (even just read shared) may cause increased access latency due to cache coherency. Excessive data sharing can drastically harm multithreaded performance. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_NO_FWD. Related metrics: tma_bottleneck_memory_synchronization, tma_contested_accesses, tma_false_sharing, tma_machine_clears, tma_remote_cache", "ScaleUnit": "100%", "Unit": "cpu_core" }, { "BriefDescription": "This metric represents fraction of cycles where decoder-0 was the only active decoder", - "MetricExpr": "(cpu_core@INST_DECODED.DECODERS\\,cmask\\=0x1@ - cpu_core@INST_DECODED.DECODERS\\,cmask\\=0x2@) / tma_info_core_core_clks / 2", + "MetricExpr": "(cpu_core@INST_DECODED.DECODERS\\,cmask\\=1@ - cpu_core@INST_DECODED.DECODERS\\,cmask\\=2@) / tma_info_core_core_clks / 2", "MetricGroup": "DSBmiss;FetchBW;TopdownL4;tma_L4_group;tma_issueD0;tma_mite_group", "MetricName": "tma_decoder0_alone", - "MetricThreshold": "tma_decoder0_alone > 0.1 & tma_mite > 0.1 & tma_fetch_bandwidth > 0.2", + "MetricThreshold": "tma_decoder0_alone > 0.1 & (tma_mite > 0.1 & tma_fetch_bandwidth > 0.2)", "PublicDescription": "This metric represents fraction of cycles where decoder-0 was the only active decoder. Related metrics: tma_few_uops_instructions", "ScaleUnit": "100%", "Unit": "cpu_core" @@ -1051,7 +1053,7 @@ "MetricExpr": "cpu_core@ARITH.DIV_ACTIVE@ / tma_info_thread_clks", "MetricGroup": "BvCB;TopdownL3;tma_L3_group;tma_core_bound_group", "MetricName": "tma_divider", - "MetricThreshold": "tma_divider > 0.2 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_divider > 0.2 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)", "PublicDescription": "This metric represents fraction of cycles where the Divider unit was active. Divide and square root instructions are performed by the Divider unit and can take considerably longer latency than integer or Floating Point addition; subtraction; or multiplication. Sample with: ARITH.DIV_ACTIVE", "ScaleUnit": "100%", "Unit": "cpu_core" @@ -1061,7 +1063,7 @@ "MetricExpr": "cpu_core@MEMORY_ACTIVITY.STALLS_L3_MISS@ / tma_info_thread_clks", "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_dram_bound", - "MetricThreshold": "tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", "PublicDescription": "This metric estimates how often the CPU was stalled on accesses to external memory (DRAM) by loads. Better caching can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L3_MISS", "ScaleUnit": "100%", "Unit": "cpu_core" @@ -1072,7 +1074,7 @@ "MetricGroup": "DSB;FetchBW;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group", "MetricName": "tma_dsb", "MetricThreshold": "tma_dsb > 0.15 & tma_fetch_bandwidth > 0.2", - "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to DSB (decoded uop cache) fetch pipeline. For example; inefficient utilization of the DSB cache structure or bank conflict when reading from it; are categorized here", + "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to DSB (decoded uop cache) fetch pipeline. For example; inefficient utilization of the DSB cache structure or bank conflict when reading from it; are categorized here.", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -1081,28 +1083,28 @@ "MetricExpr": "cpu_core@DSB2MITE_SWITCHES.PENALTY_CYCLES@ / tma_info_thread_clks", "MetricGroup": "DSBmiss;FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueFB", "MetricName": "tma_dsb_switches", - "MetricThreshold": "tma_dsb_switches > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", - "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines. The DSB (decoded i-cache) is a Uop Cache where the front-end directly delivers Uops (micro operations) avoiding heavy x86 decoding. The DSB pipeline has shorter latency and delivered higher bandwidth than the MITE (legacy instruction decode pipeline). Switching between the two pipelines can cause penalties hence this metric measures the exposed penalty. Sample with: FRONTEND_RETIRED.DSB_MISS. Related metrics: tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp", + "MetricThreshold": "tma_dsb_switches > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines. The DSB (decoded i-cache) is a Uop Cache where the front-end directly delivers Uops (micro operations) avoiding heavy x86 decoding. The DSB pipeline has shorter latency and delivered higher bandwidth than the MITE (legacy instruction decode pipeline). Switching between the two pipelines can cause penalties hence this metric measures the exposed penalty. Sample with: FRONTEND_RETIRED.DSB_MISS_PS. Related metrics: tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp", "ScaleUnit": "100%", "Unit": "cpu_core" }, { "BriefDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses", - "MetricExpr": "(min(cpu_core@MEM_INST_RETIRED.STLB_HIT_LOADS@ * cpu_core@mem_inst_retired.stlb_hit_loads@R, cpu_core@MEM_INST_RETIRED.STLB_HIT_LOADS@ * 7) if 0 < cpu_core@mem_inst_retired.stlb_hit_loads@R else cpu_core@MEM_INST_RETIRED.STLB_HIT_LOADS@ * 7) / tma_info_thread_clks + tma_load_stlb_miss", + "MetricExpr": "cpu_core@MEM_INST_RETIRED.STLB_HIT_LOADS@ * min(cpu_core@MEM_INST_RETIRED.STLB_HIT_LOADS@R, 7) / tma_info_thread_clks + tma_load_stlb_miss", "MetricGroup": "BvMT;MemoryTLB;TopdownL4;tma_L4_group;tma_issueTLB;tma_l1_bound_group", "MetricName": "tma_dtlb_load", - "MetricThreshold": "tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", - "PublicDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses. TLBs (Translation Look-aside Buffers) are processor caches for recently used entries out of the Page Tables that are used to map virtual- to physical-addresses by the operating system. This metric approximates the potential delay of demand loads missing the first-level data TLB (assuming worst case scenario with back to back misses to different pages). This includes hitting in the second-level TLB (STLB) as well as performing a hardware page walk on an STLB miss. Sample with: MEM_INST_RETIRED.STLB_MISS_LOADS. Related metrics: tma_bottleneck_memory_data_tlbs, tma_dtlb_store", + "MetricThreshold": "tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses. TLBs (Translation Look-aside Buffers) are processor caches for recently used entries out of the Page Tables that are used to map virtual- to physical-addresses by the operating system. This metric approximates the potential delay of demand loads missing the first-level data TLB (assuming worst case scenario with back to back misses to different pages). This includes hitting in the second-level TLB (STLB) as well as performing a hardware page walk on an STLB miss. Sample with: MEM_INST_RETIRED.STLB_MISS_LOADS_PS. Related metrics: tma_bottleneck_memory_data_tlbs, tma_dtlb_store", "ScaleUnit": "100%", "Unit": "cpu_core" }, { "BriefDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses", - "MetricExpr": "(min(cpu_core@MEM_INST_RETIRED.STLB_HIT_STORES@ * cpu_core@mem_inst_retired.stlb_hit_stores@R, cpu_core@MEM_INST_RETIRED.STLB_HIT_STORES@ * 7) if 0 < cpu_core@mem_inst_retired.stlb_hit_stores@R else cpu_core@MEM_INST_RETIRED.STLB_HIT_STORES@ * 7) / tma_info_thread_clks + tma_store_stlb_miss", + "MetricExpr": "cpu_core@MEM_INST_RETIRED.STLB_HIT_STORES@ * min(cpu_core@MEM_INST_RETIRED.STLB_HIT_STORES@R, 7) / tma_info_thread_clks + tma_store_stlb_miss", "MetricGroup": "BvMT;MemoryTLB;TopdownL4;tma_L4_group;tma_issueTLB;tma_store_bound_group", "MetricName": "tma_dtlb_store", - "MetricThreshold": "tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", - "PublicDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses. As with ordinary data caching; focus on improving data locality and reducing working-set size to reduce DTLB overhead. Additionally; consider using profile-guided optimization (PGO) to collocate frequently-used data on the same page. Try using larger page sizes for large amounts of frequently-used data. Sample with: MEM_INST_RETIRED.STLB_MISS_STORES. Related metrics: tma_bottleneck_memory_data_tlbs, tma_dtlb_load", + "MetricThreshold": "tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses. As with ordinary data caching; focus on improving data locality and reducing working-set size to reduce DTLB overhead. Additionally; consider using profile-guided optimization (PGO) to collocate frequently-used data on the same page. Try using larger page sizes for large amounts of frequently-used data. Sample with: MEM_INST_RETIRED.STLB_MISS_STORES_PS. Related metrics: tma_bottleneck_memory_data_tlbs, tma_dtlb_load", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -1111,8 +1113,8 @@ "MetricExpr": "28 * tma_info_system_core_frequency * cpu_core@OCR.DEMAND_RFO.L3_HIT.SNOOP_HITM@ / tma_info_thread_clks", "MetricGroup": "BvMS;DataSharing;LockCont;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_store_bound_group", "MetricName": "tma_false_sharing", - "MetricThreshold": "tma_false_sharing > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", - "PublicDescription": "This metric roughly estimates how often CPU was handling synchronizations due to False Sharing. False Sharing is a multithreading hiccup; where multiple Logical Processors contend on different data-elements mapped into the same cache line. Sample with: OCR.DEMAND_RFO.L3_HIT.SNOOP_HITM. Related metrics: tma_bottleneck_memory_synchronization, tma_contested_accesses, tma_data_sharing, tma_machine_clears", + "MetricThreshold": "tma_false_sharing > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric roughly estimates how often CPU was handling synchronizations due to False Sharing. False Sharing is a multithreading hiccup; where multiple Logical Processors contend on different data-elements mapped into the same cache line. Sample with: OCR.DEMAND_RFO.L3_HIT.SNOOP_HITM. Related metrics: tma_bottleneck_memory_synchronization, tma_contested_accesses, tma_data_sharing, tma_machine_clears, tma_remote_cache", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -1122,7 +1124,7 @@ "MetricGroup": "BvMB;MemoryBW;TopdownL4;tma_L4_group;tma_issueBW;tma_issueSL;tma_issueSmSt;tma_l1_bound_group", "MetricName": "tma_fb_full", "MetricThreshold": "tma_fb_full > 0.3", - "PublicDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed. The higher the metric value; the deeper the memory hierarchy level the misses are satisfied from (metric values >1 are valid). Often it hints on approaching bandwidth limits (to L2 cache; L3 cache or external memory). Related metrics: tma_bottleneck_cache_memory_bandwidth, tma_mem_bandwidth, tma_sq_full, tma_store_latency, tma_streaming_stores", + "PublicDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed. The higher the metric value; the deeper the memory hierarchy level the misses are satisfied from (metric values >1 are valid). Often it hints on approaching bandwidth limits (to L2 cache; L3 cache or external memory). Related metrics: tma_bottleneck_cache_memory_bandwidth, tma_info_system_dram_bw_use, tma_mem_bandwidth, tma_sq_full, tma_store_latency, tma_streaming_stores", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -1133,18 +1135,18 @@ "MetricName": "tma_fetch_bandwidth", "MetricThreshold": "tma_fetch_bandwidth > 0.2", "MetricgroupNoGroup": "TopdownL2", - "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues. For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Sample with: FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1, FRONTEND_RETIRED.LATENCY_GE_1, FRONTEND_RETIRED.LATENCY_GE_2. Related metrics: tma_dsb_switches, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp", + "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues. For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Sample with: FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1;FRONTEND_RETIRED.LATENCY_GE_1;FRONTEND_RETIRED.LATENCY_GE_2. Related metrics: tma_dsb_switches, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp", "ScaleUnit": "100%", "Unit": "cpu_core" }, { "BriefDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues", - "MetricExpr": "topdown\\-fetch\\-lat / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) - cpu_core@INT_MISC.UOP_DROPPING@ / tma_info_thread_slots", + "MetricExpr": "cpu_core@topdown\\-fetch\\-lat@ / (cpu_core@topdown\\-fe\\-bound@ + cpu_core@topdown\\-bad\\-spec@ + cpu_core@topdown\\-retiring@ + cpu_core@topdown\\-be\\-bound@) - cpu_core@INT_MISC.UOP_DROPPING@ / tma_info_thread_slots", "MetricGroup": "Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group", "MetricName": "tma_fetch_latency", "MetricThreshold": "tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", "MetricgroupNoGroup": "TopdownL2", - "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues. For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: FRONTEND_RETIRED.LATENCY_GE_16, FRONTEND_RETIRED.LATENCY_GE_8", + "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues. For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: FRONTEND_RETIRED.LATENCY_GE_16_PS;FRONTEND_RETIRED.LATENCY_GE_8_PS", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -1164,7 +1166,7 @@ "MetricGroup": "HPC;TopdownL3;tma_L3_group;tma_light_operations_group", "MetricName": "tma_fp_arith", "MetricThreshold": "tma_fp_arith > 0.2 & tma_light_operations > 0.6", - "PublicDescription": "This metric represents overall arithmetic floating-point (FP) operations fraction the CPU has executed (retired). Note this metric's value may exceed its parent due to use of \"Uops\" CountDomain and FMA double-counting", + "PublicDescription": "This metric represents overall arithmetic floating-point (FP) operations fraction the CPU has executed (retired). Note this metric's value may exceed its parent due to use of \"Uops\" CountDomain and FMA double-counting.", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -1174,16 +1176,16 @@ "MetricGroup": "HPC;TopdownL5;tma_L5_group;tma_assists_group", "MetricName": "tma_fp_assists", "MetricThreshold": "tma_fp_assists > 0.1", - "PublicDescription": "This metric roughly estimates fraction of slots the CPU retired uops as a result of handing Floating Point (FP) Assists. FP Assist may apply when working with very small floating point values (so-called Denormals)", + "PublicDescription": "This metric roughly estimates fraction of slots the CPU retired uops as a result of handing Floating Point (FP) Assists. FP Assist may apply when working with very small floating point values (so-called Denormals).", "ScaleUnit": "100%", "Unit": "cpu_core" }, { - "BriefDescription": "This metric represents fraction of cycles where the Floating-Point Divider unit was active", + "BriefDescription": "This metric represents fraction of cycles where the Floating-Point Divider unit was active.", "MetricExpr": "cpu_core@ARITH.FPDIV_ACTIVE@ / tma_info_thread_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_divider_group", "MetricName": "tma_fp_divider", - "MetricThreshold": "tma_fp_divider > 0.2 & tma_divider > 0.2 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_fp_divider > 0.2 & (tma_divider > 0.2 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -1192,8 +1194,8 @@ "MetricExpr": "cpu_core@FP_ARITH_INST_RETIRED.SCALAR@ / (tma_retiring * tma_info_thread_slots)", "MetricGroup": "Compute;Flops;TopdownL4;tma_L4_group;tma_fp_arith_group;tma_issue2P", "MetricName": "tma_fp_scalar", - "MetricThreshold": "tma_fp_scalar > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6", - "PublicDescription": "This metric approximates arithmetic floating-point (FP) scalar uops fraction the CPU has retired. May overcount due to FMA double counting. Related metrics: tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_6, tma_ports_utilized_2", + "MetricThreshold": "tma_fp_scalar > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6)", + "PublicDescription": "This metric approximates arithmetic floating-point (FP) scalar uops fraction the CPU has retired. May overcount due to FMA double counting. Related metrics: tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -1202,8 +1204,8 @@ "MetricExpr": "cpu_core@FP_ARITH_INST_RETIRED.VECTOR@ / (tma_retiring * tma_info_thread_slots)", "MetricGroup": "Compute;Flops;TopdownL4;tma_L4_group;tma_fp_arith_group;tma_issue2P", "MetricName": "tma_fp_vector", - "MetricThreshold": "tma_fp_vector > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6", - "PublicDescription": "This metric approximates arithmetic floating-point (FP) vector uops fraction the CPU has retired aggregated across all vector widths. May overcount due to FMA double counting. Related metrics: tma_fp_scalar, tma_fp_vector_128b, tma_fp_vector_256b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_6, tma_ports_utilized_2", + "MetricThreshold": "tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6)", + "PublicDescription": "This metric approximates arithmetic floating-point (FP) vector uops fraction the CPU has retired aggregated across all vector widths. May overcount due to FMA double counting. Related metrics: tma_fp_scalar, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -1212,8 +1214,8 @@ "MetricExpr": "(cpu_core@FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE@ + cpu_core@FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE@) / (tma_retiring * tma_info_thread_slots)", "MetricGroup": "Compute;Flops;TopdownL5;tma_L5_group;tma_fp_vector_group;tma_issue2P", "MetricName": "tma_fp_vector_128b", - "MetricThreshold": "tma_fp_vector_128b > 0.1 & tma_fp_vector > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6", - "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 128-bit wide vectors. May overcount due to FMA double counting prior to LNL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_256b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_6, tma_ports_utilized_2", + "MetricThreshold": "tma_fp_vector_128b > 0.1 & (tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6))", + "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 128-bit wide vectors. May overcount due to FMA double counting prior to LNL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -1222,41 +1224,41 @@ "MetricExpr": "(cpu_core@FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE@ + cpu_core@FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE@) / (tma_retiring * tma_info_thread_slots)", "MetricGroup": "Compute;Flops;TopdownL5;tma_L5_group;tma_fp_vector_group;tma_issue2P", "MetricName": "tma_fp_vector_256b", - "MetricThreshold": "tma_fp_vector_256b > 0.1 & tma_fp_vector > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6", - "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 256-bit wide vectors. May overcount due to FMA double counting prior to LNL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_6, tma_ports_utilized_2", + "MetricThreshold": "tma_fp_vector_256b > 0.1 & (tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6))", + "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 256-bit wide vectors. May overcount due to FMA double counting prior to LNL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%", "Unit": "cpu_core" }, { "BriefDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend", "DefaultMetricgroupName": "TopdownL1", - "MetricExpr": "topdown\\-fe\\-bound / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) - cpu_core@INT_MISC.UOP_DROPPING@ / tma_info_thread_slots", + "MetricExpr": "cpu_core@topdown\\-fe\\-bound@ / (cpu_core@topdown\\-fe\\-bound@ + cpu_core@topdown\\-bad\\-spec@ + cpu_core@topdown\\-retiring@ + cpu_core@topdown\\-be\\-bound@) - cpu_core@INT_MISC.UOP_DROPPING@ / tma_info_thread_slots", "MetricGroup": "BvFB;BvIO;Default;PGO;TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_frontend_bound", "MetricThreshold": "tma_frontend_bound > 0.15", "MetricgroupNoGroup": "TopdownL1;Default", - "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound. Sample with: FRONTEND_RETIRED.LATENCY_GE_4", + "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound. Sample with: FRONTEND_RETIRED.LATENCY_GE_4_PS", "ScaleUnit": "100%", "Unit": "cpu_core" }, { - "BriefDescription": "This metric represents fraction of slots where the CPU was retiring fused instructions , where one uop can represent multiple contiguous instructions", + "BriefDescription": "This metric represents fraction of slots where the CPU was retiring fused instructions -- where one uop can represent multiple contiguous instructions", "MetricExpr": "tma_light_operations * cpu_core@INST_RETIRED.MACRO_FUSED@ / (tma_retiring * tma_info_thread_slots)", "MetricGroup": "Branches;BvBO;Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group", "MetricName": "tma_fused_instructions", "MetricThreshold": "tma_fused_instructions > 0.1 & tma_light_operations > 0.6", - "PublicDescription": "This metric represents fraction of slots where the CPU was retiring fused instructions , where one uop can represent multiple contiguous instructions. CMP+JCC or DEC+JCC are common examples of legacy fusions. {([MTL] Note new MOV+OP and Load+OP fusions appear under Other_Light_Ops in MTL!)}", + "PublicDescription": "This metric represents fraction of slots where the CPU was retiring fused instructions -- where one uop can represent multiple contiguous instructions. CMP+JCC or DEC+JCC are common examples of legacy fusions. {([MTL] Note new MOV+OP and Load+OP fusions appear under Other_Light_Ops in MTL!)}", "ScaleUnit": "100%", "Unit": "cpu_core" }, { - "BriefDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations , instructions that require two or more uops or micro-coded sequences", - "MetricExpr": "topdown\\-heavy\\-ops / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * slots", + "BriefDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences", + "MetricExpr": "cpu_core@topdown\\-heavy\\-ops@ / (cpu_core@topdown\\-fe\\-bound@ + cpu_core@topdown\\-bad\\-spec@ + cpu_core@topdown\\-retiring@ + cpu_core@topdown\\-be\\-bound@) + 0 * tma_info_thread_slots", "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_heavy_operations", "MetricThreshold": "tma_heavy_operations > 0.1", "MetricgroupNoGroup": "TopdownL2", - "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations , instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences.([ICL+] Note this may overcount due to approximation using indirect events; [ADL+]). Sample with: UOPS_RETIRED.HEAVY", + "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences.([ICL+] Note this may overcount due to approximation using indirect events; [ADL+]). Sample with: UOPS_RETIRED.HEAVY", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -1265,26 +1267,26 @@ "MetricExpr": "cpu_core@ICACHE_DATA.STALLS@ / tma_info_thread_clks", "MetricGroup": "BigFootprint;BvBC;FetchLat;IcMiss;TopdownL3;tma_L3_group;tma_fetch_latency_group", "MetricName": "tma_icache_misses", - "MetricThreshold": "tma_icache_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", - "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to instruction cache misses. Sample with: FRONTEND_RETIRED.L2_MISS, FRONTEND_RETIRED.L1I_MISS", + "MetricThreshold": "tma_icache_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to instruction cache misses. Sample with: FRONTEND_RETIRED.L2_MISS_PS;FRONTEND_RETIRED.L1I_MISS_PS", "ScaleUnit": "100%", "Unit": "cpu_core" }, { - "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to retired misprediction by indirect CALL instructions", - "MetricExpr": "cpu_core@BR_MISP_RETIRED.INDIRECT_CALL_COST@ * cpu_core@br_misp_retired.indirect_call_cost@R / tma_info_thread_clks", + "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to retired misprediction by indirect CALL instructions.", + "MetricExpr": "cpu_core@BR_MISP_RETIRED.INDIRECT_CALL_COST@ * cpu_core@BR_MISP_RETIRED.INDIRECT_CALL_COST@R / tma_info_thread_clks", "MetricGroup": "BrMispredicts;TopdownL3;tma_L3_group;tma_branch_mispredicts_group", "MetricName": "tma_ind_call_mispredicts", - "MetricThreshold": "tma_ind_call_mispredicts > 0.05 & tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", + "MetricThreshold": "tma_ind_call_mispredicts > 0.05 & (tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15)", "ScaleUnit": "100%", "Unit": "cpu_core" }, { - "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to retired misprediction by indirect JMP instructions", - "MetricExpr": "max((cpu_core@BR_MISP_RETIRED.INDIRECT_COST@ * cpu_core@br_misp_retired.indirect_cost@R - cpu_core@BR_MISP_RETIRED.INDIRECT_CALL_COST@ * cpu_core@br_misp_retired.indirect_call_cost@R) / tma_info_thread_clks, 0)", + "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to retired misprediction by indirect JMP instructions.", + "MetricExpr": "max((cpu_core@BR_MISP_RETIRED.INDIRECT_COST@ * cpu_core@BR_MISP_RETIRED.INDIRECT_COST@R - cpu_core@BR_MISP_RETIRED.INDIRECT_CALL_COST@ * cpu_core@BR_MISP_RETIRED.INDIRECT_CALL_COST@R) / tma_info_thread_clks, 0)", "MetricGroup": "BrMispredicts;TopdownL3;tma_L3_group;tma_branch_mispredicts_group", "MetricName": "tma_ind_jump_mispredicts", - "MetricThreshold": "tma_ind_jump_mispredicts > 0.05 & tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", + "MetricThreshold": "tma_ind_jump_mispredicts > 0.05 & (tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15)", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -1297,7 +1299,7 @@ "Unit": "cpu_core" }, { - "BriefDescription": "Instructions per retired Mispredicts for conditional non-taken branches (lower number means higher occurrence rate)", + "BriefDescription": "Instructions per retired Mispredicts for conditional non-taken branches (lower number means higher occurrence rate).", "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / cpu_core@BR_MISP_RETIRED.COND_NTAKEN@", "MetricGroup": "Bad;BrMispredicts", "MetricName": "tma_info_bad_spec_ipmisp_cond_ntaken", @@ -1305,7 +1307,7 @@ "Unit": "cpu_core" }, { - "BriefDescription": "Instructions per retired Mispredicts for conditional taken branches (lower number means higher occurrence rate)", + "BriefDescription": "Instructions per retired Mispredicts for conditional taken branches (lower number means higher occurrence rate).", "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / cpu_core@BR_MISP_RETIRED.COND_TAKEN@", "MetricGroup": "Bad;BrMispredicts", "MetricName": "tma_info_bad_spec_ipmisp_cond_taken", @@ -1313,15 +1315,15 @@ "Unit": "cpu_core" }, { - "BriefDescription": "Instructions per retired Mispredicts for indirect CALL or JMP branches (lower number means higher occurrence rate)", + "BriefDescription": "Instructions per retired Mispredicts for indirect CALL or JMP branches (lower number means higher occurrence rate).", "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / cpu_core@BR_MISP_RETIRED.INDIRECT@", "MetricGroup": "Bad;BrMispredicts", "MetricName": "tma_info_bad_spec_ipmisp_indirect", - "MetricThreshold": "tma_info_bad_spec_ipmisp_indirect < 1000", + "MetricThreshold": "tma_info_bad_spec_ipmisp_indirect < 1e3", "Unit": "cpu_core" }, { - "BriefDescription": "Instructions per retired Mispredicts for return branches (lower number means higher occurrence rate)", + "BriefDescription": "Instructions per retired Mispredicts for return branches (lower number means higher occurrence rate).", "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / cpu_core@BR_MISP_RETIRED.RET@", "MetricGroup": "Bad;BrMispredicts", "MetricName": "tma_info_bad_spec_ipmisp_ret", @@ -1353,7 +1355,7 @@ }, { "BriefDescription": "Total pipeline cost of DSB (uop cache) hits - subset of the Instruction_Fetch_BW Bottleneck", - "MetricExpr": "100 * (tma_frontend_bound * (tma_fetch_bandwidth / (tma_fetch_latency + tma_fetch_bandwidth)) * (tma_dsb / (tma_mite + tma_dsb + tma_lsd + tma_ms)))", + "MetricExpr": "100 * (tma_frontend_bound * (tma_fetch_bandwidth / (tma_fetch_bandwidth + tma_fetch_latency)) * (tma_dsb / (tma_dsb + tma_lsd + tma_mite + tma_ms)))", "MetricGroup": "DSB;Fed;FetchBW;tma_issueFB", "MetricName": "tma_info_botlnk_l2_dsb_bandwidth", "MetricThreshold": "tma_info_botlnk_l2_dsb_bandwidth > 10", @@ -1362,7 +1364,7 @@ }, { "BriefDescription": "Total pipeline cost of DSB (uop cache) misses - subset of the Instruction_Fetch_BW Bottleneck", - "MetricExpr": "100 * (tma_fetch_latency * tma_dsb_switches / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches) + tma_fetch_bandwidth * tma_mite / (tma_mite + tma_dsb + tma_lsd + tma_ms))", + "MetricExpr": "100 * (tma_fetch_latency * tma_dsb_switches / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) + tma_fetch_bandwidth * tma_mite / (tma_dsb + tma_lsd + tma_mite + tma_ms))", "MetricGroup": "DSBmiss;Fed;tma_issueFB", "MetricName": "tma_info_botlnk_l2_dsb_misses", "MetricThreshold": "tma_info_botlnk_l2_dsb_misses > 10", @@ -1371,10 +1373,11 @@ }, { "BriefDescription": "Total pipeline cost of Instruction Cache misses - subset of the Big_Code Bottleneck", - "MetricExpr": "100 * (tma_fetch_latency * tma_icache_misses / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches))", + "MetricExpr": "100 * (tma_fetch_latency * tma_icache_misses / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches))", "MetricGroup": "Fed;FetchLat;IcMiss;tma_issueFL", "MetricName": "tma_info_botlnk_l2_ic_misses", "MetricThreshold": "tma_info_botlnk_l2_ic_misses > 5", + "PublicDescription": "Total pipeline cost of Instruction Cache misses - subset of the Big_Code Bottleneck. Related metrics: ", "Unit": "cpu_core" }, { @@ -1445,12 +1448,12 @@ "MetricExpr": "(cpu_core@FP_ARITH_DISPATCHED.PORT_0@ + cpu_core@FP_ARITH_DISPATCHED.PORT_1@ + cpu_core@FP_ARITH_DISPATCHED.PORT_5@) / (2 * tma_info_core_core_clks)", "MetricGroup": "Cor;Flops;HPC", "MetricName": "tma_info_core_fp_arith_utilization", - "PublicDescription": "Actual per-core usage of the Floating Point non-X87 execution units (regardless of precision or vector-width). Values > 1 are possible due to ([BDW+] Fused-Multiply Add (FMA) counting - common; [ADL+] use all of ADD/MUL/FMA in Scalar or 128/256-bit vectors - less common)", + "PublicDescription": "Actual per-core usage of the Floating Point non-X87 execution units (regardless of precision or vector-width). Values > 1 are possible due to ([BDW+] Fused-Multiply Add (FMA) counting - common; [ADL+] use all of ADD/MUL/FMA in Scalar or 128/256-bit vectors - less common).", "Unit": "cpu_core" }, { "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is execution) per thread (logical-processor)", - "MetricExpr": "cpu_core@UOPS_EXECUTED.THREAD@ / cpu_core@UOPS_EXECUTED.THREAD\\,cmask\\=0x1@", + "MetricExpr": "cpu_core@UOPS_EXECUTED.THREAD@ / cpu_core@UOPS_EXECUTED.THREAD\\,cmask\\=1@", "MetricGroup": "Backend;Cor;Pipeline;PortsUtil", "MetricName": "tma_info_core_ilp", "Unit": "cpu_core" @@ -1465,15 +1468,15 @@ "Unit": "cpu_core" }, { - "BriefDescription": "Average number of cycles of a switch from the DSB fetch-unit to MITE fetch unit - see DSB_Switches tree node for details", - "MetricExpr": "cpu_core@DSB2MITE_SWITCHES.PENALTY_CYCLES@ / cpu_core@DSB2MITE_SWITCHES.PENALTY_CYCLES\\,cmask\\=0x1\\,edge\\=0x1@", + "BriefDescription": "Average number of cycles of a switch from the DSB fetch-unit to MITE fetch unit - see DSB_Switches tree node for details.", + "MetricExpr": "cpu_core@DSB2MITE_SWITCHES.PENALTY_CYCLES@ / cpu_core@DSB2MITE_SWITCHES.PENALTY_CYCLES\\,cmask\\=1\\,edge@", "MetricGroup": "DSBmiss", "MetricName": "tma_info_frontend_dsb_switch_cost", "Unit": "cpu_core" }, { "BriefDescription": "This metric represents fraction of cycles the CPU retirement was stalled likely due to retired DSB misses", - "MetricExpr": "cpu_core@FRONTEND_RETIRED.ANY_DSB_MISS@ * cpu_core@frontend_retired.any_dsb_miss@R / tma_info_thread_clks", + "MetricExpr": "cpu_core@FRONTEND_RETIRED.ANY_DSB_MISS@ * cpu_core@FRONTEND_RETIRED.ANY_DSB_MISS@R / tma_info_thread_clks", "MetricGroup": "DSBmiss;Fed;FetchLat", "MetricName": "tma_info_frontend_dsb_switches_ret", "MetricThreshold": "tma_info_frontend_dsb_switches_ret > 0.05", @@ -1481,7 +1484,7 @@ }, { "BriefDescription": "Average number of Uops issued by front-end when it issued something", - "MetricExpr": "cpu_core@UOPS_ISSUED.ANY@ / cpu_core@UOPS_ISSUED.ANY\\,cmask\\=0x1@", + "MetricExpr": "cpu_core@UOPS_ISSUED.ANY@ / cpu_core@UOPS_ISSUED.ANY\\,cmask\\=1@", "MetricGroup": "Fed;FetchBW", "MetricName": "tma_info_frontend_fetch_upc", "Unit": "cpu_core" @@ -1531,7 +1534,7 @@ }, { "BriefDescription": "This metric represents fraction of cycles the CPU retirement was stalled likely due to retired operations that invoke the Microcode Sequencer", - "MetricExpr": "cpu_core@FRONTEND_RETIRED.MS_FLOWS@ * cpu_core@frontend_retired.ms_flows@R / tma_info_thread_clks", + "MetricExpr": "cpu_core@FRONTEND_RETIRED.MS_FLOWS@ * cpu_core@FRONTEND_RETIRED.MS_FLOWS@R / tma_info_thread_clks", "MetricGroup": "Fed;FetchLat;MicroSeq", "MetricName": "tma_info_frontend_ms_latency_ret", "MetricThreshold": "tma_info_frontend_ms_latency_ret > 0.05", @@ -1546,21 +1549,21 @@ }, { "BriefDescription": "Average number of cycles the front-end was delayed due to an Unknown Branch detection", - "MetricExpr": "cpu_core@INT_MISC.UNKNOWN_BRANCH_CYCLES@ / cpu_core@INT_MISC.UNKNOWN_BRANCH_CYCLES\\,cmask\\=0x1\\,edge\\=0x1@", + "MetricExpr": "cpu_core@INT_MISC.UNKNOWN_BRANCH_CYCLES@ / cpu_core@INT_MISC.UNKNOWN_BRANCH_CYCLES\\,cmask\\=1\\,edge@", "MetricGroup": "Fed", "MetricName": "tma_info_frontend_unknown_branch_cost", - "PublicDescription": "Average number of cycles the front-end was delayed due to an Unknown Branch detection. See Unknown_Branches node", + "PublicDescription": "Average number of cycles the front-end was delayed due to an Unknown Branch detection. See Unknown_Branches node.", "Unit": "cpu_core" }, { "BriefDescription": "This metric represents fraction of cycles the CPU retirement was stalled likely due to retired branches who got branch address clears", - "MetricExpr": "cpu_core@FRONTEND_RETIRED.UNKNOWN_BRANCH@ * cpu_core@frontend_retired.unknown_branch@R / tma_info_thread_clks", + "MetricExpr": "cpu_core@FRONTEND_RETIRED.UNKNOWN_BRANCH@ * cpu_core@FRONTEND_RETIRED.UNKNOWN_BRANCH@R / tma_info_thread_clks", "MetricGroup": "Fed;FetchLat", "MetricName": "tma_info_frontend_unknown_branches_ret", "Unit": "cpu_core" }, { - "BriefDescription": "Branch instructions per taken branch", + "BriefDescription": "Branch instructions per taken branch.", "MetricExpr": "cpu_core@BR_INST_RETIRED.ALL_BRANCHES@ / cpu_core@BR_INST_RETIRED.NEAR_TAKEN@", "MetricGroup": "Branches;Fed;PGO", "MetricName": "tma_info_inst_mix_bptkbranch", @@ -1580,7 +1583,7 @@ "MetricGroup": "Flops;InsType", "MetricName": "tma_info_inst_mix_iparith", "MetricThreshold": "tma_info_inst_mix_iparith < 10", - "PublicDescription": "Instructions per FP Arithmetic instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting. Approximated prior to BDW", + "PublicDescription": "Instructions per FP Arithmetic instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting. Approximated prior to BDW.", "Unit": "cpu_core" }, { @@ -1589,7 +1592,7 @@ "MetricGroup": "Flops;FpVector;InsType", "MetricName": "tma_info_inst_mix_iparith_avx128", "MetricThreshold": "tma_info_inst_mix_iparith_avx128 < 10", - "PublicDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting", + "PublicDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting.", "Unit": "cpu_core" }, { @@ -1598,7 +1601,7 @@ "MetricGroup": "Flops;FpVector;InsType", "MetricName": "tma_info_inst_mix_iparith_avx256", "MetricThreshold": "tma_info_inst_mix_iparith_avx256 < 10", - "PublicDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting", + "PublicDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting.", "Unit": "cpu_core" }, { @@ -1607,7 +1610,7 @@ "MetricGroup": "Flops;FpScalar;InsType", "MetricName": "tma_info_inst_mix_iparith_scalar_dp", "MetricThreshold": "tma_info_inst_mix_iparith_scalar_dp < 10", - "PublicDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting", + "PublicDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting.", "Unit": "cpu_core" }, { @@ -1616,7 +1619,7 @@ "MetricGroup": "Flops;FpScalar;InsType", "MetricName": "tma_info_inst_mix_iparith_scalar_sp", "MetricThreshold": "tma_info_inst_mix_iparith_scalar_sp < 10", - "PublicDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting", + "PublicDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting.", "Unit": "cpu_core" }, { @@ -1679,7 +1682,7 @@ "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / cpu_core@BR_INST_RETIRED.NEAR_TAKEN@", "MetricGroup": "Branches;Fed;FetchBW;Frontend;PGO;tma_issueFB", "MetricName": "tma_info_inst_mix_iptb", - "MetricThreshold": "tma_info_inst_mix_iptb < 6 * 2 + 1", + "MetricThreshold": "tma_info_inst_mix_iptb < 13", "PublicDescription": "Instructions per taken branch. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_lcp", "Unit": "cpu_core" }, @@ -1825,7 +1828,7 @@ }, { "BriefDescription": "Average Parallel L2 cache miss demand Loads", - "MetricExpr": "cpu_core@OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD@ / cpu_core@OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD\\,cmask\\=0x1@", + "MetricExpr": "cpu_core@OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD@ / cpu_core@OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD\\,cmask\\=1@", "MetricGroup": "Memory_BW;Offcore", "MetricName": "tma_info_memory_latency_load_l2_mlp", "Unit": "cpu_core" @@ -1883,7 +1886,7 @@ }, { "BriefDescription": "This metric represents fraction of cycles the CPU retirement was stalled likely due to STLB misses by demand loads", - "MetricExpr": "cpu_core@MEM_INST_RETIRED.STLB_MISS_LOADS@ * cpu_core@mem_inst_retired.stlb_miss_loads@R / tma_info_thread_clks", + "MetricExpr": "cpu_core@MEM_INST_RETIRED.STLB_MISS_LOADS@ * cpu_core@MEM_INST_RETIRED.STLB_MISS_LOADS@R / tma_info_thread_clks", "MetricGroup": "Mem;MemoryTLB", "MetricName": "tma_info_memory_tlb_load_stlb_miss_ret", "MetricThreshold": "tma_info_memory_tlb_load_stlb_miss_ret > 0.05", @@ -1906,7 +1909,7 @@ }, { "BriefDescription": "This metric represents fraction of cycles the CPU retirement was stalled likely due to STLB misses by demand stores", - "MetricExpr": "cpu_core@MEM_INST_RETIRED.STLB_MISS_STORES@ * cpu_core@mem_inst_retired.stlb_miss_stores@R / tma_info_thread_clks", + "MetricExpr": "cpu_core@MEM_INST_RETIRED.STLB_MISS_STORES@ * cpu_core@MEM_INST_RETIRED.STLB_MISS_STORES@R / tma_info_thread_clks", "MetricGroup": "Mem;MemoryTLB", "MetricName": "tma_info_memory_tlb_store_stlb_miss_ret", "MetricThreshold": "tma_info_memory_tlb_store_stlb_miss_ret > 0.05", @@ -1921,7 +1924,7 @@ }, { "BriefDescription": "", - "MetricExpr": "cpu_core@UOPS_EXECUTED.THREAD@ / (cpu_core@UOPS_EXECUTED.CORE_CYCLES_GE_1@ / 2 if #SMT_on else cpu_core@UOPS_EXECUTED.THREAD\\,cmask\\=0x1@)", + "MetricExpr": "cpu_core@UOPS_EXECUTED.THREAD@ / (cpu_core@UOPS_EXECUTED.CORE_CYCLES_GE_1@ / 2 if #SMT_on else cpu_core@UOPS_EXECUTED.THREAD\\,cmask\\=1@)", "MetricGroup": "Cor;Pipeline;PortsUtil;SMT", "MetricName": "tma_info_pipeline_execute", "Unit": "cpu_core" @@ -1952,20 +1955,20 @@ "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / cpu_core@ASSISTS.ANY@", "MetricGroup": "MicroSeq;Pipeline;Ret;Retire", "MetricName": "tma_info_pipeline_ipassist", - "MetricThreshold": "tma_info_pipeline_ipassist < 100000", + "MetricThreshold": "tma_info_pipeline_ipassist < 100e3", "PublicDescription": "Instructions per a microcode Assist invocation. See Assists tree node for details (lower number means higher occurrence rate)", "Unit": "cpu_core" }, { - "BriefDescription": "Average number of Uops retired in cycles where at least one uop has retired", - "MetricExpr": "tma_retiring * tma_info_thread_slots / cpu_core@UOPS_RETIRED.SLOTS\\,cmask\\=0x1@", + "BriefDescription": "Average number of Uops retired in cycles where at least one uop has retired.", + "MetricExpr": "tma_retiring * tma_info_thread_slots / cpu_core@UOPS_RETIRED.SLOTS\\,cmask\\=1@", "MetricGroup": "Pipeline;Ret", "MetricName": "tma_info_pipeline_retire", "Unit": "cpu_core" }, { "BriefDescription": "Estimated fraction of retirement-cycles dealing with repeat instructions", - "MetricExpr": "cpu_core@INST_RETIRED.REP_ITERATION@ / cpu_core@UOPS_RETIRED.SLOTS\\,cmask\\=0x1@", + "MetricExpr": "cpu_core@INST_RETIRED.REP_ITERATION@ / cpu_core@UOPS_RETIRED.SLOTS\\,cmask\\=1@", "MetricGroup": "MicroSeq;Pipeline;Ret", "MetricName": "tma_info_pipeline_strings_cycles", "MetricThreshold": "tma_info_pipeline_strings_cycles > 0.1", @@ -2018,23 +2021,22 @@ }, { "BriefDescription": "Instructions per Far Branch ( Far Branches apply upon transition from application to operating system, handling interrupts, exceptions) [lower number means higher occurrence rate]", - "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / BR_INST_RETIRED.FAR_BRANCH:u", + "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / cpu_core@BR_INST_RETIRED.FAR_BRANCH@u", "MetricGroup": "Branches;OS", "MetricName": "tma_info_system_ipfarbranch", - "MetricThreshold": "tma_info_system_ipfarbranch < 1000000", + "MetricThreshold": "tma_info_system_ipfarbranch < 1e6", "Unit": "cpu_core" }, { "BriefDescription": "Cycles Per Instruction for the Operating System (OS) Kernel mode", - "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P:k / INST_RETIRED.ANY_P:k", + "MetricExpr": "cpu_core@CPU_CLK_UNHALTED.THREAD_P@k / cpu_core@INST_RETIRED.ANY_P@k", "MetricGroup": "OS", "MetricName": "tma_info_system_kernel_cpi", - "ScaleUnit": "1per_instr", "Unit": "cpu_core" }, { "BriefDescription": "Fraction of cycles spent in the Operating System (OS) Kernel mode", - "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P:k / cpu_core@CPU_CLK_UNHALTED.THREAD@", + "MetricExpr": "cpu_core@CPU_CLK_UNHALTED.THREAD_P@k / cpu_core@CPU_CLK_UNHALTED.THREAD@", "MetricGroup": "OS", "MetricName": "tma_info_system_kernel_utilization", "MetricThreshold": "tma_info_system_kernel_utilization > 0.05", @@ -2042,7 +2044,7 @@ }, { "BriefDescription": "Average number of parallel data read requests to external memory", - "MetricExpr": "UNC_ARB_DAT_OCCUPANCY.RD / UNC_ARB_DAT_OCCUPANCY.RD@thresh\\=0x1@", + "MetricExpr": "UNC_ARB_DAT_OCCUPANCY.RD / UNC_ARB_DAT_OCCUPANCY.RD@cmask\\=1@", "MetricGroup": "Mem;MemoryBW;SoC", "MetricName": "tma_info_system_mem_parallel_reads", "PublicDescription": "Average number of parallel data read requests to external memory. Accounts for demand loads and L1/L2 prefetches", @@ -2093,7 +2095,7 @@ "Unit": "cpu_core" }, { - "BriefDescription": "Per-Logical Processor actual clocks when the Logical Processor is active", + "BriefDescription": "Per-Logical Processor actual clocks when the Logical Processor is active.", "MetricExpr": "cpu_core@CPU_CLK_UNHALTED.THREAD@", "MetricGroup": "Pipeline", "MetricName": "tma_info_thread_clks", @@ -2104,7 +2106,6 @@ "MetricExpr": "1 / tma_info_thread_ipc", "MetricGroup": "Mem;Pipeline", "MetricName": "tma_info_thread_cpi", - "ScaleUnit": "1per_instr", "Unit": "cpu_core" }, { @@ -2112,7 +2113,7 @@ "MetricExpr": "cpu_core@UOPS_EXECUTED.THREAD@ / cpu_core@UOPS_ISSUED.ANY@", "MetricGroup": "Cor;Pipeline", "MetricName": "tma_info_thread_execute_per_issue", - "PublicDescription": "The ratio of Executed- by Issued-Uops. Ratio > 1 suggests high rate of uop micro-fusions. Ratio < 1 suggest high rate of \"execute\" at rename stage", + "PublicDescription": "The ratio of Executed- by Issued-Uops. Ratio > 1 suggests high rate of uop micro-fusions. Ratio < 1 suggest high rate of \"execute\" at rename stage.", "Unit": "cpu_core" }, { @@ -2124,14 +2125,14 @@ }, { "BriefDescription": "Total issue-pipeline slots (per-Physical Core till ICL; per-Logical Processor ICL onward)", - "MetricExpr": "slots", + "MetricExpr": "cpu_core@TOPDOWN.SLOTS@", "MetricGroup": "TmaL1;tma_L1_group", "MetricName": "tma_info_thread_slots", "Unit": "cpu_core" }, { "BriefDescription": "Fraction of Physical Core issue-slots utilized by this Logical Processor", - "MetricExpr": "(tma_info_thread_slots / (slots / 2) if #SMT_on else 1)", + "MetricExpr": "(tma_info_thread_slots / (cpu_core@TOPDOWN.SLOTS@ / 2) if #SMT_on else 1)", "MetricGroup": "SMT;TmaL1;tma_L1_group", "MetricName": "tma_info_thread_slots_utilization", "Unit": "cpu_core" @@ -2149,15 +2150,15 @@ "MetricExpr": "tma_retiring * tma_info_thread_slots / cpu_core@BR_INST_RETIRED.NEAR_TAKEN@", "MetricGroup": "Branches;Fed;FetchBW", "MetricName": "tma_info_thread_uptb", - "MetricThreshold": "tma_info_thread_uptb < 6 * 1.5", + "MetricThreshold": "tma_info_thread_uptb < 9", "Unit": "cpu_core" }, { - "BriefDescription": "This metric represents fraction of cycles where the Integer Divider unit was active", + "BriefDescription": "This metric represents fraction of cycles where the Integer Divider unit was active.", "MetricExpr": "tma_divider - tma_fp_divider", "MetricGroup": "TopdownL4;tma_L4_group;tma_divider_group", "MetricName": "tma_int_divider", - "MetricThreshold": "tma_int_divider > 0.2 & tma_divider > 0.2 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_int_divider > 0.2 & (tma_divider > 0.2 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -2167,7 +2168,7 @@ "MetricGroup": "Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group", "MetricName": "tma_int_operations", "MetricThreshold": "tma_int_operations > 0.1 & tma_light_operations > 0.6", - "PublicDescription": "This metric represents overall Integer (Int) select operations fraction the CPU has executed (retired). Vector/Matrix Int operations and shuffles are counted. Note this metric's value may exceed its parent due to use of \"Uops\" CountDomain", + "PublicDescription": "This metric represents overall Integer (Int) select operations fraction the CPU has executed (retired). Vector/Matrix Int operations and shuffles are counted. Note this metric's value may exceed its parent due to use of \"Uops\" CountDomain.", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -2176,8 +2177,8 @@ "MetricExpr": "(cpu_core@INT_VEC_RETIRED.ADD_128@ + cpu_core@INT_VEC_RETIRED.VNNI_128@) / (tma_retiring * tma_info_thread_slots)", "MetricGroup": "Compute;IntVector;Pipeline;TopdownL4;tma_L4_group;tma_int_operations_group;tma_issue2P", "MetricName": "tma_int_vector_128b", - "MetricThreshold": "tma_int_vector_128b > 0.1 & tma_int_operations > 0.1 & tma_light_operations > 0.6", - "PublicDescription": "This metric represents 128-bit vector Integer ADD/SUB/SAD or VNNI (Vector Neural Network Instructions) uops fraction the CPU has retired. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_6, tma_ports_utilized_2", + "MetricThreshold": "tma_int_vector_128b > 0.1 & (tma_int_operations > 0.1 & tma_light_operations > 0.6)", + "PublicDescription": "This metric represents 128-bit vector Integer ADD/SUB/SAD or VNNI (Vector Neural Network Instructions) uops fraction the CPU has retired. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -2186,8 +2187,8 @@ "MetricExpr": "(cpu_core@INT_VEC_RETIRED.ADD_256@ + cpu_core@INT_VEC_RETIRED.MUL_256@ + cpu_core@INT_VEC_RETIRED.VNNI_256@) / (tma_retiring * tma_info_thread_slots)", "MetricGroup": "Compute;IntVector;Pipeline;TopdownL4;tma_L4_group;tma_int_operations_group;tma_issue2P", "MetricName": "tma_int_vector_256b", - "MetricThreshold": "tma_int_vector_256b > 0.1 & tma_int_operations > 0.1 & tma_light_operations > 0.6", - "PublicDescription": "This metric represents 256-bit vector Integer ADD/SUB/SAD/MUL or VNNI (Vector Neural Network Instructions) uops fraction the CPU has retired. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_int_vector_128b, tma_port_0, tma_port_1, tma_port_6, tma_ports_utilized_2", + "MetricThreshold": "tma_int_vector_256b > 0.1 & (tma_int_operations > 0.1 & tma_light_operations > 0.6)", + "PublicDescription": "This metric represents 256-bit vector Integer ADD/SUB/SAD/MUL or VNNI (Vector Neural Network Instructions) uops fraction the CPU has retired. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -2196,8 +2197,8 @@ "MetricExpr": "cpu_core@ICACHE_TAG.STALLS@ / tma_info_thread_clks", "MetricGroup": "BigFootprint;BvBC;FetchLat;MemoryTLB;TopdownL3;tma_L3_group;tma_fetch_latency_group", "MetricName": "tma_itlb_misses", - "MetricThreshold": "tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", - "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Instruction TLB (ITLB) misses. Sample with: FRONTEND_RETIRED.STLB_MISS, FRONTEND_RETIRED.ITLB_MISS", + "MetricThreshold": "tma_itlb_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Instruction TLB (ITLB) misses. Sample with: FRONTEND_RETIRED.STLB_MISS_PS;FRONTEND_RETIRED.ITLB_MISS_PS", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -2206,7 +2207,7 @@ "MetricExpr": "max((cpu_core@EXE_ACTIVITY.BOUND_ON_LOADS@ - cpu_core@MEMORY_ACTIVITY.STALLS_L1D_MISS@) / tma_info_thread_clks, 0)", "MetricGroup": "CacheHits;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_issueL1;tma_issueMC;tma_memory_bound_group", "MetricName": "tma_l1_bound", - "MetricThreshold": "tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", "PublicDescription": "This metric estimates how often the CPU was stalled without loads missing the L1 Data (L1D) cache. The L1D cache typically has the shortest latency. However; in certain cases like loads blocked on older stores; a load might suffer due to high latency even though it is being satisfied by the L1D. Another example is loads who miss in the TLB. These cases are characterized by execution unit stalls; while some non-completed demand load lives in the machine without having that demand load missing the L1 cache. Sample with: MEM_LOAD_RETIRED.L1_HIT. Related metrics: tma_clears_resteers, tma_machine_clears, tma_microcode_sequencer, tma_ms_switches, tma_ports_utilized_1", "ScaleUnit": "100%", "Unit": "cpu_core" @@ -2216,7 +2217,7 @@ "MetricExpr": "min(2 * (cpu_core@MEM_INST_RETIRED.ALL_LOADS@ - cpu_core@MEM_LOAD_RETIRED.FB_HIT@ - cpu_core@MEM_LOAD_RETIRED.L1_MISS@) * 20 / 100, max(cpu_core@CYCLE_ACTIVITY.CYCLES_MEM_ANY@ - cpu_core@MEMORY_ACTIVITY.CYCLES_L1D_MISS@, 0)) / tma_info_thread_clks", "MetricGroup": "BvML;MemoryLat;TopdownL4;tma_L4_group;tma_l1_bound_group", "MetricName": "tma_l1_latency_dependency", - "MetricThreshold": "tma_l1_latency_dependency > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_l1_latency_dependency > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", "PublicDescription": "This metric([SKL+] roughly; [LNL]) estimates fraction of cycles with demand load accesses that hit the L1D cache. The short latency of the L1D cache may be exposed in pointer-chasing memory access patterns as an example. Sample with: MEM_LOAD_RETIRED.L1_HIT", "ScaleUnit": "100%", "Unit": "cpu_core" @@ -2226,17 +2227,18 @@ "MetricExpr": "(cpu_core@MEMORY_ACTIVITY.STALLS_L1D_MISS@ - cpu_core@MEMORY_ACTIVITY.STALLS_L2_MISS@) / tma_info_thread_clks", "MetricGroup": "BvML;CacheHits;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_l2_bound", - "MetricThreshold": "tma_l2_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_l2_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", "PublicDescription": "This metric estimates how often the CPU was stalled due to L2 cache accesses by loads. Avoiding cache misses (i.e. L1 misses/L2 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L2_HIT", "ScaleUnit": "100%", "Unit": "cpu_core" }, { "BriefDescription": "This metric represents fraction of cycles with demand load accesses that hit the L2 cache under unloaded scenarios (possibly L2 latency limited)", - "MetricExpr": "(min(cpu_core@MEM_LOAD_RETIRED.L2_HIT@ * cpu_core@mem_load_retired.l2_hit@R, cpu_core@MEM_LOAD_RETIRED.L2_HIT@ * (3 * tma_info_system_core_frequency)) if 0 < cpu_core@mem_load_retired.l2_hit@R else cpu_core@MEM_LOAD_RETIRED.L2_HIT@ * (3 * tma_info_system_core_frequency)) * (1 + cpu_core@MEM_LOAD_RETIRED.FB_HIT@ / cpu_core@MEM_LOAD_RETIRED.L1_MISS@ / 2) / tma_info_thread_clks", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "cpu_core@MEM_LOAD_RETIRED.L2_HIT@ * min(cpu_core@MEM_LOAD_RETIRED.L2_HIT@R, 3 * tma_info_system_core_frequency) * (1 + cpu_core@MEM_LOAD_RETIRED.FB_HIT@ / cpu_core@MEM_LOAD_RETIRED.L1_MISS@ / 2) / tma_info_thread_clks", "MetricGroup": "MemoryLat;TopdownL4;tma_L4_group;tma_l2_bound_group", "MetricName": "tma_l2_hit_latency", - "MetricThreshold": "tma_l2_hit_latency > 0.05 & tma_l2_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_l2_hit_latency > 0.05 & (tma_l2_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", "PublicDescription": "This metric represents fraction of cycles with demand load accesses that hit the L2 cache under unloaded scenarios (possibly L2 latency limited). Avoiding L1 cache misses (i.e. L1 misses/L2 hits) will improve the latency. Sample with: MEM_LOAD_RETIRED.L2_HIT", "ScaleUnit": "100%", "Unit": "cpu_core" @@ -2246,18 +2248,19 @@ "MetricExpr": "(cpu_core@MEMORY_ACTIVITY.STALLS_L2_MISS@ - cpu_core@MEMORY_ACTIVITY.STALLS_L3_MISS@) / tma_info_thread_clks", "MetricGroup": "CacheHits;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_l3_bound", - "MetricThreshold": "tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", - "PublicDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core. Avoiding cache misses (i.e. L2 misses/L3 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L3_HIT", + "MetricThreshold": "tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", + "PublicDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core. Avoiding cache misses (i.e. L2 misses/L3 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L3_HIT_PS", "ScaleUnit": "100%", "Unit": "cpu_core" }, { "BriefDescription": "This metric estimates fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited)", - "MetricExpr": "(min(cpu_core@MEM_LOAD_RETIRED.L3_HIT@ * cpu_core@mem_load_retired.l3_hit@R, cpu_core@MEM_LOAD_RETIRED.L3_HIT@ * (12 * tma_info_system_core_frequency) - 3 * tma_info_system_core_frequency) if 0 < cpu_core@mem_load_retired.l3_hit@R else cpu_core@MEM_LOAD_RETIRED.L3_HIT@ * (12 * tma_info_system_core_frequency) - 3 * tma_info_system_core_frequency) * (1 + cpu_core@MEM_LOAD_RETIRED.FB_HIT@ / cpu_core@MEM_LOAD_RETIRED.L1_MISS@ / 2) / tma_info_thread_clks", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "cpu_core@MEM_LOAD_RETIRED.L3_HIT@ * min(cpu_core@MEM_LOAD_RETIRED.L3_HIT@R, 9 * tma_info_system_core_frequency) * (1 + cpu_core@MEM_LOAD_RETIRED.FB_HIT@ / cpu_core@MEM_LOAD_RETIRED.L1_MISS@ / 2) / tma_info_thread_clks", "MetricGroup": "BvML;MemoryLat;TopdownL4;tma_L4_group;tma_issueLat;tma_l3_bound_group", "MetricName": "tma_l3_hit_latency", - "MetricThreshold": "tma_l3_hit_latency > 0.1 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", - "PublicDescription": "This metric estimates fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited). Avoiding private cache misses (i.e. L2 misses/L3 hits) will improve the latency; reduce contention with sibling physical cores and increase performance. Note the value of this node may overlap with its siblings. Sample with: MEM_LOAD_RETIRED.L3_HIT. Related metrics: tma_bottleneck_cache_memory_latency, tma_branch_resteers, tma_mem_latency, tma_store_latency", + "MetricThreshold": "tma_l3_hit_latency > 0.1 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric estimates fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited). Avoiding private cache misses (i.e. L2 misses/L3 hits) will improve the latency; reduce contention with sibling physical cores and increase performance. Note the value of this node may overlap with its siblings. Sample with: MEM_LOAD_RETIRED.L3_HIT_PS. Related metrics: tma_bottleneck_cache_memory_latency, tma_mem_latency", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -2266,19 +2269,19 @@ "MetricExpr": "cpu_core@DECODE.LCP@ / tma_info_thread_clks", "MetricGroup": "FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueFB", "MetricName": "tma_lcp", - "MetricThreshold": "tma_lcp > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", - "PublicDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs). Using proper compiler flags or Intel Compiler by default will certainly avoid this. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb", + "MetricThreshold": "tma_lcp > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", + "PublicDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs). Using proper compiler flags or Intel Compiler by default will certainly avoid this. #Link: Optimization Guide about LCP BKMs. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb", "ScaleUnit": "100%", "Unit": "cpu_core" }, { - "BriefDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations , instructions that require no more than one uop (micro-operation)", + "BriefDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation)", "MetricExpr": "max(0, tma_retiring - tma_heavy_operations)", "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_light_operations", "MetricThreshold": "tma_light_operations > 0.6", "MetricgroupNoGroup": "TopdownL2", - "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations , instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized code running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. ([ICL+] Note this may undercount due to approximation using indirect events; [ADL+] .). Sample with: INST_RETIRED.PREC_DIST", + "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized code running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. ([ICL+] Note this may undercount due to approximation using indirect events; [ADL+] .). Sample with: INST_RETIRED.PREC_DIST", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -2297,7 +2300,7 @@ "MetricExpr": "max(0, tma_dtlb_load - tma_load_stlb_miss)", "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_load_group", "MetricName": "tma_load_stlb_hit", - "MetricThreshold": "tma_load_stlb_hit > 0.05 & tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_load_stlb_hit > 0.05 & (tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -2306,43 +2309,43 @@ "MetricExpr": "cpu_core@DTLB_LOAD_MISSES.WALK_ACTIVE@ / tma_info_thread_clks", "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_load_group", "MetricName": "tma_load_stlb_miss", - "MetricThreshold": "tma_load_stlb_miss > 0.05 & tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_load_stlb_miss > 0.05 & (tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))", "ScaleUnit": "100%", "Unit": "cpu_core" }, { - "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 1 GB pages for data load accesses", + "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 1 GB pages for data load accesses.", "MetricExpr": "tma_load_stlb_miss * cpu_core@DTLB_LOAD_MISSES.WALK_COMPLETED_1G@ / (cpu_core@DTLB_LOAD_MISSES.WALK_COMPLETED_4K@ + cpu_core@DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M@ + cpu_core@DTLB_LOAD_MISSES.WALK_COMPLETED_1G@)", "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_load_stlb_miss_group", "MetricName": "tma_load_stlb_miss_1g", - "MetricThreshold": "tma_load_stlb_miss_1g > 0.05 & tma_load_stlb_miss > 0.05 & tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_load_stlb_miss_1g > 0.05 & (tma_load_stlb_miss > 0.05 & (tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))))", "ScaleUnit": "100%", "Unit": "cpu_core" }, { - "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 2 or 4 MB pages for data load accesses", + "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 2 or 4 MB pages for data load accesses.", "MetricExpr": "tma_load_stlb_miss * cpu_core@DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M@ / (cpu_core@DTLB_LOAD_MISSES.WALK_COMPLETED_4K@ + cpu_core@DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M@ + cpu_core@DTLB_LOAD_MISSES.WALK_COMPLETED_1G@)", "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_load_stlb_miss_group", "MetricName": "tma_load_stlb_miss_2m", - "MetricThreshold": "tma_load_stlb_miss_2m > 0.05 & tma_load_stlb_miss > 0.05 & tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_load_stlb_miss_2m > 0.05 & (tma_load_stlb_miss > 0.05 & (tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))))", "ScaleUnit": "100%", "Unit": "cpu_core" }, { - "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 4 KB pages for data load accesses", + "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 4 KB pages for data load accesses.", "MetricExpr": "tma_load_stlb_miss * cpu_core@DTLB_LOAD_MISSES.WALK_COMPLETED_4K@ / (cpu_core@DTLB_LOAD_MISSES.WALK_COMPLETED_4K@ + cpu_core@DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M@ + cpu_core@DTLB_LOAD_MISSES.WALK_COMPLETED_1G@)", "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_load_stlb_miss_group", "MetricName": "tma_load_stlb_miss_4k", - "MetricThreshold": "tma_load_stlb_miss_4k > 0.05 & tma_load_stlb_miss > 0.05 & tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_load_stlb_miss_4k > 0.05 & (tma_load_stlb_miss > 0.05 & (tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))))", "ScaleUnit": "100%", "Unit": "cpu_core" }, { "BriefDescription": "This metric represents fraction of cycles the CPU spent handling cache misses due to lock operations", - "MetricExpr": "cpu_core@MEM_INST_RETIRED.LOCK_LOADS@ * cpu_core@mem_inst_retired.lock_loads@R / tma_info_thread_clks", + "MetricExpr": "cpu_core@MEM_INST_RETIRED.LOCK_LOADS@ * cpu_core@MEM_INST_RETIRED.LOCK_LOADS@R / tma_info_thread_clks", "MetricGroup": "LockCont;Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_l1_bound_group", "MetricName": "tma_lock_latency", - "MetricThreshold": "tma_lock_latency > 0.2 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_lock_latency > 0.2 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", "PublicDescription": "This metric represents fraction of cycles the CPU spent handling cache misses due to lock operations. Due to the microarchitecture handling of locks; they are classified as L1_Bound regardless of what memory source satisfied them. Sample with: MEM_INST_RETIRED.LOCK_LOADS. Related metrics: tma_store_latency", "ScaleUnit": "100%", "Unit": "cpu_core" @@ -2353,7 +2356,7 @@ "MetricGroup": "FetchBW;LSD;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group", "MetricName": "tma_lsd", "MetricThreshold": "tma_lsd > 0.15 & tma_fetch_bandwidth > 0.2", - "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to LSD (Loop Stream Detector) unit. LSD typically does well sustaining Uop supply. However; in some rare cases; optimal uop-delivery could not be reached for small loops whose size (in terms of number of uops) does not suit well the LSD structure", + "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to LSD (Loop Stream Detector) unit. LSD typically does well sustaining Uop supply. However; in some rare cases; optimal uop-delivery could not be reached for small loops whose size (in terms of number of uops) does not suit well the LSD structure.", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -2364,17 +2367,17 @@ "MetricName": "tma_machine_clears", "MetricThreshold": "tma_machine_clears > 0.1 & tma_bad_speculation > 0.15", "MetricgroupNoGroup": "TopdownL2", - "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears. These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT. Related metrics: tma_bottleneck_memory_synchronization, tma_clears_resteers, tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_l1_bound, tma_microcode_sequencer, tma_ms_switches", + "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears. These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT. Related metrics: tma_bottleneck_memory_synchronization, tma_clears_resteers, tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_l1_bound, tma_microcode_sequencer, tma_ms_switches, tma_remote_cache", "ScaleUnit": "100%", "Unit": "cpu_core" }, { "BriefDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory - DRAM ([SPR-HBM] and/or HBM)", - "MetricExpr": "min(cpu_core@CPU_CLK_UNHALTED.THREAD@, cpu_core@OFFCORE_REQUESTS_OUTSTANDING.DATA_RD\\,cmask\\=0x4@) / tma_info_thread_clks", + "MetricExpr": "min(cpu_core@CPU_CLK_UNHALTED.THREAD@, cpu_core@OFFCORE_REQUESTS_OUTSTANDING.DATA_RD\\,cmask\\=4@) / tma_info_thread_clks", "MetricGroup": "BvMB;MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueBW", "MetricName": "tma_mem_bandwidth", - "MetricThreshold": "tma_mem_bandwidth > 0.2 & tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", - "PublicDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory - DRAM ([SPR-HBM] and/or HBM). The underlying heuristic assumes that a similar off-core traffic is generated by all IA cores. This metric does not aggregate non-data-read requests by this logical processor; requests from other IA Logical Processors/Physical Cores/sockets; or other non-IA devices like GPU; hence the maximum external memory bandwidth limits may or may not be approached when this metric is flagged (see Uncore counters for that). Related metrics: tma_bottleneck_cache_memory_bandwidth, tma_fb_full, tma_sq_full", + "MetricThreshold": "tma_mem_bandwidth > 0.2 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory - DRAM ([SPR-HBM] and/or HBM). The underlying heuristic assumes that a similar off-core traffic is generated by all IA cores. This metric does not aggregate non-data-read requests by this logical processor; requests from other IA Logical Processors/Physical Cores/sockets; or other non-IA devices like GPU; hence the maximum external memory bandwidth limits may or may not be approached when this metric is flagged (see Uncore counters for that). Related metrics: tma_bottleneck_cache_memory_bandwidth, tma_fb_full, tma_info_system_dram_bw_use, tma_sq_full", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -2383,34 +2386,34 @@ "MetricExpr": "min(cpu_core@CPU_CLK_UNHALTED.THREAD@, cpu_core@OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD@) / tma_info_thread_clks - tma_mem_bandwidth", "MetricGroup": "BvML;MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueLat", "MetricName": "tma_mem_latency", - "MetricThreshold": "tma_mem_latency > 0.1 & tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_mem_latency > 0.1 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", "PublicDescription": "This metric estimates fraction of cycles where the performance was likely hurt due to latency from external memory - DRAM ([SPR-HBM] and/or HBM). This metric does not aggregate requests from other Logical Processors/Physical Cores/sockets (see Uncore counters for that). Related metrics: tma_bottleneck_cache_memory_latency, tma_l3_hit_latency", "ScaleUnit": "100%", "Unit": "cpu_core" }, { "BriefDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck", - "MetricExpr": "topdown\\-mem\\-bound / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * slots", + "MetricExpr": "cpu_core@topdown\\-mem\\-bound@ / (cpu_core@topdown\\-fe\\-bound@ + cpu_core@topdown\\-bad\\-spec@ + cpu_core@topdown\\-retiring@ + cpu_core@topdown\\-be\\-bound@) + 0 * tma_info_thread_slots", "MetricGroup": "Backend;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_memory_bound", "MetricThreshold": "tma_memory_bound > 0.2 & tma_backend_bound > 0.2", "MetricgroupNoGroup": "TopdownL2", - "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck. Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two)", + "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck. Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two).", "ScaleUnit": "100%", "Unit": "cpu_core" }, { - "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to LFENCE Instructions", + "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to LFENCE Instructions.", "MetricConstraint": "NO_GROUP_EVENTS_NMI", "MetricExpr": "13 * cpu_core@MISC2_RETIRED.LFENCE@ / tma_info_thread_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_serializing_operation_group", "MetricName": "tma_memory_fence", - "MetricThreshold": "tma_memory_fence > 0.05 & tma_serializing_operation > 0.1 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_memory_fence > 0.05 & (tma_serializing_operation > 0.1 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", "ScaleUnit": "100%", "Unit": "cpu_core" }, { - "BriefDescription": "This metric represents fraction of slots where the CPU was retiring memory operations , uops for memory load or store accesses", + "BriefDescription": "This metric represents fraction of slots where the CPU was retiring memory operations -- uops for memory load or store accesses.", "MetricExpr": "tma_light_operations * cpu_core@MEM_UOP_RETIRED.ANY@ / (tma_retiring * tma_info_thread_slots)", "MetricGroup": "Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group", "MetricName": "tma_memory_operations", @@ -2433,7 +2436,7 @@ "MetricExpr": "tma_branch_mispredicts / tma_bad_speculation * cpu_core@INT_MISC.CLEAR_RESTEER_CYCLES@ / tma_info_thread_clks", "MetricGroup": "BadSpec;BrMispredicts;BvMP;TopdownL4;tma_L4_group;tma_branch_resteers_group;tma_issueBM", "MetricName": "tma_mispredicts_resteers", - "MetricThreshold": "tma_mispredicts_resteers > 0.05 & tma_branch_resteers > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricThreshold": "tma_mispredicts_resteers > 0.05 & (tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))", "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Branch Misprediction at execution stage. Sample with: INT_MISC.CLEAR_RESTEER_CYCLES. Related metrics: tma_bottleneck_mispredictions, tma_branch_mispredicts, tma_info_bad_spec_branch_misprediction_cost", "ScaleUnit": "100%", "Unit": "cpu_core" @@ -2449,18 +2452,18 @@ "Unit": "cpu_core" }, { - "BriefDescription": "This metric estimates penalty in terms of percentage of([SKL+] injected blend uops out of all Uops Issued , the Count Domain; [ADL+] cycles)", + "BriefDescription": "This metric estimates penalty in terms of percentage of([SKL+] injected blend uops out of all Uops Issued -- the Count Domain; [ADL+] cycles)", "MetricExpr": "160 * cpu_core@ASSISTS.SSE_AVX_MIX@ / tma_info_thread_clks", "MetricGroup": "TopdownL5;tma_L5_group;tma_issueMV;tma_ports_utilized_0_group", "MetricName": "tma_mixing_vectors", "MetricThreshold": "tma_mixing_vectors > 0.05", - "PublicDescription": "This metric estimates penalty in terms of percentage of([SKL+] injected blend uops out of all Uops Issued , the Count Domain; [ADL+] cycles). Usually a Mixing_Vectors over 5% is worth investigating. Read more in Appendix B1 of the Optimizations Guide for this topic. Related metrics: tma_ms_switches", + "PublicDescription": "This metric estimates penalty in terms of percentage of([SKL+] injected blend uops out of all Uops Issued -- the Count Domain; [ADL+] cycles). Usually a Mixing_Vectors over 5% is worth investigating. Read more in Appendix B1 of the Optimizations Guide for this topic. Related metrics: tma_ms_switches", "ScaleUnit": "100%", "Unit": "cpu_core" }, { - "BriefDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to the Microcode Sequencer (MS) unit - see Microcode_Sequencer node for details", - "MetricExpr": "max(cpu_core@IDQ.MS_CYCLES_ANY@, cpu_core@UOPS_RETIRED.MS\\,cmask\\=0x1@ / (cpu_core@UOPS_RETIRED.SLOTS@ / cpu_core@UOPS_ISSUED.ANY@)) / tma_info_core_core_clks / 2", + "BriefDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to the Microcode Sequencer (MS) unit - see Microcode_Sequencer node for details.", + "MetricExpr": "max(cpu_core@IDQ.MS_CYCLES_ANY@, cpu_core@UOPS_RETIRED.MS\\,cmask\\=1@ / (cpu_core@UOPS_RETIRED.SLOTS@ / cpu_core@UOPS_ISSUED.ANY@)) / tma_info_core_core_clks / 2", "MetricGroup": "MicroSeq;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group", "MetricName": "tma_ms", "MetricThreshold": "tma_ms > 0.05 & tma_fetch_bandwidth > 0.2", @@ -2469,10 +2472,10 @@ }, { "BriefDescription": "This metric estimates the fraction of cycles when the CPU was stalled due to switches of uop delivery to the Microcode Sequencer (MS)", - "MetricExpr": "3 * cpu_core@UOPS_RETIRED.MS\\,cmask\\=0x1\\,edge\\=0x1@ / (cpu_core@UOPS_RETIRED.SLOTS@ / cpu_core@UOPS_ISSUED.ANY@) / tma_info_thread_clks", + "MetricExpr": "3 * cpu_core@UOPS_RETIRED.MS\\,cmask\\=1\\,edge@ / (cpu_core@UOPS_RETIRED.SLOTS@ / cpu_core@UOPS_ISSUED.ANY@) / tma_info_thread_clks", "MetricGroup": "FetchLat;MicroSeq;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueMC;tma_issueMS;tma_issueMV;tma_issueSO", "MetricName": "tma_ms_switches", - "MetricThreshold": "tma_ms_switches > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricThreshold": "tma_ms_switches > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", "PublicDescription": "This metric estimates the fraction of cycles when the CPU was stalled due to switches of uop delivery to the Microcode Sequencer (MS). Commonly used instructions are optimized for delivery by the DSB (decoded i-cache) or MITE (legacy instruction decode) pipelines. Certain operations cannot be handled natively by the execution pipeline; and must be performed by microcode (small programs injected into the execution stream). Switching to the MS too often can negatively impact performance. The MS is designated to deliver long uop flows required by CISC instructions like CPUID; or uncommon conditions like Floating Point Assists when dealing with Denormals. Sample with: FRONTEND_RETIRED.MS_FLOWS. Related metrics: tma_bottleneck_irregular_overhead, tma_clears_resteers, tma_l1_bound, tma_machine_clears, tma_microcode_sequencer, tma_mixing_vectors, tma_serializing_operation", "ScaleUnit": "100%", "Unit": "cpu_core" @@ -2483,7 +2486,7 @@ "MetricGroup": "Branches;BvBO;Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group", "MetricName": "tma_non_fused_branches", "MetricThreshold": "tma_non_fused_branches > 0.1 & tma_light_operations > 0.6", - "PublicDescription": "This metric represents fraction of slots where the CPU was retiring branch instructions that were not fused. Non-conditional branches like direct JMP or CALL would count here. Can be used to examine fusible conditional jumps that were not fused", + "PublicDescription": "This metric represents fraction of slots where the CPU was retiring branch instructions that were not fused. Non-conditional branches like direct JMP or CALL would count here. Can be used to examine fusible conditional jumps that were not fused.", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -2492,7 +2495,7 @@ "MetricExpr": "tma_light_operations * cpu_core@INST_RETIRED.NOP@ / (tma_retiring * tma_info_thread_slots)", "MetricGroup": "BvBO;Pipeline;TopdownL4;tma_L4_group;tma_other_light_ops_group", "MetricName": "tma_nop_instructions", - "MetricThreshold": "tma_nop_instructions > 0.1 & tma_other_light_ops > 0.3 & tma_light_operations > 0.6", + "MetricThreshold": "tma_nop_instructions > 0.1 & (tma_other_light_ops > 0.3 & tma_light_operations > 0.6)", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring NOP (no op) instructions. Compilers often use NOPs for certain address alignments - e.g. start address of a function or loop body. Sample with: INST_RETIRED.NOP", "ScaleUnit": "100%", "Unit": "cpu_core" @@ -2508,20 +2511,20 @@ "Unit": "cpu_core" }, { - "BriefDescription": "This metric estimates fraction of slots the CPU was stalled due to other cases of misprediction (non-retired x86 branches or other types)", + "BriefDescription": "This metric estimates fraction of slots the CPU was stalled due to other cases of misprediction (non-retired x86 branches or other types).", "MetricExpr": "max(tma_branch_mispredicts * (1 - cpu_core@BR_MISP_RETIRED.ALL_BRANCHES@ / (cpu_core@INT_MISC.CLEARS_COUNT@ - cpu_core@MACHINE_CLEARS.COUNT@)), 0.0001)", "MetricGroup": "BrMispredicts;BvIO;TopdownL3;tma_L3_group;tma_branch_mispredicts_group", "MetricName": "tma_other_mispredicts", - "MetricThreshold": "tma_other_mispredicts > 0.05 & tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", + "MetricThreshold": "tma_other_mispredicts > 0.05 & (tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15)", "ScaleUnit": "100%", "Unit": "cpu_core" }, { - "BriefDescription": "This metric represents fraction of slots the CPU has wasted due to Nukes (Machine Clears) not related to memory ordering", + "BriefDescription": "This metric represents fraction of slots the CPU has wasted due to Nukes (Machine Clears) not related to memory ordering.", "MetricExpr": "max(tma_machine_clears * (1 - cpu_core@MACHINE_CLEARS.MEMORY_ORDERING@ / cpu_core@MACHINE_CLEARS.COUNT@), 0.0001)", "MetricGroup": "BvIO;Machine_Clears;TopdownL3;tma_L3_group;tma_machine_clears_group", "MetricName": "tma_other_nukes", - "MetricThreshold": "tma_other_nukes > 0.05 & tma_machine_clears > 0.1 & tma_bad_speculation > 0.15", + "MetricThreshold": "tma_other_nukes > 0.05 & (tma_machine_clears > 0.1 & tma_bad_speculation > 0.15)", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -2531,7 +2534,7 @@ "MetricGroup": "TopdownL5;tma_L5_group;tma_assists_group", "MetricName": "tma_page_faults", "MetricThreshold": "tma_page_faults > 0.05", - "PublicDescription": "This metric roughly estimates fraction of slots the CPU retired uops as a result of handing Page Faults. A Page Fault may apply on first application access to a memory page. Note operating system handling of page faults accounts for the majority of its cost", + "PublicDescription": "This metric roughly estimates fraction of slots the CPU retired uops as a result of handing Page Faults. A Page Fault may apply on first application access to a memory page. Note operating system handling of page faults accounts for the majority of its cost.", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -2541,7 +2544,7 @@ "MetricGroup": "Compute;TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P", "MetricName": "tma_port_0", "MetricThreshold": "tma_port_0 > 0.6", - "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 0 ([SNB+] ALU; [HSW+] ALU and 2nd branch). Sample with: UOPS_DISPATCHED.PORT_0. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_int_vector_128b, tma_int_vector_256b, tma_port_1, tma_port_6, tma_ports_utilized_2", + "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 0 ([SNB+] ALU; [HSW+] ALU and 2nd branch). Sample with: UOPS_DISPATCHED.PORT_0. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -2551,7 +2554,7 @@ "MetricGroup": "TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P", "MetricName": "tma_port_1", "MetricThreshold": "tma_port_1 > 0.6", - "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 1 (ALU). Sample with: UOPS_DISPATCHED.PORT_1. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_6, tma_ports_utilized_2", + "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 1 (ALU). Sample with: UOPS_DISPATCHED.PORT_1. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_5, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -2561,7 +2564,7 @@ "MetricGroup": "TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P", "MetricName": "tma_port_6", "MetricThreshold": "tma_port_6 > 0.6", - "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 6 ([HSW+] Primary Branch and simple ALU). Sample with: UOPS_DISPATCHED.PORT_1. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_ports_utilized_2", + "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 6 ([HSW+] Primary Branch and simple ALU). Sample with: UOPS_DISPATCHED.PORT_1. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_ports_utilized_2", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -2570,8 +2573,8 @@ "MetricExpr": "((tma_ports_utilized_0 * tma_info_thread_clks + (cpu_core@EXE_ACTIVITY.1_PORTS_UTIL@ + tma_retiring * cpu_core@EXE_ACTIVITY.2_3_PORTS_UTIL@)) / tma_info_thread_clks if cpu_core@ARITH.DIV_ACTIVE@ < cpu_core@CYCLE_ACTIVITY.STALLS_TOTAL@ - cpu_core@EXE_ACTIVITY.BOUND_ON_LOADS@ else (cpu_core@EXE_ACTIVITY.1_PORTS_UTIL@ + tma_retiring * cpu_core@EXE_ACTIVITY.2_3_PORTS_UTIL@) / tma_info_thread_clks)", "MetricGroup": "PortsUtil;TopdownL3;tma_L3_group;tma_core_bound_group", "MetricName": "tma_ports_utilization", - "MetricThreshold": "tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", - "PublicDescription": "This metric estimates fraction of cycles the CPU performance was potentially limited due to Core computation issues (non divider-related). Two distinct categories can be attributed into this metric: (1) heavy data-dependency among contiguous instructions would manifest in this metric - such cases are often referred to as low Instruction Level Parallelism (ILP). (2) Contention on some hardware execution unit other than Divider. For example; when there are too many multiply operations", + "MetricThreshold": "tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)", + "PublicDescription": "This metric estimates fraction of cycles the CPU performance was potentially limited due to Core computation issues (non divider-related). Two distinct categories can be attributed into this metric: (1) heavy data-dependency among contiguous instructions would manifest in this metric - such cases are often referred to as low Instruction Level Parallelism (ILP). (2) Contention on some hardware execution unit other than Divider. For example; when there are too many multiply operations.", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -2580,8 +2583,8 @@ "MetricExpr": "max(cpu_core@EXE_ACTIVITY.EXE_BOUND_0_PORTS@ - cpu_core@RESOURCE_STALLS.SCOREBOARD@, 0) / tma_info_thread_clks", "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group", "MetricName": "tma_ports_utilized_0", - "MetricThreshold": "tma_ports_utilized_0 > 0.2 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", - "PublicDescription": "This metric represents fraction of cycles CPU executed no uops on any execution port (Logical Processor cycles since ICL, Physical Core cycles otherwise). Long-latency instructions like divides may contribute to this metric", + "MetricThreshold": "tma_ports_utilized_0 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric represents fraction of cycles CPU executed no uops on any execution port (Logical Processor cycles since ICL, Physical Core cycles otherwise). Long-latency instructions like divides may contribute to this metric.", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -2590,7 +2593,7 @@ "MetricExpr": "cpu_core@EXE_ACTIVITY.1_PORTS_UTIL@ / tma_info_thread_clks", "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_issueL1;tma_ports_utilization_group", "MetricName": "tma_ports_utilized_1", - "MetricThreshold": "tma_ports_utilized_1 > 0.2 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_ports_utilized_1 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", "PublicDescription": "This metric represents fraction of cycles where the CPU executed total of 1 uop per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise). This can be due to heavy data-dependency among software instructions; or over oversubscribing a particular hardware resource. In some other cases with high 1_Port_Utilized and L1_Bound; this metric can point to L1 data-cache latency bottleneck that may not necessarily manifest with complete execution starvation (due to the short L1 latency e.g. walking a linked list) - looking at the assembly can be helpful. Sample with: EXE_ACTIVITY.1_PORTS_UTIL. Related metrics: tma_l1_bound", "ScaleUnit": "100%", "Unit": "cpu_core" @@ -2601,8 +2604,8 @@ "MetricExpr": "cpu_core@EXE_ACTIVITY.2_PORTS_UTIL@ / tma_info_thread_clks", "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_issue2P;tma_ports_utilization_group", "MetricName": "tma_ports_utilized_2", - "MetricThreshold": "tma_ports_utilized_2 > 0.15 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", - "PublicDescription": "This metric represents fraction of cycles CPU executed total of 2 uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise). Loop Vectorization -most compilers feature auto-Vectorization options today- reduces pressure on the execution ports as multiple elements are calculated with same uop. Sample with: EXE_ACTIVITY.2_PORTS_UTIL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_6", + "MetricThreshold": "tma_ports_utilized_2 > 0.15 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric represents fraction of cycles CPU executed total of 2 uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise). Loop Vectorization -most compilers feature auto-Vectorization options today- reduces pressure on the execution ports as multiple elements are calculated with same uop. Sample with: EXE_ACTIVITY.2_PORTS_UTIL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_port_6", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -2612,24 +2615,24 @@ "MetricExpr": "cpu_core@UOPS_EXECUTED.CYCLES_GE_3@ / tma_info_thread_clks", "MetricGroup": "BvCB;PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group", "MetricName": "tma_ports_utilized_3m", - "MetricThreshold": "tma_ports_utilized_3m > 0.4 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_ports_utilized_3m > 0.4 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", "PublicDescription": "This metric represents fraction of cycles CPU executed total of 3 or more uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise). Sample with: UOPS_EXECUTED.CYCLES_GE_3", "ScaleUnit": "100%", "Unit": "cpu_core" }, { - "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to retired misprediction by (indirect) RET instructions", - "MetricExpr": "cpu_core@BR_MISP_RETIRED.RET_COST@ * cpu_core@br_misp_retired.ret_cost@R / tma_info_thread_clks", + "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to retired misprediction by (indirect) RET instructions.", + "MetricExpr": "cpu_core@BR_MISP_RETIRED.RET_COST@ * cpu_core@BR_MISP_RETIRED.RET_COST@R / tma_info_thread_clks", "MetricGroup": "BrMispredicts;TopdownL3;tma_L3_group;tma_branch_mispredicts_group", "MetricName": "tma_ret_mispredicts", - "MetricThreshold": "tma_ret_mispredicts > 0.05 & tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", + "MetricThreshold": "tma_ret_mispredicts > 0.05 & (tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15)", "ScaleUnit": "100%", "Unit": "cpu_core" }, { "BriefDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired", "DefaultMetricgroupName": "TopdownL1", - "MetricExpr": "topdown\\-retiring / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * slots", + "MetricExpr": "cpu_core@topdown\\-retiring@ / (cpu_core@topdown\\-fe\\-bound@ + cpu_core@topdown\\-bad\\-spec@ + cpu_core@topdown\\-retiring@ + cpu_core@topdown\\-be\\-bound@) + 0 * tma_info_thread_slots", "MetricGroup": "BvUW;Default;TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_retiring", "MetricThreshold": "tma_retiring > 0.7 | tma_heavy_operations > 0.1", @@ -2643,7 +2646,7 @@ "MetricExpr": "cpu_core@RESOURCE_STALLS.SCOREBOARD@ / tma_info_thread_clks + tma_c02_wait", "MetricGroup": "BvIO;PortsUtil;TopdownL3;tma_L3_group;tma_core_bound_group;tma_issueSO", "MetricName": "tma_serializing_operation", - "MetricThreshold": "tma_serializing_operation > 0.1 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_serializing_operation > 0.1 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)", "PublicDescription": "This metric represents fraction of cycles the CPU issue-pipeline was stalled due to serializing operations. Instructions like CPUID; WRMSR or LFENCE serialize the out-of-order execution which may limit performance. Sample with: RESOURCE_STALLS.SCOREBOARD. Related metrics: tma_ms_switches", "ScaleUnit": "100%", "Unit": "cpu_core" @@ -2653,8 +2656,8 @@ "MetricExpr": "tma_light_operations * cpu_core@INT_VEC_RETIRED.SHUFFLES@ / (tma_retiring * tma_info_thread_slots)", "MetricGroup": "HPC;Pipeline;TopdownL4;tma_L4_group;tma_other_light_ops_group", "MetricName": "tma_shuffles_256b", - "MetricThreshold": "tma_shuffles_256b > 0.1 & tma_other_light_ops > 0.3 & tma_light_operations > 0.6", - "PublicDescription": "This metric represents fraction of slots where the CPU was retiring Shuffle operations of 256-bit vector size (FP or Integer). Shuffles may incur slow cross \"vector lane\" data transfers", + "MetricThreshold": "tma_shuffles_256b > 0.1 & (tma_other_light_ops > 0.3 & tma_light_operations > 0.6)", + "PublicDescription": "This metric represents fraction of slots where the CPU was retiring Shuffle operations of 256-bit vector size (FP or Integer). Shuffles may incur slow cross \"vector lane\" data transfers.", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -2664,28 +2667,28 @@ "MetricExpr": "cpu_core@CPU_CLK_UNHALTED.PAUSE@ / tma_info_thread_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_serializing_operation_group", "MetricName": "tma_slow_pause", - "MetricThreshold": "tma_slow_pause > 0.05 & tma_serializing_operation > 0.1 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_slow_pause > 0.05 & (tma_serializing_operation > 0.1 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to PAUSE Instructions. Sample with: CPU_CLK_UNHALTED.PAUSE_INST", "ScaleUnit": "100%", "Unit": "cpu_core" }, { "BriefDescription": "This metric estimates fraction of cycles handling memory load split accesses - load that cross 64-byte cache line boundary", - "MetricExpr": "(min(cpu_core@MEM_INST_RETIRED.SPLIT_LOADS@ * cpu_core@mem_inst_retired.split_loads@R, cpu_core@MEM_INST_RETIRED.SPLIT_LOADS@ * tma_info_memory_load_miss_real_latency) if 0 < cpu_core@mem_inst_retired.split_loads@R else cpu_core@MEM_INST_RETIRED.SPLIT_LOADS@ * tma_info_memory_load_miss_real_latency) / tma_info_thread_clks", + "MetricExpr": "cpu_core@MEM_INST_RETIRED.SPLIT_LOADS@ * min(cpu_core@MEM_INST_RETIRED.SPLIT_LOADS@R, tma_info_memory_load_miss_real_latency) / tma_info_thread_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group", "MetricName": "tma_split_loads", "MetricThreshold": "tma_split_loads > 0.3", - "PublicDescription": "This metric estimates fraction of cycles handling memory load split accesses - load that cross 64-byte cache line boundary. Sample with: MEM_INST_RETIRED.SPLIT_LOADS", + "PublicDescription": "This metric estimates fraction of cycles handling memory load split accesses - load that cross 64-byte cache line boundary. Sample with: MEM_INST_RETIRED.SPLIT_LOADS_PS", "ScaleUnit": "100%", "Unit": "cpu_core" }, { "BriefDescription": "This metric represents rate of split store accesses", - "MetricExpr": "(min(cpu_core@MEM_INST_RETIRED.SPLIT_STORES@ * cpu_core@mem_inst_retired.split_stores@R, cpu_core@MEM_INST_RETIRED.SPLIT_STORES@) if 0 < cpu_core@mem_inst_retired.split_stores@R else cpu_core@MEM_INST_RETIRED.SPLIT_STORES@) / tma_info_thread_clks", + "MetricExpr": "cpu_core@MEM_INST_RETIRED.SPLIT_STORES@ * min(cpu_core@MEM_INST_RETIRED.SPLIT_STORES@R, 1) / tma_info_thread_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_issueSpSt;tma_store_bound_group", "MetricName": "tma_split_stores", - "MetricThreshold": "tma_split_stores > 0.2 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", - "PublicDescription": "This metric represents rate of split store accesses. Consider aligning your data to the 64-byte cache line granularity. Sample with: MEM_INST_RETIRED.SPLIT_STORES", + "MetricThreshold": "tma_split_stores > 0.2 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric represents rate of split store accesses. Consider aligning your data to the 64-byte cache line granularity. Sample with: MEM_INST_RETIRED.SPLIT_STORES_PS. Related metrics: tma_port_4", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -2694,8 +2697,8 @@ "MetricExpr": "(cpu_core@XQ.FULL_CYCLES@ + cpu_core@L1D_PEND_MISS.L2_STALLS@) / tma_info_thread_clks", "MetricGroup": "BvMB;MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_issueBW;tma_l3_bound_group", "MetricName": "tma_sq_full", - "MetricThreshold": "tma_sq_full > 0.3 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", - "PublicDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors). Related metrics: tma_bottleneck_cache_memory_bandwidth, tma_fb_full, tma_mem_bandwidth", + "MetricThreshold": "tma_sq_full > 0.3 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors). Related metrics: tma_bottleneck_cache_memory_bandwidth, tma_fb_full, tma_info_system_dram_bw_use, tma_mem_bandwidth", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -2704,8 +2707,8 @@ "MetricExpr": "cpu_core@EXE_ACTIVITY.BOUND_ON_STORES@ / tma_info_thread_clks", "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_store_bound", - "MetricThreshold": "tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", - "PublicDescription": "This metric estimates how often CPU was stalled due to RFO store memory accesses; RFO store issue a read-for-ownership request before the write. Even though store accesses do not typically stall out-of-order CPUs; there are few cases where stores can lead to actual stalls. This metric will be flagged should RFO stores be a bottleneck. Sample with: MEM_INST_RETIRED.ALL_STORES", + "MetricThreshold": "tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", + "PublicDescription": "This metric estimates how often CPU was stalled due to RFO store memory accesses; RFO store issue a read-for-ownership request before the write. Even though store accesses do not typically stall out-of-order CPUs; there are few cases where stores can lead to actual stalls. This metric will be flagged should RFO stores be a bottleneck. Sample with: MEM_INST_RETIRED.ALL_STORES_PS", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -2714,8 +2717,8 @@ "MetricExpr": "13 * cpu_core@LD_BLOCKS.STORE_FORWARD@ / tma_info_thread_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group", "MetricName": "tma_store_fwd_blk", - "MetricThreshold": "tma_store_fwd_blk > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", - "PublicDescription": "This metric roughly estimates fraction of cycles when the memory subsystem had loads blocked since they could not forward data from earlier (in program order) overlapping stores. To streamline memory operations in the pipeline; a load can avoid waiting for memory if a prior in-flight store is writing the data that the load wants to read (store forwarding process). However; in some cases the load may be blocked for a significant time pending the store forward. For example; when the prior store is writing a smaller region than the load is reading", + "MetricThreshold": "tma_store_fwd_blk > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric roughly estimates fraction of cycles when the memory subsystem had loads blocked since they could not forward data from earlier (in program order) overlapping stores. To streamline memory operations in the pipeline; a load can avoid waiting for memory if a prior in-flight store is writing the data that the load wants to read (store forwarding process). However; in some cases the load may be blocked for a significant time pending the store forward. For example; when the prior store is writing a smaller region than the load is reading.", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -2724,8 +2727,8 @@ "MetricExpr": "(cpu_core@MEM_STORE_RETIRED.L2_HIT@ * 10 * (1 - cpu_core@MEM_INST_RETIRED.LOCK_LOADS@ / cpu_core@MEM_INST_RETIRED.ALL_STORES@) + (1 - cpu_core@MEM_INST_RETIRED.LOCK_LOADS@ / cpu_core@MEM_INST_RETIRED.ALL_STORES@) * min(cpu_core@CPU_CLK_UNHALTED.THREAD@, cpu_core@OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO@)) / tma_info_thread_clks", "MetricGroup": "BvML;LockCont;MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_issueSL;tma_store_bound_group", "MetricName": "tma_store_latency", - "MetricThreshold": "tma_store_latency > 0.1 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", - "PublicDescription": "This metric estimates fraction of cycles the CPU spent handling L1D store misses. Store accesses usually less impact out-of-order core performance; however; holding resources for longer time can lead into undesired implications (e.g. contention on L1D fill-buffer entries - see FB_Full). Related metrics: tma_branch_resteers, tma_fb_full, tma_l3_hit_latency, tma_lock_latency", + "MetricThreshold": "tma_store_latency > 0.1 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric estimates fraction of cycles the CPU spent handling L1D store misses. Store accesses usually less impact out-of-order core performance; however; holding resources for longer time can lead into undesired implications (e.g. contention on L1D fill-buffer entries - see FB_Full). Related metrics: tma_fb_full, tma_lock_latency", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -2744,7 +2747,7 @@ "MetricExpr": "max(0, tma_dtlb_store - tma_store_stlb_miss)", "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_store_group", "MetricName": "tma_store_stlb_hit", - "MetricThreshold": "tma_store_stlb_hit > 0.05 & tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_store_stlb_hit > 0.05 & (tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -2753,34 +2756,34 @@ "MetricExpr": "cpu_core@DTLB_STORE_MISSES.WALK_ACTIVE@ / tma_info_core_core_clks", "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_store_group", "MetricName": "tma_store_stlb_miss", - "MetricThreshold": "tma_store_stlb_miss > 0.05 & tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_store_stlb_miss > 0.05 & (tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))", "ScaleUnit": "100%", "Unit": "cpu_core" }, { - "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 1 GB pages for data store accesses", + "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 1 GB pages for data store accesses.", "MetricExpr": "tma_store_stlb_miss * cpu_core@DTLB_STORE_MISSES.WALK_COMPLETED_1G@ / (cpu_core@DTLB_STORE_MISSES.WALK_COMPLETED_4K@ + cpu_core@DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M@ + cpu_core@DTLB_STORE_MISSES.WALK_COMPLETED_1G@)", "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_store_stlb_miss_group", "MetricName": "tma_store_stlb_miss_1g", - "MetricThreshold": "tma_store_stlb_miss_1g > 0.05 & tma_store_stlb_miss > 0.05 & tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_store_stlb_miss_1g > 0.05 & (tma_store_stlb_miss > 0.05 & (tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))))", "ScaleUnit": "100%", "Unit": "cpu_core" }, { - "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 2 or 4 MB pages for data store accesses", + "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 2 or 4 MB pages for data store accesses.", "MetricExpr": "tma_store_stlb_miss * cpu_core@DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M@ / (cpu_core@DTLB_STORE_MISSES.WALK_COMPLETED_4K@ + cpu_core@DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M@ + cpu_core@DTLB_STORE_MISSES.WALK_COMPLETED_1G@)", "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_store_stlb_miss_group", "MetricName": "tma_store_stlb_miss_2m", - "MetricThreshold": "tma_store_stlb_miss_2m > 0.05 & tma_store_stlb_miss > 0.05 & tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_store_stlb_miss_2m > 0.05 & (tma_store_stlb_miss > 0.05 & (tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))))", "ScaleUnit": "100%", "Unit": "cpu_core" }, { - "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 4 KB pages for data store accesses", + "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 4 KB pages for data store accesses.", "MetricExpr": "tma_store_stlb_miss * cpu_core@DTLB_STORE_MISSES.WALK_COMPLETED_4K@ / (cpu_core@DTLB_STORE_MISSES.WALK_COMPLETED_4K@ + cpu_core@DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M@ + cpu_core@DTLB_STORE_MISSES.WALK_COMPLETED_1G@)", "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_store_stlb_miss_group", "MetricName": "tma_store_stlb_miss_4k", - "MetricThreshold": "tma_store_stlb_miss_4k > 0.05 & tma_store_stlb_miss > 0.05 & tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_store_stlb_miss_4k > 0.05 & (tma_store_stlb_miss > 0.05 & (tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))))", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -2789,7 +2792,7 @@ "MetricExpr": "9 * cpu_core@OCR.STREAMING_WR.ANY_RESPONSE@ / tma_info_thread_clks", "MetricGroup": "MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_issueSmSt;tma_store_bound_group", "MetricName": "tma_streaming_stores", - "MetricThreshold": "tma_streaming_stores > 0.2 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_streaming_stores > 0.2 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", "PublicDescription": "This metric estimates how often CPU was stalled due to Streaming store memory accesses; Streaming store optimize out a read request required by RFO stores. Even though store accesses do not typically stall out-of-order CPUs; there are few cases where stores can lead to actual stalls. This metric will be flagged should Streaming stores be a bottleneck. Sample with: OCR.STREAMING_WR.ANY_RESPONSE. Related metrics: tma_fb_full", "ScaleUnit": "100%", "Unit": "cpu_core" @@ -2799,7 +2802,7 @@ "MetricExpr": "cpu_core@INT_MISC.UNKNOWN_BRANCH_CYCLES@ / tma_info_thread_clks", "MetricGroup": "BigFootprint;BvBC;FetchLat;TopdownL4;tma_L4_group;tma_branch_resteers_group", "MetricName": "tma_unknown_branches", - "MetricThreshold": "tma_unknown_branches > 0.05 & tma_branch_resteers > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricThreshold": "tma_unknown_branches > 0.05 & (tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))", "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to new branch address clears. These are fetched branches the Branch Prediction Unit was unable to recognize (e.g. first time the branch is fetched or hitting BTB capacity limit) hence called Unknown Branches. Sample with: FRONTEND_RETIRED.UNKNOWN_BRANCH", "ScaleUnit": "100%", "Unit": "cpu_core" @@ -2809,8 +2812,8 @@ "MetricExpr": "tma_retiring * cpu_core@UOPS_EXECUTED.X87@ / cpu_core@UOPS_EXECUTED.THREAD@", "MetricGroup": "Compute;TopdownL4;tma_L4_group;tma_fp_arith_group", "MetricName": "tma_x87_use", - "MetricThreshold": "tma_x87_use > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6", - "PublicDescription": "This metric serves as an approximation of legacy x87 usage. It accounts for instructions beyond X87 FP arithmetic operations; hence may be used as a thermometer to avoid X87 high usage and preferably upgrade to modern ISA. See Tip under Tuning Hint", + "MetricThreshold": "tma_x87_use > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6)", + "PublicDescription": "This metric serves as an approximation of legacy x87 usage. It accounts for instructions beyond X87 FP arithmetic operations; hence may be used as a thermometer to avoid X87 high usage and preferably upgrade to modern ISA. See Tip under Tuning Hint.", "ScaleUnit": "100%", "Unit": "cpu_core" } diff --git a/tools/perf/pmu-events/arch/x86/meteorlake/other.json b/tools/perf/pmu-events/arch/x86/meteorlake/other.json index 46a21776a4e9..cb21bb933617 100644 --- a/tools/perf/pmu-events/arch/x86/meteorlake/other.json +++ b/tools/perf/pmu-events/arch/x86/meteorlake/other.json @@ -4,7 +4,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc1", "EventName": "ASSISTS.HARDWARE", - "PublicDescription": "Count all other hardware assists or traps that are not necessarily architecturally exposed (through a software handler) beyond FP; SSE-AVX mix and A/D assists who are counted by dedicated sub-events. This includes, but not limited to, assists at EXE or MEM uop writeback like AVX* load/store/gather/scatter (non-FP GSSE-assist ) , assists generated by ROB like PEBS and RTIT, Uncore trap, RAR (Remote Action Request) and CET (Control flow Enforcement Technology) assists. the event also counts for Machine Ordering count.", + "PublicDescription": "Count all other hardware assists or traps that are not necessarily architecturally exposed (through a software handler) beyond FP; SSE-AVX mix and A/D assists who are counted by dedicated sub-events. This includes, but not limited to, assists at EXE or MEM uop writeback like AVX* load/store/gather/scatter (non-FP GSSE-assist ) , assists generated by ROB like PEBS and RTIT, Uncore trap, RAR (Remote Action Request) and CET (Control flow Enforcement Technology) assists. the event also counts for Machine Ordering count. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x4", "Unit": "cpu_core" @@ -14,6 +14,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc1", "EventName": "ASSISTS.PAGE_FAULT", + "PublicDescription": "ASSISTS.PAGE_FAULT Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x8", "Unit": "cpu_core" @@ -29,111 +30,13 @@ "Unit": "cpu_atom" }, { - "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that have any type of response.", - "Counter": "0,1,2,3,4,5,6,7", - "EventCode": "0xB7", - "EventName": "OCR.DEMAND_CODE_RD.ANY_RESPONSE", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x10004", - "SampleAfterValue": "100003", - "UMask": "0x1", - "Unit": "cpu_atom" - }, - { - "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were supplied by DRAM.", - "Counter": "0,1,2,3,4,5,6,7", - "EventCode": "0xB7", - "EventName": "OCR.DEMAND_CODE_RD.DRAM", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x184000004", - "SampleAfterValue": "100003", - "UMask": "0x1", - "Unit": "cpu_atom" - }, - { - "BriefDescription": "Counts demand data reads that have any type of response.", - "Counter": "0,1,2,3,4,5,6,7", - "EventCode": "0xB7", - "EventName": "OCR.DEMAND_DATA_RD.ANY_RESPONSE", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x10001", - "SampleAfterValue": "100003", - "UMask": "0x1", - "Unit": "cpu_atom" - }, - { - "BriefDescription": "Counts demand data reads that have any type of response.", - "Counter": "0,1,2,3", - "EventCode": "0x2A,0x2B", - "EventName": "OCR.DEMAND_DATA_RD.ANY_RESPONSE", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x10001", - "SampleAfterValue": "100003", - "UMask": "0x1", - "Unit": "cpu_core" - }, - { - "BriefDescription": "Counts demand data reads that were supplied by DRAM.", - "Counter": "0,1,2,3,4,5,6,7", - "EventCode": "0xB7", - "EventName": "OCR.DEMAND_DATA_RD.DRAM", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x184000001", - "SampleAfterValue": "100003", - "UMask": "0x1", - "Unit": "cpu_atom" - }, - { - "BriefDescription": "Counts demand data reads that were supplied by DRAM.", - "Counter": "0,1,2,3", - "EventCode": "0x2A,0x2B", - "EventName": "OCR.DEMAND_DATA_RD.DRAM", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x184000001", - "SampleAfterValue": "100003", - "UMask": "0x1", - "Unit": "cpu_core" - }, - { - "BriefDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that have any type of response.", - "Counter": "0,1,2,3,4,5,6,7", - "EventCode": "0xB7", - "EventName": "OCR.DEMAND_RFO.ANY_RESPONSE", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x10002", - "SampleAfterValue": "100003", - "UMask": "0x1", - "Unit": "cpu_atom" - }, - { - "BriefDescription": "Counts demand read for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that have any type of response.", - "Counter": "0,1,2,3", - "EventCode": "0x2A,0x2B", - "EventName": "OCR.DEMAND_RFO.ANY_RESPONSE", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x10002", - "SampleAfterValue": "100003", - "UMask": "0x1", - "Unit": "cpu_core" - }, - { - "BriefDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that were supplied by DRAM.", - "Counter": "0,1,2,3,4,5,6,7", - "EventCode": "0xB7", - "EventName": "OCR.DEMAND_RFO.DRAM", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x184000002", - "SampleAfterValue": "100003", - "UMask": "0x1", - "Unit": "cpu_atom" - }, - { "BriefDescription": "Counts streaming stores which modify a full 64 byte cacheline that have any type of response.", "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xB7", "EventName": "OCR.FULL_STREAMING_WR.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x800000010000", + "PublicDescription": "Counts streaming stores which modify a full 64 byte cacheline that have any type of response. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1", "Unit": "cpu_atom" @@ -145,6 +48,7 @@ "EventName": "OCR.PARTIAL_STREAMING_WR.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x400000010000", + "PublicDescription": "Counts streaming stores which modify only part of a 64 byte cacheline that have any type of response. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1", "Unit": "cpu_atom" @@ -156,6 +60,7 @@ "EventName": "OCR.STREAMING_WR.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x10800", + "PublicDescription": "Counts streaming stores that have any type of response. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1", "Unit": "cpu_atom" @@ -167,58 +72,18 @@ "EventName": "OCR.STREAMING_WR.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x10800", + "PublicDescription": "Counts streaming stores that have any type of response. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1", "Unit": "cpu_core" }, { - "BriefDescription": "Cycles when Reservation Station (RS) is empty for the thread.", - "Counter": "0,1,2,3,4,5,6,7", - "EventCode": "0xa5", - "EventName": "RS.EMPTY", - "PublicDescription": "Counts cycles during which the reservation station (RS) is empty for this logical processor. This is usually caused when the front-end pipeline runs into starvation periods (e.g. branch mispredictions or i-cache misses)", - "SampleAfterValue": "1000003", - "UMask": "0x7", - "Unit": "cpu_core" - }, - { - "BriefDescription": "Counts end of periods where the Reservation Station (RS) was empty.", - "Counter": "0,1,2,3,4,5,6,7", - "CounterMask": "1", - "EdgeDetect": "1", - "EventCode": "0xa5", - "EventName": "RS.EMPTY_COUNT", - "Invert": "1", - "PublicDescription": "Counts end of periods where the Reservation Station (RS) was empty. Could be useful to closely sample on front-end latency issues (see the FRONTEND_RETIRED event of designated precise events)", - "SampleAfterValue": "100003", - "UMask": "0x7", - "Unit": "cpu_core" - }, - { - "BriefDescription": "Cycles when RS was empty and a resource allocation stall is asserted", - "Counter": "0,1,2,3,4,5,6,7", - "EventCode": "0xa5", - "EventName": "RS.EMPTY_RESOURCE", - "SampleAfterValue": "1000003", - "UMask": "0x1", - "Unit": "cpu_core" - }, - { - "BriefDescription": "Counts the number of issue slots in a UMWAIT or TPAUSE instruction where no uop issues due to the instruction putting the CPU into the C0.1 activity state.", - "Counter": "0,1,2,3,4,5,6,7", - "EventCode": "0x75", - "EventName": "SERIALIZATION.C01_MS_SCB", - "SampleAfterValue": "200003", - "UMask": "0x4", - "Unit": "cpu_atom" - }, - { "BriefDescription": "Cycles the uncore cannot take further requests", "Counter": "0,1,2,3", "CounterMask": "1", "EventCode": "0x2d", "EventName": "XQ.FULL_CYCLES", - "PublicDescription": "number of cycles when the thread is active and the uncore cannot take any further requests (for example prefetches, loads or stores initiated by the Core that miss the L2 cache).", + "PublicDescription": "number of cycles when the thread is active and the uncore cannot take any further requests (for example prefetches, loads or stores initiated by the Core that miss the L2 cache). Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x1", "Unit": "cpu_core" diff --git a/tools/perf/pmu-events/arch/x86/meteorlake/pipeline.json b/tools/perf/pmu-events/arch/x86/meteorlake/pipeline.json index 265f6c5a0248..a833d6f53d0e 100644 --- a/tools/perf/pmu-events/arch/x86/meteorlake/pipeline.json +++ b/tools/perf/pmu-events/arch/x86/meteorlake/pipeline.json @@ -15,7 +15,7 @@ "CounterMask": "1", "EventCode": "0xb0", "EventName": "ARITH.DIV_ACTIVE", - "PublicDescription": "Counts cycles when divide unit is busy executing divide or square root operations. Accounts for integer and floating-point operations.", + "PublicDescription": "Counts cycles when divide unit is busy executing divide or square root operations. Accounts for integer and floating-point operations. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x9", "Unit": "cpu_core" @@ -26,6 +26,7 @@ "CounterMask": "1", "EventCode": "0xb0", "EventName": "ARITH.IDIV_ACTIVE", + "PublicDescription": "This event counts the cycles the integer divider is busy. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x8", "Unit": "cpu_core" @@ -35,7 +36,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc1", "EventName": "ASSISTS.ANY", - "PublicDescription": "Counts the number of occurrences where a microcode assist is invoked by hardware. Examples include AD (page Access Dirty), FP and AVX related assists.", + "PublicDescription": "Counts the number of occurrences where a microcode assist is invoked by hardware. Examples include AD (page Access Dirty), FP and AVX related assists. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1b", "Unit": "cpu_core" @@ -54,7 +55,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.ALL_BRANCHES", - "PublicDescription": "Counts all branch instructions retired.", + "PublicDescription": "Counts all branch instructions retired. Available PDIST counters: 0", "SampleAfterValue": "400009", "Unit": "cpu_core" }, @@ -72,7 +73,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.COND", - "PublicDescription": "Counts conditional branch instructions retired.", + "PublicDescription": "Counts conditional branch instructions retired. Available PDIST counters: 0", "SampleAfterValue": "400009", "UMask": "0x11", "Unit": "cpu_core" @@ -82,7 +83,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.COND_NTAKEN", - "PublicDescription": "Counts not taken branch instructions retired.", + "PublicDescription": "Counts not taken branch instructions retired. Available PDIST counters: 0", "SampleAfterValue": "400009", "UMask": "0x10", "Unit": "cpu_core" @@ -101,7 +102,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.COND_TAKEN", - "PublicDescription": "Counts taken conditional branch instructions retired.", + "PublicDescription": "Counts taken conditional branch instructions retired. Available PDIST counters: 0", "SampleAfterValue": "400009", "UMask": "0x1", "Unit": "cpu_core" @@ -120,7 +121,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.FAR_BRANCH", - "PublicDescription": "Counts far branch instructions retired.", + "PublicDescription": "Counts far branch instructions retired. Available PDIST counters: 0", "SampleAfterValue": "100007", "UMask": "0x40", "Unit": "cpu_core" @@ -139,7 +140,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.INDIRECT", - "PublicDescription": "Counts near indirect branch instructions retired excluding returns. TSX abort is an indirect branch.", + "PublicDescription": "Counts near indirect branch instructions retired excluding returns. TSX abort is an indirect branch. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x80", "Unit": "cpu_core" @@ -186,7 +187,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.NEAR_CALL", - "PublicDescription": "Counts both direct and indirect near call instructions retired.", + "PublicDescription": "Counts both direct and indirect near call instructions retired. Available PDIST counters: 0", "SampleAfterValue": "100007", "UMask": "0x2", "Unit": "cpu_core" @@ -205,7 +206,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.NEAR_RETURN", - "PublicDescription": "Counts return instructions retired.", + "PublicDescription": "Counts return instructions retired. Available PDIST counters: 0", "SampleAfterValue": "100007", "UMask": "0x8", "Unit": "cpu_core" @@ -224,7 +225,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.NEAR_TAKEN", - "PublicDescription": "Counts taken branch instructions retired.", + "PublicDescription": "Counts taken branch instructions retired. Available PDIST counters: 0", "SampleAfterValue": "400009", "UMask": "0x20", "Unit": "cpu_core" @@ -261,7 +262,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.ALL_BRANCHES", - "PublicDescription": "Counts all the retired branch instructions that were mispredicted by the processor. A branch misprediction occurs when the processor incorrectly predicts the destination of the branch. When the misprediction is discovered at execution, all the instructions executed in the wrong (speculative) path must be discarded, and the processor must start fetching from the correct path.", + "PublicDescription": "Counts all the retired branch instructions that were mispredicted by the processor. A branch misprediction occurs when the processor incorrectly predicts the destination of the branch. When the misprediction is discovered at execution, all the instructions executed in the wrong (speculative) path must be discarded, and the processor must start fetching from the correct path. Available PDIST counters: 0", "SampleAfterValue": "400009", "Unit": "cpu_core" }, @@ -270,6 +271,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.ALL_BRANCHES_COST", + "PublicDescription": "All mispredicted branch instructions retired. This precise event may be used to get the misprediction cost via the Retire_Latency field of PEBS. It fires on the instruction that immediately follows the mispredicted branch. Available PDIST counters: 0", "SampleAfterValue": "400009", "UMask": "0x44", "Unit": "cpu_core" @@ -288,7 +290,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.COND", - "PublicDescription": "Counts mispredicted conditional branch instructions retired.", + "PublicDescription": "Counts mispredicted conditional branch instructions retired. Available PDIST counters: 0", "SampleAfterValue": "400009", "UMask": "0x11", "Unit": "cpu_core" @@ -298,6 +300,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.COND_COST", + "PublicDescription": "Mispredicted conditional branch instructions retired. This precise event may be used to get the misprediction cost via the Retire_Latency field of PEBS. It fires on the instruction that immediately follows the mispredicted branch. Available PDIST counters: 0", "SampleAfterValue": "400009", "UMask": "0x51", "Unit": "cpu_core" @@ -307,7 +310,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.COND_NTAKEN", - "PublicDescription": "Counts the number of conditional branch instructions retired that were mispredicted and the branch direction was not taken.", + "PublicDescription": "Counts the number of conditional branch instructions retired that were mispredicted and the branch direction was not taken. Available PDIST counters: 0", "SampleAfterValue": "400009", "UMask": "0x10", "Unit": "cpu_core" @@ -317,6 +320,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.COND_NTAKEN_COST", + "PublicDescription": "Mispredicted non-taken conditional branch instructions retired. This precise event may be used to get the misprediction cost via the Retire_Latency field of PEBS. It fires on the instruction that immediately follows the mispredicted branch. Available PDIST counters: 0", "SampleAfterValue": "400009", "UMask": "0x50", "Unit": "cpu_core" @@ -335,7 +339,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.COND_TAKEN", - "PublicDescription": "Counts taken conditional mispredicted branch instructions retired.", + "PublicDescription": "Counts taken conditional mispredicted branch instructions retired. Available PDIST counters: 0", "SampleAfterValue": "400009", "UMask": "0x1", "Unit": "cpu_core" @@ -345,6 +349,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.COND_TAKEN_COST", + "PublicDescription": "Mispredicted taken conditional branch instructions retired. This precise event may be used to get the misprediction cost via the Retire_Latency field of PEBS. It fires on the instruction that immediately follows the mispredicted branch. Available PDIST counters: 0", "SampleAfterValue": "400009", "UMask": "0x41", "Unit": "cpu_core" @@ -363,7 +368,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.INDIRECT", - "PublicDescription": "Counts miss-predicted near indirect branch instructions retired excluding returns. TSX abort is an indirect branch.", + "PublicDescription": "Counts miss-predicted near indirect branch instructions retired excluding returns. TSX abort is an indirect branch. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x80", "Unit": "cpu_core" @@ -382,7 +387,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.INDIRECT_CALL", - "PublicDescription": "Counts retired mispredicted indirect (near taken) CALL instructions, including both register and memory indirect.", + "PublicDescription": "Counts retired mispredicted indirect (near taken) CALL instructions, including both register and memory indirect. Available PDIST counters: 0", "SampleAfterValue": "400009", "UMask": "0x2", "Unit": "cpu_core" @@ -392,6 +397,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.INDIRECT_CALL_COST", + "PublicDescription": "Mispredicted indirect CALL retired. This precise event may be used to get the misprediction cost via the Retire_Latency field of PEBS. It fires on the instruction that immediately follows the mispredicted branch. Available PDIST counters: 0", "SampleAfterValue": "400009", "UMask": "0x42", "Unit": "cpu_core" @@ -401,6 +407,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.INDIRECT_COST", + "PublicDescription": "Mispredicted near indirect branch instructions retired (excluding returns). This precise event may be used to get the misprediction cost via the Retire_Latency field of PEBS. It fires on the instruction that immediately follows the mispredicted branch. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0xc0", "Unit": "cpu_core" @@ -428,7 +435,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.NEAR_TAKEN", - "PublicDescription": "Counts number of near branch instructions retired that were mispredicted and taken.", + "PublicDescription": "Counts number of near branch instructions retired that were mispredicted and taken. Available PDIST counters: 0", "SampleAfterValue": "400009", "UMask": "0x20", "Unit": "cpu_core" @@ -438,6 +445,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.NEAR_TAKEN_COST", + "PublicDescription": "Mispredicted taken near branch instructions retired. This precise event may be used to get the misprediction cost via the Retire_Latency field of PEBS. It fires on the instruction that immediately follows the mispredicted branch. Available PDIST counters: 0", "SampleAfterValue": "400009", "UMask": "0x60", "Unit": "cpu_core" @@ -447,7 +455,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.RET", - "PublicDescription": "This is a non-precise version (that is, does not use PEBS) of the event that counts mispredicted return instructions retired.", + "PublicDescription": "This is a non-precise version (that is, does not use PEBS) of the event that counts mispredicted return instructions retired. Available PDIST counters: 0", "SampleAfterValue": "100007", "UMask": "0x8", "Unit": "cpu_core" @@ -466,6 +474,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.RET_COST", + "PublicDescription": "Mispredicted ret instructions retired. This precise event may be used to get the misprediction cost via the Retire_Latency field of PEBS. It fires on the instruction that immediately follows the mispredicted branch. Available PDIST counters: 0", "SampleAfterValue": "100007", "UMask": "0x48", "Unit": "cpu_core" @@ -475,7 +484,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xec", "EventName": "CPU_CLK_UNHALTED.C01", - "PublicDescription": "Counts core clocks when the thread is in the C0.1 light-weight slower wakeup time but more power saving optimized state. This state can be entered via the TPAUSE or UMWAIT instructions.", + "PublicDescription": "Counts core clocks when the thread is in the C0.1 light-weight slower wakeup time but more power saving optimized state. This state can be entered via the TPAUSE or UMWAIT instructions. Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x10", "Unit": "cpu_core" @@ -485,7 +494,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xec", "EventName": "CPU_CLK_UNHALTED.C02", - "PublicDescription": "Counts core clocks when the thread is in the C0.2 light-weight faster wakeup time but less power saving optimized state. This state can be entered via the TPAUSE or UMWAIT instructions.", + "PublicDescription": "Counts core clocks when the thread is in the C0.2 light-weight faster wakeup time but less power saving optimized state. This state can be entered via the TPAUSE or UMWAIT instructions. Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x20", "Unit": "cpu_core" @@ -495,7 +504,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xec", "EventName": "CPU_CLK_UNHALTED.C0_WAIT", - "PublicDescription": "Counts core clocks when the thread is in the C0.1 or C0.2 power saving optimized states (TPAUSE or UMWAIT instructions) or running the PAUSE instruction.", + "PublicDescription": "Counts core clocks when the thread is in the C0.1 or C0.2 power saving optimized states (TPAUSE or UMWAIT instructions) or running the PAUSE instruction. Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x70", "Unit": "cpu_core" @@ -521,7 +530,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xec", "EventName": "CPU_CLK_UNHALTED.DISTRIBUTED", - "PublicDescription": "This event distributes cycle counts between active hyperthreads, i.e., those in C0. A hyperthread becomes inactive when it executes the HLT or MWAIT instructions. If all other hyperthreads are inactive (or disabled or do not exist), all counts are attributed to this hyperthread. To obtain the full count when the Core is active, sum the counts from each hyperthread.", + "PublicDescription": "This event distributes cycle counts between active hyperthreads, i.e., those in C0. A hyperthread becomes inactive when it executes the HLT or MWAIT instructions. If all other hyperthreads are inactive (or disabled or do not exist), all counts are attributed to this hyperthread. To obtain the full count when the Core is active, sum the counts from each hyperthread. Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x2", "Unit": "cpu_core" @@ -531,7 +540,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0x3c", "EventName": "CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE", - "PublicDescription": "Counts Core crystal clock cycles when current thread is unhalted and the other thread is halted.", + "PublicDescription": "Counts Core crystal clock cycles when current thread is unhalted and the other thread is halted. Available PDIST counters: 0", "SampleAfterValue": "25003", "UMask": "0x2", "Unit": "cpu_core" @@ -541,6 +550,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xec", "EventName": "CPU_CLK_UNHALTED.PAUSE", + "PublicDescription": "CPU_CLK_UNHALTED.PAUSE Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x40", "Unit": "cpu_core" @@ -552,6 +562,7 @@ "EdgeDetect": "1", "EventCode": "0xec", "EventName": "CPU_CLK_UNHALTED.PAUSE_INST", + "PublicDescription": "CPU_CLK_UNHALTED.PAUSE_INST Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x40", "Unit": "cpu_core" @@ -561,7 +572,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0x3c", "EventName": "CPU_CLK_UNHALTED.REF_DISTRIBUTED", - "PublicDescription": "This event distributes Core crystal clock cycle counts between active hyperthreads, i.e., those in C0 sleep-state. A hyperthread becomes inactive when it executes the HLT or MWAIT instructions. If one thread is active in a core, all counts are attributed to this hyperthread. To obtain the full count when the Core is active, sum the counts from each hyperthread.", + "PublicDescription": "This event distributes Core crystal clock cycle counts between active hyperthreads, i.e., those in C0 sleep-state. A hyperthread becomes inactive when it executes the HLT or MWAIT instructions. If one thread is active in a core, all counts are attributed to this hyperthread. To obtain the full count when the Core is active, sum the counts from each hyperthread. Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x8", "Unit": "cpu_core" @@ -578,7 +589,7 @@ "BriefDescription": "Reference cycles when the core is not in halt state.", "Counter": "Fixed counter 2", "EventName": "CPU_CLK_UNHALTED.REF_TSC", - "PublicDescription": "Counts the number of reference cycles when the core is not in a halt state. The core enters the halt state when it is running the HLT instruction or the MWAIT instruction. This event is not affected by core frequency changes (for example, P states, TM2 transitions) but has the same incrementing frequency as the time stamp counter. This event can approximate elapsed time while the core was not in a halt state. It is counted on a dedicated fixed counter, leaving the eight programmable counters available for other events. Note: On all current platforms this event stops counting during 'throttling (TM)' states duty off periods the processor is 'halted'. The counter update is done at a lower clock rate then the core clock the overflow status bit for this counter may appear 'sticky'. After the counter has overflowed and software clears the overflow status bit and resets the counter to less than MAX. The reset value to the counter is not clocked immediately so the overflow status bit will flip 'high (1)' and generate another PMI (if enabled) after which the reset value gets clocked into the counter. Therefore, software will get the interrupt, read the overflow status bit '1 for bit 34 while the counter value is less than MAX. Software should ignore this case.", + "PublicDescription": "Counts the number of reference cycles when the core is not in a halt state. The core enters the halt state when it is running the HLT instruction or the MWAIT instruction. This event is not affected by core frequency changes (for example, P states, TM2 transitions) but has the same incrementing frequency as the time stamp counter. This event can approximate elapsed time while the core was not in a halt state. It is counted on a dedicated fixed counter, leaving the eight programmable counters available for other events. Note: On all current platforms this event stops counting during 'throttling (TM)' states duty off periods the processor is 'halted'. The counter update is done at a lower clock rate then the core clock the overflow status bit for this counter may appear 'sticky'. After the counter has overflowed and software clears the overflow status bit and resets the counter to less than MAX. The reset value to the counter is not clocked immediately so the overflow status bit will flip 'high (1)' and generate another PMI (if enabled) after which the reset value gets clocked into the counter. Therefore, software will get the interrupt, read the overflow status bit '1 for bit 34 while the counter value is less than MAX. Software should ignore this case. Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x3", "Unit": "cpu_core" @@ -598,7 +609,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0x3c", "EventName": "CPU_CLK_UNHALTED.REF_TSC_P", - "PublicDescription": "Counts the number of reference cycles when the core is not in a halt state. The core enters the halt state when it is running the HLT instruction or the MWAIT instruction. This event is not affected by core frequency changes (for example, P states, TM2 transitions) but has the same incrementing frequency as the time stamp counter. This event can approximate elapsed time while the core was not in a halt state. It is counted on a dedicated fixed counter, leaving the four (eight when Hyperthreading is disabled) programmable counters available for other events. Note: On all current platforms this event stops counting during 'throttling (TM)' states duty off periods the processor is 'halted'. The counter update is done at a lower clock rate then the core clock the overflow status bit for this counter may appear 'sticky'. After the counter has overflowed and software clears the overflow status bit and resets the counter to less than MAX. The reset value to the counter is not clocked immediately so the overflow status bit will flip 'high (1)' and generate another PMI (if enabled) after which the reset value gets clocked into the counter. Therefore, software will get the interrupt, read the overflow status bit '1 for bit 34 while the counter value is less than MAX. Software should ignore this case.", + "PublicDescription": "Counts the number of reference cycles when the core is not in a halt state. The core enters the halt state when it is running the HLT instruction or the MWAIT instruction. This event is not affected by core frequency changes (for example, P states, TM2 transitions) but has the same incrementing frequency as the time stamp counter. This event can approximate elapsed time while the core was not in a halt state. It is counted on a dedicated fixed counter, leaving the four (eight when Hyperthreading is disabled) programmable counters available for other events. Note: On all current platforms this event stops counting during 'throttling (TM)' states duty off periods the processor is 'halted'. The counter update is done at a lower clock rate then the core clock the overflow status bit for this counter may appear 'sticky'. After the counter has overflowed and software clears the overflow status bit and resets the counter to less than MAX. The reset value to the counter is not clocked immediately so the overflow status bit will flip 'high (1)' and generate another PMI (if enabled) after which the reset value gets clocked into the counter. Therefore, software will get the interrupt, read the overflow status bit '1 for bit 34 while the counter value is less than MAX. Software should ignore this case. Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x1", "Unit": "cpu_core" @@ -615,7 +626,7 @@ "BriefDescription": "Core cycles when the thread is not in halt state", "Counter": "Fixed counter 1", "EventName": "CPU_CLK_UNHALTED.THREAD", - "PublicDescription": "Counts the number of core cycles while the thread is not in a halt state. The thread enters the halt state when it is running the HLT instruction. This event is a component in many key event ratios. The core frequency may change from time to time due to transitions associated with Enhanced Intel SpeedStep Technology or TM2. For this reason this event may have a changing ratio with regards to time. When the core frequency is constant, this event can approximate elapsed time while the core was not in the halt state. It is counted on a dedicated fixed counter, leaving the eight programmable counters available for other events.", + "PublicDescription": "Counts the number of core cycles while the thread is not in a halt state. The thread enters the halt state when it is running the HLT instruction. This event is a component in many key event ratios. The core frequency may change from time to time due to transitions associated with Enhanced Intel SpeedStep Technology or TM2. For this reason this event may have a changing ratio with regards to time. When the core frequency is constant, this event can approximate elapsed time while the core was not in the halt state. It is counted on a dedicated fixed counter, leaving the eight programmable counters available for other events. Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x2", "Unit": "cpu_core" @@ -633,7 +644,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0x3c", "EventName": "CPU_CLK_UNHALTED.THREAD_P", - "PublicDescription": "This is an architectural event that counts the number of thread cycles while the thread is not in a halt state. The thread enters the halt state when it is running the HLT instruction. The core frequency may change from time to time due to power or thermal throttling. For this reason, this event may have a changing ratio with regards to wall clock time.", + "PublicDescription": "This is an architectural event that counts the number of thread cycles while the thread is not in a halt state. The thread enters the halt state when it is running the HLT instruction. The core frequency may change from time to time due to power or thermal throttling. For this reason, this event may have a changing ratio with regards to wall clock time. Available PDIST counters: 0", "SampleAfterValue": "2000003", "Unit": "cpu_core" }, @@ -643,6 +654,7 @@ "CounterMask": "8", "EventCode": "0xa3", "EventName": "CYCLE_ACTIVITY.CYCLES_L1D_MISS", + "PublicDescription": "Cycles while L1 cache miss demand load is outstanding. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x8", "Unit": "cpu_core" @@ -653,6 +665,7 @@ "CounterMask": "1", "EventCode": "0xa3", "EventName": "CYCLE_ACTIVITY.CYCLES_L2_MISS", + "PublicDescription": "Cycles while L2 cache miss demand load is outstanding. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x1", "Unit": "cpu_core" @@ -663,6 +676,7 @@ "CounterMask": "16", "EventCode": "0xa3", "EventName": "CYCLE_ACTIVITY.CYCLES_MEM_ANY", + "PublicDescription": "Cycles while memory subsystem has an outstanding load. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x10", "Unit": "cpu_core" @@ -673,6 +687,7 @@ "CounterMask": "12", "EventCode": "0xa3", "EventName": "CYCLE_ACTIVITY.STALLS_L1D_MISS", + "PublicDescription": "Execution stalls while L1 cache miss demand load is outstanding. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0xc", "Unit": "cpu_core" @@ -683,6 +698,7 @@ "CounterMask": "5", "EventCode": "0xa3", "EventName": "CYCLE_ACTIVITY.STALLS_L2_MISS", + "PublicDescription": "Execution stalls while L2 cache miss demand load is outstanding. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x5", "Unit": "cpu_core" @@ -693,6 +709,7 @@ "CounterMask": "4", "EventCode": "0xa3", "EventName": "CYCLE_ACTIVITY.STALLS_TOTAL", + "PublicDescription": "Total execution stalls. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x4", "Unit": "cpu_core" @@ -702,7 +719,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xa6", "EventName": "EXE_ACTIVITY.1_PORTS_UTIL", - "PublicDescription": "Counts cycles during which a total of 1 uop was executed on all ports and Reservation Station (RS) was not empty.", + "PublicDescription": "Counts cycles during which a total of 1 uop was executed on all ports and Reservation Station (RS) was not empty. Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x2", "Unit": "cpu_core" @@ -712,6 +729,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xa6", "EventName": "EXE_ACTIVITY.2_3_PORTS_UTIL", + "PublicDescription": "Cycles total of 2 or 3 uops are executed on all ports and Reservation Station (RS) was not empty. Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0xc", "Unit": "cpu_core" @@ -721,7 +739,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xa6", "EventName": "EXE_ACTIVITY.2_PORTS_UTIL", - "PublicDescription": "Counts cycles during which a total of 2 uops were executed on all ports and Reservation Station (RS) was not empty.", + "PublicDescription": "Counts cycles during which a total of 2 uops were executed on all ports and Reservation Station (RS) was not empty. Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x4", "Unit": "cpu_core" @@ -731,7 +749,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xa6", "EventName": "EXE_ACTIVITY.3_PORTS_UTIL", - "PublicDescription": "Cycles total of 3 uops are executed on all ports and Reservation Station (RS) was not empty.", + "PublicDescription": "Cycles total of 3 uops are executed on all ports and Reservation Station (RS) was not empty. Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x8", "Unit": "cpu_core" @@ -741,7 +759,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xa6", "EventName": "EXE_ACTIVITY.4_PORTS_UTIL", - "PublicDescription": "Cycles total of 4 uops are executed on all ports and Reservation Station (RS) was not empty.", + "PublicDescription": "Cycles total of 4 uops are executed on all ports and Reservation Station (RS) was not empty. Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x10", "Unit": "cpu_core" @@ -752,6 +770,7 @@ "CounterMask": "5", "EventCode": "0xa6", "EventName": "EXE_ACTIVITY.BOUND_ON_LOADS", + "PublicDescription": "Execution stalls while memory subsystem has an outstanding load. Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x21", "Unit": "cpu_core" @@ -762,7 +781,7 @@ "CounterMask": "2", "EventCode": "0xa6", "EventName": "EXE_ACTIVITY.BOUND_ON_STORES", - "PublicDescription": "Counts cycles where the Store Buffer was full and no loads caused an execution stall.", + "PublicDescription": "Counts cycles where the Store Buffer was full and no loads caused an execution stall. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x40", "Unit": "cpu_core" @@ -772,7 +791,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xa6", "EventName": "EXE_ACTIVITY.EXE_BOUND_0_PORTS", - "PublicDescription": "Number of cycles total of 0 uops executed on all ports, Reservation Station (RS) was not empty, the Store Buffer (SB) was not full and there was no outstanding load.", + "PublicDescription": "Number of cycles total of 0 uops executed on all ports, Reservation Station (RS) was not empty, the Store Buffer (SB) was not full and there was no outstanding load. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x80", "Unit": "cpu_core" @@ -782,7 +801,7 @@ "Counter": "0,1,2,3", "EventCode": "0x75", "EventName": "INST_DECODED.DECODERS", - "PublicDescription": "Number of decoders utilized in a cycle when the MITE (legacy decode pipeline) fetches instructions.", + "PublicDescription": "Number of decoders utilized in a cycle when the MITE (legacy decode pipeline) fetches instructions. Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x1", "Unit": "cpu_core" @@ -791,6 +810,7 @@ "BriefDescription": "Fixed Counter: Counts the number of instructions retired", "Counter": "Fixed counter 0", "EventName": "INST_RETIRED.ANY", + "PublicDescription": "Fixed Counter: Counts the number of instructions retired Available PDIST counters: 32", "SampleAfterValue": "2000003", "UMask": "0x1", "Unit": "cpu_atom" @@ -799,7 +819,7 @@ "BriefDescription": "Number of instructions retired. Fixed Counter - architectural event", "Counter": "Fixed counter 0", "EventName": "INST_RETIRED.ANY", - "PublicDescription": "Counts the number of X86 instructions retired - an Architectural PerfMon event. Counting continues during hardware interrupts, traps, and inside interrupt handlers. Notes: INST_RETIRED.ANY is counted by a designated fixed counter freeing up programmable counters to count other events. INST_RETIRED.ANY_P is counted by a programmable counter.", + "PublicDescription": "Counts the number of X86 instructions retired - an Architectural PerfMon event. Counting continues during hardware interrupts, traps, and inside interrupt handlers. Notes: INST_RETIRED.ANY is counted by a designated fixed counter freeing up programmable counters to count other events. INST_RETIRED.ANY_P is counted by a programmable counter. Available PDIST counters: 32", "SampleAfterValue": "2000003", "UMask": "0x1", "Unit": "cpu_core" @@ -826,6 +846,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc0", "EventName": "INST_RETIRED.MACRO_FUSED", + "PublicDescription": "INST_RETIRED.MACRO_FUSED Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x10", "Unit": "cpu_core" @@ -835,7 +856,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc0", "EventName": "INST_RETIRED.NOP", - "PublicDescription": "Counts all retired NOP or ENDBR32/64 or PREFETCHIT0/1 instructions", + "PublicDescription": "Counts all retired NOP or ENDBR32/64 or PREFETCHIT0/1 instructions Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x2", "Unit": "cpu_core" @@ -844,7 +865,7 @@ "BriefDescription": "Precise instruction retired with PEBS precise-distribution", "Counter": "Fixed counter 0", "EventName": "INST_RETIRED.PREC_DIST", - "PublicDescription": "A version of INST_RETIRED that allows for a precise distribution of samples across instructions retired. It utilizes the Precise Distribution of Instructions Retired (PDIR++) feature to fix bias in how retired instructions get sampled. Use on Fixed Counter 0.", + "PublicDescription": "A version of INST_RETIRED that allows for a precise distribution of samples across instructions retired. It utilizes the Precise Distribution of Instructions Retired (PDIR++) feature to fix bias in how retired instructions get sampled. Use on Fixed Counter 0. Available PDIST counters: 32", "SampleAfterValue": "2000003", "UMask": "0x1", "Unit": "cpu_core" @@ -854,7 +875,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc0", "EventName": "INST_RETIRED.REP_ITERATION", - "PublicDescription": "Number of iterations of Repeat (REP) string retired instructions such as MOVS, CMPS, and SCAS. Each has a byte, word, and doubleword version and string instructions can be repeated using a repetition prefix, REP, that allows their architectural execution to be repeated a number of times as specified by the RCX register. Note the number of iterations is implementation-dependent.", + "PublicDescription": "Number of iterations of Repeat (REP) string retired instructions such as MOVS, CMPS, and SCAS. Each has a byte, word, and doubleword version and string instructions can be repeated using a repetition prefix, REP, that allows their architectural execution to be repeated a number of times as specified by the RCX register. Note the number of iterations is implementation-dependent. Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x8", "Unit": "cpu_core" @@ -866,7 +887,7 @@ "EdgeDetect": "1", "EventCode": "0xad", "EventName": "INT_MISC.CLEARS_COUNT", - "PublicDescription": "Counts the number of speculative clears due to any type of branch misprediction or machine clears", + "PublicDescription": "Counts the number of speculative clears due to any type of branch misprediction or machine clears Available PDIST counters: 0", "SampleAfterValue": "500009", "UMask": "0x1", "Unit": "cpu_core" @@ -876,7 +897,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xad", "EventName": "INT_MISC.CLEAR_RESTEER_CYCLES", - "PublicDescription": "Cycles after recovery from a branch misprediction or machine clear till the first uop is issued from the resteered path.", + "PublicDescription": "Cycles after recovery from a branch misprediction or machine clear till the first uop is issued from the resteered path. Available PDIST counters: 0", "SampleAfterValue": "500009", "UMask": "0x80", "Unit": "cpu_core" @@ -886,7 +907,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xad", "EventName": "INT_MISC.RECOVERY_CYCLES", - "PublicDescription": "Counts core cycles when the Resource allocator was stalled due to recovery from an earlier branch misprediction or machine clear event.", + "PublicDescription": "Counts core cycles when the Resource allocator was stalled due to recovery from an earlier branch misprediction or machine clear event. Available PDIST counters: 0", "SampleAfterValue": "500009", "UMask": "0x1", "Unit": "cpu_core" @@ -898,6 +919,7 @@ "EventName": "INT_MISC.UNKNOWN_BRANCH_CYCLES", "MSRIndex": "0x3F7", "MSRValue": "0x7", + "PublicDescription": "Bubble cycles of BAClear (Unknown Branch). Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x40", "Unit": "cpu_core" @@ -907,7 +929,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xad", "EventName": "INT_MISC.UOP_DROPPING", - "PublicDescription": "Estimated number of Top-down Microarchitecture Analysis slots that got dropped due to non front-end reasons", + "PublicDescription": "Estimated number of Top-down Microarchitecture Analysis slots that got dropped due to non front-end reasons Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x10", "Unit": "cpu_core" @@ -917,6 +939,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xe7", "EventName": "INT_VEC_RETIRED.128BIT", + "PublicDescription": "INT_VEC_RETIRED.128BIT Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x13", "Unit": "cpu_core" @@ -926,6 +949,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xe7", "EventName": "INT_VEC_RETIRED.256BIT", + "PublicDescription": "INT_VEC_RETIRED.256BIT Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0xac", "Unit": "cpu_core" @@ -935,7 +959,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xe7", "EventName": "INT_VEC_RETIRED.ADD_128", - "PublicDescription": "Number of retired integer ADD/SUB (regular or horizontal), SAD 128-bit vector instructions.", + "PublicDescription": "Number of retired integer ADD/SUB (regular or horizontal), SAD 128-bit vector instructions. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x3", "Unit": "cpu_core" @@ -945,7 +969,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xe7", "EventName": "INT_VEC_RETIRED.ADD_256", - "PublicDescription": "Number of retired integer ADD/SUB (regular or horizontal), SAD 256-bit vector instructions.", + "PublicDescription": "Number of retired integer ADD/SUB (regular or horizontal), SAD 256-bit vector instructions. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0xc", "Unit": "cpu_core" @@ -955,6 +979,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xe7", "EventName": "INT_VEC_RETIRED.MUL_256", + "PublicDescription": "INT_VEC_RETIRED.MUL_256 Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x80", "Unit": "cpu_core" @@ -964,6 +989,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xe7", "EventName": "INT_VEC_RETIRED.SHUFFLES", + "PublicDescription": "INT_VEC_RETIRED.SHUFFLES Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x40", "Unit": "cpu_core" @@ -973,6 +999,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xe7", "EventName": "INT_VEC_RETIRED.VNNI_128", + "PublicDescription": "INT_VEC_RETIRED.VNNI_128 Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x10", "Unit": "cpu_core" @@ -982,6 +1009,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xe7", "EventName": "INT_VEC_RETIRED.VNNI_256", + "PublicDescription": "INT_VEC_RETIRED.VNNI_256 Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x20", "Unit": "cpu_core" @@ -1000,7 +1028,7 @@ "Counter": "0,1,2,3", "EventCode": "0x03", "EventName": "LD_BLOCKS.ADDRESS_ALIAS", - "PublicDescription": "Counts the number of times a load got blocked due to false dependencies in MOB due to partial compare on address.", + "PublicDescription": "Counts the number of times a load got blocked due to false dependencies in MOB due to partial compare on address. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x4", "Unit": "cpu_core" @@ -1019,7 +1047,7 @@ "Counter": "0,1,2,3", "EventCode": "0x03", "EventName": "LD_BLOCKS.NO_SR", - "PublicDescription": "Counts the number of times that split load operations are temporarily blocked because all resources for handling the split accesses are in use.", + "PublicDescription": "Counts the number of times that split load operations are temporarily blocked because all resources for handling the split accesses are in use. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x88", "Unit": "cpu_core" @@ -1038,7 +1066,7 @@ "Counter": "0,1,2,3", "EventCode": "0x03", "EventName": "LD_BLOCKS.STORE_FORWARD", - "PublicDescription": "Counts the number of times where store forwarding was prevented for a load operation. The most common case is a load blocked due to the address of memory access (partially) overlapping with a preceding uncompleted store. Note: See the table of not supported store forwards in the Optimization Guide.", + "PublicDescription": "Counts the number of times where store forwarding was prevented for a load operation. The most common case is a load blocked due to the address of memory access (partially) overlapping with a preceding uncompleted store. Note: See the table of not supported store forwards in the Optimization Guide. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x82", "Unit": "cpu_core" @@ -1048,7 +1076,7 @@ "Counter": "0,1,2,3", "EventCode": "0x4c", "EventName": "LOAD_HIT_PREFETCH.SWPF", - "PublicDescription": "Counts all not software-prefetch load dispatches that hit the fill buffer (FB) allocated for the software prefetch. It can also be incremented by some lock instructions. So it should only be used with profiling so that the locks can be excluded by ASM (Assembly File) inspection of the nearby instructions.", + "PublicDescription": "Counts all not software-prefetch load dispatches that hit the fill buffer (FB) allocated for the software prefetch. It can also be incremented by some lock instructions. So it should only be used with profiling so that the locks can be excluded by ASM (Assembly File) inspection of the nearby instructions. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1", "Unit": "cpu_core" @@ -1059,7 +1087,7 @@ "CounterMask": "1", "EventCode": "0xa8", "EventName": "LSD.CYCLES_ACTIVE", - "PublicDescription": "Counts the cycles when at least one uop is delivered by the LSD (Loop-stream detector).", + "PublicDescription": "Counts the cycles when at least one uop is delivered by the LSD (Loop-stream detector). Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x1", "Unit": "cpu_core" @@ -1070,7 +1098,7 @@ "CounterMask": "6", "EventCode": "0xa8", "EventName": "LSD.CYCLES_OK", - "PublicDescription": "Counts the cycles when optimal number of uops is delivered by the LSD (Loop-stream detector).", + "PublicDescription": "Counts the cycles when optimal number of uops is delivered by the LSD (Loop-stream detector). Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x1", "Unit": "cpu_core" @@ -1080,7 +1108,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xa8", "EventName": "LSD.UOPS", - "PublicDescription": "Counts the number of uops delivered to the back-end by the LSD(Loop Stream Detector).", + "PublicDescription": "Counts the number of uops delivered to the back-end by the LSD(Loop Stream Detector). Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x1", "Unit": "cpu_core" @@ -1100,7 +1128,7 @@ "EdgeDetect": "1", "EventCode": "0xc3", "EventName": "MACHINE_CLEARS.COUNT", - "PublicDescription": "Counts the number of machine clears (nukes) of any type.", + "PublicDescription": "Counts the number of machine clears (nukes) of any type. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1", "Unit": "cpu_core" @@ -1133,8 +1161,9 @@ "Unit": "cpu_atom" }, { - "BriefDescription": "Counts the number of machine clears that flush the pipeline and restart the machine with the use of microcode due to SMC, MEMORY_ORDERING, FP_ASSISTS, PAGE_FAULT, DISAMBIGUATION, and FPC_VIRTUAL_TRAP.", + "BriefDescription": "This event is deprecated.", "Counter": "0,1,2,3,4,5,6,7", + "Deprecated": "1", "EventCode": "0xc3", "EventName": "MACHINE_CLEARS.SLOW", "SampleAfterValue": "20003", @@ -1155,7 +1184,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc3", "EventName": "MACHINE_CLEARS.SMC", - "PublicDescription": "Counts self-modifying code (SMC) detected, which causes a machine clear.", + "PublicDescription": "Counts self-modifying code (SMC) detected, which causes a machine clear. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x4", "Unit": "cpu_core" @@ -1165,7 +1194,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xe0", "EventName": "MISC2_RETIRED.LFENCE", - "PublicDescription": "number of LFENCE retired instructions", + "PublicDescription": "number of LFENCE retired instructions Available PDIST counters: 0", "SampleAfterValue": "400009", "UMask": "0x20", "Unit": "cpu_core" @@ -1184,7 +1213,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xcc", "EventName": "MISC_RETIRED.LBR_INSERTS", - "PublicDescription": "Increments when an entry is added to the Last Branch Record (LBR) array (or removed from the array in case of RETURNs in call stack mode). The event requires LBR enable via IA32_DEBUGCTL MSR and branch type selection via MSR_LBR_SELECT.", + "PublicDescription": "Increments when an entry is added to the Last Branch Record (LBR) array (or removed from the array in case of RETURNs in call stack mode). The event requires LBR enable via IA32_DEBUGCTL MSR and branch type selection via MSR_LBR_SELECT. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x20", "Unit": "cpu_core" @@ -1194,7 +1223,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xa2", "EventName": "RESOURCE_STALLS.SB", - "PublicDescription": "Counts allocation stall cycles caused by the store buffer (SB) being full. This counts cycles that the pipeline back-end blocked uop delivery from the front-end.", + "PublicDescription": "Counts allocation stall cycles caused by the store buffer (SB) being full. This counts cycles that the pipeline back-end blocked uop delivery from the front-end. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x8", "Unit": "cpu_core" @@ -1204,16 +1233,59 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xa2", "EventName": "RESOURCE_STALLS.SCOREBOARD", + "PublicDescription": "Counts cycles where the pipeline is stalled due to serializing operations. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x2", "Unit": "cpu_core" }, { + "BriefDescription": "Cycles when Reservation Station (RS) is empty for the thread.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xa5", + "EventName": "RS.EMPTY", + "PublicDescription": "Counts cycles during which the reservation station (RS) is empty for this logical processor. This is usually caused when the front-end pipeline runs into starvation periods (e.g. branch mispredictions or i-cache misses) Available PDIST counters: 0", + "SampleAfterValue": "1000003", + "UMask": "0x7", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts end of periods where the Reservation Station (RS) was empty.", + "Counter": "0,1,2,3,4,5,6,7", + "CounterMask": "1", + "EdgeDetect": "1", + "EventCode": "0xa5", + "EventName": "RS.EMPTY_COUNT", + "Invert": "1", + "PublicDescription": "Counts end of periods where the Reservation Station (RS) was empty. Could be useful to closely sample on front-end latency issues (see the FRONTEND_RETIRED event of designated precise events) Available PDIST counters: 0", + "SampleAfterValue": "100003", + "UMask": "0x7", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Cycles when RS was empty and a resource allocation stall is asserted", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xa5", + "EventName": "RS.EMPTY_RESOURCE", + "PublicDescription": "Cycles when RS was empty and a resource allocation stall is asserted Available PDIST counters: 0", + "SampleAfterValue": "1000003", + "UMask": "0x1", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts the number of issue slots in a UMWAIT or TPAUSE instruction where no uop issues due to the instruction putting the CPU into the C0.1 activity state.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x75", + "EventName": "SERIALIZATION.C01_MS_SCB", + "SampleAfterValue": "200003", + "UMask": "0x4", + "Unit": "cpu_atom" + }, + { "BriefDescription": "This event counts a subset of the Topdown Slots event that were not consumed by the back-end pipeline due to lack of back-end resources, as a result of memory subsystem delays, execution units limitations, or other conditions.", "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xa4", "EventName": "TOPDOWN.BACKEND_BOUND_SLOTS", - "PublicDescription": "This event counts a subset of the Topdown Slots event that were not consumed by the back-end pipeline due to lack of back-end resources, as a result of memory subsystem delays, execution units limitations, or other conditions. The count is distributed among unhalted logical processors (hyper-threads) who share the same physical core, in processors that support Intel Hyper-Threading Technology. Software can use this event as the numerator for the Backend Bound metric (or top-level category) of the Top-down Microarchitecture Analysis method.", + "PublicDescription": "This event counts a subset of the Topdown Slots event that were not consumed by the back-end pipeline due to lack of back-end resources, as a result of memory subsystem delays, execution units limitations, or other conditions. The count is distributed among unhalted logical processors (hyper-threads) who share the same physical core, in processors that support Intel Hyper-Threading Technology. Software can use this event as the numerator for the Backend Bound metric (or top-level category) of the Top-down Microarchitecture Analysis method. Available PDIST counters: 0", "SampleAfterValue": "10000003", "UMask": "0x2", "Unit": "cpu_core" @@ -1223,7 +1295,7 @@ "Counter": "0", "EventCode": "0xa4", "EventName": "TOPDOWN.BAD_SPEC_SLOTS", - "PublicDescription": "Number of slots of TMA method that were wasted due to incorrect speculation. It covers all types of control-flow or data-related mis-speculations.", + "PublicDescription": "Number of slots of TMA method that were wasted due to incorrect speculation. It covers all types of control-flow or data-related mis-speculations. Available PDIST counters: 0", "SampleAfterValue": "10000003", "UMask": "0x4", "Unit": "cpu_core" @@ -1233,7 +1305,7 @@ "Counter": "0", "EventCode": "0xa4", "EventName": "TOPDOWN.BR_MISPREDICT_SLOTS", - "PublicDescription": "Number of TMA slots that were wasted due to incorrect speculation by (any type of) branch mispredictions. This event estimates number of speculative operations that were issued but not retired as well as the out-of-order engine recovery past a branch misprediction.", + "PublicDescription": "Number of TMA slots that were wasted due to incorrect speculation by (any type of) branch mispredictions. This event estimates number of speculative operations that were issued but not retired as well as the out-of-order engine recovery past a branch misprediction. Available PDIST counters: 0", "SampleAfterValue": "10000003", "UMask": "0x8", "Unit": "cpu_core" @@ -1243,6 +1315,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xa4", "EventName": "TOPDOWN.MEMORY_BOUND_SLOTS", + "PublicDescription": "TOPDOWN.MEMORY_BOUND_SLOTS Available PDIST counters: 0", "SampleAfterValue": "10000003", "UMask": "0x10", "Unit": "cpu_core" @@ -1251,7 +1324,7 @@ "BriefDescription": "TMA slots available for an unhalted logical processor. Fixed counter - architectural event", "Counter": "Fixed counter 3", "EventName": "TOPDOWN.SLOTS", - "PublicDescription": "Number of available slots for an unhalted logical processor. The event increments by machine-width of the narrowest pipeline as employed by the Top-down Microarchitecture Analysis method (TMA). The count is distributed among unhalted logical processors (hyper-threads) who share the same physical core. Software can use this event as the denominator for the top-level metrics of the TMA method. This architectural event is counted on a designated fixed counter (Fixed Counter 3).", + "PublicDescription": "Number of available slots for an unhalted logical processor. The event increments by machine-width of the narrowest pipeline as employed by the Top-down Microarchitecture Analysis method (TMA). The count is distributed among unhalted logical processors (hyper-threads) who share the same physical core. Software can use this event as the denominator for the top-level metrics of the TMA method. This architectural event is counted on a designated fixed counter (Fixed Counter 3). Available PDIST counters: 0", "SampleAfterValue": "10000003", "UMask": "0x4", "Unit": "cpu_core" @@ -1261,7 +1334,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xa4", "EventName": "TOPDOWN.SLOTS_P", - "PublicDescription": "Counts the number of available slots for an unhalted logical processor. The event increments by machine-width of the narrowest pipeline as employed by the Top-down Microarchitecture Analysis method. The count is distributed among unhalted logical processors (hyper-threads) who share the same physical core.", + "PublicDescription": "Counts the number of available slots for an unhalted logical processor. The event increments by machine-width of the narrowest pipeline as employed by the Top-down Microarchitecture Analysis method. The count is distributed among unhalted logical processors (hyper-threads) who share the same physical core. Available PDIST counters: 0", "SampleAfterValue": "10000003", "UMask": "0x1", "Unit": "cpu_core" @@ -1518,7 +1591,7 @@ "Counter": "0,1,2,3", "EventCode": "0x76", "EventName": "UOPS_DECODED.DEC0_UOPS", - "PublicDescription": "This event counts the number of not dec-by-all uops decoded by decoder 0.", + "PublicDescription": "This event counts the number of not dec-by-all uops decoded by decoder 0. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x1", "Unit": "cpu_core" @@ -1528,7 +1601,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xb2", "EventName": "UOPS_DISPATCHED.PORT_0", - "PublicDescription": "Number of uops dispatch to execution port 0.", + "PublicDescription": "Number of uops dispatch to execution port 0. Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x1", "Unit": "cpu_core" @@ -1538,7 +1611,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xb2", "EventName": "UOPS_DISPATCHED.PORT_1", - "PublicDescription": "Number of uops dispatch to execution port 1.", + "PublicDescription": "Number of uops dispatch to execution port 1. Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x2", "Unit": "cpu_core" @@ -1548,7 +1621,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xb2", "EventName": "UOPS_DISPATCHED.PORT_2_3_10", - "PublicDescription": "Number of uops dispatch to execution ports 2, 3 and 10", + "PublicDescription": "Number of uops dispatch to execution ports 2, 3 and 10 Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x4", "Unit": "cpu_core" @@ -1558,7 +1631,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xb2", "EventName": "UOPS_DISPATCHED.PORT_4_9", - "PublicDescription": "Number of uops dispatch to execution ports 4 and 9", + "PublicDescription": "Number of uops dispatch to execution ports 4 and 9 Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x10", "Unit": "cpu_core" @@ -1568,7 +1641,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xb2", "EventName": "UOPS_DISPATCHED.PORT_5_11", - "PublicDescription": "Number of uops dispatch to execution ports 5 and 11", + "PublicDescription": "Number of uops dispatch to execution ports 5 and 11 Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x20", "Unit": "cpu_core" @@ -1578,7 +1651,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xb2", "EventName": "UOPS_DISPATCHED.PORT_6", - "PublicDescription": "Number of uops dispatch to execution port 6.", + "PublicDescription": "Number of uops dispatch to execution port 6. Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x40", "Unit": "cpu_core" @@ -1588,7 +1661,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xb2", "EventName": "UOPS_DISPATCHED.PORT_7_8", - "PublicDescription": "Number of uops dispatch to execution ports 7 and 8.", + "PublicDescription": "Number of uops dispatch to execution ports 7 and 8. Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x80", "Unit": "cpu_core" @@ -1598,7 +1671,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xb1", "EventName": "UOPS_EXECUTED.CORE", - "PublicDescription": "Counts the number of uops executed from any thread.", + "PublicDescription": "Counts the number of uops executed from any thread. Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x2", "Unit": "cpu_core" @@ -1609,7 +1682,7 @@ "CounterMask": "1", "EventCode": "0xb1", "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_1", - "PublicDescription": "Counts cycles when at least 1 micro-op is executed from any thread on physical core.", + "PublicDescription": "Counts cycles when at least 1 micro-op is executed from any thread on physical core. Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x2", "Unit": "cpu_core" @@ -1620,7 +1693,7 @@ "CounterMask": "2", "EventCode": "0xb1", "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_2", - "PublicDescription": "Counts cycles when at least 2 micro-ops are executed from any thread on physical core.", + "PublicDescription": "Counts cycles when at least 2 micro-ops are executed from any thread on physical core. Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x2", "Unit": "cpu_core" @@ -1631,7 +1704,7 @@ "CounterMask": "3", "EventCode": "0xb1", "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_3", - "PublicDescription": "Counts cycles when at least 3 micro-ops are executed from any thread on physical core.", + "PublicDescription": "Counts cycles when at least 3 micro-ops are executed from any thread on physical core. Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x2", "Unit": "cpu_core" @@ -1642,7 +1715,7 @@ "CounterMask": "4", "EventCode": "0xb1", "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_4", - "PublicDescription": "Counts cycles when at least 4 micro-ops are executed from any thread on physical core.", + "PublicDescription": "Counts cycles when at least 4 micro-ops are executed from any thread on physical core. Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x2", "Unit": "cpu_core" @@ -1653,7 +1726,7 @@ "CounterMask": "1", "EventCode": "0xb1", "EventName": "UOPS_EXECUTED.CYCLES_GE_1", - "PublicDescription": "Cycles where at least 1 uop was executed per-thread.", + "PublicDescription": "Cycles where at least 1 uop was executed per-thread. Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x1", "Unit": "cpu_core" @@ -1664,7 +1737,7 @@ "CounterMask": "2", "EventCode": "0xb1", "EventName": "UOPS_EXECUTED.CYCLES_GE_2", - "PublicDescription": "Cycles where at least 2 uops were executed per-thread.", + "PublicDescription": "Cycles where at least 2 uops were executed per-thread. Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x1", "Unit": "cpu_core" @@ -1675,7 +1748,7 @@ "CounterMask": "3", "EventCode": "0xb1", "EventName": "UOPS_EXECUTED.CYCLES_GE_3", - "PublicDescription": "Cycles where at least 3 uops were executed per-thread.", + "PublicDescription": "Cycles where at least 3 uops were executed per-thread. Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x1", "Unit": "cpu_core" @@ -1686,7 +1759,7 @@ "CounterMask": "4", "EventCode": "0xb1", "EventName": "UOPS_EXECUTED.CYCLES_GE_4", - "PublicDescription": "Cycles where at least 4 uops were executed per-thread.", + "PublicDescription": "Cycles where at least 4 uops were executed per-thread. Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x1", "Unit": "cpu_core" @@ -1698,7 +1771,7 @@ "EventCode": "0xb1", "EventName": "UOPS_EXECUTED.STALLS", "Invert": "1", - "PublicDescription": "Counts cycles during which no uops were dispatched from the Reservation Station (RS) per thread.", + "PublicDescription": "Counts cycles during which no uops were dispatched from the Reservation Station (RS) per thread. Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x1", "Unit": "cpu_core" @@ -1708,6 +1781,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xb1", "EventName": "UOPS_EXECUTED.THREAD", + "PublicDescription": "Counts the number of uops to be executed per-thread each cycle. Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x1", "Unit": "cpu_core" @@ -1717,7 +1791,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xb1", "EventName": "UOPS_EXECUTED.X87", - "PublicDescription": "Counts the number of x87 uops executed.", + "PublicDescription": "Counts the number of x87 uops executed. Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x10", "Unit": "cpu_core" @@ -1736,7 +1810,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xae", "EventName": "UOPS_ISSUED.ANY", - "PublicDescription": "Counts the number of uops that the Resource Allocation Table (RAT) issues to the Reservation Station (RS).", + "PublicDescription": "Counts the number of uops that the Resource Allocation Table (RAT) issues to the Reservation Station (RS). Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x1", "Unit": "cpu_core" @@ -1747,6 +1821,7 @@ "CounterMask": "1", "EventCode": "0xae", "EventName": "UOPS_ISSUED.CYCLES", + "PublicDescription": "UOPS_ISSUED.CYCLES Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x1", "Unit": "cpu_core" @@ -1765,7 +1840,7 @@ "CounterMask": "1", "EventCode": "0xc2", "EventName": "UOPS_RETIRED.CYCLES", - "PublicDescription": "Counts cycles where at least one uop has retired.", + "PublicDescription": "Counts cycles where at least one uop has retired. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x2", "Unit": "cpu_core" @@ -1775,7 +1850,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc2", "EventName": "UOPS_RETIRED.HEAVY", - "PublicDescription": "Counts the number of retired micro-operations (uops) except the last uop of each instruction. An instruction that is decoded into less than two uops does not contribute to the count.", + "PublicDescription": "Counts the number of retired micro-operations (uops) except the last uop of each instruction. An instruction that is decoded into less than two uops does not contribute to the count. Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x1", "Unit": "cpu_core" @@ -1805,6 +1880,7 @@ "EventName": "UOPS_RETIRED.MS", "MSRIndex": "0x3F7", "MSRValue": "0x8", + "PublicDescription": "UOPS_RETIRED.MS Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x4", "Unit": "cpu_core" @@ -1814,7 +1890,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc2", "EventName": "UOPS_RETIRED.SLOTS", - "PublicDescription": "This event counts a subset of the Topdown Slots event that are utilized by operations that eventually get retired (committed) by the processor pipeline. Usually, this event positively correlates with higher performance for example, as measured by the instructions-per-cycle metric. Software can use this event as the numerator for the Retiring metric (or top-level category) of the Top-down Microarchitecture Analysis method.", + "PublicDescription": "This event counts a subset of the Topdown Slots event that are utilized by operations that eventually get retired (committed) by the processor pipeline. Usually, this event positively correlates with higher performance for example, as measured by the instructions-per-cycle metric. Software can use this event as the numerator for the Retiring metric (or top-level category) of the Top-down Microarchitecture Analysis method. Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x2", "Unit": "cpu_core" @@ -1826,7 +1902,7 @@ "EventCode": "0xc2", "EventName": "UOPS_RETIRED.STALLS", "Invert": "1", - "PublicDescription": "This event counts cycles without actually retired uops.", + "PublicDescription": "This event counts cycles without actually retired uops. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x2", "Unit": "cpu_core" diff --git a/tools/perf/pmu-events/arch/x86/meteorlake/uncore-memory.json b/tools/perf/pmu-events/arch/x86/meteorlake/uncore-memory.json index 783a4f7fd05b..ceb8839f0767 100644 --- a/tools/perf/pmu-events/arch/x86/meteorlake/uncore-memory.json +++ b/tools/perf/pmu-events/arch/x86/meteorlake/uncore-memory.json @@ -100,6 +100,24 @@ "Unit": "iMC" }, { + "BriefDescription": "Any Rank at Hot state", + "Counter": "0,1,2,3,4", + "EventCode": "0x19", + "EventName": "UNC_M_DRAM_THERMAL_HOT", + "Experimental": "1", + "PerPkg": "1", + "Unit": "iMC" + }, + { + "BriefDescription": "Any Rank at Warm state", + "Counter": "0,1,2,3,4", + "EventCode": "0x1A", + "EventName": "UNC_M_DRAM_THERMAL_WARM", + "Experimental": "1", + "PerPkg": "1", + "Unit": "iMC" + }, + { "BriefDescription": "PRE command sent to DRAM due to page table idle timer expiration", "Counter": "0,1,2,3,4", "EventCode": "0x28", diff --git a/tools/perf/pmu-events/arch/x86/meteorlake/virtual-memory.json b/tools/perf/pmu-events/arch/x86/meteorlake/virtual-memory.json index 305b96b26a4e..f300129e9e2d 100644 --- a/tools/perf/pmu-events/arch/x86/meteorlake/virtual-memory.json +++ b/tools/perf/pmu-events/arch/x86/meteorlake/virtual-memory.json @@ -13,7 +13,7 @@ "Counter": "0,1,2,3", "EventCode": "0x12", "EventName": "DTLB_LOAD_MISSES.STLB_HIT", - "PublicDescription": "Counts loads that miss the DTLB (Data TLB) and hit the STLB (Second level TLB).", + "PublicDescription": "Counts loads that miss the DTLB (Data TLB) and hit the STLB (Second level TLB). Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x20", "Unit": "cpu_core" @@ -24,7 +24,7 @@ "CounterMask": "1", "EventCode": "0x12", "EventName": "DTLB_LOAD_MISSES.WALK_ACTIVE", - "PublicDescription": "Counts cycles when at least one PMH (Page Miss Handler) is busy with a page walk for a demand load.", + "PublicDescription": "Counts cycles when at least one PMH (Page Miss Handler) is busy with a page walk for a demand load. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x10", "Unit": "cpu_core" @@ -43,7 +43,7 @@ "Counter": "0,1,2,3", "EventCode": "0x12", "EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED", - "PublicDescription": "Counts completed page walks (all page sizes) caused by demand data loads. This implies it missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.", + "PublicDescription": "Counts completed page walks (all page sizes) caused by demand data loads. This implies it missed in the DTLB and further levels of TLB. The page walk can end with or without a fault. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0xe", "Unit": "cpu_core" @@ -53,7 +53,7 @@ "Counter": "0,1,2,3", "EventCode": "0x12", "EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED_1G", - "PublicDescription": "Counts completed page walks (1G sizes) caused by demand data loads. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.", + "PublicDescription": "Counts completed page walks (1G sizes) caused by demand data loads. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x8", "Unit": "cpu_core" @@ -73,7 +73,7 @@ "Counter": "0,1,2,3", "EventCode": "0x12", "EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M", - "PublicDescription": "Counts completed page walks (2M/4M sizes) caused by demand data loads. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.", + "PublicDescription": "Counts completed page walks (2M/4M sizes) caused by demand data loads. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x4", "Unit": "cpu_core" @@ -93,7 +93,7 @@ "Counter": "0,1,2,3", "EventCode": "0x12", "EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED_4K", - "PublicDescription": "Counts completed page walks (4K sizes) caused by demand data loads. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.", + "PublicDescription": "Counts completed page walks (4K sizes) caused by demand data loads. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x2", "Unit": "cpu_core" @@ -113,7 +113,7 @@ "Counter": "0,1,2,3", "EventCode": "0x12", "EventName": "DTLB_LOAD_MISSES.WALK_PENDING", - "PublicDescription": "Counts the number of page walks outstanding for a demand load in the PMH (Page Miss Handler) each cycle.", + "PublicDescription": "Counts the number of page walks outstanding for a demand load in the PMH (Page Miss Handler) each cycle. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x10", "Unit": "cpu_core" @@ -132,7 +132,7 @@ "Counter": "0,1,2,3", "EventCode": "0x13", "EventName": "DTLB_STORE_MISSES.STLB_HIT", - "PublicDescription": "Counts stores that miss the DTLB (Data TLB) and hit the STLB (2nd Level TLB).", + "PublicDescription": "Counts stores that miss the DTLB (Data TLB) and hit the STLB (2nd Level TLB). Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x20", "Unit": "cpu_core" @@ -143,7 +143,7 @@ "CounterMask": "1", "EventCode": "0x13", "EventName": "DTLB_STORE_MISSES.WALK_ACTIVE", - "PublicDescription": "Counts cycles when at least one PMH (Page Miss Handler) is busy with a page walk for a store.", + "PublicDescription": "Counts cycles when at least one PMH (Page Miss Handler) is busy with a page walk for a store. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x10", "Unit": "cpu_core" @@ -162,7 +162,7 @@ "Counter": "0,1,2,3", "EventCode": "0x13", "EventName": "DTLB_STORE_MISSES.WALK_COMPLETED", - "PublicDescription": "Counts completed page walks (all page sizes) caused by demand data stores. This implies it missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.", + "PublicDescription": "Counts completed page walks (all page sizes) caused by demand data stores. This implies it missed in the DTLB and further levels of TLB. The page walk can end with or without a fault. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0xe", "Unit": "cpu_core" @@ -172,7 +172,7 @@ "Counter": "0,1,2,3", "EventCode": "0x13", "EventName": "DTLB_STORE_MISSES.WALK_COMPLETED_1G", - "PublicDescription": "Counts completed page walks (1G sizes) caused by demand data stores. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.", + "PublicDescription": "Counts completed page walks (1G sizes) caused by demand data stores. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x8", "Unit": "cpu_core" @@ -192,7 +192,7 @@ "Counter": "0,1,2,3", "EventCode": "0x13", "EventName": "DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M", - "PublicDescription": "Counts completed page walks (2M/4M sizes) caused by demand data stores. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.", + "PublicDescription": "Counts completed page walks (2M/4M sizes) caused by demand data stores. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x4", "Unit": "cpu_core" @@ -212,7 +212,7 @@ "Counter": "0,1,2,3", "EventCode": "0x13", "EventName": "DTLB_STORE_MISSES.WALK_COMPLETED_4K", - "PublicDescription": "Counts completed page walks (4K sizes) caused by demand data stores. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.", + "PublicDescription": "Counts completed page walks (4K sizes) caused by demand data stores. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x2", "Unit": "cpu_core" @@ -232,7 +232,7 @@ "Counter": "0,1,2,3", "EventCode": "0x13", "EventName": "DTLB_STORE_MISSES.WALK_PENDING", - "PublicDescription": "Counts the number of page walks outstanding for a store in the PMH (Page Miss Handler) each cycle.", + "PublicDescription": "Counts the number of page walks outstanding for a store in the PMH (Page Miss Handler) each cycle. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x10", "Unit": "cpu_core" @@ -260,7 +260,7 @@ "Counter": "0,1,2,3", "EventCode": "0x11", "EventName": "ITLB_MISSES.STLB_HIT", - "PublicDescription": "Counts instruction fetch requests that miss the ITLB (Instruction TLB) and hit the STLB (Second-level TLB).", + "PublicDescription": "Counts instruction fetch requests that miss the ITLB (Instruction TLB) and hit the STLB (Second-level TLB). Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x20", "Unit": "cpu_core" @@ -271,7 +271,7 @@ "CounterMask": "1", "EventCode": "0x11", "EventName": "ITLB_MISSES.WALK_ACTIVE", - "PublicDescription": "Counts cycles when at least one PMH (Page Miss Handler) is busy with a page walk for a code (instruction fetch) request.", + "PublicDescription": "Counts cycles when at least one PMH (Page Miss Handler) is busy with a page walk for a code (instruction fetch) request. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x10", "Unit": "cpu_core" @@ -291,7 +291,7 @@ "Counter": "0,1,2,3", "EventCode": "0x11", "EventName": "ITLB_MISSES.WALK_COMPLETED", - "PublicDescription": "Counts completed page walks (all page sizes) caused by a code fetch. This implies it missed in the ITLB (Instruction TLB) and further levels of TLB. The page walk can end with or without a fault.", + "PublicDescription": "Counts completed page walks (all page sizes) caused by a code fetch. This implies it missed in the ITLB (Instruction TLB) and further levels of TLB. The page walk can end with or without a fault. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0xe", "Unit": "cpu_core" @@ -311,7 +311,7 @@ "Counter": "0,1,2,3", "EventCode": "0x11", "EventName": "ITLB_MISSES.WALK_COMPLETED_2M_4M", - "PublicDescription": "Counts completed page walks (2M/4M page sizes) caused by a code fetch. This implies it missed in the ITLB (Instruction TLB) and further levels of TLB. The page walk can end with or without a fault.", + "PublicDescription": "Counts completed page walks (2M/4M page sizes) caused by a code fetch. This implies it missed in the ITLB (Instruction TLB) and further levels of TLB. The page walk can end with or without a fault. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x4", "Unit": "cpu_core" @@ -331,7 +331,7 @@ "Counter": "0,1,2,3", "EventCode": "0x11", "EventName": "ITLB_MISSES.WALK_COMPLETED_4K", - "PublicDescription": "Counts completed page walks (4K page sizes) caused by a code fetch. This implies it missed in the ITLB (Instruction TLB) and further levels of TLB. The page walk can end with or without a fault.", + "PublicDescription": "Counts completed page walks (4K page sizes) caused by a code fetch. This implies it missed in the ITLB (Instruction TLB) and further levels of TLB. The page walk can end with or without a fault. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x2", "Unit": "cpu_core" @@ -351,7 +351,7 @@ "Counter": "0,1,2,3", "EventCode": "0x11", "EventName": "ITLB_MISSES.WALK_PENDING", - "PublicDescription": "Counts the number of page walks outstanding for an outstanding code (instruction fetch) request in the PMH (Page Miss Handler) each cycle.", + "PublicDescription": "Counts the number of page walks outstanding for an outstanding code (instruction fetch) request in the PMH (Page Miss Handler) each cycle. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x10", "Unit": "cpu_core" diff --git a/tools/perf/pmu-events/arch/x86/nehalemep/cache.json b/tools/perf/pmu-events/arch/x86/nehalemep/cache.json index b90026df2ce7..c9d154f1d09a 100644 --- a/tools/perf/pmu-events/arch/x86/nehalemep/cache.json +++ b/tools/perf/pmu-events/arch/x86/nehalemep/cache.json @@ -240,6 +240,38 @@ "UMask": "0x2" }, { + "BriefDescription": "L1I instruction fetch stall cycles", + "Counter": "0,1,2,3", + "EventCode": "0x80", + "EventName": "L1I.CYCLES_STALLED", + "SampleAfterValue": "2000000", + "UMask": "0x4" + }, + { + "BriefDescription": "L1I instruction fetch hits", + "Counter": "0,1,2,3", + "EventCode": "0x80", + "EventName": "L1I.HITS", + "SampleAfterValue": "2000000", + "UMask": "0x1" + }, + { + "BriefDescription": "L1I instruction fetch misses", + "Counter": "0,1,2,3", + "EventCode": "0x80", + "EventName": "L1I.MISSES", + "SampleAfterValue": "2000000", + "UMask": "0x2" + }, + { + "BriefDescription": "L1I Instruction fetches", + "Counter": "0,1,2,3", + "EventCode": "0x80", + "EventName": "L1I.READS", + "SampleAfterValue": "2000000", + "UMask": "0x3" + }, + { "BriefDescription": "All L2 data requests", "Counter": "0,1,2,3", "EventCode": "0x26", diff --git a/tools/perf/pmu-events/arch/x86/nehalemep/other.json b/tools/perf/pmu-events/arch/x86/nehalemep/other.json index f6887b234b0e..5fe5ca778e9f 100644 --- a/tools/perf/pmu-events/arch/x86/nehalemep/other.json +++ b/tools/perf/pmu-events/arch/x86/nehalemep/other.json @@ -16,46 +16,6 @@ "UMask": "0x1" }, { - "BriefDescription": "L1I instruction fetch stall cycles", - "Counter": "0,1,2,3", - "EventCode": "0x80", - "EventName": "L1I.CYCLES_STALLED", - "SampleAfterValue": "2000000", - "UMask": "0x4" - }, - { - "BriefDescription": "L1I instruction fetch hits", - "Counter": "0,1,2,3", - "EventCode": "0x80", - "EventName": "L1I.HITS", - "SampleAfterValue": "2000000", - "UMask": "0x1" - }, - { - "BriefDescription": "L1I instruction fetch misses", - "Counter": "0,1,2,3", - "EventCode": "0x80", - "EventName": "L1I.MISSES", - "SampleAfterValue": "2000000", - "UMask": "0x2" - }, - { - "BriefDescription": "L1I Instruction fetches", - "Counter": "0,1,2,3", - "EventCode": "0x80", - "EventName": "L1I.READS", - "SampleAfterValue": "2000000", - "UMask": "0x3" - }, - { - "BriefDescription": "Large ITLB hit", - "Counter": "0,1,2,3", - "EventCode": "0x82", - "EventName": "LARGE_ITLB.HIT", - "SampleAfterValue": "200000", - "UMask": "0x1" - }, - { "BriefDescription": "All loads dispatched", "Counter": "0,1,2,3", "EventCode": "0x13", diff --git a/tools/perf/pmu-events/arch/x86/nehalemep/virtual-memory.json b/tools/perf/pmu-events/arch/x86/nehalemep/virtual-memory.json index e88c0802e679..accd263cfbfd 100644 --- a/tools/perf/pmu-events/arch/x86/nehalemep/virtual-memory.json +++ b/tools/perf/pmu-events/arch/x86/nehalemep/virtual-memory.json @@ -89,6 +89,14 @@ "UMask": "0x20" }, { + "BriefDescription": "Large ITLB hit", + "Counter": "0,1,2,3", + "EventCode": "0x82", + "EventName": "LARGE_ITLB.HIT", + "SampleAfterValue": "200000", + "UMask": "0x1" + }, + { "BriefDescription": "Retired loads that miss the DTLB (Precise Event)", "Counter": "0,1,2,3", "EventCode": "0xCB", diff --git a/tools/perf/pmu-events/arch/x86/nehalemex/cache.json b/tools/perf/pmu-events/arch/x86/nehalemex/cache.json index 2c0ea6f8c4e0..b6c6b22a3188 100644 --- a/tools/perf/pmu-events/arch/x86/nehalemex/cache.json +++ b/tools/perf/pmu-events/arch/x86/nehalemex/cache.json @@ -240,6 +240,38 @@ "UMask": "0x2" }, { + "BriefDescription": "L1I instruction fetch stall cycles", + "Counter": "0,1,2,3", + "EventCode": "0x80", + "EventName": "L1I.CYCLES_STALLED", + "SampleAfterValue": "2000000", + "UMask": "0x4" + }, + { + "BriefDescription": "L1I instruction fetch hits", + "Counter": "0,1,2,3", + "EventCode": "0x80", + "EventName": "L1I.HITS", + "SampleAfterValue": "2000000", + "UMask": "0x1" + }, + { + "BriefDescription": "L1I instruction fetch misses", + "Counter": "0,1,2,3", + "EventCode": "0x80", + "EventName": "L1I.MISSES", + "SampleAfterValue": "2000000", + "UMask": "0x2" + }, + { + "BriefDescription": "L1I Instruction fetches", + "Counter": "0,1,2,3", + "EventCode": "0x80", + "EventName": "L1I.READS", + "SampleAfterValue": "2000000", + "UMask": "0x3" + }, + { "BriefDescription": "All L2 data requests", "Counter": "0,1,2,3", "EventCode": "0x26", diff --git a/tools/perf/pmu-events/arch/x86/nehalemex/other.json b/tools/perf/pmu-events/arch/x86/nehalemex/other.json index f6887b234b0e..5fe5ca778e9f 100644 --- a/tools/perf/pmu-events/arch/x86/nehalemex/other.json +++ b/tools/perf/pmu-events/arch/x86/nehalemex/other.json @@ -16,46 +16,6 @@ "UMask": "0x1" }, { - "BriefDescription": "L1I instruction fetch stall cycles", - "Counter": "0,1,2,3", - "EventCode": "0x80", - "EventName": "L1I.CYCLES_STALLED", - "SampleAfterValue": "2000000", - "UMask": "0x4" - }, - { - "BriefDescription": "L1I instruction fetch hits", - "Counter": "0,1,2,3", - "EventCode": "0x80", - "EventName": "L1I.HITS", - "SampleAfterValue": "2000000", - "UMask": "0x1" - }, - { - "BriefDescription": "L1I instruction fetch misses", - "Counter": "0,1,2,3", - "EventCode": "0x80", - "EventName": "L1I.MISSES", - "SampleAfterValue": "2000000", - "UMask": "0x2" - }, - { - "BriefDescription": "L1I Instruction fetches", - "Counter": "0,1,2,3", - "EventCode": "0x80", - "EventName": "L1I.READS", - "SampleAfterValue": "2000000", - "UMask": "0x3" - }, - { - "BriefDescription": "Large ITLB hit", - "Counter": "0,1,2,3", - "EventCode": "0x82", - "EventName": "LARGE_ITLB.HIT", - "SampleAfterValue": "200000", - "UMask": "0x1" - }, - { "BriefDescription": "All loads dispatched", "Counter": "0,1,2,3", "EventCode": "0x13", diff --git a/tools/perf/pmu-events/arch/x86/nehalemex/virtual-memory.json b/tools/perf/pmu-events/arch/x86/nehalemex/virtual-memory.json index e88c0802e679..accd263cfbfd 100644 --- a/tools/perf/pmu-events/arch/x86/nehalemex/virtual-memory.json +++ b/tools/perf/pmu-events/arch/x86/nehalemex/virtual-memory.json @@ -89,6 +89,14 @@ "UMask": "0x20" }, { + "BriefDescription": "Large ITLB hit", + "Counter": "0,1,2,3", + "EventCode": "0x82", + "EventName": "LARGE_ITLB.HIT", + "SampleAfterValue": "200000", + "UMask": "0x1" + }, + { "BriefDescription": "Retired loads that miss the DTLB (Precise Event)", "Counter": "0,1,2,3", "EventCode": "0xCB", diff --git a/tools/perf/pmu-events/arch/x86/rocketlake/cache.json b/tools/perf/pmu-events/arch/x86/rocketlake/cache.json index 791fa526d192..0f543325ec1a 100644 --- a/tools/perf/pmu-events/arch/x86/rocketlake/cache.json +++ b/tools/perf/pmu-events/arch/x86/rocketlake/cache.json @@ -446,6 +446,16 @@ "UMask": "0x20" }, { + "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that have any type of response.", + "Counter": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OCR.DEMAND_CODE_RD.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x10004", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that hit a cacheline in the L3 where a snoop was sent or not.", "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -506,6 +516,16 @@ "UMask": "0x1" }, { + "BriefDescription": "Counts demand data reads that have any type of response.", + "Counter": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OCR.DEMAND_DATA_RD.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x10001", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { "BriefDescription": "Counts demand data reads that hit a cacheline in the L3 where a snoop was sent or not.", "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -566,6 +586,16 @@ "UMask": "0x1" }, { + "BriefDescription": "Counts demand reads for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that have any type of response.", + "Counter": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OCR.DEMAND_RFO.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x10002", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { "BriefDescription": "Counts demand reads for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that hit a cacheline in the L3 where a snoop was sent or not.", "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -626,6 +656,16 @@ "UMask": "0x1" }, { + "BriefDescription": "Counts L1 data cache prefetch requests and software prefetches (except PREFETCHW) that have any type of response.", + "Counter": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OCR.HWPF_L1D_AND_SWPF.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x10400", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { "BriefDescription": "Counts L1 data cache prefetch requests and software prefetches (except PREFETCHW) that hit a cacheline in the L3 where a snoop was sent or not.", "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -656,6 +696,16 @@ "UMask": "0x1" }, { + "BriefDescription": "Counts hardware prefetch data reads (which bring data to L2) that have any type of response.", + "Counter": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OCR.HWPF_L2_DATA_RD.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x10010", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { "BriefDescription": "Counts hardware prefetch data reads (which bring data to L2) that hit a cacheline in the L3 where a snoop was sent or not.", "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -716,6 +766,16 @@ "UMask": "0x1" }, { + "BriefDescription": "Counts hardware prefetch RFOs (which bring data to L2) that have any type of response.", + "Counter": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OCR.HWPF_L2_RFO.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x10020", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { "BriefDescription": "Counts hardware prefetch RFOs (which bring data to L2) that hit a cacheline in the L3 where a snoop was sent or not.", "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", diff --git a/tools/perf/pmu-events/arch/x86/rocketlake/memory.json b/tools/perf/pmu-events/arch/x86/rocketlake/memory.json index abaf3f4f9d63..1455aaac37b1 100644 --- a/tools/perf/pmu-events/arch/x86/rocketlake/memory.json +++ b/tools/perf/pmu-events/arch/x86/rocketlake/memory.json @@ -177,6 +177,16 @@ "UMask": "0x1" }, { + "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that DRAM supplied the request.", + "Counter": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OCR.DEMAND_CODE_RD.DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x184000004", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that was not supplied by the L3 cache.", "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -187,6 +197,26 @@ "UMask": "0x1" }, { + "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that DRAM supplied the request.", + "Counter": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OCR.DEMAND_CODE_RD.LOCAL_DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x184000004", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts demand data reads that DRAM supplied the request.", + "Counter": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OCR.DEMAND_DATA_RD.DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x184000001", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { "BriefDescription": "Counts demand data reads that was not supplied by the L3 cache.", "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -197,6 +227,26 @@ "UMask": "0x1" }, { + "BriefDescription": "Counts demand data reads that DRAM supplied the request.", + "Counter": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OCR.DEMAND_DATA_RD.LOCAL_DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x184000001", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts demand reads for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that DRAM supplied the request.", + "Counter": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OCR.DEMAND_RFO.DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x184000002", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { "BriefDescription": "Counts demand reads for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that was not supplied by the L3 cache.", "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -207,6 +257,26 @@ "UMask": "0x1" }, { + "BriefDescription": "Counts demand reads for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that DRAM supplied the request.", + "Counter": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OCR.DEMAND_RFO.LOCAL_DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x184000002", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts L1 data cache prefetch requests and software prefetches (except PREFETCHW) that DRAM supplied the request.", + "Counter": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OCR.HWPF_L1D_AND_SWPF.DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x184000400", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { "BriefDescription": "Counts L1 data cache prefetch requests and software prefetches (except PREFETCHW) that was not supplied by the L3 cache.", "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -217,6 +287,26 @@ "UMask": "0x1" }, { + "BriefDescription": "Counts L1 data cache prefetch requests and software prefetches (except PREFETCHW) that DRAM supplied the request.", + "Counter": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OCR.HWPF_L1D_AND_SWPF.LOCAL_DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x184000400", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts hardware prefetch data reads (which bring data to L2) that DRAM supplied the request.", + "Counter": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OCR.HWPF_L2_DATA_RD.DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x184000010", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { "BriefDescription": "Counts hardware prefetch data reads (which bring data to L2) that was not supplied by the L3 cache.", "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -227,6 +317,26 @@ "UMask": "0x1" }, { + "BriefDescription": "Counts hardware prefetch data reads (which bring data to L2) that DRAM supplied the request.", + "Counter": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OCR.HWPF_L2_DATA_RD.LOCAL_DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x184000010", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts hardware prefetch RFOs (which bring data to L2) that DRAM supplied the request.", + "Counter": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OCR.HWPF_L2_RFO.DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x184000020", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { "BriefDescription": "Counts hardware prefetch RFOs (which bring data to L2) that was not supplied by the L3 cache.", "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -237,6 +347,26 @@ "UMask": "0x1" }, { + "BriefDescription": "Counts hardware prefetch RFOs (which bring data to L2) that DRAM supplied the request.", + "Counter": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OCR.HWPF_L2_RFO.LOCAL_DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x184000020", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts miscellaneous requests, such as I/O and un-cacheable accesses that DRAM supplied the request.", + "Counter": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OCR.OTHER.DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x184008000", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { "BriefDescription": "Counts miscellaneous requests, such as I/O and un-cacheable accesses that was not supplied by the L3 cache.", "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -247,6 +377,26 @@ "UMask": "0x1" }, { + "BriefDescription": "Counts miscellaneous requests, such as I/O and un-cacheable accesses that DRAM supplied the request.", + "Counter": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OCR.OTHER.LOCAL_DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x184008000", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts streaming stores that DRAM supplied the request.", + "Counter": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OCR.STREAMING_WR.DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x184000800", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { "BriefDescription": "Counts streaming stores that was not supplied by the L3 cache.", "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -257,6 +407,16 @@ "UMask": "0x1" }, { + "BriefDescription": "Counts streaming stores that DRAM supplied the request.", + "Counter": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OCR.STREAMING_WR.LOCAL_DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x184000800", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { "BriefDescription": "Counts demand data read requests that miss the L3 cache.", "Counter": "0,1,2,3", "EventCode": "0xb0", diff --git a/tools/perf/pmu-events/arch/x86/rocketlake/other.json b/tools/perf/pmu-events/arch/x86/rocketlake/other.json index a96b2a989d3f..141cd30a30af 100644 --- a/tools/perf/pmu-events/arch/x86/rocketlake/other.json +++ b/tools/perf/pmu-events/arch/x86/rocketlake/other.json @@ -27,186 +27,6 @@ "UMask": "0x20" }, { - "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that have any type of response.", - "Counter": "0,1,2,3", - "EventCode": "0xB7, 0xBB", - "EventName": "OCR.DEMAND_CODE_RD.ANY_RESPONSE", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x10004", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that DRAM supplied the request.", - "Counter": "0,1,2,3", - "EventCode": "0xB7, 0xBB", - "EventName": "OCR.DEMAND_CODE_RD.DRAM", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x184000004", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that DRAM supplied the request.", - "Counter": "0,1,2,3", - "EventCode": "0xB7, 0xBB", - "EventName": "OCR.DEMAND_CODE_RD.LOCAL_DRAM", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x184000004", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts demand data reads that have any type of response.", - "Counter": "0,1,2,3", - "EventCode": "0xB7, 0xBB", - "EventName": "OCR.DEMAND_DATA_RD.ANY_RESPONSE", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x10001", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts demand data reads that DRAM supplied the request.", - "Counter": "0,1,2,3", - "EventCode": "0xB7, 0xBB", - "EventName": "OCR.DEMAND_DATA_RD.DRAM", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x184000001", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts demand data reads that DRAM supplied the request.", - "Counter": "0,1,2,3", - "EventCode": "0xB7, 0xBB", - "EventName": "OCR.DEMAND_DATA_RD.LOCAL_DRAM", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x184000001", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts demand reads for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that have any type of response.", - "Counter": "0,1,2,3", - "EventCode": "0xB7, 0xBB", - "EventName": "OCR.DEMAND_RFO.ANY_RESPONSE", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x10002", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts demand reads for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that DRAM supplied the request.", - "Counter": "0,1,2,3", - "EventCode": "0xB7, 0xBB", - "EventName": "OCR.DEMAND_RFO.DRAM", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x184000002", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts demand reads for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that DRAM supplied the request.", - "Counter": "0,1,2,3", - "EventCode": "0xB7, 0xBB", - "EventName": "OCR.DEMAND_RFO.LOCAL_DRAM", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x184000002", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts L1 data cache prefetch requests and software prefetches (except PREFETCHW) that have any type of response.", - "Counter": "0,1,2,3", - "EventCode": "0xB7, 0xBB", - "EventName": "OCR.HWPF_L1D_AND_SWPF.ANY_RESPONSE", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x10400", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts L1 data cache prefetch requests and software prefetches (except PREFETCHW) that DRAM supplied the request.", - "Counter": "0,1,2,3", - "EventCode": "0xB7, 0xBB", - "EventName": "OCR.HWPF_L1D_AND_SWPF.DRAM", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x184000400", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts L1 data cache prefetch requests and software prefetches (except PREFETCHW) that DRAM supplied the request.", - "Counter": "0,1,2,3", - "EventCode": "0xB7, 0xBB", - "EventName": "OCR.HWPF_L1D_AND_SWPF.LOCAL_DRAM", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x184000400", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts hardware prefetch data reads (which bring data to L2) that have any type of response.", - "Counter": "0,1,2,3", - "EventCode": "0xB7, 0xBB", - "EventName": "OCR.HWPF_L2_DATA_RD.ANY_RESPONSE", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x10010", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts hardware prefetch data reads (which bring data to L2) that DRAM supplied the request.", - "Counter": "0,1,2,3", - "EventCode": "0xB7, 0xBB", - "EventName": "OCR.HWPF_L2_DATA_RD.DRAM", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x184000010", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts hardware prefetch data reads (which bring data to L2) that DRAM supplied the request.", - "Counter": "0,1,2,3", - "EventCode": "0xB7, 0xBB", - "EventName": "OCR.HWPF_L2_DATA_RD.LOCAL_DRAM", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x184000010", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts hardware prefetch RFOs (which bring data to L2) that have any type of response.", - "Counter": "0,1,2,3", - "EventCode": "0xB7, 0xBB", - "EventName": "OCR.HWPF_L2_RFO.ANY_RESPONSE", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x10020", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts hardware prefetch RFOs (which bring data to L2) that DRAM supplied the request.", - "Counter": "0,1,2,3", - "EventCode": "0xB7, 0xBB", - "EventName": "OCR.HWPF_L2_RFO.DRAM", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x184000020", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts hardware prefetch RFOs (which bring data to L2) that DRAM supplied the request.", - "Counter": "0,1,2,3", - "EventCode": "0xB7, 0xBB", - "EventName": "OCR.HWPF_L2_RFO.LOCAL_DRAM", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x184000020", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { "BriefDescription": "Counts miscellaneous requests, such as I/O and un-cacheable accesses that have any type of response.", "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -217,26 +37,6 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts miscellaneous requests, such as I/O and un-cacheable accesses that DRAM supplied the request.", - "Counter": "0,1,2,3", - "EventCode": "0xB7, 0xBB", - "EventName": "OCR.OTHER.DRAM", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x184008000", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts miscellaneous requests, such as I/O and un-cacheable accesses that DRAM supplied the request.", - "Counter": "0,1,2,3", - "EventCode": "0xB7, 0xBB", - "EventName": "OCR.OTHER.LOCAL_DRAM", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x184008000", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { "BriefDescription": "Counts streaming stores that have any type of response.", "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -245,25 +45,5 @@ "MSRValue": "0x10800", "SampleAfterValue": "100003", "UMask": "0x1" - }, - { - "BriefDescription": "Counts streaming stores that DRAM supplied the request.", - "Counter": "0,1,2,3", - "EventCode": "0xB7, 0xBB", - "EventName": "OCR.STREAMING_WR.DRAM", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x184000800", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts streaming stores that DRAM supplied the request.", - "Counter": "0,1,2,3", - "EventCode": "0xB7, 0xBB", - "EventName": "OCR.STREAMING_WR.LOCAL_DRAM", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x184000800", - "SampleAfterValue": "100003", - "UMask": "0x1" } ] diff --git a/tools/perf/pmu-events/arch/x86/rocketlake/rkl-metrics.json b/tools/perf/pmu-events/arch/x86/rocketlake/rkl-metrics.json index cfda8956353e..71737a1a1997 100644 --- a/tools/perf/pmu-events/arch/x86/rocketlake/rkl-metrics.json +++ b/tools/perf/pmu-events/arch/x86/rocketlake/rkl-metrics.json @@ -89,12 +89,12 @@ "MetricExpr": "LD_BLOCKS_PARTIAL.ADDRESS_ALIAS / tma_info_thread_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group", "MetricName": "tma_4k_aliasing", - "MetricThreshold": "tma_4k_aliasing > 0.2 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", - "PublicDescription": "This metric estimates how often memory load accesses were aliased by preceding stores (in program order) with a 4K address offset. False match is possible; which incur a few cycles load re-issue. However; the short re-issue duration is often hidden by the out-of-order core and HW optimizations; hence a user may safely ignore a high value of this metric unless it manages to propagate up into parent nodes of the hierarchy (e.g. to L1_Bound)", + "MetricThreshold": "tma_4k_aliasing > 0.2 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric estimates how often memory load accesses were aliased by preceding stores (in program order) with a 4K address offset. False match is possible; which incur a few cycles load re-issue. However; the short re-issue duration is often hidden by the out-of-order core and HW optimizations; hence a user may safely ignore a high value of this metric unless it manages to propagate up into parent nodes of the hierarchy (e.g. to L1_Bound).", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution ports for ALU operations", + "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution ports for ALU operations.", "MetricExpr": "(UOPS_DISPATCHED.PORT_0 + UOPS_DISPATCHED.PORT_1 + UOPS_DISPATCHED.PORT_5 + UOPS_DISPATCHED.PORT_6) / (4 * tma_info_core_core_clks)", "MetricGroup": "TopdownL5;tma_L5_group;tma_ports_utilized_3m_group", "MetricName": "tma_alu_op_utilization", @@ -106,7 +106,7 @@ "MetricExpr": "34 * ASSISTS.ANY / tma_info_thread_slots", "MetricGroup": "BvIO;TopdownL4;tma_L4_group;tma_microcode_sequencer_group", "MetricName": "tma_assists", - "MetricThreshold": "tma_assists > 0.1 & tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1", + "MetricThreshold": "tma_assists > 0.1 & (tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1)", "PublicDescription": "This metric estimates fraction of slots the CPU retired uops delivered by the Microcode_Sequencer as a result of Assists. Assists are long sequences of uops that are required in certain corner-cases for operations that cannot be handled natively by the execution pipeline. For example; when working with very small floating point values (so-called Denormals); the FP units are not set up to perform these operations natively. Instead; a sequence of instructions to perform the computation on the Denormals is injected into the pipeline. Since these microcode sequences might be dozens of uops long; Assists can be extremely deleterious to performance and they can be avoided in many cases. Sample with: ASSISTS.ANY", "ScaleUnit": "100%" }, @@ -129,12 +129,12 @@ "MetricName": "tma_bad_speculation", "MetricThreshold": "tma_bad_speculation > 0.15", "MetricgroupNoGroup": "TopdownL1;Default", - "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example", + "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.", "ScaleUnit": "100%" }, { "BriefDescription": "Total pipeline cost of instruction fetch related bottlenecks by large code footprint programs (i-side cache; TLB and BTB misses)", - "MetricExpr": "100 * tma_fetch_latency * (tma_itlb_misses + tma_icache_misses + tma_unknown_branches) / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches)", + "MetricExpr": "100 * tma_fetch_latency * (tma_itlb_misses + tma_icache_misses + tma_unknown_branches) / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches)", "MetricGroup": "BigFootprint;BvBC;Fed;Frontend;IcMiss;MemoryTLB", "MetricName": "tma_bottleneck_big_code", "MetricThreshold": "tma_bottleneck_big_code > 20" @@ -149,7 +149,7 @@ }, { "BriefDescription": "Total pipeline cost of external Memory- or Cache-Bandwidth related bottlenecks", - "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_mem_bandwidth / (tma_mem_bandwidth + tma_mem_latency)) + tma_memory_bound * (tma_l3_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_sq_full / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_memory_bound * (tma_l1_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_fb_full / (tma_dtlb_load + tma_store_fwd_blk + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_4k_aliasing + tma_fb_full)))", + "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_mem_bandwidth / (tma_mem_bandwidth + tma_mem_latency)) + tma_memory_bound * (tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_sq_full / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_fb_full / (tma_4k_aliasing + tma_dtlb_load + tma_fb_full + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)))", "MetricGroup": "BvMB;Mem;MemoryBW;Offcore;tma_issueBW", "MetricName": "tma_bottleneck_cache_memory_bandwidth", "MetricThreshold": "tma_bottleneck_cache_memory_bandwidth > 20", @@ -157,7 +157,7 @@ }, { "BriefDescription": "Total pipeline cost of external Memory- or Cache-Latency related bottlenecks", - "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_mem_latency / (tma_mem_bandwidth + tma_mem_latency)) + tma_memory_bound * (tma_l3_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_l3_hit_latency / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_memory_bound * tma_l2_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound) + tma_memory_bound * (tma_l1_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_l1_latency_dependency / (tma_dtlb_load + tma_store_fwd_blk + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_4k_aliasing + tma_fb_full)) + tma_memory_bound * (tma_l1_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_lock_latency / (tma_dtlb_load + tma_store_fwd_blk + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_4k_aliasing + tma_fb_full)) + tma_memory_bound * (tma_l1_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_split_loads / (tma_dtlb_load + tma_store_fwd_blk + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_4k_aliasing + tma_fb_full)) + tma_memory_bound * (tma_store_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_split_stores / (tma_store_latency + tma_false_sharing + tma_split_stores + tma_streaming_stores + tma_dtlb_store)) + tma_memory_bound * (tma_store_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_store_latency / (tma_store_latency + tma_false_sharing + tma_split_stores + tma_streaming_stores + tma_dtlb_store)))", + "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_mem_latency / (tma_mem_bandwidth + tma_mem_latency)) + tma_memory_bound * (tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_l3_hit_latency / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_memory_bound * tma_l2_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) + tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_l1_latency_dependency / (tma_4k_aliasing + tma_dtlb_load + tma_fb_full + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_lock_latency / (tma_4k_aliasing + tma_dtlb_load + tma_fb_full + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_split_loads / (tma_4k_aliasing + tma_dtlb_load + tma_fb_full + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_memory_bound * (tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_split_stores / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency + tma_streaming_stores)) + tma_memory_bound * (tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_store_latency / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency + tma_streaming_stores)))", "MetricGroup": "BvML;Mem;MemoryLat;Offcore;tma_issueLat", "MetricName": "tma_bottleneck_cache_memory_latency", "MetricThreshold": "tma_bottleneck_cache_memory_latency > 20", @@ -165,22 +165,22 @@ }, { "BriefDescription": "Total pipeline cost when the execution is compute-bound - an estimation", - "MetricExpr": "100 * (tma_core_bound * tma_divider / (tma_divider + tma_serializing_operation + tma_ports_utilization) + tma_core_bound * (tma_ports_utilization / (tma_divider + tma_serializing_operation + tma_ports_utilization)) * (tma_ports_utilized_3m / (tma_ports_utilized_0 + tma_ports_utilized_1 + tma_ports_utilized_2 + tma_ports_utilized_3m)))", + "MetricExpr": "100 * (tma_core_bound * tma_divider / (tma_divider + tma_ports_utilization + tma_serializing_operation) + tma_core_bound * (tma_ports_utilization / (tma_divider + tma_ports_utilization + tma_serializing_operation)) * (tma_ports_utilized_3m / (tma_ports_utilized_0 + tma_ports_utilized_1 + tma_ports_utilized_2 + tma_ports_utilized_3m)))", "MetricGroup": "BvCB;Cor;tma_issueComp", "MetricName": "tma_bottleneck_compute_bound_est", "MetricThreshold": "tma_bottleneck_compute_bound_est > 20", - "PublicDescription": "Total pipeline cost when the execution is compute-bound - an estimation. Covers Core Bound when High ILP as well as when long-latency execution units are busy" + "PublicDescription": "Total pipeline cost when the execution is compute-bound - an estimation. Covers Core Bound when High ILP as well as when long-latency execution units are busy. Related metrics: " }, { "BriefDescription": "Total pipeline cost of instruction fetch bandwidth related bottlenecks (when the front-end could not sustain operations delivery to the back-end)", - "MetricExpr": "100 * (tma_frontend_bound - (1 - 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts) * tma_fetch_latency * tma_mispredicts_resteers / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches) - tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * (tma_fetch_latency * (tma_ms_switches + tma_branch_resteers * (tma_clears_resteers + 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts * tma_mispredicts_resteers) / (tma_mispredicts_resteers + tma_clears_resteers + tma_unknown_branches)) / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches) + tma_fetch_bandwidth * tma_ms / (tma_mite + tma_dsb + tma_lsd + tma_ms))) - tma_bottleneck_big_code", + "MetricExpr": "100 * (tma_frontend_bound - (1 - 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts) * tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) - tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * (tma_fetch_latency * (tma_ms_switches + tma_branch_resteers * (tma_clears_resteers + 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts * tma_mispredicts_resteers) / (tma_clears_resteers + tma_mispredicts_resteers + tma_unknown_branches)) / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) + tma_fetch_bandwidth * tma_ms / (tma_dsb + tma_lsd + tma_mite + tma_ms))) - tma_bottleneck_big_code", "MetricGroup": "BvFB;Fed;FetchBW;Frontend", "MetricName": "tma_bottleneck_instruction_fetch_bw", "MetricThreshold": "tma_bottleneck_instruction_fetch_bw > 20" }, { "BriefDescription": "Total pipeline cost of irregular execution (e.g", - "MetricExpr": "100 * (tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * (tma_fetch_latency * (tma_ms_switches + tma_branch_resteers * (tma_clears_resteers + 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts * tma_mispredicts_resteers) / (tma_mispredicts_resteers + tma_clears_resteers + tma_unknown_branches)) / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches) + tma_fetch_bandwidth * tma_ms / (tma_mite + tma_dsb + tma_lsd + tma_ms)) + 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts * tma_branch_mispredicts + tma_machine_clears * tma_other_nukes / tma_other_nukes + tma_core_bound * (tma_serializing_operation + tma_core_bound * RS_EVENTS.EMPTY_CYCLES / tma_info_thread_clks * tma_ports_utilized_0) / (tma_divider + tma_serializing_operation + tma_ports_utilization) + tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * tma_heavy_operations)", + "MetricExpr": "100 * (tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * (tma_fetch_latency * (tma_ms_switches + tma_branch_resteers * (tma_clears_resteers + 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts * tma_mispredicts_resteers) / (tma_clears_resteers + tma_mispredicts_resteers + tma_unknown_branches)) / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) + tma_fetch_bandwidth * tma_ms / (tma_dsb + tma_lsd + tma_mite + tma_ms)) + 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts * tma_branch_mispredicts + tma_machine_clears * tma_other_nukes / tma_other_nukes + tma_core_bound * (tma_serializing_operation + tma_core_bound * RS_EVENTS.EMPTY_CYCLES / tma_info_thread_clks * tma_ports_utilized_0) / (tma_divider + tma_ports_utilization + tma_serializing_operation) + tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * tma_heavy_operations)", "MetricGroup": "Bad;BvIO;Cor;Ret;tma_issueMS", "MetricName": "tma_bottleneck_irregular_overhead", "MetricThreshold": "tma_bottleneck_irregular_overhead > 10", @@ -188,7 +188,7 @@ }, { "BriefDescription": "Total pipeline cost of Memory Address Translation related bottlenecks (data-side TLBs)", - "MetricExpr": "100 * (tma_memory_bound * (tma_l1_bound / max(tma_memory_bound, tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_dtlb_load / max(tma_l1_bound, tma_dtlb_load + tma_store_fwd_blk + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_4k_aliasing + tma_fb_full)) + tma_memory_bound * (tma_store_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_dtlb_store / (tma_store_latency + tma_false_sharing + tma_split_stores + tma_streaming_stores + tma_dtlb_store)))", + "MetricExpr": "100 * (tma_memory_bound * (tma_l1_bound / max(tma_memory_bound, tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_dtlb_load / max(tma_l1_bound, tma_4k_aliasing + tma_dtlb_load + tma_fb_full + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_memory_bound * (tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_dtlb_store / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency + tma_streaming_stores)))", "MetricGroup": "BvMT;Mem;MemoryTLB;Offcore;tma_issueTLB", "MetricName": "tma_bottleneck_memory_data_tlbs", "MetricThreshold": "tma_bottleneck_memory_data_tlbs > 20", @@ -196,15 +196,15 @@ }, { "BriefDescription": "Total pipeline cost of Memory Synchronization related bottlenecks (data transfers and coherency updates across processors)", - "MetricExpr": "100 * (tma_memory_bound * (tma_l3_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound) * (tma_contested_accesses + tma_data_sharing) / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full) + tma_store_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound) * tma_false_sharing / (tma_store_latency + tma_false_sharing + tma_split_stores + tma_streaming_stores + tma_dtlb_store - tma_store_latency)) + tma_machine_clears * (1 - tma_other_nukes / tma_other_nukes))", + "MetricExpr": "100 * (tma_memory_bound * (tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_contested_accesses + tma_data_sharing) / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full) + tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * tma_false_sharing / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency + tma_streaming_stores - tma_store_latency)) + tma_machine_clears * (1 - tma_other_nukes / tma_other_nukes))", "MetricGroup": "BvMS;LockCont;Mem;Offcore;tma_issueSyncxn", "MetricName": "tma_bottleneck_memory_synchronization", "MetricThreshold": "tma_bottleneck_memory_synchronization > 10", - "PublicDescription": "Total pipeline cost of Memory Synchronization related bottlenecks (data transfers and coherency updates across processors). Related metrics: tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_machine_clears" + "PublicDescription": "Total pipeline cost of Memory Synchronization related bottlenecks (data transfers and coherency updates across processors). Related metrics: tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_machine_clears, tma_remote_cache" }, { "BriefDescription": "Total pipeline cost of Branch Misprediction related bottlenecks", - "MetricExpr": "100 * (1 - 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts) * (tma_branch_mispredicts + tma_fetch_latency * tma_mispredicts_resteers / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches))", + "MetricExpr": "100 * (1 - 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts) * (tma_branch_mispredicts + tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches))", "MetricGroup": "Bad;BadSpec;BrMispredicts;BvMP;tma_issueBM", "MetricName": "tma_bottleneck_mispredictions", "MetricThreshold": "tma_bottleneck_mispredictions > 20", @@ -216,17 +216,17 @@ "MetricGroup": "BvOB;Cor;Offcore", "MetricName": "tma_bottleneck_other_bottlenecks", "MetricThreshold": "tma_bottleneck_other_bottlenecks > 20", - "PublicDescription": "Total pipeline cost of remaining bottlenecks in the back-end. Examples include data-dependencies (Core Bound when Low ILP) and other unlisted memory-related stalls" + "PublicDescription": "Total pipeline cost of remaining bottlenecks in the back-end. Examples include data-dependencies (Core Bound when Low ILP) and other unlisted memory-related stalls." }, { - "BriefDescription": "Total pipeline cost of \"useful operations\" - the portion of Retiring category not covered by Branching_Overhead nor Irregular_Overhead", + "BriefDescription": "Total pipeline cost of \"useful operations\" - the portion of Retiring category not covered by Branching_Overhead nor Irregular_Overhead.", "MetricExpr": "100 * (tma_retiring - (BR_INST_RETIRED.ALL_BRANCHES + 2 * BR_INST_RETIRED.NEAR_CALL + INST_RETIRED.NOP) / tma_info_thread_slots - tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * tma_heavy_operations)", "MetricGroup": "BvUW;Ret", "MetricName": "tma_bottleneck_useful_work", "MetricThreshold": "tma_bottleneck_useful_work > 20" }, { - "BriefDescription": "This metric represents fraction of slots where the CPU was retiring branch instructions", + "BriefDescription": "This metric represents fraction of slots where the CPU was retiring branch instructions.", "MetricExpr": "tma_light_operations * BR_INST_RETIRED.ALL_BRANCHES / (tma_retiring * tma_info_thread_slots)", "MetricGroup": "Branches;BvBO;Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group", "MetricName": "tma_branch_instructions", @@ -248,8 +248,8 @@ "MetricExpr": "INT_MISC.CLEAR_RESTEER_CYCLES / tma_info_thread_clks + tma_unknown_branches", "MetricGroup": "FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group", "MetricName": "tma_branch_resteers", - "MetricThreshold": "tma_branch_resteers > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", - "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers. Branch Resteers estimates the Frontend delay in fetching operations from corrected path; following all sorts of miss-predicted branches. For example; branchy code with lots of miss-predictions might get categorized under Branch Resteers. Note the value of this node may overlap with its siblings. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_l3_hit_latency, tma_store_latency", + "MetricThreshold": "tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers. Branch Resteers estimates the Frontend delay in fetching operations from corrected path; following all sorts of miss-predicted branches. For example; branchy code with lots of miss-predictions might get categorized under Branch Resteers. Note the value of this node may overlap with its siblings. Sample with: BR_MISP_RETIRED.ALL_BRANCHES", "ScaleUnit": "100%" }, { @@ -257,8 +257,8 @@ "MetricExpr": "max(0, tma_microcode_sequencer - tma_assists)", "MetricGroup": "TopdownL4;tma_L4_group;tma_microcode_sequencer_group", "MetricName": "tma_cisc", - "MetricThreshold": "tma_cisc > 0.1 & tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1", - "PublicDescription": "This metric estimates fraction of cycles the CPU retired uops originated from CISC (complex instruction set computer) instruction. A CISC instruction has multiple uops that are required to perform the instruction's functionality as in the case of read-modify-write as an example. Since these instructions require multiple uops they may or may not imply sub-optimal use of machine resources", + "MetricThreshold": "tma_cisc > 0.1 & (tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1)", + "PublicDescription": "This metric estimates fraction of cycles the CPU retired uops originated from CISC (complex instruction set computer) instruction. A CISC instruction has multiple uops that are required to perform the instruction's functionality as in the case of read-modify-write as an example. Since these instructions require multiple uops they may or may not imply sub-optimal use of machine resources.", "ScaleUnit": "100%" }, { @@ -266,24 +266,24 @@ "MetricExpr": "(1 - BR_MISP_RETIRED.ALL_BRANCHES / (BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT)) * INT_MISC.CLEAR_RESTEER_CYCLES / tma_info_thread_clks", "MetricGroup": "BadSpec;MachineClears;TopdownL4;tma_L4_group;tma_branch_resteers_group;tma_issueMC", "MetricName": "tma_clears_resteers", - "MetricThreshold": "tma_clears_resteers > 0.05 & tma_branch_resteers > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricThreshold": "tma_clears_resteers > 0.05 & (tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))", "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Machine Clears. Sample with: INT_MISC.CLEAR_RESTEER_CYCLES. Related metrics: tma_l1_bound, tma_machine_clears, tma_microcode_sequencer, tma_ms_switches", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates fraction of cycles the CPU was stalled due to instruction cache misses that hit in the L2 cache", + "BriefDescription": "This metric estimates fraction of cycles the CPU was stalled due to instruction cache misses that hit in the L2 cache.", "MetricExpr": "max(0, tma_icache_misses - tma_code_l2_miss)", "MetricGroup": "FetchLat;IcMiss;Offcore;TopdownL4;tma_L4_group;tma_icache_misses_group", "MetricName": "tma_code_l2_hit", - "MetricThreshold": "tma_code_l2_hit > 0.05 & tma_icache_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricThreshold": "tma_code_l2_hit > 0.05 & (tma_icache_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates fraction of cycles the CPU was stalled due to instruction cache misses that miss in the L2 cache", + "BriefDescription": "This metric estimates fraction of cycles the CPU was stalled due to instruction cache misses that miss in the L2 cache.", "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_CODE_RD / tma_info_thread_clks", "MetricGroup": "FetchLat;IcMiss;Offcore;TopdownL4;tma_L4_group;tma_icache_misses_group", "MetricName": "tma_code_l2_miss", - "MetricThreshold": "tma_code_l2_miss > 0.05 & tma_icache_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricThreshold": "tma_code_l2_miss > 0.05 & (tma_icache_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))", "ScaleUnit": "100%" }, { @@ -291,7 +291,7 @@ "MetricExpr": "max(0, tma_itlb_misses - tma_code_stlb_miss)", "MetricGroup": "FetchLat;MemoryTLB;TopdownL4;tma_L4_group;tma_itlb_misses_group", "MetricName": "tma_code_stlb_hit", - "MetricThreshold": "tma_code_stlb_hit > 0.05 & tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricThreshold": "tma_code_stlb_hit > 0.05 & (tma_itlb_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))", "ScaleUnit": "100%" }, { @@ -299,33 +299,33 @@ "MetricExpr": "ITLB_MISSES.WALK_ACTIVE / tma_info_thread_clks", "MetricGroup": "FetchLat;MemoryTLB;TopdownL4;tma_L4_group;tma_itlb_misses_group", "MetricName": "tma_code_stlb_miss", - "MetricThreshold": "tma_code_stlb_miss > 0.05 & tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricThreshold": "tma_code_stlb_miss > 0.05 & (tma_itlb_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 2 or 4 MB pages for (instruction) code accesses", + "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 2 or 4 MB pages for (instruction) code accesses.", "MetricExpr": "tma_code_stlb_miss * ITLB_MISSES.WALK_COMPLETED_2M_4M / (ITLB_MISSES.WALK_COMPLETED_4K + ITLB_MISSES.WALK_COMPLETED_2M_4M)", "MetricGroup": "FetchLat;MemoryTLB;TopdownL5;tma_L5_group;tma_code_stlb_miss_group", "MetricName": "tma_code_stlb_miss_2m", - "MetricThreshold": "tma_code_stlb_miss_2m > 0.05 & tma_code_stlb_miss > 0.05 & tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricThreshold": "tma_code_stlb_miss_2m > 0.05 & (tma_code_stlb_miss > 0.05 & (tma_itlb_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)))", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 4 KB pages for (instruction) code accesses", + "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 4 KB pages for (instruction) code accesses.", "MetricExpr": "tma_code_stlb_miss * ITLB_MISSES.WALK_COMPLETED_4K / (ITLB_MISSES.WALK_COMPLETED_4K + ITLB_MISSES.WALK_COMPLETED_2M_4M)", "MetricGroup": "FetchLat;MemoryTLB;TopdownL5;tma_L5_group;tma_code_stlb_miss_group", "MetricName": "tma_code_stlb_miss_4k", - "MetricThreshold": "tma_code_stlb_miss_4k > 0.05 & tma_code_stlb_miss > 0.05 & tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricThreshold": "tma_code_stlb_miss_4k > 0.05 & (tma_code_stlb_miss > 0.05 & (tma_itlb_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)))", "ScaleUnit": "100%" }, { "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses", "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "((32.5 * tma_info_system_core_frequency - 3.5 * tma_info_system_core_frequency) * MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM + (27 * tma_info_system_core_frequency - 3.5 * tma_info_system_core_frequency) * MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks", + "MetricExpr": "(29 * tma_info_system_core_frequency * MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM + 23.5 * tma_info_system_core_frequency * MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks", "MetricGroup": "BvMS;DataSharing;LockCont;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group", "MetricName": "tma_contested_accesses", - "MetricThreshold": "tma_contested_accesses > 0.05 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", - "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses. Contested accesses occur when data written by one Logical Processor are read by another Logical Processor on a different Physical Core. Examples of contested accesses include synchronizations such as locks; true data sharing such as modified locked variables; and false sharing. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM, MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS. Related metrics: tma_bottleneck_memory_synchronization, tma_data_sharing, tma_false_sharing, tma_machine_clears", + "MetricThreshold": "tma_contested_accesses > 0.05 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses. Contested accesses occur when data written by one Logical Processor are read by another Logical Processor on a different Physical Core. Examples of contested accesses include synchronizations such as locks; true data sharing such as modified locked variables; and false sharing. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM_PS;MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS_PS. Related metrics: tma_bottleneck_memory_synchronization, tma_data_sharing, tma_false_sharing, tma_machine_clears, tma_remote_cache", "ScaleUnit": "100%" }, { @@ -335,25 +335,25 @@ "MetricName": "tma_core_bound", "MetricThreshold": "tma_core_bound > 0.1 & tma_backend_bound > 0.2", "MetricgroupNoGroup": "TopdownL2", - "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck. Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations)", + "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck. Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations).", "ScaleUnit": "100%" }, { "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses", "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "(27 * tma_info_system_core_frequency - 3.5 * tma_info_system_core_frequency) * MEM_LOAD_L3_HIT_RETIRED.XSNP_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks", + "MetricExpr": "23.5 * tma_info_system_core_frequency * MEM_LOAD_L3_HIT_RETIRED.XSNP_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks", "MetricGroup": "BvMS;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group", "MetricName": "tma_data_sharing", - "MetricThreshold": "tma_data_sharing > 0.05 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", - "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses. Data shared by multiple Logical Processors (even just read shared) may cause increased access latency due to cache coherency. Excessive data sharing can drastically harm multithreaded performance. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_HIT. Related metrics: tma_bottleneck_memory_synchronization, tma_contested_accesses, tma_false_sharing, tma_machine_clears", + "MetricThreshold": "tma_data_sharing > 0.05 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses. Data shared by multiple Logical Processors (even just read shared) may cause increased access latency due to cache coherency. Excessive data sharing can drastically harm multithreaded performance. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_HIT_PS. Related metrics: tma_bottleneck_memory_synchronization, tma_contested_accesses, tma_false_sharing, tma_machine_clears, tma_remote_cache", "ScaleUnit": "100%" }, { "BriefDescription": "This metric represents fraction of cycles where decoder-0 was the only active decoder", - "MetricExpr": "(cpu@INST_DECODED.DECODERS\\,cmask\\=0x1@ - cpu@INST_DECODED.DECODERS\\,cmask\\=0x2@) / tma_info_core_core_clks / 2", + "MetricExpr": "(cpu@INST_DECODED.DECODERS\\,cmask\\=1@ - cpu@INST_DECODED.DECODERS\\,cmask\\=2@) / tma_info_core_core_clks / 2", "MetricGroup": "DSBmiss;FetchBW;TopdownL4;tma_L4_group;tma_issueD0;tma_mite_group", "MetricName": "tma_decoder0_alone", - "MetricThreshold": "tma_decoder0_alone > 0.1 & tma_mite > 0.1 & tma_fetch_bandwidth > 0.2", + "MetricThreshold": "tma_decoder0_alone > 0.1 & (tma_mite > 0.1 & tma_fetch_bandwidth > 0.2)", "PublicDescription": "This metric represents fraction of cycles where decoder-0 was the only active decoder. Related metrics: tma_few_uops_instructions", "ScaleUnit": "100%" }, @@ -362,7 +362,7 @@ "MetricExpr": "ARITH.DIVIDER_ACTIVE / tma_info_thread_clks", "MetricGroup": "BvCB;TopdownL3;tma_L3_group;tma_core_bound_group", "MetricName": "tma_divider", - "MetricThreshold": "tma_divider > 0.2 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_divider > 0.2 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)", "PublicDescription": "This metric represents fraction of cycles where the Divider unit was active. Divide and square root instructions are performed by the Divider unit and can take considerably longer latency than integer or Floating Point addition; subtraction; or multiplication. Sample with: ARITH.DIVIDER_ACTIVE", "ScaleUnit": "100%" }, @@ -372,7 +372,7 @@ "MetricExpr": "CYCLE_ACTIVITY.STALLS_L3_MISS / tma_info_thread_clks + (CYCLE_ACTIVITY.STALLS_L1D_MISS - CYCLE_ACTIVITY.STALLS_L2_MISS) / tma_info_thread_clks - tma_l2_bound", "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_dram_bound", - "MetricThreshold": "tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", "PublicDescription": "This metric estimates how often the CPU was stalled on accesses to external memory (DRAM) by loads. Better caching can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L3_MISS", "ScaleUnit": "100%" }, @@ -382,7 +382,7 @@ "MetricGroup": "DSB;FetchBW;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group", "MetricName": "tma_dsb", "MetricThreshold": "tma_dsb > 0.15 & tma_fetch_bandwidth > 0.2", - "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to DSB (decoded uop cache) fetch pipeline. For example; inefficient utilization of the DSB cache structure or bank conflict when reading from it; are categorized here", + "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to DSB (decoded uop cache) fetch pipeline. For example; inefficient utilization of the DSB cache structure or bank conflict when reading from it; are categorized here.", "ScaleUnit": "100%" }, { @@ -390,26 +390,26 @@ "MetricExpr": "DSB2MITE_SWITCHES.PENALTY_CYCLES / tma_info_thread_clks", "MetricGroup": "DSBmiss;FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueFB", "MetricName": "tma_dsb_switches", - "MetricThreshold": "tma_dsb_switches > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", - "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines. The DSB (decoded i-cache) is a Uop Cache where the front-end directly delivers Uops (micro operations) avoiding heavy x86 decoding. The DSB pipeline has shorter latency and delivered higher bandwidth than the MITE (legacy instruction decode pipeline). Switching between the two pipelines can cause penalties hence this metric measures the exposed penalty. Sample with: FRONTEND_RETIRED.DSB_MISS. Related metrics: tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp", + "MetricThreshold": "tma_dsb_switches > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines. The DSB (decoded i-cache) is a Uop Cache where the front-end directly delivers Uops (micro operations) avoiding heavy x86 decoding. The DSB pipeline has shorter latency and delivered higher bandwidth than the MITE (legacy instruction decode pipeline). Switching between the two pipelines can cause penalties hence this metric measures the exposed penalty. Sample with: FRONTEND_RETIRED.DSB_MISS_PS. Related metrics: tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp", "ScaleUnit": "100%" }, { "BriefDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses", - "MetricExpr": "min(7 * cpu@DTLB_LOAD_MISSES.STLB_HIT\\,cmask\\=0x1@ + DTLB_LOAD_MISSES.WALK_ACTIVE, max(CYCLE_ACTIVITY.CYCLES_MEM_ANY - CYCLE_ACTIVITY.CYCLES_L1D_MISS, 0)) / tma_info_thread_clks", + "MetricExpr": "min(7 * cpu@DTLB_LOAD_MISSES.STLB_HIT\\,cmask\\=1@ + DTLB_LOAD_MISSES.WALK_ACTIVE, max(CYCLE_ACTIVITY.CYCLES_MEM_ANY - CYCLE_ACTIVITY.CYCLES_L1D_MISS, 0)) / tma_info_thread_clks", "MetricGroup": "BvMT;MemoryTLB;TopdownL4;tma_L4_group;tma_issueTLB;tma_l1_bound_group", "MetricName": "tma_dtlb_load", - "MetricThreshold": "tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", - "PublicDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses. TLBs (Translation Look-aside Buffers) are processor caches for recently used entries out of the Page Tables that are used to map virtual- to physical-addresses by the operating system. This metric approximates the potential delay of demand loads missing the first-level data TLB (assuming worst case scenario with back to back misses to different pages). This includes hitting in the second-level TLB (STLB) as well as performing a hardware page walk on an STLB miss. Sample with: MEM_INST_RETIRED.STLB_MISS_LOADS. Related metrics: tma_bottleneck_memory_data_tlbs, tma_dtlb_store", + "MetricThreshold": "tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses. TLBs (Translation Look-aside Buffers) are processor caches for recently used entries out of the Page Tables that are used to map virtual- to physical-addresses by the operating system. This metric approximates the potential delay of demand loads missing the first-level data TLB (assuming worst case scenario with back to back misses to different pages). This includes hitting in the second-level TLB (STLB) as well as performing a hardware page walk on an STLB miss. Sample with: MEM_INST_RETIRED.STLB_MISS_LOADS_PS. Related metrics: tma_bottleneck_memory_data_tlbs, tma_dtlb_store", "ScaleUnit": "100%" }, { "BriefDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses", - "MetricExpr": "(7 * cpu@DTLB_STORE_MISSES.STLB_HIT\\,cmask\\=0x1@ + DTLB_STORE_MISSES.WALK_ACTIVE) / tma_info_core_core_clks", + "MetricExpr": "(7 * cpu@DTLB_STORE_MISSES.STLB_HIT\\,cmask\\=1@ + DTLB_STORE_MISSES.WALK_ACTIVE) / tma_info_core_core_clks", "MetricGroup": "BvMT;MemoryTLB;TopdownL4;tma_L4_group;tma_issueTLB;tma_store_bound_group", "MetricName": "tma_dtlb_store", - "MetricThreshold": "tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", - "PublicDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses. As with ordinary data caching; focus on improving data locality and reducing working-set size to reduce DTLB overhead. Additionally; consider using profile-guided optimization (PGO) to collocate frequently-used data on the same page. Try using larger page sizes for large amounts of frequently-used data. Sample with: MEM_INST_RETIRED.STLB_MISS_STORES. Related metrics: tma_bottleneck_memory_data_tlbs, tma_dtlb_load", + "MetricThreshold": "tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses. As with ordinary data caching; focus on improving data locality and reducing working-set size to reduce DTLB overhead. Additionally; consider using profile-guided optimization (PGO) to collocate frequently-used data on the same page. Try using larger page sizes for large amounts of frequently-used data. Sample with: MEM_INST_RETIRED.STLB_MISS_STORES_PS. Related metrics: tma_bottleneck_memory_data_tlbs, tma_dtlb_load", "ScaleUnit": "100%" }, { @@ -417,8 +417,8 @@ "MetricExpr": "32.5 * tma_info_system_core_frequency * OCR.DEMAND_RFO.L3_HIT.SNOOP_HITM / tma_info_thread_clks", "MetricGroup": "BvMS;DataSharing;LockCont;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_store_bound_group", "MetricName": "tma_false_sharing", - "MetricThreshold": "tma_false_sharing > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", - "PublicDescription": "This metric roughly estimates how often CPU was handling synchronizations due to False Sharing. False Sharing is a multithreading hiccup; where multiple Logical Processors contend on different data-elements mapped into the same cache line. Sample with: OCR.DEMAND_RFO.L3_HIT.SNOOP_HITM. Related metrics: tma_bottleneck_memory_synchronization, tma_contested_accesses, tma_data_sharing, tma_machine_clears", + "MetricThreshold": "tma_false_sharing > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric roughly estimates how often CPU was handling synchronizations due to False Sharing. False Sharing is a multithreading hiccup; where multiple Logical Processors contend on different data-elements mapped into the same cache line. Sample with: OCR.DEMAND_RFO.L3_HIT.SNOOP_HITM. Related metrics: tma_bottleneck_memory_synchronization, tma_contested_accesses, tma_data_sharing, tma_machine_clears, tma_remote_cache", "ScaleUnit": "100%" }, { @@ -437,7 +437,7 @@ "MetricName": "tma_fetch_bandwidth", "MetricThreshold": "tma_fetch_bandwidth > 0.2", "MetricgroupNoGroup": "TopdownL2", - "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues. For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Sample with: FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1, FRONTEND_RETIRED.LATENCY_GE_1, FRONTEND_RETIRED.LATENCY_GE_2. Related metrics: tma_dsb_switches, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp", + "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues. For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Sample with: FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1;FRONTEND_RETIRED.LATENCY_GE_1;FRONTEND_RETIRED.LATENCY_GE_2. Related metrics: tma_dsb_switches, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp", "ScaleUnit": "100%" }, { @@ -447,7 +447,7 @@ "MetricName": "tma_fetch_latency", "MetricThreshold": "tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", "MetricgroupNoGroup": "TopdownL2", - "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues. For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: FRONTEND_RETIRED.LATENCY_GE_16, FRONTEND_RETIRED.LATENCY_GE_8", + "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues. For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: FRONTEND_RETIRED.LATENCY_GE_16_PS;FRONTEND_RETIRED.LATENCY_GE_8_PS", "ScaleUnit": "100%" }, { @@ -465,7 +465,7 @@ "MetricGroup": "HPC;TopdownL3;tma_L3_group;tma_light_operations_group", "MetricName": "tma_fp_arith", "MetricThreshold": "tma_fp_arith > 0.2 & tma_light_operations > 0.6", - "PublicDescription": "This metric represents overall arithmetic floating-point (FP) operations fraction the CPU has executed (retired). Note this metric's value may exceed its parent due to use of \"Uops\" CountDomain and FMA double-counting", + "PublicDescription": "This metric represents overall arithmetic floating-point (FP) operations fraction the CPU has executed (retired). Note this metric's value may exceed its parent due to use of \"Uops\" CountDomain and FMA double-counting.", "ScaleUnit": "100%" }, { @@ -474,15 +474,15 @@ "MetricGroup": "HPC;TopdownL5;tma_L5_group;tma_assists_group", "MetricName": "tma_fp_assists", "MetricThreshold": "tma_fp_assists > 0.1", - "PublicDescription": "This metric roughly estimates fraction of slots the CPU retired uops as a result of handing Floating Point (FP) Assists. FP Assist may apply when working with very small floating point values (so-called Denormals)", + "PublicDescription": "This metric roughly estimates fraction of slots the CPU retired uops as a result of handing Floating Point (FP) Assists. FP Assist may apply when working with very small floating point values (so-called Denormals).", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of cycles where the Floating-Point Divider unit was active", + "BriefDescription": "This metric represents fraction of cycles where the Floating-Point Divider unit was active.", "MetricExpr": "ARITH.FP_DIVIDER_ACTIVE / tma_info_thread_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_divider_group", "MetricName": "tma_fp_divider", - "MetricThreshold": "tma_fp_divider > 0.2 & tma_divider > 0.2 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_fp_divider > 0.2 & (tma_divider > 0.2 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", "ScaleUnit": "100%" }, { @@ -490,7 +490,7 @@ "MetricExpr": "FP_ARITH_INST_RETIRED.SCALAR / (tma_retiring * tma_info_thread_slots)", "MetricGroup": "Compute;Flops;TopdownL4;tma_L4_group;tma_fp_arith_group;tma_issue2P", "MetricName": "tma_fp_scalar", - "MetricThreshold": "tma_fp_scalar > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6", + "MetricThreshold": "tma_fp_scalar > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6)", "PublicDescription": "This metric approximates arithmetic floating-point (FP) scalar uops fraction the CPU has retired. May overcount due to FMA double counting. Related metrics: tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%" }, @@ -499,7 +499,7 @@ "MetricExpr": "FP_ARITH_INST_RETIRED.VECTOR / (tma_retiring * tma_info_thread_slots)", "MetricGroup": "Compute;Flops;TopdownL4;tma_L4_group;tma_fp_arith_group;tma_issue2P", "MetricName": "tma_fp_vector", - "MetricThreshold": "tma_fp_vector > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6", + "MetricThreshold": "tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6)", "PublicDescription": "This metric approximates arithmetic floating-point (FP) vector uops fraction the CPU has retired aggregated across all vector widths. May overcount due to FMA double counting. Related metrics: tma_fp_scalar, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%" }, @@ -508,7 +508,7 @@ "MetricExpr": "(FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE) / (tma_retiring * tma_info_thread_slots)", "MetricGroup": "Compute;Flops;TopdownL5;tma_L5_group;tma_fp_vector_group;tma_issue2P", "MetricName": "tma_fp_vector_128b", - "MetricThreshold": "tma_fp_vector_128b > 0.1 & tma_fp_vector > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6", + "MetricThreshold": "tma_fp_vector_128b > 0.1 & (tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6))", "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 128-bit wide vectors. May overcount due to FMA double counting prior to LNL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%" }, @@ -517,7 +517,7 @@ "MetricExpr": "(FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE) / (tma_retiring * tma_info_thread_slots)", "MetricGroup": "Compute;Flops;TopdownL5;tma_L5_group;tma_fp_vector_group;tma_issue2P", "MetricName": "tma_fp_vector_256b", - "MetricThreshold": "tma_fp_vector_256b > 0.1 & tma_fp_vector > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6", + "MetricThreshold": "tma_fp_vector_256b > 0.1 & (tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6))", "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 256-bit wide vectors. May overcount due to FMA double counting prior to LNL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%" }, @@ -526,7 +526,7 @@ "MetricExpr": "(FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE) / (tma_retiring * tma_info_thread_slots)", "MetricGroup": "Compute;Flops;TopdownL5;tma_L5_group;tma_fp_vector_group;tma_issue2P", "MetricName": "tma_fp_vector_512b", - "MetricThreshold": "tma_fp_vector_512b > 0.1 & tma_fp_vector > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6", + "MetricThreshold": "tma_fp_vector_512b > 0.1 & (tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6))", "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 512-bit wide vectors. May overcount due to FMA double counting. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%" }, @@ -538,17 +538,17 @@ "MetricName": "tma_frontend_bound", "MetricThreshold": "tma_frontend_bound > 0.15", "MetricgroupNoGroup": "TopdownL1;Default", - "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound. Sample with: FRONTEND_RETIRED.LATENCY_GE_4", + "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound. Sample with: FRONTEND_RETIRED.LATENCY_GE_4_PS", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations , instructions that require two or more uops or micro-coded sequences", - "MetricExpr": "tma_microcode_sequencer + tma_retiring * (UOPS_DECODED.DEC0 - cpu@UOPS_DECODED.DEC0\\,cmask\\=0x1@) / IDQ.MITE_UOPS", + "BriefDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences", + "MetricExpr": "tma_microcode_sequencer + tma_retiring * (UOPS_DECODED.DEC0 - cpu@UOPS_DECODED.DEC0\\,cmask\\=1@) / IDQ.MITE_UOPS", "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_heavy_operations", "MetricThreshold": "tma_heavy_operations > 0.1", "MetricgroupNoGroup": "TopdownL2", - "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations , instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences.([ICL+] Note this may overcount due to approximation using indirect events; [ADL+])", + "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences.([ICL+] Note this may overcount due to approximation using indirect events; [ADL+])", "ScaleUnit": "100%" }, { @@ -556,8 +556,8 @@ "MetricExpr": "ICACHE_DATA.STALLS / tma_info_thread_clks", "MetricGroup": "BigFootprint;BvBC;FetchLat;IcMiss;TopdownL3;tma_L3_group;tma_fetch_latency_group", "MetricName": "tma_icache_misses", - "MetricThreshold": "tma_icache_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", - "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to instruction cache misses. Sample with: FRONTEND_RETIRED.L2_MISS, FRONTEND_RETIRED.L1I_MISS", + "MetricThreshold": "tma_icache_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to instruction cache misses. Sample with: FRONTEND_RETIRED.L2_MISS_PS;FRONTEND_RETIRED.L1I_MISS_PS", "ScaleUnit": "100%" }, { @@ -569,28 +569,28 @@ "PublicDescription": "Branch Misprediction Cost: Cycles representing fraction of TMA slots wasted per non-speculative branch misprediction (retired JEClear). Related metrics: tma_bottleneck_mispredictions, tma_branch_mispredicts, tma_mispredicts_resteers" }, { - "BriefDescription": "Instructions per retired Mispredicts for conditional non-taken branches (lower number means higher occurrence rate)", + "BriefDescription": "Instructions per retired Mispredicts for conditional non-taken branches (lower number means higher occurrence rate).", "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.COND_NTAKEN", "MetricGroup": "Bad;BrMispredicts", "MetricName": "tma_info_bad_spec_ipmisp_cond_ntaken", "MetricThreshold": "tma_info_bad_spec_ipmisp_cond_ntaken < 200" }, { - "BriefDescription": "Instructions per retired Mispredicts for conditional taken branches (lower number means higher occurrence rate)", + "BriefDescription": "Instructions per retired Mispredicts for conditional taken branches (lower number means higher occurrence rate).", "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.COND_TAKEN", "MetricGroup": "Bad;BrMispredicts", "MetricName": "tma_info_bad_spec_ipmisp_cond_taken", "MetricThreshold": "tma_info_bad_spec_ipmisp_cond_taken < 200" }, { - "BriefDescription": "Instructions per retired Mispredicts for indirect CALL or JMP branches (lower number means higher occurrence rate)", + "BriefDescription": "Instructions per retired Mispredicts for indirect CALL or JMP branches (lower number means higher occurrence rate).", "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.INDIRECT", "MetricGroup": "Bad;BrMispredicts", "MetricName": "tma_info_bad_spec_ipmisp_indirect", - "MetricThreshold": "tma_info_bad_spec_ipmisp_indirect < 1000" + "MetricThreshold": "tma_info_bad_spec_ipmisp_indirect < 1e3" }, { - "BriefDescription": "Instructions per retired Mispredicts for return branches (lower number means higher occurrence rate)", + "BriefDescription": "Instructions per retired Mispredicts for return branches (lower number means higher occurrence rate).", "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.RET", "MetricGroup": "Bad;BrMispredicts", "MetricName": "tma_info_bad_spec_ipmisp_ret", @@ -619,7 +619,7 @@ }, { "BriefDescription": "Total pipeline cost of DSB (uop cache) hits - subset of the Instruction_Fetch_BW Bottleneck", - "MetricExpr": "100 * (tma_frontend_bound * (tma_fetch_bandwidth / (tma_fetch_latency + tma_fetch_bandwidth)) * (tma_dsb / (tma_mite + tma_dsb + tma_lsd + tma_ms)))", + "MetricExpr": "100 * (tma_frontend_bound * (tma_fetch_bandwidth / (tma_fetch_bandwidth + tma_fetch_latency)) * (tma_dsb / (tma_dsb + tma_lsd + tma_mite + tma_ms)))", "MetricGroup": "DSB;Fed;FetchBW;tma_issueFB", "MetricName": "tma_info_botlnk_l2_dsb_bandwidth", "MetricThreshold": "tma_info_botlnk_l2_dsb_bandwidth > 10", @@ -628,7 +628,7 @@ { "BriefDescription": "Total pipeline cost of DSB (uop cache) misses - subset of the Instruction_Fetch_BW Bottleneck", "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "100 * (tma_fetch_latency * tma_dsb_switches / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches) + tma_fetch_bandwidth * tma_mite / (tma_mite + tma_dsb + tma_lsd + tma_ms))", + "MetricExpr": "100 * (tma_fetch_latency * tma_dsb_switches / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) + tma_fetch_bandwidth * tma_mite / (tma_dsb + tma_lsd + tma_mite + tma_ms))", "MetricGroup": "DSBmiss;Fed;tma_issueFB", "MetricName": "tma_info_botlnk_l2_dsb_misses", "MetricThreshold": "tma_info_botlnk_l2_dsb_misses > 10", @@ -637,10 +637,11 @@ { "BriefDescription": "Total pipeline cost of Instruction Cache misses - subset of the Big_Code Bottleneck", "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "100 * (tma_fetch_latency * tma_icache_misses / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches))", + "MetricExpr": "100 * (tma_fetch_latency * tma_icache_misses / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches))", "MetricGroup": "Fed;FetchLat;IcMiss;tma_issueFL", "MetricName": "tma_info_botlnk_l2_ic_misses", - "MetricThreshold": "tma_info_botlnk_l2_ic_misses > 5" + "MetricThreshold": "tma_info_botlnk_l2_ic_misses > 5", + "PublicDescription": "Total pipeline cost of Instruction Cache misses - subset of the Big_Code Bottleneck. Related metrics: " }, { "BriefDescription": "Fraction of branches that are CALL or RET", @@ -701,11 +702,11 @@ "MetricExpr": "(FP_ARITH_INST_RETIRED.SCALAR + FP_ARITH_INST_RETIRED.VECTOR) / (2 * tma_info_core_core_clks)", "MetricGroup": "Cor;Flops;HPC", "MetricName": "tma_info_core_fp_arith_utilization", - "PublicDescription": "Actual per-core usage of the Floating Point non-X87 execution units (regardless of precision or vector-width). Values > 1 are possible due to ([BDW+] Fused-Multiply Add (FMA) counting - common; [ADL+] use all of ADD/MUL/FMA in Scalar or 128/256-bit vectors - less common)" + "PublicDescription": "Actual per-core usage of the Floating Point non-X87 execution units (regardless of precision or vector-width). Values > 1 are possible due to ([BDW+] Fused-Multiply Add (FMA) counting - common; [ADL+] use all of ADD/MUL/FMA in Scalar or 128/256-bit vectors - less common)." }, { "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is execution) per thread (logical-processor)", - "MetricExpr": "UOPS_EXECUTED.THREAD / cpu@UOPS_EXECUTED.THREAD\\,cmask\\=0x1@", + "MetricExpr": "UOPS_EXECUTED.THREAD / cpu@UOPS_EXECUTED.THREAD\\,cmask\\=1@", "MetricGroup": "Backend;Cor;Pipeline;PortsUtil", "MetricName": "tma_info_core_ilp" }, @@ -718,20 +719,20 @@ "PublicDescription": "Fraction of Uops delivered by the DSB (aka Decoded ICache; or Uop Cache). Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_inst_mix_iptb, tma_lcp" }, { - "BriefDescription": "Average number of cycles of a switch from the DSB fetch-unit to MITE fetch unit - see DSB_Switches tree node for details", - "MetricExpr": "DSB2MITE_SWITCHES.PENALTY_CYCLES / cpu@DSB2MITE_SWITCHES.PENALTY_CYCLES\\,cmask\\=0x1\\,edge\\=0x1@", + "BriefDescription": "Average number of cycles of a switch from the DSB fetch-unit to MITE fetch unit - see DSB_Switches tree node for details.", + "MetricExpr": "DSB2MITE_SWITCHES.PENALTY_CYCLES / cpu@DSB2MITE_SWITCHES.PENALTY_CYCLES\\,cmask\\=1\\,edge@", "MetricGroup": "DSBmiss", "MetricName": "tma_info_frontend_dsb_switch_cost" }, { "BriefDescription": "Average number of Uops issued by front-end when it issued something", - "MetricExpr": "UOPS_ISSUED.ANY / cpu@UOPS_ISSUED.ANY\\,cmask\\=0x1@", + "MetricExpr": "UOPS_ISSUED.ANY / cpu@UOPS_ISSUED.ANY\\,cmask\\=1@", "MetricGroup": "Fed;FetchBW", "MetricName": "tma_info_frontend_fetch_upc" }, { "BriefDescription": "Average Latency for L1 instruction cache misses", - "MetricExpr": "ICACHE_16B.IFDATA_STALL / cpu@ICACHE_16B.IFDATA_STALL\\,cmask\\=0x1\\,edge\\=0x1@", + "MetricExpr": "ICACHE_16B.IFDATA_STALL / cpu@ICACHE_16B.IFDATA_STALL\\,cmask\\=1\\,edge@", "MetricGroup": "Fed;FetchLat;IcMiss", "MetricName": "tma_info_frontend_icache_miss_latency" }, @@ -773,7 +774,7 @@ "MetricName": "tma_info_frontend_tbpc" }, { - "BriefDescription": "Branch instructions per taken branch", + "BriefDescription": "Branch instructions per taken branch.", "MetricExpr": "BR_INST_RETIRED.ALL_BRANCHES / BR_INST_RETIRED.NEAR_TAKEN", "MetricGroup": "Branches;Fed;PGO", "MetricName": "tma_info_inst_mix_bptkbranch" @@ -791,7 +792,7 @@ "MetricGroup": "Flops;InsType", "MetricName": "tma_info_inst_mix_iparith", "MetricThreshold": "tma_info_inst_mix_iparith < 10", - "PublicDescription": "Instructions per FP Arithmetic instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting. Approximated prior to BDW" + "PublicDescription": "Instructions per FP Arithmetic instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting. Approximated prior to BDW." }, { "BriefDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number means higher occurrence rate)", @@ -799,7 +800,7 @@ "MetricGroup": "Flops;FpVector;InsType", "MetricName": "tma_info_inst_mix_iparith_avx128", "MetricThreshold": "tma_info_inst_mix_iparith_avx128 < 10", - "PublicDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting" + "PublicDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting." }, { "BriefDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means higher occurrence rate)", @@ -807,7 +808,7 @@ "MetricGroup": "Flops;FpVector;InsType", "MetricName": "tma_info_inst_mix_iparith_avx256", "MetricThreshold": "tma_info_inst_mix_iparith_avx256 < 10", - "PublicDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting" + "PublicDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting." }, { "BriefDescription": "Instructions per FP Arithmetic AVX 512-bit instruction (lower number means higher occurrence rate)", @@ -815,7 +816,7 @@ "MetricGroup": "Flops;FpVector;InsType", "MetricName": "tma_info_inst_mix_iparith_avx512", "MetricThreshold": "tma_info_inst_mix_iparith_avx512 < 10", - "PublicDescription": "Instructions per FP Arithmetic AVX 512-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting" + "PublicDescription": "Instructions per FP Arithmetic AVX 512-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting." }, { "BriefDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction (lower number means higher occurrence rate)", @@ -823,7 +824,7 @@ "MetricGroup": "Flops;FpScalar;InsType", "MetricName": "tma_info_inst_mix_iparith_scalar_dp", "MetricThreshold": "tma_info_inst_mix_iparith_scalar_dp < 10", - "PublicDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting" + "PublicDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting." }, { "BriefDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction (lower number means higher occurrence rate)", @@ -831,7 +832,7 @@ "MetricGroup": "Flops;FpScalar;InsType", "MetricName": "tma_info_inst_mix_iparith_scalar_sp", "MetricThreshold": "tma_info_inst_mix_iparith_scalar_sp < 10", - "PublicDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting" + "PublicDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting." }, { "BriefDescription": "Instructions per Branch (lower number means higher occurrence rate)", @@ -886,7 +887,7 @@ "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_TAKEN", "MetricGroup": "Branches;Fed;FetchBW;Frontend;PGO;tma_issueFB", "MetricName": "tma_info_inst_mix_iptb", - "MetricThreshold": "tma_info_inst_mix_iptb < 5 * 2 + 1", + "MetricThreshold": "tma_info_inst_mix_iptb < 11", "PublicDescription": "Instructions per taken branch. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_lcp" }, { @@ -1011,7 +1012,7 @@ }, { "BriefDescription": "Average Parallel L2 cache miss demand Loads", - "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD / cpu@OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD\\,cmask\\=0x1@", + "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD / cpu@OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD\\,cmask\\=1@", "MetricGroup": "Memory_BW;Offcore", "MetricName": "tma_info_memory_latency_load_l2_mlp" }, @@ -1073,8 +1074,8 @@ "MetricName": "tma_info_memory_tlb_store_stlb_mpki" }, { - "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is execution) per core", - "MetricExpr": "UOPS_EXECUTED.THREAD / (UOPS_EXECUTED.CORE_CYCLES_GE_1 / 2 if #SMT_on else cpu@UOPS_EXECUTED.THREAD\\,cmask\\=0x1@)", + "BriefDescription": "", + "MetricExpr": "UOPS_EXECUTED.THREAD / (UOPS_EXECUTED.CORE_CYCLES_GE_1 / 2 if #SMT_on else cpu@UOPS_EXECUTED.THREAD\\,cmask\\=1@)", "MetricGroup": "Cor;Pipeline;PortsUtil;SMT", "MetricName": "tma_info_pipeline_execute" }, @@ -1101,12 +1102,12 @@ "MetricExpr": "INST_RETIRED.ANY / ASSISTS.ANY", "MetricGroup": "MicroSeq;Pipeline;Ret;Retire", "MetricName": "tma_info_pipeline_ipassist", - "MetricThreshold": "tma_info_pipeline_ipassist < 100000", + "MetricThreshold": "tma_info_pipeline_ipassist < 100e3", "PublicDescription": "Instructions per a microcode Assist invocation. See Assists tree node for details (lower number means higher occurrence rate)" }, { - "BriefDescription": "Average number of Uops retired in cycles where at least one uop has retired", - "MetricExpr": "tma_retiring * tma_info_thread_slots / cpu@UOPS_RETIRED.SLOTS\\,cmask\\=0x1@", + "BriefDescription": "Average number of Uops retired in cycles where at least one uop has retired.", + "MetricExpr": "tma_retiring * tma_info_thread_slots / cpu@UOPS_RETIRED.SLOTS\\,cmask\\=1@", "MetricGroup": "Pipeline;Ret", "MetricName": "tma_info_pipeline_retire" }, @@ -1147,14 +1148,13 @@ "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.FAR_BRANCH:u", "MetricGroup": "Branches;OS", "MetricName": "tma_info_system_ipfarbranch", - "MetricThreshold": "tma_info_system_ipfarbranch < 1000000" + "MetricThreshold": "tma_info_system_ipfarbranch < 1e6" }, { "BriefDescription": "Cycles Per Instruction for the Operating System (OS) Kernel mode", "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P:k / INST_RETIRED.ANY_P:k", "MetricGroup": "OS", - "MetricName": "tma_info_system_kernel_cpi", - "ScaleUnit": "1per_instr" + "MetricName": "tma_info_system_kernel_cpi" }, { "BriefDescription": "Fraction of cycles spent in the Operating System (OS) Kernel mode", @@ -1195,7 +1195,7 @@ "MetricExpr": "CORE_POWER.LVL0_TURBO_LICENSE / tma_info_core_core_clks", "MetricGroup": "Power", "MetricName": "tma_info_system_power_license0_utilization", - "PublicDescription": "Fraction of Core cycles where the core was running with power-delivery for baseline license level 0. This includes non-AVX codes, SSE, AVX 128-bit, and low-current AVX 256-bit codes" + "PublicDescription": "Fraction of Core cycles where the core was running with power-delivery for baseline license level 0. This includes non-AVX codes, SSE, AVX 128-bit, and low-current AVX 256-bit codes." }, { "BriefDescription": "Fraction of Core cycles where the core was running with power-delivery for license level 1", @@ -1203,7 +1203,7 @@ "MetricGroup": "Power", "MetricName": "tma_info_system_power_license1_utilization", "MetricThreshold": "tma_info_system_power_license1_utilization > 0.5", - "PublicDescription": "Fraction of Core cycles where the core was running with power-delivery for license level 1. This includes high current AVX 256-bit instructions as well as low current AVX 512-bit instructions" + "PublicDescription": "Fraction of Core cycles where the core was running with power-delivery for license level 1. This includes high current AVX 256-bit instructions as well as low current AVX 512-bit instructions." }, { "BriefDescription": "Fraction of Core cycles where the core was running with power-delivery for license level 2 (introduced in SKX)", @@ -1211,7 +1211,7 @@ "MetricGroup": "Power", "MetricName": "tma_info_system_power_license2_utilization", "MetricThreshold": "tma_info_system_power_license2_utilization > 0.5", - "PublicDescription": "Fraction of Core cycles where the core was running with power-delivery for license level 2 (introduced in SKX). This includes high current AVX 512-bit instructions" + "PublicDescription": "Fraction of Core cycles where the core was running with power-delivery for license level 2 (introduced in SKX). This includes high current AVX 512-bit instructions." }, { "BriefDescription": "Fraction of cycles where both hardware Logical Processors were active", @@ -1239,7 +1239,7 @@ "MetricName": "tma_info_system_turbo_utilization" }, { - "BriefDescription": "Per-Logical Processor actual clocks when the Logical Processor is active", + "BriefDescription": "Per-Logical Processor actual clocks when the Logical Processor is active.", "MetricExpr": "CPU_CLK_UNHALTED.THREAD", "MetricGroup": "Pipeline", "MetricName": "tma_info_thread_clks" @@ -1248,15 +1248,14 @@ "BriefDescription": "Cycles Per Instruction (per Logical Processor)", "MetricExpr": "1 / tma_info_thread_ipc", "MetricGroup": "Mem;Pipeline", - "MetricName": "tma_info_thread_cpi", - "ScaleUnit": "1per_instr" + "MetricName": "tma_info_thread_cpi" }, { "BriefDescription": "The ratio of Executed- by Issued-Uops", "MetricExpr": "UOPS_EXECUTED.THREAD / UOPS_ISSUED.ANY", "MetricGroup": "Cor;Pipeline", "MetricName": "tma_info_thread_execute_per_issue", - "PublicDescription": "The ratio of Executed- by Issued-Uops. Ratio > 1 suggests high rate of uop micro-fusions. Ratio < 1 suggest high rate of \"execute\" at rename stage" + "PublicDescription": "The ratio of Executed- by Issued-Uops. Ratio > 1 suggests high rate of uop micro-fusions. Ratio < 1 suggest high rate of \"execute\" at rename stage." }, { "BriefDescription": "Instructions Per Cycle (per Logical Processor)", @@ -1266,13 +1265,13 @@ }, { "BriefDescription": "Total issue-pipeline slots (per-Physical Core till ICL; per-Logical Processor ICL onward)", - "MetricExpr": "slots", + "MetricExpr": "TOPDOWN.SLOTS", "MetricGroup": "TmaL1;tma_L1_group", "MetricName": "tma_info_thread_slots" }, { "BriefDescription": "Fraction of Physical Core issue-slots utilized by this Logical Processor", - "MetricExpr": "(tma_info_thread_slots / (slots / 2) if #SMT_on else 1)", + "MetricExpr": "(tma_info_thread_slots / (TOPDOWN.SLOTS / 2) if #SMT_on else 1)", "MetricGroup": "SMT;TmaL1;tma_L1_group", "MetricName": "tma_info_thread_slots_utilization" }, @@ -1288,14 +1287,14 @@ "MetricExpr": "tma_retiring * tma_info_thread_slots / BR_INST_RETIRED.NEAR_TAKEN", "MetricGroup": "Branches;Fed;FetchBW", "MetricName": "tma_info_thread_uptb", - "MetricThreshold": "tma_info_thread_uptb < 5 * 1.5" + "MetricThreshold": "tma_info_thread_uptb < 7.5" }, { - "BriefDescription": "This metric represents fraction of cycles where the Integer Divider unit was active", + "BriefDescription": "This metric represents fraction of cycles where the Integer Divider unit was active.", "MetricExpr": "tma_divider - tma_fp_divider", "MetricGroup": "TopdownL4;tma_L4_group;tma_divider_group", "MetricName": "tma_int_divider", - "MetricThreshold": "tma_int_divider > 0.2 & tma_divider > 0.2 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_int_divider > 0.2 & (tma_divider > 0.2 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", "ScaleUnit": "100%" }, { @@ -1303,8 +1302,8 @@ "MetricExpr": "ICACHE_TAG.STALLS / tma_info_thread_clks", "MetricGroup": "BigFootprint;BvBC;FetchLat;MemoryTLB;TopdownL3;tma_L3_group;tma_fetch_latency_group", "MetricName": "tma_itlb_misses", - "MetricThreshold": "tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", - "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Instruction TLB (ITLB) misses. Sample with: FRONTEND_RETIRED.STLB_MISS, FRONTEND_RETIRED.ITLB_MISS", + "MetricThreshold": "tma_itlb_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Instruction TLB (ITLB) misses. Sample with: FRONTEND_RETIRED.STLB_MISS_PS;FRONTEND_RETIRED.ITLB_MISS_PS", "ScaleUnit": "100%" }, { @@ -1312,7 +1311,7 @@ "MetricExpr": "max((CYCLE_ACTIVITY.STALLS_MEM_ANY - CYCLE_ACTIVITY.STALLS_L1D_MISS) / tma_info_thread_clks, 0)", "MetricGroup": "CacheHits;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_issueL1;tma_issueMC;tma_memory_bound_group", "MetricName": "tma_l1_bound", - "MetricThreshold": "tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", "PublicDescription": "This metric estimates how often the CPU was stalled without loads missing the L1 Data (L1D) cache. The L1D cache typically has the shortest latency. However; in certain cases like loads blocked on older stores; a load might suffer due to high latency even though it is being satisfied by the L1D. Another example is loads who miss in the TLB. These cases are characterized by execution unit stalls; while some non-completed demand load lives in the machine without having that demand load missing the L1 cache. Sample with: MEM_LOAD_RETIRED.L1_HIT. Related metrics: tma_clears_resteers, tma_machine_clears, tma_microcode_sequencer, tma_ms_switches, tma_ports_utilized_1", "ScaleUnit": "100%" }, @@ -1321,7 +1320,7 @@ "MetricExpr": "min(2 * (MEM_INST_RETIRED.ALL_LOADS - MEM_LOAD_RETIRED.FB_HIT - MEM_LOAD_RETIRED.L1_MISS) * 20 / 100, max(CYCLE_ACTIVITY.CYCLES_MEM_ANY - CYCLE_ACTIVITY.CYCLES_L1D_MISS, 0)) / tma_info_thread_clks", "MetricGroup": "BvML;MemoryLat;TopdownL4;tma_L4_group;tma_l1_bound_group", "MetricName": "tma_l1_latency_dependency", - "MetricThreshold": "tma_l1_latency_dependency > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_l1_latency_dependency > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", "PublicDescription": "This metric([SKL+] roughly; [LNL]) estimates fraction of cycles with demand load accesses that hit the L1D cache. The short latency of the L1D cache may be exposed in pointer-chasing memory access patterns as an example. Sample with: MEM_LOAD_RETIRED.L1_HIT", "ScaleUnit": "100%" }, @@ -1331,7 +1330,7 @@ "MetricExpr": "MEM_LOAD_RETIRED.L2_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) / (MEM_LOAD_RETIRED.L2_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) + L1D_PEND_MISS.FB_FULL_PERIODS) * ((CYCLE_ACTIVITY.STALLS_L1D_MISS - CYCLE_ACTIVITY.STALLS_L2_MISS) / tma_info_thread_clks)", "MetricGroup": "BvML;CacheHits;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_l2_bound", - "MetricThreshold": "tma_l2_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_l2_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", "PublicDescription": "This metric estimates how often the CPU was stalled due to L2 cache accesses by loads. Avoiding cache misses (i.e. L1 misses/L2 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L2_HIT", "ScaleUnit": "100%" }, @@ -1340,7 +1339,7 @@ "MetricExpr": "3.5 * tma_info_system_core_frequency * MEM_LOAD_RETIRED.L2_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks", "MetricGroup": "MemoryLat;TopdownL4;tma_L4_group;tma_l2_bound_group", "MetricName": "tma_l2_hit_latency", - "MetricThreshold": "tma_l2_hit_latency > 0.05 & tma_l2_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_l2_hit_latency > 0.05 & (tma_l2_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", "PublicDescription": "This metric represents fraction of cycles with demand load accesses that hit the L2 cache under unloaded scenarios (possibly L2 latency limited). Avoiding L1 cache misses (i.e. L1 misses/L2 hits) will improve the latency. Sample with: MEM_LOAD_RETIRED.L2_HIT", "ScaleUnit": "100%" }, @@ -1350,17 +1349,17 @@ "MetricExpr": "(CYCLE_ACTIVITY.STALLS_L2_MISS - CYCLE_ACTIVITY.STALLS_L3_MISS) / tma_info_thread_clks", "MetricGroup": "CacheHits;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_l3_bound", - "MetricThreshold": "tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", - "PublicDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core. Avoiding cache misses (i.e. L2 misses/L3 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L3_HIT", + "MetricThreshold": "tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", + "PublicDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core. Avoiding cache misses (i.e. L2 misses/L3 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L3_HIT_PS", "ScaleUnit": "100%" }, { "BriefDescription": "This metric estimates fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited)", - "MetricExpr": "(12.5 * tma_info_system_core_frequency - 3.5 * tma_info_system_core_frequency) * (MEM_LOAD_RETIRED.L3_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2)) / tma_info_thread_clks", + "MetricExpr": "9 * tma_info_system_core_frequency * (MEM_LOAD_RETIRED.L3_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2)) / tma_info_thread_clks", "MetricGroup": "BvML;MemoryLat;TopdownL4;tma_L4_group;tma_issueLat;tma_l3_bound_group", "MetricName": "tma_l3_hit_latency", - "MetricThreshold": "tma_l3_hit_latency > 0.1 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", - "PublicDescription": "This metric estimates fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited). Avoiding private cache misses (i.e. L2 misses/L3 hits) will improve the latency; reduce contention with sibling physical cores and increase performance. Note the value of this node may overlap with its siblings. Sample with: MEM_LOAD_RETIRED.L3_HIT. Related metrics: tma_bottleneck_cache_memory_latency, tma_branch_resteers, tma_mem_latency, tma_store_latency", + "MetricThreshold": "tma_l3_hit_latency > 0.1 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric estimates fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited). Avoiding private cache misses (i.e. L2 misses/L3 hits) will improve the latency; reduce contention with sibling physical cores and increase performance. Note the value of this node may overlap with its siblings. Sample with: MEM_LOAD_RETIRED.L3_HIT_PS. Related metrics: tma_bottleneck_cache_memory_latency, tma_mem_latency", "ScaleUnit": "100%" }, { @@ -1368,18 +1367,18 @@ "MetricExpr": "DECODE.LCP / tma_info_thread_clks", "MetricGroup": "FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueFB", "MetricName": "tma_lcp", - "MetricThreshold": "tma_lcp > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", - "PublicDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs). Using proper compiler flags or Intel Compiler by default will certainly avoid this. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb", + "MetricThreshold": "tma_lcp > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", + "PublicDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs). Using proper compiler flags or Intel Compiler by default will certainly avoid this. #Link: Optimization Guide about LCP BKMs. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations , instructions that require no more than one uop (micro-operation)", + "BriefDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation)", "MetricExpr": "max(0, tma_retiring - tma_heavy_operations)", "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_light_operations", "MetricThreshold": "tma_light_operations > 0.6", "MetricgroupNoGroup": "TopdownL2", - "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations , instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized code running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. ([ICL+] Note this may undercount due to approximation using indirect events; [ADL+] .). Sample with: INST_RETIRED.PREC_DIST", + "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized code running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. ([ICL+] Note this may undercount due to approximation using indirect events; [ADL+] .). Sample with: INST_RETIRED.PREC_DIST", "ScaleUnit": "100%" }, { @@ -1396,7 +1395,7 @@ "MetricExpr": "tma_dtlb_load - tma_load_stlb_miss", "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_load_group", "MetricName": "tma_load_stlb_hit", - "MetricThreshold": "tma_load_stlb_hit > 0.05 & tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_load_stlb_hit > 0.05 & (tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))", "ScaleUnit": "100%" }, { @@ -1404,31 +1403,31 @@ "MetricExpr": "DTLB_LOAD_MISSES.WALK_ACTIVE / tma_info_thread_clks", "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_load_group", "MetricName": "tma_load_stlb_miss", - "MetricThreshold": "tma_load_stlb_miss > 0.05 & tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_load_stlb_miss > 0.05 & (tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 1 GB pages for data load accesses", + "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 1 GB pages for data load accesses.", "MetricExpr": "tma_load_stlb_miss * DTLB_LOAD_MISSES.WALK_COMPLETED_1G / (DTLB_LOAD_MISSES.WALK_COMPLETED_4K + DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M + DTLB_LOAD_MISSES.WALK_COMPLETED_1G)", "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_load_stlb_miss_group", "MetricName": "tma_load_stlb_miss_1g", - "MetricThreshold": "tma_load_stlb_miss_1g > 0.05 & tma_load_stlb_miss > 0.05 & tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_load_stlb_miss_1g > 0.05 & (tma_load_stlb_miss > 0.05 & (tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))))", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 2 or 4 MB pages for data load accesses", + "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 2 or 4 MB pages for data load accesses.", "MetricExpr": "tma_load_stlb_miss * DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M / (DTLB_LOAD_MISSES.WALK_COMPLETED_4K + DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M + DTLB_LOAD_MISSES.WALK_COMPLETED_1G)", "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_load_stlb_miss_group", "MetricName": "tma_load_stlb_miss_2m", - "MetricThreshold": "tma_load_stlb_miss_2m > 0.05 & tma_load_stlb_miss > 0.05 & tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_load_stlb_miss_2m > 0.05 & (tma_load_stlb_miss > 0.05 & (tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))))", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 4 KB pages for data load accesses", + "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 4 KB pages for data load accesses.", "MetricExpr": "tma_load_stlb_miss * DTLB_LOAD_MISSES.WALK_COMPLETED_4K / (DTLB_LOAD_MISSES.WALK_COMPLETED_4K + DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M + DTLB_LOAD_MISSES.WALK_COMPLETED_1G)", "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_load_stlb_miss_group", "MetricName": "tma_load_stlb_miss_4k", - "MetricThreshold": "tma_load_stlb_miss_4k > 0.05 & tma_load_stlb_miss > 0.05 & tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_load_stlb_miss_4k > 0.05 & (tma_load_stlb_miss > 0.05 & (tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))))", "ScaleUnit": "100%" }, { @@ -1437,7 +1436,7 @@ "MetricExpr": "(16 * max(0, MEM_INST_RETIRED.LOCK_LOADS - L2_RQSTS.ALL_RFO) + MEM_INST_RETIRED.LOCK_LOADS / MEM_INST_RETIRED.ALL_STORES * (10 * L2_RQSTS.RFO_HIT + min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO))) / tma_info_thread_clks", "MetricGroup": "LockCont;Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_l1_bound_group", "MetricName": "tma_lock_latency", - "MetricThreshold": "tma_lock_latency > 0.2 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_lock_latency > 0.2 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", "PublicDescription": "This metric represents fraction of cycles the CPU spent handling cache misses due to lock operations. Due to the microarchitecture handling of locks; they are classified as L1_Bound regardless of what memory source satisfied them. Sample with: MEM_INST_RETIRED.LOCK_LOADS. Related metrics: tma_store_latency", "ScaleUnit": "100%" }, @@ -1447,7 +1446,7 @@ "MetricGroup": "FetchBW;LSD;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group", "MetricName": "tma_lsd", "MetricThreshold": "tma_lsd > 0.15 & tma_fetch_bandwidth > 0.2", - "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to LSD (Loop Stream Detector) unit. LSD typically does well sustaining Uop supply. However; in some rare cases; optimal uop-delivery could not be reached for small loops whose size (in terms of number of uops) does not suit well the LSD structure", + "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to LSD (Loop Stream Detector) unit. LSD typically does well sustaining Uop supply. However; in some rare cases; optimal uop-delivery could not be reached for small loops whose size (in terms of number of uops) does not suit well the LSD structure.", "ScaleUnit": "100%" }, { @@ -1457,15 +1456,15 @@ "MetricName": "tma_machine_clears", "MetricThreshold": "tma_machine_clears > 0.1 & tma_bad_speculation > 0.15", "MetricgroupNoGroup": "TopdownL2", - "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears. These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT. Related metrics: tma_bottleneck_memory_synchronization, tma_clears_resteers, tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_l1_bound, tma_microcode_sequencer, tma_ms_switches", + "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears. These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT. Related metrics: tma_bottleneck_memory_synchronization, tma_clears_resteers, tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_l1_bound, tma_microcode_sequencer, tma_ms_switches, tma_remote_cache", "ScaleUnit": "100%" }, { "BriefDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory - DRAM ([SPR-HBM] and/or HBM)", - "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, cpu@OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD\\,cmask\\=0x4@) / tma_info_thread_clks", + "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, cpu@OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD\\,cmask\\=4@) / tma_info_thread_clks", "MetricGroup": "BvMB;MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueBW", "MetricName": "tma_mem_bandwidth", - "MetricThreshold": "tma_mem_bandwidth > 0.2 & tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_mem_bandwidth > 0.2 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", "PublicDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory - DRAM ([SPR-HBM] and/or HBM). The underlying heuristic assumes that a similar off-core traffic is generated by all IA cores. This metric does not aggregate non-data-read requests by this logical processor; requests from other IA Logical Processors/Physical Cores/sockets; or other non-IA devices like GPU; hence the maximum external memory bandwidth limits may or may not be approached when this metric is flagged (see Uncore counters for that). Related metrics: tma_bottleneck_cache_memory_bandwidth, tma_fb_full, tma_info_system_dram_bw_use, tma_sq_full", "ScaleUnit": "100%" }, @@ -1474,7 +1473,7 @@ "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD) / tma_info_thread_clks - tma_mem_bandwidth", "MetricGroup": "BvML;MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueLat", "MetricName": "tma_mem_latency", - "MetricThreshold": "tma_mem_latency > 0.1 & tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_mem_latency > 0.1 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", "PublicDescription": "This metric estimates fraction of cycles where the performance was likely hurt due to latency from external memory - DRAM ([SPR-HBM] and/or HBM). This metric does not aggregate requests from other Logical Processors/Physical Cores/sockets (see Uncore counters for that). Related metrics: tma_bottleneck_cache_memory_latency, tma_l3_hit_latency", "ScaleUnit": "100%" }, @@ -1485,11 +1484,11 @@ "MetricName": "tma_memory_bound", "MetricThreshold": "tma_memory_bound > 0.2 & tma_backend_bound > 0.2", "MetricgroupNoGroup": "TopdownL2", - "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck. Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two)", + "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck. Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two).", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of slots where the CPU was retiring memory operations , uops for memory load or store accesses", + "BriefDescription": "This metric represents fraction of slots where the CPU was retiring memory operations -- uops for memory load or store accesses.", "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "tma_light_operations * MEM_INST_RETIRED.ANY / INST_RETIRED.ANY", "MetricGroup": "Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group", @@ -1511,7 +1510,7 @@ "MetricExpr": "BR_MISP_RETIRED.ALL_BRANCHES / (BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT) * INT_MISC.CLEAR_RESTEER_CYCLES / tma_info_thread_clks", "MetricGroup": "BadSpec;BrMispredicts;BvMP;TopdownL4;tma_L4_group;tma_branch_resteers_group;tma_issueBM", "MetricName": "tma_mispredicts_resteers", - "MetricThreshold": "tma_mispredicts_resteers > 0.05 & tma_branch_resteers > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricThreshold": "tma_mispredicts_resteers > 0.05 & (tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))", "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Branch Misprediction at execution stage. Sample with: INT_MISC.CLEAR_RESTEER_CYCLES. Related metrics: tma_bottleneck_mispredictions, tma_branch_mispredicts, tma_info_bad_spec_branch_misprediction_cost", "ScaleUnit": "100%" }, @@ -1526,24 +1525,24 @@ }, { "BriefDescription": "This metric represents fraction of cycles where (only) 4 uops were delivered by the MITE pipeline", - "MetricExpr": "(cpu@IDQ.MITE_UOPS\\,cmask\\=0x4@ - cpu@IDQ.MITE_UOPS\\,cmask\\=0x5@) / tma_info_thread_clks", + "MetricExpr": "(cpu@IDQ.MITE_UOPS\\,cmask\\=4@ - cpu@IDQ.MITE_UOPS\\,cmask\\=5@) / tma_info_thread_clks", "MetricGroup": "DSBmiss;FetchBW;TopdownL4;tma_L4_group;tma_mite_group", "MetricName": "tma_mite_4wide", - "MetricThreshold": "tma_mite_4wide > 0.05 & tma_mite > 0.1 & tma_fetch_bandwidth > 0.2", + "MetricThreshold": "tma_mite_4wide > 0.05 & (tma_mite > 0.1 & tma_fetch_bandwidth > 0.2)", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates penalty in terms of percentage of([SKL+] injected blend uops out of all Uops Issued , the Count Domain; [ADL+] cycles)", + "BriefDescription": "This metric estimates penalty in terms of percentage of([SKL+] injected blend uops out of all Uops Issued -- the Count Domain; [ADL+] cycles)", "MetricExpr": "UOPS_ISSUED.VECTOR_WIDTH_MISMATCH / UOPS_ISSUED.ANY", "MetricGroup": "TopdownL5;tma_L5_group;tma_issueMV;tma_ports_utilized_0_group", "MetricName": "tma_mixing_vectors", "MetricThreshold": "tma_mixing_vectors > 0.05", - "PublicDescription": "This metric estimates penalty in terms of percentage of([SKL+] injected blend uops out of all Uops Issued , the Count Domain; [ADL+] cycles). Usually a Mixing_Vectors over 5% is worth investigating. Read more in Appendix B1 of the Optimizations Guide for this topic. Related metrics: tma_ms_switches", + "PublicDescription": "This metric estimates penalty in terms of percentage of([SKL+] injected blend uops out of all Uops Issued -- the Count Domain; [ADL+] cycles). Usually a Mixing_Vectors over 5% is worth investigating. Read more in Appendix B1 of the Optimizations Guide for this topic. Related metrics: tma_ms_switches", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to the Microcode Sequencer (MS) unit - see Microcode_Sequencer node for details", - "MetricExpr": "cpu@IDQ.MS_UOPS\\,cmask\\=0x1@ / tma_info_core_core_clks / 2", + "BriefDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to the Microcode Sequencer (MS) unit - see Microcode_Sequencer node for details.", + "MetricExpr": "cpu@IDQ.MS_UOPS\\,cmask\\=1@ / tma_info_core_core_clks / 2", "MetricGroup": "MicroSeq;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group", "MetricName": "tma_ms", "MetricThreshold": "tma_ms > 0.05 & tma_fetch_bandwidth > 0.2", @@ -1554,7 +1553,7 @@ "MetricExpr": "3 * IDQ.MS_SWITCHES / tma_info_thread_clks", "MetricGroup": "FetchLat;MicroSeq;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueMC;tma_issueMS;tma_issueMV;tma_issueSO", "MetricName": "tma_ms_switches", - "MetricThreshold": "tma_ms_switches > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricThreshold": "tma_ms_switches > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", "PublicDescription": "This metric estimates the fraction of cycles when the CPU was stalled due to switches of uop delivery to the Microcode Sequencer (MS). Commonly used instructions are optimized for delivery by the DSB (decoded i-cache) or MITE (legacy instruction decode) pipelines. Certain operations cannot be handled natively by the execution pipeline; and must be performed by microcode (small programs injected into the execution stream). Switching to the MS too often can negatively impact performance. The MS is designated to deliver long uop flows required by CISC instructions like CPUID; or uncommon conditions like Floating Point Assists when dealing with Denormals. Sample with: IDQ.MS_SWITCHES. Related metrics: tma_bottleneck_irregular_overhead, tma_clears_resteers, tma_l1_bound, tma_machine_clears, tma_microcode_sequencer, tma_mixing_vectors, tma_serializing_operation", "ScaleUnit": "100%" }, @@ -1563,7 +1562,7 @@ "MetricExpr": "tma_light_operations * INST_RETIRED.NOP / (tma_retiring * tma_info_thread_slots)", "MetricGroup": "BvBO;Pipeline;TopdownL4;tma_L4_group;tma_other_light_ops_group", "MetricName": "tma_nop_instructions", - "MetricThreshold": "tma_nop_instructions > 0.1 & tma_other_light_ops > 0.3 & tma_light_operations > 0.6", + "MetricThreshold": "tma_nop_instructions > 0.1 & (tma_other_light_ops > 0.3 & tma_light_operations > 0.6)", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring NOP (no op) instructions. Compilers often use NOPs for certain address alignments - e.g. start address of a function or loop body. Sample with: INST_RETIRED.NOP", "ScaleUnit": "100%" }, @@ -1578,19 +1577,19 @@ "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates fraction of slots the CPU was stalled due to other cases of misprediction (non-retired x86 branches or other types)", + "BriefDescription": "This metric estimates fraction of slots the CPU was stalled due to other cases of misprediction (non-retired x86 branches or other types).", "MetricExpr": "max(tma_branch_mispredicts * (1 - BR_MISP_RETIRED.ALL_BRANCHES / (INT_MISC.CLEARS_COUNT - MACHINE_CLEARS.COUNT)), 0.0001)", "MetricGroup": "BrMispredicts;BvIO;TopdownL3;tma_L3_group;tma_branch_mispredicts_group", "MetricName": "tma_other_mispredicts", - "MetricThreshold": "tma_other_mispredicts > 0.05 & tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", + "MetricThreshold": "tma_other_mispredicts > 0.05 & (tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15)", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of slots the CPU has wasted due to Nukes (Machine Clears) not related to memory ordering", + "BriefDescription": "This metric represents fraction of slots the CPU has wasted due to Nukes (Machine Clears) not related to memory ordering.", "MetricExpr": "max(tma_machine_clears * (1 - MACHINE_CLEARS.MEMORY_ORDERING / MACHINE_CLEARS.COUNT), 0.0001)", "MetricGroup": "BvIO;Machine_Clears;TopdownL3;tma_L3_group;tma_machine_clears_group", "MetricName": "tma_other_nukes", - "MetricThreshold": "tma_other_nukes > 0.05 & tma_machine_clears > 0.1 & tma_bad_speculation > 0.15", + "MetricThreshold": "tma_other_nukes > 0.05 & (tma_machine_clears > 0.1 & tma_bad_speculation > 0.15)", "ScaleUnit": "100%" }, { @@ -1634,8 +1633,8 @@ "MetricExpr": "((tma_ports_utilized_0 * tma_info_thread_clks + (EXE_ACTIVITY.1_PORTS_UTIL + tma_retiring * EXE_ACTIVITY.2_PORTS_UTIL)) / tma_info_thread_clks if ARITH.DIVIDER_ACTIVE < CYCLE_ACTIVITY.STALLS_TOTAL - CYCLE_ACTIVITY.STALLS_MEM_ANY else (EXE_ACTIVITY.1_PORTS_UTIL + tma_retiring * EXE_ACTIVITY.2_PORTS_UTIL) / tma_info_thread_clks)", "MetricGroup": "PortsUtil;TopdownL3;tma_L3_group;tma_core_bound_group", "MetricName": "tma_ports_utilization", - "MetricThreshold": "tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", - "PublicDescription": "This metric estimates fraction of cycles the CPU performance was potentially limited due to Core computation issues (non divider-related). Two distinct categories can be attributed into this metric: (1) heavy data-dependency among contiguous instructions would manifest in this metric - such cases are often referred to as low Instruction Level Parallelism (ILP). (2) Contention on some hardware execution unit other than Divider. For example; when there are too many multiply operations", + "MetricThreshold": "tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)", + "PublicDescription": "This metric estimates fraction of cycles the CPU performance was potentially limited due to Core computation issues (non divider-related). Two distinct categories can be attributed into this metric: (1) heavy data-dependency among contiguous instructions would manifest in this metric - such cases are often referred to as low Instruction Level Parallelism (ILP). (2) Contention on some hardware execution unit other than Divider. For example; when there are too many multiply operations.", "ScaleUnit": "100%" }, { @@ -1643,8 +1642,8 @@ "MetricExpr": "cpu@EXE_ACTIVITY.3_PORTS_UTIL\\,umask\\=0x80@ / tma_info_thread_clks", "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group", "MetricName": "tma_ports_utilized_0", - "MetricThreshold": "tma_ports_utilized_0 > 0.2 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", - "PublicDescription": "This metric represents fraction of cycles CPU executed no uops on any execution port (Logical Processor cycles since ICL, Physical Core cycles otherwise). Long-latency instructions like divides may contribute to this metric", + "MetricThreshold": "tma_ports_utilized_0 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric represents fraction of cycles CPU executed no uops on any execution port (Logical Processor cycles since ICL, Physical Core cycles otherwise). Long-latency instructions like divides may contribute to this metric.", "ScaleUnit": "100%" }, { @@ -1652,7 +1651,7 @@ "MetricExpr": "EXE_ACTIVITY.1_PORTS_UTIL / tma_info_thread_clks", "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_issueL1;tma_ports_utilization_group", "MetricName": "tma_ports_utilized_1", - "MetricThreshold": "tma_ports_utilized_1 > 0.2 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_ports_utilized_1 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", "PublicDescription": "This metric represents fraction of cycles where the CPU executed total of 1 uop per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise). This can be due to heavy data-dependency among software instructions; or over oversubscribing a particular hardware resource. In some other cases with high 1_Port_Utilized and L1_Bound; this metric can point to L1 data-cache latency bottleneck that may not necessarily manifest with complete execution starvation (due to the short L1 latency e.g. walking a linked list) - looking at the assembly can be helpful. Sample with: EXE_ACTIVITY.1_PORTS_UTIL. Related metrics: tma_l1_bound", "ScaleUnit": "100%" }, @@ -1661,7 +1660,7 @@ "MetricExpr": "EXE_ACTIVITY.2_PORTS_UTIL / tma_info_thread_clks", "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_issue2P;tma_ports_utilization_group", "MetricName": "tma_ports_utilized_2", - "MetricThreshold": "tma_ports_utilized_2 > 0.15 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_ports_utilized_2 > 0.15 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", "PublicDescription": "This metric represents fraction of cycles CPU executed total of 2 uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise). Loop Vectorization -most compilers feature auto-Vectorization options today- reduces pressure on the execution ports as multiple elements are calculated with same uop. Sample with: EXE_ACTIVITY.2_PORTS_UTIL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6", "ScaleUnit": "100%" }, @@ -1670,14 +1669,14 @@ "MetricExpr": "UOPS_EXECUTED.CYCLES_GE_3 / tma_info_thread_clks", "MetricGroup": "BvCB;PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group", "MetricName": "tma_ports_utilized_3m", - "MetricThreshold": "tma_ports_utilized_3m > 0.4 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_ports_utilized_3m > 0.4 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", "PublicDescription": "This metric represents fraction of cycles CPU executed total of 3 or more uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise). Sample with: UOPS_EXECUTED.CYCLES_GE_3", "ScaleUnit": "100%" }, { "BriefDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired", "DefaultMetricgroupName": "TopdownL1", - "MetricExpr": "topdown\\-retiring / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * slots", + "MetricExpr": "topdown\\-retiring / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * tma_info_thread_slots", "MetricGroup": "BvUW;Default;TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_retiring", "MetricThreshold": "tma_retiring > 0.7 | tma_heavy_operations > 0.1", @@ -1690,7 +1689,7 @@ "MetricExpr": "RESOURCE_STALLS.SCOREBOARD / tma_info_thread_clks", "MetricGroup": "BvIO;PortsUtil;TopdownL3;tma_L3_group;tma_core_bound_group;tma_issueSO", "MetricName": "tma_serializing_operation", - "MetricThreshold": "tma_serializing_operation > 0.1 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_serializing_operation > 0.1 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)", "PublicDescription": "This metric represents fraction of cycles the CPU issue-pipeline was stalled due to serializing operations. Instructions like CPUID; WRMSR or LFENCE serialize the out-of-order execution which may limit performance. Sample with: RESOURCE_STALLS.SCOREBOARD. Related metrics: tma_ms_switches", "ScaleUnit": "100%" }, @@ -1699,7 +1698,7 @@ "MetricExpr": "140 * MISC_RETIRED.PAUSE_INST / tma_info_thread_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_serializing_operation_group", "MetricName": "tma_slow_pause", - "MetricThreshold": "tma_slow_pause > 0.05 & tma_serializing_operation > 0.1 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_slow_pause > 0.05 & (tma_serializing_operation > 0.1 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to PAUSE Instructions. Sample with: MISC_RETIRED.PAUSE_INST", "ScaleUnit": "100%" }, @@ -1709,7 +1708,7 @@ "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group", "MetricName": "tma_split_loads", "MetricThreshold": "tma_split_loads > 0.3", - "PublicDescription": "This metric estimates fraction of cycles handling memory load split accesses - load that cross 64-byte cache line boundary. Sample with: MEM_INST_RETIRED.SPLIT_LOADS", + "PublicDescription": "This metric estimates fraction of cycles handling memory load split accesses - load that cross 64-byte cache line boundary. Sample with: MEM_INST_RETIRED.SPLIT_LOADS_PS", "ScaleUnit": "100%" }, { @@ -1718,8 +1717,8 @@ "MetricExpr": "MEM_INST_RETIRED.SPLIT_STORES / tma_info_core_core_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_issueSpSt;tma_store_bound_group", "MetricName": "tma_split_stores", - "MetricThreshold": "tma_split_stores > 0.2 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", - "PublicDescription": "This metric represents rate of split store accesses. Consider aligning your data to the 64-byte cache line granularity. Sample with: MEM_INST_RETIRED.SPLIT_STORES", + "MetricThreshold": "tma_split_stores > 0.2 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric represents rate of split store accesses. Consider aligning your data to the 64-byte cache line granularity. Sample with: MEM_INST_RETIRED.SPLIT_STORES_PS. Related metrics: tma_port_4", "ScaleUnit": "100%" }, { @@ -1727,7 +1726,7 @@ "MetricExpr": "L1D_PEND_MISS.L2_STALL / tma_info_thread_clks", "MetricGroup": "BvMB;MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_issueBW;tma_l3_bound_group", "MetricName": "tma_sq_full", - "MetricThreshold": "tma_sq_full > 0.3 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_sq_full > 0.3 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", "PublicDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors). Related metrics: tma_bottleneck_cache_memory_bandwidth, tma_fb_full, tma_info_system_dram_bw_use, tma_mem_bandwidth", "ScaleUnit": "100%" }, @@ -1736,8 +1735,8 @@ "MetricExpr": "EXE_ACTIVITY.BOUND_ON_STORES / tma_info_thread_clks", "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_store_bound", - "MetricThreshold": "tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", - "PublicDescription": "This metric estimates how often CPU was stalled due to RFO store memory accesses; RFO store issue a read-for-ownership request before the write. Even though store accesses do not typically stall out-of-order CPUs; there are few cases where stores can lead to actual stalls. This metric will be flagged should RFO stores be a bottleneck. Sample with: MEM_INST_RETIRED.ALL_STORES", + "MetricThreshold": "tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", + "PublicDescription": "This metric estimates how often CPU was stalled due to RFO store memory accesses; RFO store issue a read-for-ownership request before the write. Even though store accesses do not typically stall out-of-order CPUs; there are few cases where stores can lead to actual stalls. This metric will be flagged should RFO stores be a bottleneck. Sample with: MEM_INST_RETIRED.ALL_STORES_PS", "ScaleUnit": "100%" }, { @@ -1746,8 +1745,8 @@ "MetricExpr": "13 * LD_BLOCKS.STORE_FORWARD / tma_info_thread_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group", "MetricName": "tma_store_fwd_blk", - "MetricThreshold": "tma_store_fwd_blk > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", - "PublicDescription": "This metric roughly estimates fraction of cycles when the memory subsystem had loads blocked since they could not forward data from earlier (in program order) overlapping stores. To streamline memory operations in the pipeline; a load can avoid waiting for memory if a prior in-flight store is writing the data that the load wants to read (store forwarding process). However; in some cases the load may be blocked for a significant time pending the store forward. For example; when the prior store is writing a smaller region than the load is reading", + "MetricThreshold": "tma_store_fwd_blk > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric roughly estimates fraction of cycles when the memory subsystem had loads blocked since they could not forward data from earlier (in program order) overlapping stores. To streamline memory operations in the pipeline; a load can avoid waiting for memory if a prior in-flight store is writing the data that the load wants to read (store forwarding process). However; in some cases the load may be blocked for a significant time pending the store forward. For example; when the prior store is writing a smaller region than the load is reading.", "ScaleUnit": "100%" }, { @@ -1755,8 +1754,8 @@ "MetricExpr": "(L2_RQSTS.RFO_HIT * 10 * (1 - MEM_INST_RETIRED.LOCK_LOADS / MEM_INST_RETIRED.ALL_STORES) + (1 - MEM_INST_RETIRED.LOCK_LOADS / MEM_INST_RETIRED.ALL_STORES) * min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO)) / tma_info_thread_clks", "MetricGroup": "BvML;LockCont;MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_issueSL;tma_store_bound_group", "MetricName": "tma_store_latency", - "MetricThreshold": "tma_store_latency > 0.1 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", - "PublicDescription": "This metric estimates fraction of cycles the CPU spent handling L1D store misses. Store accesses usually less impact out-of-order core performance; however; holding resources for longer time can lead into undesired implications (e.g. contention on L1D fill-buffer entries - see FB_Full). Related metrics: tma_branch_resteers, tma_fb_full, tma_l3_hit_latency, tma_lock_latency", + "MetricThreshold": "tma_store_latency > 0.1 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric estimates fraction of cycles the CPU spent handling L1D store misses. Store accesses usually less impact out-of-order core performance; however; holding resources for longer time can lead into undesired implications (e.g. contention on L1D fill-buffer entries - see FB_Full). Related metrics: tma_fb_full, tma_lock_latency", "ScaleUnit": "100%" }, { @@ -1773,7 +1772,7 @@ "MetricExpr": "tma_dtlb_store - tma_store_stlb_miss", "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_store_group", "MetricName": "tma_store_stlb_hit", - "MetricThreshold": "tma_store_stlb_hit > 0.05 & tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_store_stlb_hit > 0.05 & (tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))", "ScaleUnit": "100%" }, { @@ -1781,31 +1780,31 @@ "MetricExpr": "DTLB_STORE_MISSES.WALK_ACTIVE / tma_info_core_core_clks", "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_store_group", "MetricName": "tma_store_stlb_miss", - "MetricThreshold": "tma_store_stlb_miss > 0.05 & tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_store_stlb_miss > 0.05 & (tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 1 GB pages for data store accesses", + "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 1 GB pages for data store accesses.", "MetricExpr": "tma_store_stlb_miss * DTLB_STORE_MISSES.WALK_COMPLETED_1G / (DTLB_STORE_MISSES.WALK_COMPLETED_4K + DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M + DTLB_STORE_MISSES.WALK_COMPLETED_1G)", "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_store_stlb_miss_group", "MetricName": "tma_store_stlb_miss_1g", - "MetricThreshold": "tma_store_stlb_miss_1g > 0.05 & tma_store_stlb_miss > 0.05 & tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_store_stlb_miss_1g > 0.05 & (tma_store_stlb_miss > 0.05 & (tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))))", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 2 or 4 MB pages for data store accesses", + "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 2 or 4 MB pages for data store accesses.", "MetricExpr": "tma_store_stlb_miss * DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M / (DTLB_STORE_MISSES.WALK_COMPLETED_4K + DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M + DTLB_STORE_MISSES.WALK_COMPLETED_1G)", "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_store_stlb_miss_group", "MetricName": "tma_store_stlb_miss_2m", - "MetricThreshold": "tma_store_stlb_miss_2m > 0.05 & tma_store_stlb_miss > 0.05 & tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_store_stlb_miss_2m > 0.05 & (tma_store_stlb_miss > 0.05 & (tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))))", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 4 KB pages for data store accesses", + "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 4 KB pages for data store accesses.", "MetricExpr": "tma_store_stlb_miss * DTLB_STORE_MISSES.WALK_COMPLETED_4K / (DTLB_STORE_MISSES.WALK_COMPLETED_4K + DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M + DTLB_STORE_MISSES.WALK_COMPLETED_1G)", "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_store_stlb_miss_group", "MetricName": "tma_store_stlb_miss_4k", - "MetricThreshold": "tma_store_stlb_miss_4k > 0.05 & tma_store_stlb_miss > 0.05 & tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_store_stlb_miss_4k > 0.05 & (tma_store_stlb_miss > 0.05 & (tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))))", "ScaleUnit": "100%" }, { @@ -1813,7 +1812,7 @@ "MetricExpr": "9 * OCR.STREAMING_WR.ANY_RESPONSE / tma_info_thread_clks", "MetricGroup": "MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_issueSmSt;tma_store_bound_group", "MetricName": "tma_streaming_stores", - "MetricThreshold": "tma_streaming_stores > 0.2 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_streaming_stores > 0.2 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", "PublicDescription": "This metric estimates how often CPU was stalled due to Streaming store memory accesses; Streaming store optimize out a read request required by RFO stores. Even though store accesses do not typically stall out-of-order CPUs; there are few cases where stores can lead to actual stalls. This metric will be flagged should Streaming stores be a bottleneck. Sample with: OCR.STREAMING_WR.ANY_RESPONSE. Related metrics: tma_fb_full", "ScaleUnit": "100%" }, @@ -1822,7 +1821,7 @@ "MetricExpr": "10 * BACLEARS.ANY / tma_info_thread_clks", "MetricGroup": "BigFootprint;BvBC;FetchLat;TopdownL4;tma_L4_group;tma_branch_resteers_group", "MetricName": "tma_unknown_branches", - "MetricThreshold": "tma_unknown_branches > 0.05 & tma_branch_resteers > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricThreshold": "tma_unknown_branches > 0.05 & (tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))", "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to new branch address clears. These are fetched branches the Branch Prediction Unit was unable to recognize (e.g. first time the branch is fetched or hitting BTB capacity limit) hence called Unknown Branches. Sample with: BACLEARS.ANY", "ScaleUnit": "100%" }, @@ -1831,8 +1830,8 @@ "MetricExpr": "tma_retiring * UOPS_EXECUTED.X87 / UOPS_EXECUTED.THREAD", "MetricGroup": "Compute;TopdownL4;tma_L4_group;tma_fp_arith_group", "MetricName": "tma_x87_use", - "MetricThreshold": "tma_x87_use > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6", - "PublicDescription": "This metric serves as an approximation of legacy x87 usage. It accounts for instructions beyond X87 FP arithmetic operations; hence may be used as a thermometer to avoid X87 high usage and preferably upgrade to modern ISA. See Tip under Tuning Hint", + "MetricThreshold": "tma_x87_use > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6)", + "PublicDescription": "This metric serves as an approximation of legacy x87 usage. It accounts for instructions beyond X87 FP arithmetic operations; hence may be used as a thermometer to avoid X87 high usage and preferably upgrade to modern ISA. See Tip under Tuning Hint.", "ScaleUnit": "100%" }, { diff --git a/tools/perf/pmu-events/arch/x86/sandybridge/frontend.json b/tools/perf/pmu-events/arch/x86/sandybridge/frontend.json index e95d1005e22f..5c9ab7680762 100644 --- a/tools/perf/pmu-events/arch/x86/sandybridge/frontend.json +++ b/tools/perf/pmu-events/arch/x86/sandybridge/frontend.json @@ -278,5 +278,13 @@ "EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_LE_3_UOP_DELIV.CORE", "SampleAfterValue": "2000003", "UMask": "0x1" + }, + { + "BriefDescription": "Valid instructions written to IQ per cycle.", + "Counter": "0,1,2,3", + "EventCode": "0x17", + "EventName": "INSTS_WRITTEN_TO_IQ.INSTS", + "SampleAfterValue": "2000003", + "UMask": "0x1" } ] diff --git a/tools/perf/pmu-events/arch/x86/sandybridge/metricgroups.json b/tools/perf/pmu-events/arch/x86/sandybridge/metricgroups.json index 7dc7eb0d3dd3..eb8fbd14138a 100644 --- a/tools/perf/pmu-events/arch/x86/sandybridge/metricgroups.json +++ b/tools/perf/pmu-events/arch/x86/sandybridge/metricgroups.json @@ -9,6 +9,7 @@ "BvCB": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", "BvFB": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", "BvIO": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "BvMB": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", "BvML": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", "BvMP": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", "BvMS": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", @@ -33,6 +34,7 @@ "InsType": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", "L2Evicts": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", "LSD": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "LockCont": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", "MachineClears": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", "Machine_Clears": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", "Mem": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", @@ -48,6 +50,7 @@ "Pipeline": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", "PortsUtil": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", "Power": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Prefetches": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", "Ret": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", "Retire": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", "SMT": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", @@ -75,6 +78,7 @@ "tma_bad_speculation_group": "Metrics contributing to tma_bad_speculation category", "tma_branch_resteers_group": "Metrics contributing to tma_branch_resteers category", "tma_core_bound_group": "Metrics contributing to tma_core_bound category", + "tma_divider_group": "Metrics contributing to tma_divider category", "tma_dram_bound_group": "Metrics contributing to tma_dram_bound category", "tma_dtlb_load_group": "Metrics contributing to tma_dtlb_load category", "tma_dtlb_store_group": "Metrics contributing to tma_dtlb_store category", @@ -99,6 +103,7 @@ "tma_issueSmSt": "Metrics related by the issue $issueSmSt", "tma_issueSyncxn": "Metrics related by the issue $issueSyncxn", "tma_issueTLB": "Metrics related by the issue $issueTLB", + "tma_itlb_misses_group": "Metrics contributing to tma_itlb_misses category", "tma_l1_bound_group": "Metrics contributing to tma_l1_bound category", "tma_light_operations_group": "Metrics contributing to tma_light_operations category", "tma_machine_clears_group": "Metrics contributing to tma_machine_clears category", diff --git a/tools/perf/pmu-events/arch/x86/sandybridge/other.json b/tools/perf/pmu-events/arch/x86/sandybridge/other.json index 42692fa24b6c..970839a9c786 100644 --- a/tools/perf/pmu-events/arch/x86/sandybridge/other.json +++ b/tools/perf/pmu-events/arch/x86/sandybridge/other.json @@ -34,14 +34,6 @@ "UMask": "0x2" }, { - "BriefDescription": "Valid instructions written to IQ per cycle.", - "Counter": "0,1,2,3", - "EventCode": "0x17", - "EventName": "INSTS_WRITTEN_TO_IQ.INSTS", - "SampleAfterValue": "2000003", - "UMask": "0x1" - }, - { "BriefDescription": "Cycles when L1 and L2 are locked due to UC or split lock.", "Counter": "0,1,2,3", "EventCode": "0x63", diff --git a/tools/perf/pmu-events/arch/x86/sandybridge/snb-metrics.json b/tools/perf/pmu-events/arch/x86/sandybridge/snb-metrics.json index ff2e515c744a..823d8b7c4224 100644 --- a/tools/perf/pmu-events/arch/x86/sandybridge/snb-metrics.json +++ b/tools/perf/pmu-events/arch/x86/sandybridge/snb-metrics.json @@ -127,7 +127,7 @@ "MetricGroup": "BvCB;TopdownL3;tma_L3_group;tma_core_bound_group", "MetricName": "tma_divider", "MetricThreshold": "tma_divider > 0.2 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)", - "PublicDescription": "This metric represents fraction of cycles where the Divider unit was active. Divide and square root instructions are performed by the Divider unit and can take considerably longer latency than integer or Floating Point addition; subtraction; or multiplication. Sample with: ARITH.DIVIDER_UOPS", + "PublicDescription": "This metric represents fraction of cycles where the Divider unit was active. Divide and square root instructions are performed by the Divider unit and can take considerably longer latency than integer or Floating Point addition; subtraction; or multiplication. Sample with: ARITH.DIVIDER_ACTIVE", "ScaleUnit": "100%" }, { @@ -211,7 +211,7 @@ "MetricGroup": "Compute;Flops;TopdownL5;tma_L5_group;tma_fp_vector_group;tma_issue2P", "MetricName": "tma_fp_vector_128b", "MetricThreshold": "tma_fp_vector_128b > 0.1 & (tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6))", - "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 128-bit wide vectors. May overcount due to FMA double counting. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_6, tma_ports_utilized_2", + "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 128-bit wide vectors. May overcount due to FMA double counting prior to LNL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%" }, { @@ -220,7 +220,7 @@ "MetricGroup": "Compute;Flops;TopdownL5;tma_L5_group;tma_fp_vector_group;tma_issue2P", "MetricName": "tma_fp_vector_256b", "MetricThreshold": "tma_fp_vector_256b > 0.1 & (tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6))", - "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 256-bit wide vectors. May overcount due to FMA double counting. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_512b, tma_port_6, tma_ports_utilized_2", + "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 256-bit wide vectors. May overcount due to FMA double counting prior to LNL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_512b, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%" }, { @@ -240,7 +240,7 @@ "MetricName": "tma_heavy_operations", "MetricThreshold": "tma_heavy_operations > 0.1", "MetricgroupNoGroup": "TopdownL2", - "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences. ([ICL+] Note this may overcount due to approximation using indirect events; [ADL+] .)", + "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences.([ICL+] Note this may overcount due to approximation using indirect events; [ADL+])", "ScaleUnit": "100%" }, { @@ -276,6 +276,12 @@ "PublicDescription": "Fraction of Uops delivered by the DSB (aka Decoded ICache; or Uop Cache). Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_lcp" }, { + "BriefDescription": "Taken Branches retired Per Cycle", + "MetricExpr": "BR_INST_RETIRED.NEAR_TAKEN / tma_info_thread_clks", + "MetricGroup": "Branches;FetchBW", + "MetricName": "tma_info_frontend_tbpc" + }, + { "BriefDescription": "Total number of retired Instructions", "MetricExpr": "INST_RETIRED.ANY", "MetricGroup": "Summary;TmaL1;tma_L1_group", @@ -290,7 +296,7 @@ }, { "BriefDescription": "Measured Average Core Frequency for unhalted processors [GHz]", - "MetricExpr": "tma_info_system_turbo_utilization * TSC / 1e9 / duration_time", + "MetricExpr": "tma_info_system_turbo_utilization * TSC / 1e9 / tma_info_system_time", "MetricGroup": "Power;Summary", "MetricName": "tma_info_system_core_frequency" }, @@ -308,14 +314,14 @@ }, { "BriefDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]", - "MetricExpr": "64 * (UNC_ARB_TRK_REQUESTS.ALL + UNC_ARB_COH_TRK_REQUESTS.ALL) / 1e6 / duration_time / 1e3", + "MetricExpr": "64 * (UNC_ARB_TRK_REQUESTS.ALL + UNC_ARB_COH_TRK_REQUESTS.ALL) / 1e6 / tma_info_system_time / 1e3", "MetricGroup": "HPC;MemOffcore;MemoryBW;SoC;tma_issueBW", "MetricName": "tma_info_system_dram_bw_use", "PublicDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]. Related metrics: tma_mem_bandwidth" }, { "BriefDescription": "Giga Floating Point Operations Per Second", - "MetricExpr": "(FP_COMP_OPS_EXE.SSE_SCALAR_SINGLE + FP_COMP_OPS_EXE.SSE_SCALAR_DOUBLE + 2 * FP_COMP_OPS_EXE.SSE_PACKED_DOUBLE + 4 * (FP_COMP_OPS_EXE.SSE_PACKED_SINGLE + SIMD_FP_256.PACKED_DOUBLE) + 8 * SIMD_FP_256.PACKED_SINGLE) / 1e9 / duration_time", + "MetricExpr": "(FP_COMP_OPS_EXE.SSE_SCALAR_SINGLE + FP_COMP_OPS_EXE.SSE_SCALAR_DOUBLE + 2 * FP_COMP_OPS_EXE.SSE_PACKED_DOUBLE + 4 * (FP_COMP_OPS_EXE.SSE_PACKED_SINGLE + SIMD_FP_256.PACKED_DOUBLE) + 8 * SIMD_FP_256.PACKED_SINGLE) / 1e9 / tma_info_system_time", "MetricGroup": "Cor;Flops;HPC", "MetricName": "tma_info_system_gflops", "PublicDescription": "Giga Floating Point Operations Per Second. Aggregate across all supported options of: FP precisions, scalar and vector instructions, vector-width" @@ -341,6 +347,13 @@ "MetricThreshold": "tma_info_system_kernel_utilization > 0.05" }, { + "BriefDescription": "PerfMon Event Multiplexing accuracy indicator", + "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P / CPU_CLK_UNHALTED.THREAD", + "MetricGroup": "Summary", + "MetricName": "tma_info_system_mux", + "MetricThreshold": "tma_info_system_mux > 1.1 | tma_info_system_mux < 0.9" + }, + { "BriefDescription": "Fraction of cycles where both hardware Logical Processors were active", "MetricExpr": "(1 - CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / (CPU_CLK_UNHALTED.REF_XCLK_ANY / 2) if #SMT_on else 0)", "MetricGroup": "SMT", @@ -353,6 +366,13 @@ "MetricName": "tma_info_system_socket_clks" }, { + "BriefDescription": "Run duration time in seconds", + "MetricExpr": "duration_time", + "MetricGroup": "Summary", + "MetricName": "tma_info_system_time", + "MetricThreshold": "tma_info_system_time < 1" + }, + { "BriefDescription": "Average Frequency Utilization relative nominal frequency", "MetricExpr": "tma_info_thread_clks / CPU_CLK_UNHALTED.REF_TSC", "MetricGroup": "Power", @@ -448,7 +468,7 @@ { "BriefDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory - DRAM ([SPR-HBM] and/or HBM)", "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, cpu@OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD\\,cmask\\=6@) / tma_info_thread_clks", - "MetricGroup": "BvMS;MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueBW", + "MetricGroup": "BvMB;MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueBW", "MetricName": "tma_mem_bandwidth", "MetricThreshold": "tma_mem_bandwidth > 0.2 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", "PublicDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory - DRAM ([SPR-HBM] and/or HBM). The underlying heuristic assumes that a similar off-core traffic is generated by all IA cores. This metric does not aggregate non-data-read requests by this logical processor; requests from other IA Logical Processors/Physical Cores/sockets; or other non-IA devices like GPU; hence the maximum external memory bandwidth limits may or may not be approached when this metric is flagged (see Uncore counters for that). Related metrics: tma_info_system_dram_bw_use", diff --git a/tools/perf/pmu-events/arch/x86/sapphirerapids/cache.json b/tools/perf/pmu-events/arch/x86/sapphirerapids/cache.json index e35dbb7c2ccd..21db53f9e9d6 100644 --- a/tools/perf/pmu-events/arch/x86/sapphirerapids/cache.json +++ b/tools/perf/pmu-events/arch/x86/sapphirerapids/cache.json @@ -4,6 +4,7 @@ "Counter": "0,1,2,3", "EventCode": "0x51", "EventName": "L1D.HWPF_MISS", + "PublicDescription": "L1D.HWPF_MISS Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x20" }, @@ -12,7 +13,7 @@ "Counter": "0,1,2,3", "EventCode": "0x51", "EventName": "L1D.REPLACEMENT", - "PublicDescription": "Counts L1D data line replacements including opportunistic replacements, and replacements that require stall-for-replace or block-for-replace.", + "PublicDescription": "Counts L1D data line replacements including opportunistic replacements, and replacements that require stall-for-replace or block-for-replace. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -21,7 +22,7 @@ "Counter": "0,1,2,3", "EventCode": "0x48", "EventName": "L1D_PEND_MISS.FB_FULL", - "PublicDescription": "Counts number of cycles a demand request has waited due to L1D Fill Buffer (FB) unavailability. Demand requests include cacheable/uncacheable demand load, store, lock or SW prefetch accesses.", + "PublicDescription": "Counts number of cycles a demand request has waited due to L1D Fill Buffer (FB) unavailability. Demand requests include cacheable/uncacheable demand load, store, lock or SW prefetch accesses. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x2" }, @@ -32,7 +33,7 @@ "EdgeDetect": "1", "EventCode": "0x48", "EventName": "L1D_PEND_MISS.FB_FULL_PERIODS", - "PublicDescription": "Counts number of phases a demand request has waited due to L1D Fill Buffer (FB) unavailability. Demand requests include cacheable/uncacheable demand load, store, lock or SW prefetch accesses.", + "PublicDescription": "Counts number of phases a demand request has waited due to L1D Fill Buffer (FB) unavailability. Demand requests include cacheable/uncacheable demand load, store, lock or SW prefetch accesses. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x2" }, @@ -42,6 +43,7 @@ "Deprecated": "1", "EventCode": "0x48", "EventName": "L1D_PEND_MISS.L2_STALL", + "PublicDescription": "This event is deprecated. Refer to new event L1D_PEND_MISS.L2_STALLS Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x4" }, @@ -50,7 +52,7 @@ "Counter": "0,1,2,3", "EventCode": "0x48", "EventName": "L1D_PEND_MISS.L2_STALLS", - "PublicDescription": "Counts number of cycles a demand request has waited due to L1D due to lack of L2 resources. Demand requests include cacheable/uncacheable demand load, store, lock or SW prefetch accesses.", + "PublicDescription": "Counts number of cycles a demand request has waited due to L1D due to lack of L2 resources. Demand requests include cacheable/uncacheable demand load, store, lock or SW prefetch accesses. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x4" }, @@ -59,7 +61,7 @@ "Counter": "0,1,2,3", "EventCode": "0x48", "EventName": "L1D_PEND_MISS.PENDING", - "PublicDescription": "Counts number of L1D misses that are outstanding in each cycle, that is each cycle the number of Fill Buffers (FB) outstanding required by Demand Reads. FB either is held by demand loads, or it is held by non-demand loads and gets hit at least once by demand. The valid outstanding interval is defined until the FB deallocation by one of the following ways: from FB allocation, if FB is allocated by demand from the demand Hit FB, if it is allocated by hardware or software prefetch. Note: In the L1D, a Demand Read contains cacheable or noncacheable demand loads, including ones causing cache-line splits and reads due to page walks resulted from any request type.", + "PublicDescription": "Counts number of L1D misses that are outstanding in each cycle, that is each cycle the number of Fill Buffers (FB) outstanding required by Demand Reads. FB either is held by demand loads, or it is held by non-demand loads and gets hit at least once by demand. The valid outstanding interval is defined until the FB deallocation by one of the following ways: from FB allocation, if FB is allocated by demand from the demand Hit FB, if it is allocated by hardware or software prefetch. Note: In the L1D, a Demand Read contains cacheable or noncacheable demand loads, including ones causing cache-line splits and reads due to page walks resulted from any request type. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x1" }, @@ -69,7 +71,7 @@ "CounterMask": "1", "EventCode": "0x48", "EventName": "L1D_PEND_MISS.PENDING_CYCLES", - "PublicDescription": "Counts duration of L1D miss outstanding in cycles.", + "PublicDescription": "Counts duration of L1D miss outstanding in cycles. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x1" }, @@ -78,7 +80,7 @@ "Counter": "0,1,2,3", "EventCode": "0x25", "EventName": "L2_LINES_IN.ALL", - "PublicDescription": "Counts the number of L2 cache lines filling the L2. Counting does not cover rejects.", + "PublicDescription": "Counts the number of L2 cache lines filling the L2. Counting does not cover rejects. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1f" }, @@ -87,7 +89,7 @@ "Counter": "0,1,2,3", "EventCode": "0x26", "EventName": "L2_LINES_OUT.NON_SILENT", - "PublicDescription": "Counts the number of lines that are evicted by L2 cache when triggered by an L2 cache fill. Those lines are in Modified state. Modified lines are written back to L3", + "PublicDescription": "Counts the number of lines that are evicted by L2 cache when triggered by an L2 cache fill. Those lines are in Modified state. Modified lines are written back to L3 Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0x2" }, @@ -96,7 +98,7 @@ "Counter": "0,1,2,3", "EventCode": "0x26", "EventName": "L2_LINES_OUT.SILENT", - "PublicDescription": "Counts the number of lines that are silently dropped by L2 cache. These lines are typically in Shared or Exclusive state. A non-threaded event.", + "PublicDescription": "Counts the number of lines that are silently dropped by L2 cache. These lines are typically in Shared or Exclusive state. A non-threaded event. Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0x1" }, @@ -105,7 +107,7 @@ "Counter": "0,1,2,3", "EventCode": "0x26", "EventName": "L2_LINES_OUT.USELESS_HWPF", - "PublicDescription": "Counts the number of cache lines that have been prefetched by the L2 hardware prefetcher but not used by demand access when evicted from the L2 cache", + "PublicDescription": "Counts the number of cache lines that have been prefetched by the L2 hardware prefetcher but not used by demand access when evicted from the L2 cache Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0x4" }, @@ -114,7 +116,7 @@ "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_REQUEST.ALL", - "PublicDescription": "Counts all requests that were hit or true misses in L2 cache. True-miss excludes misses that were merged with ongoing L2 misses. [This event is alias to L2_RQSTS.REFERENCES]", + "PublicDescription": "Counts all requests that were hit or true misses in L2 cache. True-miss excludes misses that were merged with ongoing L2 misses. [This event is alias to L2_RQSTS.REFERENCES] Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0xff" }, @@ -123,7 +125,7 @@ "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_REQUEST.MISS", - "PublicDescription": "Counts read requests of any type with true-miss in the L2 cache. True-miss excludes L2 misses that were merged with ongoing L2 misses. [This event is alias to L2_RQSTS.MISS]", + "PublicDescription": "Counts read requests of any type with true-miss in the L2 cache. True-miss excludes L2 misses that were merged with ongoing L2 misses. [This event is alias to L2_RQSTS.MISS] Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0x3f" }, @@ -132,7 +134,7 @@ "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_RQSTS.ALL_CODE_RD", - "PublicDescription": "Counts the total number of L2 code requests.", + "PublicDescription": "Counts the total number of L2 code requests. Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0xe4" }, @@ -141,7 +143,7 @@ "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_RQSTS.ALL_DEMAND_DATA_RD", - "PublicDescription": "Counts Demand Data Read requests accessing the L2 cache. These requests may hit or miss L2 cache. True-miss exclude misses that were merged with ongoing L2 misses. An access is counted once.", + "PublicDescription": "Counts Demand Data Read requests accessing the L2 cache. These requests may hit or miss L2 cache. True-miss exclude misses that were merged with ongoing L2 misses. An access is counted once. Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0xe1" }, @@ -150,7 +152,7 @@ "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_RQSTS.ALL_DEMAND_MISS", - "PublicDescription": "Counts demand requests that miss L2 cache.", + "PublicDescription": "Counts demand requests that miss L2 cache. Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0x27" }, @@ -159,7 +161,7 @@ "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_RQSTS.ALL_DEMAND_REFERENCES", - "PublicDescription": "Counts demand requests to L2 cache.", + "PublicDescription": "Counts demand requests to L2 cache. Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0xe7" }, @@ -168,6 +170,7 @@ "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_RQSTS.ALL_HWPF", + "PublicDescription": "L2_RQSTS.ALL_HWPF Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0xf0" }, @@ -176,7 +179,7 @@ "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_RQSTS.ALL_RFO", - "PublicDescription": "Counts the total number of RFO (read for ownership) requests to L2 cache. L2 RFO requests include both L1D demand RFO misses as well as L1D RFO prefetches.", + "PublicDescription": "Counts the total number of RFO (read for ownership) requests to L2 cache. L2 RFO requests include both L1D demand RFO misses as well as L1D RFO prefetches. Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0xe2" }, @@ -185,7 +188,7 @@ "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_RQSTS.CODE_RD_HIT", - "PublicDescription": "Counts L2 cache hits when fetching instructions, code reads.", + "PublicDescription": "Counts L2 cache hits when fetching instructions, code reads. Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0xc4" }, @@ -194,7 +197,7 @@ "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_RQSTS.CODE_RD_MISS", - "PublicDescription": "Counts L2 cache misses when fetching instructions.", + "PublicDescription": "Counts L2 cache misses when fetching instructions. Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0x24" }, @@ -203,7 +206,7 @@ "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_RQSTS.DEMAND_DATA_RD_HIT", - "PublicDescription": "Counts the number of demand Data Read requests initiated by load instructions that hit L2 cache.", + "PublicDescription": "Counts the number of demand Data Read requests initiated by load instructions that hit L2 cache. Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0xc1" }, @@ -212,7 +215,7 @@ "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_RQSTS.DEMAND_DATA_RD_MISS", - "PublicDescription": "Counts demand Data Read requests with true-miss in the L2 cache. True-miss excludes misses that were merged with ongoing L2 misses. An access is counted once.", + "PublicDescription": "Counts demand Data Read requests with true-miss in the L2 cache. True-miss excludes misses that were merged with ongoing L2 misses. An access is counted once. Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0x21" }, @@ -221,6 +224,7 @@ "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_RQSTS.HWPF_MISS", + "PublicDescription": "L2_RQSTS.HWPF_MISS Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0x30" }, @@ -229,7 +233,7 @@ "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_RQSTS.MISS", - "PublicDescription": "Counts read requests of any type with true-miss in the L2 cache. True-miss excludes L2 misses that were merged with ongoing L2 misses. [This event is alias to L2_REQUEST.MISS]", + "PublicDescription": "Counts read requests of any type with true-miss in the L2 cache. True-miss excludes L2 misses that were merged with ongoing L2 misses. [This event is alias to L2_REQUEST.MISS] Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0x3f" }, @@ -238,7 +242,7 @@ "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_RQSTS.REFERENCES", - "PublicDescription": "Counts all requests that were hit or true misses in L2 cache. True-miss excludes misses that were merged with ongoing L2 misses. [This event is alias to L2_REQUEST.ALL]", + "PublicDescription": "Counts all requests that were hit or true misses in L2 cache. True-miss excludes misses that were merged with ongoing L2 misses. [This event is alias to L2_REQUEST.ALL] Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0xff" }, @@ -247,7 +251,7 @@ "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_RQSTS.RFO_HIT", - "PublicDescription": "Counts the RFO (Read-for-Ownership) requests that hit L2 cache.", + "PublicDescription": "Counts the RFO (Read-for-Ownership) requests that hit L2 cache. Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0xc2" }, @@ -256,7 +260,7 @@ "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_RQSTS.RFO_MISS", - "PublicDescription": "Counts the RFO (Read-for-Ownership) requests that miss L2 cache.", + "PublicDescription": "Counts the RFO (Read-for-Ownership) requests that miss L2 cache. Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0x22" }, @@ -265,7 +269,7 @@ "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_RQSTS.SWPF_HIT", - "PublicDescription": "Counts Software prefetch requests that hit the L2 cache. Accounts for PREFETCHNTA and PREFETCHT0/1/2 instructions when FB is not full.", + "PublicDescription": "Counts Software prefetch requests that hit the L2 cache. Accounts for PREFETCHNTA and PREFETCHT0/1/2 instructions when FB is not full. Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0xc8" }, @@ -274,7 +278,7 @@ "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_RQSTS.SWPF_MISS", - "PublicDescription": "Counts Software prefetch requests that miss the L2 cache. Accounts for PREFETCHNTA and PREFETCHT0/1/2 instructions when FB is not full.", + "PublicDescription": "Counts Software prefetch requests that miss the L2 cache. Accounts for PREFETCHNTA and PREFETCHT0/1/2 instructions when FB is not full. Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0x28" }, @@ -283,7 +287,7 @@ "Counter": "0,1,2,3", "EventCode": "0x23", "EventName": "L2_TRANS.L2_WB", - "PublicDescription": "Counts L2 writebacks that access L2 cache.", + "PublicDescription": "Counts L2 writebacks that access L2 cache. Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0x40" }, @@ -292,7 +296,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0x2e", "EventName": "LONGEST_LAT_CACHE.MISS", - "PublicDescription": "Counts core-originated cacheable requests that miss the L3 cache (Longest Latency cache). Requests include data and code reads, Reads-for-Ownership (RFOs), speculative accesses and hardware prefetches to the L1 and L2. It does not include hardware prefetches to the L3, and may not count other types of requests to the L3.", + "PublicDescription": "Counts core-originated cacheable requests that miss the L3 cache (Longest Latency cache). Requests include data and code reads, Reads-for-Ownership (RFOs), speculative accesses and hardware prefetches to the L1 and L2. It does not include hardware prefetches to the L3, and may not count other types of requests to the L3. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x41" }, @@ -301,7 +305,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0x2e", "EventName": "LONGEST_LAT_CACHE.REFERENCE", - "PublicDescription": "Counts core-originated cacheable requests to the L3 cache (Longest Latency cache). Requests include data and code reads, Reads-for-Ownership (RFOs), speculative accesses and hardware prefetches to the L1 and L2. It does not include hardware prefetches to the L3, and may not count other types of requests to the L3.", + "PublicDescription": "Counts core-originated cacheable requests to the L3 cache (Longest Latency cache). Requests include data and code reads, Reads-for-Ownership (RFOs), speculative accesses and hardware prefetches to the L1 and L2. It does not include hardware prefetches to the L3, and may not count other types of requests to the L3. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x4f" }, @@ -311,7 +315,7 @@ "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_INST_RETIRED.ALL_LOADS", - "PublicDescription": "Counts all retired load instructions. This event accounts for SW prefetch instructions of PREFETCHNTA or PREFETCHT0/1/2 or PREFETCHW.", + "PublicDescription": "Counts all retired load instructions. This event accounts for SW prefetch instructions of PREFETCHNTA or PREFETCHT0/1/2 or PREFETCHW. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x81" }, @@ -321,7 +325,7 @@ "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_INST_RETIRED.ALL_STORES", - "PublicDescription": "Counts all retired store instructions.", + "PublicDescription": "Counts all retired store instructions. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x82" }, @@ -331,7 +335,7 @@ "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_INST_RETIRED.ANY", - "PublicDescription": "Counts all retired memory instructions - loads and stores.", + "PublicDescription": "Counts all retired memory instructions - loads and stores. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x83" }, @@ -341,7 +345,7 @@ "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_INST_RETIRED.LOCK_LOADS", - "PublicDescription": "Counts retired load instructions with locked access.", + "PublicDescription": "Counts retired load instructions with locked access. Available PDIST counters: 0", "SampleAfterValue": "100007", "UMask": "0x21" }, @@ -351,7 +355,7 @@ "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_INST_RETIRED.SPLIT_LOADS", - "PublicDescription": "Counts retired load instructions that split across a cacheline boundary.", + "PublicDescription": "Counts retired load instructions that split across a cacheline boundary. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x41" }, @@ -361,7 +365,7 @@ "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_INST_RETIRED.SPLIT_STORES", - "PublicDescription": "Counts retired store instructions that split across a cacheline boundary.", + "PublicDescription": "Counts retired store instructions that split across a cacheline boundary. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x42" }, @@ -371,7 +375,7 @@ "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_INST_RETIRED.STLB_MISS_LOADS", - "PublicDescription": "Number of retired load instructions that (start a) miss in the 2nd-level TLB (STLB).", + "PublicDescription": "Number of retired load instructions that (start a) miss in the 2nd-level TLB (STLB). Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x11" }, @@ -381,7 +385,7 @@ "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_INST_RETIRED.STLB_MISS_STORES", - "PublicDescription": "Number of retired store instructions that (start a) miss in the 2nd-level TLB (STLB).", + "PublicDescription": "Number of retired store instructions that (start a) miss in the 2nd-level TLB (STLB). Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x12" }, @@ -390,7 +394,7 @@ "Counter": "0,1,2,3", "EventCode": "0x43", "EventName": "MEM_LOAD_COMPLETED.L1_MISS_ANY", - "PublicDescription": "Number of completed demand load requests that missed the L1 data cache including shadow misses (FB hits, merge to an ongoing L1D miss)", + "PublicDescription": "Number of completed demand load requests that missed the L1 data cache including shadow misses (FB hits, merge to an ongoing L1D miss) Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0xfd" }, @@ -400,7 +404,7 @@ "Data_LA": "1", "EventCode": "0xd2", "EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD", - "PublicDescription": "Counts retired load instructions whose data sources were HitM responses from shared L3.", + "PublicDescription": "Counts retired load instructions whose data sources were HitM responses from shared L3. Available PDIST counters: 0", "SampleAfterValue": "20011", "UMask": "0x4" }, @@ -410,7 +414,7 @@ "Data_LA": "1", "EventCode": "0xd2", "EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS", - "PublicDescription": "Counts the retired load instructions whose data sources were L3 hit and cross-core snoop missed in on-pkg core cache.", + "PublicDescription": "Counts the retired load instructions whose data sources were L3 hit and cross-core snoop missed in on-pkg core cache. Available PDIST counters: 0", "SampleAfterValue": "20011", "UMask": "0x1" }, @@ -420,7 +424,7 @@ "Data_LA": "1", "EventCode": "0xd2", "EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_NONE", - "PublicDescription": "Counts retired load instructions whose data sources were hits in L3 without snoops required.", + "PublicDescription": "Counts retired load instructions whose data sources were hits in L3 without snoops required. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x8" }, @@ -430,7 +434,7 @@ "Data_LA": "1", "EventCode": "0xd2", "EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_NO_FWD", - "PublicDescription": "Counts retired load instructions whose data sources were L3 and cross-core snoop hits in on-pkg core cache.", + "PublicDescription": "Counts retired load instructions whose data sources were L3 and cross-core snoop hits in on-pkg core cache. Available PDIST counters: 0", "SampleAfterValue": "20011", "UMask": "0x2" }, @@ -440,7 +444,7 @@ "Data_LA": "1", "EventCode": "0xd3", "EventName": "MEM_LOAD_L3_MISS_RETIRED.LOCAL_DRAM", - "PublicDescription": "Retired load instructions which data sources missed L3 but serviced from local DRAM.", + "PublicDescription": "Retired load instructions which data sources missed L3 but serviced from local DRAM. Available PDIST counters: 0", "SampleAfterValue": "100007", "UMask": "0x1" }, @@ -450,6 +454,7 @@ "Data_LA": "1", "EventCode": "0xd3", "EventName": "MEM_LOAD_L3_MISS_RETIRED.REMOTE_DRAM", + "PublicDescription": "MEM_LOAD_L3_MISS_RETIRED.REMOTE_DRAM Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x2" }, @@ -459,7 +464,7 @@ "Data_LA": "1", "EventCode": "0xd3", "EventName": "MEM_LOAD_L3_MISS_RETIRED.REMOTE_FWD", - "PublicDescription": "Retired load instructions whose data sources was forwarded from a remote cache.", + "PublicDescription": "Retired load instructions whose data sources was forwarded from a remote cache. Available PDIST counters: 0", "SampleAfterValue": "100007", "UMask": "0x8" }, @@ -469,6 +474,7 @@ "Data_LA": "1", "EventCode": "0xd3", "EventName": "MEM_LOAD_L3_MISS_RETIRED.REMOTE_HITM", + "PublicDescription": "MEM_LOAD_L3_MISS_RETIRED.REMOTE_HITM Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x4" }, @@ -477,7 +483,7 @@ "Counter": "0,1,2,3", "EventCode": "0xd3", "EventName": "MEM_LOAD_L3_MISS_RETIRED.REMOTE_PMM", - "PublicDescription": "Counts retired load instructions with remote Intel(R) Optane(TM) DC persistent memory as the data source and the data request missed L3.", + "PublicDescription": "Counts retired load instructions with remote Intel(R) Optane(TM) DC persistent memory as the data source and the data request missed L3. Available PDIST counters: 0", "SampleAfterValue": "100007", "UMask": "0x10" }, @@ -487,7 +493,7 @@ "Data_LA": "1", "EventCode": "0xd4", "EventName": "MEM_LOAD_MISC_RETIRED.UC", - "PublicDescription": "Retired instructions with at least one load to uncacheable memory-type, or at least one cache-line split locked access (Bus Lock).", + "PublicDescription": "Retired instructions with at least one load to uncacheable memory-type, or at least one cache-line split locked access (Bus Lock). Available PDIST counters: 0", "SampleAfterValue": "100007", "UMask": "0x4" }, @@ -497,7 +503,7 @@ "Data_LA": "1", "EventCode": "0xd1", "EventName": "MEM_LOAD_RETIRED.FB_HIT", - "PublicDescription": "Counts retired load instructions with at least one uop was load missed in L1 but hit FB (Fill Buffers) due to preceding miss to the same cache line with data not ready.", + "PublicDescription": "Counts retired load instructions with at least one uop was load missed in L1 but hit FB (Fill Buffers) due to preceding miss to the same cache line with data not ready. Available PDIST counters: 0", "SampleAfterValue": "100007", "UMask": "0x40" }, @@ -507,7 +513,7 @@ "Data_LA": "1", "EventCode": "0xd1", "EventName": "MEM_LOAD_RETIRED.L1_HIT", - "PublicDescription": "Counts retired load instructions with at least one uop that hit in the L1 data cache. This event includes all SW prefetches and lock instructions regardless of the data source.", + "PublicDescription": "Counts retired load instructions with at least one uop that hit in the L1 data cache. This event includes all SW prefetches and lock instructions regardless of the data source. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x1" }, @@ -517,7 +523,7 @@ "Data_LA": "1", "EventCode": "0xd1", "EventName": "MEM_LOAD_RETIRED.L1_MISS", - "PublicDescription": "Counts retired load instructions with at least one uop that missed in the L1 cache.", + "PublicDescription": "Counts retired load instructions with at least one uop that missed in the L1 cache. Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0x8" }, @@ -527,7 +533,7 @@ "Data_LA": "1", "EventCode": "0xd1", "EventName": "MEM_LOAD_RETIRED.L2_HIT", - "PublicDescription": "Counts retired load instructions with L2 cache hits as data sources.", + "PublicDescription": "Counts retired load instructions with L2 cache hits as data sources. Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0x2" }, @@ -537,7 +543,7 @@ "Data_LA": "1", "EventCode": "0xd1", "EventName": "MEM_LOAD_RETIRED.L2_MISS", - "PublicDescription": "Counts retired load instructions missed L2 cache as data sources.", + "PublicDescription": "Counts retired load instructions missed L2 cache as data sources. Available PDIST counters: 0", "SampleAfterValue": "100021", "UMask": "0x10" }, @@ -547,7 +553,7 @@ "Data_LA": "1", "EventCode": "0xd1", "EventName": "MEM_LOAD_RETIRED.L3_HIT", - "PublicDescription": "Counts retired load instructions with at least one uop that hit in the L3 cache.", + "PublicDescription": "Counts retired load instructions with at least one uop that hit in the L3 cache. Available PDIST counters: 0", "SampleAfterValue": "100021", "UMask": "0x4" }, @@ -557,7 +563,7 @@ "Data_LA": "1", "EventCode": "0xd1", "EventName": "MEM_LOAD_RETIRED.L3_MISS", - "PublicDescription": "Counts retired load instructions with at least one uop that missed in the L3 cache.", + "PublicDescription": "Counts retired load instructions with at least one uop that missed in the L3 cache. Available PDIST counters: 0", "SampleAfterValue": "50021", "UMask": "0x20" }, @@ -567,7 +573,7 @@ "Data_LA": "1", "EventCode": "0xd1", "EventName": "MEM_LOAD_RETIRED.LOCAL_PMM", - "PublicDescription": "Counts retired load instructions with local Intel(R) Optane(TM) DC persistent memory as the data source and the data request missed L3.", + "PublicDescription": "Counts retired load instructions with local Intel(R) Optane(TM) DC persistent memory as the data source and the data request missed L3. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x80" }, @@ -576,6 +582,7 @@ "Counter": "0,1,2,3", "EventCode": "0x44", "EventName": "MEM_STORE_RETIRED.L2_HIT", + "PublicDescription": "MEM_STORE_RETIRED.L2_HIT Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0x1" }, @@ -584,17 +591,29 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xe5", "EventName": "MEM_UOP_RETIRED.ANY", - "PublicDescription": "Number of retired micro-operations (uops) for load or store memory accesses", + "PublicDescription": "Number of retired micro-operations (uops) for load or store memory accesses Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x3" }, { + "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that have any type of response.", + "Counter": "0,1,2,3", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.DEMAND_CODE_RD.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x10004", + "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that have any type of response. Available PDIST counters: 0", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that hit in the L3 or were snooped from another core's caches on the same socket.", "Counter": "0,1,2,3", "EventCode": "0x2A,0x2B", "EventName": "OCR.DEMAND_CODE_RD.L3_HIT", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x3F803C0004", + "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that hit in the L3 or were snooped from another core's caches on the same socket. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -605,6 +624,7 @@ "EventName": "OCR.DEMAND_CODE_RD.L3_HIT.SNOOP_HITM", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x10003C0004", + "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that resulted in a snoop hit a modified line in another core's caches which forwarded the data. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -615,6 +635,7 @@ "EventName": "OCR.DEMAND_CODE_RD.SNC_CACHE.HITM", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x1008000004", + "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that hit a modified line in a distant L3 Cache or were snooped from a distant core's L1/L2 caches on this socket when the system is in SNC (sub-NUMA cluster) mode. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -625,6 +646,18 @@ "EventName": "OCR.DEMAND_CODE_RD.SNC_CACHE.HIT_WITH_FWD", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x808000004", + "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that either hit a non-modified line in a distant L3 Cache or were snooped from a distant core's L1/L2 caches on this socket when the system is in SNC (sub-NUMA cluster) mode. Available PDIST counters: 0", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts demand data reads that have any type of response.", + "Counter": "0,1,2,3", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.DEMAND_DATA_RD.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x10001", + "PublicDescription": "Counts demand data reads that have any type of response. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -635,6 +668,7 @@ "EventName": "OCR.DEMAND_DATA_RD.L3_HIT", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x3F803C0001", + "PublicDescription": "Counts demand data reads that hit in the L3 or were snooped from another core's caches on the same socket. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -645,6 +679,7 @@ "EventName": "OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x10003C0001", + "PublicDescription": "Counts demand data reads that resulted in a snoop hit a modified line in another core's caches which forwarded the data. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -655,6 +690,7 @@ "EventName": "OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_NO_FWD", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x4003C0001", + "PublicDescription": "Counts demand data reads that resulted in a snoop that hit in another core, which did not forward the data. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -665,6 +701,29 @@ "EventName": "OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x8003C0001", + "PublicDescription": "Counts demand data reads that resulted in a snoop hit in another core's caches which forwarded the unmodified data to the requesting core. Available PDIST counters: 0", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts demand data reads that were supplied by PMM attached to this socket, whether or not in Sub NUMA Cluster(SNC) Mode. In SNC Mode counts PMM accesses that are controlled by the close or distant SNC Cluster.", + "Counter": "0,1,2,3", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.DEMAND_DATA_RD.LOCAL_SOCKET_PMM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x700C00001", + "PublicDescription": "Counts demand data reads that were supplied by PMM attached to this socket, whether or not in Sub NUMA Cluster(SNC) Mode. In SNC Mode counts PMM accesses that are controlled by the close or distant SNC Cluster. Available PDIST counters: 0", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts demand data reads that were supplied by PMM.", + "Counter": "0,1,2,3", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.DEMAND_DATA_RD.PMM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x703C00001", + "PublicDescription": "Counts demand data reads that were supplied by PMM. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -675,6 +734,7 @@ "EventName": "OCR.DEMAND_DATA_RD.REMOTE_CACHE.SNOOP_HITM", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x1030000001", + "PublicDescription": "Counts demand data reads that were supplied by a cache on a remote socket where a snoop hit a modified line in another core's caches which forwarded the data. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -685,6 +745,18 @@ "EventName": "OCR.DEMAND_DATA_RD.REMOTE_CACHE.SNOOP_HIT_WITH_FWD", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x830000001", + "PublicDescription": "Counts demand data reads that were supplied by a cache on a remote socket where a snoop hit in another core's caches which forwarded the unmodified data to the requesting core. Available PDIST counters: 0", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts demand data reads that were supplied by PMM attached to another socket.", + "Counter": "0,1,2,3", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.DEMAND_DATA_RD.REMOTE_PMM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x703000001", + "PublicDescription": "Counts demand data reads that were supplied by PMM attached to another socket. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -695,6 +767,7 @@ "EventName": "OCR.DEMAND_DATA_RD.SNC_CACHE.HITM", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x1008000001", + "PublicDescription": "Counts demand data reads that hit a modified line in a distant L3 Cache or were snooped from a distant core's L1/L2 caches on this socket when the system is in SNC (sub-NUMA cluster) mode. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -705,6 +778,18 @@ "EventName": "OCR.DEMAND_DATA_RD.SNC_CACHE.HIT_WITH_FWD", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x808000001", + "PublicDescription": "Counts demand data reads that either hit a non-modified line in a distant L3 Cache or were snooped from a distant core's L1/L2 caches on this socket when the system is in SNC (sub-NUMA cluster) mode. Available PDIST counters: 0", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts demand reads for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that have any type of response.", + "Counter": "0,1,2,3", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.DEMAND_RFO.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x3F3FFC0002", + "PublicDescription": "Counts demand reads for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that have any type of response. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -715,6 +800,7 @@ "EventName": "OCR.DEMAND_RFO.L3_HIT", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x3F803C0002", + "PublicDescription": "Counts demand reads for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that hit in the L3 or were snooped from another core's caches on the same socket. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -725,6 +811,7 @@ "EventName": "OCR.DEMAND_RFO.L3_HIT.SNOOP_HITM", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x10003C0002", + "PublicDescription": "Counts demand reads for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that resulted in a snoop hit a modified line in another core's caches which forwarded the data. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -735,6 +822,7 @@ "EventName": "OCR.DEMAND_RFO.SNC_CACHE.HITM", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x1008000002", + "PublicDescription": "Counts demand reads for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that hit a modified line in a distant L3 Cache or were snooped from a distant core's L1/L2 caches on this socket when the system is in SNC (sub-NUMA cluster) mode. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -745,6 +833,40 @@ "EventName": "OCR.DEMAND_RFO.SNC_CACHE.HIT_WITH_FWD", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x808000002", + "PublicDescription": "Counts demand reads for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that either hit a non-modified line in a distant L3 Cache or were snooped from a distant core's L1/L2 caches on this socket when the system is in SNC (sub-NUMA cluster) mode. Available PDIST counters: 0", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts data load hardware prefetch requests to the L1 data cache that have any type of response.", + "Counter": "0,1,2,3", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.HWPF_L1D.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x10400", + "PublicDescription": "Counts data load hardware prefetch requests to the L1 data cache that have any type of response. Available PDIST counters: 0", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts hardware prefetches (which bring data to L2) that have any type of response.", + "Counter": "0,1,2,3", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.HWPF_L2.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x10070", + "PublicDescription": "Counts hardware prefetches (which bring data to L2) that have any type of response. Available PDIST counters: 0", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts hardware prefetches to the L3 only that have any type of response.", + "Counter": "0,1,2,3", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.HWPF_L3.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x12380", + "PublicDescription": "Counts hardware prefetches to the L3 only that have any type of response. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -755,6 +877,40 @@ "EventName": "OCR.HWPF_L3.L3_HIT", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x80082380", + "PublicDescription": "Counts hardware prefetches to the L3 only that hit in the L3 or were snooped from another core's caches on the same socket. Available PDIST counters: 0", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts hardware prefetches to the L3 only that were not supplied by the local socket's L1, L2, or L3 caches and the cacheline was homed in a remote socket.", + "Counter": "0,1,2,3", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.HWPF_L3.REMOTE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x90002380", + "PublicDescription": "Counts hardware prefetches to the L3 only that were not supplied by the local socket's L1, L2, or L3 caches and the cacheline was homed in a remote socket. Available PDIST counters: 0", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts writebacks of modified cachelines and streaming stores that have any type of response.", + "Counter": "0,1,2,3", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.MODIFIED_WRITE.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x10808", + "PublicDescription": "Counts writebacks of modified cachelines and streaming stores that have any type of response. Available PDIST counters: 0", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that have any type of response.", + "Counter": "0,1,2,3", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.READS_TO_CORE.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x3F3FFC4477", + "PublicDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that have any type of response. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -765,6 +921,7 @@ "EventName": "OCR.READS_TO_CORE.L3_HIT", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x3F003C4477", + "PublicDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that hit in the L3 or were snooped from another core's caches on the same socket. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -775,6 +932,7 @@ "EventName": "OCR.READS_TO_CORE.L3_HIT.SNOOP_HITM", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x10003C4477", + "PublicDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that resulted in a snoop hit a modified line in another core's caches which forwarded the data. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -785,6 +943,7 @@ "EventName": "OCR.READS_TO_CORE.L3_HIT.SNOOP_HIT_NO_FWD", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x4003C4477", + "PublicDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that resulted in a snoop that hit in another core, which did not forward the data. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -795,6 +954,29 @@ "EventName": "OCR.READS_TO_CORE.L3_HIT.SNOOP_HIT_WITH_FWD", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x8003C4477", + "PublicDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that resulted in a snoop hit in another core's caches which forwarded the unmodified data to the requesting core. Available PDIST counters: 0", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by PMM attached to this socket, whether or not in Sub NUMA Cluster(SNC) Mode. In SNC Mode counts PMM accesses that are controlled by the close or distant SNC Cluster.", + "Counter": "0,1,2,3", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.READS_TO_CORE.LOCAL_SOCKET_PMM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x700C04477", + "PublicDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by PMM attached to this socket, whether or not in Sub NUMA Cluster(SNC) Mode. In SNC Mode counts PMM accesses that are controlled by the close or distant SNC Cluster. Available PDIST counters: 0", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were not supplied by the local socket's L1, L2, or L3 caches and were supplied by a remote socket.", + "Counter": "0,1,2,3", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.READS_TO_CORE.REMOTE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x3F33004477", + "PublicDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were not supplied by the local socket's L1, L2, or L3 caches and were supplied by a remote socket. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -805,6 +987,7 @@ "EventName": "OCR.READS_TO_CORE.REMOTE_CACHE.SNOOP_FWD", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x1830004477", + "PublicDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by a cache on a remote socket where a snoop was sent and data was returned (Modified or Not Modified). Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -815,6 +998,7 @@ "EventName": "OCR.READS_TO_CORE.REMOTE_CACHE.SNOOP_HITM", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x1030004477", + "PublicDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by a cache on a remote socket where a snoop hit a modified line in another core's caches which forwarded the data. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -825,6 +1009,18 @@ "EventName": "OCR.READS_TO_CORE.REMOTE_CACHE.SNOOP_HIT_WITH_FWD", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x830004477", + "PublicDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by a cache on a remote socket where a snoop hit in another core's caches which forwarded the unmodified data to the requesting core. Available PDIST counters: 0", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by PMM attached to another socket.", + "Counter": "0,1,2,3", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.READS_TO_CORE.REMOTE_PMM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x703004477", + "PublicDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by PMM attached to another socket. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -835,6 +1031,7 @@ "EventName": "OCR.READS_TO_CORE.SNC_CACHE.HITM", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x1008004477", + "PublicDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that hit a modified line in a distant L3 Cache or were snooped from a distant core's L1/L2 caches on this socket when the system is in SNC (sub-NUMA cluster) mode. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -845,6 +1042,7 @@ "EventName": "OCR.READS_TO_CORE.SNC_CACHE.HIT_WITH_FWD", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x808004477", + "PublicDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that either hit a non-modified line in a distant L3 Cache or were snooped from a distant core's L1/L2 caches on this socket when the system is in SNC (sub-NUMA cluster) mode. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -855,6 +1053,7 @@ "EventName": "OCR.RFO_TO_CORE.L3_HIT_M", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x1F80040022", + "PublicDescription": "Counts demand reads for ownership (RFO), hardware prefetch RFOs (which bring data to L2), and software prefetches for exclusive ownership (PREFETCHW) that hit to a (M)odified cacheline in the L3 or snoop filter. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -865,6 +1064,7 @@ "EventName": "OCR.STREAMING_WR.L3_HIT", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x80080800", + "PublicDescription": "Counts streaming stores that hit in the L3 or were snooped from another core's caches on the same socket. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -873,6 +1073,7 @@ "Counter": "0,1,2,3", "EventCode": "0x21", "EventName": "OFFCORE_REQUESTS.ALL_REQUESTS", + "PublicDescription": "OFFCORE_REQUESTS.ALL_REQUESTS Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x80" }, @@ -881,7 +1082,7 @@ "Counter": "0,1,2,3", "EventCode": "0x21", "EventName": "OFFCORE_REQUESTS.DATA_RD", - "PublicDescription": "Counts the demand and prefetch data reads. All Core Data Reads include cacheable 'Demands' and L2 prefetchers (not L3 prefetchers). Counting also covers reads due to page walks resulted from any request type.", + "PublicDescription": "Counts the demand and prefetch data reads. All Core Data Reads include cacheable 'Demands' and L2 prefetchers (not L3 prefetchers). Counting also covers reads due to page walks resulted from any request type. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x8" }, @@ -890,7 +1091,7 @@ "Counter": "0,1,2,3", "EventCode": "0x21", "EventName": "OFFCORE_REQUESTS.DEMAND_CODE_RD", - "PublicDescription": "Counts both cacheable and non-cacheable code read requests.", + "PublicDescription": "Counts both cacheable and non-cacheable code read requests. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x2" }, @@ -899,7 +1100,7 @@ "Counter": "0,1,2,3", "EventCode": "0x21", "EventName": "OFFCORE_REQUESTS.DEMAND_DATA_RD", - "PublicDescription": "Counts the Demand Data Read requests sent to uncore. Use it in conjunction with OFFCORE_REQUESTS_OUTSTANDING to determine average latency in the uncore.", + "PublicDescription": "Counts the Demand Data Read requests sent to uncore. Use it in conjunction with OFFCORE_REQUESTS_OUTSTANDING to determine average latency in the uncore. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -908,7 +1109,7 @@ "Counter": "0,1,2,3", "EventCode": "0x21", "EventName": "OFFCORE_REQUESTS.DEMAND_RFO", - "PublicDescription": "Counts the demand RFO (read for ownership) requests including regular RFOs, locks, ItoM.", + "PublicDescription": "Counts the demand RFO (read for ownership) requests including regular RFOs, locks, ItoM. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x4" }, @@ -918,6 +1119,7 @@ "Deprecated": "1", "EventCode": "0x20", "EventName": "OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD", + "PublicDescription": "This event is deprecated. Refer to new event OFFCORE_REQUESTS_OUTSTANDING.DATA_RD Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x8" }, @@ -927,6 +1129,7 @@ "CounterMask": "1", "EventCode": "0x20", "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD", + "PublicDescription": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x8" }, @@ -936,7 +1139,7 @@ "CounterMask": "1", "EventCode": "0x20", "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_CODE_RD", - "PublicDescription": "Counts the number of offcore outstanding Code Reads transactions in the super queue every cycle. The 'Offcore outstanding' state of the transaction lasts from the L2 miss until the sending transaction completion to requestor (SQ deallocation). See the corresponding Umask under OFFCORE_REQUESTS.", + "PublicDescription": "Counts the number of offcore outstanding Code Reads transactions in the super queue every cycle. The 'Offcore outstanding' state of the transaction lasts from the L2 miss until the sending transaction completion to requestor (SQ deallocation). See the corresponding Umask under OFFCORE_REQUESTS. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x2" }, @@ -946,6 +1149,7 @@ "CounterMask": "1", "EventCode": "0x20", "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_DATA_RD", + "PublicDescription": "Cycles where at least 1 outstanding demand data read request is pending. Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x1" }, @@ -955,6 +1159,7 @@ "CounterMask": "1", "EventCode": "0x20", "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO", + "PublicDescription": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x4" }, @@ -963,6 +1168,7 @@ "Counter": "0,1,2,3", "EventCode": "0x20", "EventName": "OFFCORE_REQUESTS_OUTSTANDING.DATA_RD", + "PublicDescription": "OFFCORE_REQUESTS_OUTSTANDING.DATA_RD Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x8" }, @@ -971,7 +1177,7 @@ "Counter": "0,1,2,3", "EventCode": "0x20", "EventName": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_CODE_RD", - "PublicDescription": "Counts the number of offcore outstanding Code Reads transactions in the super queue every cycle. The 'Offcore outstanding' state of the transaction lasts from the L2 miss until the sending transaction completion to requestor (SQ deallocation). See the corresponding Umask under OFFCORE_REQUESTS.", + "PublicDescription": "Counts the number of offcore outstanding Code Reads transactions in the super queue every cycle. The 'Offcore outstanding' state of the transaction lasts from the L2 miss until the sending transaction completion to requestor (SQ deallocation). See the corresponding Umask under OFFCORE_REQUESTS. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x2" }, @@ -980,7 +1186,7 @@ "Counter": "0,1,2,3", "EventCode": "0x20", "EventName": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD", - "PublicDescription": "For every cycle, increments by the number of outstanding demand data read requests pending. Requests are considered outstanding from the time they miss the core's L2 cache until the transaction completion message is sent to the requestor.", + "PublicDescription": "For every cycle, increments by the number of outstanding demand data read requests pending. Requests are considered outstanding from the time they miss the core's L2 cache until the transaction completion message is sent to the requestor. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x1" }, @@ -989,7 +1195,7 @@ "Counter": "0,1,2,3", "EventCode": "0x2c", "EventName": "SQ_MISC.BUS_LOCK", - "PublicDescription": "Counts the more expensive bus lock needed to enforce cache coherency for certain memory accesses that need to be done atomically. Can be created by issuing an atomic instruction (via the LOCK prefix) which causes a cache line split or accesses uncacheable memory.", + "PublicDescription": "Counts the more expensive bus lock needed to enforce cache coherency for certain memory accesses that need to be done atomically. Can be created by issuing an atomic instruction (via the LOCK prefix) which causes a cache line split or accesses uncacheable memory. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x10" }, @@ -998,6 +1204,7 @@ "Counter": "0,1,2,3", "EventCode": "0x40", "EventName": "SW_PREFETCH_ACCESS.ANY", + "PublicDescription": "Counts the number of PREFETCHNTA, PREFETCHW, PREFETCHT0, PREFETCHT1 or PREFETCHT2 instructions executed. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0xf" }, @@ -1006,7 +1213,7 @@ "Counter": "0,1,2,3", "EventCode": "0x40", "EventName": "SW_PREFETCH_ACCESS.NTA", - "PublicDescription": "Counts the number of PREFETCHNTA instructions executed.", + "PublicDescription": "Counts the number of PREFETCHNTA instructions executed. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -1015,7 +1222,7 @@ "Counter": "0,1,2,3", "EventCode": "0x40", "EventName": "SW_PREFETCH_ACCESS.PREFETCHW", - "PublicDescription": "Counts the number of PREFETCHW instructions executed.", + "PublicDescription": "Counts the number of PREFETCHW instructions executed. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x8" }, @@ -1024,7 +1231,7 @@ "Counter": "0,1,2,3", "EventCode": "0x40", "EventName": "SW_PREFETCH_ACCESS.T0", - "PublicDescription": "Counts the number of PREFETCHT0 instructions executed.", + "PublicDescription": "Counts the number of PREFETCHT0 instructions executed. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x2" }, @@ -1033,7 +1240,7 @@ "Counter": "0,1,2,3", "EventCode": "0x40", "EventName": "SW_PREFETCH_ACCESS.T1_T2", - "PublicDescription": "Counts the number of PREFETCHT1 or PREFETCHT2 instructions executed.", + "PublicDescription": "Counts the number of PREFETCHT1 or PREFETCHT2 instructions executed. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x4" } diff --git a/tools/perf/pmu-events/arch/x86/sapphirerapids/floating-point.json b/tools/perf/pmu-events/arch/x86/sapphirerapids/floating-point.json index bc475e163227..8c9207750c82 100644 --- a/tools/perf/pmu-events/arch/x86/sapphirerapids/floating-point.json +++ b/tools/perf/pmu-events/arch/x86/sapphirerapids/floating-point.json @@ -5,6 +5,7 @@ "CounterMask": "1", "EventCode": "0xb0", "EventName": "ARITH.FPDIV_ACTIVE", + "PublicDescription": "ARITH.FPDIV_ACTIVE Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x1" }, @@ -13,7 +14,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc1", "EventName": "ASSISTS.FP", - "PublicDescription": "Counts all microcode Floating Point assists.", + "PublicDescription": "Counts all microcode Floating Point assists. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x2" }, @@ -22,6 +23,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc1", "EventName": "ASSISTS.SSE_AVX_MIX", + "PublicDescription": "ASSISTS.SSE_AVX_MIX Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x10" }, @@ -30,6 +32,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xb3", "EventName": "FP_ARITH_DISPATCHED.PORT_0", + "PublicDescription": "FP_ARITH_DISPATCHED.PORT_0 [This event is alias to FP_ARITH_DISPATCHED.V0] Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x1" }, @@ -38,6 +41,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xb3", "EventName": "FP_ARITH_DISPATCHED.PORT_1", + "PublicDescription": "FP_ARITH_DISPATCHED.PORT_1 [This event is alias to FP_ARITH_DISPATCHED.V1] Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x2" }, @@ -46,6 +50,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xb3", "EventName": "FP_ARITH_DISPATCHED.PORT_5", + "PublicDescription": "FP_ARITH_DISPATCHED.PORT_5 [This event is alias to FP_ARITH_DISPATCHED.V2] Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x4" }, @@ -54,6 +59,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xb3", "EventName": "FP_ARITH_DISPATCHED.V0", + "PublicDescription": "FP_ARITH_DISPATCHED.V0 [This event is alias to FP_ARITH_DISPATCHED.PORT_0] Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x1" }, @@ -62,6 +68,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xb3", "EventName": "FP_ARITH_DISPATCHED.V1", + "PublicDescription": "FP_ARITH_DISPATCHED.V1 [This event is alias to FP_ARITH_DISPATCHED.PORT_1] Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x2" }, @@ -70,6 +77,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xb3", "EventName": "FP_ARITH_DISPATCHED.V2", + "PublicDescription": "FP_ARITH_DISPATCHED.V2 [This event is alias to FP_ARITH_DISPATCHED.PORT_5] Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x4" }, @@ -78,7 +86,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc7", "EventName": "FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE", - "PublicDescription": "Number of SSE/AVX computational 128-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 2 computation operations, one for each element. Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.", + "PublicDescription": "Number of SSE/AVX computational 128-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 2 computation operations, one for each element. Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x4" }, @@ -87,7 +95,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc7", "EventName": "FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE", - "PublicDescription": "Number of SSE/AVX computational 128-bit packed single precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 4 computation operations, one for each element. Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT RSQRT RCP DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.", + "PublicDescription": "Number of SSE/AVX computational 128-bit packed single precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 4 computation operations, one for each element. Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT RSQRT RCP DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x8" }, @@ -96,7 +104,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc7", "EventName": "FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE", - "PublicDescription": "Number of SSE/AVX computational 256-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 4 computation operations, one for each element. Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.", + "PublicDescription": "Number of SSE/AVX computational 256-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 4 computation operations, one for each element. Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x10" }, @@ -105,7 +113,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc7", "EventName": "FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE", - "PublicDescription": "Number of SSE/AVX computational 256-bit packed single precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 8 computation operations, one for each element. Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT RSQRT RCP DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.", + "PublicDescription": "Number of SSE/AVX computational 256-bit packed single precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 8 computation operations, one for each element. Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT RSQRT RCP DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x20" }, @@ -114,7 +122,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc7", "EventName": "FP_ARITH_INST_RETIRED.4_FLOPS", - "PublicDescription": "Number of SSE/AVX computational 128-bit packed single precision and 256-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 2 or/and 4 computation operations, one for each element. Applies to SSE* and AVX* packed single precision floating-point and packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX RCP14 RSQRT14 SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.", + "PublicDescription": "Number of SSE/AVX computational 128-bit packed single precision and 256-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 2 or/and 4 computation operations, one for each element. Applies to SSE* and AVX* packed single precision floating-point and packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX RCP14 RSQRT14 SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x18" }, @@ -123,7 +131,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc7", "EventName": "FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE", - "PublicDescription": "Number of SSE/AVX computational 512-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 8 computation operations, one for each element. Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT RSQRT14 RCP14 FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.", + "PublicDescription": "Number of SSE/AVX computational 512-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 8 computation operations, one for each element. Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT RSQRT14 RCP14 FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x40" }, @@ -132,7 +140,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc7", "EventName": "FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE", - "PublicDescription": "Number of SSE/AVX computational 512-bit packed single precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 16 computation operations, one for each element. Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT RSQRT14 RCP14 FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.", + "PublicDescription": "Number of SSE/AVX computational 512-bit packed single precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 16 computation operations, one for each element. Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT RSQRT14 RCP14 FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x80" }, @@ -141,7 +149,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc7", "EventName": "FP_ARITH_INST_RETIRED.8_FLOPS", - "PublicDescription": "Number of SSE/AVX computational 256-bit packed single precision and 512-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 8 computation operations, one for each element. Applies to SSE* and AVX* packed single precision and double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT RSQRT RSQRT14 RCP RCP14 DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.", + "PublicDescription": "Number of SSE/AVX computational 256-bit packed single precision and 512-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 8 computation operations, one for each element. Applies to SSE* and AVX* packed single precision and double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT RSQRT RSQRT14 RCP RCP14 DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x60" }, @@ -150,7 +158,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc7", "EventName": "FP_ARITH_INST_RETIRED.SCALAR", - "PublicDescription": "Number of SSE/AVX computational scalar single precision and double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 1 computational operation. Applies to SSE* and AVX* scalar single precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT RSQRT RCP FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.", + "PublicDescription": "Number of SSE/AVX computational scalar single precision and double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 1 computational operation. Applies to SSE* and AVX* scalar single precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT RSQRT RCP FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x3" }, @@ -159,7 +167,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc7", "EventName": "FP_ARITH_INST_RETIRED.SCALAR_DOUBLE", - "PublicDescription": "Number of SSE/AVX computational scalar double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 1 computational operation. Applies to SSE* and AVX* scalar double precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.", + "PublicDescription": "Number of SSE/AVX computational scalar double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 1 computational operation. Applies to SSE* and AVX* scalar double precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -168,7 +176,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc7", "EventName": "FP_ARITH_INST_RETIRED.SCALAR_SINGLE", - "PublicDescription": "Number of SSE/AVX computational scalar single precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 1 computational operation. Applies to SSE* and AVX* scalar single precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT RSQRT RCP FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.", + "PublicDescription": "Number of SSE/AVX computational scalar single precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 1 computational operation. Applies to SSE* and AVX* scalar single precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT RSQRT RCP FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x2" }, @@ -177,7 +185,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc7", "EventName": "FP_ARITH_INST_RETIRED.VECTOR", - "PublicDescription": "Number of any Vector retired FP arithmetic instructions. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.", + "PublicDescription": "Number of any Vector retired FP arithmetic instructions. The DAZ and FTZ flags in the MXCSR register need to be set when using these events. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0xfc" }, @@ -186,6 +194,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xcf", "EventName": "FP_ARITH_INST_RETIRED2.128B_PACKED_HALF", + "PublicDescription": "FP_ARITH_INST_RETIRED2.128B_PACKED_HALF Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x4" }, @@ -194,6 +203,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xcf", "EventName": "FP_ARITH_INST_RETIRED2.256B_PACKED_HALF", + "PublicDescription": "FP_ARITH_INST_RETIRED2.256B_PACKED_HALF Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x8" }, @@ -202,6 +212,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xcf", "EventName": "FP_ARITH_INST_RETIRED2.512B_PACKED_HALF", + "PublicDescription": "FP_ARITH_INST_RETIRED2.512B_PACKED_HALF Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x10" }, @@ -210,6 +221,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xcf", "EventName": "FP_ARITH_INST_RETIRED2.COMPLEX_SCALAR_HALF", + "PublicDescription": "FP_ARITH_INST_RETIRED2.COMPLEX_SCALAR_HALF Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x2" }, @@ -218,7 +230,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xcf", "EventName": "FP_ARITH_INST_RETIRED2.SCALAR", - "PublicDescription": "FP_ARITH_INST_RETIRED2.SCALAR", + "PublicDescription": "FP_ARITH_INST_RETIRED2.SCALAR Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x3" }, @@ -227,6 +239,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xcf", "EventName": "FP_ARITH_INST_RETIRED2.SCALAR_HALF", + "PublicDescription": "FP_ARITH_INST_RETIRED2.SCALAR_HALF Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -235,7 +248,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xcf", "EventName": "FP_ARITH_INST_RETIRED2.VECTOR", - "PublicDescription": "FP_ARITH_INST_RETIRED2.VECTOR", + "PublicDescription": "FP_ARITH_INST_RETIRED2.VECTOR Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1c" } diff --git a/tools/perf/pmu-events/arch/x86/sapphirerapids/frontend.json b/tools/perf/pmu-events/arch/x86/sapphirerapids/frontend.json index bf68493d4509..9fe9d62b867a 100644 --- a/tools/perf/pmu-events/arch/x86/sapphirerapids/frontend.json +++ b/tools/perf/pmu-events/arch/x86/sapphirerapids/frontend.json @@ -4,7 +4,7 @@ "Counter": "0,1,2,3", "EventCode": "0x60", "EventName": "BACLEARS.ANY", - "PublicDescription": "Number of times the front-end is resteered when it finds a branch instruction in a fetch line. This is called Unknown Branch which occurs for the first time a branch instruction is fetched or when the branch is not tracked by the BPU (Branch Prediction Unit) anymore.", + "PublicDescription": "Number of times the front-end is resteered when it finds a branch instruction in a fetch line. This is called Unknown Branch which occurs for the first time a branch instruction is fetched or when the branch is not tracked by the BPU (Branch Prediction Unit) anymore. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -13,7 +13,7 @@ "Counter": "0,1,2,3", "EventCode": "0x87", "EventName": "DECODE.LCP", - "PublicDescription": "Counts cycles that the Instruction Length decoder (ILD) stalls occurred due to dynamically changing prefix length of the decoded instruction (by operand size prefix instruction 0x66, address size prefix instruction 0x67 or REX.W for Intel64). Count is proportional to the number of prefixes in a 16B-line. This may result in a three-cycle penalty for each LCP (Length changing prefix) in a 16-byte chunk.", + "PublicDescription": "Counts cycles that the Instruction Length decoder (ILD) stalls occurred due to dynamically changing prefix length of the decoded instruction (by operand size prefix instruction 0x66, address size prefix instruction 0x67 or REX.W for Intel64). Count is proportional to the number of prefixes in a 16B-line. This may result in a three-cycle penalty for each LCP (Length changing prefix) in a 16-byte chunk. Available PDIST counters: 0", "SampleAfterValue": "500009", "UMask": "0x1" }, @@ -22,6 +22,7 @@ "Counter": "0,1,2,3", "EventCode": "0x87", "EventName": "DECODE.MS_BUSY", + "PublicDescription": "Cycles the Microcode Sequencer is busy. Available PDIST counters: 0", "SampleAfterValue": "500009", "UMask": "0x2" }, @@ -30,7 +31,7 @@ "Counter": "0,1,2,3", "EventCode": "0x61", "EventName": "DSB2MITE_SWITCHES.PENALTY_CYCLES", - "PublicDescription": "Decode Stream Buffer (DSB) is a Uop-cache that holds translations of previously fetched instructions that were decoded by the legacy x86 decode pipeline (MITE). This event counts fetch penalty cycles when a transition occurs from DSB to MITE.", + "PublicDescription": "Decode Stream Buffer (DSB) is a Uop-cache that holds translations of previously fetched instructions that were decoded by the legacy x86 decode pipeline (MITE). This event counts fetch penalty cycles when a transition occurs from DSB to MITE. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x2" }, @@ -41,7 +42,7 @@ "EventName": "FRONTEND_RETIRED.ANY_DSB_MISS", "MSRIndex": "0x3F7", "MSRValue": "0x1", - "PublicDescription": "Counts retired Instructions that experienced DSB (Decode stream buffer i.e. the decoded instruction-cache) miss.", + "PublicDescription": "Counts retired Instructions that experienced DSB (Decode stream buffer i.e. the decoded instruction-cache) miss. Available PDIST counters: 0", "SampleAfterValue": "100007", "UMask": "0x1" }, @@ -52,7 +53,7 @@ "EventName": "FRONTEND_RETIRED.DSB_MISS", "MSRIndex": "0x3F7", "MSRValue": "0x11", - "PublicDescription": "Number of retired Instructions that experienced a critical DSB (Decode stream buffer i.e. the decoded instruction-cache) miss. Critical means stalls were exposed to the back-end as a result of the DSB miss.", + "PublicDescription": "Number of retired Instructions that experienced a critical DSB (Decode stream buffer i.e. the decoded instruction-cache) miss. Critical means stalls were exposed to the back-end as a result of the DSB miss. Available PDIST counters: 0", "SampleAfterValue": "100007", "UMask": "0x1" }, @@ -63,7 +64,7 @@ "EventName": "FRONTEND_RETIRED.ITLB_MISS", "MSRIndex": "0x3F7", "MSRValue": "0x14", - "PublicDescription": "Counts retired Instructions that experienced iTLB (Instruction TLB) true miss.", + "PublicDescription": "Counts retired Instructions that experienced iTLB (Instruction TLB) true miss. Available PDIST counters: 0", "SampleAfterValue": "100007", "UMask": "0x1" }, @@ -74,7 +75,7 @@ "EventName": "FRONTEND_RETIRED.L1I_MISS", "MSRIndex": "0x3F7", "MSRValue": "0x12", - "PublicDescription": "Counts retired Instructions who experienced Instruction L1 Cache true miss.", + "PublicDescription": "Counts retired Instructions who experienced Instruction L1 Cache true miss. Available PDIST counters: 0", "SampleAfterValue": "100007", "UMask": "0x1" }, @@ -85,7 +86,7 @@ "EventName": "FRONTEND_RETIRED.L2_MISS", "MSRIndex": "0x3F7", "MSRValue": "0x13", - "PublicDescription": "Counts retired Instructions who experienced Instruction L2 Cache true miss.", + "PublicDescription": "Counts retired Instructions who experienced Instruction L2 Cache true miss. Available PDIST counters: 0", "SampleAfterValue": "100007", "UMask": "0x1" }, @@ -96,7 +97,7 @@ "EventName": "FRONTEND_RETIRED.LATENCY_GE_1", "MSRIndex": "0x3F7", "MSRValue": "0x600106", - "PublicDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of at least 1 cycle which was not interrupted by a back-end stall.", + "PublicDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of at least 1 cycle which was not interrupted by a back-end stall. Available PDIST counters: 0", "SampleAfterValue": "100007", "UMask": "0x1" }, @@ -107,7 +108,7 @@ "EventName": "FRONTEND_RETIRED.LATENCY_GE_128", "MSRIndex": "0x3F7", "MSRValue": "0x608006", - "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 128 cycles which was not interrupted by a back-end stall.", + "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 128 cycles which was not interrupted by a back-end stall. Available PDIST counters: 0", "SampleAfterValue": "100007", "UMask": "0x1" }, @@ -118,7 +119,7 @@ "EventName": "FRONTEND_RETIRED.LATENCY_GE_16", "MSRIndex": "0x3F7", "MSRValue": "0x601006", - "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 16 cycles. During this period the front-end delivered no uops.", + "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 16 cycles. During this period the front-end delivered no uops. Available PDIST counters: 0", "SampleAfterValue": "100007", "UMask": "0x1" }, @@ -129,7 +130,7 @@ "EventName": "FRONTEND_RETIRED.LATENCY_GE_2", "MSRIndex": "0x3F7", "MSRValue": "0x600206", - "PublicDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of at least 2 cycles which was not interrupted by a back-end stall.", + "PublicDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of at least 2 cycles which was not interrupted by a back-end stall. Available PDIST counters: 0", "SampleAfterValue": "100007", "UMask": "0x1" }, @@ -140,7 +141,7 @@ "EventName": "FRONTEND_RETIRED.LATENCY_GE_256", "MSRIndex": "0x3F7", "MSRValue": "0x610006", - "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 256 cycles which was not interrupted by a back-end stall.", + "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 256 cycles which was not interrupted by a back-end stall. Available PDIST counters: 0", "SampleAfterValue": "100007", "UMask": "0x1" }, @@ -151,7 +152,7 @@ "EventName": "FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1", "MSRIndex": "0x3F7", "MSRValue": "0x100206", - "PublicDescription": "Counts retired instructions that are delivered to the back-end after the front-end had at least 1 bubble-slot for a period of 2 cycles. A bubble-slot is an empty issue-pipeline slot while there was no RAT stall.", + "PublicDescription": "Counts retired instructions that are delivered to the back-end after the front-end had at least 1 bubble-slot for a period of 2 cycles. A bubble-slot is an empty issue-pipeline slot while there was no RAT stall. Available PDIST counters: 0", "SampleAfterValue": "100007", "UMask": "0x1" }, @@ -162,7 +163,7 @@ "EventName": "FRONTEND_RETIRED.LATENCY_GE_32", "MSRIndex": "0x3F7", "MSRValue": "0x602006", - "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 32 cycles. During this period the front-end delivered no uops.", + "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 32 cycles. During this period the front-end delivered no uops. Available PDIST counters: 0", "SampleAfterValue": "100007", "UMask": "0x1" }, @@ -173,7 +174,7 @@ "EventName": "FRONTEND_RETIRED.LATENCY_GE_4", "MSRIndex": "0x3F7", "MSRValue": "0x600406", - "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 4 cycles which was not interrupted by a back-end stall.", + "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 4 cycles which was not interrupted by a back-end stall. Available PDIST counters: 0", "SampleAfterValue": "100007", "UMask": "0x1" }, @@ -184,7 +185,7 @@ "EventName": "FRONTEND_RETIRED.LATENCY_GE_512", "MSRIndex": "0x3F7", "MSRValue": "0x620006", - "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 512 cycles which was not interrupted by a back-end stall.", + "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 512 cycles which was not interrupted by a back-end stall. Available PDIST counters: 0", "SampleAfterValue": "100007", "UMask": "0x1" }, @@ -195,7 +196,7 @@ "EventName": "FRONTEND_RETIRED.LATENCY_GE_64", "MSRIndex": "0x3F7", "MSRValue": "0x604006", - "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 64 cycles which was not interrupted by a back-end stall.", + "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 64 cycles which was not interrupted by a back-end stall. Available PDIST counters: 0", "SampleAfterValue": "100007", "UMask": "0x1" }, @@ -206,7 +207,7 @@ "EventName": "FRONTEND_RETIRED.LATENCY_GE_8", "MSRIndex": "0x3F7", "MSRValue": "0x600806", - "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 8 cycles. During this period the front-end delivered no uops.", + "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 8 cycles. During this period the front-end delivered no uops. Available PDIST counters: 0", "SampleAfterValue": "100007", "UMask": "0x1" }, @@ -217,6 +218,7 @@ "EventName": "FRONTEND_RETIRED.MS_FLOWS", "MSRIndex": "0x3F7", "MSRValue": "0x8", + "PublicDescription": "FRONTEND_RETIRED.MS_FLOWS Available PDIST counters: 0", "SampleAfterValue": "100007", "UMask": "0x1" }, @@ -227,7 +229,7 @@ "EventName": "FRONTEND_RETIRED.STLB_MISS", "MSRIndex": "0x3F7", "MSRValue": "0x15", - "PublicDescription": "Counts retired Instructions that experienced STLB (2nd level TLB) true miss.", + "PublicDescription": "Counts retired Instructions that experienced STLB (2nd level TLB) true miss. Available PDIST counters: 0", "SampleAfterValue": "100007", "UMask": "0x1" }, @@ -238,6 +240,7 @@ "EventName": "FRONTEND_RETIRED.UNKNOWN_BRANCH", "MSRIndex": "0x3F7", "MSRValue": "0x17", + "PublicDescription": "FRONTEND_RETIRED.UNKNOWN_BRANCH Available PDIST counters: 0", "SampleAfterValue": "100007", "UMask": "0x1" }, @@ -246,7 +249,7 @@ "Counter": "0,1,2,3", "EventCode": "0x80", "EventName": "ICACHE_DATA.STALLS", - "PublicDescription": "Counts cycles where a code line fetch is stalled due to an L1 instruction cache miss. The decode pipeline works at a 32 Byte granularity.", + "PublicDescription": "Counts cycles where a code line fetch is stalled due to an L1 instruction cache miss. The decode pipeline works at a 32 Byte granularity. Available PDIST counters: 0", "SampleAfterValue": "500009", "UMask": "0x4" }, @@ -257,6 +260,7 @@ "EdgeDetect": "1", "EventCode": "0x80", "EventName": "ICACHE_DATA.STALL_PERIODS", + "PublicDescription": "ICACHE_DATA.STALL_PERIODS Available PDIST counters: 0", "SampleAfterValue": "500009", "UMask": "0x4" }, @@ -265,7 +269,7 @@ "Counter": "0,1,2,3", "EventCode": "0x83", "EventName": "ICACHE_TAG.STALLS", - "PublicDescription": "Counts cycles where a code fetch is stalled due to L1 instruction cache tag miss.", + "PublicDescription": "Counts cycles where a code fetch is stalled due to L1 instruction cache tag miss. Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0x4" }, @@ -275,7 +279,7 @@ "CounterMask": "1", "EventCode": "0x79", "EventName": "IDQ.DSB_CYCLES_ANY", - "PublicDescription": "Counts the number of cycles uops were delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path.", + "PublicDescription": "Counts the number of cycles uops were delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path. Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x8" }, @@ -285,7 +289,7 @@ "CounterMask": "6", "EventCode": "0x79", "EventName": "IDQ.DSB_CYCLES_OK", - "PublicDescription": "Counts the number of cycles where optimal number of uops was delivered to the Instruction Decode Queue (IDQ) from the DSB (Decode Stream Buffer) path. Count includes uops that may 'bypass' the IDQ.", + "PublicDescription": "Counts the number of cycles where optimal number of uops was delivered to the Instruction Decode Queue (IDQ) from the DSB (Decode Stream Buffer) path. Count includes uops that may 'bypass' the IDQ. Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x8" }, @@ -294,7 +298,7 @@ "Counter": "0,1,2,3", "EventCode": "0x79", "EventName": "IDQ.DSB_UOPS", - "PublicDescription": "Counts the number of uops delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path.", + "PublicDescription": "Counts the number of uops delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path. Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x8" }, @@ -304,7 +308,7 @@ "CounterMask": "1", "EventCode": "0x79", "EventName": "IDQ.MITE_CYCLES_ANY", - "PublicDescription": "Counts the number of cycles uops were delivered to the Instruction Decode Queue (IDQ) from the MITE (legacy decode pipeline) path. During these cycles uops are not being delivered from the Decode Stream Buffer (DSB).", + "PublicDescription": "Counts the number of cycles uops were delivered to the Instruction Decode Queue (IDQ) from the MITE (legacy decode pipeline) path. During these cycles uops are not being delivered from the Decode Stream Buffer (DSB). Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x4" }, @@ -314,7 +318,7 @@ "CounterMask": "6", "EventCode": "0x79", "EventName": "IDQ.MITE_CYCLES_OK", - "PublicDescription": "Counts the number of cycles where optimal number of uops was delivered to the Instruction Decode Queue (IDQ) from the MITE (legacy decode pipeline) path. During these cycles uops are not being delivered from the Decode Stream Buffer (DSB).", + "PublicDescription": "Counts the number of cycles where optimal number of uops was delivered to the Instruction Decode Queue (IDQ) from the MITE (legacy decode pipeline) path. During these cycles uops are not being delivered from the Decode Stream Buffer (DSB). Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x4" }, @@ -323,7 +327,7 @@ "Counter": "0,1,2,3", "EventCode": "0x79", "EventName": "IDQ.MITE_UOPS", - "PublicDescription": "Counts the number of uops delivered to Instruction Decode Queue (IDQ) from the MITE path. This also means that uops are not being delivered from the Decode Stream Buffer (DSB).", + "PublicDescription": "Counts the number of uops delivered to Instruction Decode Queue (IDQ) from the MITE path. This also means that uops are not being delivered from the Decode Stream Buffer (DSB). Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x4" }, @@ -333,7 +337,7 @@ "CounterMask": "1", "EventCode": "0x79", "EventName": "IDQ.MS_CYCLES_ANY", - "PublicDescription": "Counts cycles during which uops are being delivered to Instruction Decode Queue (IDQ) while the Microcode Sequencer (MS) is busy. Uops maybe initiated by Decode Stream Buffer (DSB) or MITE.", + "PublicDescription": "Counts cycles during which uops are being delivered to Instruction Decode Queue (IDQ) while the Microcode Sequencer (MS) is busy. Uops maybe initiated by Decode Stream Buffer (DSB) or MITE. Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x20" }, @@ -344,7 +348,7 @@ "EdgeDetect": "1", "EventCode": "0x79", "EventName": "IDQ.MS_SWITCHES", - "PublicDescription": "Number of switches from DSB (Decode Stream Buffer) or MITE (legacy decode pipeline) to the Microcode Sequencer.", + "PublicDescription": "Number of switches from DSB (Decode Stream Buffer) or MITE (legacy decode pipeline) to the Microcode Sequencer. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x20" }, @@ -353,7 +357,7 @@ "Counter": "0,1,2,3", "EventCode": "0x79", "EventName": "IDQ.MS_UOPS", - "PublicDescription": "Counts the total number of uops delivered by the Microcode Sequencer (MS).", + "PublicDescription": "Counts the total number of uops delivered by the Microcode Sequencer (MS). Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x20" }, @@ -362,7 +366,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0x9c", "EventName": "IDQ_BUBBLES.CORE", - "PublicDescription": "Counts the number of uops not delivered to by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle. [This event is alias to IDQ_UOPS_NOT_DELIVERED.CORE]", + "PublicDescription": "Counts the number of uops not delivered to by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle. [This event is alias to IDQ_UOPS_NOT_DELIVERED.CORE] Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x1" }, @@ -372,7 +376,7 @@ "CounterMask": "6", "EventCode": "0x9c", "EventName": "IDQ_BUBBLES.CYCLES_0_UOPS_DELIV.CORE", - "PublicDescription": "Counts the number of cycles when no uops were delivered by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle. [This event is alias to IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE]", + "PublicDescription": "Counts the number of cycles when no uops were delivered by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle. [This event is alias to IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE] Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x1" }, @@ -383,7 +387,7 @@ "EventCode": "0x9c", "EventName": "IDQ_BUBBLES.CYCLES_FE_WAS_OK", "Invert": "1", - "PublicDescription": "Counts the number of cycles when the optimal number of uops were delivered by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle. [This event is alias to IDQ_UOPS_NOT_DELIVERED.CYCLES_FE_WAS_OK]", + "PublicDescription": "Counts the number of cycles when the optimal number of uops were delivered by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle. [This event is alias to IDQ_UOPS_NOT_DELIVERED.CYCLES_FE_WAS_OK] Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x1" }, @@ -392,7 +396,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0x9c", "EventName": "IDQ_UOPS_NOT_DELIVERED.CORE", - "PublicDescription": "Counts the number of uops not delivered to by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle. [This event is alias to IDQ_BUBBLES.CORE]", + "PublicDescription": "Counts the number of uops not delivered to by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle. [This event is alias to IDQ_BUBBLES.CORE] Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x1" }, @@ -402,7 +406,7 @@ "CounterMask": "6", "EventCode": "0x9c", "EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE", - "PublicDescription": "Counts the number of cycles when no uops were delivered by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle. [This event is alias to IDQ_BUBBLES.CYCLES_0_UOPS_DELIV.CORE]", + "PublicDescription": "Counts the number of cycles when no uops were delivered by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle. [This event is alias to IDQ_BUBBLES.CYCLES_0_UOPS_DELIV.CORE] Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x1" }, @@ -413,7 +417,7 @@ "EventCode": "0x9c", "EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_FE_WAS_OK", "Invert": "1", - "PublicDescription": "Counts the number of cycles when the optimal number of uops were delivered by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle. [This event is alias to IDQ_BUBBLES.CYCLES_FE_WAS_OK]", + "PublicDescription": "Counts the number of cycles when the optimal number of uops were delivered by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle. [This event is alias to IDQ_BUBBLES.CYCLES_FE_WAS_OK] Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x1" } diff --git a/tools/perf/pmu-events/arch/x86/sapphirerapids/memory.json b/tools/perf/pmu-events/arch/x86/sapphirerapids/memory.json index 41d4120d4dae..7c3f9b76d367 100644 --- a/tools/perf/pmu-events/arch/x86/sapphirerapids/memory.json +++ b/tools/perf/pmu-events/arch/x86/sapphirerapids/memory.json @@ -5,6 +5,7 @@ "CounterMask": "6", "EventCode": "0xa3", "EventName": "CYCLE_ACTIVITY.STALLS_L3_MISS", + "PublicDescription": "Execution stalls while L3 cache miss demand load is outstanding. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x6" }, @@ -13,7 +14,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc3", "EventName": "MACHINE_CLEARS.MEMORY_ORDERING", - "PublicDescription": "Counts the number of Machine Clears detected dye to memory ordering. Memory Ordering Machine Clears may apply when a memory read may not conform to the memory ordering rules of the x86 architecture", + "PublicDescription": "Counts the number of Machine Clears detected dye to memory ordering. Memory Ordering Machine Clears may apply when a memory read may not conform to the memory ordering rules of the x86 architecture Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x2" }, @@ -23,6 +24,7 @@ "CounterMask": "2", "EventCode": "0x47", "EventName": "MEMORY_ACTIVITY.CYCLES_L1D_MISS", + "PublicDescription": "Cycles while L1 cache miss demand load is outstanding. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x2" }, @@ -32,6 +34,7 @@ "CounterMask": "3", "EventCode": "0x47", "EventName": "MEMORY_ACTIVITY.STALLS_L1D_MISS", + "PublicDescription": "Execution stalls while L1 cache miss demand load is outstanding. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x3" }, @@ -41,7 +44,7 @@ "CounterMask": "5", "EventCode": "0x47", "EventName": "MEMORY_ACTIVITY.STALLS_L2_MISS", - "PublicDescription": "Execution stalls while L2 cache miss demand cacheable load request is outstanding (will not count for uncacheable demand requests e.g. bus lock).", + "PublicDescription": "Execution stalls while L2 cache miss demand cacheable load request is outstanding (will not count for uncacheable demand requests e.g. bus lock). Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x5" }, @@ -51,7 +54,7 @@ "CounterMask": "9", "EventCode": "0x47", "EventName": "MEMORY_ACTIVITY.STALLS_L3_MISS", - "PublicDescription": "Execution stalls while L3 cache miss demand cacheable load request is outstanding (will not count for uncacheable demand requests e.g. bus lock).", + "PublicDescription": "Execution stalls while L3 cache miss demand cacheable load request is outstanding (will not count for uncacheable demand requests e.g. bus lock). Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x9" }, @@ -169,17 +172,62 @@ "Data_LA": "1", "EventCode": "0xcd", "EventName": "MEM_TRANS_RETIRED.STORE_SAMPLE", - "PublicDescription": "Counts Retired memory accesses with at least 1 store operation. This PEBS event is the precisely-distributed (PDist) trigger covering all stores uops for sampling by the PEBS Store Latency Facility. The facility is described in Intel SDM Volume 3 section 19.9.8", + "PublicDescription": "Counts Retired memory accesses with at least 1 store operation. This PEBS event is the precisely-distributed (PDist) trigger covering all stores uops for sampling by the PEBS Store Latency Facility. The facility is described in Intel SDM Volume 3 section 19.9.8 Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x2" }, { + "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were supplied by DRAM.", + "Counter": "0,1,2,3", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.DEMAND_CODE_RD.DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x73C000004", + "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were supplied by DRAM. Available PDIST counters: 0", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were not supplied by the local socket's L1, L2, or L3 caches.", "Counter": "0,1,2,3", "EventCode": "0x2A,0x2B", "EventName": "OCR.DEMAND_CODE_RD.L3_MISS", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x3FBFC00004", + "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were not supplied by the local socket's L1, L2, or L3 caches. Available PDIST counters: 0", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were supplied by DRAM attached to this socket, unless in Sub NUMA Cluster(SNC) Mode. In SNC Mode counts only those DRAM accesses that are controlled by the close SNC Cluster.", + "Counter": "0,1,2,3", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.DEMAND_CODE_RD.LOCAL_DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x104000004", + "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were supplied by DRAM attached to this socket, unless in Sub NUMA Cluster(SNC) Mode. In SNC Mode counts only those DRAM accesses that are controlled by the close SNC Cluster. Available PDIST counters: 0", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were supplied by DRAM on a distant memory controller of this socket when the system is in SNC (sub-NUMA cluster) mode.", + "Counter": "0,1,2,3", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.DEMAND_CODE_RD.SNC_DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x708000004", + "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were supplied by DRAM on a distant memory controller of this socket when the system is in SNC (sub-NUMA cluster) mode. Available PDIST counters: 0", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts demand data reads that were supplied by DRAM.", + "Counter": "0,1,2,3", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.DEMAND_DATA_RD.DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x73C000001", + "PublicDescription": "Counts demand data reads that were supplied by DRAM. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -190,6 +238,51 @@ "EventName": "OCR.DEMAND_DATA_RD.L3_MISS", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x3FBFC00001", + "PublicDescription": "Counts demand data reads that were not supplied by the local socket's L1, L2, or L3 caches. Available PDIST counters: 0", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts demand data reads that were supplied by DRAM attached to this socket, unless in Sub NUMA Cluster(SNC) Mode. In SNC Mode counts only those DRAM accesses that are controlled by the close SNC Cluster.", + "Counter": "0,1,2,3", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.DEMAND_DATA_RD.LOCAL_DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x104000001", + "PublicDescription": "Counts demand data reads that were supplied by DRAM attached to this socket, unless in Sub NUMA Cluster(SNC) Mode. In SNC Mode counts only those DRAM accesses that are controlled by the close SNC Cluster. Available PDIST counters: 0", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts demand data reads that were supplied by DRAM attached to another socket.", + "Counter": "0,1,2,3", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.DEMAND_DATA_RD.REMOTE_DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x730000001", + "PublicDescription": "Counts demand data reads that were supplied by DRAM attached to another socket. Available PDIST counters: 0", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts demand data reads that were supplied by DRAM on a distant memory controller of this socket when the system is in SNC (sub-NUMA cluster) mode.", + "Counter": "0,1,2,3", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.DEMAND_DATA_RD.SNC_DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x708000001", + "PublicDescription": "Counts demand data reads that were supplied by DRAM on a distant memory controller of this socket when the system is in SNC (sub-NUMA cluster) mode. Available PDIST counters: 0", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts demand reads for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that were supplied by DRAM.", + "Counter": "0,1,2,3", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.DEMAND_RFO.DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x73C000002", + "PublicDescription": "Counts demand reads for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that were supplied by DRAM. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -200,6 +293,29 @@ "EventName": "OCR.DEMAND_RFO.L3_MISS", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x3F3FC00002", + "PublicDescription": "Counts demand reads for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that were not supplied by the local socket's L1, L2, or L3 caches. Available PDIST counters: 0", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts demand reads for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that were supplied by DRAM attached to this socket, unless in Sub NUMA Cluster(SNC) Mode. In SNC Mode counts only those DRAM accesses that are controlled by the close SNC Cluster.", + "Counter": "0,1,2,3", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.DEMAND_RFO.LOCAL_DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x104000002", + "PublicDescription": "Counts demand reads for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that were supplied by DRAM attached to this socket, unless in Sub NUMA Cluster(SNC) Mode. In SNC Mode counts only those DRAM accesses that are controlled by the close SNC Cluster. Available PDIST counters: 0", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts demand reads for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that were supplied by DRAM on a distant memory controller of this socket when the system is in SNC (sub-NUMA cluster) mode.", + "Counter": "0,1,2,3", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.DEMAND_RFO.SNC_DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x708000002", + "PublicDescription": "Counts demand reads for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that were supplied by DRAM on a distant memory controller of this socket when the system is in SNC (sub-NUMA cluster) mode. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -210,6 +326,7 @@ "EventName": "OCR.HWPF_L3.L3_MISS", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x94002380", + "PublicDescription": "Counts hardware prefetches to the L3 only that missed the local socket's L1, L2, and L3 caches. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -220,6 +337,18 @@ "EventName": "OCR.HWPF_L3.L3_MISS_LOCAL", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x84002380", + "PublicDescription": "Counts hardware prefetches to the L3 only that were not supplied by the local socket's L1, L2, or L3 caches and the cacheline is homed locally. Available PDIST counters: 0", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by DRAM.", + "Counter": "0,1,2,3", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.READS_TO_CORE.DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x73C004477", + "PublicDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by DRAM. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -230,6 +359,7 @@ "EventName": "OCR.READS_TO_CORE.L3_MISS", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x3F3FC04477", + "PublicDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were not supplied by the local socket's L1, L2, or L3 caches. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -240,6 +370,7 @@ "EventName": "OCR.READS_TO_CORE.L3_MISS_LOCAL", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x3F04C04477", + "PublicDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were not supplied by the local socket's L1, L2, or L3 caches and the cacheline is homed locally. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -250,6 +381,62 @@ "EventName": "OCR.READS_TO_CORE.L3_MISS_LOCAL_SOCKET", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x70CC04477", + "PublicDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that missed the L3 Cache and were supplied by the local socket (DRAM or PMM), whether or not in Sub NUMA Cluster(SNC) Mode. In SNC Mode counts PMM or DRAM accesses that are controlled by the close or distant SNC Cluster. It does not count misses to the L3 which go to Local CXL Type 2 Memory or Local Non DRAM. Available PDIST counters: 0", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by DRAM attached to this socket, unless in Sub NUMA Cluster(SNC) Mode. In SNC Mode counts only those DRAM accesses that are controlled by the close SNC Cluster.", + "Counter": "0,1,2,3", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.READS_TO_CORE.LOCAL_DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x104004477", + "PublicDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by DRAM attached to this socket, unless in Sub NUMA Cluster(SNC) Mode. In SNC Mode counts only those DRAM accesses that are controlled by the close SNC Cluster. Available PDIST counters: 0", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by DRAM attached to this socket, whether or not in Sub NUMA Cluster(SNC) Mode. In SNC Mode counts DRAM accesses that are controlled by the close or distant SNC Cluster.", + "Counter": "0,1,2,3", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.READS_TO_CORE.LOCAL_SOCKET_DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x70C004477", + "PublicDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by DRAM attached to this socket, whether or not in Sub NUMA Cluster(SNC) Mode. In SNC Mode counts DRAM accesses that are controlled by the close or distant SNC Cluster. Available PDIST counters: 0", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by DRAM attached to another socket.", + "Counter": "0,1,2,3", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.READS_TO_CORE.REMOTE_DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x730004477", + "PublicDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by DRAM attached to another socket. Available PDIST counters: 0", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by DRAM or PMM attached to another socket.", + "Counter": "0,1,2,3", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.READS_TO_CORE.REMOTE_MEMORY", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x733004477", + "PublicDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by DRAM or PMM attached to another socket. Available PDIST counters: 0", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by DRAM on a distant memory controller of this socket when the system is in SNC (sub-NUMA cluster) mode.", + "Counter": "0,1,2,3", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.READS_TO_CORE.SNC_DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x708004477", + "PublicDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by DRAM on a distant memory controller of this socket when the system is in SNC (sub-NUMA cluster) mode. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -260,6 +447,7 @@ "EventName": "OCR.STREAMING_WR.L3_MISS", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x94000800", + "PublicDescription": "Counts streaming stores that missed the local socket's L1, L2, and L3 caches. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -270,6 +458,18 @@ "EventName": "OCR.STREAMING_WR.L3_MISS_LOCAL", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x84000800", + "PublicDescription": "Counts streaming stores that were not supplied by the local socket's L1, L2, or L3 caches and the cacheline is homed locally. Available PDIST counters: 0", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts Demand RFOs, ItoM's, PREFECTHW's, Hardware RFO Prefetches to the L1/L2 and Streaming stores that likely resulted in a store to Memory (DRAM or PMM)", + "Counter": "0,1,2,3", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.WRITE_ESTIMATE.MEMORY", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0xFBFF80822", + "PublicDescription": "Counts Demand RFOs, ItoM's, PREFECTHW's, Hardware RFO Prefetches to the L1/L2 and Streaming stores that likely resulted in a store to Memory (DRAM or PMM) Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -278,6 +478,7 @@ "Counter": "0,1,2,3", "EventCode": "0x21", "EventName": "OFFCORE_REQUESTS.L3_MISS_DEMAND_DATA_RD", + "PublicDescription": "Counts demand data read requests that miss the L3 cache. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x10" }, @@ -286,7 +487,7 @@ "Counter": "0,1,2,3", "EventCode": "0x20", "EventName": "OFFCORE_REQUESTS_OUTSTANDING.L3_MISS_DEMAND_DATA_RD", - "PublicDescription": "For every cycle, increments by the number of demand data read requests pending that are known to have missed the L3 cache. Note that this does not capture all elapsed cycles while requests are outstanding - only cycles from when the requests were known by the requesting core to have missed the L3 cache.", + "PublicDescription": "For every cycle, increments by the number of demand data read requests pending that are known to have missed the L3 cache. Note that this does not capture all elapsed cycles while requests are outstanding - only cycles from when the requests were known by the requesting core to have missed the L3 cache. Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x10" }, @@ -295,7 +496,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc9", "EventName": "RTM_RETIRED.ABORTED", - "PublicDescription": "Counts the number of times RTM abort was triggered.", + "PublicDescription": "Counts the number of times RTM abort was triggered. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x4" }, @@ -304,7 +505,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc9", "EventName": "RTM_RETIRED.ABORTED_EVENTS", - "PublicDescription": "Counts the number of times an RTM execution aborted due to none of the previous 3 categories (e.g. interrupt).", + "PublicDescription": "Counts the number of times an RTM execution aborted due to none of the previous 3 categories (e.g. interrupt). Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x80" }, @@ -313,7 +514,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc9", "EventName": "RTM_RETIRED.ABORTED_MEM", - "PublicDescription": "Counts the number of times an RTM execution aborted due to various memory events (e.g. read/write capacity and conflicts).", + "PublicDescription": "Counts the number of times an RTM execution aborted due to various memory events (e.g. read/write capacity and conflicts). Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x8" }, @@ -322,7 +523,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc9", "EventName": "RTM_RETIRED.ABORTED_MEMTYPE", - "PublicDescription": "Counts the number of times an RTM execution aborted due to incompatible memory type.", + "PublicDescription": "Counts the number of times an RTM execution aborted due to incompatible memory type. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x40" }, @@ -331,7 +532,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc9", "EventName": "RTM_RETIRED.ABORTED_UNFRIENDLY", - "PublicDescription": "Counts the number of times an RTM execution aborted due to HLE-unfriendly instructions.", + "PublicDescription": "Counts the number of times an RTM execution aborted due to HLE-unfriendly instructions. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x20" }, @@ -340,7 +541,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc9", "EventName": "RTM_RETIRED.COMMIT", - "PublicDescription": "Counts the number of times RTM commit succeeded.", + "PublicDescription": "Counts the number of times RTM commit succeeded. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x2" }, @@ -349,7 +550,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc9", "EventName": "RTM_RETIRED.START", - "PublicDescription": "Counts the number of times we entered an RTM region. Does not count nested transactions.", + "PublicDescription": "Counts the number of times we entered an RTM region. Does not count nested transactions. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -358,7 +559,7 @@ "Counter": "0,1,2,3", "EventCode": "0x54", "EventName": "TX_MEM.ABORT_CAPACITY_READ", - "PublicDescription": "Speculatively counts the number of Transactional Synchronization Extensions (TSX) aborts due to a data capacity limitation for transactional reads", + "PublicDescription": "Speculatively counts the number of Transactional Synchronization Extensions (TSX) aborts due to a data capacity limitation for transactional reads Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x80" }, @@ -367,7 +568,7 @@ "Counter": "0,1,2,3", "EventCode": "0x54", "EventName": "TX_MEM.ABORT_CAPACITY_WRITE", - "PublicDescription": "Speculatively counts the number of Transactional Synchronization Extensions (TSX) aborts due to a data capacity limitation for transactional writes.", + "PublicDescription": "Speculatively counts the number of Transactional Synchronization Extensions (TSX) aborts due to a data capacity limitation for transactional writes. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x2" }, @@ -376,7 +577,7 @@ "Counter": "0,1,2,3", "EventCode": "0x54", "EventName": "TX_MEM.ABORT_CONFLICT", - "PublicDescription": "Counts the number of times a TSX line had a cache conflict.", + "PublicDescription": "Counts the number of times a TSX line had a cache conflict. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" } diff --git a/tools/perf/pmu-events/arch/x86/sapphirerapids/other.json b/tools/perf/pmu-events/arch/x86/sapphirerapids/other.json index 05d8f14956ee..a58d65556609 100644 --- a/tools/perf/pmu-events/arch/x86/sapphirerapids/other.json +++ b/tools/perf/pmu-events/arch/x86/sapphirerapids/other.json @@ -4,404 +4,28 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc1", "EventName": "ASSISTS.PAGE_FAULT", + "PublicDescription": "ASSISTS.PAGE_FAULT Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x8" }, { - "BriefDescription": "Counts the cycles where the AMX (Advance Matrix Extension) unit is busy performing an operation.", - "Counter": "0,1,2,3,4,5,6,7", - "EventCode": "0xb7", - "EventName": "EXE.AMX_BUSY", - "SampleAfterValue": "2000003", - "UMask": "0x2" - }, - { - "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that have any type of response.", - "Counter": "0,1,2,3", - "EventCode": "0x2A,0x2B", - "EventName": "OCR.DEMAND_CODE_RD.ANY_RESPONSE", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x10004", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were supplied by DRAM.", - "Counter": "0,1,2,3", - "EventCode": "0x2A,0x2B", - "EventName": "OCR.DEMAND_CODE_RD.DRAM", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x73C000004", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were supplied by DRAM attached to this socket, unless in Sub NUMA Cluster(SNC) Mode. In SNC Mode counts only those DRAM accesses that are controlled by the close SNC Cluster.", - "Counter": "0,1,2,3", - "EventCode": "0x2A,0x2B", - "EventName": "OCR.DEMAND_CODE_RD.LOCAL_DRAM", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x104000004", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were supplied by DRAM on a distant memory controller of this socket when the system is in SNC (sub-NUMA cluster) mode.", - "Counter": "0,1,2,3", - "EventCode": "0x2A,0x2B", - "EventName": "OCR.DEMAND_CODE_RD.SNC_DRAM", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x708000004", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts demand data reads that have any type of response.", - "Counter": "0,1,2,3", - "EventCode": "0x2A,0x2B", - "EventName": "OCR.DEMAND_DATA_RD.ANY_RESPONSE", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x10001", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts demand data reads that were supplied by DRAM.", - "Counter": "0,1,2,3", - "EventCode": "0x2A,0x2B", - "EventName": "OCR.DEMAND_DATA_RD.DRAM", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x73C000001", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts demand data reads that were supplied by DRAM attached to this socket, unless in Sub NUMA Cluster(SNC) Mode. In SNC Mode counts only those DRAM accesses that are controlled by the close SNC Cluster.", - "Counter": "0,1,2,3", - "EventCode": "0x2A,0x2B", - "EventName": "OCR.DEMAND_DATA_RD.LOCAL_DRAM", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x104000001", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts demand data reads that were supplied by PMM attached to this socket, whether or not in Sub NUMA Cluster(SNC) Mode. In SNC Mode counts PMM accesses that are controlled by the close or distant SNC Cluster.", - "Counter": "0,1,2,3", - "EventCode": "0x2A,0x2B", - "EventName": "OCR.DEMAND_DATA_RD.LOCAL_SOCKET_PMM", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x700C00001", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts demand data reads that were supplied by PMM.", - "Counter": "0,1,2,3", - "EventCode": "0x2A,0x2B", - "EventName": "OCR.DEMAND_DATA_RD.PMM", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x703C00001", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts demand data reads that were supplied by DRAM attached to another socket.", - "Counter": "0,1,2,3", - "EventCode": "0x2A,0x2B", - "EventName": "OCR.DEMAND_DATA_RD.REMOTE_DRAM", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x730000001", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts demand data reads that were supplied by PMM attached to another socket.", - "Counter": "0,1,2,3", - "EventCode": "0x2A,0x2B", - "EventName": "OCR.DEMAND_DATA_RD.REMOTE_PMM", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x703000001", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts demand data reads that were supplied by DRAM on a distant memory controller of this socket when the system is in SNC (sub-NUMA cluster) mode.", - "Counter": "0,1,2,3", - "EventCode": "0x2A,0x2B", - "EventName": "OCR.DEMAND_DATA_RD.SNC_DRAM", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x708000001", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts demand reads for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that have any type of response.", - "Counter": "0,1,2,3", - "EventCode": "0x2A,0x2B", - "EventName": "OCR.DEMAND_RFO.ANY_RESPONSE", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x3F3FFC0002", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts demand reads for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that were supplied by DRAM.", - "Counter": "0,1,2,3", - "EventCode": "0x2A,0x2B", - "EventName": "OCR.DEMAND_RFO.DRAM", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x73C000002", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts demand reads for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that were supplied by DRAM attached to this socket, unless in Sub NUMA Cluster(SNC) Mode. In SNC Mode counts only those DRAM accesses that are controlled by the close SNC Cluster.", - "Counter": "0,1,2,3", - "EventCode": "0x2A,0x2B", - "EventName": "OCR.DEMAND_RFO.LOCAL_DRAM", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x104000002", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts demand reads for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that were supplied by DRAM on a distant memory controller of this socket when the system is in SNC (sub-NUMA cluster) mode.", - "Counter": "0,1,2,3", - "EventCode": "0x2A,0x2B", - "EventName": "OCR.DEMAND_RFO.SNC_DRAM", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x708000002", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts data load hardware prefetch requests to the L1 data cache that have any type of response.", - "Counter": "0,1,2,3", - "EventCode": "0x2A,0x2B", - "EventName": "OCR.HWPF_L1D.ANY_RESPONSE", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x10400", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts hardware prefetches (which bring data to L2) that have any type of response.", - "Counter": "0,1,2,3", - "EventCode": "0x2A,0x2B", - "EventName": "OCR.HWPF_L2.ANY_RESPONSE", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x10070", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts hardware prefetches to the L3 only that have any type of response.", - "Counter": "0,1,2,3", - "EventCode": "0x2A,0x2B", - "EventName": "OCR.HWPF_L3.ANY_RESPONSE", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x12380", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts hardware prefetches to the L3 only that were not supplied by the local socket's L1, L2, or L3 caches and the cacheline was homed in a remote socket.", - "Counter": "0,1,2,3", - "EventCode": "0x2A,0x2B", - "EventName": "OCR.HWPF_L3.REMOTE", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x90002380", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts writebacks of modified cachelines and streaming stores that have any type of response.", - "Counter": "0,1,2,3", - "EventCode": "0x2A,0x2B", - "EventName": "OCR.MODIFIED_WRITE.ANY_RESPONSE", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x10808", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that have any type of response.", - "Counter": "0,1,2,3", - "EventCode": "0x2A,0x2B", - "EventName": "OCR.READS_TO_CORE.ANY_RESPONSE", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x3F3FFC4477", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by DRAM.", - "Counter": "0,1,2,3", - "EventCode": "0x2A,0x2B", - "EventName": "OCR.READS_TO_CORE.DRAM", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x73C004477", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by DRAM attached to this socket, unless in Sub NUMA Cluster(SNC) Mode. In SNC Mode counts only those DRAM accesses that are controlled by the close SNC Cluster.", - "Counter": "0,1,2,3", - "EventCode": "0x2A,0x2B", - "EventName": "OCR.READS_TO_CORE.LOCAL_DRAM", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x104004477", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by DRAM attached to this socket, whether or not in Sub NUMA Cluster(SNC) Mode. In SNC Mode counts DRAM accesses that are controlled by the close or distant SNC Cluster.", - "Counter": "0,1,2,3", - "EventCode": "0x2A,0x2B", - "EventName": "OCR.READS_TO_CORE.LOCAL_SOCKET_DRAM", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x70C004477", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by PMM attached to this socket, whether or not in Sub NUMA Cluster(SNC) Mode. In SNC Mode counts PMM accesses that are controlled by the close or distant SNC Cluster.", - "Counter": "0,1,2,3", - "EventCode": "0x2A,0x2B", - "EventName": "OCR.READS_TO_CORE.LOCAL_SOCKET_PMM", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x700C04477", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were not supplied by the local socket's L1, L2, or L3 caches and were supplied by a remote socket.", - "Counter": "0,1,2,3", - "EventCode": "0x2A,0x2B", - "EventName": "OCR.READS_TO_CORE.REMOTE", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x3F33004477", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by DRAM attached to another socket.", - "Counter": "0,1,2,3", - "EventCode": "0x2A,0x2B", - "EventName": "OCR.READS_TO_CORE.REMOTE_DRAM", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x730004477", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by DRAM or PMM attached to another socket.", - "Counter": "0,1,2,3", - "EventCode": "0x2A,0x2B", - "EventName": "OCR.READS_TO_CORE.REMOTE_MEMORY", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x733004477", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by PMM attached to another socket.", - "Counter": "0,1,2,3", - "EventCode": "0x2A,0x2B", - "EventName": "OCR.READS_TO_CORE.REMOTE_PMM", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x703004477", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by DRAM on a distant memory controller of this socket when the system is in SNC (sub-NUMA cluster) mode.", - "Counter": "0,1,2,3", - "EventCode": "0x2A,0x2B", - "EventName": "OCR.READS_TO_CORE.SNC_DRAM", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x708004477", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { "BriefDescription": "Counts streaming stores that have any type of response.", "Counter": "0,1,2,3", "EventCode": "0x2A,0x2B", "EventName": "OCR.STREAMING_WR.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x10800", + "PublicDescription": "Counts streaming stores that have any type of response. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, { - "BriefDescription": "Counts Demand RFOs, ItoM's, PREFECTHW's, Hardware RFO Prefetches to the L1/L2 and Streaming stores that likely resulted in a store to Memory (DRAM or PMM)", - "Counter": "0,1,2,3", - "EventCode": "0x2A,0x2B", - "EventName": "OCR.WRITE_ESTIMATE.MEMORY", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0xFBFF80822", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Cycles when Reservation Station (RS) is empty for the thread.", - "Counter": "0,1,2,3,4,5,6,7", - "EventCode": "0xa5", - "EventName": "RS.EMPTY", - "PublicDescription": "Counts cycles during which the reservation station (RS) is empty for this logical processor. This is usually caused when the front-end pipeline runs into starvation periods (e.g. branch mispredictions or i-cache misses)", - "SampleAfterValue": "1000003", - "UMask": "0x7" - }, - { - "BriefDescription": "Counts end of periods where the Reservation Station (RS) was empty.", - "Counter": "0,1,2,3,4,5,6,7", - "CounterMask": "1", - "EdgeDetect": "1", - "EventCode": "0xa5", - "EventName": "RS.EMPTY_COUNT", - "Invert": "1", - "PublicDescription": "Counts end of periods where the Reservation Station (RS) was empty. Could be useful to closely sample on front-end latency issues (see the FRONTEND_RETIRED event of designated precise events)", - "SampleAfterValue": "100003", - "UMask": "0x7" - }, - { - "BriefDescription": "Cycles when Reservation Station (RS) is empty due to a resource in the back-end", - "Counter": "0,1,2,3,4,5,6,7", - "EventCode": "0xa5", - "EventName": "RS.EMPTY_RESOURCE", - "SampleAfterValue": "1000003", - "UMask": "0x1" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event RS.EMPTY_COUNT", - "Counter": "0,1,2,3,4,5,6,7", - "CounterMask": "1", - "Deprecated": "1", - "EdgeDetect": "1", - "EventCode": "0xa5", - "EventName": "RS_EMPTY.COUNT", - "Invert": "1", - "SampleAfterValue": "100003", - "UMask": "0x7" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event RS.EMPTY", - "Counter": "0,1,2,3,4,5,6,7", - "Deprecated": "1", - "EventCode": "0xa5", - "EventName": "RS_EMPTY.CYCLES", - "SampleAfterValue": "1000003", - "UMask": "0x7" - }, - { "BriefDescription": "Cycles the uncore cannot take further requests", "Counter": "0,1,2,3", "CounterMask": "1", "EventCode": "0x2d", "EventName": "XQ.FULL_CYCLES", - "PublicDescription": "number of cycles when the thread is active and the uncore cannot take any further requests (for example prefetches, loads or stores initiated by the Core that miss the L2 cache).", + "PublicDescription": "number of cycles when the thread is active and the uncore cannot take any further requests (for example prefetches, loads or stores initiated by the Core that miss the L2 cache). Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x1" } diff --git a/tools/perf/pmu-events/arch/x86/sapphirerapids/pipeline.json b/tools/perf/pmu-events/arch/x86/sapphirerapids/pipeline.json index 50cacfbbc7cf..00b05a77c289 100644 --- a/tools/perf/pmu-events/arch/x86/sapphirerapids/pipeline.json +++ b/tools/perf/pmu-events/arch/x86/sapphirerapids/pipeline.json @@ -6,6 +6,7 @@ "Deprecated": "1", "EventCode": "0xb0", "EventName": "ARITH.DIVIDER_ACTIVE", + "PublicDescription": "This event is deprecated. Refer to new event ARITH.DIV_ACTIVE Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x9" }, @@ -15,7 +16,7 @@ "CounterMask": "1", "EventCode": "0xb0", "EventName": "ARITH.DIV_ACTIVE", - "PublicDescription": "Counts cycles when divide unit is busy executing divide or square root operations. Accounts for integer and floating-point operations.", + "PublicDescription": "Counts cycles when divide unit is busy executing divide or square root operations. Accounts for integer and floating-point operations. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x9" }, @@ -26,6 +27,7 @@ "Deprecated": "1", "EventCode": "0xb0", "EventName": "ARITH.FP_DIVIDER_ACTIVE", + "PublicDescription": "This event is deprecated. Refer to new event ARITH.FPDIV_ACTIVE Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x1" }, @@ -35,6 +37,7 @@ "CounterMask": "1", "EventCode": "0xb0", "EventName": "ARITH.IDIV_ACTIVE", + "PublicDescription": "This event counts the cycles the integer divider is busy. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x8" }, @@ -45,6 +48,7 @@ "Deprecated": "1", "EventCode": "0xb0", "EventName": "ARITH.INT_DIVIDER_ACTIVE", + "PublicDescription": "This event is deprecated. Refer to new event ARITH.IDIV_ACTIVE Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x8" }, @@ -53,7 +57,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc1", "EventName": "ASSISTS.ANY", - "PublicDescription": "Counts the number of occurrences where a microcode assist is invoked by hardware. Examples include AD (page Access Dirty), FP and AVX related assists.", + "PublicDescription": "Counts the number of occurrences where a microcode assist is invoked by hardware. Examples include AD (page Access Dirty), FP and AVX related assists. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1b" }, @@ -62,7 +66,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.ALL_BRANCHES", - "PublicDescription": "Counts all branch instructions retired.", + "PublicDescription": "Counts all branch instructions retired. Available PDIST counters: 0", "SampleAfterValue": "400009" }, { @@ -70,7 +74,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.COND", - "PublicDescription": "Counts conditional branch instructions retired.", + "PublicDescription": "Counts conditional branch instructions retired. Available PDIST counters: 0", "SampleAfterValue": "400009", "UMask": "0x11" }, @@ -79,7 +83,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.COND_NTAKEN", - "PublicDescription": "Counts not taken branch instructions retired.", + "PublicDescription": "Counts not taken branch instructions retired. Available PDIST counters: 0", "SampleAfterValue": "400009", "UMask": "0x10" }, @@ -88,7 +92,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.COND_TAKEN", - "PublicDescription": "Counts taken conditional branch instructions retired.", + "PublicDescription": "Counts taken conditional branch instructions retired. Available PDIST counters: 0", "SampleAfterValue": "400009", "UMask": "0x1" }, @@ -97,7 +101,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.FAR_BRANCH", - "PublicDescription": "Counts far branch instructions retired.", + "PublicDescription": "Counts far branch instructions retired. Available PDIST counters: 0", "SampleAfterValue": "100007", "UMask": "0x40" }, @@ -106,7 +110,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.INDIRECT", - "PublicDescription": "Counts near indirect branch instructions retired excluding returns. TSX abort is an indirect branch.", + "PublicDescription": "Counts near indirect branch instructions retired excluding returns. TSX abort is an indirect branch. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x80" }, @@ -115,7 +119,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.NEAR_CALL", - "PublicDescription": "Counts both direct and indirect near call instructions retired.", + "PublicDescription": "Counts both direct and indirect near call instructions retired. Available PDIST counters: 0", "SampleAfterValue": "100007", "UMask": "0x2" }, @@ -124,7 +128,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.NEAR_RETURN", - "PublicDescription": "Counts return instructions retired.", + "PublicDescription": "Counts return instructions retired. Available PDIST counters: 0", "SampleAfterValue": "100007", "UMask": "0x8" }, @@ -133,7 +137,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.NEAR_TAKEN", - "PublicDescription": "Counts taken branch instructions retired.", + "PublicDescription": "Counts taken branch instructions retired. Available PDIST counters: 0", "SampleAfterValue": "400009", "UMask": "0x20" }, @@ -142,7 +146,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.ALL_BRANCHES", - "PublicDescription": "Counts all the retired branch instructions that were mispredicted by the processor. A branch misprediction occurs when the processor incorrectly predicts the destination of the branch. When the misprediction is discovered at execution, all the instructions executed in the wrong (speculative) path must be discarded, and the processor must start fetching from the correct path.", + "PublicDescription": "Counts all the retired branch instructions that were mispredicted by the processor. A branch misprediction occurs when the processor incorrectly predicts the destination of the branch. When the misprediction is discovered at execution, all the instructions executed in the wrong (speculative) path must be discarded, and the processor must start fetching from the correct path. Available PDIST counters: 0", "SampleAfterValue": "400009" }, { @@ -150,7 +154,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.COND", - "PublicDescription": "Counts mispredicted conditional branch instructions retired.", + "PublicDescription": "Counts mispredicted conditional branch instructions retired. Available PDIST counters: 0", "SampleAfterValue": "400009", "UMask": "0x11" }, @@ -159,7 +163,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.COND_NTAKEN", - "PublicDescription": "Counts the number of conditional branch instructions retired that were mispredicted and the branch direction was not taken.", + "PublicDescription": "Counts the number of conditional branch instructions retired that were mispredicted and the branch direction was not taken. Available PDIST counters: 0", "SampleAfterValue": "400009", "UMask": "0x10" }, @@ -168,7 +172,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.COND_TAKEN", - "PublicDescription": "Counts taken conditional mispredicted branch instructions retired.", + "PublicDescription": "Counts taken conditional mispredicted branch instructions retired. Available PDIST counters: 0", "SampleAfterValue": "400009", "UMask": "0x1" }, @@ -177,7 +181,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.INDIRECT", - "PublicDescription": "Counts miss-predicted near indirect branch instructions retired excluding returns. TSX abort is an indirect branch.", + "PublicDescription": "Counts miss-predicted near indirect branch instructions retired excluding returns. TSX abort is an indirect branch. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x80" }, @@ -186,7 +190,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.INDIRECT_CALL", - "PublicDescription": "Counts retired mispredicted indirect (near taken) CALL instructions, including both register and memory indirect.", + "PublicDescription": "Counts retired mispredicted indirect (near taken) CALL instructions, including both register and memory indirect. Available PDIST counters: 0", "SampleAfterValue": "400009", "UMask": "0x2" }, @@ -195,7 +199,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.NEAR_TAKEN", - "PublicDescription": "Counts number of near branch instructions retired that were mispredicted and taken.", + "PublicDescription": "Counts number of near branch instructions retired that were mispredicted and taken. Available PDIST counters: 0", "SampleAfterValue": "400009", "UMask": "0x20" }, @@ -204,7 +208,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.RET", - "PublicDescription": "This is a non-precise version (that is, does not use PEBS) of the event that counts mispredicted return instructions retired.", + "PublicDescription": "This is a non-precise version (that is, does not use PEBS) of the event that counts mispredicted return instructions retired. Available PDIST counters: 0", "SampleAfterValue": "100007", "UMask": "0x8" }, @@ -213,7 +217,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xec", "EventName": "CPU_CLK_UNHALTED.C01", - "PublicDescription": "Counts core clocks when the thread is in the C0.1 light-weight slower wakeup time but more power saving optimized state. This state can be entered via the TPAUSE or UMWAIT instructions.", + "PublicDescription": "Counts core clocks when the thread is in the C0.1 light-weight slower wakeup time but more power saving optimized state. This state can be entered via the TPAUSE or UMWAIT instructions. Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x10" }, @@ -222,7 +226,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xec", "EventName": "CPU_CLK_UNHALTED.C02", - "PublicDescription": "Counts core clocks when the thread is in the C0.2 light-weight faster wakeup time but less power saving optimized state. This state can be entered via the TPAUSE or UMWAIT instructions.", + "PublicDescription": "Counts core clocks when the thread is in the C0.2 light-weight faster wakeup time but less power saving optimized state. This state can be entered via the TPAUSE or UMWAIT instructions. Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x20" }, @@ -231,7 +235,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xec", "EventName": "CPU_CLK_UNHALTED.C0_WAIT", - "PublicDescription": "Counts core clocks when the thread is in the C0.1 or C0.2 power saving optimized states (TPAUSE or UMWAIT instructions) or running the PAUSE instruction.", + "PublicDescription": "Counts core clocks when the thread is in the C0.1 or C0.2 power saving optimized states (TPAUSE or UMWAIT instructions) or running the PAUSE instruction. Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x70" }, @@ -240,7 +244,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xec", "EventName": "CPU_CLK_UNHALTED.DISTRIBUTED", - "PublicDescription": "This event distributes cycle counts between active hyperthreads, i.e., those in C0. A hyperthread becomes inactive when it executes the HLT or MWAIT instructions. If all other hyperthreads are inactive (or disabled or do not exist), all counts are attributed to this hyperthread. To obtain the full count when the Core is active, sum the counts from each hyperthread.", + "PublicDescription": "This event distributes cycle counts between active hyperthreads, i.e., those in C0. A hyperthread becomes inactive when it executes the HLT or MWAIT instructions. If all other hyperthreads are inactive (or disabled or do not exist), all counts are attributed to this hyperthread. To obtain the full count when the Core is active, sum the counts from each hyperthread. Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x2" }, @@ -249,7 +253,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0x3c", "EventName": "CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE", - "PublicDescription": "Counts Core crystal clock cycles when current thread is unhalted and the other thread is halted.", + "PublicDescription": "Counts Core crystal clock cycles when current thread is unhalted and the other thread is halted. Available PDIST counters: 0", "SampleAfterValue": "25003", "UMask": "0x2" }, @@ -258,6 +262,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xec", "EventName": "CPU_CLK_UNHALTED.PAUSE", + "PublicDescription": "CPU_CLK_UNHALTED.PAUSE Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x40" }, @@ -268,6 +273,7 @@ "EdgeDetect": "1", "EventCode": "0xec", "EventName": "CPU_CLK_UNHALTED.PAUSE_INST", + "PublicDescription": "CPU_CLK_UNHALTED.PAUSE_INST Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x40" }, @@ -276,7 +282,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0x3c", "EventName": "CPU_CLK_UNHALTED.REF_DISTRIBUTED", - "PublicDescription": "This event distributes Core crystal clock cycle counts between active hyperthreads, i.e., those in C0 sleep-state. A hyperthread becomes inactive when it executes the HLT or MWAIT instructions. If one thread is active in a core, all counts are attributed to this hyperthread. To obtain the full count when the Core is active, sum the counts from each hyperthread.", + "PublicDescription": "This event distributes Core crystal clock cycle counts between active hyperthreads, i.e., those in C0 sleep-state. A hyperthread becomes inactive when it executes the HLT or MWAIT instructions. If one thread is active in a core, all counts are attributed to this hyperthread. To obtain the full count when the Core is active, sum the counts from each hyperthread. Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x8" }, @@ -293,7 +299,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0x3c", "EventName": "CPU_CLK_UNHALTED.REF_TSC_P", - "PublicDescription": "Counts the number of reference cycles when the core is not in a halt state. The core enters the halt state when it is running the HLT instruction or the MWAIT instruction. This event is not affected by core frequency changes (for example, P states, TM2 transitions) but has the same incrementing frequency as the time stamp counter. This event can approximate elapsed time while the core was not in a halt state. It is counted on a dedicated fixed counter, leaving the four (eight when Hyperthreading is disabled) programmable counters available for other events. Note: On all current platforms this event stops counting during 'throttling (TM)' states duty off periods the processor is 'halted'. The counter update is done at a lower clock rate then the core clock the overflow status bit for this counter may appear 'sticky'. After the counter has overflowed and software clears the overflow status bit and resets the counter to less than MAX. The reset value to the counter is not clocked immediately so the overflow status bit will flip 'high (1)' and generate another PMI (if enabled) after which the reset value gets clocked into the counter. Therefore, software will get the interrupt, read the overflow status bit '1 for bit 34 while the counter value is less than MAX. Software should ignore this case.", + "PublicDescription": "Counts the number of reference cycles when the core is not in a halt state. The core enters the halt state when it is running the HLT instruction or the MWAIT instruction. This event is not affected by core frequency changes (for example, P states, TM2 transitions) but has the same incrementing frequency as the time stamp counter. This event can approximate elapsed time while the core was not in a halt state. It is counted on a dedicated fixed counter, leaving the four (eight when Hyperthreading is disabled) programmable counters available for other events. Note: On all current platforms this event stops counting during 'throttling (TM)' states duty off periods the processor is 'halted'. The counter update is done at a lower clock rate then the core clock the overflow status bit for this counter may appear 'sticky'. After the counter has overflowed and software clears the overflow status bit and resets the counter to less than MAX. The reset value to the counter is not clocked immediately so the overflow status bit will flip 'high (1)' and generate another PMI (if enabled) after which the reset value gets clocked into the counter. Therefore, software will get the interrupt, read the overflow status bit '1 for bit 34 while the counter value is less than MAX. Software should ignore this case. Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x1" }, @@ -310,7 +316,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0x3c", "EventName": "CPU_CLK_UNHALTED.THREAD_P", - "PublicDescription": "This is an architectural event that counts the number of thread cycles while the thread is not in a halt state. The thread enters the halt state when it is running the HLT instruction. The core frequency may change from time to time due to power or thermal throttling. For this reason, this event may have a changing ratio with regards to wall clock time.", + "PublicDescription": "This is an architectural event that counts the number of thread cycles while the thread is not in a halt state. The thread enters the halt state when it is running the HLT instruction. The core frequency may change from time to time due to power or thermal throttling. For this reason, this event may have a changing ratio with regards to wall clock time. Available PDIST counters: 0", "SampleAfterValue": "2000003" }, { @@ -319,6 +325,7 @@ "CounterMask": "8", "EventCode": "0xa3", "EventName": "CYCLE_ACTIVITY.CYCLES_L1D_MISS", + "PublicDescription": "Cycles while L1 cache miss demand load is outstanding. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x8" }, @@ -328,6 +335,7 @@ "CounterMask": "1", "EventCode": "0xa3", "EventName": "CYCLE_ACTIVITY.CYCLES_L2_MISS", + "PublicDescription": "Cycles while L2 cache miss demand load is outstanding. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x1" }, @@ -337,6 +345,7 @@ "CounterMask": "16", "EventCode": "0xa3", "EventName": "CYCLE_ACTIVITY.CYCLES_MEM_ANY", + "PublicDescription": "Cycles while memory subsystem has an outstanding load. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x10" }, @@ -346,6 +355,7 @@ "CounterMask": "12", "EventCode": "0xa3", "EventName": "CYCLE_ACTIVITY.STALLS_L1D_MISS", + "PublicDescription": "Execution stalls while L1 cache miss demand load is outstanding. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0xc" }, @@ -355,6 +365,7 @@ "CounterMask": "5", "EventCode": "0xa3", "EventName": "CYCLE_ACTIVITY.STALLS_L2_MISS", + "PublicDescription": "Execution stalls while L2 cache miss demand load is outstanding. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x5" }, @@ -364,15 +375,25 @@ "CounterMask": "4", "EventCode": "0xa3", "EventName": "CYCLE_ACTIVITY.STALLS_TOTAL", + "PublicDescription": "Total execution stalls. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x4" }, { + "BriefDescription": "Counts the cycles where the AMX (Advance Matrix Extension) unit is busy performing an operation.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xb7", + "EventName": "EXE.AMX_BUSY", + "PublicDescription": "Counts the cycles where the AMX (Advance Matrix Extension) unit is busy performing an operation. Available PDIST counters: 0", + "SampleAfterValue": "2000003", + "UMask": "0x2" + }, + { "BriefDescription": "Cycles total of 1 uop is executed on all ports and Reservation Station was not empty.", "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xa6", "EventName": "EXE_ACTIVITY.1_PORTS_UTIL", - "PublicDescription": "Counts cycles during which a total of 1 uop was executed on all ports and Reservation Station (RS) was not empty.", + "PublicDescription": "Counts cycles during which a total of 1 uop was executed on all ports and Reservation Station (RS) was not empty. Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x2" }, @@ -381,6 +402,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xa6", "EventName": "EXE_ACTIVITY.2_3_PORTS_UTIL", + "PublicDescription": "Cycles total of 2 or 3 uops are executed on all ports and Reservation Station (RS) was not empty. Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0xc" }, @@ -389,7 +411,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xa6", "EventName": "EXE_ACTIVITY.2_PORTS_UTIL", - "PublicDescription": "Counts cycles during which a total of 2 uops were executed on all ports and Reservation Station (RS) was not empty.", + "PublicDescription": "Counts cycles during which a total of 2 uops were executed on all ports and Reservation Station (RS) was not empty. Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x4" }, @@ -398,7 +420,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xa6", "EventName": "EXE_ACTIVITY.3_PORTS_UTIL", - "PublicDescription": "Cycles total of 3 uops are executed on all ports and Reservation Station (RS) was not empty.", + "PublicDescription": "Cycles total of 3 uops are executed on all ports and Reservation Station (RS) was not empty. Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x8" }, @@ -407,7 +429,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xa6", "EventName": "EXE_ACTIVITY.4_PORTS_UTIL", - "PublicDescription": "Cycles total of 4 uops are executed on all ports and Reservation Station (RS) was not empty.", + "PublicDescription": "Cycles total of 4 uops are executed on all ports and Reservation Station (RS) was not empty. Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x10" }, @@ -417,6 +439,7 @@ "CounterMask": "5", "EventCode": "0xa6", "EventName": "EXE_ACTIVITY.BOUND_ON_LOADS", + "PublicDescription": "Execution stalls while memory subsystem has an outstanding load. Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x21" }, @@ -426,7 +449,7 @@ "CounterMask": "2", "EventCode": "0xa6", "EventName": "EXE_ACTIVITY.BOUND_ON_STORES", - "PublicDescription": "Counts cycles where the Store Buffer was full and no loads caused an execution stall.", + "PublicDescription": "Counts cycles where the Store Buffer was full and no loads caused an execution stall. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x40" }, @@ -435,7 +458,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xa6", "EventName": "EXE_ACTIVITY.EXE_BOUND_0_PORTS", - "PublicDescription": "Number of cycles total of 0 uops executed on all ports, Reservation Station (RS) was not empty, the Store Buffer (SB) was not full and there was no outstanding load.", + "PublicDescription": "Number of cycles total of 0 uops executed on all ports, Reservation Station (RS) was not empty, the Store Buffer (SB) was not full and there was no outstanding load. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x80" }, @@ -444,7 +467,7 @@ "Counter": "0,1,2,3", "EventCode": "0x75", "EventName": "INST_DECODED.DECODERS", - "PublicDescription": "Number of decoders utilized in a cycle when the MITE (legacy decode pipeline) fetches instructions.", + "PublicDescription": "Number of decoders utilized in a cycle when the MITE (legacy decode pipeline) fetches instructions. Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x1" }, @@ -452,7 +475,7 @@ "BriefDescription": "Number of instructions retired. Fixed Counter - architectural event", "Counter": "Fixed counter 0", "EventName": "INST_RETIRED.ANY", - "PublicDescription": "Counts the number of X86 instructions retired - an Architectural PerfMon event. Counting continues during hardware interrupts, traps, and inside interrupt handlers. Notes: INST_RETIRED.ANY is counted by a designated fixed counter freeing up programmable counters to count other events. INST_RETIRED.ANY_P is counted by a programmable counter.", + "PublicDescription": "Counts the number of X86 instructions retired - an Architectural PerfMon event. Counting continues during hardware interrupts, traps, and inside interrupt handlers. Notes: INST_RETIRED.ANY is counted by a designated fixed counter freeing up programmable counters to count other events. INST_RETIRED.ANY_P is counted by a programmable counter. Available PDIST counters: 32", "SampleAfterValue": "2000003", "UMask": "0x1" }, @@ -469,6 +492,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc0", "EventName": "INST_RETIRED.MACRO_FUSED", + "PublicDescription": "INST_RETIRED.MACRO_FUSED Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x10" }, @@ -477,7 +501,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc0", "EventName": "INST_RETIRED.NOP", - "PublicDescription": "Counts all retired NOP or ENDBR32/64 instructions", + "PublicDescription": "Counts all retired NOP or ENDBR32/64 instructions Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x2" }, @@ -485,7 +509,7 @@ "BriefDescription": "Precise instruction retired with PEBS precise-distribution", "Counter": "Fixed counter 0", "EventName": "INST_RETIRED.PREC_DIST", - "PublicDescription": "A version of INST_RETIRED that allows for a precise distribution of samples across instructions retired. It utilizes the Precise Distribution of Instructions Retired (PDIR++) feature to fix bias in how retired instructions get sampled. Use on Fixed Counter 0.", + "PublicDescription": "A version of INST_RETIRED that allows for a precise distribution of samples across instructions retired. It utilizes the Precise Distribution of Instructions Retired (PDIR++) feature to fix bias in how retired instructions get sampled. Use on Fixed Counter 0. Available PDIST counters: 32", "SampleAfterValue": "2000003", "UMask": "0x1" }, @@ -494,7 +518,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc0", "EventName": "INST_RETIRED.REP_ITERATION", - "PublicDescription": "Number of iterations of Repeat (REP) string retired instructions such as MOVS, CMPS, and SCAS. Each has a byte, word, and doubleword version and string instructions can be repeated using a repetition prefix, REP, that allows their architectural execution to be repeated a number of times as specified by the RCX register. Note the number of iterations is implementation-dependent.", + "PublicDescription": "Number of iterations of Repeat (REP) string retired instructions such as MOVS, CMPS, and SCAS. Each has a byte, word, and doubleword version and string instructions can be repeated using a repetition prefix, REP, that allows their architectural execution to be repeated a number of times as specified by the RCX register. Note the number of iterations is implementation-dependent. Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x8" }, @@ -505,7 +529,7 @@ "EdgeDetect": "1", "EventCode": "0xad", "EventName": "INT_MISC.CLEARS_COUNT", - "PublicDescription": "Counts the number of speculative clears due to any type of branch misprediction or machine clears", + "PublicDescription": "Counts the number of speculative clears due to any type of branch misprediction or machine clears Available PDIST counters: 0", "SampleAfterValue": "500009", "UMask": "0x1" }, @@ -514,7 +538,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xad", "EventName": "INT_MISC.CLEAR_RESTEER_CYCLES", - "PublicDescription": "Cycles after recovery from a branch misprediction or machine clear till the first uop is issued from the resteered path.", + "PublicDescription": "Cycles after recovery from a branch misprediction or machine clear till the first uop is issued from the resteered path. Available PDIST counters: 0", "SampleAfterValue": "500009", "UMask": "0x80" }, @@ -523,6 +547,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xad", "EventName": "INT_MISC.MBA_STALLS", + "PublicDescription": "INT_MISC.MBA_STALLS Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x20" }, @@ -531,7 +556,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xad", "EventName": "INT_MISC.RECOVERY_CYCLES", - "PublicDescription": "Counts core cycles when the Resource allocator was stalled due to recovery from an earlier branch misprediction or machine clear event.", + "PublicDescription": "Counts core cycles when the Resource allocator was stalled due to recovery from an earlier branch misprediction or machine clear event. Available PDIST counters: 0", "SampleAfterValue": "500009", "UMask": "0x1" }, @@ -542,6 +567,7 @@ "EventName": "INT_MISC.UNKNOWN_BRANCH_CYCLES", "MSRIndex": "0x3F7", "MSRValue": "0x7", + "PublicDescription": "Bubble cycles of BAClear (Unknown Branch). Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x40" }, @@ -550,7 +576,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xad", "EventName": "INT_MISC.UOP_DROPPING", - "PublicDescription": "Estimated number of Top-down Microarchitecture Analysis slots that got dropped due to non front-end reasons", + "PublicDescription": "Estimated number of Top-down Microarchitecture Analysis slots that got dropped due to non front-end reasons Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x10" }, @@ -559,6 +585,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xe7", "EventName": "INT_VEC_RETIRED.128BIT", + "PublicDescription": "INT_VEC_RETIRED.128BIT Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x13" }, @@ -567,6 +594,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xe7", "EventName": "INT_VEC_RETIRED.256BIT", + "PublicDescription": "INT_VEC_RETIRED.256BIT Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0xac" }, @@ -575,7 +603,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xe7", "EventName": "INT_VEC_RETIRED.ADD_128", - "PublicDescription": "Number of retired integer ADD/SUB (regular or horizontal), SAD 128-bit vector instructions.", + "PublicDescription": "Number of retired integer ADD/SUB (regular or horizontal), SAD 128-bit vector instructions. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x3" }, @@ -584,7 +612,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xe7", "EventName": "INT_VEC_RETIRED.ADD_256", - "PublicDescription": "Number of retired integer ADD/SUB (regular or horizontal), SAD 256-bit vector instructions.", + "PublicDescription": "Number of retired integer ADD/SUB (regular or horizontal), SAD 256-bit vector instructions. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0xc" }, @@ -593,6 +621,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xe7", "EventName": "INT_VEC_RETIRED.MUL_256", + "PublicDescription": "INT_VEC_RETIRED.MUL_256 Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x80" }, @@ -601,6 +630,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xe7", "EventName": "INT_VEC_RETIRED.SHUFFLES", + "PublicDescription": "INT_VEC_RETIRED.SHUFFLES Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x40" }, @@ -609,6 +639,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xe7", "EventName": "INT_VEC_RETIRED.VNNI_128", + "PublicDescription": "INT_VEC_RETIRED.VNNI_128 Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x10" }, @@ -617,6 +648,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xe7", "EventName": "INT_VEC_RETIRED.VNNI_256", + "PublicDescription": "INT_VEC_RETIRED.VNNI_256 Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x20" }, @@ -625,7 +657,7 @@ "Counter": "0,1,2,3", "EventCode": "0x03", "EventName": "LD_BLOCKS.ADDRESS_ALIAS", - "PublicDescription": "Counts the number of times a load got blocked due to false dependencies in MOB due to partial compare on address.", + "PublicDescription": "Counts the number of times a load got blocked due to false dependencies in MOB due to partial compare on address. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x4" }, @@ -634,7 +666,7 @@ "Counter": "0,1,2,3", "EventCode": "0x03", "EventName": "LD_BLOCKS.NO_SR", - "PublicDescription": "Counts the number of times that split load operations are temporarily blocked because all resources for handling the split accesses are in use.", + "PublicDescription": "Counts the number of times that split load operations are temporarily blocked because all resources for handling the split accesses are in use. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x88" }, @@ -643,7 +675,7 @@ "Counter": "0,1,2,3", "EventCode": "0x03", "EventName": "LD_BLOCKS.STORE_FORWARD", - "PublicDescription": "Counts the number of times where store forwarding was prevented for a load operation. The most common case is a load blocked due to the address of memory access (partially) overlapping with a preceding uncompleted store. Note: See the table of not supported store forwards in the Optimization Guide.", + "PublicDescription": "Counts the number of times where store forwarding was prevented for a load operation. The most common case is a load blocked due to the address of memory access (partially) overlapping with a preceding uncompleted store. Note: See the table of not supported store forwards in the Optimization Guide. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x82" }, @@ -652,7 +684,7 @@ "Counter": "0,1,2,3", "EventCode": "0x4c", "EventName": "LOAD_HIT_PREFETCH.SWPF", - "PublicDescription": "Counts all not software-prefetch load dispatches that hit the fill buffer (FB) allocated for the software prefetch. It can also be incremented by some lock instructions. So it should only be used with profiling so that the locks can be excluded by ASM (Assembly File) inspection of the nearby instructions.", + "PublicDescription": "Counts all not software-prefetch load dispatches that hit the fill buffer (FB) allocated for the software prefetch. It can also be incremented by some lock instructions. So it should only be used with profiling so that the locks can be excluded by ASM (Assembly File) inspection of the nearby instructions. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -662,7 +694,7 @@ "CounterMask": "1", "EventCode": "0xa8", "EventName": "LSD.CYCLES_ACTIVE", - "PublicDescription": "Counts the cycles when at least one uop is delivered by the LSD (Loop-stream detector).", + "PublicDescription": "Counts the cycles when at least one uop is delivered by the LSD (Loop-stream detector). Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x1" }, @@ -672,7 +704,7 @@ "CounterMask": "6", "EventCode": "0xa8", "EventName": "LSD.CYCLES_OK", - "PublicDescription": "Counts the cycles when optimal number of uops is delivered by the LSD (Loop-stream detector).", + "PublicDescription": "Counts the cycles when optimal number of uops is delivered by the LSD (Loop-stream detector). Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x1" }, @@ -681,7 +713,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xa8", "EventName": "LSD.UOPS", - "PublicDescription": "Counts the number of uops delivered to the back-end by the LSD(Loop Stream Detector).", + "PublicDescription": "Counts the number of uops delivered to the back-end by the LSD(Loop Stream Detector). Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x1" }, @@ -692,7 +724,7 @@ "EdgeDetect": "1", "EventCode": "0xc3", "EventName": "MACHINE_CLEARS.COUNT", - "PublicDescription": "Counts the number of machine clears (nukes) of any type.", + "PublicDescription": "Counts the number of machine clears (nukes) of any type. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -701,7 +733,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc3", "EventName": "MACHINE_CLEARS.SMC", - "PublicDescription": "Counts self-modifying code (SMC) detected, which causes a machine clear.", + "PublicDescription": "Counts self-modifying code (SMC) detected, which causes a machine clear. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x4" }, @@ -710,7 +742,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xe0", "EventName": "MISC2_RETIRED.LFENCE", - "PublicDescription": "number of LFENCE retired instructions", + "PublicDescription": "number of LFENCE retired instructions Available PDIST counters: 0", "SampleAfterValue": "400009", "UMask": "0x20" }, @@ -719,7 +751,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xcc", "EventName": "MISC_RETIRED.LBR_INSERTS", - "PublicDescription": "Increments when an entry is added to the Last Branch Record (LBR) array (or removed from the array in case of RETURNs in call stack mode). The event requires LBR enable via IA32_DEBUGCTL MSR and branch type selection via MSR_LBR_SELECT.", + "PublicDescription": "Increments when an entry is added to the Last Branch Record (LBR) array (or removed from the array in case of RETURNs in call stack mode). The event requires LBR enable via IA32_DEBUGCTL MSR and branch type selection via MSR_LBR_SELECT. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x20" }, @@ -728,7 +760,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xa2", "EventName": "RESOURCE_STALLS.SB", - "PublicDescription": "Counts allocation stall cycles caused by the store buffer (SB) being full. This counts cycles that the pipeline back-end blocked uop delivery from the front-end.", + "PublicDescription": "Counts allocation stall cycles caused by the store buffer (SB) being full. This counts cycles that the pipeline back-end blocked uop delivery from the front-end. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x8" }, @@ -737,15 +769,69 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xa2", "EventName": "RESOURCE_STALLS.SCOREBOARD", + "PublicDescription": "Counts cycles where the pipeline is stalled due to serializing operations. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x2" }, { + "BriefDescription": "Cycles when Reservation Station (RS) is empty for the thread.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xa5", + "EventName": "RS.EMPTY", + "PublicDescription": "Counts cycles during which the reservation station (RS) is empty for this logical processor. This is usually caused when the front-end pipeline runs into starvation periods (e.g. branch mispredictions or i-cache misses) Available PDIST counters: 0", + "SampleAfterValue": "1000003", + "UMask": "0x7" + }, + { + "BriefDescription": "Counts end of periods where the Reservation Station (RS) was empty.", + "Counter": "0,1,2,3,4,5,6,7", + "CounterMask": "1", + "EdgeDetect": "1", + "EventCode": "0xa5", + "EventName": "RS.EMPTY_COUNT", + "Invert": "1", + "PublicDescription": "Counts end of periods where the Reservation Station (RS) was empty. Could be useful to closely sample on front-end latency issues (see the FRONTEND_RETIRED event of designated precise events) Available PDIST counters: 0", + "SampleAfterValue": "100003", + "UMask": "0x7" + }, + { + "BriefDescription": "Cycles when Reservation Station (RS) is empty due to a resource in the back-end", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xa5", + "EventName": "RS.EMPTY_RESOURCE", + "PublicDescription": "Cycles when Reservation Station (RS) is empty due to a resource in the back-end Available PDIST counters: 0", + "SampleAfterValue": "1000003", + "UMask": "0x1" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event RS.EMPTY_COUNT", + "Counter": "0,1,2,3,4,5,6,7", + "CounterMask": "1", + "Deprecated": "1", + "EdgeDetect": "1", + "EventCode": "0xa5", + "EventName": "RS_EMPTY.COUNT", + "Invert": "1", + "PublicDescription": "This event is deprecated. Refer to new event RS.EMPTY_COUNT Available PDIST counters: 0", + "SampleAfterValue": "100003", + "UMask": "0x7" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event RS.EMPTY", + "Counter": "0,1,2,3,4,5,6,7", + "Deprecated": "1", + "EventCode": "0xa5", + "EventName": "RS_EMPTY.CYCLES", + "PublicDescription": "This event is deprecated. Refer to new event RS.EMPTY Available PDIST counters: 0", + "SampleAfterValue": "1000003", + "UMask": "0x7" + }, + { "BriefDescription": "TMA slots where no uops were being issued due to lack of back-end resources.", "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xa4", "EventName": "TOPDOWN.BACKEND_BOUND_SLOTS", - "PublicDescription": "Number of slots in TMA method where no micro-operations were being issued from front-end to back-end of the machine due to lack of back-end resources.", + "PublicDescription": "Number of slots in TMA method where no micro-operations were being issued from front-end to back-end of the machine due to lack of back-end resources. Available PDIST counters: 0", "SampleAfterValue": "10000003", "UMask": "0x2" }, @@ -754,7 +840,7 @@ "Counter": "0", "EventCode": "0xa4", "EventName": "TOPDOWN.BAD_SPEC_SLOTS", - "PublicDescription": "Number of slots of TMA method that were wasted due to incorrect speculation. It covers all types of control-flow or data-related mis-speculations.", + "PublicDescription": "Number of slots of TMA method that were wasted due to incorrect speculation. It covers all types of control-flow or data-related mis-speculations. Available PDIST counters: 0", "SampleAfterValue": "10000003", "UMask": "0x4" }, @@ -763,7 +849,7 @@ "Counter": "0", "EventCode": "0xa4", "EventName": "TOPDOWN.BR_MISPREDICT_SLOTS", - "PublicDescription": "Number of TMA slots that were wasted due to incorrect speculation by (any type of) branch mispredictions. This event estimates number of speculative operations that were issued but not retired as well as the out-of-order engine recovery past a branch misprediction.", + "PublicDescription": "Number of TMA slots that were wasted due to incorrect speculation by (any type of) branch mispredictions. This event estimates number of speculative operations that were issued but not retired as well as the out-of-order engine recovery past a branch misprediction. Available PDIST counters: 0", "SampleAfterValue": "10000003", "UMask": "0x8" }, @@ -772,6 +858,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xa4", "EventName": "TOPDOWN.MEMORY_BOUND_SLOTS", + "PublicDescription": "TOPDOWN.MEMORY_BOUND_SLOTS Available PDIST counters: 0", "SampleAfterValue": "10000003", "UMask": "0x10" }, @@ -788,7 +875,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xa4", "EventName": "TOPDOWN.SLOTS_P", - "PublicDescription": "Counts the number of available slots for an unhalted logical processor. The event increments by machine-width of the narrowest pipeline as employed by the Top-down Microarchitecture Analysis method. The count is distributed among unhalted logical processors (hyper-threads) who share the same physical core.", + "PublicDescription": "Counts the number of available slots for an unhalted logical processor. The event increments by machine-width of the narrowest pipeline as employed by the Top-down Microarchitecture Analysis method. The count is distributed among unhalted logical processors (hyper-threads) who share the same physical core. Available PDIST counters: 0", "SampleAfterValue": "10000003", "UMask": "0x1" }, @@ -797,6 +884,7 @@ "Counter": "0,1,2,3", "EventCode": "0x76", "EventName": "UOPS_DECODED.DEC0_UOPS", + "PublicDescription": "UOPS_DECODED.DEC0_UOPS Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x1" }, @@ -805,7 +893,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xb2", "EventName": "UOPS_DISPATCHED.PORT_0", - "PublicDescription": "Number of uops dispatch to execution port 0.", + "PublicDescription": "Number of uops dispatch to execution port 0. Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x1" }, @@ -814,7 +902,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xb2", "EventName": "UOPS_DISPATCHED.PORT_1", - "PublicDescription": "Number of uops dispatch to execution port 1.", + "PublicDescription": "Number of uops dispatch to execution port 1. Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x2" }, @@ -823,7 +911,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xb2", "EventName": "UOPS_DISPATCHED.PORT_2_3_10", - "PublicDescription": "Number of uops dispatch to execution ports 2, 3 and 10", + "PublicDescription": "Number of uops dispatch to execution ports 2, 3 and 10 Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x4" }, @@ -832,7 +920,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xb2", "EventName": "UOPS_DISPATCHED.PORT_4_9", - "PublicDescription": "Number of uops dispatch to execution ports 4 and 9", + "PublicDescription": "Number of uops dispatch to execution ports 4 and 9 Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x10" }, @@ -841,7 +929,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xb2", "EventName": "UOPS_DISPATCHED.PORT_5_11", - "PublicDescription": "Number of uops dispatch to execution ports 5 and 11", + "PublicDescription": "Number of uops dispatch to execution ports 5 and 11 Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x20" }, @@ -850,7 +938,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xb2", "EventName": "UOPS_DISPATCHED.PORT_6", - "PublicDescription": "Number of uops dispatch to execution port 6.", + "PublicDescription": "Number of uops dispatch to execution port 6. Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x40" }, @@ -859,7 +947,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xb2", "EventName": "UOPS_DISPATCHED.PORT_7_8", - "PublicDescription": "Number of uops dispatch to execution ports 7 and 8.", + "PublicDescription": "Number of uops dispatch to execution ports 7 and 8. Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x80" }, @@ -868,7 +956,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xb1", "EventName": "UOPS_EXECUTED.CORE", - "PublicDescription": "Counts the number of uops executed from any thread.", + "PublicDescription": "Counts the number of uops executed from any thread. Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x2" }, @@ -878,7 +966,7 @@ "CounterMask": "1", "EventCode": "0xb1", "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_1", - "PublicDescription": "Counts cycles when at least 1 micro-op is executed from any thread on physical core.", + "PublicDescription": "Counts cycles when at least 1 micro-op is executed from any thread on physical core. Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x2" }, @@ -888,7 +976,7 @@ "CounterMask": "2", "EventCode": "0xb1", "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_2", - "PublicDescription": "Counts cycles when at least 2 micro-ops are executed from any thread on physical core.", + "PublicDescription": "Counts cycles when at least 2 micro-ops are executed from any thread on physical core. Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x2" }, @@ -898,7 +986,7 @@ "CounterMask": "3", "EventCode": "0xb1", "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_3", - "PublicDescription": "Counts cycles when at least 3 micro-ops are executed from any thread on physical core.", + "PublicDescription": "Counts cycles when at least 3 micro-ops are executed from any thread on physical core. Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x2" }, @@ -908,7 +996,7 @@ "CounterMask": "4", "EventCode": "0xb1", "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_4", - "PublicDescription": "Counts cycles when at least 4 micro-ops are executed from any thread on physical core.", + "PublicDescription": "Counts cycles when at least 4 micro-ops are executed from any thread on physical core. Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x2" }, @@ -918,7 +1006,7 @@ "CounterMask": "1", "EventCode": "0xb1", "EventName": "UOPS_EXECUTED.CYCLES_GE_1", - "PublicDescription": "Cycles where at least 1 uop was executed per-thread.", + "PublicDescription": "Cycles where at least 1 uop was executed per-thread. Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x1" }, @@ -928,7 +1016,7 @@ "CounterMask": "2", "EventCode": "0xb1", "EventName": "UOPS_EXECUTED.CYCLES_GE_2", - "PublicDescription": "Cycles where at least 2 uops were executed per-thread.", + "PublicDescription": "Cycles where at least 2 uops were executed per-thread. Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x1" }, @@ -938,7 +1026,7 @@ "CounterMask": "3", "EventCode": "0xb1", "EventName": "UOPS_EXECUTED.CYCLES_GE_3", - "PublicDescription": "Cycles where at least 3 uops were executed per-thread.", + "PublicDescription": "Cycles where at least 3 uops were executed per-thread. Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x1" }, @@ -948,7 +1036,7 @@ "CounterMask": "4", "EventCode": "0xb1", "EventName": "UOPS_EXECUTED.CYCLES_GE_4", - "PublicDescription": "Cycles where at least 4 uops were executed per-thread.", + "PublicDescription": "Cycles where at least 4 uops were executed per-thread. Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x1" }, @@ -959,7 +1047,7 @@ "EventCode": "0xb1", "EventName": "UOPS_EXECUTED.STALLS", "Invert": "1", - "PublicDescription": "Counts cycles during which no uops were dispatched from the Reservation Station (RS) per thread.", + "PublicDescription": "Counts cycles during which no uops were dispatched from the Reservation Station (RS) per thread. Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x1" }, @@ -971,6 +1059,7 @@ "EventCode": "0xb1", "EventName": "UOPS_EXECUTED.STALL_CYCLES", "Invert": "1", + "PublicDescription": "This event is deprecated. Refer to new event UOPS_EXECUTED.STALLS Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x1" }, @@ -979,6 +1068,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xb1", "EventName": "UOPS_EXECUTED.THREAD", + "PublicDescription": "Counts the number of uops to be executed per-thread each cycle. Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x1" }, @@ -987,7 +1077,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xb1", "EventName": "UOPS_EXECUTED.X87", - "PublicDescription": "Counts the number of x87 uops executed.", + "PublicDescription": "Counts the number of x87 uops executed. Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x10" }, @@ -996,7 +1086,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xae", "EventName": "UOPS_ISSUED.ANY", - "PublicDescription": "Counts the number of uops that the Resource Allocation Table (RAT) issues to the Reservation Station (RS).", + "PublicDescription": "Counts the number of uops that the Resource Allocation Table (RAT) issues to the Reservation Station (RS). Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x1" }, @@ -1006,6 +1096,7 @@ "CounterMask": "1", "EventCode": "0xae", "EventName": "UOPS_ISSUED.CYCLES", + "PublicDescription": "UOPS_ISSUED.CYCLES Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x1" }, @@ -1015,7 +1106,7 @@ "CounterMask": "1", "EventCode": "0xc2", "EventName": "UOPS_RETIRED.CYCLES", - "PublicDescription": "Counts cycles where at least one uop has retired.", + "PublicDescription": "Counts cycles where at least one uop has retired. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x2" }, @@ -1024,7 +1115,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc2", "EventName": "UOPS_RETIRED.HEAVY", - "PublicDescription": "Counts the number of retired micro-operations (uops) except the last uop of each instruction. An instruction that is decoded into less than two uops does not contribute to the count.", + "PublicDescription": "Counts the number of retired micro-operations (uops) except the last uop of each instruction. An instruction that is decoded into less than two uops does not contribute to the count. Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x1" }, @@ -1035,6 +1126,7 @@ "EventName": "UOPS_RETIRED.MS", "MSRIndex": "0x3F7", "MSRValue": "0x8", + "PublicDescription": "UOPS_RETIRED.MS Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x4" }, @@ -1043,7 +1135,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc2", "EventName": "UOPS_RETIRED.SLOTS", - "PublicDescription": "Counts the retirement slots used each cycle.", + "PublicDescription": "Counts the retirement slots used each cycle. Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x2" }, @@ -1054,7 +1146,7 @@ "EventCode": "0xc2", "EventName": "UOPS_RETIRED.STALLS", "Invert": "1", - "PublicDescription": "This event counts cycles without actually retired uops.", + "PublicDescription": "This event counts cycles without actually retired uops. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x2" }, @@ -1066,6 +1158,7 @@ "EventCode": "0xc2", "EventName": "UOPS_RETIRED.STALL_CYCLES", "Invert": "1", + "PublicDescription": "This event is deprecated. Refer to new event UOPS_RETIRED.STALLS Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x2" } diff --git a/tools/perf/pmu-events/arch/x86/sapphirerapids/spr-metrics.json b/tools/perf/pmu-events/arch/x86/sapphirerapids/spr-metrics.json index b59fae4a887d..fe3f288be10e 100644 --- a/tools/perf/pmu-events/arch/x86/sapphirerapids/spr-metrics.json +++ b/tools/perf/pmu-events/arch/x86/sapphirerapids/spr-metrics.json @@ -360,7 +360,7 @@ "ScaleUnit": "1per_instr" }, { - "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution ports for ALU operations", + "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution ports for ALU operations.", "MetricExpr": "(UOPS_DISPATCHED.PORT_0 + UOPS_DISPATCHED.PORT_1 + UOPS_DISPATCHED.PORT_5_11 + UOPS_DISPATCHED.PORT_6) / (5 * tma_info_core_core_clks)", "MetricGroup": "TopdownL5;tma_L5_group;tma_ports_utilized_3m_group", "MetricName": "tma_alu_op_utilization", @@ -372,7 +372,7 @@ "MetricExpr": "EXE.AMX_BUSY / tma_info_core_core_clks", "MetricGroup": "BvCB;Compute;HPC;Server;TopdownL3;tma_L3_group;tma_core_bound_group", "MetricName": "tma_amx_busy", - "MetricThreshold": "tma_amx_busy > 0.5 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_amx_busy > 0.5 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)", "ScaleUnit": "100%" }, { @@ -380,12 +380,12 @@ "MetricExpr": "78 * ASSISTS.ANY / tma_info_thread_slots", "MetricGroup": "BvIO;TopdownL4;tma_L4_group;tma_microcode_sequencer_group", "MetricName": "tma_assists", - "MetricThreshold": "tma_assists > 0.1 & tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1", + "MetricThreshold": "tma_assists > 0.1 & (tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1)", "PublicDescription": "This metric estimates fraction of slots the CPU retired uops delivered by the Microcode_Sequencer as a result of Assists. Assists are long sequences of uops that are required in certain corner-cases for operations that cannot be handled natively by the execution pipeline. For example; when working with very small floating point values (so-called Denormals); the FP units are not set up to perform these operations natively. Instead; a sequence of instructions to perform the computation on the Denormals is injected into the pipeline. Since these microcode sequences might be dozens of uops long; Assists can be extremely deleterious to performance and they can be avoided in many cases. Sample with: ASSISTS.ANY", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates fraction of slots the CPU retired uops as a result of handing SSE to AVX* or AVX* to SSE transition Assists", + "BriefDescription": "This metric estimates fraction of slots the CPU retired uops as a result of handing SSE to AVX* or AVX* to SSE transition Assists.", "MetricExpr": "63 * ASSISTS.SSE_AVX_MIX / tma_info_thread_slots", "MetricGroup": "HPC;TopdownL5;tma_L5_group;tma_assists_group", "MetricName": "tma_avx_assists", @@ -395,7 +395,7 @@ { "BriefDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend", "DefaultMetricgroupName": "TopdownL1", - "MetricExpr": "topdown\\-be\\-bound / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * slots", + "MetricExpr": "topdown\\-be\\-bound / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * tma_info_thread_slots", "MetricGroup": "BvOB;Default;TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_backend_bound", "MetricThreshold": "tma_backend_bound > 0.2", @@ -411,12 +411,12 @@ "MetricName": "tma_bad_speculation", "MetricThreshold": "tma_bad_speculation > 0.15", "MetricgroupNoGroup": "TopdownL1;Default", - "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example", + "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.", "ScaleUnit": "100%" }, { "BriefDescription": "Total pipeline cost of instruction fetch related bottlenecks by large code footprint programs (i-side cache; TLB and BTB misses)", - "MetricExpr": "100 * tma_fetch_latency * (tma_itlb_misses + tma_icache_misses + tma_unknown_branches) / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches)", + "MetricExpr": "100 * tma_fetch_latency * (tma_itlb_misses + tma_icache_misses + tma_unknown_branches) / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches)", "MetricGroup": "BigFootprint;BvBC;Fed;Frontend;IcMiss;MemoryTLB", "MetricName": "tma_bottleneck_big_code", "MetricThreshold": "tma_bottleneck_big_code > 20" @@ -431,7 +431,7 @@ }, { "BriefDescription": "Total pipeline cost of external Memory- or Cache-Bandwidth related bottlenecks", - "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_mem_bandwidth / (tma_mem_bandwidth + tma_mem_latency)) + tma_memory_bound * (tma_l3_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_sq_full / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_memory_bound * (tma_l1_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_fb_full / (tma_dtlb_load + tma_store_fwd_blk + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_fb_full)))", + "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_mem_bandwidth / (tma_mem_bandwidth + tma_mem_latency)) + tma_memory_bound * (tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_sq_full / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_fb_full / (tma_dtlb_load + tma_fb_full + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)))", "MetricGroup": "BvMB;Mem;MemoryBW;Offcore;tma_issueBW", "MetricName": "tma_bottleneck_cache_memory_bandwidth", "MetricThreshold": "tma_bottleneck_cache_memory_bandwidth > 20", @@ -439,7 +439,7 @@ }, { "BriefDescription": "Total pipeline cost of external Memory- or Cache-Latency related bottlenecks", - "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_mem_latency / (tma_mem_bandwidth + tma_mem_latency)) + tma_memory_bound * (tma_l3_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_l3_hit_latency / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_memory_bound * tma_l2_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound) + tma_memory_bound * (tma_l1_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_l1_latency_dependency / (tma_dtlb_load + tma_store_fwd_blk + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_fb_full)) + tma_memory_bound * (tma_l1_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_lock_latency / (tma_dtlb_load + tma_store_fwd_blk + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_fb_full)) + tma_memory_bound * (tma_l1_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_split_loads / (tma_dtlb_load + tma_store_fwd_blk + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_fb_full)) + tma_memory_bound * (tma_store_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_split_stores / (tma_store_latency + tma_false_sharing + tma_split_stores + tma_streaming_stores + tma_dtlb_store)) + tma_memory_bound * (tma_store_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_store_latency / (tma_store_latency + tma_false_sharing + tma_split_stores + tma_streaming_stores + tma_dtlb_store)))", + "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_mem_latency / (tma_mem_bandwidth + tma_mem_latency)) + tma_memory_bound * (tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_l3_hit_latency / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_memory_bound * tma_l2_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) + tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_l1_latency_dependency / (tma_dtlb_load + tma_fb_full + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_lock_latency / (tma_dtlb_load + tma_fb_full + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_split_loads / (tma_dtlb_load + tma_fb_full + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_memory_bound * (tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_split_stores / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency + tma_streaming_stores)) + tma_memory_bound * (tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_store_latency / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency + tma_streaming_stores)))", "MetricGroup": "BvML;Mem;MemoryLat;Offcore;tma_issueLat", "MetricName": "tma_bottleneck_cache_memory_latency", "MetricThreshold": "tma_bottleneck_cache_memory_latency > 20", @@ -447,22 +447,22 @@ }, { "BriefDescription": "Total pipeline cost when the execution is compute-bound - an estimation", - "MetricExpr": "100 * (tma_core_bound * tma_divider / (tma_divider + tma_serializing_operation + tma_amx_busy + tma_ports_utilization) + tma_core_bound * tma_amx_busy / (tma_divider + tma_serializing_operation + tma_amx_busy + tma_ports_utilization) + tma_core_bound * (tma_ports_utilization / (tma_divider + tma_serializing_operation + tma_amx_busy + tma_ports_utilization)) * (tma_ports_utilized_3m / (tma_ports_utilized_0 + tma_ports_utilized_1 + tma_ports_utilized_2 + tma_ports_utilized_3m)))", + "MetricExpr": "100 * (tma_core_bound * tma_divider / (tma_amx_busy + tma_divider + tma_ports_utilization + tma_serializing_operation) + tma_core_bound * tma_amx_busy / (tma_amx_busy + tma_divider + tma_ports_utilization + tma_serializing_operation) + tma_core_bound * (tma_ports_utilization / (tma_amx_busy + tma_divider + tma_ports_utilization + tma_serializing_operation)) * (tma_ports_utilized_3m / (tma_ports_utilized_0 + tma_ports_utilized_1 + tma_ports_utilized_2 + tma_ports_utilized_3m)))", "MetricGroup": "BvCB;Cor;tma_issueComp", "MetricName": "tma_bottleneck_compute_bound_est", "MetricThreshold": "tma_bottleneck_compute_bound_est > 20", - "PublicDescription": "Total pipeline cost when the execution is compute-bound - an estimation. Covers Core Bound when High ILP as well as when long-latency execution units are busy" + "PublicDescription": "Total pipeline cost when the execution is compute-bound - an estimation. Covers Core Bound when High ILP as well as when long-latency execution units are busy. Related metrics: " }, { "BriefDescription": "Total pipeline cost of instruction fetch bandwidth related bottlenecks (when the front-end could not sustain operations delivery to the back-end)", - "MetricExpr": "100 * (tma_frontend_bound - (1 - 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts) * tma_fetch_latency * tma_mispredicts_resteers / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches) - (1 - INST_RETIRED.REP_ITERATION / cpu@UOPS_RETIRED.MS\\,cmask\\=0x1@) * (tma_fetch_latency * (tma_ms_switches + tma_branch_resteers * (tma_clears_resteers + tma_mispredicts_resteers * tma_other_mispredicts / tma_branch_mispredicts) / (tma_mispredicts_resteers + tma_clears_resteers + tma_unknown_branches)) / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches) + tma_fetch_bandwidth * tma_ms / (tma_mite + tma_dsb + tma_ms))) - tma_bottleneck_big_code", + "MetricExpr": "100 * (tma_frontend_bound - (1 - 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts) * tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) - (1 - INST_RETIRED.REP_ITERATION / cpu@UOPS_RETIRED.MS\\,cmask\\=1@) * (tma_fetch_latency * (tma_ms_switches + tma_branch_resteers * (tma_clears_resteers + tma_mispredicts_resteers * tma_other_mispredicts / tma_branch_mispredicts) / (tma_clears_resteers + tma_mispredicts_resteers + tma_unknown_branches)) / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) + tma_fetch_bandwidth * tma_ms / (tma_dsb + tma_mite + tma_ms))) - tma_bottleneck_big_code", "MetricGroup": "BvFB;Fed;FetchBW;Frontend", "MetricName": "tma_bottleneck_instruction_fetch_bw", "MetricThreshold": "tma_bottleneck_instruction_fetch_bw > 20" }, { "BriefDescription": "Total pipeline cost of irregular execution (e.g", - "MetricExpr": "100 * ((1 - INST_RETIRED.REP_ITERATION / cpu@UOPS_RETIRED.MS\\,cmask\\=0x1@) * (tma_fetch_latency * (tma_ms_switches + tma_branch_resteers * (tma_clears_resteers + tma_mispredicts_resteers * tma_other_mispredicts / tma_branch_mispredicts) / (tma_mispredicts_resteers + tma_clears_resteers + tma_unknown_branches)) / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches) + tma_fetch_bandwidth * tma_ms / (tma_mite + tma_dsb + tma_ms)) + 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts * tma_branch_mispredicts + tma_machine_clears * tma_other_nukes / tma_other_nukes + tma_core_bound * (tma_serializing_operation + RS.EMPTY_RESOURCE / tma_info_thread_clks * tma_ports_utilized_0) / (tma_divider + tma_serializing_operation + tma_amx_busy + tma_ports_utilization) + tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * tma_heavy_operations)", + "MetricExpr": "100 * ((1 - INST_RETIRED.REP_ITERATION / cpu@UOPS_RETIRED.MS\\,cmask\\=1@) * (tma_fetch_latency * (tma_ms_switches + tma_branch_resteers * (tma_clears_resteers + tma_mispredicts_resteers * tma_other_mispredicts / tma_branch_mispredicts) / (tma_clears_resteers + tma_mispredicts_resteers + tma_unknown_branches)) / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) + tma_fetch_bandwidth * tma_ms / (tma_dsb + tma_mite + tma_ms)) + 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts * tma_branch_mispredicts + tma_machine_clears * tma_other_nukes / tma_other_nukes + tma_core_bound * (tma_serializing_operation + RS.EMPTY_RESOURCE / tma_info_thread_clks * tma_ports_utilized_0) / (tma_amx_busy + tma_divider + tma_ports_utilization + tma_serializing_operation) + tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * tma_heavy_operations)", "MetricGroup": "Bad;BvIO;Cor;Ret;tma_issueMS", "MetricName": "tma_bottleneck_irregular_overhead", "MetricThreshold": "tma_bottleneck_irregular_overhead > 10", @@ -470,7 +470,7 @@ }, { "BriefDescription": "Total pipeline cost of Memory Address Translation related bottlenecks (data-side TLBs)", - "MetricExpr": "100 * (tma_memory_bound * (tma_l1_bound / max(tma_memory_bound, tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_dtlb_load / max(tma_l1_bound, tma_dtlb_load + tma_store_fwd_blk + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_fb_full)) + tma_memory_bound * (tma_store_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_dtlb_store / (tma_store_latency + tma_false_sharing + tma_split_stores + tma_streaming_stores + tma_dtlb_store)))", + "MetricExpr": "100 * (tma_memory_bound * (tma_l1_bound / max(tma_memory_bound, tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_dtlb_load / max(tma_l1_bound, tma_dtlb_load + tma_fb_full + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_memory_bound * (tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_dtlb_store / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency + tma_streaming_stores)))", "MetricGroup": "BvMT;Mem;MemoryTLB;Offcore;tma_issueTLB", "MetricName": "tma_bottleneck_memory_data_tlbs", "MetricThreshold": "tma_bottleneck_memory_data_tlbs > 20", @@ -478,7 +478,7 @@ }, { "BriefDescription": "Total pipeline cost of Memory Synchronization related bottlenecks (data transfers and coherency updates across processors)", - "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound) * (tma_mem_latency / (tma_mem_bandwidth + tma_mem_latency)) * tma_remote_cache / (tma_local_mem + tma_remote_mem + tma_remote_cache) + tma_l3_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound) * (tma_contested_accesses + tma_data_sharing) / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full) + tma_store_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound) * tma_false_sharing / (tma_store_latency + tma_false_sharing + tma_split_stores + tma_streaming_stores + tma_dtlb_store - tma_store_latency)) + tma_machine_clears * (1 - tma_other_nukes / tma_other_nukes))", + "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_mem_latency / (tma_mem_bandwidth + tma_mem_latency)) * tma_remote_cache / (tma_local_mem + tma_remote_cache + tma_remote_mem) + tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_contested_accesses + tma_data_sharing) / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full) + tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * tma_false_sharing / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency + tma_streaming_stores - tma_store_latency)) + tma_machine_clears * (1 - tma_other_nukes / tma_other_nukes))", "MetricGroup": "BvMS;LockCont;Mem;Offcore;tma_issueSyncxn", "MetricName": "tma_bottleneck_memory_synchronization", "MetricThreshold": "tma_bottleneck_memory_synchronization > 10", @@ -486,7 +486,7 @@ }, { "BriefDescription": "Total pipeline cost of Branch Misprediction related bottlenecks", - "MetricExpr": "100 * (1 - 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts) * (tma_branch_mispredicts + tma_fetch_latency * tma_mispredicts_resteers / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches))", + "MetricExpr": "100 * (1 - 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts) * (tma_branch_mispredicts + tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches))", "MetricGroup": "Bad;BadSpec;BrMispredicts;BvMP;tma_issueBM", "MetricName": "tma_bottleneck_mispredictions", "MetricThreshold": "tma_bottleneck_mispredictions > 20", @@ -498,10 +498,10 @@ "MetricGroup": "BvOB;Cor;Offcore", "MetricName": "tma_bottleneck_other_bottlenecks", "MetricThreshold": "tma_bottleneck_other_bottlenecks > 20", - "PublicDescription": "Total pipeline cost of remaining bottlenecks in the back-end. Examples include data-dependencies (Core Bound when Low ILP) and other unlisted memory-related stalls" + "PublicDescription": "Total pipeline cost of remaining bottlenecks in the back-end. Examples include data-dependencies (Core Bound when Low ILP) and other unlisted memory-related stalls." }, { - "BriefDescription": "Total pipeline cost of \"useful operations\" - the portion of Retiring category not covered by Branching_Overhead nor Irregular_Overhead", + "BriefDescription": "Total pipeline cost of \"useful operations\" - the portion of Retiring category not covered by Branching_Overhead nor Irregular_Overhead.", "MetricExpr": "100 * (tma_retiring - (BR_INST_RETIRED.ALL_BRANCHES + 2 * BR_INST_RETIRED.NEAR_CALL + INST_RETIRED.NOP) / tma_info_thread_slots - tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * tma_heavy_operations)", "MetricGroup": "BvUW;Ret", "MetricName": "tma_bottleneck_useful_work", @@ -510,7 +510,7 @@ { "BriefDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction", "DefaultMetricgroupName": "TopdownL2", - "MetricExpr": "topdown\\-br\\-mispredict / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * slots", + "MetricExpr": "topdown\\-br\\-mispredict / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * tma_info_thread_slots", "MetricGroup": "BadSpec;BrMispredicts;BvMP;Default;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueBM", "MetricName": "tma_branch_mispredicts", "MetricThreshold": "tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", @@ -523,24 +523,24 @@ "MetricExpr": "INT_MISC.CLEAR_RESTEER_CYCLES / tma_info_thread_clks + tma_unknown_branches", "MetricGroup": "FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group", "MetricName": "tma_branch_resteers", - "MetricThreshold": "tma_branch_resteers > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", - "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers. Branch Resteers estimates the Frontend delay in fetching operations from corrected path; following all sorts of miss-predicted branches. For example; branchy code with lots of miss-predictions might get categorized under Branch Resteers. Note the value of this node may overlap with its siblings. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_l3_hit_latency, tma_store_latency", + "MetricThreshold": "tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers. Branch Resteers estimates the Frontend delay in fetching operations from corrected path; following all sorts of miss-predicted branches. For example; branchy code with lots of miss-predictions might get categorized under Branch Resteers. Note the value of this node may overlap with its siblings. Sample with: BR_MISP_RETIRED.ALL_BRANCHES", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due staying in C0.1 power-performance optimized state (Faster wakeup time; Smaller power savings)", + "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due staying in C0.1 power-performance optimized state (Faster wakeup time; Smaller power savings).", "MetricExpr": "CPU_CLK_UNHALTED.C01 / tma_info_thread_clks", "MetricGroup": "C0Wait;TopdownL4;tma_L4_group;tma_serializing_operation_group", "MetricName": "tma_c01_wait", - "MetricThreshold": "tma_c01_wait > 0.05 & tma_serializing_operation > 0.1 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_c01_wait > 0.05 & (tma_serializing_operation > 0.1 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due staying in C0.2 power-performance optimized state (Slower wakeup time; Larger power savings)", + "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due staying in C0.2 power-performance optimized state (Slower wakeup time; Larger power savings).", "MetricExpr": "CPU_CLK_UNHALTED.C02 / tma_info_thread_clks", "MetricGroup": "C0Wait;TopdownL4;tma_L4_group;tma_serializing_operation_group", "MetricName": "tma_c02_wait", - "MetricThreshold": "tma_c02_wait > 0.05 & tma_serializing_operation > 0.1 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_c02_wait > 0.05 & (tma_serializing_operation > 0.1 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", "ScaleUnit": "100%" }, { @@ -548,7 +548,7 @@ "MetricExpr": "max(0, tma_microcode_sequencer - tma_assists)", "MetricGroup": "TopdownL4;tma_L4_group;tma_microcode_sequencer_group", "MetricName": "tma_cisc", - "MetricThreshold": "tma_cisc > 0.1 & tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1", + "MetricThreshold": "tma_cisc > 0.1 & (tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1)", "PublicDescription": "This metric estimates fraction of cycles the CPU retired uops originated from CISC (complex instruction set computer) instruction. A CISC instruction has multiple uops that are required to perform the instruction's functionality as in the case of read-modify-write as an example. Since these instructions require multiple uops they may or may not imply sub-optimal use of machine resources. Sample with: FRONTEND_RETIRED.MS_FLOWS", "ScaleUnit": "100%" }, @@ -557,24 +557,24 @@ "MetricExpr": "(1 - tma_branch_mispredicts / tma_bad_speculation) * INT_MISC.CLEAR_RESTEER_CYCLES / tma_info_thread_clks", "MetricGroup": "BadSpec;MachineClears;TopdownL4;tma_L4_group;tma_branch_resteers_group;tma_issueMC", "MetricName": "tma_clears_resteers", - "MetricThreshold": "tma_clears_resteers > 0.05 & tma_branch_resteers > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricThreshold": "tma_clears_resteers > 0.05 & (tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))", "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Machine Clears. Sample with: INT_MISC.CLEAR_RESTEER_CYCLES. Related metrics: tma_l1_bound, tma_machine_clears, tma_microcode_sequencer, tma_ms_switches", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates fraction of cycles the CPU was stalled due to instruction cache misses that hit in the L2 cache", + "BriefDescription": "This metric estimates fraction of cycles the CPU was stalled due to instruction cache misses that hit in the L2 cache.", "MetricExpr": "max(0, tma_icache_misses - tma_code_l2_miss)", "MetricGroup": "FetchLat;IcMiss;Offcore;TopdownL4;tma_L4_group;tma_icache_misses_group", "MetricName": "tma_code_l2_hit", - "MetricThreshold": "tma_code_l2_hit > 0.05 & tma_icache_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricThreshold": "tma_code_l2_hit > 0.05 & (tma_icache_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates fraction of cycles the CPU was stalled due to instruction cache misses that miss in the L2 cache", + "BriefDescription": "This metric estimates fraction of cycles the CPU was stalled due to instruction cache misses that miss in the L2 cache.", "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_CODE_RD / tma_info_thread_clks", "MetricGroup": "FetchLat;IcMiss;Offcore;TopdownL4;tma_L4_group;tma_icache_misses_group", "MetricName": "tma_code_l2_miss", - "MetricThreshold": "tma_code_l2_miss > 0.05 & tma_icache_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricThreshold": "tma_code_l2_miss > 0.05 & (tma_icache_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))", "ScaleUnit": "100%" }, { @@ -582,7 +582,7 @@ "MetricExpr": "max(0, tma_itlb_misses - tma_code_stlb_miss)", "MetricGroup": "FetchLat;MemoryTLB;TopdownL4;tma_L4_group;tma_itlb_misses_group", "MetricName": "tma_code_stlb_hit", - "MetricThreshold": "tma_code_stlb_hit > 0.05 & tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricThreshold": "tma_code_stlb_hit > 0.05 & (tma_itlb_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))", "ScaleUnit": "100%" }, { @@ -590,32 +590,33 @@ "MetricExpr": "ITLB_MISSES.WALK_ACTIVE / tma_info_thread_clks", "MetricGroup": "FetchLat;MemoryTLB;TopdownL4;tma_L4_group;tma_itlb_misses_group", "MetricName": "tma_code_stlb_miss", - "MetricThreshold": "tma_code_stlb_miss > 0.05 & tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricThreshold": "tma_code_stlb_miss > 0.05 & (tma_itlb_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 2 or 4 MB pages for (instruction) code accesses", + "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 2 or 4 MB pages for (instruction) code accesses.", "MetricExpr": "tma_code_stlb_miss * ITLB_MISSES.WALK_COMPLETED_2M_4M / (ITLB_MISSES.WALK_COMPLETED_4K + ITLB_MISSES.WALK_COMPLETED_2M_4M)", "MetricGroup": "FetchLat;MemoryTLB;TopdownL5;tma_L5_group;tma_code_stlb_miss_group", "MetricName": "tma_code_stlb_miss_2m", - "MetricThreshold": "tma_code_stlb_miss_2m > 0.05 & tma_code_stlb_miss > 0.05 & tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricThreshold": "tma_code_stlb_miss_2m > 0.05 & (tma_code_stlb_miss > 0.05 & (tma_itlb_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)))", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 4 KB pages for (instruction) code accesses", + "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 4 KB pages for (instruction) code accesses.", "MetricExpr": "tma_code_stlb_miss * ITLB_MISSES.WALK_COMPLETED_4K / (ITLB_MISSES.WALK_COMPLETED_4K + ITLB_MISSES.WALK_COMPLETED_2M_4M)", "MetricGroup": "FetchLat;MemoryTLB;TopdownL5;tma_L5_group;tma_code_stlb_miss_group", "MetricName": "tma_code_stlb_miss_4k", - "MetricThreshold": "tma_code_stlb_miss_4k > 0.05 & tma_code_stlb_miss > 0.05 & tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricThreshold": "tma_code_stlb_miss_4k > 0.05 & (tma_code_stlb_miss > 0.05 & (tma_itlb_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)))", "ScaleUnit": "100%" }, { "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses", - "MetricExpr": "((81 * tma_info_system_core_frequency - 4.4 * tma_info_system_core_frequency) * (MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD * (OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM / (OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM + OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD))) + (79 * tma_info_system_core_frequency - 4.4 * tma_info_system_core_frequency) * MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "(76.6 * tma_info_system_core_frequency * (MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD * (OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM / (OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM + OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD))) + 74.6 * tma_info_system_core_frequency * MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks", "MetricGroup": "BvMS;DataSharing;LockCont;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group", "MetricName": "tma_contested_accesses", - "MetricThreshold": "tma_contested_accesses > 0.05 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", - "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses. Contested accesses occur when data written by one Logical Processor are read by another Logical Processor on a different Physical Core. Examples of contested accesses include synchronizations such as locks; true data sharing such as modified locked variables; and false sharing. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD, MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS. Related metrics: tma_bottleneck_memory_synchronization, tma_data_sharing, tma_false_sharing, tma_machine_clears, tma_remote_cache", + "MetricThreshold": "tma_contested_accesses > 0.05 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses. Contested accesses occur when data written by one Logical Processor are read by another Logical Processor on a different Physical Core. Examples of contested accesses include synchronizations such as locks; true data sharing such as modified locked variables; and false sharing. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD;MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS. Related metrics: tma_bottleneck_memory_synchronization, tma_data_sharing, tma_false_sharing, tma_machine_clears, tma_remote_cache", "ScaleUnit": "100%" }, { @@ -626,24 +627,25 @@ "MetricName": "tma_core_bound", "MetricThreshold": "tma_core_bound > 0.1 & tma_backend_bound > 0.2", "MetricgroupNoGroup": "TopdownL2;Default", - "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck. Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations)", + "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck. Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations).", "ScaleUnit": "100%" }, { "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses", - "MetricExpr": "(79 * tma_info_system_core_frequency - 4.4 * tma_info_system_core_frequency) * (MEM_LOAD_L3_HIT_RETIRED.XSNP_NO_FWD + MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD * (1 - OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM / (OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM + OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD))) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "74.6 * tma_info_system_core_frequency * (MEM_LOAD_L3_HIT_RETIRED.XSNP_NO_FWD + MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD * (1 - OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM / (OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM + OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD))) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks", "MetricGroup": "BvMS;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group", "MetricName": "tma_data_sharing", - "MetricThreshold": "tma_data_sharing > 0.05 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_data_sharing > 0.05 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses. Data shared by multiple Logical Processors (even just read shared) may cause increased access latency due to cache coherency. Excessive data sharing can drastically harm multithreaded performance. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_NO_FWD. Related metrics: tma_bottleneck_memory_synchronization, tma_contested_accesses, tma_false_sharing, tma_machine_clears, tma_remote_cache", "ScaleUnit": "100%" }, { "BriefDescription": "This metric represents fraction of cycles where decoder-0 was the only active decoder", - "MetricExpr": "(cpu@INST_DECODED.DECODERS\\,cmask\\=0x1@ - cpu@INST_DECODED.DECODERS\\,cmask\\=0x2@) / tma_info_core_core_clks / 2", + "MetricExpr": "(cpu@INST_DECODED.DECODERS\\,cmask\\=1@ - cpu@INST_DECODED.DECODERS\\,cmask\\=2@) / tma_info_core_core_clks / 2", "MetricGroup": "DSBmiss;FetchBW;TopdownL4;tma_L4_group;tma_issueD0;tma_mite_group", "MetricName": "tma_decoder0_alone", - "MetricThreshold": "tma_decoder0_alone > 0.1 & tma_mite > 0.1 & tma_fetch_bandwidth > 0.2", + "MetricThreshold": "tma_decoder0_alone > 0.1 & (tma_mite > 0.1 & tma_fetch_bandwidth > 0.2)", "PublicDescription": "This metric represents fraction of cycles where decoder-0 was the only active decoder. Related metrics: tma_few_uops_instructions", "ScaleUnit": "100%" }, @@ -652,7 +654,7 @@ "MetricExpr": "ARITH.DIV_ACTIVE / tma_info_thread_clks", "MetricGroup": "BvCB;TopdownL3;tma_L3_group;tma_core_bound_group", "MetricName": "tma_divider", - "MetricThreshold": "tma_divider > 0.2 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_divider > 0.2 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)", "PublicDescription": "This metric represents fraction of cycles where the Divider unit was active. Divide and square root instructions are performed by the Divider unit and can take considerably longer latency than integer or Floating Point addition; subtraction; or multiplication. Sample with: ARITH.DIVIDER_ACTIVE", "ScaleUnit": "100%" }, @@ -661,7 +663,7 @@ "MetricExpr": "MEMORY_ACTIVITY.STALLS_L3_MISS / tma_info_thread_clks", "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_dram_bound", - "MetricThreshold": "tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", "PublicDescription": "This metric estimates how often the CPU was stalled on accesses to external memory (DRAM) by loads. Better caching can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L3_MISS", "ScaleUnit": "100%" }, @@ -671,7 +673,7 @@ "MetricGroup": "DSB;FetchBW;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group", "MetricName": "tma_dsb", "MetricThreshold": "tma_dsb > 0.15 & tma_fetch_bandwidth > 0.2", - "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to DSB (decoded uop cache) fetch pipeline. For example; inefficient utilization of the DSB cache structure or bank conflict when reading from it; are categorized here", + "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to DSB (decoded uop cache) fetch pipeline. For example; inefficient utilization of the DSB cache structure or bank conflict when reading from it; are categorized here.", "ScaleUnit": "100%" }, { @@ -679,34 +681,34 @@ "MetricExpr": "DSB2MITE_SWITCHES.PENALTY_CYCLES / tma_info_thread_clks", "MetricGroup": "DSBmiss;FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueFB", "MetricName": "tma_dsb_switches", - "MetricThreshold": "tma_dsb_switches > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", - "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines. The DSB (decoded i-cache) is a Uop Cache where the front-end directly delivers Uops (micro operations) avoiding heavy x86 decoding. The DSB pipeline has shorter latency and delivered higher bandwidth than the MITE (legacy instruction decode pipeline). Switching between the two pipelines can cause penalties hence this metric measures the exposed penalty. Sample with: FRONTEND_RETIRED.DSB_MISS. Related metrics: tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp", + "MetricThreshold": "tma_dsb_switches > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines. The DSB (decoded i-cache) is a Uop Cache where the front-end directly delivers Uops (micro operations) avoiding heavy x86 decoding. The DSB pipeline has shorter latency and delivered higher bandwidth than the MITE (legacy instruction decode pipeline). Switching between the two pipelines can cause penalties hence this metric measures the exposed penalty. Sample with: FRONTEND_RETIRED.DSB_MISS_PS. Related metrics: tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp", "ScaleUnit": "100%" }, { "BriefDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses", - "MetricExpr": "min(7 * cpu@DTLB_LOAD_MISSES.STLB_HIT\\,cmask\\=0x1@ + DTLB_LOAD_MISSES.WALK_ACTIVE, max(CYCLE_ACTIVITY.CYCLES_MEM_ANY - MEMORY_ACTIVITY.CYCLES_L1D_MISS, 0)) / tma_info_thread_clks", + "MetricExpr": "min(7 * cpu@DTLB_LOAD_MISSES.STLB_HIT\\,cmask\\=1@ + DTLB_LOAD_MISSES.WALK_ACTIVE, max(CYCLE_ACTIVITY.CYCLES_MEM_ANY - MEMORY_ACTIVITY.CYCLES_L1D_MISS, 0)) / tma_info_thread_clks", "MetricGroup": "BvMT;MemoryTLB;TopdownL4;tma_L4_group;tma_issueTLB;tma_l1_bound_group", "MetricName": "tma_dtlb_load", - "MetricThreshold": "tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", - "PublicDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses. TLBs (Translation Look-aside Buffers) are processor caches for recently used entries out of the Page Tables that are used to map virtual- to physical-addresses by the operating system. This metric approximates the potential delay of demand loads missing the first-level data TLB (assuming worst case scenario with back to back misses to different pages). This includes hitting in the second-level TLB (STLB) as well as performing a hardware page walk on an STLB miss. Sample with: MEM_INST_RETIRED.STLB_MISS_LOADS. Related metrics: tma_bottleneck_memory_data_tlbs, tma_dtlb_store", + "MetricThreshold": "tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses. TLBs (Translation Look-aside Buffers) are processor caches for recently used entries out of the Page Tables that are used to map virtual- to physical-addresses by the operating system. This metric approximates the potential delay of demand loads missing the first-level data TLB (assuming worst case scenario with back to back misses to different pages). This includes hitting in the second-level TLB (STLB) as well as performing a hardware page walk on an STLB miss. Sample with: MEM_INST_RETIRED.STLB_MISS_LOADS_PS. Related metrics: tma_bottleneck_memory_data_tlbs, tma_dtlb_store", "ScaleUnit": "100%" }, { "BriefDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses", - "MetricExpr": "(7 * cpu@DTLB_STORE_MISSES.STLB_HIT\\,cmask\\=0x1@ + DTLB_STORE_MISSES.WALK_ACTIVE) / tma_info_core_core_clks", + "MetricExpr": "(7 * cpu@DTLB_STORE_MISSES.STLB_HIT\\,cmask\\=1@ + DTLB_STORE_MISSES.WALK_ACTIVE) / tma_info_core_core_clks", "MetricGroup": "BvMT;MemoryTLB;TopdownL4;tma_L4_group;tma_issueTLB;tma_store_bound_group", "MetricName": "tma_dtlb_store", - "MetricThreshold": "tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", - "PublicDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses. As with ordinary data caching; focus on improving data locality and reducing working-set size to reduce DTLB overhead. Additionally; consider using profile-guided optimization (PGO) to collocate frequently-used data on the same page. Try using larger page sizes for large amounts of frequently-used data. Sample with: MEM_INST_RETIRED.STLB_MISS_STORES. Related metrics: tma_bottleneck_memory_data_tlbs, tma_dtlb_load", + "MetricThreshold": "tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses. As with ordinary data caching; focus on improving data locality and reducing working-set size to reduce DTLB overhead. Additionally; consider using profile-guided optimization (PGO) to collocate frequently-used data on the same page. Try using larger page sizes for large amounts of frequently-used data. Sample with: MEM_INST_RETIRED.STLB_MISS_STORES_PS. Related metrics: tma_bottleneck_memory_data_tlbs, tma_dtlb_load", "ScaleUnit": "100%" }, { "BriefDescription": "This metric roughly estimates how often CPU was handling synchronizations due to False Sharing", - "MetricExpr": "(170 * tma_info_system_core_frequency * cpu@OCR.DEMAND_RFO.L3_MISS\\,offcore_rsp\\=0x103b800002@ + 81 * tma_info_system_core_frequency * OCR.DEMAND_RFO.L3_HIT.SNOOP_HITM) / tma_info_thread_clks", + "MetricExpr": "(170 * tma_info_system_core_frequency * OCR.DEMAND_RFO.L3_MISS@offcore_rsp\\=0x103b800002@ + 81 * tma_info_system_core_frequency * OCR.DEMAND_RFO.L3_HIT.SNOOP_HITM) / tma_info_thread_clks", "MetricGroup": "BvMS;DataSharing;LockCont;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_store_bound_group", "MetricName": "tma_false_sharing", - "MetricThreshold": "tma_false_sharing > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_false_sharing > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", "PublicDescription": "This metric roughly estimates how often CPU was handling synchronizations due to False Sharing. False Sharing is a multithreading hiccup; where multiple Logical Processors contend on different data-elements mapped into the same cache line. Sample with: OCR.DEMAND_RFO.L3_HIT.SNOOP_HITM. Related metrics: tma_bottleneck_memory_synchronization, tma_contested_accesses, tma_data_sharing, tma_machine_clears, tma_remote_cache", "ScaleUnit": "100%" }, @@ -727,7 +729,7 @@ "MetricName": "tma_fetch_bandwidth", "MetricThreshold": "tma_fetch_bandwidth > 0.2", "MetricgroupNoGroup": "TopdownL2;Default", - "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues. For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Sample with: FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1, FRONTEND_RETIRED.LATENCY_GE_1, FRONTEND_RETIRED.LATENCY_GE_2. Related metrics: tma_dsb_switches, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp", + "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues. For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Sample with: FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1;FRONTEND_RETIRED.LATENCY_GE_1;FRONTEND_RETIRED.LATENCY_GE_2. Related metrics: tma_dsb_switches, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp", "ScaleUnit": "100%" }, { @@ -738,7 +740,7 @@ "MetricName": "tma_fetch_latency", "MetricThreshold": "tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", "MetricgroupNoGroup": "TopdownL2;Default", - "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues. For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: FRONTEND_RETIRED.LATENCY_GE_16, FRONTEND_RETIRED.LATENCY_GE_8", + "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues. For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: FRONTEND_RETIRED.LATENCY_GE_16_PS;FRONTEND_RETIRED.LATENCY_GE_8_PS", "ScaleUnit": "100%" }, { @@ -756,7 +758,7 @@ "MetricGroup": "HPC;TopdownL3;tma_L3_group;tma_light_operations_group", "MetricName": "tma_fp_arith", "MetricThreshold": "tma_fp_arith > 0.2 & tma_light_operations > 0.6", - "PublicDescription": "This metric represents overall arithmetic floating-point (FP) operations fraction the CPU has executed (retired). Note this metric's value may exceed its parent due to use of \"Uops\" CountDomain and FMA double-counting", + "PublicDescription": "This metric represents overall arithmetic floating-point (FP) operations fraction the CPU has executed (retired). Note this metric's value may exceed its parent due to use of \"Uops\" CountDomain and FMA double-counting.", "ScaleUnit": "100%" }, { @@ -765,15 +767,15 @@ "MetricGroup": "HPC;TopdownL5;tma_L5_group;tma_assists_group", "MetricName": "tma_fp_assists", "MetricThreshold": "tma_fp_assists > 0.1", - "PublicDescription": "This metric roughly estimates fraction of slots the CPU retired uops as a result of handing Floating Point (FP) Assists. FP Assist may apply when working with very small floating point values (so-called Denormals)", + "PublicDescription": "This metric roughly estimates fraction of slots the CPU retired uops as a result of handing Floating Point (FP) Assists. FP Assist may apply when working with very small floating point values (so-called Denormals).", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of cycles where the Floating-Point Divider unit was active", + "BriefDescription": "This metric represents fraction of cycles where the Floating-Point Divider unit was active.", "MetricExpr": "ARITH.FPDIV_ACTIVE / tma_info_thread_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_divider_group", "MetricName": "tma_fp_divider", - "MetricThreshold": "tma_fp_divider > 0.2 & tma_divider > 0.2 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_fp_divider > 0.2 & (tma_divider > 0.2 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", "ScaleUnit": "100%" }, { @@ -781,8 +783,8 @@ "MetricExpr": "(FP_ARITH_INST_RETIRED.SCALAR + FP_ARITH_INST_RETIRED2.SCALAR) / (tma_retiring * tma_info_thread_slots)", "MetricGroup": "Compute;Flops;TopdownL4;tma_L4_group;tma_fp_arith_group;tma_issue2P", "MetricName": "tma_fp_scalar", - "MetricThreshold": "tma_fp_scalar > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6", - "PublicDescription": "This metric approximates arithmetic floating-point (FP) scalar uops fraction the CPU has retired. May overcount due to FMA double counting. Related metrics: tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_6, tma_ports_utilized_2", + "MetricThreshold": "tma_fp_scalar > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6)", + "PublicDescription": "This metric approximates arithmetic floating-point (FP) scalar uops fraction the CPU has retired. May overcount due to FMA double counting. Related metrics: tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%" }, { @@ -790,8 +792,8 @@ "MetricExpr": "(FP_ARITH_INST_RETIRED.VECTOR + FP_ARITH_INST_RETIRED2.VECTOR) / (tma_retiring * tma_info_thread_slots)", "MetricGroup": "Compute;Flops;TopdownL4;tma_L4_group;tma_fp_arith_group;tma_issue2P", "MetricName": "tma_fp_vector", - "MetricThreshold": "tma_fp_vector > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6", - "PublicDescription": "This metric approximates arithmetic floating-point (FP) vector uops fraction the CPU has retired aggregated across all vector widths. May overcount due to FMA double counting. Related metrics: tma_fp_scalar, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_6, tma_ports_utilized_2", + "MetricThreshold": "tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6)", + "PublicDescription": "This metric approximates arithmetic floating-point (FP) vector uops fraction the CPU has retired aggregated across all vector widths. May overcount due to FMA double counting. Related metrics: tma_fp_scalar, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%" }, { @@ -799,8 +801,8 @@ "MetricExpr": "(FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED2.128B_PACKED_HALF) / (tma_retiring * tma_info_thread_slots)", "MetricGroup": "Compute;Flops;TopdownL5;tma_L5_group;tma_fp_vector_group;tma_issue2P", "MetricName": "tma_fp_vector_128b", - "MetricThreshold": "tma_fp_vector_128b > 0.1 & tma_fp_vector > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6", - "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 128-bit wide vectors. May overcount due to FMA double counting prior to LNL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_6, tma_ports_utilized_2", + "MetricThreshold": "tma_fp_vector_128b > 0.1 & (tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6))", + "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 128-bit wide vectors. May overcount due to FMA double counting prior to LNL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%" }, { @@ -808,8 +810,8 @@ "MetricExpr": "(FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE + FP_ARITH_INST_RETIRED2.256B_PACKED_HALF) / (tma_retiring * tma_info_thread_slots)", "MetricGroup": "Compute;Flops;TopdownL5;tma_L5_group;tma_fp_vector_group;tma_issue2P", "MetricName": "tma_fp_vector_256b", - "MetricThreshold": "tma_fp_vector_256b > 0.1 & tma_fp_vector > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6", - "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 256-bit wide vectors. May overcount due to FMA double counting prior to LNL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_6, tma_ports_utilized_2", + "MetricThreshold": "tma_fp_vector_256b > 0.1 & (tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6))", + "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 256-bit wide vectors. May overcount due to FMA double counting prior to LNL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%" }, { @@ -817,8 +819,8 @@ "MetricExpr": "(FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE + FP_ARITH_INST_RETIRED2.512B_PACKED_HALF) / (tma_retiring * tma_info_thread_slots)", "MetricGroup": "Compute;Flops;TopdownL5;tma_L5_group;tma_fp_vector_group;tma_issue2P", "MetricName": "tma_fp_vector_512b", - "MetricThreshold": "tma_fp_vector_512b > 0.1 & tma_fp_vector > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6", - "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 512-bit wide vectors. May overcount due to FMA double counting. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_6, tma_ports_utilized_2", + "MetricThreshold": "tma_fp_vector_512b > 0.1 & (tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6))", + "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 512-bit wide vectors. May overcount due to FMA double counting. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%" }, { @@ -829,27 +831,27 @@ "MetricName": "tma_frontend_bound", "MetricThreshold": "tma_frontend_bound > 0.15", "MetricgroupNoGroup": "TopdownL1;Default", - "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound. Sample with: FRONTEND_RETIRED.LATENCY_GE_4", + "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound. Sample with: FRONTEND_RETIRED.LATENCY_GE_4_PS", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of slots where the CPU was retiring fused instructions , where one uop can represent multiple contiguous instructions", + "BriefDescription": "This metric represents fraction of slots where the CPU was retiring fused instructions -- where one uop can represent multiple contiguous instructions", "MetricExpr": "tma_light_operations * INST_RETIRED.MACRO_FUSED / (tma_retiring * tma_info_thread_slots)", "MetricGroup": "Branches;BvBO;Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group", "MetricName": "tma_fused_instructions", "MetricThreshold": "tma_fused_instructions > 0.1 & tma_light_operations > 0.6", - "PublicDescription": "This metric represents fraction of slots where the CPU was retiring fused instructions , where one uop can represent multiple contiguous instructions. CMP+JCC or DEC+JCC are common examples of legacy fusions. {([MTL] Note new MOV+OP and Load+OP fusions appear under Other_Light_Ops in MTL!)}", + "PublicDescription": "This metric represents fraction of slots where the CPU was retiring fused instructions -- where one uop can represent multiple contiguous instructions. CMP+JCC or DEC+JCC are common examples of legacy fusions. {([MTL] Note new MOV+OP and Load+OP fusions appear under Other_Light_Ops in MTL!)}", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations , instructions that require two or more uops or micro-coded sequences", + "BriefDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences", "DefaultMetricgroupName": "TopdownL2", - "MetricExpr": "topdown\\-heavy\\-ops / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * slots", + "MetricExpr": "topdown\\-heavy\\-ops / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * tma_info_thread_slots", "MetricGroup": "Default;Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_heavy_operations", "MetricThreshold": "tma_heavy_operations > 0.1", "MetricgroupNoGroup": "TopdownL2;Default", - "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations , instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences.([ICL+] Note this may overcount due to approximation using indirect events; [ADL+]). Sample with: UOPS_RETIRED.HEAVY", + "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences.([ICL+] Note this may overcount due to approximation using indirect events; [ADL+]). Sample with: UOPS_RETIRED.HEAVY", "ScaleUnit": "100%" }, { @@ -857,8 +859,8 @@ "MetricExpr": "ICACHE_DATA.STALLS / tma_info_thread_clks", "MetricGroup": "BigFootprint;BvBC;FetchLat;IcMiss;TopdownL3;tma_L3_group;tma_fetch_latency_group", "MetricName": "tma_icache_misses", - "MetricThreshold": "tma_icache_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", - "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to instruction cache misses. Sample with: FRONTEND_RETIRED.L2_MISS, FRONTEND_RETIRED.L1I_MISS", + "MetricThreshold": "tma_icache_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to instruction cache misses. Sample with: FRONTEND_RETIRED.L2_MISS_PS;FRONTEND_RETIRED.L1I_MISS_PS", "ScaleUnit": "100%" }, { @@ -869,28 +871,28 @@ "PublicDescription": "Branch Misprediction Cost: Cycles representing fraction of TMA slots wasted per non-speculative branch misprediction (retired JEClear). Related metrics: tma_bottleneck_mispredictions, tma_branch_mispredicts, tma_mispredicts_resteers" }, { - "BriefDescription": "Instructions per retired Mispredicts for conditional non-taken branches (lower number means higher occurrence rate)", + "BriefDescription": "Instructions per retired Mispredicts for conditional non-taken branches (lower number means higher occurrence rate).", "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.COND_NTAKEN", "MetricGroup": "Bad;BrMispredicts", "MetricName": "tma_info_bad_spec_ipmisp_cond_ntaken", "MetricThreshold": "tma_info_bad_spec_ipmisp_cond_ntaken < 200" }, { - "BriefDescription": "Instructions per retired Mispredicts for conditional taken branches (lower number means higher occurrence rate)", + "BriefDescription": "Instructions per retired Mispredicts for conditional taken branches (lower number means higher occurrence rate).", "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.COND_TAKEN", "MetricGroup": "Bad;BrMispredicts", "MetricName": "tma_info_bad_spec_ipmisp_cond_taken", "MetricThreshold": "tma_info_bad_spec_ipmisp_cond_taken < 200" }, { - "BriefDescription": "Instructions per retired Mispredicts for indirect CALL or JMP branches (lower number means higher occurrence rate)", + "BriefDescription": "Instructions per retired Mispredicts for indirect CALL or JMP branches (lower number means higher occurrence rate).", "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.INDIRECT", "MetricGroup": "Bad;BrMispredicts", "MetricName": "tma_info_bad_spec_ipmisp_indirect", - "MetricThreshold": "tma_info_bad_spec_ipmisp_indirect < 1000" + "MetricThreshold": "tma_info_bad_spec_ipmisp_indirect < 1e3" }, { - "BriefDescription": "Instructions per retired Mispredicts for return branches (lower number means higher occurrence rate)", + "BriefDescription": "Instructions per retired Mispredicts for return branches (lower number means higher occurrence rate).", "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.RET", "MetricGroup": "Bad;BrMispredicts", "MetricName": "tma_info_bad_spec_ipmisp_ret", @@ -918,7 +920,7 @@ }, { "BriefDescription": "Total pipeline cost of DSB (uop cache) hits - subset of the Instruction_Fetch_BW Bottleneck", - "MetricExpr": "100 * (tma_frontend_bound * (tma_fetch_bandwidth / (tma_fetch_latency + tma_fetch_bandwidth)) * (tma_dsb / (tma_mite + tma_dsb + tma_ms)))", + "MetricExpr": "100 * (tma_frontend_bound * (tma_fetch_bandwidth / (tma_fetch_bandwidth + tma_fetch_latency)) * (tma_dsb / (tma_dsb + tma_mite + tma_ms)))", "MetricGroup": "DSB;Fed;FetchBW;tma_issueFB", "MetricName": "tma_info_botlnk_l2_dsb_bandwidth", "MetricThreshold": "tma_info_botlnk_l2_dsb_bandwidth > 10", @@ -926,7 +928,7 @@ }, { "BriefDescription": "Total pipeline cost of DSB (uop cache) misses - subset of the Instruction_Fetch_BW Bottleneck", - "MetricExpr": "100 * (tma_fetch_latency * tma_dsb_switches / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches) + tma_fetch_bandwidth * tma_mite / (tma_mite + tma_dsb + tma_ms))", + "MetricExpr": "100 * (tma_fetch_latency * tma_dsb_switches / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) + tma_fetch_bandwidth * tma_mite / (tma_dsb + tma_mite + tma_ms))", "MetricGroup": "DSBmiss;Fed;tma_issueFB", "MetricName": "tma_info_botlnk_l2_dsb_misses", "MetricThreshold": "tma_info_botlnk_l2_dsb_misses > 10", @@ -934,10 +936,11 @@ }, { "BriefDescription": "Total pipeline cost of Instruction Cache misses - subset of the Big_Code Bottleneck", - "MetricExpr": "100 * (tma_fetch_latency * tma_icache_misses / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches))", + "MetricExpr": "100 * (tma_fetch_latency * tma_icache_misses / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches))", "MetricGroup": "Fed;FetchLat;IcMiss;tma_issueFL", "MetricName": "tma_info_botlnk_l2_ic_misses", - "MetricThreshold": "tma_info_botlnk_l2_ic_misses > 5" + "MetricThreshold": "tma_info_botlnk_l2_ic_misses > 5", + "PublicDescription": "Total pipeline cost of Instruction Cache misses - subset of the Big_Code Bottleneck. Related metrics: " }, { "BriefDescription": "Fraction of branches that are CALL or RET", @@ -998,11 +1001,11 @@ "MetricExpr": "(FP_ARITH_DISPATCHED.PORT_0 + FP_ARITH_DISPATCHED.PORT_1 + FP_ARITH_DISPATCHED.PORT_5) / (2 * tma_info_core_core_clks)", "MetricGroup": "Cor;Flops;HPC", "MetricName": "tma_info_core_fp_arith_utilization", - "PublicDescription": "Actual per-core usage of the Floating Point non-X87 execution units (regardless of precision or vector-width). Values > 1 are possible due to ([BDW+] Fused-Multiply Add (FMA) counting - common; [ADL+] use all of ADD/MUL/FMA in Scalar or 128/256-bit vectors - less common)" + "PublicDescription": "Actual per-core usage of the Floating Point non-X87 execution units (regardless of precision or vector-width). Values > 1 are possible due to ([BDW+] Fused-Multiply Add (FMA) counting - common; [ADL+] use all of ADD/MUL/FMA in Scalar or 128/256-bit vectors - less common)." }, { "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is execution) per thread (logical-processor)", - "MetricExpr": "UOPS_EXECUTED.THREAD / cpu@UOPS_EXECUTED.THREAD\\,cmask\\=0x1@", + "MetricExpr": "UOPS_EXECUTED.THREAD / cpu@UOPS_EXECUTED.THREAD\\,cmask\\=1@", "MetricGroup": "Backend;Cor;Pipeline;PortsUtil", "MetricName": "tma_info_core_ilp" }, @@ -1015,20 +1018,20 @@ "PublicDescription": "Fraction of Uops delivered by the DSB (aka Decoded ICache; or Uop Cache). Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_inst_mix_iptb, tma_lcp" }, { - "BriefDescription": "Average number of cycles of a switch from the DSB fetch-unit to MITE fetch unit - see DSB_Switches tree node for details", - "MetricExpr": "DSB2MITE_SWITCHES.PENALTY_CYCLES / cpu@DSB2MITE_SWITCHES.PENALTY_CYCLES\\,cmask\\=0x1\\,edge\\=0x1@", + "BriefDescription": "Average number of cycles of a switch from the DSB fetch-unit to MITE fetch unit - see DSB_Switches tree node for details.", + "MetricExpr": "DSB2MITE_SWITCHES.PENALTY_CYCLES / cpu@DSB2MITE_SWITCHES.PENALTY_CYCLES\\,cmask\\=1\\,edge@", "MetricGroup": "DSBmiss", "MetricName": "tma_info_frontend_dsb_switch_cost" }, { "BriefDescription": "Average number of Uops issued by front-end when it issued something", - "MetricExpr": "UOPS_ISSUED.ANY / cpu@UOPS_ISSUED.ANY\\,cmask\\=0x1@", + "MetricExpr": "UOPS_ISSUED.ANY / cpu@UOPS_ISSUED.ANY\\,cmask\\=1@", "MetricGroup": "Fed;FetchBW", "MetricName": "tma_info_frontend_fetch_upc" }, { "BriefDescription": "Average Latency for L1 instruction cache misses", - "MetricExpr": "ICACHE_DATA.STALLS / cpu@ICACHE_DATA.STALLS\\,cmask\\=0x1\\,edge\\=0x1@", + "MetricExpr": "ICACHE_DATA.STALLS / cpu@ICACHE_DATA.STALLS\\,cmask\\=1\\,edge@", "MetricGroup": "Fed;FetchLat;IcMiss", "MetricName": "tma_info_frontend_icache_miss_latency" }, @@ -1065,13 +1068,13 @@ }, { "BriefDescription": "Average number of cycles the front-end was delayed due to an Unknown Branch detection", - "MetricExpr": "INT_MISC.UNKNOWN_BRANCH_CYCLES / cpu@INT_MISC.UNKNOWN_BRANCH_CYCLES\\,cmask\\=0x1\\,edge\\=0x1@", + "MetricExpr": "INT_MISC.UNKNOWN_BRANCH_CYCLES / cpu@INT_MISC.UNKNOWN_BRANCH_CYCLES\\,cmask\\=1\\,edge@", "MetricGroup": "Fed", "MetricName": "tma_info_frontend_unknown_branch_cost", - "PublicDescription": "Average number of cycles the front-end was delayed due to an Unknown Branch detection. See Unknown_Branches node" + "PublicDescription": "Average number of cycles the front-end was delayed due to an Unknown Branch detection. See Unknown_Branches node." }, { - "BriefDescription": "Branch instructions per taken branch", + "BriefDescription": "Branch instructions per taken branch.", "MetricExpr": "BR_INST_RETIRED.ALL_BRANCHES / BR_INST_RETIRED.NEAR_TAKEN", "MetricGroup": "Branches;Fed;PGO", "MetricName": "tma_info_inst_mix_bptkbranch" @@ -1089,7 +1092,7 @@ "MetricGroup": "Flops;InsType", "MetricName": "tma_info_inst_mix_iparith", "MetricThreshold": "tma_info_inst_mix_iparith < 10", - "PublicDescription": "Instructions per FP Arithmetic instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting. Approximated prior to BDW" + "PublicDescription": "Instructions per FP Arithmetic instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting. Approximated prior to BDW." }, { "BriefDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number means higher occurrence rate)", @@ -1097,7 +1100,7 @@ "MetricGroup": "Flops;FpVector;InsType", "MetricName": "tma_info_inst_mix_iparith_avx128", "MetricThreshold": "tma_info_inst_mix_iparith_avx128 < 10", - "PublicDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting" + "PublicDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting." }, { "BriefDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means higher occurrence rate)", @@ -1105,7 +1108,7 @@ "MetricGroup": "Flops;FpVector;InsType", "MetricName": "tma_info_inst_mix_iparith_avx256", "MetricThreshold": "tma_info_inst_mix_iparith_avx256 < 10", - "PublicDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting" + "PublicDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting." }, { "BriefDescription": "Instructions per FP Arithmetic AVX 512-bit instruction (lower number means higher occurrence rate)", @@ -1113,7 +1116,7 @@ "MetricGroup": "Flops;FpVector;InsType", "MetricName": "tma_info_inst_mix_iparith_avx512", "MetricThreshold": "tma_info_inst_mix_iparith_avx512 < 10", - "PublicDescription": "Instructions per FP Arithmetic AVX 512-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting" + "PublicDescription": "Instructions per FP Arithmetic AVX 512-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting." }, { "BriefDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction (lower number means higher occurrence rate)", @@ -1121,7 +1124,7 @@ "MetricGroup": "Flops;FpScalar;InsType", "MetricName": "tma_info_inst_mix_iparith_scalar_dp", "MetricThreshold": "tma_info_inst_mix_iparith_scalar_dp < 10", - "PublicDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting" + "PublicDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting." }, { "BriefDescription": "Instructions per FP Arithmetic Scalar Half-Precision instruction (lower number means higher occurrence rate)", @@ -1129,7 +1132,7 @@ "MetricGroup": "Flops;FpScalar;InsType;Server", "MetricName": "tma_info_inst_mix_iparith_scalar_hp", "MetricThreshold": "tma_info_inst_mix_iparith_scalar_hp < 10", - "PublicDescription": "Instructions per FP Arithmetic Scalar Half-Precision instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting" + "PublicDescription": "Instructions per FP Arithmetic Scalar Half-Precision instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting." }, { "BriefDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction (lower number means higher occurrence rate)", @@ -1137,7 +1140,7 @@ "MetricGroup": "Flops;FpScalar;InsType", "MetricName": "tma_info_inst_mix_iparith_scalar_sp", "MetricThreshold": "tma_info_inst_mix_iparith_scalar_sp < 10", - "PublicDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting" + "PublicDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting." }, { "BriefDescription": "Instructions per Branch (lower number means higher occurrence rate)", @@ -1192,7 +1195,7 @@ "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_TAKEN", "MetricGroup": "Branches;Fed;FetchBW;Frontend;PGO;tma_issueFB", "MetricName": "tma_info_inst_mix_iptb", - "MetricThreshold": "tma_info_inst_mix_iptb < 6 * 2 + 1", + "MetricThreshold": "tma_info_inst_mix_iptb < 13", "PublicDescription": "Instructions per taken branch. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_lcp" }, { @@ -1329,7 +1332,7 @@ }, { "BriefDescription": "Average Parallel L2 cache miss demand Loads", - "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD / cpu@OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD\\,cmask\\=0x1@", + "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD / cpu@OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD\\,cmask\\=1@", "MetricGroup": "Memory_BW;Offcore", "MetricName": "tma_info_memory_latency_load_l2_mlp" }, @@ -1394,21 +1397,21 @@ "MetricExpr": "64 * OCR.READS_TO_CORE.DRAM / 1e9 / tma_info_system_time", "MetricGroup": "HPC;Mem;MemoryBW;SoC", "MetricName": "tma_info_memory_soc_r2c_dram_bw", - "PublicDescription": "Average DRAM BW for Reads-to-Core (R2C) covering for memory attached to local- and remote-socket. See R2C_Offcore_BW" + "PublicDescription": "Average DRAM BW for Reads-to-Core (R2C) covering for memory attached to local- and remote-socket. See R2C_Offcore_BW." }, { "BriefDescription": "Average L3-cache miss BW for Reads-to-Core (R2C)", "MetricExpr": "64 * OCR.READS_TO_CORE.L3_MISS / 1e9 / tma_info_system_time", "MetricGroup": "HPC;Mem;MemoryBW;SoC", "MetricName": "tma_info_memory_soc_r2c_l3m_bw", - "PublicDescription": "Average L3-cache miss BW for Reads-to-Core (R2C). This covering going to DRAM or other memory off-chip memory tears. See R2C_Offcore_BW" + "PublicDescription": "Average L3-cache miss BW for Reads-to-Core (R2C). This covering going to DRAM or other memory off-chip memory tears. See R2C_Offcore_BW." }, { "BriefDescription": "Average Off-core access BW for Reads-to-Core (R2C)", "MetricExpr": "64 * OCR.READS_TO_CORE.ANY_RESPONSE / 1e9 / tma_info_system_time", "MetricGroup": "HPC;Mem;MemoryBW;SoC", "MetricName": "tma_info_memory_soc_r2c_offcore_bw", - "PublicDescription": "Average Off-core access BW for Reads-to-Core (R2C). R2C account for demand or prefetch load/RFO/code access that fill data into the Core caches" + "PublicDescription": "Average Off-core access BW for Reads-to-Core (R2C). R2C account for demand or prefetch load/RFO/code access that fill data into the Core caches." }, { "BriefDescription": "STLB (2nd level TLB) code speculative misses per kilo instruction (misses of any page-size that complete the page walk)", @@ -1436,8 +1439,8 @@ "MetricName": "tma_info_memory_tlb_store_stlb_mpki" }, { - "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is execution) per core", - "MetricExpr": "UOPS_EXECUTED.THREAD / (UOPS_EXECUTED.CORE_CYCLES_GE_1 / 2 if #SMT_on else cpu@UOPS_EXECUTED.THREAD\\,cmask\\=0x1@)", + "BriefDescription": "", + "MetricExpr": "UOPS_EXECUTED.THREAD / (UOPS_EXECUTED.CORE_CYCLES_GE_1 / 2 if #SMT_on else cpu@UOPS_EXECUTED.THREAD\\,cmask\\=1@)", "MetricGroup": "Cor;Pipeline;PortsUtil;SMT", "MetricName": "tma_info_pipeline_execute" }, @@ -1458,18 +1461,18 @@ "MetricExpr": "INST_RETIRED.ANY / ASSISTS.ANY", "MetricGroup": "MicroSeq;Pipeline;Ret;Retire", "MetricName": "tma_info_pipeline_ipassist", - "MetricThreshold": "tma_info_pipeline_ipassist < 100000", + "MetricThreshold": "tma_info_pipeline_ipassist < 100e3", "PublicDescription": "Instructions per a microcode Assist invocation. See Assists tree node for details (lower number means higher occurrence rate)" }, { - "BriefDescription": "Average number of Uops retired in cycles where at least one uop has retired", - "MetricExpr": "tma_retiring * tma_info_thread_slots / cpu@UOPS_RETIRED.SLOTS\\,cmask\\=0x1@", + "BriefDescription": "Average number of Uops retired in cycles where at least one uop has retired.", + "MetricExpr": "tma_retiring * tma_info_thread_slots / cpu@UOPS_RETIRED.SLOTS\\,cmask\\=1@", "MetricGroup": "Pipeline;Ret", "MetricName": "tma_info_pipeline_retire" }, { "BriefDescription": "Estimated fraction of retirement-cycles dealing with repeat instructions", - "MetricExpr": "INST_RETIRED.REP_ITERATION / cpu@UOPS_RETIRED.SLOTS\\,cmask\\=0x1@", + "MetricExpr": "INST_RETIRED.REP_ITERATION / cpu@UOPS_RETIRED.SLOTS\\,cmask\\=1@", "MetricGroup": "MicroSeq;Pipeline;Ret", "MetricName": "tma_info_pipeline_strings_cycles", "MetricThreshold": "tma_info_pipeline_strings_cycles > 0.1" @@ -1532,14 +1535,13 @@ "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.FAR_BRANCH:u", "MetricGroup": "Branches;OS", "MetricName": "tma_info_system_ipfarbranch", - "MetricThreshold": "tma_info_system_ipfarbranch < 1000000" + "MetricThreshold": "tma_info_system_ipfarbranch < 1e6" }, { "BriefDescription": "Cycles Per Instruction for the Operating System (OS) Kernel mode", "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P:k / INST_RETIRED.ANY_P:k", "MetricGroup": "OS", - "MetricName": "tma_info_system_kernel_cpi", - "ScaleUnit": "1per_instr" + "MetricName": "tma_info_system_kernel_cpi" }, { "BriefDescription": "Fraction of cycles spent in the Operating System (OS) Kernel mode", @@ -1550,7 +1552,7 @@ }, { "BriefDescription": "Average latency of data read request to external DRAM memory [in nanoseconds]", - "MetricExpr": "1e9 * (UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_DDR / UNC_CHA_TOR_INSERTS.IA_MISS_DRD_DDR) / cha_0@event\\=0x0@", + "MetricExpr": "1e9 * (UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_DDR / UNC_CHA_TOR_INSERTS.IA_MISS_DRD_DDR) / uncore_cha_0@event\\=0x1@", "MetricGroup": "MemOffcore;MemoryLat;Server;SoC", "MetricName": "tma_info_system_mem_dram_read_latency", "PublicDescription": "Average latency of data read request to external DRAM memory [in nanoseconds]. Accounts for demand loads and L1/L2 data-read prefetches" @@ -1560,11 +1562,11 @@ "MetricExpr": "UNC_CHA_RxC_IRQ1_REJECT.PA_MATCH / UNC_CHA_CLOCKTICKS", "MetricGroup": "LockCont;MemOffcore;Server;SoC", "MetricName": "tma_info_system_mem_irq_duplicate_address", - "MetricThreshold": "(tma_info_system_mem_irq_duplicate_address > 0.1)" + "MetricThreshold": "tma_info_system_mem_irq_duplicate_address > 0.1" }, { "BriefDescription": "Average number of parallel data read requests to external memory", - "MetricExpr": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD / cha@UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD\\,thresh\\=0x1@", + "MetricExpr": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD / UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD@thresh\\=1@", "MetricGroup": "Mem;MemoryBW;SoC", "MetricName": "tma_info_system_mem_parallel_reads", "PublicDescription": "Average number of parallel data read requests to external memory. Accounts for demand loads and L1/L2 prefetches" @@ -1598,7 +1600,7 @@ }, { "BriefDescription": "Socket actual clocks when any core is active on that socket", - "MetricExpr": "cha_0@event\\=0x0@", + "MetricExpr": "uncore_cha_0@event\\=0x1@", "MetricGroup": "SoC", "MetricName": "tma_info_system_socket_clks" }, @@ -1628,7 +1630,7 @@ "MetricName": "tma_info_system_upi_data_transmit_bw" }, { - "BriefDescription": "Per-Logical Processor actual clocks when the Logical Processor is active", + "BriefDescription": "Per-Logical Processor actual clocks when the Logical Processor is active.", "MetricExpr": "CPU_CLK_UNHALTED.THREAD", "MetricGroup": "Pipeline", "MetricName": "tma_info_thread_clks" @@ -1637,15 +1639,14 @@ "BriefDescription": "Cycles Per Instruction (per Logical Processor)", "MetricExpr": "1 / tma_info_thread_ipc", "MetricGroup": "Mem;Pipeline", - "MetricName": "tma_info_thread_cpi", - "ScaleUnit": "1per_instr" + "MetricName": "tma_info_thread_cpi" }, { "BriefDescription": "The ratio of Executed- by Issued-Uops", "MetricExpr": "UOPS_EXECUTED.THREAD / UOPS_ISSUED.ANY", "MetricGroup": "Cor;Pipeline", "MetricName": "tma_info_thread_execute_per_issue", - "PublicDescription": "The ratio of Executed- by Issued-Uops. Ratio > 1 suggests high rate of uop micro-fusions. Ratio < 1 suggest high rate of \"execute\" at rename stage" + "PublicDescription": "The ratio of Executed- by Issued-Uops. Ratio > 1 suggests high rate of uop micro-fusions. Ratio < 1 suggest high rate of \"execute\" at rename stage." }, { "BriefDescription": "Instructions Per Cycle (per Logical Processor)", @@ -1655,13 +1656,13 @@ }, { "BriefDescription": "Total issue-pipeline slots (per-Physical Core till ICL; per-Logical Processor ICL onward)", - "MetricExpr": "slots", + "MetricExpr": "TOPDOWN.SLOTS", "MetricGroup": "TmaL1;tma_L1_group", "MetricName": "tma_info_thread_slots" }, { "BriefDescription": "Fraction of Physical Core issue-slots utilized by this Logical Processor", - "MetricExpr": "(tma_info_thread_slots / (slots / 2) if #SMT_on else 1)", + "MetricExpr": "(tma_info_thread_slots / (TOPDOWN.SLOTS / 2) if #SMT_on else 1)", "MetricGroup": "SMT;TmaL1;tma_L1_group", "MetricName": "tma_info_thread_slots_utilization" }, @@ -1677,14 +1678,14 @@ "MetricExpr": "tma_retiring * tma_info_thread_slots / BR_INST_RETIRED.NEAR_TAKEN", "MetricGroup": "Branches;Fed;FetchBW", "MetricName": "tma_info_thread_uptb", - "MetricThreshold": "tma_info_thread_uptb < 6 * 1.5" + "MetricThreshold": "tma_info_thread_uptb < 9" }, { - "BriefDescription": "This metric represents fraction of cycles where the Integer Divider unit was active", + "BriefDescription": "This metric represents fraction of cycles where the Integer Divider unit was active.", "MetricExpr": "tma_divider - tma_fp_divider", "MetricGroup": "TopdownL4;tma_L4_group;tma_divider_group", "MetricName": "tma_int_divider", - "MetricThreshold": "tma_int_divider > 0.2 & tma_divider > 0.2 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_int_divider > 0.2 & (tma_divider > 0.2 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", "ScaleUnit": "100%" }, { @@ -1693,7 +1694,7 @@ "MetricGroup": "Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group", "MetricName": "tma_int_operations", "MetricThreshold": "tma_int_operations > 0.1 & tma_light_operations > 0.6", - "PublicDescription": "This metric represents overall Integer (Int) select operations fraction the CPU has executed (retired). Vector/Matrix Int operations and shuffles are counted. Note this metric's value may exceed its parent due to use of \"Uops\" CountDomain", + "PublicDescription": "This metric represents overall Integer (Int) select operations fraction the CPU has executed (retired). Vector/Matrix Int operations and shuffles are counted. Note this metric's value may exceed its parent due to use of \"Uops\" CountDomain.", "ScaleUnit": "100%" }, { @@ -1701,8 +1702,8 @@ "MetricExpr": "(INT_VEC_RETIRED.ADD_128 + INT_VEC_RETIRED.VNNI_128) / (tma_retiring * tma_info_thread_slots)", "MetricGroup": "Compute;IntVector;Pipeline;TopdownL4;tma_L4_group;tma_int_operations_group;tma_issue2P", "MetricName": "tma_int_vector_128b", - "MetricThreshold": "tma_int_vector_128b > 0.1 & tma_int_operations > 0.1 & tma_light_operations > 0.6", - "PublicDescription": "This metric represents 128-bit vector Integer ADD/SUB/SAD or VNNI (Vector Neural Network Instructions) uops fraction the CPU has retired. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_6, tma_ports_utilized_2", + "MetricThreshold": "tma_int_vector_128b > 0.1 & (tma_int_operations > 0.1 & tma_light_operations > 0.6)", + "PublicDescription": "This metric represents 128-bit vector Integer ADD/SUB/SAD or VNNI (Vector Neural Network Instructions) uops fraction the CPU has retired. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%" }, { @@ -1710,8 +1711,8 @@ "MetricExpr": "(INT_VEC_RETIRED.ADD_256 + INT_VEC_RETIRED.MUL_256 + INT_VEC_RETIRED.VNNI_256) / (tma_retiring * tma_info_thread_slots)", "MetricGroup": "Compute;IntVector;Pipeline;TopdownL4;tma_L4_group;tma_int_operations_group;tma_issue2P", "MetricName": "tma_int_vector_256b", - "MetricThreshold": "tma_int_vector_256b > 0.1 & tma_int_operations > 0.1 & tma_light_operations > 0.6", - "PublicDescription": "This metric represents 256-bit vector Integer ADD/SUB/SAD/MUL or VNNI (Vector Neural Network Instructions) uops fraction the CPU has retired. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_port_0, tma_port_1, tma_port_6, tma_ports_utilized_2", + "MetricThreshold": "tma_int_vector_256b > 0.1 & (tma_int_operations > 0.1 & tma_light_operations > 0.6)", + "PublicDescription": "This metric represents 256-bit vector Integer ADD/SUB/SAD/MUL or VNNI (Vector Neural Network Instructions) uops fraction the CPU has retired. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%" }, { @@ -1719,8 +1720,8 @@ "MetricExpr": "ICACHE_TAG.STALLS / tma_info_thread_clks", "MetricGroup": "BigFootprint;BvBC;FetchLat;MemoryTLB;TopdownL3;tma_L3_group;tma_fetch_latency_group", "MetricName": "tma_itlb_misses", - "MetricThreshold": "tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", - "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Instruction TLB (ITLB) misses. Sample with: FRONTEND_RETIRED.STLB_MISS, FRONTEND_RETIRED.ITLB_MISS", + "MetricThreshold": "tma_itlb_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Instruction TLB (ITLB) misses. Sample with: FRONTEND_RETIRED.STLB_MISS_PS;FRONTEND_RETIRED.ITLB_MISS_PS", "ScaleUnit": "100%" }, { @@ -1728,7 +1729,7 @@ "MetricExpr": "max((EXE_ACTIVITY.BOUND_ON_LOADS - MEMORY_ACTIVITY.STALLS_L1D_MISS) / tma_info_thread_clks, 0)", "MetricGroup": "CacheHits;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_issueL1;tma_issueMC;tma_memory_bound_group", "MetricName": "tma_l1_bound", - "MetricThreshold": "tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", "PublicDescription": "This metric estimates how often the CPU was stalled without loads missing the L1 Data (L1D) cache. The L1D cache typically has the shortest latency. However; in certain cases like loads blocked on older stores; a load might suffer due to high latency even though it is being satisfied by the L1D. Another example is loads who miss in the TLB. These cases are characterized by execution unit stalls; while some non-completed demand load lives in the machine without having that demand load missing the L1 cache. Sample with: MEM_LOAD_RETIRED.L1_HIT. Related metrics: tma_clears_resteers, tma_machine_clears, tma_microcode_sequencer, tma_ms_switches, tma_ports_utilized_1", "ScaleUnit": "100%" }, @@ -1737,7 +1738,7 @@ "MetricExpr": "min(2 * (MEM_INST_RETIRED.ALL_LOADS - MEM_LOAD_RETIRED.FB_HIT - MEM_LOAD_RETIRED.L1_MISS) * 20 / 100, max(CYCLE_ACTIVITY.CYCLES_MEM_ANY - MEMORY_ACTIVITY.CYCLES_L1D_MISS, 0)) / tma_info_thread_clks", "MetricGroup": "BvML;MemoryLat;TopdownL4;tma_L4_group;tma_l1_bound_group", "MetricName": "tma_l1_latency_dependency", - "MetricThreshold": "tma_l1_latency_dependency > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_l1_latency_dependency > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", "PublicDescription": "This metric([SKL+] roughly; [LNL]) estimates fraction of cycles with demand load accesses that hit the L1D cache. The short latency of the L1D cache may be exposed in pointer-chasing memory access patterns as an example. Sample with: MEM_LOAD_RETIRED.L1_HIT", "ScaleUnit": "100%" }, @@ -1746,16 +1747,17 @@ "MetricExpr": "(MEMORY_ACTIVITY.STALLS_L1D_MISS - MEMORY_ACTIVITY.STALLS_L2_MISS) / tma_info_thread_clks", "MetricGroup": "BvML;CacheHits;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_l2_bound", - "MetricThreshold": "tma_l2_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_l2_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", "PublicDescription": "This metric estimates how often the CPU was stalled due to L2 cache accesses by loads. Avoiding cache misses (i.e. L1 misses/L2 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L2_HIT", "ScaleUnit": "100%" }, { "BriefDescription": "This metric represents fraction of cycles with demand load accesses that hit the L2 cache under unloaded scenarios (possibly L2 latency limited)", + "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "4.4 * tma_info_system_core_frequency * MEM_LOAD_RETIRED.L2_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks", "MetricGroup": "MemoryLat;TopdownL4;tma_L4_group;tma_l2_bound_group", "MetricName": "tma_l2_hit_latency", - "MetricThreshold": "tma_l2_hit_latency > 0.05 & tma_l2_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_l2_hit_latency > 0.05 & (tma_l2_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", "PublicDescription": "This metric represents fraction of cycles with demand load accesses that hit the L2 cache under unloaded scenarios (possibly L2 latency limited). Avoiding L1 cache misses (i.e. L1 misses/L2 hits) will improve the latency. Sample with: MEM_LOAD_RETIRED.L2_HIT", "ScaleUnit": "100%" }, @@ -1764,17 +1766,18 @@ "MetricExpr": "(MEMORY_ACTIVITY.STALLS_L2_MISS - MEMORY_ACTIVITY.STALLS_L3_MISS) / tma_info_thread_clks", "MetricGroup": "CacheHits;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_l3_bound", - "MetricThreshold": "tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", - "PublicDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core. Avoiding cache misses (i.e. L2 misses/L3 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L3_HIT", + "MetricThreshold": "tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", + "PublicDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core. Avoiding cache misses (i.e. L2 misses/L3 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L3_HIT_PS", "ScaleUnit": "100%" }, { "BriefDescription": "This metric estimates fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited)", - "MetricExpr": "(37 * tma_info_system_core_frequency - 4.4 * tma_info_system_core_frequency) * (MEM_LOAD_RETIRED.L3_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2)) / tma_info_thread_clks", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "32.6 * tma_info_system_core_frequency * (MEM_LOAD_RETIRED.L3_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2)) / tma_info_thread_clks", "MetricGroup": "BvML;MemoryLat;TopdownL4;tma_L4_group;tma_issueLat;tma_l3_bound_group", "MetricName": "tma_l3_hit_latency", - "MetricThreshold": "tma_l3_hit_latency > 0.1 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", - "PublicDescription": "This metric estimates fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited). Avoiding private cache misses (i.e. L2 misses/L3 hits) will improve the latency; reduce contention with sibling physical cores and increase performance. Note the value of this node may overlap with its siblings. Sample with: MEM_LOAD_RETIRED.L3_HIT. Related metrics: tma_bottleneck_cache_memory_latency, tma_branch_resteers, tma_mem_latency, tma_store_latency", + "MetricThreshold": "tma_l3_hit_latency > 0.1 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric estimates fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited). Avoiding private cache misses (i.e. L2 misses/L3 hits) will improve the latency; reduce contention with sibling physical cores and increase performance. Note the value of this node may overlap with its siblings. Sample with: MEM_LOAD_RETIRED.L3_HIT_PS. Related metrics: tma_bottleneck_cache_memory_latency, tma_mem_latency", "ScaleUnit": "100%" }, { @@ -1782,19 +1785,19 @@ "MetricExpr": "DECODE.LCP / tma_info_thread_clks", "MetricGroup": "FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueFB", "MetricName": "tma_lcp", - "MetricThreshold": "tma_lcp > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", - "PublicDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs). Using proper compiler flags or Intel Compiler by default will certainly avoid this. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb", + "MetricThreshold": "tma_lcp > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", + "PublicDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs). Using proper compiler flags or Intel Compiler by default will certainly avoid this. #Link: Optimization Guide about LCP BKMs. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations , instructions that require no more than one uop (micro-operation)", + "BriefDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation)", "DefaultMetricgroupName": "TopdownL2", "MetricExpr": "max(0, tma_retiring - tma_heavy_operations)", "MetricGroup": "Default;Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_light_operations", "MetricThreshold": "tma_light_operations > 0.6", "MetricgroupNoGroup": "TopdownL2;Default", - "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations , instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized code running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. ([ICL+] Note this may undercount due to approximation using indirect events; [ADL+] .). Sample with: INST_RETIRED.PREC_DIST", + "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized code running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. ([ICL+] Note this may undercount due to approximation using indirect events; [ADL+] .). Sample with: INST_RETIRED.PREC_DIST", "ScaleUnit": "100%" }, { @@ -1811,7 +1814,7 @@ "MetricExpr": "tma_dtlb_load - tma_load_stlb_miss", "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_load_group", "MetricName": "tma_load_stlb_hit", - "MetricThreshold": "tma_load_stlb_hit > 0.05 & tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_load_stlb_hit > 0.05 & (tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))", "ScaleUnit": "100%" }, { @@ -1819,39 +1822,39 @@ "MetricExpr": "DTLB_LOAD_MISSES.WALK_ACTIVE / tma_info_thread_clks", "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_load_group", "MetricName": "tma_load_stlb_miss", - "MetricThreshold": "tma_load_stlb_miss > 0.05 & tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_load_stlb_miss > 0.05 & (tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 1 GB pages for data load accesses", + "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 1 GB pages for data load accesses.", "MetricExpr": "tma_load_stlb_miss * DTLB_LOAD_MISSES.WALK_COMPLETED_1G / (DTLB_LOAD_MISSES.WALK_COMPLETED_4K + DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M + DTLB_LOAD_MISSES.WALK_COMPLETED_1G)", "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_load_stlb_miss_group", "MetricName": "tma_load_stlb_miss_1g", - "MetricThreshold": "tma_load_stlb_miss_1g > 0.05 & tma_load_stlb_miss > 0.05 & tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_load_stlb_miss_1g > 0.05 & (tma_load_stlb_miss > 0.05 & (tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))))", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 2 or 4 MB pages for data load accesses", + "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 2 or 4 MB pages for data load accesses.", "MetricExpr": "tma_load_stlb_miss * DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M / (DTLB_LOAD_MISSES.WALK_COMPLETED_4K + DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M + DTLB_LOAD_MISSES.WALK_COMPLETED_1G)", "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_load_stlb_miss_group", "MetricName": "tma_load_stlb_miss_2m", - "MetricThreshold": "tma_load_stlb_miss_2m > 0.05 & tma_load_stlb_miss > 0.05 & tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_load_stlb_miss_2m > 0.05 & (tma_load_stlb_miss > 0.05 & (tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))))", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 4 KB pages for data load accesses", + "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 4 KB pages for data load accesses.", "MetricExpr": "tma_load_stlb_miss * DTLB_LOAD_MISSES.WALK_COMPLETED_4K / (DTLB_LOAD_MISSES.WALK_COMPLETED_4K + DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M + DTLB_LOAD_MISSES.WALK_COMPLETED_1G)", "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_load_stlb_miss_group", "MetricName": "tma_load_stlb_miss_4k", - "MetricThreshold": "tma_load_stlb_miss_4k > 0.05 & tma_load_stlb_miss > 0.05 & tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_load_stlb_miss_4k > 0.05 & (tma_load_stlb_miss > 0.05 & (tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))))", "ScaleUnit": "100%" }, { "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from local memory", - "MetricExpr": "(109 * tma_info_system_core_frequency - 37 * tma_info_system_core_frequency) * MEM_LOAD_L3_MISS_RETIRED.LOCAL_DRAM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks", + "MetricExpr": "72 * tma_info_system_core_frequency * MEM_LOAD_L3_MISS_RETIRED.LOCAL_DRAM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks", "MetricGroup": "Server;TopdownL5;tma_L5_group;tma_mem_latency_group", "MetricName": "tma_local_mem", - "MetricThreshold": "tma_local_mem > 0.1 & tma_mem_latency > 0.1 & tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_local_mem > 0.1 & (tma_mem_latency > 0.1 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))", "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from local memory. Caching will improve the latency and increase performance. Sample with: MEM_LOAD_L3_MISS_RETIRED.LOCAL_DRAM", "ScaleUnit": "100%" }, @@ -1860,7 +1863,7 @@ "MetricExpr": "(16 * max(0, MEM_INST_RETIRED.LOCK_LOADS - L2_RQSTS.ALL_RFO) + MEM_INST_RETIRED.LOCK_LOADS / MEM_INST_RETIRED.ALL_STORES * (10 * L2_RQSTS.RFO_HIT + min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO))) / tma_info_thread_clks", "MetricGroup": "LockCont;Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_l1_bound_group", "MetricName": "tma_lock_latency", - "MetricThreshold": "tma_lock_latency > 0.2 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_lock_latency > 0.2 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", "PublicDescription": "This metric represents fraction of cycles the CPU spent handling cache misses due to lock operations. Due to the microarchitecture handling of locks; they are classified as L1_Bound regardless of what memory source satisfied them. Sample with: MEM_INST_RETIRED.LOCK_LOADS. Related metrics: tma_store_latency", "ScaleUnit": "100%" }, @@ -1876,19 +1879,19 @@ "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to memory bandwidth Allocation feature (RDT's memory bandwidth throttling)", + "BriefDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to memory bandwidth Allocation feature (RDT's memory bandwidth throttling).", "MetricExpr": "INT_MISC.MBA_STALLS / tma_info_thread_clks", "MetricGroup": "MemoryBW;Offcore;Server;TopdownL5;tma_L5_group;tma_mem_bandwidth_group", "MetricName": "tma_mba_stalls", - "MetricThreshold": "tma_mba_stalls > 0.1 & tma_mem_bandwidth > 0.2 & tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_mba_stalls > 0.1 & (tma_mem_bandwidth > 0.2 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))", "ScaleUnit": "100%" }, { "BriefDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory - DRAM ([SPR-HBM] and/or HBM)", - "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, cpu@OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD\\,cmask\\=0x4@) / tma_info_thread_clks", + "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, cpu@OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD\\,cmask\\=4@) / tma_info_thread_clks", "MetricGroup": "BvMB;MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueBW", "MetricName": "tma_mem_bandwidth", - "MetricThreshold": "tma_mem_bandwidth > 0.2 & tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_mem_bandwidth > 0.2 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", "PublicDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory - DRAM ([SPR-HBM] and/or HBM). The underlying heuristic assumes that a similar off-core traffic is generated by all IA cores. This metric does not aggregate non-data-read requests by this logical processor; requests from other IA Logical Processors/Physical Cores/sockets; or other non-IA devices like GPU; hence the maximum external memory bandwidth limits may or may not be approached when this metric is flagged (see Uncore counters for that). Related metrics: tma_bottleneck_cache_memory_bandwidth, tma_fb_full, tma_info_system_dram_bw_use, tma_sq_full", "ScaleUnit": "100%" }, @@ -1897,32 +1900,32 @@ "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD) / tma_info_thread_clks - tma_mem_bandwidth", "MetricGroup": "BvML;MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueLat", "MetricName": "tma_mem_latency", - "MetricThreshold": "tma_mem_latency > 0.1 & tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_mem_latency > 0.1 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", "PublicDescription": "This metric estimates fraction of cycles where the performance was likely hurt due to latency from external memory - DRAM ([SPR-HBM] and/or HBM). This metric does not aggregate requests from other Logical Processors/Physical Cores/sockets (see Uncore counters for that). Related metrics: tma_bottleneck_cache_memory_latency, tma_l3_hit_latency", "ScaleUnit": "100%" }, { "BriefDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck", "DefaultMetricgroupName": "TopdownL2", - "MetricExpr": "topdown\\-mem\\-bound / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * slots", + "MetricExpr": "topdown\\-mem\\-bound / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * tma_info_thread_slots", "MetricGroup": "Backend;Default;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_memory_bound", "MetricThreshold": "tma_memory_bound > 0.2 & tma_backend_bound > 0.2", "MetricgroupNoGroup": "TopdownL2;Default", - "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck. Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two)", + "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck. Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two).", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to LFENCE Instructions", + "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to LFENCE Instructions.", "MetricConstraint": "NO_GROUP_EVENTS_NMI", "MetricExpr": "13 * MISC2_RETIRED.LFENCE / tma_info_thread_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_serializing_operation_group", "MetricName": "tma_memory_fence", - "MetricThreshold": "tma_memory_fence > 0.05 & tma_serializing_operation > 0.1 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_memory_fence > 0.05 & (tma_serializing_operation > 0.1 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of slots where the CPU was retiring memory operations , uops for memory load or store accesses", + "BriefDescription": "This metric represents fraction of slots where the CPU was retiring memory operations -- uops for memory load or store accesses.", "MetricExpr": "tma_light_operations * MEM_UOP_RETIRED.ANY / (tma_retiring * tma_info_thread_slots)", "MetricGroup": "Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group", "MetricName": "tma_memory_operations", @@ -1943,7 +1946,7 @@ "MetricExpr": "tma_branch_mispredicts / tma_bad_speculation * INT_MISC.CLEAR_RESTEER_CYCLES / tma_info_thread_clks", "MetricGroup": "BadSpec;BrMispredicts;BvMP;TopdownL4;tma_L4_group;tma_branch_resteers_group;tma_issueBM", "MetricName": "tma_mispredicts_resteers", - "MetricThreshold": "tma_mispredicts_resteers > 0.05 & tma_branch_resteers > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricThreshold": "tma_mispredicts_resteers > 0.05 & (tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))", "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Branch Misprediction at execution stage. Sample with: INT_MISC.CLEAR_RESTEER_CYCLES. Related metrics: tma_bottleneck_mispredictions, tma_branch_mispredicts, tma_info_bad_spec_branch_misprediction_cost", "ScaleUnit": "100%" }, @@ -1957,17 +1960,17 @@ "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates penalty in terms of percentage of([SKL+] injected blend uops out of all Uops Issued , the Count Domain; [ADL+] cycles)", + "BriefDescription": "This metric estimates penalty in terms of percentage of([SKL+] injected blend uops out of all Uops Issued -- the Count Domain; [ADL+] cycles)", "MetricExpr": "160 * ASSISTS.SSE_AVX_MIX / tma_info_thread_clks", "MetricGroup": "TopdownL5;tma_L5_group;tma_issueMV;tma_ports_utilized_0_group", "MetricName": "tma_mixing_vectors", "MetricThreshold": "tma_mixing_vectors > 0.05", - "PublicDescription": "This metric estimates penalty in terms of percentage of([SKL+] injected blend uops out of all Uops Issued , the Count Domain; [ADL+] cycles). Usually a Mixing_Vectors over 5% is worth investigating. Read more in Appendix B1 of the Optimizations Guide for this topic. Related metrics: tma_ms_switches", + "PublicDescription": "This metric estimates penalty in terms of percentage of([SKL+] injected blend uops out of all Uops Issued -- the Count Domain; [ADL+] cycles). Usually a Mixing_Vectors over 5% is worth investigating. Read more in Appendix B1 of the Optimizations Guide for this topic. Related metrics: tma_ms_switches", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to the Microcode Sequencer (MS) unit - see Microcode_Sequencer node for details", - "MetricExpr": "max(IDQ.MS_CYCLES_ANY, cpu@UOPS_RETIRED.MS\\,cmask\\=0x1@ / (UOPS_RETIRED.SLOTS / UOPS_ISSUED.ANY)) / tma_info_core_core_clks / 2", + "BriefDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to the Microcode Sequencer (MS) unit - see Microcode_Sequencer node for details.", + "MetricExpr": "max(IDQ.MS_CYCLES_ANY, cpu@UOPS_RETIRED.MS\\,cmask\\=1@ / (UOPS_RETIRED.SLOTS / UOPS_ISSUED.ANY)) / tma_info_core_core_clks / 2", "MetricGroup": "MicroSeq;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group", "MetricName": "tma_ms", "MetricThreshold": "tma_ms > 0.05 & tma_fetch_bandwidth > 0.2", @@ -1975,10 +1978,10 @@ }, { "BriefDescription": "This metric estimates the fraction of cycles when the CPU was stalled due to switches of uop delivery to the Microcode Sequencer (MS)", - "MetricExpr": "3 * cpu@UOPS_RETIRED.MS\\,cmask\\=0x1\\,edge\\=0x1@ / (UOPS_RETIRED.SLOTS / UOPS_ISSUED.ANY) / tma_info_thread_clks", + "MetricExpr": "3 * cpu@UOPS_RETIRED.MS\\,cmask\\=1\\,edge@ / (UOPS_RETIRED.SLOTS / UOPS_ISSUED.ANY) / tma_info_thread_clks", "MetricGroup": "FetchLat;MicroSeq;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueMC;tma_issueMS;tma_issueMV;tma_issueSO", "MetricName": "tma_ms_switches", - "MetricThreshold": "tma_ms_switches > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricThreshold": "tma_ms_switches > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", "PublicDescription": "This metric estimates the fraction of cycles when the CPU was stalled due to switches of uop delivery to the Microcode Sequencer (MS). Commonly used instructions are optimized for delivery by the DSB (decoded i-cache) or MITE (legacy instruction decode) pipelines. Certain operations cannot be handled natively by the execution pipeline; and must be performed by microcode (small programs injected into the execution stream). Switching to the MS too often can negatively impact performance. The MS is designated to deliver long uop flows required by CISC instructions like CPUID; or uncommon conditions like Floating Point Assists when dealing with Denormals. Sample with: FRONTEND_RETIRED.MS_FLOWS. Related metrics: tma_bottleneck_irregular_overhead, tma_clears_resteers, tma_l1_bound, tma_machine_clears, tma_microcode_sequencer, tma_mixing_vectors, tma_serializing_operation", "ScaleUnit": "100%" }, @@ -1988,7 +1991,7 @@ "MetricGroup": "Branches;BvBO;Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group", "MetricName": "tma_non_fused_branches", "MetricThreshold": "tma_non_fused_branches > 0.1 & tma_light_operations > 0.6", - "PublicDescription": "This metric represents fraction of slots where the CPU was retiring branch instructions that were not fused. Non-conditional branches like direct JMP or CALL would count here. Can be used to examine fusible conditional jumps that were not fused", + "PublicDescription": "This metric represents fraction of slots where the CPU was retiring branch instructions that were not fused. Non-conditional branches like direct JMP or CALL would count here. Can be used to examine fusible conditional jumps that were not fused.", "ScaleUnit": "100%" }, { @@ -1996,7 +1999,7 @@ "MetricExpr": "tma_light_operations * INST_RETIRED.NOP / (tma_retiring * tma_info_thread_slots)", "MetricGroup": "BvBO;Pipeline;TopdownL4;tma_L4_group;tma_other_light_ops_group", "MetricName": "tma_nop_instructions", - "MetricThreshold": "tma_nop_instructions > 0.1 & tma_other_light_ops > 0.3 & tma_light_operations > 0.6", + "MetricThreshold": "tma_nop_instructions > 0.1 & (tma_other_light_ops > 0.3 & tma_light_operations > 0.6)", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring NOP (no op) instructions. Compilers often use NOPs for certain address alignments - e.g. start address of a function or loop body. Sample with: INST_RETIRED.NOP", "ScaleUnit": "100%" }, @@ -2010,19 +2013,19 @@ "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates fraction of slots the CPU was stalled due to other cases of misprediction (non-retired x86 branches or other types)", + "BriefDescription": "This metric estimates fraction of slots the CPU was stalled due to other cases of misprediction (non-retired x86 branches or other types).", "MetricExpr": "max(tma_branch_mispredicts * (1 - BR_MISP_RETIRED.ALL_BRANCHES / (INT_MISC.CLEARS_COUNT - MACHINE_CLEARS.COUNT)), 0.0001)", "MetricGroup": "BrMispredicts;BvIO;TopdownL3;tma_L3_group;tma_branch_mispredicts_group", "MetricName": "tma_other_mispredicts", - "MetricThreshold": "tma_other_mispredicts > 0.05 & tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", + "MetricThreshold": "tma_other_mispredicts > 0.05 & (tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15)", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of slots the CPU has wasted due to Nukes (Machine Clears) not related to memory ordering", + "BriefDescription": "This metric represents fraction of slots the CPU has wasted due to Nukes (Machine Clears) not related to memory ordering.", "MetricExpr": "max(tma_machine_clears * (1 - MACHINE_CLEARS.MEMORY_ORDERING / MACHINE_CLEARS.COUNT), 0.0001)", "MetricGroup": "BvIO;Machine_Clears;TopdownL3;tma_L3_group;tma_machine_clears_group", "MetricName": "tma_other_nukes", - "MetricThreshold": "tma_other_nukes > 0.05 & tma_machine_clears > 0.1 & tma_bad_speculation > 0.15", + "MetricThreshold": "tma_other_nukes > 0.05 & (tma_machine_clears > 0.1 & tma_bad_speculation > 0.15)", "ScaleUnit": "100%" }, { @@ -2031,7 +2034,7 @@ "MetricGroup": "TopdownL5;tma_L5_group;tma_assists_group", "MetricName": "tma_page_faults", "MetricThreshold": "tma_page_faults > 0.05", - "PublicDescription": "This metric roughly estimates fraction of slots the CPU retired uops as a result of handing Page Faults. A Page Fault may apply on first application access to a memory page. Note operating system handling of page faults accounts for the majority of its cost", + "PublicDescription": "This metric roughly estimates fraction of slots the CPU retired uops as a result of handing Page Faults. A Page Fault may apply on first application access to a memory page. Note operating system handling of page faults accounts for the majority of its cost.", "ScaleUnit": "100%" }, { @@ -2040,7 +2043,7 @@ "MetricGroup": "Compute;TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P", "MetricName": "tma_port_0", "MetricThreshold": "tma_port_0 > 0.6", - "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 0 ([SNB+] ALU; [HSW+] ALU and 2nd branch). Sample with: UOPS_DISPATCHED.PORT_0. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_1, tma_port_6, tma_ports_utilized_2", + "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 0 ([SNB+] ALU; [HSW+] ALU and 2nd branch). Sample with: UOPS_DISPATCHED.PORT_0. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%" }, { @@ -2049,7 +2052,7 @@ "MetricGroup": "TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P", "MetricName": "tma_port_1", "MetricThreshold": "tma_port_1 > 0.6", - "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 1 (ALU). Sample with: UOPS_DISPATCHED.PORT_1. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_6, tma_ports_utilized_2", + "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 1 (ALU). Sample with: UOPS_DISPATCHED.PORT_1. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_5, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%" }, { @@ -2058,7 +2061,7 @@ "MetricGroup": "TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P", "MetricName": "tma_port_6", "MetricThreshold": "tma_port_6 > 0.6", - "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 6 ([HSW+] Primary Branch and simple ALU). Sample with: UOPS_DISPATCHED.PORT_1. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_ports_utilized_2", + "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 6 ([HSW+] Primary Branch and simple ALU). Sample with: UOPS_DISPATCHED.PORT_1. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_ports_utilized_2", "ScaleUnit": "100%" }, { @@ -2066,8 +2069,8 @@ "MetricExpr": "((tma_ports_utilized_0 * tma_info_thread_clks + (EXE_ACTIVITY.1_PORTS_UTIL + tma_retiring * EXE_ACTIVITY.2_3_PORTS_UTIL)) / tma_info_thread_clks if ARITH.DIV_ACTIVE < CYCLE_ACTIVITY.STALLS_TOTAL - EXE_ACTIVITY.BOUND_ON_LOADS else (EXE_ACTIVITY.1_PORTS_UTIL + tma_retiring * EXE_ACTIVITY.2_3_PORTS_UTIL) / tma_info_thread_clks)", "MetricGroup": "PortsUtil;TopdownL3;tma_L3_group;tma_core_bound_group", "MetricName": "tma_ports_utilization", - "MetricThreshold": "tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", - "PublicDescription": "This metric estimates fraction of cycles the CPU performance was potentially limited due to Core computation issues (non divider-related). Two distinct categories can be attributed into this metric: (1) heavy data-dependency among contiguous instructions would manifest in this metric - such cases are often referred to as low Instruction Level Parallelism (ILP). (2) Contention on some hardware execution unit other than Divider. For example; when there are too many multiply operations", + "MetricThreshold": "tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)", + "PublicDescription": "This metric estimates fraction of cycles the CPU performance was potentially limited due to Core computation issues (non divider-related). Two distinct categories can be attributed into this metric: (1) heavy data-dependency among contiguous instructions would manifest in this metric - such cases are often referred to as low Instruction Level Parallelism (ILP). (2) Contention on some hardware execution unit other than Divider. For example; when there are too many multiply operations.", "ScaleUnit": "100%" }, { @@ -2075,8 +2078,8 @@ "MetricExpr": "(EXE_ACTIVITY.EXE_BOUND_0_PORTS + max(RS.EMPTY_RESOURCE - RESOURCE_STALLS.SCOREBOARD, 0)) / tma_info_thread_clks * (CYCLE_ACTIVITY.STALLS_TOTAL - EXE_ACTIVITY.BOUND_ON_LOADS) / tma_info_thread_clks", "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group", "MetricName": "tma_ports_utilized_0", - "MetricThreshold": "tma_ports_utilized_0 > 0.2 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", - "PublicDescription": "This metric represents fraction of cycles CPU executed no uops on any execution port (Logical Processor cycles since ICL, Physical Core cycles otherwise). Long-latency instructions like divides may contribute to this metric", + "MetricThreshold": "tma_ports_utilized_0 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric represents fraction of cycles CPU executed no uops on any execution port (Logical Processor cycles since ICL, Physical Core cycles otherwise). Long-latency instructions like divides may contribute to this metric.", "ScaleUnit": "100%" }, { @@ -2084,7 +2087,7 @@ "MetricExpr": "EXE_ACTIVITY.1_PORTS_UTIL / tma_info_thread_clks", "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_issueL1;tma_ports_utilization_group", "MetricName": "tma_ports_utilized_1", - "MetricThreshold": "tma_ports_utilized_1 > 0.2 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_ports_utilized_1 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", "PublicDescription": "This metric represents fraction of cycles where the CPU executed total of 1 uop per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise). This can be due to heavy data-dependency among software instructions; or over oversubscribing a particular hardware resource. In some other cases with high 1_Port_Utilized and L1_Bound; this metric can point to L1 data-cache latency bottleneck that may not necessarily manifest with complete execution starvation (due to the short L1 latency e.g. walking a linked list) - looking at the assembly can be helpful. Sample with: EXE_ACTIVITY.1_PORTS_UTIL. Related metrics: tma_l1_bound", "ScaleUnit": "100%" }, @@ -2094,8 +2097,8 @@ "MetricExpr": "EXE_ACTIVITY.2_PORTS_UTIL / tma_info_thread_clks", "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_issue2P;tma_ports_utilization_group", "MetricName": "tma_ports_utilized_2", - "MetricThreshold": "tma_ports_utilized_2 > 0.15 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", - "PublicDescription": "This metric represents fraction of cycles CPU executed total of 2 uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise). Loop Vectorization -most compilers feature auto-Vectorization options today- reduces pressure on the execution ports as multiple elements are calculated with same uop. Sample with: EXE_ACTIVITY.2_PORTS_UTIL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_6", + "MetricThreshold": "tma_ports_utilized_2 > 0.15 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric represents fraction of cycles CPU executed total of 2 uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise). Loop Vectorization -most compilers feature auto-Vectorization options today- reduces pressure on the execution ports as multiple elements are calculated with same uop. Sample with: EXE_ACTIVITY.2_PORTS_UTIL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_port_6", "ScaleUnit": "100%" }, { @@ -2104,32 +2107,32 @@ "MetricExpr": "UOPS_EXECUTED.CYCLES_GE_3 / tma_info_thread_clks", "MetricGroup": "BvCB;PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group", "MetricName": "tma_ports_utilized_3m", - "MetricThreshold": "tma_ports_utilized_3m > 0.4 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_ports_utilized_3m > 0.4 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", "PublicDescription": "This metric represents fraction of cycles CPU executed total of 3 or more uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise). Sample with: UOPS_EXECUTED.CYCLES_GE_3", "ScaleUnit": "100%" }, { "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from remote cache in other sockets including synchronizations issues", - "MetricExpr": "((170 * tma_info_system_core_frequency - 37 * tma_info_system_core_frequency) * MEM_LOAD_L3_MISS_RETIRED.REMOTE_HITM + (170 * tma_info_system_core_frequency - 37 * tma_info_system_core_frequency) * MEM_LOAD_L3_MISS_RETIRED.REMOTE_FWD) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks", + "MetricExpr": "(133 * tma_info_system_core_frequency * MEM_LOAD_L3_MISS_RETIRED.REMOTE_HITM + 133 * tma_info_system_core_frequency * MEM_LOAD_L3_MISS_RETIRED.REMOTE_FWD) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks", "MetricGroup": "Offcore;Server;Snoop;TopdownL5;tma_L5_group;tma_issueSyncxn;tma_mem_latency_group", "MetricName": "tma_remote_cache", - "MetricThreshold": "tma_remote_cache > 0.05 & tma_mem_latency > 0.1 & tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", - "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from remote cache in other sockets including synchronizations issues. This is caused often due to non-optimal NUMA allocations. Sample with: MEM_LOAD_L3_MISS_RETIRED.REMOTE_HITM, MEM_LOAD_L3_MISS_RETIRED.REMOTE_FWD. Related metrics: tma_bottleneck_memory_synchronization, tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_machine_clears", + "MetricThreshold": "tma_remote_cache > 0.05 & (tma_mem_latency > 0.1 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))", + "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from remote cache in other sockets including synchronizations issues. This is caused often due to non-optimal NUMA allocations. #link to NUMA article. Sample with: MEM_LOAD_L3_MISS_RETIRED.REMOTE_HITM_PS;MEM_LOAD_L3_MISS_RETIRED.REMOTE_FWD_PS. Related metrics: tma_bottleneck_memory_synchronization, tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_machine_clears", "ScaleUnit": "100%" }, { "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from remote memory", - "MetricExpr": "(190 * tma_info_system_core_frequency - 37 * tma_info_system_core_frequency) * MEM_LOAD_L3_MISS_RETIRED.REMOTE_DRAM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks", + "MetricExpr": "153 * tma_info_system_core_frequency * MEM_LOAD_L3_MISS_RETIRED.REMOTE_DRAM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks", "MetricGroup": "Server;Snoop;TopdownL5;tma_L5_group;tma_mem_latency_group", "MetricName": "tma_remote_mem", - "MetricThreshold": "tma_remote_mem > 0.1 & tma_mem_latency > 0.1 & tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", - "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from remote memory. This is caused often due to non-optimal NUMA allocations. Sample with: MEM_LOAD_L3_MISS_RETIRED.REMOTE_DRAM", + "MetricThreshold": "tma_remote_mem > 0.1 & (tma_mem_latency > 0.1 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))", + "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from remote memory. This is caused often due to non-optimal NUMA allocations. #link to NUMA article. Sample with: MEM_LOAD_L3_MISS_RETIRED.REMOTE_DRAM_PS", "ScaleUnit": "100%" }, { "BriefDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired", "DefaultMetricgroupName": "TopdownL1", - "MetricExpr": "topdown\\-retiring / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * slots", + "MetricExpr": "topdown\\-retiring / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * tma_info_thread_slots", "MetricGroup": "BvUW;Default;TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_retiring", "MetricThreshold": "tma_retiring > 0.7 | tma_heavy_operations > 0.1", @@ -2142,7 +2145,7 @@ "MetricExpr": "RESOURCE_STALLS.SCOREBOARD / tma_info_thread_clks + tma_c02_wait", "MetricGroup": "BvIO;PortsUtil;TopdownL3;tma_L3_group;tma_core_bound_group;tma_issueSO", "MetricName": "tma_serializing_operation", - "MetricThreshold": "tma_serializing_operation > 0.1 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_serializing_operation > 0.1 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)", "PublicDescription": "This metric represents fraction of cycles the CPU issue-pipeline was stalled due to serializing operations. Instructions like CPUID; WRMSR or LFENCE serialize the out-of-order execution which may limit performance. Sample with: RESOURCE_STALLS.SCOREBOARD. Related metrics: tma_ms_switches", "ScaleUnit": "100%" }, @@ -2151,8 +2154,8 @@ "MetricExpr": "tma_light_operations * INT_VEC_RETIRED.SHUFFLES / (tma_retiring * tma_info_thread_slots)", "MetricGroup": "HPC;Pipeline;TopdownL4;tma_L4_group;tma_other_light_ops_group", "MetricName": "tma_shuffles_256b", - "MetricThreshold": "tma_shuffles_256b > 0.1 & tma_other_light_ops > 0.3 & tma_light_operations > 0.6", - "PublicDescription": "This metric represents fraction of slots where the CPU was retiring Shuffle operations of 256-bit vector size (FP or Integer). Shuffles may incur slow cross \"vector lane\" data transfers", + "MetricThreshold": "tma_shuffles_256b > 0.1 & (tma_other_light_ops > 0.3 & tma_light_operations > 0.6)", + "PublicDescription": "This metric represents fraction of slots where the CPU was retiring Shuffle operations of 256-bit vector size (FP or Integer). Shuffles may incur slow cross \"vector lane\" data transfers.", "ScaleUnit": "100%" }, { @@ -2161,7 +2164,7 @@ "MetricExpr": "CPU_CLK_UNHALTED.PAUSE / tma_info_thread_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_serializing_operation_group", "MetricName": "tma_slow_pause", - "MetricThreshold": "tma_slow_pause > 0.05 & tma_serializing_operation > 0.1 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_slow_pause > 0.05 & (tma_serializing_operation > 0.1 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to PAUSE Instructions. Sample with: CPU_CLK_UNHALTED.PAUSE_INST", "ScaleUnit": "100%" }, @@ -2171,7 +2174,7 @@ "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group", "MetricName": "tma_split_loads", "MetricThreshold": "tma_split_loads > 0.3", - "PublicDescription": "This metric estimates fraction of cycles handling memory load split accesses - load that cross 64-byte cache line boundary. Sample with: MEM_INST_RETIRED.SPLIT_LOADS", + "PublicDescription": "This metric estimates fraction of cycles handling memory load split accesses - load that cross 64-byte cache line boundary. Sample with: MEM_INST_RETIRED.SPLIT_LOADS_PS", "ScaleUnit": "100%" }, { @@ -2179,8 +2182,8 @@ "MetricExpr": "MEM_INST_RETIRED.SPLIT_STORES / tma_info_core_core_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_issueSpSt;tma_store_bound_group", "MetricName": "tma_split_stores", - "MetricThreshold": "tma_split_stores > 0.2 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", - "PublicDescription": "This metric represents rate of split store accesses. Consider aligning your data to the 64-byte cache line granularity. Sample with: MEM_INST_RETIRED.SPLIT_STORES", + "MetricThreshold": "tma_split_stores > 0.2 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric represents rate of split store accesses. Consider aligning your data to the 64-byte cache line granularity. Sample with: MEM_INST_RETIRED.SPLIT_STORES_PS. Related metrics: tma_port_4", "ScaleUnit": "100%" }, { @@ -2188,7 +2191,7 @@ "MetricExpr": "(XQ.FULL_CYCLES + L1D_PEND_MISS.L2_STALLS) / tma_info_thread_clks", "MetricGroup": "BvMB;MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_issueBW;tma_l3_bound_group", "MetricName": "tma_sq_full", - "MetricThreshold": "tma_sq_full > 0.3 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_sq_full > 0.3 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", "PublicDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors). Related metrics: tma_bottleneck_cache_memory_bandwidth, tma_fb_full, tma_info_system_dram_bw_use, tma_mem_bandwidth", "ScaleUnit": "100%" }, @@ -2197,8 +2200,8 @@ "MetricExpr": "EXE_ACTIVITY.BOUND_ON_STORES / tma_info_thread_clks", "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_store_bound", - "MetricThreshold": "tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", - "PublicDescription": "This metric estimates how often CPU was stalled due to RFO store memory accesses; RFO store issue a read-for-ownership request before the write. Even though store accesses do not typically stall out-of-order CPUs; there are few cases where stores can lead to actual stalls. This metric will be flagged should RFO stores be a bottleneck. Sample with: MEM_INST_RETIRED.ALL_STORES", + "MetricThreshold": "tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", + "PublicDescription": "This metric estimates how often CPU was stalled due to RFO store memory accesses; RFO store issue a read-for-ownership request before the write. Even though store accesses do not typically stall out-of-order CPUs; there are few cases where stores can lead to actual stalls. This metric will be flagged should RFO stores be a bottleneck. Sample with: MEM_INST_RETIRED.ALL_STORES_PS", "ScaleUnit": "100%" }, { @@ -2206,8 +2209,8 @@ "MetricExpr": "13 * LD_BLOCKS.STORE_FORWARD / tma_info_thread_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group", "MetricName": "tma_store_fwd_blk", - "MetricThreshold": "tma_store_fwd_blk > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", - "PublicDescription": "This metric roughly estimates fraction of cycles when the memory subsystem had loads blocked since they could not forward data from earlier (in program order) overlapping stores. To streamline memory operations in the pipeline; a load can avoid waiting for memory if a prior in-flight store is writing the data that the load wants to read (store forwarding process). However; in some cases the load may be blocked for a significant time pending the store forward. For example; when the prior store is writing a smaller region than the load is reading", + "MetricThreshold": "tma_store_fwd_blk > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric roughly estimates fraction of cycles when the memory subsystem had loads blocked since they could not forward data from earlier (in program order) overlapping stores. To streamline memory operations in the pipeline; a load can avoid waiting for memory if a prior in-flight store is writing the data that the load wants to read (store forwarding process). However; in some cases the load may be blocked for a significant time pending the store forward. For example; when the prior store is writing a smaller region than the load is reading.", "ScaleUnit": "100%" }, { @@ -2215,8 +2218,8 @@ "MetricExpr": "(MEM_STORE_RETIRED.L2_HIT * 10 * (1 - MEM_INST_RETIRED.LOCK_LOADS / MEM_INST_RETIRED.ALL_STORES) + (1 - MEM_INST_RETIRED.LOCK_LOADS / MEM_INST_RETIRED.ALL_STORES) * min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO)) / tma_info_thread_clks", "MetricGroup": "BvML;LockCont;MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_issueSL;tma_store_bound_group", "MetricName": "tma_store_latency", - "MetricThreshold": "tma_store_latency > 0.1 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", - "PublicDescription": "This metric estimates fraction of cycles the CPU spent handling L1D store misses. Store accesses usually less impact out-of-order core performance; however; holding resources for longer time can lead into undesired implications (e.g. contention on L1D fill-buffer entries - see FB_Full). Related metrics: tma_branch_resteers, tma_fb_full, tma_l3_hit_latency, tma_lock_latency", + "MetricThreshold": "tma_store_latency > 0.1 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric estimates fraction of cycles the CPU spent handling L1D store misses. Store accesses usually less impact out-of-order core performance; however; holding resources for longer time can lead into undesired implications (e.g. contention on L1D fill-buffer entries - see FB_Full). Related metrics: tma_fb_full, tma_lock_latency", "ScaleUnit": "100%" }, { @@ -2233,7 +2236,7 @@ "MetricExpr": "tma_dtlb_store - tma_store_stlb_miss", "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_store_group", "MetricName": "tma_store_stlb_hit", - "MetricThreshold": "tma_store_stlb_hit > 0.05 & tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_store_stlb_hit > 0.05 & (tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))", "ScaleUnit": "100%" }, { @@ -2241,31 +2244,31 @@ "MetricExpr": "DTLB_STORE_MISSES.WALK_ACTIVE / tma_info_core_core_clks", "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_store_group", "MetricName": "tma_store_stlb_miss", - "MetricThreshold": "tma_store_stlb_miss > 0.05 & tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_store_stlb_miss > 0.05 & (tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 1 GB pages for data store accesses", + "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 1 GB pages for data store accesses.", "MetricExpr": "tma_store_stlb_miss * DTLB_STORE_MISSES.WALK_COMPLETED_1G / (DTLB_STORE_MISSES.WALK_COMPLETED_4K + DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M + DTLB_STORE_MISSES.WALK_COMPLETED_1G)", "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_store_stlb_miss_group", "MetricName": "tma_store_stlb_miss_1g", - "MetricThreshold": "tma_store_stlb_miss_1g > 0.05 & tma_store_stlb_miss > 0.05 & tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_store_stlb_miss_1g > 0.05 & (tma_store_stlb_miss > 0.05 & (tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))))", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 2 or 4 MB pages for data store accesses", + "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 2 or 4 MB pages for data store accesses.", "MetricExpr": "tma_store_stlb_miss * DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M / (DTLB_STORE_MISSES.WALK_COMPLETED_4K + DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M + DTLB_STORE_MISSES.WALK_COMPLETED_1G)", "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_store_stlb_miss_group", "MetricName": "tma_store_stlb_miss_2m", - "MetricThreshold": "tma_store_stlb_miss_2m > 0.05 & tma_store_stlb_miss > 0.05 & tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_store_stlb_miss_2m > 0.05 & (tma_store_stlb_miss > 0.05 & (tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))))", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 4 KB pages for data store accesses", + "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 4 KB pages for data store accesses.", "MetricExpr": "tma_store_stlb_miss * DTLB_STORE_MISSES.WALK_COMPLETED_4K / (DTLB_STORE_MISSES.WALK_COMPLETED_4K + DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M + DTLB_STORE_MISSES.WALK_COMPLETED_1G)", "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_store_stlb_miss_group", "MetricName": "tma_store_stlb_miss_4k", - "MetricThreshold": "tma_store_stlb_miss_4k > 0.05 & tma_store_stlb_miss > 0.05 & tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_store_stlb_miss_4k > 0.05 & (tma_store_stlb_miss > 0.05 & (tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))))", "ScaleUnit": "100%" }, { @@ -2273,7 +2276,7 @@ "MetricExpr": "9 * OCR.STREAMING_WR.ANY_RESPONSE / tma_info_thread_clks", "MetricGroup": "MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_issueSmSt;tma_store_bound_group", "MetricName": "tma_streaming_stores", - "MetricThreshold": "tma_streaming_stores > 0.2 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_streaming_stores > 0.2 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", "PublicDescription": "This metric estimates how often CPU was stalled due to Streaming store memory accesses; Streaming store optimize out a read request required by RFO stores. Even though store accesses do not typically stall out-of-order CPUs; there are few cases where stores can lead to actual stalls. This metric will be flagged should Streaming stores be a bottleneck. Sample with: OCR.STREAMING_WR.ANY_RESPONSE. Related metrics: tma_fb_full", "ScaleUnit": "100%" }, @@ -2282,7 +2285,7 @@ "MetricExpr": "INT_MISC.UNKNOWN_BRANCH_CYCLES / tma_info_thread_clks", "MetricGroup": "BigFootprint;BvBC;FetchLat;TopdownL4;tma_L4_group;tma_branch_resteers_group", "MetricName": "tma_unknown_branches", - "MetricThreshold": "tma_unknown_branches > 0.05 & tma_branch_resteers > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricThreshold": "tma_unknown_branches > 0.05 & (tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))", "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to new branch address clears. These are fetched branches the Branch Prediction Unit was unable to recognize (e.g. first time the branch is fetched or hitting BTB capacity limit) hence called Unknown Branches. Sample with: FRONTEND_RETIRED.UNKNOWN_BRANCH", "ScaleUnit": "100%" }, @@ -2291,8 +2294,8 @@ "MetricExpr": "tma_retiring * UOPS_EXECUTED.X87 / UOPS_EXECUTED.THREAD", "MetricGroup": "Compute;TopdownL4;tma_L4_group;tma_fp_arith_group", "MetricName": "tma_x87_use", - "MetricThreshold": "tma_x87_use > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6", - "PublicDescription": "This metric serves as an approximation of legacy x87 usage. It accounts for instructions beyond X87 FP arithmetic operations; hence may be used as a thermometer to avoid X87 high usage and preferably upgrade to modern ISA. See Tip under Tuning Hint", + "MetricThreshold": "tma_x87_use > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6)", + "PublicDescription": "This metric serves as an approximation of legacy x87 usage. It accounts for instructions beyond X87 FP arithmetic operations; hence may be used as a thermometer to avoid X87 high usage and preferably upgrade to modern ISA. See Tip under Tuning Hint.", "ScaleUnit": "100%" }, { diff --git a/tools/perf/pmu-events/arch/x86/sapphirerapids/virtual-memory.json b/tools/perf/pmu-events/arch/x86/sapphirerapids/virtual-memory.json index 609a9549cbf3..3d3f88600e26 100644 --- a/tools/perf/pmu-events/arch/x86/sapphirerapids/virtual-memory.json +++ b/tools/perf/pmu-events/arch/x86/sapphirerapids/virtual-memory.json @@ -4,7 +4,7 @@ "Counter": "0,1,2,3", "EventCode": "0x12", "EventName": "DTLB_LOAD_MISSES.STLB_HIT", - "PublicDescription": "Counts loads that miss the DTLB (Data TLB) and hit the STLB (Second level TLB).", + "PublicDescription": "Counts loads that miss the DTLB (Data TLB) and hit the STLB (Second level TLB). Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x20" }, @@ -14,7 +14,7 @@ "CounterMask": "1", "EventCode": "0x12", "EventName": "DTLB_LOAD_MISSES.WALK_ACTIVE", - "PublicDescription": "Counts cycles when at least one PMH (Page Miss Handler) is busy with a page walk for a demand load.", + "PublicDescription": "Counts cycles when at least one PMH (Page Miss Handler) is busy with a page walk for a demand load. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x10" }, @@ -23,7 +23,7 @@ "Counter": "0,1,2,3", "EventCode": "0x12", "EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED", - "PublicDescription": "Counts completed page walks (all page sizes) caused by demand data loads. This implies it missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.", + "PublicDescription": "Counts completed page walks (all page sizes) caused by demand data loads. This implies it missed in the DTLB and further levels of TLB. The page walk can end with or without a fault. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0xe" }, @@ -32,7 +32,7 @@ "Counter": "0,1,2,3", "EventCode": "0x12", "EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED_1G", - "PublicDescription": "Counts completed page walks (1G sizes) caused by demand data loads. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.", + "PublicDescription": "Counts completed page walks (1G sizes) caused by demand data loads. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x8" }, @@ -41,7 +41,7 @@ "Counter": "0,1,2,3", "EventCode": "0x12", "EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M", - "PublicDescription": "Counts completed page walks (2M/4M sizes) caused by demand data loads. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.", + "PublicDescription": "Counts completed page walks (2M/4M sizes) caused by demand data loads. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x4" }, @@ -50,7 +50,7 @@ "Counter": "0,1,2,3", "EventCode": "0x12", "EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED_4K", - "PublicDescription": "Counts completed page walks (4K sizes) caused by demand data loads. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.", + "PublicDescription": "Counts completed page walks (4K sizes) caused by demand data loads. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x2" }, @@ -59,7 +59,7 @@ "Counter": "0,1,2,3", "EventCode": "0x12", "EventName": "DTLB_LOAD_MISSES.WALK_PENDING", - "PublicDescription": "Counts the number of page walks outstanding for a demand load in the PMH (Page Miss Handler) each cycle.", + "PublicDescription": "Counts the number of page walks outstanding for a demand load in the PMH (Page Miss Handler) each cycle. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x10" }, @@ -68,7 +68,7 @@ "Counter": "0,1,2,3", "EventCode": "0x13", "EventName": "DTLB_STORE_MISSES.STLB_HIT", - "PublicDescription": "Counts stores that miss the DTLB (Data TLB) and hit the STLB (2nd Level TLB).", + "PublicDescription": "Counts stores that miss the DTLB (Data TLB) and hit the STLB (2nd Level TLB). Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x20" }, @@ -78,7 +78,7 @@ "CounterMask": "1", "EventCode": "0x13", "EventName": "DTLB_STORE_MISSES.WALK_ACTIVE", - "PublicDescription": "Counts cycles when at least one PMH (Page Miss Handler) is busy with a page walk for a store.", + "PublicDescription": "Counts cycles when at least one PMH (Page Miss Handler) is busy with a page walk for a store. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x10" }, @@ -87,7 +87,7 @@ "Counter": "0,1,2,3", "EventCode": "0x13", "EventName": "DTLB_STORE_MISSES.WALK_COMPLETED", - "PublicDescription": "Counts completed page walks (all page sizes) caused by demand data stores. This implies it missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.", + "PublicDescription": "Counts completed page walks (all page sizes) caused by demand data stores. This implies it missed in the DTLB and further levels of TLB. The page walk can end with or without a fault. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0xe" }, @@ -96,7 +96,7 @@ "Counter": "0,1,2,3", "EventCode": "0x13", "EventName": "DTLB_STORE_MISSES.WALK_COMPLETED_1G", - "PublicDescription": "Counts completed page walks (1G sizes) caused by demand data stores. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.", + "PublicDescription": "Counts completed page walks (1G sizes) caused by demand data stores. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x8" }, @@ -105,7 +105,7 @@ "Counter": "0,1,2,3", "EventCode": "0x13", "EventName": "DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M", - "PublicDescription": "Counts completed page walks (2M/4M sizes) caused by demand data stores. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.", + "PublicDescription": "Counts completed page walks (2M/4M sizes) caused by demand data stores. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x4" }, @@ -114,7 +114,7 @@ "Counter": "0,1,2,3", "EventCode": "0x13", "EventName": "DTLB_STORE_MISSES.WALK_COMPLETED_4K", - "PublicDescription": "Counts completed page walks (4K sizes) caused by demand data stores. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.", + "PublicDescription": "Counts completed page walks (4K sizes) caused by demand data stores. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x2" }, @@ -123,7 +123,7 @@ "Counter": "0,1,2,3", "EventCode": "0x13", "EventName": "DTLB_STORE_MISSES.WALK_PENDING", - "PublicDescription": "Counts the number of page walks outstanding for a store in the PMH (Page Miss Handler) each cycle.", + "PublicDescription": "Counts the number of page walks outstanding for a store in the PMH (Page Miss Handler) each cycle. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x10" }, @@ -132,7 +132,7 @@ "Counter": "0,1,2,3", "EventCode": "0x11", "EventName": "ITLB_MISSES.STLB_HIT", - "PublicDescription": "Counts instruction fetch requests that miss the ITLB (Instruction TLB) and hit the STLB (Second-level TLB).", + "PublicDescription": "Counts instruction fetch requests that miss the ITLB (Instruction TLB) and hit the STLB (Second-level TLB). Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x20" }, @@ -142,7 +142,7 @@ "CounterMask": "1", "EventCode": "0x11", "EventName": "ITLB_MISSES.WALK_ACTIVE", - "PublicDescription": "Counts cycles when at least one PMH (Page Miss Handler) is busy with a page walk for a code (instruction fetch) request.", + "PublicDescription": "Counts cycles when at least one PMH (Page Miss Handler) is busy with a page walk for a code (instruction fetch) request. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x10" }, @@ -151,7 +151,7 @@ "Counter": "0,1,2,3", "EventCode": "0x11", "EventName": "ITLB_MISSES.WALK_COMPLETED", - "PublicDescription": "Counts completed page walks (all page sizes) caused by a code fetch. This implies it missed in the ITLB (Instruction TLB) and further levels of TLB. The page walk can end with or without a fault.", + "PublicDescription": "Counts completed page walks (all page sizes) caused by a code fetch. This implies it missed in the ITLB (Instruction TLB) and further levels of TLB. The page walk can end with or without a fault. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0xe" }, @@ -160,7 +160,7 @@ "Counter": "0,1,2,3", "EventCode": "0x11", "EventName": "ITLB_MISSES.WALK_COMPLETED_2M_4M", - "PublicDescription": "Counts completed page walks (2M/4M page sizes) caused by a code fetch. This implies it missed in the ITLB (Instruction TLB) and further levels of TLB. The page walk can end with or without a fault.", + "PublicDescription": "Counts completed page walks (2M/4M page sizes) caused by a code fetch. This implies it missed in the ITLB (Instruction TLB) and further levels of TLB. The page walk can end with or without a fault. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x4" }, @@ -169,7 +169,7 @@ "Counter": "0,1,2,3", "EventCode": "0x11", "EventName": "ITLB_MISSES.WALK_COMPLETED_4K", - "PublicDescription": "Counts completed page walks (4K page sizes) caused by a code fetch. This implies it missed in the ITLB (Instruction TLB) and further levels of TLB. The page walk can end with or without a fault.", + "PublicDescription": "Counts completed page walks (4K page sizes) caused by a code fetch. This implies it missed in the ITLB (Instruction TLB) and further levels of TLB. The page walk can end with or without a fault. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x2" }, @@ -178,7 +178,7 @@ "Counter": "0,1,2,3", "EventCode": "0x11", "EventName": "ITLB_MISSES.WALK_PENDING", - "PublicDescription": "Counts the number of page walks outstanding for an outstanding code (instruction fetch) request in the PMH (Page Miss Handler) each cycle.", + "PublicDescription": "Counts the number of page walks outstanding for an outstanding code (instruction fetch) request in the PMH (Page Miss Handler) each cycle. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x10" } diff --git a/tools/perf/pmu-events/arch/x86/sierraforest/cache.json b/tools/perf/pmu-events/arch/x86/sierraforest/cache.json index 072df00aff92..877052db1490 100644 --- a/tools/perf/pmu-events/arch/x86/sierraforest/cache.json +++ b/tools/perf/pmu-events/arch/x86/sierraforest/cache.json @@ -467,12 +467,24 @@ "UMask": "0x6" }, { + "BriefDescription": "Counts demand data reads that have any type of response.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xB7", + "EventName": "OCR.DEMAND_DATA_RD.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x10001", + "PublicDescription": "Counts demand data reads that have any type of response. Available PDIST counters: 0", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { "BriefDescription": "Counts demand data reads that were supplied by the L3 cache where a snoop was sent, the snoop hit, and modified data was forwarded.", "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xB7", "EventName": "OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x10003C0001", + "PublicDescription": "Counts demand data reads that were supplied by the L3 cache where a snoop was sent, the snoop hit, and modified data was forwarded. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -483,6 +495,18 @@ "EventName": "OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x8003C0001", + "PublicDescription": "Counts demand data reads that were supplied by the L3 cache where a snoop was sent, the snoop hit, and non-modified data was forwarded. Available PDIST counters: 0", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that have any type of response.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xB7", + "EventName": "OCR.DEMAND_RFO.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x10002", + "PublicDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that have any type of response. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -493,6 +517,7 @@ "EventName": "OCR.DEMAND_RFO.L3_HIT.SNOOP_HITM", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x10003C0002", + "PublicDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that were supplied by the L3 cache where a snoop was sent, the snoop hit, and modified data was forwarded. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, diff --git a/tools/perf/pmu-events/arch/x86/sierraforest/memory.json b/tools/perf/pmu-events/arch/x86/sierraforest/memory.json index 22d23077618e..dc850a179517 100644 --- a/tools/perf/pmu-events/arch/x86/sierraforest/memory.json +++ b/tools/perf/pmu-events/arch/x86/sierraforest/memory.json @@ -79,6 +79,29 @@ "EventName": "OCR.DEMAND_DATA_RD.L3_MISS", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x3FBFC00001", + "PublicDescription": "Counts demand data reads that were not supplied by the L3 cache. Available PDIST counters: 0", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts demand data reads that were supplied by DRAM attached to this socket.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xB7", + "EventName": "OCR.DEMAND_DATA_RD.LOCAL_DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x184000001", + "PublicDescription": "Counts demand data reads that were supplied by DRAM attached to this socket. Available PDIST counters: 0", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts demand data reads that were supplied by DRAM attached to another socket.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xB7", + "EventName": "OCR.DEMAND_DATA_RD.REMOTE_DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x730000001", + "PublicDescription": "Counts demand data reads that were supplied by DRAM attached to another socket. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -89,6 +112,7 @@ "EventName": "OCR.DEMAND_RFO.L3_MISS", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x3FBFC00002", + "PublicDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that were not supplied by the L3 cache. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" } diff --git a/tools/perf/pmu-events/arch/x86/sierraforest/other.json b/tools/perf/pmu-events/arch/x86/sierraforest/other.json index 4c77dac8ec78..ea34103a8292 100644 --- a/tools/perf/pmu-events/arch/x86/sierraforest/other.json +++ b/tools/perf/pmu-events/arch/x86/sierraforest/other.json @@ -9,61 +9,14 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts demand data reads that have any type of response.", - "Counter": "0,1,2,3,4,5,6,7", - "EventCode": "0xB7", - "EventName": "OCR.DEMAND_DATA_RD.ANY_RESPONSE", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x10001", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts demand data reads that were supplied by DRAM attached to this socket.", - "Counter": "0,1,2,3,4,5,6,7", - "EventCode": "0xB7", - "EventName": "OCR.DEMAND_DATA_RD.LOCAL_DRAM", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x184000001", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts demand data reads that were supplied by DRAM attached to another socket.", - "Counter": "0,1,2,3,4,5,6,7", - "EventCode": "0xB7", - "EventName": "OCR.DEMAND_DATA_RD.REMOTE_DRAM", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x730000001", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that have any type of response.", - "Counter": "0,1,2,3,4,5,6,7", - "EventCode": "0xB7", - "EventName": "OCR.DEMAND_RFO.ANY_RESPONSE", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x10002", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { "BriefDescription": "Counts streaming stores that have any type of response.", "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xB7", "EventName": "OCR.STREAMING_WR.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x10800", + "PublicDescription": "Counts streaming stores that have any type of response. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" - }, - { - "BriefDescription": "Counts the number of issue slots in a UMWAIT or TPAUSE instruction where no uop issues due to the instruction putting the CPU into the C0.1 activity state.", - "Counter": "0,1,2,3,4,5,6,7", - "EventCode": "0x75", - "EventName": "SERIALIZATION.C01_MS_SCB", - "SampleAfterValue": "200003", - "UMask": "0x4" } ] diff --git a/tools/perf/pmu-events/arch/x86/sierraforest/pipeline.json b/tools/perf/pmu-events/arch/x86/sierraforest/pipeline.json index df2c7bb474a0..f56d8d816e53 100644 --- a/tools/perf/pmu-events/arch/x86/sierraforest/pipeline.json +++ b/tools/perf/pmu-events/arch/x86/sierraforest/pipeline.json @@ -225,6 +225,7 @@ "BriefDescription": "Fixed Counter: Counts the number of instructions retired", "Counter": "Fixed counter 0", "EventName": "INST_RETIRED.ANY", + "PublicDescription": "Fixed Counter: Counts the number of instructions retired Available PDIST counters: 32", "SampleAfterValue": "2000003", "UMask": "0x1" }, @@ -301,6 +302,14 @@ "UMask": "0x1" }, { + "BriefDescription": "Counts the number of issue slots in a UMWAIT or TPAUSE instruction where no uop issues due to the instruction putting the CPU into the C0.1 activity state.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x75", + "EventName": "SERIALIZATION.C01_MS_SCB", + "SampleAfterValue": "200003", + "UMask": "0x4" + }, + { "BriefDescription": "Counts the number of issue slots that were not consumed by the backend because allocation is stalled due to a mispredicted jump or a machine clear. [This event is alias to TOPDOWN_BAD_SPECULATION.ALL_P]", "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0x73", diff --git a/tools/perf/pmu-events/arch/x86/sierraforest/srf-metrics.json b/tools/perf/pmu-events/arch/x86/sierraforest/srf-metrics.json index 83c86afd2960..ef629e4e91ce 100644 --- a/tools/perf/pmu-events/arch/x86/sierraforest/srf-metrics.json +++ b/tools/perf/pmu-events/arch/x86/sierraforest/srf-metrics.json @@ -288,15 +288,17 @@ { "BriefDescription": "Counts the number of issue slots that were not consumed by the backend due to certain allocation restrictions", "MetricExpr": "tma_core_bound", - "MetricGroup": "Slots;TopdownL3;tma_L3_group;tma_core_bound_group", + "MetricGroup": "TopdownL3;tma_L3_group;tma_core_bound_group", "MetricName": "tma_allocation_restriction", + "MetricThreshold": "tma_allocation_restriction > 0.1 & (tma_core_bound > 0.1 & tma_backend_bound > 0.1)", "ScaleUnit": "100%" }, { "BriefDescription": "Counts the total number of issue slots that were not consumed by the backend due to backend stalls", "MetricExpr": "TOPDOWN_BE_BOUND.ALL_P / (6 * CPU_CLK_UNHALTED.CORE)", - "MetricGroup": "Slots;TopdownL1;tma_L1_group", + "MetricGroup": "TopdownL1;tma_L1_group", "MetricName": "tma_backend_bound", + "MetricThreshold": "tma_backend_bound > 0.1", "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "Counts the total number of issue slots that were not consumed by the backend due to backend stalls. Note that uops must be available for consumption in order for this event to count. If a uop is not available (IQ is empty), this event will not count", "ScaleUnit": "100%" @@ -304,92 +306,104 @@ { "BriefDescription": "Counts the total number of issue slots that were not consumed by the backend because allocation is stalled due to a mispredicted jump or a machine clear", "MetricExpr": "TOPDOWN_BAD_SPECULATION.ALL_P / (6 * CPU_CLK_UNHALTED.CORE)", - "MetricGroup": "Slots;TopdownL1;tma_L1_group", + "MetricGroup": "TopdownL1;tma_L1_group", "MetricName": "tma_bad_speculation", + "MetricThreshold": "tma_bad_speculation > 0.15", "MetricgroupNoGroup": "TopdownL1", - "PublicDescription": "Counts the total number of issue slots that were not consumed by the backend because allocation is stalled due to a mispredicted jump or a machine clear. Only issue slots wasted due to fast nukes such as memory ordering nukes are counted. Other nukes are not accounted for. Counts all issue slots blocked during this recovery window including relevant microcode flows and while uops are not yet available in the instruction queue (IQ). Also includes the issue slots that were consumed by the backend but were thrown away because they were younger than the mispredict or machine clear", + "PublicDescription": "Counts the total number of issue slots that were not consumed by the backend because allocation is stalled due to a mispredicted jump or a machine clear. Only issue slots wasted due to fast nukes such as memory ordering nukes are counted. Other nukes are not accounted for. Counts all issue slots blocked during this recovery window including relevant microcode flows and while uops are not yet available in the instruction queue (IQ). Also includes the issue slots that were consumed by the backend but were thrown away because they were younger than the mispredict or machine clear.", "ScaleUnit": "100%" }, { "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to BACLEARS, which occurs when the Branch Target Buffer (BTB) prediction or lack thereof, was corrected by a later branch predictor in the frontend", "MetricExpr": "TOPDOWN_FE_BOUND.BRANCH_DETECT / (6 * CPU_CLK_UNHALTED.CORE)", - "MetricGroup": "Slots;TopdownL3;tma_L3_group;tma_ifetch_latency_group", + "MetricGroup": "TopdownL3;tma_L3_group;tma_ifetch_latency_group", "MetricName": "tma_branch_detect", - "PublicDescription": "Counts the number of issue slots that were not delivered by the frontend due to BACLEARS, which occurs when the Branch Target Buffer (BTB) prediction or lack thereof, was corrected by a later branch predictor in the frontend. Includes BACLEARS due to all branch types including conditional and unconditional jumps, returns, and indirect branches", + "MetricThreshold": "tma_branch_detect > 0.05 & (tma_ifetch_latency > 0.15 & tma_frontend_bound > 0.2)", + "PublicDescription": "Counts the number of issue slots that were not delivered by the frontend due to BACLEARS, which occurs when the Branch Target Buffer (BTB) prediction or lack thereof, was corrected by a later branch predictor in the frontend. Includes BACLEARS due to all branch types including conditional and unconditional jumps, returns, and indirect branches.", "ScaleUnit": "100%" }, { "BriefDescription": "Counts the number of issue slots that were not consumed by the backend due to branch mispredicts", "MetricExpr": "TOPDOWN_BAD_SPECULATION.MISPREDICT / (6 * CPU_CLK_UNHALTED.CORE)", - "MetricGroup": "Slots;TopdownL2;tma_L2_group;tma_bad_speculation_group", + "MetricGroup": "TopdownL2;tma_L2_group;tma_bad_speculation_group", "MetricName": "tma_branch_mispredicts", + "MetricThreshold": "tma_branch_mispredicts > 0.05 & tma_bad_speculation > 0.15", "MetricgroupNoGroup": "TopdownL2", "ScaleUnit": "100%" }, { - "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to BTCLEARS, which occurs when the Branch Target Buffer (BTB) predicts a taken branch", + "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to BTCLEARS, which occurs when the Branch Target Buffer (BTB) predicts a taken branch.", "MetricExpr": "TOPDOWN_FE_BOUND.BRANCH_RESTEER / (6 * CPU_CLK_UNHALTED.CORE)", - "MetricGroup": "Slots;TopdownL3;tma_L3_group;tma_ifetch_latency_group", + "MetricGroup": "TopdownL3;tma_L3_group;tma_ifetch_latency_group", "MetricName": "tma_branch_resteer", + "MetricThreshold": "tma_branch_resteer > 0.05 & (tma_ifetch_latency > 0.15 & tma_frontend_bound > 0.2)", "ScaleUnit": "100%" }, { - "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to the microcode sequencer (MS)", + "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to the microcode sequencer (MS).", "MetricExpr": "TOPDOWN_FE_BOUND.CISC / (6 * CPU_CLK_UNHALTED.CORE)", - "MetricGroup": "Slots;TopdownL3;tma_L3_group;tma_ifetch_bandwidth_group", + "MetricGroup": "TopdownL3;tma_L3_group;tma_ifetch_bandwidth_group", "MetricName": "tma_cisc", + "MetricThreshold": "tma_cisc > 0.05 & (tma_ifetch_bandwidth > 0.1 & tma_frontend_bound > 0.2)", "ScaleUnit": "100%" }, { "BriefDescription": "Counts the number of cycles due to backend bound stalls that are bounded by core restrictions and not attributed to an outstanding load or stores, or resource limitation", "MetricExpr": "TOPDOWN_BE_BOUND.ALLOC_RESTRICTIONS / (6 * CPU_CLK_UNHALTED.CORE)", - "MetricGroup": "Slots;TopdownL2;tma_L2_group;tma_backend_bound_group", + "MetricGroup": "TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_core_bound", + "MetricThreshold": "tma_core_bound > 0.1 & tma_backend_bound > 0.1", "MetricgroupNoGroup": "TopdownL2", "ScaleUnit": "100%" }, { - "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to decode stalls", + "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to decode stalls.", "MetricExpr": "TOPDOWN_FE_BOUND.DECODE / (6 * CPU_CLK_UNHALTED.CORE)", - "MetricGroup": "Slots;TopdownL3;tma_L3_group;tma_ifetch_bandwidth_group", + "MetricGroup": "TopdownL3;tma_L3_group;tma_ifetch_bandwidth_group", "MetricName": "tma_decode", + "MetricThreshold": "tma_decode > 0.05 & (tma_ifetch_bandwidth > 0.1 & tma_frontend_bound > 0.2)", "ScaleUnit": "100%" }, { "BriefDescription": "Counts the number of issue slots that were not consumed by the backend due to a machine clear that does not require the use of microcode, classified as a fast nuke, due to memory ordering, memory disambiguation and memory renaming", "MetricExpr": "TOPDOWN_BAD_SPECULATION.FASTNUKE / (6 * CPU_CLK_UNHALTED.CORE)", - "MetricGroup": "Slots;TopdownL3;tma_L3_group;tma_machine_clears_group", + "MetricGroup": "TopdownL3;tma_L3_group;tma_machine_clears_group", "MetricName": "tma_fast_nuke", + "MetricThreshold": "tma_fast_nuke > 0.05 & (tma_machine_clears > 0.05 & tma_bad_speculation > 0.15)", "ScaleUnit": "100%" }, { - "BriefDescription": "Counts the number of issue slots that were not consumed by the backend due to frontend stalls", + "BriefDescription": "Counts the number of issue slots that were not consumed by the backend due to frontend stalls.", "MetricExpr": "TOPDOWN_FE_BOUND.ALL_P / (6 * CPU_CLK_UNHALTED.CORE)", - "MetricGroup": "Slots;TopdownL1;tma_L1_group", + "MetricGroup": "TopdownL1;tma_L1_group", "MetricName": "tma_frontend_bound", + "MetricThreshold": "tma_frontend_bound > 0.2", "MetricgroupNoGroup": "TopdownL1", "ScaleUnit": "100%" }, { - "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to instruction cache misses", + "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to instruction cache misses.", "MetricExpr": "TOPDOWN_FE_BOUND.ICACHE / (6 * CPU_CLK_UNHALTED.CORE)", - "MetricGroup": "Slots;TopdownL3;tma_L3_group;tma_ifetch_latency_group", + "MetricGroup": "TopdownL3;tma_L3_group;tma_ifetch_latency_group", "MetricName": "tma_icache_misses", + "MetricThreshold": "tma_icache_misses > 0.05 & (tma_ifetch_latency > 0.15 & tma_frontend_bound > 0.2)", "ScaleUnit": "100%" }, { - "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to frontend bandwidth restrictions due to decode, predecode, cisc, and other limitations", + "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to frontend bandwidth restrictions due to decode, predecode, cisc, and other limitations.", "MetricExpr": "TOPDOWN_FE_BOUND.FRONTEND_BANDWIDTH / (6 * CPU_CLK_UNHALTED.CORE)", - "MetricGroup": "Slots;TopdownL2;tma_L2_group;tma_frontend_bound_group", + "MetricGroup": "TopdownL2;tma_L2_group;tma_frontend_bound_group", "MetricName": "tma_ifetch_bandwidth", + "MetricThreshold": "tma_ifetch_bandwidth > 0.1 & tma_frontend_bound > 0.2", "MetricgroupNoGroup": "TopdownL2", "ScaleUnit": "100%" }, { - "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to frontend latency restrictions due to icache misses, itlb misses, branch detection, and resteer limitations", + "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to frontend latency restrictions due to icache misses, itlb misses, branch detection, and resteer limitations.", "MetricExpr": "TOPDOWN_FE_BOUND.FRONTEND_LATENCY / (6 * CPU_CLK_UNHALTED.CORE)", - "MetricGroup": "Slots;TopdownL2;tma_L2_group;tma_frontend_bound_group", + "MetricGroup": "TopdownL2;tma_L2_group;tma_frontend_bound_group", "MetricName": "tma_ifetch_latency", + "MetricThreshold": "tma_ifetch_latency > 0.15 & tma_frontend_bound > 0.2", "MetricgroupNoGroup": "TopdownL2", "ScaleUnit": "100%" }, @@ -420,33 +434,28 @@ { "BriefDescription": "Percentage of time that retirement is stalled due to a first level data TLB miss", "MetricExpr": "100 * (LD_HEAD.DTLB_MISS_AT_RET + LD_HEAD.PGWALK_AT_RET) / CPU_CLK_UNHALTED.CORE", - "MetricGroup": "Cycles", - "MetricName": "tma_info_bottleneck_dtlb_miss_bound_cycles", - "ScaleUnit": "100%" + "MetricName": "tma_info_bottleneck_%_dtlb_miss_bound_cycles" }, { "BriefDescription": "Percentage of time that allocation and retirement is stalled by the Frontend Cluster due to an Ifetch Miss, either Icache or ITLB Miss", "MetricExpr": "100 * MEM_BOUND_STALLS_IFETCH.ALL / CPU_CLK_UNHALTED.CORE", - "MetricGroup": "Cycles;Ifetch", - "MetricName": "tma_info_bottleneck_ifetch_miss_bound_cycles", - "PublicDescription": "Percentage of time that allocation and retirement is stalled by the Frontend Cluster due to an Ifetch Miss, either Icache or ITLB Miss. See Info.Ifetch_Bound", - "ScaleUnit": "100%" + "MetricGroup": "Ifetch", + "MetricName": "tma_info_bottleneck_%_ifetch_miss_bound_cycles", + "PublicDescription": "Percentage of time that allocation and retirement is stalled by the Frontend Cluster due to an Ifetch Miss, either Icache or ITLB Miss. See Info.Ifetch_Bound" }, { "BriefDescription": "Percentage of time that retirement is stalled due to an L1 miss", "MetricExpr": "100 * MEM_BOUND_STALLS_LOAD.ALL / CPU_CLK_UNHALTED.CORE", - "MetricGroup": "Cycles;Load_Store_Miss", - "MetricName": "tma_info_bottleneck_load_miss_bound_cycles", - "PublicDescription": "Percentage of time that retirement is stalled due to an L1 miss. See Info.Load_Miss_Bound", - "ScaleUnit": "100%" + "MetricGroup": "Load_Store_Miss", + "MetricName": "tma_info_bottleneck_%_load_miss_bound_cycles", + "PublicDescription": "Percentage of time that retirement is stalled due to an L1 miss. See Info.Load_Miss_Bound" }, { "BriefDescription": "Percentage of time that retirement is stalled by the Memory Cluster due to a pipeline stall", "MetricExpr": "100 * LD_HEAD.ANY_AT_RET / CPU_CLK_UNHALTED.CORE", - "MetricGroup": "Cycles;Mem_Exec", - "MetricName": "tma_info_bottleneck_mem_exec_bound_cycles", - "PublicDescription": "Percentage of time that retirement is stalled by the Memory Cluster due to a pipeline stall. See Info.Mem_Exec_Bound", - "ScaleUnit": "100%" + "MetricGroup": "Mem_Exec", + "MetricName": "tma_info_bottleneck_%_mem_exec_bound_cycles", + "PublicDescription": "Percentage of time that retirement is stalled by the Memory Cluster due to a pipeline stall. See Info.Mem_Exec_Bound" }, { "BriefDescription": "Instructions per Branch (lower number means higher occurrence rate)", @@ -501,26 +510,22 @@ { "BriefDescription": "Percentage of time that allocation is stalled due to load buffer full", "MetricExpr": "100 * MEM_SCHEDULER_BLOCK.LD_BUF / CPU_CLK_UNHALTED.CORE", - "MetricName": "tma_info_buffer_stalls_load_buffer_stall_cycles", - "ScaleUnit": "100%" + "MetricName": "tma_info_buffer_stalls_%_load_buffer_stall_cycles" }, { "BriefDescription": "Percentage of time that allocation is stalled due to memory reservation stations full", "MetricExpr": "100 * MEM_SCHEDULER_BLOCK.RSV / CPU_CLK_UNHALTED.CORE", - "MetricName": "tma_info_buffer_stalls_mem_rsv_stall_cycles", - "ScaleUnit": "100%" + "MetricName": "tma_info_buffer_stalls_%_mem_rsv_stall_cycles" }, { "BriefDescription": "Percentage of time that allocation is stalled due to store buffer full", "MetricExpr": "100 * MEM_SCHEDULER_BLOCK.ST_BUF / CPU_CLK_UNHALTED.CORE", - "MetricName": "tma_info_buffer_stalls_store_buffer_stall_cycles", - "ScaleUnit": "100%" + "MetricName": "tma_info_buffer_stalls_%_store_buffer_stall_cycles" }, { "BriefDescription": "Cycles Per Instruction", "MetricExpr": "CPU_CLK_UNHALTED.CORE / INST_RETIRED.ANY", - "MetricName": "tma_info_core_cpi", - "ScaleUnit": "1per_instr" + "MetricName": "tma_info_core_cpi" }, { "BriefDescription": "Floating Point Operations Per Cycle", @@ -541,28 +546,46 @@ { "BriefDescription": "Percentage of ifetch miss bound stalls, where the ifetch miss hits in the L2", "MetricExpr": "100 * MEM_BOUND_STALLS_IFETCH.L2_HIT / MEM_BOUND_STALLS_IFETCH.ALL", - "MetricName": "tma_info_ifetch_miss_bound_ifetchmissbound_with_l2hit", - "ScaleUnit": "100%" + "MetricName": "tma_info_ifetch_miss_bound_%_ifetchmissbound_with_l2hit" + }, + { + "BriefDescription": "Percentage of ifetch miss bound stalls, where the ifetch miss doesn't hit in the L2", + "MetricExpr": "100 * (MEM_BOUND_STALLS_IFETCH.LLC_HIT + MEM_BOUND_STALLS_IFETCH.LLC_MISS) / MEM_BOUND_STALLS_IFETCH.ALL", + "MetricName": "tma_info_ifetch_miss_bound_%_ifetchmissbound_with_l2miss" }, { "BriefDescription": "Percentage of ifetch miss bound stalls, where the ifetch miss hits in the L3", "MetricExpr": "100 * MEM_BOUND_STALLS_IFETCH.LLC_HIT / MEM_BOUND_STALLS_IFETCH.ALL", - "MetricName": "tma_info_ifetch_miss_bound_ifetchmissbound_with_l3hit", - "ScaleUnit": "100%" + "MetricName": "tma_info_ifetch_miss_bound_%_ifetchmissbound_with_l3hit" + }, + { + "BriefDescription": "Percentage of ifetch miss bound stalls, where the ifetch miss subsequently misses in the L3", + "MetricExpr": "100 * MEM_BOUND_STALLS_IFETCH.LLC_MISS / MEM_BOUND_STALLS_IFETCH.ALL", + "MetricName": "tma_info_ifetch_miss_bound_%_ifetchmissbound_with_l3miss" }, { "BriefDescription": "Percentage of memory bound stalls where retirement is stalled due to an L1 miss that hit the L2", "MetricExpr": "100 * MEM_BOUND_STALLS_LOAD.L2_HIT / MEM_BOUND_STALLS_LOAD.ALL", "MetricGroup": "load_store_bound", - "MetricName": "tma_info_load_miss_bound_loadmissbound_with_l2hit", - "ScaleUnit": "100%" + "MetricName": "tma_info_load_miss_bound_%_loadmissbound_with_l2hit" + }, + { + "BriefDescription": "Percentage of memory bound stalls where retirement is stalled due to an L1 miss that subsequently misses in the L2", + "MetricExpr": "100 * (MEM_BOUND_STALLS_LOAD.LLC_HIT + MEM_BOUND_STALLS_LOAD.LLC_MISS) / MEM_BOUND_STALLS_LOAD.ALL", + "MetricGroup": "load_store_bound", + "MetricName": "tma_info_load_miss_bound_%_loadmissbound_with_l2miss" }, { "BriefDescription": "Percentage of memory bound stalls where retirement is stalled due to an L1 miss that hit the L3", "MetricExpr": "100 * MEM_BOUND_STALLS_LOAD.LLC_HIT / MEM_BOUND_STALLS_LOAD.ALL", "MetricGroup": "load_store_bound", - "MetricName": "tma_info_load_miss_bound_loadmissbound_with_l3hit", - "ScaleUnit": "100%" + "MetricName": "tma_info_load_miss_bound_%_loadmissbound_with_l3hit" + }, + { + "BriefDescription": "Percentage of memory bound stalls where retirement is stalled due to an L1 miss that subsequently misses the L3", + "MetricExpr": "100 * MEM_BOUND_STALLS_LOAD.LLC_MISS / MEM_BOUND_STALLS_LOAD.ALL", + "MetricGroup": "load_store_bound", + "MetricName": "tma_info_load_miss_bound_%_loadmissbound_with_l3miss" }, { "BriefDescription": "Counts the number of cycles that the oldest load of the load buffer is stalled at retirement due to a pipeline block", @@ -600,44 +623,37 @@ { "BriefDescription": "Percentage of total non-speculative loads with an address aliasing block", "MetricExpr": "100 * LD_BLOCKS.ADDRESS_ALIAS / MEM_UOPS_RETIRED.ALL_LOADS", - "MetricName": "tma_info_mem_exec_blocks_loads_with_adressaliasing", - "ScaleUnit": "100%" + "MetricName": "tma_info_mem_exec_blocks_%_loads_with_adressaliasing" }, { "BriefDescription": "Percentage of total non-speculative loads with a store forward or unknown store address block", "MetricExpr": "100 * LD_BLOCKS.DATA_UNKNOWN / MEM_UOPS_RETIRED.ALL_LOADS", - "MetricName": "tma_info_mem_exec_blocks_loads_with_storefwdblk", - "ScaleUnit": "100%" + "MetricName": "tma_info_mem_exec_blocks_%_loads_with_storefwdblk" }, { "BriefDescription": "Percentage of Memory Execution Bound due to a first level data cache miss", "MetricExpr": "100 * LD_HEAD.L1_MISS_AT_RET / LD_HEAD.ANY_AT_RET", - "MetricName": "tma_info_mem_exec_bound_loadhead_with_l1miss", - "ScaleUnit": "100%" + "MetricName": "tma_info_mem_exec_bound_%_loadhead_with_l1miss" }, { "BriefDescription": "Percentage of Memory Execution Bound due to other block cases, such as pipeline conflicts, fences, etc", "MetricExpr": "100 * LD_HEAD.OTHER_AT_RET / LD_HEAD.ANY_AT_RET", - "MetricName": "tma_info_mem_exec_bound_loadhead_with_otherpipelineblks", - "ScaleUnit": "100%" + "MetricName": "tma_info_mem_exec_bound_%_loadhead_with_otherpipelineblks" }, { "BriefDescription": "Percentage of Memory Execution Bound due to a pagewalk", "MetricExpr": "100 * LD_HEAD.PGWALK_AT_RET / LD_HEAD.ANY_AT_RET", - "MetricName": "tma_info_mem_exec_bound_loadhead_with_pagewalk", - "ScaleUnit": "100%" + "MetricName": "tma_info_mem_exec_bound_%_loadhead_with_pagewalk" }, { "BriefDescription": "Percentage of Memory Execution Bound due to a second level TLB miss", "MetricExpr": "100 * LD_HEAD.DTLB_MISS_AT_RET / LD_HEAD.ANY_AT_RET", - "MetricName": "tma_info_mem_exec_bound_loadhead_with_stlbhit", - "ScaleUnit": "100%" + "MetricName": "tma_info_mem_exec_bound_%_loadhead_with_stlbhit" }, { "BriefDescription": "Percentage of Memory Execution Bound due to a store forward address match", "MetricExpr": "100 * LD_HEAD.ST_ADDR_AT_RET / LD_HEAD.ANY_AT_RET", - "MetricName": "tma_info_mem_exec_bound_loadhead_with_storefwding", - "ScaleUnit": "100%" + "MetricName": "tma_info_mem_exec_bound_%_loadhead_with_storefwding" }, { "BriefDescription": "Instructions per Load", @@ -667,8 +683,7 @@ { "BriefDescription": "Percentage of time that the core is stalled due to a TPAUSE or UMWAIT instruction", "MetricExpr": "100 * SERIALIZATION.C01_MS_SCB / (6 * CPU_CLK_UNHALTED.CORE)", - "MetricName": "tma_info_serialization_tpause_cycles", - "ScaleUnit": "100%" + "MetricName": "tma_info_serialization_%_tpause_cycles" }, { "BriefDescription": "Average CPU Utilization", @@ -684,17 +699,20 @@ }, { "BriefDescription": "Fraction of cycles spent in Kernel mode", - "MetricExpr": "CPU_CLK_UNHALTED.CORE_P:k / CPU_CLK_UNHALTED.CORE", + "MetricExpr": "cpu@CPU_CLK_UNHALTED.CORE_P@k / CPU_CLK_UNHALTED.CORE", + "MetricGroup": "Summary", "MetricName": "tma_info_system_kernel_utilization" }, { "BriefDescription": "PerfMon Event Multiplexing accuracy indicator", "MetricExpr": "CPU_CLK_UNHALTED.CORE_P / CPU_CLK_UNHALTED.CORE", - "MetricName": "tma_info_system_mux" + "MetricName": "tma_info_system_mux", + "MetricThreshold": "tma_info_system_mux > 1.1 | tma_info_system_mux < 0.9" }, { "BriefDescription": "Average Frequency Utilization relative nominal frequency", "MetricExpr": "CPU_CLK_UNHALTED.CORE / CPU_CLK_UNHALTED.REF_TSC", + "MetricGroup": "Power", "MetricName": "tma_info_system_turbo_utilization" }, { @@ -718,90 +736,102 @@ "MetricName": "tma_info_uop_mix_x87_uop_ratio" }, { - "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to Instruction Table Lookaside Buffer (ITLB) misses", + "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to Instruction Table Lookaside Buffer (ITLB) misses.", "MetricExpr": "TOPDOWN_FE_BOUND.ITLB_MISS / (6 * CPU_CLK_UNHALTED.CORE)", - "MetricGroup": "Slots;TopdownL3;tma_L3_group;tma_ifetch_latency_group", + "MetricGroup": "TopdownL3;tma_L3_group;tma_ifetch_latency_group", "MetricName": "tma_itlb_misses", + "MetricThreshold": "tma_itlb_misses > 0.05 & (tma_ifetch_latency > 0.15 & tma_frontend_bound > 0.2)", "ScaleUnit": "100%" }, { "BriefDescription": "Counts the total number of issue slots that were not consumed by the backend because allocation is stalled due to a machine clear (nuke) of any kind including memory ordering and memory disambiguation", "MetricExpr": "TOPDOWN_BAD_SPECULATION.MACHINE_CLEARS / (6 * CPU_CLK_UNHALTED.CORE)", - "MetricGroup": "Slots;TopdownL2;tma_L2_group;tma_bad_speculation_group", + "MetricGroup": "TopdownL2;tma_L2_group;tma_bad_speculation_group", "MetricName": "tma_machine_clears", + "MetricThreshold": "tma_machine_clears > 0.05 & tma_bad_speculation > 0.15", "MetricgroupNoGroup": "TopdownL2", "ScaleUnit": "100%" }, { "BriefDescription": "Counts the number of issue slots that were not consumed by the backend due to memory reservation stalls in which a scheduler is not able to accept uops", "MetricExpr": "TOPDOWN_BE_BOUND.MEM_SCHEDULER / (6 * CPU_CLK_UNHALTED.CORE)", - "MetricGroup": "Slots;TopdownL3;tma_L3_group;tma_resource_bound_group", + "MetricGroup": "TopdownL3;tma_L3_group;tma_resource_bound_group", "MetricName": "tma_mem_scheduler", + "MetricThreshold": "tma_mem_scheduler > 0.1 & (tma_resource_bound > 0.2 & tma_backend_bound > 0.1)", "ScaleUnit": "100%" }, { "BriefDescription": "Counts the number of issue slots that were not consumed by the backend due to IEC or FPC RAT stalls, which can be due to FIQ or IEC reservation stalls in which the integer, floating point or SIMD scheduler is not able to accept uops", "MetricExpr": "TOPDOWN_BE_BOUND.NON_MEM_SCHEDULER / (6 * CPU_CLK_UNHALTED.CORE)", - "MetricGroup": "Slots;TopdownL3;tma_L3_group;tma_resource_bound_group", + "MetricGroup": "TopdownL3;tma_L3_group;tma_resource_bound_group", "MetricName": "tma_non_mem_scheduler", + "MetricThreshold": "tma_non_mem_scheduler > 0.1 & (tma_resource_bound > 0.2 & tma_backend_bound > 0.1)", "ScaleUnit": "100%" }, { "BriefDescription": "Counts the number of issue slots that were not consumed by the backend due to a machine clear that requires the use of microcode (slow nuke)", "MetricExpr": "TOPDOWN_BAD_SPECULATION.NUKE / (6 * CPU_CLK_UNHALTED.CORE)", - "MetricGroup": "Slots;TopdownL3;tma_L3_group;tma_machine_clears_group", + "MetricGroup": "TopdownL3;tma_L3_group;tma_machine_clears_group", "MetricName": "tma_nuke", + "MetricThreshold": "tma_nuke > 0.05 & (tma_machine_clears > 0.05 & tma_bad_speculation > 0.15)", "ScaleUnit": "100%" }, { - "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to other common frontend stalls not categorized", + "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to other common frontend stalls not categorized.", "MetricExpr": "TOPDOWN_FE_BOUND.OTHER / (6 * CPU_CLK_UNHALTED.CORE)", - "MetricGroup": "Slots;TopdownL3;tma_L3_group;tma_ifetch_bandwidth_group", + "MetricGroup": "TopdownL3;tma_L3_group;tma_ifetch_bandwidth_group", "MetricName": "tma_other_fb", + "MetricThreshold": "tma_other_fb > 0.05 & (tma_ifetch_bandwidth > 0.1 & tma_frontend_bound > 0.2)", "ScaleUnit": "100%" }, { - "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to wrong predecodes", + "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to wrong predecodes.", "MetricExpr": "TOPDOWN_FE_BOUND.PREDECODE / (6 * CPU_CLK_UNHALTED.CORE)", - "MetricGroup": "Slots;TopdownL3;tma_L3_group;tma_ifetch_bandwidth_group", + "MetricGroup": "TopdownL3;tma_L3_group;tma_ifetch_bandwidth_group", "MetricName": "tma_predecode", + "MetricThreshold": "tma_predecode > 0.05 & (tma_ifetch_bandwidth > 0.1 & tma_frontend_bound > 0.2)", "ScaleUnit": "100%" }, { "BriefDescription": "Counts the number of issue slots that were not consumed by the backend due to the physical register file unable to accept an entry (marble stalls)", "MetricExpr": "TOPDOWN_BE_BOUND.REGISTER / (6 * CPU_CLK_UNHALTED.CORE)", - "MetricGroup": "Slots;TopdownL3;tma_L3_group;tma_resource_bound_group", + "MetricGroup": "TopdownL3;tma_L3_group;tma_resource_bound_group", "MetricName": "tma_register", + "MetricThreshold": "tma_register > 0.1 & (tma_resource_bound > 0.2 & tma_backend_bound > 0.1)", "ScaleUnit": "100%" }, { "BriefDescription": "Counts the number of issue slots that were not consumed by the backend due to the reorder buffer being full (ROB stalls)", "MetricExpr": "TOPDOWN_BE_BOUND.REORDER_BUFFER / (6 * CPU_CLK_UNHALTED.CORE)", - "MetricGroup": "Slots;TopdownL3;tma_L3_group;tma_resource_bound_group", + "MetricGroup": "TopdownL3;tma_L3_group;tma_resource_bound_group", "MetricName": "tma_reorder_buffer", + "MetricThreshold": "tma_reorder_buffer > 0.1 & (tma_resource_bound > 0.2 & tma_backend_bound > 0.1)", "ScaleUnit": "100%" }, { "BriefDescription": "Counts the number of cycles the core is stalled due to a resource limitation", "MetricExpr": "tma_backend_bound - tma_core_bound", - "MetricGroup": "Slots;TopdownL2;tma_L2_group;tma_backend_bound_group", + "MetricGroup": "TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_resource_bound", + "MetricThreshold": "tma_resource_bound > 0.2 & tma_backend_bound > 0.1", "MetricgroupNoGroup": "TopdownL2", "ScaleUnit": "100%" }, { "BriefDescription": "Counts the number of issue slots that result in retirement slots", "MetricExpr": "TOPDOWN_RETIRING.ALL_P / (6 * CPU_CLK_UNHALTED.CORE)", - "MetricGroup": "Slots;TopdownL1;tma_L1_group", + "MetricGroup": "TopdownL1;tma_L1_group", "MetricName": "tma_retiring", + "MetricThreshold": "tma_retiring > 0.75", "MetricgroupNoGroup": "TopdownL1", "ScaleUnit": "100%" }, { "BriefDescription": "Counts the number of issue slots that were not consumed by the backend due to scoreboards from the instruction queue (IQ), jump execution unit (JEU), or microcode sequencer (MS)", "MetricExpr": "TOPDOWN_BE_BOUND.SERIALIZATION / (6 * CPU_CLK_UNHALTED.CORE)", - "MetricGroup": "Slots;TopdownL3;tma_L3_group;tma_resource_bound_group", + "MetricGroup": "TopdownL3;tma_L3_group;tma_resource_bound_group", "MetricName": "tma_serialization", + "MetricThreshold": "tma_serialization > 0.1 & (tma_resource_bound > 0.2 & tma_backend_bound > 0.1)", "ScaleUnit": "100%" }, { diff --git a/tools/perf/pmu-events/arch/x86/sierraforest/uncore-cache.json b/tools/perf/pmu-events/arch/x86/sierraforest/uncore-cache.json index a779a1a73ea5..7182ca00ef8d 100644 --- a/tools/perf/pmu-events/arch/x86/sierraforest/uncore-cache.json +++ b/tools/perf/pmu-events/arch/x86/sierraforest/uncore-cache.json @@ -874,6 +874,38 @@ "Unit": "CHA" }, { + "BriefDescription": "Counts snoop filter capacity evictions for entries tracking exclusive lines in the cores? cache.? Snoop filter capacity evictions occur when the snoop filter is full and evicts an existing entry to track a new entry.? Does not count clean evictions such as when a core?s cache replaces a tracked cacheline with a new cacheline.", + "Counter": "0,1,2,3", + "EventCode": "0x3d", + "EventName": "UNC_CHA_SF_EVICTION.E_STATE", + "Experimental": "1", + "PerPkg": "1", + "PublicDescription": "Snoop Filter Capacity Evictions : E state", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "Counts snoop filter capacity evictions for entries tracking modified lines in the cores? cache.? Snoop filter capacity evictions occur when the snoop filter is full and evicts an existing entry to track a new entry.? Does not count clean evictions such as when a core?s cache replaces a tracked cacheline with a new cacheline.", + "Counter": "0,1,2,3", + "EventCode": "0x3d", + "EventName": "UNC_CHA_SF_EVICTION.M_STATE", + "PerPkg": "1", + "PublicDescription": "Snoop Filter Capacity Evictions : M state", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Counts snoop filter capacity evictions for entries tracking shared lines in the cores? cache.? Snoop filter capacity evictions occur when the snoop filter is full and evicts an existing entry to track a new entry.? Does not count clean evictions such as when a core?s cache replaces a tracked cacheline with a new cacheline.", + "Counter": "0,1,2,3", + "EventCode": "0x3d", + "EventName": "UNC_CHA_SF_EVICTION.S_STATE", + "Experimental": "1", + "PerPkg": "1", + "PublicDescription": "Snoop Filter Capacity Evictions : S state", + "UMask": "0x4", + "Unit": "CHA" + }, + { "BriefDescription": "All TOR Inserts", "Counter": "0,1,2,3", "EventCode": "0x35", diff --git a/tools/perf/pmu-events/arch/x86/sierraforest/uncore-memory.json b/tools/perf/pmu-events/arch/x86/sierraforest/uncore-memory.json index ae9c62b32e92..c7e9dbe02eb0 100644 --- a/tools/perf/pmu-events/arch/x86/sierraforest/uncore-memory.json +++ b/tools/perf/pmu-events/arch/x86/sierraforest/uncore-memory.json @@ -189,6 +189,94 @@ "Unit": "IMC" }, { + "BriefDescription": "# of cycles MR4 temp readings forced 2x refresh", + "Counter": "0,1,2,3", + "EventCode": "0xA7", + "EventName": "UNC_M_MR4_2XREF_CYCLES.SCH0_DIMM0", + "Experimental": "1", + "PerPkg": "1", + "PublicDescription": "-", + "UMask": "0x1", + "Unit": "IMC" + }, + { + "BriefDescription": "# of cycles MR4 temp readings forced 2x refresh", + "Counter": "0,1,2,3", + "EventCode": "0xA7", + "EventName": "UNC_M_MR4_2XREF_CYCLES.SCH0_DIMM1", + "Experimental": "1", + "PerPkg": "1", + "PublicDescription": "-", + "UMask": "0x2", + "Unit": "IMC" + }, + { + "BriefDescription": "# of cycles MR4 temp readings forced 2x refresh", + "Counter": "0,1,2,3", + "EventCode": "0xA7", + "EventName": "UNC_M_MR4_2XREF_CYCLES.SCH1_DIMM0", + "Experimental": "1", + "PerPkg": "1", + "PublicDescription": "-", + "UMask": "0x4", + "Unit": "IMC" + }, + { + "BriefDescription": "# of cycles MR4 temp readings forced 2x refresh", + "Counter": "0,1,2,3", + "EventCode": "0xA7", + "EventName": "UNC_M_MR4_2XREF_CYCLES.SCH1_DIMM1", + "Experimental": "1", + "PerPkg": "1", + "PublicDescription": "-", + "UMask": "0x8", + "Unit": "IMC" + }, + { + "BriefDescription": "# of cycles MR4 MRRs was triggered/running", + "Counter": "0,1,2,3", + "EventCode": "0xA6", + "EventName": "UNC_M_PDC_MR4ACTIVE_CYCLES.SCH0_DIMM0", + "Experimental": "1", + "PerPkg": "1", + "PublicDescription": "-", + "UMask": "0x1", + "Unit": "IMC" + }, + { + "BriefDescription": "# of cycles MR4 MRRs was triggered/running", + "Counter": "0,1,2,3", + "EventCode": "0xA6", + "EventName": "UNC_M_PDC_MR4ACTIVE_CYCLES.SCH0_DIMM1", + "Experimental": "1", + "PerPkg": "1", + "PublicDescription": "-", + "UMask": "0x2", + "Unit": "IMC" + }, + { + "BriefDescription": "# of cycles MR4 MRRs was triggered/running", + "Counter": "0,1,2,3", + "EventCode": "0xA6", + "EventName": "UNC_M_PDC_MR4ACTIVE_CYCLES.SCH1_DIMM0", + "Experimental": "1", + "PerPkg": "1", + "PublicDescription": "-", + "UMask": "0x4", + "Unit": "IMC" + }, + { + "BriefDescription": "# of cycles MR4 MRRs was triggered/running", + "Counter": "0,1,2,3", + "EventCode": "0xA6", + "EventName": "UNC_M_PDC_MR4ACTIVE_CYCLES.SCH1_DIMM1", + "Experimental": "1", + "PerPkg": "1", + "PublicDescription": "-", + "UMask": "0x8", + "Unit": "IMC" + }, + { "BriefDescription": "# of cycles a given rank is in Power Down Mode", "Counter": "0,1,2,3", "EventCode": "0x47", @@ -287,6 +375,70 @@ "Unit": "IMC" }, { + "BriefDescription": "# of cycles Throttling at Critical level on specified DIMM and throttle level is zero.", + "Counter": "0,1,2,3", + "EventCode": "0x89", + "EventName": "UNC_M_POWER_CRITICAL_THROTTLE_CYCLES.SLOT0", + "Experimental": "1", + "PerPkg": "1", + "PublicDescription": "-", + "UMask": "0x1", + "Unit": "IMC" + }, + { + "BriefDescription": "# of cycles Throttling at Critical level on specified DIMM and throttle level is zero.", + "Counter": "0,1,2,3", + "EventCode": "0x89", + "EventName": "UNC_M_POWER_CRITICAL_THROTTLE_CYCLES.SLOT1", + "Experimental": "1", + "PerPkg": "1", + "PublicDescription": "-", + "UMask": "0x2", + "Unit": "IMC" + }, + { + "BriefDescription": "UNC_M_POWER_THROTTLE_CYCLES.BW_SLOT0", + "Counter": "0,1,2,3", + "EventCode": "0x46", + "EventName": "UNC_M_POWER_THROTTLE_CYCLES.BW_SLOT0", + "Experimental": "1", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "IMC" + }, + { + "BriefDescription": "UNC_M_POWER_THROTTLE_CYCLES.BW_SLOT1", + "Counter": "0,1,2,3", + "EventCode": "0x46", + "EventName": "UNC_M_POWER_THROTTLE_CYCLES.BW_SLOT1", + "Experimental": "1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "IMC" + }, + { + "BriefDescription": "MR4 temp reading is throttling", + "Counter": "0,1,2,3", + "EventCode": "0x46", + "EventName": "UNC_M_POWER_THROTTLE_CYCLES.MR4BLKEN", + "Experimental": "1", + "PerPkg": "1", + "PublicDescription": "-", + "UMask": "0x8", + "Unit": "IMC" + }, + { + "BriefDescription": "RAPL is throttling", + "Counter": "0,1,2,3", + "EventCode": "0x46", + "EventName": "UNC_M_POWER_THROTTLE_CYCLES.RAPLBLK", + "Experimental": "1", + "PerPkg": "1", + "PublicDescription": "-", + "UMask": "0x4", + "Unit": "IMC" + }, + { "BriefDescription": "DRAM Precharge commands. : Counts the number of DRAM Precharge commands sent on this channel.", "Counter": "0,1,2,3", "EventCode": "0x03", @@ -481,6 +633,94 @@ "Unit": "IMC" }, { + "BriefDescription": "# of cycles Throttling at Critical level on specified DIMM", + "Counter": "0,1,2,3", + "EventCode": "0x8e", + "EventName": "UNC_M_THROTTLE_CRIT_CYCLES.SLOT0", + "Experimental": "1", + "PerPkg": "1", + "PublicDescription": "-", + "UMask": "0x1", + "Unit": "IMC" + }, + { + "BriefDescription": "# of cycles Throttling at Critical level on specified DIMM", + "Counter": "0,1,2,3", + "EventCode": "0x8e", + "EventName": "UNC_M_THROTTLE_CRIT_CYCLES.SLOT1", + "Experimental": "1", + "PerPkg": "1", + "PublicDescription": "-", + "UMask": "0x2", + "Unit": "IMC" + }, + { + "BriefDescription": "# of cycles Throttling at High level on specified DIMM", + "Counter": "0,1,2,3", + "EventCode": "0x8d", + "EventName": "UNC_M_THROTTLE_HIGH_CYCLES.SLOT0", + "Experimental": "1", + "PerPkg": "1", + "PublicDescription": "-", + "UMask": "0x1", + "Unit": "IMC" + }, + { + "BriefDescription": "# of cycles Throttling at High level on specified DIMM", + "Counter": "0,1,2,3", + "EventCode": "0x8d", + "EventName": "UNC_M_THROTTLE_HIGH_CYCLES.SLOT1", + "Experimental": "1", + "PerPkg": "1", + "PublicDescription": "-", + "UMask": "0x2", + "Unit": "IMC" + }, + { + "BriefDescription": "# of cycles Throttling at Normal level on specified DIMM", + "Counter": "0,1,2,3", + "EventCode": "0x8b", + "EventName": "UNC_M_THROTTLE_LOW_CYCLES.SLOT0", + "Experimental": "1", + "PerPkg": "1", + "PublicDescription": "-", + "UMask": "0x1", + "Unit": "IMC" + }, + { + "BriefDescription": "# of cycles Throttling at Normal level on specified DIMM", + "Counter": "0,1,2,3", + "EventCode": "0x8b", + "EventName": "UNC_M_THROTTLE_LOW_CYCLES.SLOT1", + "Experimental": "1", + "PerPkg": "1", + "PublicDescription": "-", + "UMask": "0x2", + "Unit": "IMC" + }, + { + "BriefDescription": "# of cycles Throttling at Mid level on specified DIMM", + "Counter": "0,1,2,3", + "EventCode": "0x8c", + "EventName": "UNC_M_THROTTLE_MID_CYCLES.SLOT0", + "Experimental": "1", + "PerPkg": "1", + "PublicDescription": "-", + "UMask": "0x1", + "Unit": "IMC" + }, + { + "BriefDescription": "# of cycles Throttling at Mid level on specified DIMM", + "Counter": "0,1,2,3", + "EventCode": "0x8c", + "EventName": "UNC_M_THROTTLE_MID_CYCLES.SLOT1", + "Experimental": "1", + "PerPkg": "1", + "PublicDescription": "-", + "UMask": "0x2", + "Unit": "IMC" + }, + { "BriefDescription": "Write Pending Queue Allocations", "Counter": "0,1,2,3", "EventCode": "0x22", diff --git a/tools/perf/pmu-events/arch/x86/skylake/skl-metrics.json b/tools/perf/pmu-events/arch/x86/skylake/skl-metrics.json index 2a76dd01fb52..2d3a037e88b5 100644 --- a/tools/perf/pmu-events/arch/x86/skylake/skl-metrics.json +++ b/tools/perf/pmu-events/arch/x86/skylake/skl-metrics.json @@ -74,12 +74,12 @@ "MetricExpr": "LD_BLOCKS_PARTIAL.ADDRESS_ALIAS / tma_info_thread_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group", "MetricName": "tma_4k_aliasing", - "MetricThreshold": "tma_4k_aliasing > 0.2 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", - "PublicDescription": "This metric estimates how often memory load accesses were aliased by preceding stores (in program order) with a 4K address offset. False match is possible; which incur a few cycles load re-issue. However; the short re-issue duration is often hidden by the out-of-order core and HW optimizations; hence a user may safely ignore a high value of this metric unless it manages to propagate up into parent nodes of the hierarchy (e.g. to L1_Bound)", + "MetricThreshold": "tma_4k_aliasing > 0.2 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric estimates how often memory load accesses were aliased by preceding stores (in program order) with a 4K address offset. False match is possible; which incur a few cycles load re-issue. However; the short re-issue duration is often hidden by the out-of-order core and HW optimizations; hence a user may safely ignore a high value of this metric unless it manages to propagate up into parent nodes of the hierarchy (e.g. to L1_Bound).", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution ports for ALU operations", + "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution ports for ALU operations.", "MetricExpr": "(UOPS_DISPATCHED_PORT.PORT_0 + UOPS_DISPATCHED_PORT.PORT_1 + UOPS_DISPATCHED_PORT.PORT_5 + UOPS_DISPATCHED_PORT.PORT_6) / tma_info_thread_slots", "MetricGroup": "TopdownL5;tma_L5_group;tma_ports_utilized_3m_group", "MetricName": "tma_alu_op_utilization", @@ -91,7 +91,7 @@ "MetricExpr": "34 * (FP_ASSIST.ANY + OTHER_ASSISTS.ANY) / tma_info_thread_slots", "MetricGroup": "BvIO;TopdownL4;tma_L4_group;tma_microcode_sequencer_group", "MetricName": "tma_assists", - "MetricThreshold": "tma_assists > 0.1 & tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1", + "MetricThreshold": "tma_assists > 0.1 & (tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1)", "PublicDescription": "This metric estimates fraction of slots the CPU retired uops delivered by the Microcode_Sequencer as a result of Assists. Assists are long sequences of uops that are required in certain corner-cases for operations that cannot be handled natively by the execution pipeline. For example; when working with very small floating point values (so-called Denormals); the FP units are not set up to perform these operations natively. Instead; a sequence of instructions to perform the computation on the Denormals is injected into the pipeline. Since these microcode sequences might be dozens of uops long; Assists can be extremely deleterious to performance and they can be avoided in many cases. Sample with: OTHER_ASSISTS.ANY", "ScaleUnit": "100%" }, @@ -102,7 +102,7 @@ "MetricName": "tma_backend_bound", "MetricThreshold": "tma_backend_bound > 0.2", "MetricgroupNoGroup": "TopdownL1", - "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound", + "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound.", "ScaleUnit": "100%" }, { @@ -112,12 +112,12 @@ "MetricName": "tma_bad_speculation", "MetricThreshold": "tma_bad_speculation > 0.15", "MetricgroupNoGroup": "TopdownL1", - "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example", + "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.", "ScaleUnit": "100%" }, { "BriefDescription": "Total pipeline cost of instruction fetch related bottlenecks by large code footprint programs (i-side cache; TLB and BTB misses)", - "MetricExpr": "100 * tma_fetch_latency * (tma_itlb_misses + tma_icache_misses + tma_unknown_branches) / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches)", + "MetricExpr": "100 * tma_fetch_latency * (tma_itlb_misses + tma_icache_misses + tma_unknown_branches) / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches)", "MetricGroup": "BigFootprint;BvBC;Fed;Frontend;IcMiss;MemoryTLB", "MetricName": "tma_bottleneck_big_code", "MetricThreshold": "tma_bottleneck_big_code > 20" @@ -132,7 +132,7 @@ }, { "BriefDescription": "Total pipeline cost of external Memory- or Cache-Bandwidth related bottlenecks", - "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_mem_bandwidth / (tma_mem_bandwidth + tma_mem_latency)) + tma_memory_bound * (tma_l3_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_sq_full / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_memory_bound * (tma_l1_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_fb_full / (tma_dtlb_load + tma_store_fwd_blk + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_4k_aliasing + tma_fb_full)))", + "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_mem_bandwidth / (tma_mem_bandwidth + tma_mem_latency)) + tma_memory_bound * (tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_sq_full / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_fb_full / (tma_4k_aliasing + tma_dtlb_load + tma_fb_full + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)))", "MetricGroup": "BvMB;Mem;MemoryBW;Offcore;tma_issueBW", "MetricName": "tma_bottleneck_cache_memory_bandwidth", "MetricThreshold": "tma_bottleneck_cache_memory_bandwidth > 20", @@ -140,7 +140,7 @@ }, { "BriefDescription": "Total pipeline cost of external Memory- or Cache-Latency related bottlenecks", - "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_mem_latency / (tma_mem_bandwidth + tma_mem_latency)) + tma_memory_bound * (tma_l3_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_l3_hit_latency / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_memory_bound * tma_l2_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound) + tma_memory_bound * (tma_l1_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_l1_latency_dependency / (tma_dtlb_load + tma_store_fwd_blk + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_4k_aliasing + tma_fb_full)) + tma_memory_bound * (tma_l1_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_lock_latency / (tma_dtlb_load + tma_store_fwd_blk + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_4k_aliasing + tma_fb_full)) + tma_memory_bound * (tma_l1_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_split_loads / (tma_dtlb_load + tma_store_fwd_blk + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_4k_aliasing + tma_fb_full)) + tma_memory_bound * (tma_store_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_split_stores / (tma_store_latency + tma_false_sharing + tma_split_stores + tma_dtlb_store)) + tma_memory_bound * (tma_store_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_store_latency / (tma_store_latency + tma_false_sharing + tma_split_stores + tma_dtlb_store)))", + "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_mem_latency / (tma_mem_bandwidth + tma_mem_latency)) + tma_memory_bound * (tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_l3_hit_latency / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_memory_bound * tma_l2_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) + tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_l1_latency_dependency / (tma_4k_aliasing + tma_dtlb_load + tma_fb_full + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_lock_latency / (tma_4k_aliasing + tma_dtlb_load + tma_fb_full + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_split_loads / (tma_4k_aliasing + tma_dtlb_load + tma_fb_full + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_memory_bound * (tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_split_stores / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency)) + tma_memory_bound * (tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_store_latency / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency)))", "MetricGroup": "BvML;Mem;MemoryLat;Offcore;tma_issueLat", "MetricName": "tma_bottleneck_cache_memory_latency", "MetricThreshold": "tma_bottleneck_cache_memory_latency > 20", @@ -148,22 +148,22 @@ }, { "BriefDescription": "Total pipeline cost when the execution is compute-bound - an estimation", - "MetricExpr": "100 * (tma_core_bound * tma_divider / (tma_divider + tma_serializing_operation + tma_ports_utilization) + tma_core_bound * (tma_ports_utilization / (tma_divider + tma_serializing_operation + tma_ports_utilization)) * (tma_ports_utilized_3m / (tma_ports_utilized_0 + tma_ports_utilized_1 + tma_ports_utilized_2 + tma_ports_utilized_3m)))", + "MetricExpr": "100 * (tma_core_bound * tma_divider / (tma_divider + tma_ports_utilization + tma_serializing_operation) + tma_core_bound * (tma_ports_utilization / (tma_divider + tma_ports_utilization + tma_serializing_operation)) * (tma_ports_utilized_3m / (tma_ports_utilized_0 + tma_ports_utilized_1 + tma_ports_utilized_2 + tma_ports_utilized_3m)))", "MetricGroup": "BvCB;Cor;tma_issueComp", "MetricName": "tma_bottleneck_compute_bound_est", "MetricThreshold": "tma_bottleneck_compute_bound_est > 20", - "PublicDescription": "Total pipeline cost when the execution is compute-bound - an estimation. Covers Core Bound when High ILP as well as when long-latency execution units are busy" + "PublicDescription": "Total pipeline cost when the execution is compute-bound - an estimation. Covers Core Bound when High ILP as well as when long-latency execution units are busy. Related metrics: " }, { "BriefDescription": "Total pipeline cost of instruction fetch bandwidth related bottlenecks (when the front-end could not sustain operations delivery to the back-end)", - "MetricExpr": "100 * (tma_frontend_bound - (1 - 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts) * tma_fetch_latency * tma_mispredicts_resteers / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches) - tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * tma_fetch_latency * (tma_ms_switches + tma_branch_resteers * (tma_clears_resteers + tma_mispredicts_resteers * (10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts)) / (tma_mispredicts_resteers + tma_clears_resteers + tma_unknown_branches)) / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches)) - tma_bottleneck_big_code", + "MetricExpr": "100 * (tma_frontend_bound - (1 - 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts) * tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) - tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * tma_fetch_latency * (tma_ms_switches + tma_branch_resteers * (tma_clears_resteers + tma_mispredicts_resteers * (10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts)) / (tma_clears_resteers + tma_mispredicts_resteers + tma_unknown_branches)) / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches)) - tma_bottleneck_big_code", "MetricGroup": "BvFB;Fed;FetchBW;Frontend", "MetricName": "tma_bottleneck_instruction_fetch_bw", "MetricThreshold": "tma_bottleneck_instruction_fetch_bw > 20" }, { "BriefDescription": "Total pipeline cost of irregular execution (e.g", - "MetricExpr": "100 * (tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * tma_fetch_latency * (tma_ms_switches + tma_branch_resteers * (tma_clears_resteers + tma_mispredicts_resteers * (10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts)) / (tma_mispredicts_resteers + tma_clears_resteers + tma_unknown_branches)) / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches) + 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts * tma_branch_mispredicts + tma_machine_clears * tma_other_nukes / tma_other_nukes + tma_core_bound * (tma_serializing_operation + tma_core_bound * RS_EVENTS.EMPTY_CYCLES / tma_info_thread_clks * tma_ports_utilized_0) / (tma_divider + tma_serializing_operation + tma_ports_utilization) + tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * tma_heavy_operations)", + "MetricExpr": "100 * (tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * tma_fetch_latency * (tma_ms_switches + tma_branch_resteers * (tma_clears_resteers + tma_mispredicts_resteers * (10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts)) / (tma_clears_resteers + tma_mispredicts_resteers + tma_unknown_branches)) / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) + 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts * tma_branch_mispredicts + tma_machine_clears * tma_other_nukes / tma_other_nukes + tma_core_bound * (tma_serializing_operation + tma_core_bound * RS_EVENTS.EMPTY_CYCLES / tma_info_thread_clks * tma_ports_utilized_0) / (tma_divider + tma_ports_utilization + tma_serializing_operation) + tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * tma_heavy_operations)", "MetricGroup": "Bad;BvIO;Cor;Ret;tma_issueMS", "MetricName": "tma_bottleneck_irregular_overhead", "MetricThreshold": "tma_bottleneck_irregular_overhead > 10", @@ -171,7 +171,7 @@ }, { "BriefDescription": "Total pipeline cost of Memory Address Translation related bottlenecks (data-side TLBs)", - "MetricExpr": "100 * (tma_memory_bound * (tma_l1_bound / max(tma_memory_bound, tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_dtlb_load / max(tma_l1_bound, tma_dtlb_load + tma_store_fwd_blk + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_4k_aliasing + tma_fb_full)) + tma_memory_bound * (tma_store_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_dtlb_store / (tma_store_latency + tma_false_sharing + tma_split_stores + tma_dtlb_store)))", + "MetricExpr": "100 * (tma_memory_bound * (tma_l1_bound / max(tma_memory_bound, tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_dtlb_load / max(tma_l1_bound, tma_4k_aliasing + tma_dtlb_load + tma_fb_full + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_memory_bound * (tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_dtlb_store / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency)))", "MetricGroup": "BvMT;Mem;MemoryTLB;Offcore;tma_issueTLB", "MetricName": "tma_bottleneck_memory_data_tlbs", "MetricThreshold": "tma_bottleneck_memory_data_tlbs > 20", @@ -179,15 +179,15 @@ }, { "BriefDescription": "Total pipeline cost of Memory Synchronization related bottlenecks (data transfers and coherency updates across processors)", - "MetricExpr": "100 * (tma_memory_bound * (tma_l3_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound) * (tma_contested_accesses + tma_data_sharing) / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full) + tma_store_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound) * tma_false_sharing / (tma_store_latency + tma_false_sharing + tma_split_stores + tma_dtlb_store - tma_store_latency)) + tma_machine_clears * (1 - tma_other_nukes / tma_other_nukes))", + "MetricExpr": "100 * (tma_memory_bound * (tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_contested_accesses + tma_data_sharing) / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full) + tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * tma_false_sharing / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency - tma_store_latency)) + tma_machine_clears * (1 - tma_other_nukes / tma_other_nukes))", "MetricGroup": "BvMS;LockCont;Mem;Offcore;tma_issueSyncxn", "MetricName": "tma_bottleneck_memory_synchronization", "MetricThreshold": "tma_bottleneck_memory_synchronization > 10", - "PublicDescription": "Total pipeline cost of Memory Synchronization related bottlenecks (data transfers and coherency updates across processors). Related metrics: tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_machine_clears" + "PublicDescription": "Total pipeline cost of Memory Synchronization related bottlenecks (data transfers and coherency updates across processors). Related metrics: tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_machine_clears, tma_remote_cache" }, { "BriefDescription": "Total pipeline cost of Branch Misprediction related bottlenecks", - "MetricExpr": "100 * (1 - 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts) * (tma_branch_mispredicts + tma_fetch_latency * tma_mispredicts_resteers / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches))", + "MetricExpr": "100 * (1 - 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts) * (tma_branch_mispredicts + tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches))", "MetricGroup": "Bad;BadSpec;BrMispredicts;BvMP;tma_issueBM", "MetricName": "tma_bottleneck_mispredictions", "MetricThreshold": "tma_bottleneck_mispredictions > 20", @@ -199,10 +199,10 @@ "MetricGroup": "BvOB;Cor;Offcore", "MetricName": "tma_bottleneck_other_bottlenecks", "MetricThreshold": "tma_bottleneck_other_bottlenecks > 20", - "PublicDescription": "Total pipeline cost of remaining bottlenecks in the back-end. Examples include data-dependencies (Core Bound when Low ILP) and other unlisted memory-related stalls" + "PublicDescription": "Total pipeline cost of remaining bottlenecks in the back-end. Examples include data-dependencies (Core Bound when Low ILP) and other unlisted memory-related stalls." }, { - "BriefDescription": "Total pipeline cost of \"useful operations\" - the portion of Retiring category not covered by Branching_Overhead nor Irregular_Overhead", + "BriefDescription": "Total pipeline cost of \"useful operations\" - the portion of Retiring category not covered by Branching_Overhead nor Irregular_Overhead.", "MetricExpr": "100 * (tma_retiring - (BR_INST_RETIRED.ALL_BRANCHES + 2 * BR_INST_RETIRED.NEAR_CALL + INST_RETIRED.NOP) / tma_info_thread_slots - tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * tma_heavy_operations)", "MetricGroup": "BvUW;Ret", "MetricName": "tma_bottleneck_useful_work", @@ -224,8 +224,8 @@ "MetricExpr": "INT_MISC.CLEAR_RESTEER_CYCLES / tma_info_thread_clks + tma_unknown_branches", "MetricGroup": "FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group", "MetricName": "tma_branch_resteers", - "MetricThreshold": "tma_branch_resteers > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", - "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers. Branch Resteers estimates the Frontend delay in fetching operations from corrected path; following all sorts of miss-predicted branches. For example; branchy code with lots of miss-predictions might get categorized under Branch Resteers. Note the value of this node may overlap with its siblings. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_l3_hit_latency, tma_store_latency", + "MetricThreshold": "tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers. Branch Resteers estimates the Frontend delay in fetching operations from corrected path; following all sorts of miss-predicted branches. For example; branchy code with lots of miss-predictions might get categorized under Branch Resteers. Note the value of this node may overlap with its siblings. Sample with: BR_MISP_RETIRED.ALL_BRANCHES", "ScaleUnit": "100%" }, { @@ -233,8 +233,8 @@ "MetricExpr": "max(0, tma_microcode_sequencer - tma_assists)", "MetricGroup": "TopdownL4;tma_L4_group;tma_microcode_sequencer_group", "MetricName": "tma_cisc", - "MetricThreshold": "tma_cisc > 0.1 & tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1", - "PublicDescription": "This metric estimates fraction of cycles the CPU retired uops originated from CISC (complex instruction set computer) instruction. A CISC instruction has multiple uops that are required to perform the instruction's functionality as in the case of read-modify-write as an example. Since these instructions require multiple uops they may or may not imply sub-optimal use of machine resources", + "MetricThreshold": "tma_cisc > 0.1 & (tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1)", + "PublicDescription": "This metric estimates fraction of cycles the CPU retired uops originated from CISC (complex instruction set computer) instruction. A CISC instruction has multiple uops that are required to perform the instruction's functionality as in the case of read-modify-write as an example. Since these instructions require multiple uops they may or may not imply sub-optimal use of machine resources.", "ScaleUnit": "100%" }, { @@ -242,7 +242,7 @@ "MetricExpr": "(1 - BR_MISP_RETIRED.ALL_BRANCHES / (BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT)) * INT_MISC.CLEAR_RESTEER_CYCLES / tma_info_thread_clks", "MetricGroup": "BadSpec;MachineClears;TopdownL4;tma_L4_group;tma_branch_resteers_group;tma_issueMC", "MetricName": "tma_clears_resteers", - "MetricThreshold": "tma_clears_resteers > 0.05 & tma_branch_resteers > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricThreshold": "tma_clears_resteers > 0.05 & (tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))", "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Machine Clears. Sample with: INT_MISC.CLEAR_RESTEER_CYCLES. Related metrics: tma_l1_bound, tma_machine_clears, tma_microcode_sequencer, tma_ms_switches", "ScaleUnit": "100%" }, @@ -251,7 +251,7 @@ "MetricExpr": "max(0, tma_itlb_misses - tma_code_stlb_miss)", "MetricGroup": "FetchLat;MemoryTLB;TopdownL4;tma_L4_group;tma_itlb_misses_group", "MetricName": "tma_code_stlb_hit", - "MetricThreshold": "tma_code_stlb_hit > 0.05 & tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricThreshold": "tma_code_stlb_hit > 0.05 & (tma_itlb_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))", "ScaleUnit": "100%" }, { @@ -259,33 +259,33 @@ "MetricExpr": "ITLB_MISSES.WALK_ACTIVE / tma_info_thread_clks", "MetricGroup": "FetchLat;MemoryTLB;TopdownL4;tma_L4_group;tma_itlb_misses_group", "MetricName": "tma_code_stlb_miss", - "MetricThreshold": "tma_code_stlb_miss > 0.05 & tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricThreshold": "tma_code_stlb_miss > 0.05 & (tma_itlb_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 2 or 4 MB pages for (instruction) code accesses", + "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 2 or 4 MB pages for (instruction) code accesses.", "MetricExpr": "tma_code_stlb_miss * ITLB_MISSES.WALK_COMPLETED_2M_4M / (ITLB_MISSES.WALK_COMPLETED_4K + ITLB_MISSES.WALK_COMPLETED_2M_4M)", "MetricGroup": "FetchLat;MemoryTLB;TopdownL5;tma_L5_group;tma_code_stlb_miss_group", "MetricName": "tma_code_stlb_miss_2m", - "MetricThreshold": "tma_code_stlb_miss_2m > 0.05 & tma_code_stlb_miss > 0.05 & tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricThreshold": "tma_code_stlb_miss_2m > 0.05 & (tma_code_stlb_miss > 0.05 & (tma_itlb_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)))", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 4 KB pages for (instruction) code accesses", + "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 4 KB pages for (instruction) code accesses.", "MetricExpr": "tma_code_stlb_miss * ITLB_MISSES.WALK_COMPLETED_4K / (ITLB_MISSES.WALK_COMPLETED_4K + ITLB_MISSES.WALK_COMPLETED_2M_4M)", "MetricGroup": "FetchLat;MemoryTLB;TopdownL5;tma_L5_group;tma_code_stlb_miss_group", "MetricName": "tma_code_stlb_miss_4k", - "MetricThreshold": "tma_code_stlb_miss_4k > 0.05 & tma_code_stlb_miss > 0.05 & tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricThreshold": "tma_code_stlb_miss_4k > 0.05 & (tma_code_stlb_miss > 0.05 & (tma_itlb_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)))", "ScaleUnit": "100%" }, { "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses", "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "((22 * tma_info_system_core_frequency - 3.5 * tma_info_system_core_frequency) * MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM + (20 * tma_info_system_core_frequency - 3.5 * tma_info_system_core_frequency) * MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks", + "MetricExpr": "(18.5 * tma_info_system_core_frequency * MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM + 16.5 * tma_info_system_core_frequency * MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks", "MetricGroup": "BvMS;DataSharing;LockCont;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group", "MetricName": "tma_contested_accesses", - "MetricThreshold": "tma_contested_accesses > 0.05 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", - "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses. Contested accesses occur when data written by one Logical Processor are read by another Logical Processor on a different Physical Core. Examples of contested accesses include synchronizations such as locks; true data sharing such as modified locked variables; and false sharing. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM, MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS. Related metrics: tma_bottleneck_memory_synchronization, tma_data_sharing, tma_false_sharing, tma_machine_clears", + "MetricThreshold": "tma_contested_accesses > 0.05 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses. Contested accesses occur when data written by one Logical Processor are read by another Logical Processor on a different Physical Core. Examples of contested accesses include synchronizations such as locks; true data sharing such as modified locked variables; and false sharing. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM_PS;MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS_PS. Related metrics: tma_bottleneck_memory_synchronization, tma_data_sharing, tma_false_sharing, tma_machine_clears, tma_remote_cache", "ScaleUnit": "100%" }, { @@ -296,25 +296,25 @@ "MetricName": "tma_core_bound", "MetricThreshold": "tma_core_bound > 0.1 & tma_backend_bound > 0.2", "MetricgroupNoGroup": "TopdownL2", - "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck. Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations)", + "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck. Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations).", "ScaleUnit": "100%" }, { "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses", "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "(20 * tma_info_system_core_frequency - 3.5 * tma_info_system_core_frequency) * MEM_LOAD_L3_HIT_RETIRED.XSNP_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks", + "MetricExpr": "16.5 * tma_info_system_core_frequency * MEM_LOAD_L3_HIT_RETIRED.XSNP_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks", "MetricGroup": "BvMS;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group", "MetricName": "tma_data_sharing", - "MetricThreshold": "tma_data_sharing > 0.05 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", - "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses. Data shared by multiple Logical Processors (even just read shared) may cause increased access latency due to cache coherency. Excessive data sharing can drastically harm multithreaded performance. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_HIT. Related metrics: tma_bottleneck_memory_synchronization, tma_contested_accesses, tma_false_sharing, tma_machine_clears", + "MetricThreshold": "tma_data_sharing > 0.05 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses. Data shared by multiple Logical Processors (even just read shared) may cause increased access latency due to cache coherency. Excessive data sharing can drastically harm multithreaded performance. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_HIT_PS. Related metrics: tma_bottleneck_memory_synchronization, tma_contested_accesses, tma_false_sharing, tma_machine_clears, tma_remote_cache", "ScaleUnit": "100%" }, { "BriefDescription": "This metric represents fraction of cycles where decoder-0 was the only active decoder", - "MetricExpr": "(cpu@INST_DECODED.DECODERS\\,cmask\\=0x1@ - cpu@INST_DECODED.DECODERS\\,cmask\\=0x2@) / tma_info_core_core_clks / 2", + "MetricExpr": "(cpu@INST_DECODED.DECODERS\\,cmask\\=1@ - cpu@INST_DECODED.DECODERS\\,cmask\\=2@) / tma_info_core_core_clks / 2", "MetricGroup": "DSBmiss;FetchBW;TopdownL4;tma_L4_group;tma_issueD0;tma_mite_group", "MetricName": "tma_decoder0_alone", - "MetricThreshold": "tma_decoder0_alone > 0.1 & tma_mite > 0.1 & tma_fetch_bandwidth > 0.2", + "MetricThreshold": "tma_decoder0_alone > 0.1 & (tma_mite > 0.1 & tma_fetch_bandwidth > 0.2)", "PublicDescription": "This metric represents fraction of cycles where decoder-0 was the only active decoder. Related metrics: tma_few_uops_instructions", "ScaleUnit": "100%" }, @@ -323,7 +323,7 @@ "MetricExpr": "ARITH.DIVIDER_ACTIVE / tma_info_thread_clks", "MetricGroup": "BvCB;TopdownL3;tma_L3_group;tma_core_bound_group", "MetricName": "tma_divider", - "MetricThreshold": "tma_divider > 0.2 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_divider > 0.2 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)", "PublicDescription": "This metric represents fraction of cycles where the Divider unit was active. Divide and square root instructions are performed by the Divider unit and can take considerably longer latency than integer or Floating Point addition; subtraction; or multiplication. Sample with: ARITH.DIVIDER_ACTIVE", "ScaleUnit": "100%" }, @@ -333,7 +333,7 @@ "MetricExpr": "CYCLE_ACTIVITY.STALLS_L3_MISS / tma_info_thread_clks + (CYCLE_ACTIVITY.STALLS_L1D_MISS - CYCLE_ACTIVITY.STALLS_L2_MISS) / tma_info_thread_clks - tma_l2_bound", "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_dram_bound", - "MetricThreshold": "tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", "PublicDescription": "This metric estimates how often the CPU was stalled on accesses to external memory (DRAM) by loads. Better caching can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L3_MISS", "ScaleUnit": "100%" }, @@ -343,7 +343,7 @@ "MetricGroup": "DSB;FetchBW;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group", "MetricName": "tma_dsb", "MetricThreshold": "tma_dsb > 0.15 & tma_fetch_bandwidth > 0.2", - "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to DSB (decoded uop cache) fetch pipeline. For example; inefficient utilization of the DSB cache structure or bank conflict when reading from it; are categorized here", + "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to DSB (decoded uop cache) fetch pipeline. For example; inefficient utilization of the DSB cache structure or bank conflict when reading from it; are categorized here.", "ScaleUnit": "100%" }, { @@ -351,27 +351,27 @@ "MetricExpr": "DSB2MITE_SWITCHES.PENALTY_CYCLES / tma_info_thread_clks", "MetricGroup": "DSBmiss;FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueFB", "MetricName": "tma_dsb_switches", - "MetricThreshold": "tma_dsb_switches > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", - "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines. The DSB (decoded i-cache) is a Uop Cache where the front-end directly delivers Uops (micro operations) avoiding heavy x86 decoding. The DSB pipeline has shorter latency and delivered higher bandwidth than the MITE (legacy instruction decode pipeline). Switching between the two pipelines can cause penalties hence this metric measures the exposed penalty. Sample with: FRONTEND_RETIRED.DSB_MISS. Related metrics: tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp", + "MetricThreshold": "tma_dsb_switches > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines. The DSB (decoded i-cache) is a Uop Cache where the front-end directly delivers Uops (micro operations) avoiding heavy x86 decoding. The DSB pipeline has shorter latency and delivered higher bandwidth than the MITE (legacy instruction decode pipeline). Switching between the two pipelines can cause penalties hence this metric measures the exposed penalty. Sample with: FRONTEND_RETIRED.DSB_MISS_PS. Related metrics: tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp", "ScaleUnit": "100%" }, { "BriefDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses", "MetricConstraint": "NO_GROUP_EVENTS_NMI", - "MetricExpr": "min(9 * cpu@DTLB_LOAD_MISSES.STLB_HIT\\,cmask\\=0x1@ + DTLB_LOAD_MISSES.WALK_ACTIVE, max(CYCLE_ACTIVITY.CYCLES_MEM_ANY - CYCLE_ACTIVITY.CYCLES_L1D_MISS, 0)) / tma_info_thread_clks", + "MetricExpr": "min(9 * cpu@DTLB_LOAD_MISSES.STLB_HIT\\,cmask\\=1@ + DTLB_LOAD_MISSES.WALK_ACTIVE, max(CYCLE_ACTIVITY.CYCLES_MEM_ANY - CYCLE_ACTIVITY.CYCLES_L1D_MISS, 0)) / tma_info_thread_clks", "MetricGroup": "BvMT;MemoryTLB;TopdownL4;tma_L4_group;tma_issueTLB;tma_l1_bound_group", "MetricName": "tma_dtlb_load", - "MetricThreshold": "tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", - "PublicDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses. TLBs (Translation Look-aside Buffers) are processor caches for recently used entries out of the Page Tables that are used to map virtual- to physical-addresses by the operating system. This metric approximates the potential delay of demand loads missing the first-level data TLB (assuming worst case scenario with back to back misses to different pages). This includes hitting in the second-level TLB (STLB) as well as performing a hardware page walk on an STLB miss. Sample with: MEM_INST_RETIRED.STLB_MISS_LOADS. Related metrics: tma_bottleneck_memory_data_tlbs, tma_dtlb_store", + "MetricThreshold": "tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses. TLBs (Translation Look-aside Buffers) are processor caches for recently used entries out of the Page Tables that are used to map virtual- to physical-addresses by the operating system. This metric approximates the potential delay of demand loads missing the first-level data TLB (assuming worst case scenario with back to back misses to different pages). This includes hitting in the second-level TLB (STLB) as well as performing a hardware page walk on an STLB miss. Sample with: MEM_INST_RETIRED.STLB_MISS_LOADS_PS. Related metrics: tma_bottleneck_memory_data_tlbs, tma_dtlb_store", "ScaleUnit": "100%" }, { "BriefDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses", - "MetricExpr": "(9 * cpu@DTLB_STORE_MISSES.STLB_HIT\\,cmask\\=0x1@ + DTLB_STORE_MISSES.WALK_ACTIVE) / tma_info_core_core_clks", + "MetricExpr": "(9 * cpu@DTLB_STORE_MISSES.STLB_HIT\\,cmask\\=1@ + DTLB_STORE_MISSES.WALK_ACTIVE) / tma_info_core_core_clks", "MetricGroup": "BvMT;MemoryTLB;TopdownL4;tma_L4_group;tma_issueTLB;tma_store_bound_group", "MetricName": "tma_dtlb_store", - "MetricThreshold": "tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", - "PublicDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses. As with ordinary data caching; focus on improving data locality and reducing working-set size to reduce DTLB overhead. Additionally; consider using profile-guided optimization (PGO) to collocate frequently-used data on the same page. Try using larger page sizes for large amounts of frequently-used data. Sample with: MEM_INST_RETIRED.STLB_MISS_STORES. Related metrics: tma_bottleneck_memory_data_tlbs, tma_dtlb_load", + "MetricThreshold": "tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses. As with ordinary data caching; focus on improving data locality and reducing working-set size to reduce DTLB overhead. Additionally; consider using profile-guided optimization (PGO) to collocate frequently-used data on the same page. Try using larger page sizes for large amounts of frequently-used data. Sample with: MEM_INST_RETIRED.STLB_MISS_STORES_PS. Related metrics: tma_bottleneck_memory_data_tlbs, tma_dtlb_load", "ScaleUnit": "100%" }, { @@ -380,18 +380,18 @@ "MetricExpr": "22 * tma_info_system_core_frequency * OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.SNOOP_HITM / tma_info_thread_clks", "MetricGroup": "BvMS;DataSharing;LockCont;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_store_bound_group", "MetricName": "tma_false_sharing", - "MetricThreshold": "tma_false_sharing > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", - "PublicDescription": "This metric roughly estimates how often CPU was handling synchronizations due to False Sharing. False Sharing is a multithreading hiccup; where multiple Logical Processors contend on different data-elements mapped into the same cache line. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM, OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.SNOOP_HITM. Related metrics: tma_bottleneck_memory_synchronization, tma_contested_accesses, tma_data_sharing, tma_machine_clears", + "MetricThreshold": "tma_false_sharing > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric roughly estimates how often CPU was handling synchronizations due to False Sharing. False Sharing is a multithreading hiccup; where multiple Logical Processors contend on different data-elements mapped into the same cache line. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM_PS;OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.SNOOP_HITM. Related metrics: tma_bottleneck_memory_synchronization, tma_contested_accesses, tma_data_sharing, tma_machine_clears, tma_remote_cache", "ScaleUnit": "100%" }, { "BriefDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed", "MetricConstraint": "NO_GROUP_EVENTS_NMI", - "MetricExpr": "tma_info_memory_load_miss_real_latency * cpu@L1D_PEND_MISS.FB_FULL\\,cmask\\=0x1@ / tma_info_thread_clks", + "MetricExpr": "tma_info_memory_load_miss_real_latency * cpu@L1D_PEND_MISS.FB_FULL\\,cmask\\=1@ / tma_info_thread_clks", "MetricGroup": "BvMB;MemoryBW;TopdownL4;tma_L4_group;tma_issueBW;tma_issueSL;tma_issueSmSt;tma_l1_bound_group", "MetricName": "tma_fb_full", "MetricThreshold": "tma_fb_full > 0.3", - "PublicDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed. The higher the metric value; the deeper the memory hierarchy level the misses are satisfied from (metric values >1 are valid). Often it hints on approaching bandwidth limits (to L2 cache; L3 cache or external memory). Related metrics: tma_bottleneck_cache_memory_bandwidth, tma_info_system_dram_bw_use, tma_mem_bandwidth, tma_sq_full, tma_store_latency", + "PublicDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed. The higher the metric value; the deeper the memory hierarchy level the misses are satisfied from (metric values >1 are valid). Often it hints on approaching bandwidth limits (to L2 cache; L3 cache or external memory). Related metrics: tma_bottleneck_cache_memory_bandwidth, tma_info_system_dram_bw_use, tma_mem_bandwidth, tma_sq_full, tma_store_latency, tma_streaming_stores", "ScaleUnit": "100%" }, { @@ -401,7 +401,7 @@ "MetricName": "tma_fetch_bandwidth", "MetricThreshold": "tma_fetch_bandwidth > 0.2", "MetricgroupNoGroup": "TopdownL2", - "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues. For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Sample with: FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1, FRONTEND_RETIRED.LATENCY_GE_1, FRONTEND_RETIRED.LATENCY_GE_2. Related metrics: tma_dsb_switches, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp", + "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues. For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Sample with: FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1;FRONTEND_RETIRED.LATENCY_GE_1;FRONTEND_RETIRED.LATENCY_GE_2. Related metrics: tma_dsb_switches, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp", "ScaleUnit": "100%" }, { @@ -411,7 +411,7 @@ "MetricName": "tma_fetch_latency", "MetricThreshold": "tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", "MetricgroupNoGroup": "TopdownL2", - "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues. For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: FRONTEND_RETIRED.LATENCY_GE_16, FRONTEND_RETIRED.LATENCY_GE_8", + "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues. For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: FRONTEND_RETIRED.LATENCY_GE_16_PS;FRONTEND_RETIRED.LATENCY_GE_8_PS", "ScaleUnit": "100%" }, { @@ -431,7 +431,7 @@ "MetricGroup": "HPC;TopdownL3;tma_L3_group;tma_light_operations_group", "MetricName": "tma_fp_arith", "MetricThreshold": "tma_fp_arith > 0.2 & tma_light_operations > 0.6", - "PublicDescription": "This metric represents overall arithmetic floating-point (FP) operations fraction the CPU has executed (retired). Note this metric's value may exceed its parent due to use of \"Uops\" CountDomain and FMA double-counting", + "PublicDescription": "This metric represents overall arithmetic floating-point (FP) operations fraction the CPU has executed (retired). Note this metric's value may exceed its parent due to use of \"Uops\" CountDomain and FMA double-counting.", "ScaleUnit": "100%" }, { @@ -440,7 +440,7 @@ "MetricGroup": "HPC;TopdownL5;tma_L5_group;tma_assists_group", "MetricName": "tma_fp_assists", "MetricThreshold": "tma_fp_assists > 0.1", - "PublicDescription": "This metric roughly estimates fraction of slots the CPU retired uops as a result of handing Floating Point (FP) Assists. FP Assist may apply when working with very small floating point values (so-called Denormals)", + "PublicDescription": "This metric roughly estimates fraction of slots the CPU retired uops as a result of handing Floating Point (FP) Assists. FP Assist may apply when working with very small floating point values (so-called Denormals).", "ScaleUnit": "100%" }, { @@ -448,8 +448,8 @@ "MetricExpr": "FP_ARITH_INST_RETIRED.SCALAR / UOPS_RETIRED.RETIRE_SLOTS", "MetricGroup": "Compute;Flops;TopdownL4;tma_L4_group;tma_fp_arith_group;tma_issue2P", "MetricName": "tma_fp_scalar", - "MetricThreshold": "tma_fp_scalar > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6", - "PublicDescription": "This metric approximates arithmetic floating-point (FP) scalar uops fraction the CPU has retired. May overcount due to FMA double counting. Related metrics: tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", + "MetricThreshold": "tma_fp_scalar > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6)", + "PublicDescription": "This metric approximates arithmetic floating-point (FP) scalar uops fraction the CPU has retired. May overcount due to FMA double counting. Related metrics: tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%" }, { @@ -458,8 +458,8 @@ "MetricExpr": "FP_ARITH_INST_RETIRED.VECTOR / UOPS_RETIRED.RETIRE_SLOTS", "MetricGroup": "Compute;Flops;TopdownL4;tma_L4_group;tma_fp_arith_group;tma_issue2P", "MetricName": "tma_fp_vector", - "MetricThreshold": "tma_fp_vector > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6", - "PublicDescription": "This metric approximates arithmetic floating-point (FP) vector uops fraction the CPU has retired aggregated across all vector widths. May overcount due to FMA double counting. Related metrics: tma_fp_scalar, tma_fp_vector_128b, tma_fp_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", + "MetricThreshold": "tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6)", + "PublicDescription": "This metric approximates arithmetic floating-point (FP) vector uops fraction the CPU has retired aggregated across all vector widths. May overcount due to FMA double counting. Related metrics: tma_fp_scalar, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%" }, { @@ -467,8 +467,8 @@ "MetricExpr": "(FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE) / UOPS_RETIRED.RETIRE_SLOTS", "MetricGroup": "Compute;Flops;TopdownL5;tma_L5_group;tma_fp_vector_group;tma_issue2P", "MetricName": "tma_fp_vector_128b", - "MetricThreshold": "tma_fp_vector_128b > 0.1 & tma_fp_vector > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6", - "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 128-bit wide vectors. May overcount due to FMA double counting prior to LNL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", + "MetricThreshold": "tma_fp_vector_128b > 0.1 & (tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6))", + "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 128-bit wide vectors. May overcount due to FMA double counting prior to LNL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%" }, { @@ -476,8 +476,8 @@ "MetricExpr": "(FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE) / UOPS_RETIRED.RETIRE_SLOTS", "MetricGroup": "Compute;Flops;TopdownL5;tma_L5_group;tma_fp_vector_group;tma_issue2P", "MetricName": "tma_fp_vector_256b", - "MetricThreshold": "tma_fp_vector_256b > 0.1 & tma_fp_vector > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6", - "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 256-bit wide vectors. May overcount due to FMA double counting prior to LNL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", + "MetricThreshold": "tma_fp_vector_256b > 0.1 & (tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6))", + "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 256-bit wide vectors. May overcount due to FMA double counting prior to LNL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%" }, { @@ -487,35 +487,35 @@ "MetricName": "tma_frontend_bound", "MetricThreshold": "tma_frontend_bound > 0.15", "MetricgroupNoGroup": "TopdownL1", - "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound. Sample with: FRONTEND_RETIRED.LATENCY_GE_4", + "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound. Sample with: FRONTEND_RETIRED.LATENCY_GE_4_PS", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of slots where the CPU was retiring fused instructions , where one uop can represent multiple contiguous instructions", + "BriefDescription": "This metric represents fraction of slots where the CPU was retiring fused instructions -- where one uop can represent multiple contiguous instructions", "MetricExpr": "tma_light_operations * UOPS_RETIRED.MACRO_FUSED / UOPS_RETIRED.RETIRE_SLOTS", "MetricGroup": "Branches;BvBO;Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group", "MetricName": "tma_fused_instructions", "MetricThreshold": "tma_fused_instructions > 0.1 & tma_light_operations > 0.6", - "PublicDescription": "This metric represents fraction of slots where the CPU was retiring fused instructions , where one uop can represent multiple contiguous instructions. CMP+JCC or DEC+JCC are common examples of legacy fusions. {([MTL] Note new MOV+OP and Load+OP fusions appear under Other_Light_Ops in MTL!)}", + "PublicDescription": "This metric represents fraction of slots where the CPU was retiring fused instructions -- where one uop can represent multiple contiguous instructions. CMP+JCC or DEC+JCC are common examples of legacy fusions. {([MTL] Note new MOV+OP and Load+OP fusions appear under Other_Light_Ops in MTL!)}", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations , instructions that require two or more uops or micro-coded sequences", + "BriefDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences", "MetricExpr": "(UOPS_RETIRED.RETIRE_SLOTS + UOPS_RETIRED.MACRO_FUSED - INST_RETIRED.ANY) / tma_info_thread_slots", "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_heavy_operations", "MetricThreshold": "tma_heavy_operations > 0.1", "MetricgroupNoGroup": "TopdownL2", - "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations , instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences.([ICL+] Note this may overcount due to approximation using indirect events; [ADL+])", + "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences.([ICL+] Note this may overcount due to approximation using indirect events; [ADL+])", "ScaleUnit": "100%" }, { "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to instruction cache misses", - "MetricExpr": "(ICACHE_16B.IFDATA_STALL + 2 * cpu@ICACHE_16B.IFDATA_STALL\\,cmask\\=0x1\\,edge\\=0x1@) / tma_info_thread_clks", + "MetricExpr": "(ICACHE_16B.IFDATA_STALL + 2 * cpu@ICACHE_16B.IFDATA_STALL\\,cmask\\=1\\,edge@) / tma_info_thread_clks", "MetricGroup": "BigFootprint;BvBC;FetchLat;IcMiss;TopdownL3;tma_L3_group;tma_fetch_latency_group", "MetricName": "tma_icache_misses", - "MetricThreshold": "tma_icache_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", - "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to instruction cache misses. Sample with: FRONTEND_RETIRED.L2_MISS, FRONTEND_RETIRED.L1I_MISS", + "MetricThreshold": "tma_icache_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to instruction cache misses. Sample with: FRONTEND_RETIRED.L2_MISS_PS;FRONTEND_RETIRED.L1I_MISS_PS", "ScaleUnit": "100%" }, { @@ -526,11 +526,11 @@ "PublicDescription": "Branch Misprediction Cost: Cycles representing fraction of TMA slots wasted per non-speculative branch misprediction (retired JEClear). Related metrics: tma_bottleneck_mispredictions, tma_branch_mispredicts, tma_mispredicts_resteers" }, { - "BriefDescription": "Instructions per retired Mispredicts for indirect CALL or JMP branches (lower number means higher occurrence rate)", + "BriefDescription": "Instructions per retired Mispredicts for indirect CALL or JMP branches (lower number means higher occurrence rate).", "MetricExpr": "tma_info_inst_mix_instructions / (UOPS_RETIRED.RETIRE_SLOTS / UOPS_ISSUED.ANY * BR_MISP_EXEC.INDIRECT)", "MetricGroup": "Bad;BrMispredicts", "MetricName": "tma_info_bad_spec_ipmisp_indirect", - "MetricThreshold": "tma_info_bad_spec_ipmisp_indirect < 1000" + "MetricThreshold": "tma_info_bad_spec_ipmisp_indirect < 1e3" }, { "BriefDescription": "Number of Instructions per non-speculative Branch Misprediction (JEClear) (lower number means higher occurrence rate)", @@ -555,7 +555,7 @@ }, { "BriefDescription": "Total pipeline cost of DSB (uop cache) hits - subset of the Instruction_Fetch_BW Bottleneck", - "MetricExpr": "100 * (tma_frontend_bound * (tma_fetch_bandwidth / (tma_fetch_latency + tma_fetch_bandwidth)) * (tma_dsb / (tma_mite + tma_dsb)))", + "MetricExpr": "100 * (tma_frontend_bound * (tma_fetch_bandwidth / (tma_fetch_bandwidth + tma_fetch_latency)) * (tma_dsb / (tma_dsb + tma_mite)))", "MetricGroup": "DSB;Fed;FetchBW;tma_issueFB", "MetricName": "tma_info_botlnk_l2_dsb_bandwidth", "MetricThreshold": "tma_info_botlnk_l2_dsb_bandwidth > 10", @@ -564,7 +564,7 @@ { "BriefDescription": "Total pipeline cost of DSB (uop cache) misses - subset of the Instruction_Fetch_BW Bottleneck", "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "100 * (tma_fetch_latency * tma_dsb_switches / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches) + tma_fetch_bandwidth * tma_mite / (tma_mite + tma_dsb))", + "MetricExpr": "100 * (tma_fetch_latency * tma_dsb_switches / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) + tma_fetch_bandwidth * tma_mite / (tma_dsb + tma_mite))", "MetricGroup": "DSBmiss;Fed;tma_issueFB", "MetricName": "tma_info_botlnk_l2_dsb_misses", "MetricThreshold": "tma_info_botlnk_l2_dsb_misses > 10", @@ -572,10 +572,11 @@ }, { "BriefDescription": "Total pipeline cost of Instruction Cache misses - subset of the Big_Code Bottleneck", - "MetricExpr": "100 * (tma_fetch_latency * tma_icache_misses / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches))", + "MetricExpr": "100 * (tma_fetch_latency * tma_icache_misses / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches))", "MetricGroup": "Fed;FetchLat;IcMiss;tma_issueFL", "MetricName": "tma_info_botlnk_l2_ic_misses", - "MetricThreshold": "tma_info_botlnk_l2_ic_misses > 5" + "MetricThreshold": "tma_info_botlnk_l2_ic_misses > 5", + "PublicDescription": "Total pipeline cost of Instruction Cache misses - subset of the Big_Code Bottleneck. Related metrics: " }, { "BriefDescription": "Fraction of branches that are CALL or RET", @@ -604,7 +605,7 @@ }, { "BriefDescription": "Core actual clocks when any Logical Processor is active on the Physical Core", - "MetricExpr": "(CPU_CLK_UNHALTED.THREAD_ANY / 2 if #SMT_on else tma_info_thread_clks)", + "MetricExpr": "(CPU_CLK_UNHALTED.THREAD / 2 * (1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK) if #core_wide < 1 else (CPU_CLK_UNHALTED.THREAD_ANY / 2 if #SMT_on else tma_info_thread_clks))", "MetricGroup": "SMT", "MetricName": "tma_info_core_core_clks" }, @@ -632,11 +633,11 @@ "MetricExpr": "(FP_ARITH_INST_RETIRED.SCALAR + FP_ARITH_INST_RETIRED.VECTOR) / (2 * tma_info_core_core_clks)", "MetricGroup": "Cor;Flops;HPC", "MetricName": "tma_info_core_fp_arith_utilization", - "PublicDescription": "Actual per-core usage of the Floating Point non-X87 execution units (regardless of precision or vector-width). Values > 1 are possible due to ([BDW+] Fused-Multiply Add (FMA) counting - common; [ADL+] use all of ADD/MUL/FMA in Scalar or 128/256-bit vectors - less common)" + "PublicDescription": "Actual per-core usage of the Floating Point non-X87 execution units (regardless of precision or vector-width). Values > 1 are possible due to ([BDW+] Fused-Multiply Add (FMA) counting - common; [ADL+] use all of ADD/MUL/FMA in Scalar or 128/256-bit vectors - less common)." }, { "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is execution) per thread (logical-processor)", - "MetricExpr": "UOPS_EXECUTED.THREAD / cpu@UOPS_EXECUTED.THREAD\\,cmask\\=0x1@", + "MetricExpr": "UOPS_EXECUTED.THREAD / cpu@UOPS_EXECUTED.THREAD\\,cmask\\=1@", "MetricGroup": "Backend;Cor;Pipeline;PortsUtil", "MetricName": "tma_info_core_ilp" }, @@ -649,20 +650,20 @@ "PublicDescription": "Fraction of Uops delivered by the DSB (aka Decoded ICache; or Uop Cache). Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_inst_mix_iptb, tma_lcp" }, { - "BriefDescription": "Average number of cycles of a switch from the DSB fetch-unit to MITE fetch unit - see DSB_Switches tree node for details", + "BriefDescription": "Average number of cycles of a switch from the DSB fetch-unit to MITE fetch unit - see DSB_Switches tree node for details.", "MetricExpr": "DSB2MITE_SWITCHES.PENALTY_CYCLES / DSB2MITE_SWITCHES.COUNT", "MetricGroup": "DSBmiss", "MetricName": "tma_info_frontend_dsb_switch_cost" }, { "BriefDescription": "Average number of Uops issued by front-end when it issued something", - "MetricExpr": "UOPS_ISSUED.ANY / cpu@UOPS_ISSUED.ANY\\,cmask\\=0x1@", + "MetricExpr": "UOPS_ISSUED.ANY / cpu@UOPS_ISSUED.ANY\\,cmask\\=1@", "MetricGroup": "Fed;FetchBW", "MetricName": "tma_info_frontend_fetch_upc" }, { "BriefDescription": "Average Latency for L1 instruction cache misses", - "MetricExpr": "ICACHE_16B.IFDATA_STALL / cpu@ICACHE_16B.IFDATA_STALL\\,cmask\\=0x1\\,edge\\=0x1@ + 2", + "MetricExpr": "ICACHE_16B.IFDATA_STALL / cpu@ICACHE_16B.IFDATA_STALL\\,cmask\\=1\\,edge@ + 2", "MetricGroup": "Fed;FetchLat;IcMiss", "MetricName": "tma_info_frontend_icache_miss_latency" }, @@ -698,7 +699,7 @@ "MetricName": "tma_info_frontend_tbpc" }, { - "BriefDescription": "Branch instructions per taken branch", + "BriefDescription": "Branch instructions per taken branch.", "MetricExpr": "BR_INST_RETIRED.ALL_BRANCHES / BR_INST_RETIRED.NEAR_TAKEN", "MetricGroup": "Branches;Fed;PGO", "MetricName": "tma_info_inst_mix_bptkbranch" @@ -717,7 +718,7 @@ "MetricGroup": "Flops;InsType", "MetricName": "tma_info_inst_mix_iparith", "MetricThreshold": "tma_info_inst_mix_iparith < 10", - "PublicDescription": "Instructions per FP Arithmetic instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting. Approximated prior to BDW" + "PublicDescription": "Instructions per FP Arithmetic instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting. Approximated prior to BDW." }, { "BriefDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number means higher occurrence rate)", @@ -725,7 +726,7 @@ "MetricGroup": "Flops;FpVector;InsType", "MetricName": "tma_info_inst_mix_iparith_avx128", "MetricThreshold": "tma_info_inst_mix_iparith_avx128 < 10", - "PublicDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting" + "PublicDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting." }, { "BriefDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means higher occurrence rate)", @@ -733,7 +734,7 @@ "MetricGroup": "Flops;FpVector;InsType", "MetricName": "tma_info_inst_mix_iparith_avx256", "MetricThreshold": "tma_info_inst_mix_iparith_avx256 < 10", - "PublicDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting" + "PublicDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting." }, { "BriefDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction (lower number means higher occurrence rate)", @@ -741,7 +742,7 @@ "MetricGroup": "Flops;FpScalar;InsType", "MetricName": "tma_info_inst_mix_iparith_scalar_dp", "MetricThreshold": "tma_info_inst_mix_iparith_scalar_dp < 10", - "PublicDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting" + "PublicDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting." }, { "BriefDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction (lower number means higher occurrence rate)", @@ -749,7 +750,7 @@ "MetricGroup": "Flops;FpScalar;InsType", "MetricName": "tma_info_inst_mix_iparith_scalar_sp", "MetricThreshold": "tma_info_inst_mix_iparith_scalar_sp < 10", - "PublicDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting" + "PublicDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting." }, { "BriefDescription": "Instructions per Branch (lower number means higher occurrence rate)", @@ -799,7 +800,7 @@ "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_TAKEN", "MetricGroup": "Branches;Fed;FetchBW;Frontend;PGO;tma_issueFB", "MetricName": "tma_info_inst_mix_iptb", - "MetricThreshold": "tma_info_inst_mix_iptb < 4 * 2 + 1", + "MetricThreshold": "tma_info_inst_mix_iptb < 9", "PublicDescription": "Instructions per taken branch. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_lcp" }, { @@ -974,8 +975,8 @@ "MetricName": "tma_info_memory_tlb_store_stlb_mpki" }, { - "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is execution) per core", - "MetricExpr": "UOPS_EXECUTED.THREAD / (UOPS_EXECUTED.CORE_CYCLES_GE_1 / 2 if #SMT_on else cpu@UOPS_EXECUTED.THREAD\\,cmask\\=0x1@)", + "BriefDescription": "", + "MetricExpr": "UOPS_EXECUTED.THREAD / (UOPS_EXECUTED.CORE_CYCLES_GE_1 / 2 if #SMT_on else cpu@UOPS_EXECUTED.THREAD\\,cmask\\=1@)", "MetricGroup": "Cor;Pipeline;PortsUtil;SMT", "MetricName": "tma_info_pipeline_execute" }, @@ -996,12 +997,12 @@ "MetricExpr": "INST_RETIRED.ANY / (FP_ASSIST.ANY + OTHER_ASSISTS.ANY)", "MetricGroup": "MicroSeq;Pipeline;Ret;Retire", "MetricName": "tma_info_pipeline_ipassist", - "MetricThreshold": "tma_info_pipeline_ipassist < 100000", + "MetricThreshold": "tma_info_pipeline_ipassist < 100e3", "PublicDescription": "Instructions per a microcode Assist invocation. See Assists tree node for details (lower number means higher occurrence rate)" }, { - "BriefDescription": "Average number of Uops retired in cycles where at least one uop has retired", - "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / cpu@UOPS_RETIRED.RETIRE_SLOTS\\,cmask\\=0x1@", + "BriefDescription": "Average number of Uops retired in cycles where at least one uop has retired.", + "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / cpu@UOPS_RETIRED.RETIRE_SLOTS\\,cmask\\=1@", "MetricGroup": "Pipeline;Ret", "MetricName": "tma_info_pipeline_retire" }, @@ -1043,14 +1044,13 @@ "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.FAR_BRANCH:u", "MetricGroup": "Branches;OS", "MetricName": "tma_info_system_ipfarbranch", - "MetricThreshold": "tma_info_system_ipfarbranch < 1000000" + "MetricThreshold": "tma_info_system_ipfarbranch < 1e6" }, { "BriefDescription": "Cycles Per Instruction for the Operating System (OS) Kernel mode", "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P:k / INST_RETIRED.ANY_P:k", "MetricGroup": "OS", - "MetricName": "tma_info_system_kernel_cpi", - "ScaleUnit": "1per_instr" + "MetricName": "tma_info_system_kernel_cpi" }, { "BriefDescription": "Fraction of cycles spent in the Operating System (OS) Kernel mode", @@ -1061,7 +1061,7 @@ }, { "BriefDescription": "Average number of parallel data read requests to external memory", - "MetricExpr": "UNC_ARB_TRK_OCCUPANCY.DATA_READ / UNC_ARB_TRK_OCCUPANCY.DATA_READ@cmask\\=0x1@", + "MetricExpr": "UNC_ARB_TRK_OCCUPANCY.DATA_READ / UNC_ARB_TRK_OCCUPANCY.DATA_READ@cmask\\=1@", "MetricGroup": "Mem;MemoryBW;SoC", "MetricName": "tma_info_system_mem_parallel_reads", "PublicDescription": "Average number of parallel data read requests to external memory. Accounts for demand loads and L1/L2 prefetches" @@ -1112,7 +1112,7 @@ "MetricName": "tma_info_system_turbo_utilization" }, { - "BriefDescription": "Per-Logical Processor actual clocks when the Logical Processor is active", + "BriefDescription": "Per-Logical Processor actual clocks when the Logical Processor is active.", "MetricExpr": "CPU_CLK_UNHALTED.THREAD", "MetricGroup": "Pipeline", "MetricName": "tma_info_thread_clks" @@ -1121,15 +1121,14 @@ "BriefDescription": "Cycles Per Instruction (per Logical Processor)", "MetricExpr": "1 / tma_info_thread_ipc", "MetricGroup": "Mem;Pipeline", - "MetricName": "tma_info_thread_cpi", - "ScaleUnit": "1per_instr" + "MetricName": "tma_info_thread_cpi" }, { "BriefDescription": "The ratio of Executed- by Issued-Uops", "MetricExpr": "UOPS_EXECUTED.THREAD / UOPS_ISSUED.ANY", "MetricGroup": "Cor;Pipeline", "MetricName": "tma_info_thread_execute_per_issue", - "PublicDescription": "The ratio of Executed- by Issued-Uops. Ratio > 1 suggests high rate of uop micro-fusions. Ratio < 1 suggest high rate of \"execute\" at rename stage" + "PublicDescription": "The ratio of Executed- by Issued-Uops. Ratio > 1 suggests high rate of uop micro-fusions. Ratio < 1 suggest high rate of \"execute\" at rename stage." }, { "BriefDescription": "Instructions Per Cycle (per Logical Processor)", @@ -1155,15 +1154,15 @@ "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / BR_INST_RETIRED.NEAR_TAKEN", "MetricGroup": "Branches;Fed;FetchBW", "MetricName": "tma_info_thread_uptb", - "MetricThreshold": "tma_info_thread_uptb < 4 * 1.5" + "MetricThreshold": "tma_info_thread_uptb < 6" }, { "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to Instruction TLB (ITLB) misses", "MetricExpr": "ICACHE_TAG.STALLS / tma_info_thread_clks", "MetricGroup": "BigFootprint;BvBC;FetchLat;MemoryTLB;TopdownL3;tma_L3_group;tma_fetch_latency_group", "MetricName": "tma_itlb_misses", - "MetricThreshold": "tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", - "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Instruction TLB (ITLB) misses. Sample with: FRONTEND_RETIRED.STLB_MISS, FRONTEND_RETIRED.ITLB_MISS", + "MetricThreshold": "tma_itlb_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Instruction TLB (ITLB) misses. Sample with: FRONTEND_RETIRED.STLB_MISS_PS;FRONTEND_RETIRED.ITLB_MISS_PS", "ScaleUnit": "100%" }, { @@ -1171,7 +1170,7 @@ "MetricExpr": "max((CYCLE_ACTIVITY.STALLS_MEM_ANY - CYCLE_ACTIVITY.STALLS_L1D_MISS) / tma_info_thread_clks, 0)", "MetricGroup": "CacheHits;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_issueL1;tma_issueMC;tma_memory_bound_group", "MetricName": "tma_l1_bound", - "MetricThreshold": "tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", "PublicDescription": "This metric estimates how often the CPU was stalled without loads missing the L1 Data (L1D) cache. The L1D cache typically has the shortest latency. However; in certain cases like loads blocked on older stores; a load might suffer due to high latency even though it is being satisfied by the L1D. Another example is loads who miss in the TLB. These cases are characterized by execution unit stalls; while some non-completed demand load lives in the machine without having that demand load missing the L1 cache. Sample with: MEM_LOAD_RETIRED.L1_HIT. Related metrics: tma_clears_resteers, tma_machine_clears, tma_microcode_sequencer, tma_ms_switches, tma_ports_utilized_1", "ScaleUnit": "100%" }, @@ -1180,17 +1179,17 @@ "MetricExpr": "min(2 * (MEM_INST_RETIRED.ALL_LOADS - MEM_LOAD_RETIRED.FB_HIT - MEM_LOAD_RETIRED.L1_MISS) * 20 / 100, max(CYCLE_ACTIVITY.CYCLES_MEM_ANY - CYCLE_ACTIVITY.CYCLES_L1D_MISS, 0)) / tma_info_thread_clks", "MetricGroup": "BvML;MemoryLat;TopdownL4;tma_L4_group;tma_l1_bound_group", "MetricName": "tma_l1_latency_dependency", - "MetricThreshold": "tma_l1_latency_dependency > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_l1_latency_dependency > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", "PublicDescription": "This metric([SKL+] roughly; [LNL]) estimates fraction of cycles with demand load accesses that hit the L1D cache. The short latency of the L1D cache may be exposed in pointer-chasing memory access patterns as an example. Sample with: MEM_LOAD_RETIRED.L1_HIT", "ScaleUnit": "100%" }, { "BriefDescription": "This metric estimates how often the CPU was stalled due to L2 cache accesses by loads", "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "MEM_LOAD_RETIRED.L2_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) / (MEM_LOAD_RETIRED.L2_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) + cpu@L1D_PEND_MISS.FB_FULL\\,cmask\\=0x1@) * ((CYCLE_ACTIVITY.STALLS_L1D_MISS - CYCLE_ACTIVITY.STALLS_L2_MISS) / tma_info_thread_clks)", + "MetricExpr": "MEM_LOAD_RETIRED.L2_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) / (MEM_LOAD_RETIRED.L2_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) + cpu@L1D_PEND_MISS.FB_FULL\\,cmask\\=1@) * ((CYCLE_ACTIVITY.STALLS_L1D_MISS - CYCLE_ACTIVITY.STALLS_L2_MISS) / tma_info_thread_clks)", "MetricGroup": "BvML;CacheHits;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_l2_bound", - "MetricThreshold": "tma_l2_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_l2_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", "PublicDescription": "This metric estimates how often the CPU was stalled due to L2 cache accesses by loads. Avoiding cache misses (i.e. L1 misses/L2 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L2_HIT", "ScaleUnit": "100%" }, @@ -1199,7 +1198,7 @@ "MetricExpr": "3.5 * tma_info_system_core_frequency * MEM_LOAD_RETIRED.L2_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks", "MetricGroup": "MemoryLat;TopdownL4;tma_L4_group;tma_l2_bound_group", "MetricName": "tma_l2_hit_latency", - "MetricThreshold": "tma_l2_hit_latency > 0.05 & tma_l2_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_l2_hit_latency > 0.05 & (tma_l2_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", "PublicDescription": "This metric represents fraction of cycles with demand load accesses that hit the L2 cache under unloaded scenarios (possibly L2 latency limited). Avoiding L1 cache misses (i.e. L1 misses/L2 hits) will improve the latency. Sample with: MEM_LOAD_RETIRED.L2_HIT", "ScaleUnit": "100%" }, @@ -1208,17 +1207,17 @@ "MetricExpr": "(CYCLE_ACTIVITY.STALLS_L2_MISS - CYCLE_ACTIVITY.STALLS_L3_MISS) / tma_info_thread_clks", "MetricGroup": "CacheHits;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_l3_bound", - "MetricThreshold": "tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", - "PublicDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core. Avoiding cache misses (i.e. L2 misses/L3 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L3_HIT", + "MetricThreshold": "tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", + "PublicDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core. Avoiding cache misses (i.e. L2 misses/L3 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L3_HIT_PS", "ScaleUnit": "100%" }, { "BriefDescription": "This metric estimates fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited)", - "MetricExpr": "(10 * tma_info_system_core_frequency - 3.5 * tma_info_system_core_frequency) * (MEM_LOAD_RETIRED.L3_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2)) / tma_info_thread_clks", + "MetricExpr": "6.5 * tma_info_system_core_frequency * (MEM_LOAD_RETIRED.L3_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2)) / tma_info_thread_clks", "MetricGroup": "BvML;MemoryLat;TopdownL4;tma_L4_group;tma_issueLat;tma_l3_bound_group", "MetricName": "tma_l3_hit_latency", - "MetricThreshold": "tma_l3_hit_latency > 0.1 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", - "PublicDescription": "This metric estimates fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited). Avoiding private cache misses (i.e. L2 misses/L3 hits) will improve the latency; reduce contention with sibling physical cores and increase performance. Note the value of this node may overlap with its siblings. Sample with: MEM_LOAD_RETIRED.L3_HIT. Related metrics: tma_bottleneck_cache_memory_latency, tma_branch_resteers, tma_mem_latency, tma_store_latency", + "MetricThreshold": "tma_l3_hit_latency > 0.1 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric estimates fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited). Avoiding private cache misses (i.e. L2 misses/L3 hits) will improve the latency; reduce contention with sibling physical cores and increase performance. Note the value of this node may overlap with its siblings. Sample with: MEM_LOAD_RETIRED.L3_HIT_PS. Related metrics: tma_bottleneck_cache_memory_latency, tma_mem_latency", "ScaleUnit": "100%" }, { @@ -1226,18 +1225,18 @@ "MetricExpr": "DECODE.LCP / tma_info_thread_clks", "MetricGroup": "FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueFB", "MetricName": "tma_lcp", - "MetricThreshold": "tma_lcp > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", - "PublicDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs). Using proper compiler flags or Intel Compiler by default will certainly avoid this. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb", + "MetricThreshold": "tma_lcp > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", + "PublicDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs). Using proper compiler flags or Intel Compiler by default will certainly avoid this. #Link: Optimization Guide about LCP BKMs. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations , instructions that require no more than one uop (micro-operation)", + "BriefDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation)", "MetricExpr": "tma_retiring - tma_heavy_operations", "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_light_operations", "MetricThreshold": "tma_light_operations > 0.6", "MetricgroupNoGroup": "TopdownL2", - "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations , instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized code running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. ([ICL+] Note this may undercount due to approximation using indirect events; [ADL+] .). Sample with: INST_RETIRED.PREC_DIST", + "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized code running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. ([ICL+] Note this may undercount due to approximation using indirect events; [ADL+] .). Sample with: INST_RETIRED.PREC_DIST", "ScaleUnit": "100%" }, { @@ -1255,7 +1254,7 @@ "MetricExpr": "tma_dtlb_load - tma_load_stlb_miss", "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_load_group", "MetricName": "tma_load_stlb_hit", - "MetricThreshold": "tma_load_stlb_hit > 0.05 & tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_load_stlb_hit > 0.05 & (tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))", "ScaleUnit": "100%" }, { @@ -1263,31 +1262,31 @@ "MetricExpr": "DTLB_LOAD_MISSES.WALK_ACTIVE / tma_info_thread_clks", "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_load_group", "MetricName": "tma_load_stlb_miss", - "MetricThreshold": "tma_load_stlb_miss > 0.05 & tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_load_stlb_miss > 0.05 & (tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 1 GB pages for data load accesses", + "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 1 GB pages for data load accesses.", "MetricExpr": "tma_load_stlb_miss * DTLB_LOAD_MISSES.WALK_COMPLETED_1G / (DTLB_LOAD_MISSES.WALK_COMPLETED_4K + DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M + DTLB_LOAD_MISSES.WALK_COMPLETED_1G)", "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_load_stlb_miss_group", "MetricName": "tma_load_stlb_miss_1g", - "MetricThreshold": "tma_load_stlb_miss_1g > 0.05 & tma_load_stlb_miss > 0.05 & tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_load_stlb_miss_1g > 0.05 & (tma_load_stlb_miss > 0.05 & (tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))))", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 2 or 4 MB pages for data load accesses", + "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 2 or 4 MB pages for data load accesses.", "MetricExpr": "tma_load_stlb_miss * DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M / (DTLB_LOAD_MISSES.WALK_COMPLETED_4K + DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M + DTLB_LOAD_MISSES.WALK_COMPLETED_1G)", "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_load_stlb_miss_group", "MetricName": "tma_load_stlb_miss_2m", - "MetricThreshold": "tma_load_stlb_miss_2m > 0.05 & tma_load_stlb_miss > 0.05 & tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_load_stlb_miss_2m > 0.05 & (tma_load_stlb_miss > 0.05 & (tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))))", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 4 KB pages for data load accesses", + "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 4 KB pages for data load accesses.", "MetricExpr": "tma_load_stlb_miss * DTLB_LOAD_MISSES.WALK_COMPLETED_4K / (DTLB_LOAD_MISSES.WALK_COMPLETED_4K + DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M + DTLB_LOAD_MISSES.WALK_COMPLETED_1G)", "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_load_stlb_miss_group", "MetricName": "tma_load_stlb_miss_4k", - "MetricThreshold": "tma_load_stlb_miss_4k > 0.05 & tma_load_stlb_miss > 0.05 & tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_load_stlb_miss_4k > 0.05 & (tma_load_stlb_miss > 0.05 & (tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))))", "ScaleUnit": "100%" }, { @@ -1295,7 +1294,7 @@ "MetricExpr": "(12 * max(0, MEM_INST_RETIRED.LOCK_LOADS - L2_RQSTS.ALL_RFO) + MEM_INST_RETIRED.LOCK_LOADS / MEM_INST_RETIRED.ALL_STORES * (9 * L2_RQSTS.RFO_HIT + min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO))) / tma_info_thread_clks", "MetricGroup": "LockCont;Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_l1_bound_group", "MetricName": "tma_lock_latency", - "MetricThreshold": "tma_lock_latency > 0.2 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_lock_latency > 0.2 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", "PublicDescription": "This metric represents fraction of cycles the CPU spent handling cache misses due to lock operations. Due to the microarchitecture handling of locks; they are classified as L1_Bound regardless of what memory source satisfied them. Sample with: MEM_INST_RETIRED.LOCK_LOADS. Related metrics: tma_store_latency", "ScaleUnit": "100%" }, @@ -1307,15 +1306,15 @@ "MetricName": "tma_machine_clears", "MetricThreshold": "tma_machine_clears > 0.1 & tma_bad_speculation > 0.15", "MetricgroupNoGroup": "TopdownL2", - "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears. These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT. Related metrics: tma_bottleneck_memory_synchronization, tma_clears_resteers, tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_l1_bound, tma_microcode_sequencer, tma_ms_switches", + "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears. These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT. Related metrics: tma_bottleneck_memory_synchronization, tma_clears_resteers, tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_l1_bound, tma_microcode_sequencer, tma_ms_switches, tma_remote_cache", "ScaleUnit": "100%" }, { "BriefDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory - DRAM ([SPR-HBM] and/or HBM)", - "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, cpu@OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD\\,cmask\\=0x4@) / tma_info_thread_clks", + "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, cpu@OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD\\,cmask\\=4@) / tma_info_thread_clks", "MetricGroup": "BvMB;MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueBW", "MetricName": "tma_mem_bandwidth", - "MetricThreshold": "tma_mem_bandwidth > 0.2 & tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_mem_bandwidth > 0.2 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", "PublicDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory - DRAM ([SPR-HBM] and/or HBM). The underlying heuristic assumes that a similar off-core traffic is generated by all IA cores. This metric does not aggregate non-data-read requests by this logical processor; requests from other IA Logical Processors/Physical Cores/sockets; or other non-IA devices like GPU; hence the maximum external memory bandwidth limits may or may not be approached when this metric is flagged (see Uncore counters for that). Related metrics: tma_bottleneck_cache_memory_bandwidth, tma_fb_full, tma_info_system_dram_bw_use, tma_sq_full", "ScaleUnit": "100%" }, @@ -1324,7 +1323,7 @@ "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD) / tma_info_thread_clks - tma_mem_bandwidth", "MetricGroup": "BvML;MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueLat", "MetricName": "tma_mem_latency", - "MetricThreshold": "tma_mem_latency > 0.1 & tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_mem_latency > 0.1 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", "PublicDescription": "This metric estimates fraction of cycles where the performance was likely hurt due to latency from external memory - DRAM ([SPR-HBM] and/or HBM). This metric does not aggregate requests from other Logical Processors/Physical Cores/sockets (see Uncore counters for that). Related metrics: tma_bottleneck_cache_memory_latency, tma_l3_hit_latency", "ScaleUnit": "100%" }, @@ -1336,11 +1335,11 @@ "MetricName": "tma_memory_bound", "MetricThreshold": "tma_memory_bound > 0.2 & tma_backend_bound > 0.2", "MetricgroupNoGroup": "TopdownL2", - "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck. Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two)", + "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck. Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two).", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of slots where the CPU was retiring memory operations , uops for memory load or store accesses", + "BriefDescription": "This metric represents fraction of slots where the CPU was retiring memory operations -- uops for memory load or store accesses.", "MetricExpr": "tma_light_operations * MEM_INST_RETIRED.ANY / INST_RETIRED.ANY", "MetricGroup": "Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group", "MetricName": "tma_memory_operations", @@ -1362,7 +1361,7 @@ "MetricExpr": "BR_MISP_RETIRED.ALL_BRANCHES / (BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT) * INT_MISC.CLEAR_RESTEER_CYCLES / tma_info_thread_clks", "MetricGroup": "BadSpec;BrMispredicts;BvMP;TopdownL4;tma_L4_group;tma_branch_resteers_group;tma_issueBM", "MetricName": "tma_mispredicts_resteers", - "MetricThreshold": "tma_mispredicts_resteers > 0.05 & tma_branch_resteers > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricThreshold": "tma_mispredicts_resteers > 0.05 & (tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))", "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Branch Misprediction at execution stage. Sample with: INT_MISC.CLEAR_RESTEER_CYCLES. Related metrics: tma_bottleneck_mispredictions, tma_branch_mispredicts, tma_info_bad_spec_branch_misprediction_cost", "ScaleUnit": "100%" }, @@ -1376,12 +1375,12 @@ "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates penalty in terms of percentage of([SKL+] injected blend uops out of all Uops Issued , the Count Domain; [ADL+] cycles)", + "BriefDescription": "This metric estimates penalty in terms of percentage of([SKL+] injected blend uops out of all Uops Issued -- the Count Domain; [ADL+] cycles)", "MetricExpr": "UOPS_ISSUED.VECTOR_WIDTH_MISMATCH / UOPS_ISSUED.ANY", "MetricGroup": "TopdownL5;tma_L5_group;tma_issueMV;tma_ports_utilized_0_group", "MetricName": "tma_mixing_vectors", "MetricThreshold": "tma_mixing_vectors > 0.05", - "PublicDescription": "This metric estimates penalty in terms of percentage of([SKL+] injected blend uops out of all Uops Issued , the Count Domain; [ADL+] cycles). Usually a Mixing_Vectors over 5% is worth investigating. Read more in Appendix B1 of the Optimizations Guide for this topic. Related metrics: tma_ms_switches", + "PublicDescription": "This metric estimates penalty in terms of percentage of([SKL+] injected blend uops out of all Uops Issued -- the Count Domain; [ADL+] cycles). Usually a Mixing_Vectors over 5% is worth investigating. Read more in Appendix B1 of the Optimizations Guide for this topic. Related metrics: tma_ms_switches", "ScaleUnit": "100%" }, { @@ -1389,7 +1388,7 @@ "MetricExpr": "2 * IDQ.MS_SWITCHES / tma_info_thread_clks", "MetricGroup": "FetchLat;MicroSeq;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueMC;tma_issueMS;tma_issueMV;tma_issueSO", "MetricName": "tma_ms_switches", - "MetricThreshold": "tma_ms_switches > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricThreshold": "tma_ms_switches > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", "PublicDescription": "This metric estimates the fraction of cycles when the CPU was stalled due to switches of uop delivery to the Microcode Sequencer (MS). Commonly used instructions are optimized for delivery by the DSB (decoded i-cache) or MITE (legacy instruction decode) pipelines. Certain operations cannot be handled natively by the execution pipeline; and must be performed by microcode (small programs injected into the execution stream). Switching to the MS too often can negatively impact performance. The MS is designated to deliver long uop flows required by CISC instructions like CPUID; or uncommon conditions like Floating Point Assists when dealing with Denormals. Sample with: IDQ.MS_SWITCHES. Related metrics: tma_bottleneck_irregular_overhead, tma_clears_resteers, tma_l1_bound, tma_machine_clears, tma_microcode_sequencer, tma_mixing_vectors, tma_serializing_operation", "ScaleUnit": "100%" }, @@ -1399,7 +1398,7 @@ "MetricGroup": "Branches;BvBO;Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group", "MetricName": "tma_non_fused_branches", "MetricThreshold": "tma_non_fused_branches > 0.1 & tma_light_operations > 0.6", - "PublicDescription": "This metric represents fraction of slots where the CPU was retiring branch instructions that were not fused. Non-conditional branches like direct JMP or CALL would count here. Can be used to examine fusible conditional jumps that were not fused", + "PublicDescription": "This metric represents fraction of slots where the CPU was retiring branch instructions that were not fused. Non-conditional branches like direct JMP or CALL would count here. Can be used to examine fusible conditional jumps that were not fused.", "ScaleUnit": "100%" }, { @@ -1407,8 +1406,8 @@ "MetricExpr": "tma_light_operations * INST_RETIRED.NOP / UOPS_RETIRED.RETIRE_SLOTS", "MetricGroup": "BvBO;Pipeline;TopdownL4;tma_L4_group;tma_other_light_ops_group", "MetricName": "tma_nop_instructions", - "MetricThreshold": "tma_nop_instructions > 0.1 & tma_other_light_ops > 0.3 & tma_light_operations > 0.6", - "PublicDescription": "This metric represents fraction of slots where the CPU was retiring NOP (no op) instructions. Compilers often use NOPs for certain address alignments - e.g. start address of a function or loop body. Sample with: INST_RETIRED.NOP", + "MetricThreshold": "tma_nop_instructions > 0.1 & (tma_other_light_ops > 0.3 & tma_light_operations > 0.6)", + "PublicDescription": "This metric represents fraction of slots where the CPU was retiring NOP (no op) instructions. Compilers often use NOPs for certain address alignments - e.g. start address of a function or loop body. Sample with: INST_RETIRED.NOP_PS", "ScaleUnit": "100%" }, { @@ -1421,19 +1420,19 @@ "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates fraction of slots the CPU was stalled due to other cases of misprediction (non-retired x86 branches or other types)", + "BriefDescription": "This metric estimates fraction of slots the CPU was stalled due to other cases of misprediction (non-retired x86 branches or other types).", "MetricExpr": "max(tma_branch_mispredicts * (1 - BR_MISP_RETIRED.ALL_BRANCHES / (INT_MISC.CLEARS_COUNT - MACHINE_CLEARS.COUNT)), 0.0001)", "MetricGroup": "BrMispredicts;BvIO;TopdownL3;tma_L3_group;tma_branch_mispredicts_group", "MetricName": "tma_other_mispredicts", - "MetricThreshold": "tma_other_mispredicts > 0.05 & tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", + "MetricThreshold": "tma_other_mispredicts > 0.05 & (tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15)", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of slots the CPU has wasted due to Nukes (Machine Clears) not related to memory ordering", + "BriefDescription": "This metric represents fraction of slots the CPU has wasted due to Nukes (Machine Clears) not related to memory ordering.", "MetricExpr": "max(tma_machine_clears * (1 - MACHINE_CLEARS.MEMORY_ORDERING / MACHINE_CLEARS.COUNT), 0.0001)", "MetricGroup": "BvIO;Machine_Clears;TopdownL3;tma_L3_group;tma_machine_clears_group", "MetricName": "tma_other_nukes", - "MetricThreshold": "tma_other_nukes > 0.05 & tma_machine_clears > 0.1 & tma_bad_speculation > 0.15", + "MetricThreshold": "tma_other_nukes > 0.05 & (tma_machine_clears > 0.1 & tma_bad_speculation > 0.15)", "ScaleUnit": "100%" }, { @@ -1442,7 +1441,7 @@ "MetricGroup": "Compute;TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P", "MetricName": "tma_port_0", "MetricThreshold": "tma_port_0 > 0.6", - "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 0 ([SNB+] ALU; [HSW+] ALU and 2nd branch). Sample with: UOPS_DISPATCHED_PORT.PORT_0. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", + "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 0 ([SNB+] ALU; [HSW+] ALU and 2nd branch). Sample with: UOPS_DISPATCHED.PORT_0. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%" }, { @@ -1451,7 +1450,7 @@ "MetricGroup": "TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P", "MetricName": "tma_port_1", "MetricThreshold": "tma_port_1 > 0.6", - "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 1 (ALU). Sample with: UOPS_DISPATCHED_PORT.PORT_1. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_port_0, tma_port_5, tma_port_6, tma_ports_utilized_2", + "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 1 (ALU). Sample with: UOPS_DISPATCHED.PORT_1. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_5, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%" }, { @@ -1487,7 +1486,7 @@ "MetricGroup": "TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P", "MetricName": "tma_port_5", "MetricThreshold": "tma_port_5 > 0.6", - "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 5 ([SNB+] Branches and ALU; [HSW+] ALU). Sample with: UOPS_DISPATCHED_PORT.PORT_5. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_port_0, tma_port_1, tma_port_6, tma_ports_utilized_2", + "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 5 ([SNB+] Branches and ALU; [HSW+] ALU). Sample with: UOPS_DISPATCHED.PORT_5. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%" }, { @@ -1496,7 +1495,7 @@ "MetricGroup": "TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P", "MetricName": "tma_port_6", "MetricThreshold": "tma_port_6 > 0.6", - "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 6 ([HSW+] Primary Branch and simple ALU). Sample with: UOPS_DISPATCHED_PORT.PORT_1. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_ports_utilized_2", + "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 6 ([HSW+] Primary Branch and simple ALU). Sample with: UOPS_DISPATCHED.PORT_1. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_ports_utilized_2", "ScaleUnit": "100%" }, { @@ -1513,8 +1512,8 @@ "MetricExpr": "((tma_ports_utilized_0 * tma_info_thread_clks + (EXE_ACTIVITY.1_PORTS_UTIL + tma_retiring * EXE_ACTIVITY.2_PORTS_UTIL)) / tma_info_thread_clks if ARITH.DIVIDER_ACTIVE < CYCLE_ACTIVITY.STALLS_TOTAL - CYCLE_ACTIVITY.STALLS_MEM_ANY else (EXE_ACTIVITY.1_PORTS_UTIL + tma_retiring * EXE_ACTIVITY.2_PORTS_UTIL) / tma_info_thread_clks)", "MetricGroup": "PortsUtil;TopdownL3;tma_L3_group;tma_core_bound_group", "MetricName": "tma_ports_utilization", - "MetricThreshold": "tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", - "PublicDescription": "This metric estimates fraction of cycles the CPU performance was potentially limited due to Core computation issues (non divider-related). Two distinct categories can be attributed into this metric: (1) heavy data-dependency among contiguous instructions would manifest in this metric - such cases are often referred to as low Instruction Level Parallelism (ILP). (2) Contention on some hardware execution unit other than Divider. For example; when there are too many multiply operations", + "MetricThreshold": "tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)", + "PublicDescription": "This metric estimates fraction of cycles the CPU performance was potentially limited due to Core computation issues (non divider-related). Two distinct categories can be attributed into this metric: (1) heavy data-dependency among contiguous instructions would manifest in this metric - such cases are often referred to as low Instruction Level Parallelism (ILP). (2) Contention on some hardware execution unit other than Divider. For example; when there are too many multiply operations.", "ScaleUnit": "100%" }, { @@ -1522,8 +1521,8 @@ "MetricExpr": "EXE_ACTIVITY.EXE_BOUND_0_PORTS / tma_info_thread_clks", "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group", "MetricName": "tma_ports_utilized_0", - "MetricThreshold": "tma_ports_utilized_0 > 0.2 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", - "PublicDescription": "This metric represents fraction of cycles CPU executed no uops on any execution port (Logical Processor cycles since ICL, Physical Core cycles otherwise). Long-latency instructions like divides may contribute to this metric", + "MetricThreshold": "tma_ports_utilized_0 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric represents fraction of cycles CPU executed no uops on any execution port (Logical Processor cycles since ICL, Physical Core cycles otherwise). Long-latency instructions like divides may contribute to this metric.", "ScaleUnit": "100%" }, { @@ -1531,7 +1530,7 @@ "MetricExpr": "((UOPS_EXECUTED.CORE_CYCLES_GE_1 - UOPS_EXECUTED.CORE_CYCLES_GE_2) / 2 if #SMT_on else EXE_ACTIVITY.1_PORTS_UTIL) / tma_info_core_core_clks", "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_issueL1;tma_ports_utilization_group", "MetricName": "tma_ports_utilized_1", - "MetricThreshold": "tma_ports_utilized_1 > 0.2 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_ports_utilized_1 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", "PublicDescription": "This metric represents fraction of cycles where the CPU executed total of 1 uop per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise). This can be due to heavy data-dependency among software instructions; or over oversubscribing a particular hardware resource. In some other cases with high 1_Port_Utilized and L1_Bound; this metric can point to L1 data-cache latency bottleneck that may not necessarily manifest with complete execution starvation (due to the short L1 latency e.g. walking a linked list) - looking at the assembly can be helpful. Related metrics: tma_l1_bound", "ScaleUnit": "100%" }, @@ -1540,16 +1539,16 @@ "MetricExpr": "((UOPS_EXECUTED.CORE_CYCLES_GE_2 - UOPS_EXECUTED.CORE_CYCLES_GE_3) / 2 if #SMT_on else EXE_ACTIVITY.2_PORTS_UTIL) / tma_info_core_core_clks", "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_issue2P;tma_ports_utilization_group", "MetricName": "tma_ports_utilized_2", - "MetricThreshold": "tma_ports_utilized_2 > 0.15 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", - "PublicDescription": "This metric represents fraction of cycles CPU executed total of 2 uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise). Loop Vectorization -most compilers feature auto-Vectorization options today- reduces pressure on the execution ports as multiple elements are calculated with same uop. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_port_6", + "MetricThreshold": "tma_ports_utilized_2 > 0.15 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric represents fraction of cycles CPU executed total of 2 uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise). Loop Vectorization -most compilers feature auto-Vectorization options today- reduces pressure on the execution ports as multiple elements are calculated with same uop. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of cycles CPU executed total of 3 or more uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise)", + "BriefDescription": "This metric represents fraction of cycles CPU executed total of 3 or more uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise).", "MetricExpr": "(UOPS_EXECUTED.CORE_CYCLES_GE_3 / 2 if #SMT_on else UOPS_EXECUTED.CORE_CYCLES_GE_3) / tma_info_core_core_clks", "MetricGroup": "BvCB;PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group", "MetricName": "tma_ports_utilized_3m", - "MetricThreshold": "tma_ports_utilized_3m > 0.4 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_ports_utilized_3m > 0.4 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", "ScaleUnit": "100%" }, { @@ -1567,7 +1566,7 @@ "MetricExpr": "PARTIAL_RAT_STALLS.SCOREBOARD / tma_info_thread_clks", "MetricGroup": "BvIO;PortsUtil;TopdownL3;tma_L3_group;tma_core_bound_group;tma_issueSO", "MetricName": "tma_serializing_operation", - "MetricThreshold": "tma_serializing_operation > 0.1 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_serializing_operation > 0.1 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)", "PublicDescription": "This metric represents fraction of cycles the CPU issue-pipeline was stalled due to serializing operations. Instructions like CPUID; WRMSR or LFENCE serialize the out-of-order execution which may limit performance. Sample with: PARTIAL_RAT_STALLS.SCOREBOARD. Related metrics: tma_ms_switches", "ScaleUnit": "100%" }, @@ -1578,7 +1577,7 @@ "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group", "MetricName": "tma_split_loads", "MetricThreshold": "tma_split_loads > 0.3", - "PublicDescription": "This metric estimates fraction of cycles handling memory load split accesses - load that cross 64-byte cache line boundary. Sample with: MEM_INST_RETIRED.SPLIT_LOADS", + "PublicDescription": "This metric estimates fraction of cycles handling memory load split accesses - load that cross 64-byte cache line boundary. Sample with: MEM_INST_RETIRED.SPLIT_LOADS_PS", "ScaleUnit": "100%" }, { @@ -1586,8 +1585,8 @@ "MetricExpr": "MEM_INST_RETIRED.SPLIT_STORES / tma_info_core_core_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_issueSpSt;tma_store_bound_group", "MetricName": "tma_split_stores", - "MetricThreshold": "tma_split_stores > 0.2 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", - "PublicDescription": "This metric represents rate of split store accesses. Consider aligning your data to the 64-byte cache line granularity. Sample with: MEM_INST_RETIRED.SPLIT_STORES. Related metrics: tma_port_4", + "MetricThreshold": "tma_split_stores > 0.2 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric represents rate of split store accesses. Consider aligning your data to the 64-byte cache line granularity. Sample with: MEM_INST_RETIRED.SPLIT_STORES_PS. Related metrics: tma_port_4", "ScaleUnit": "100%" }, { @@ -1595,7 +1594,7 @@ "MetricExpr": "(OFFCORE_REQUESTS_BUFFER.SQ_FULL / 2 if #SMT_on else OFFCORE_REQUESTS_BUFFER.SQ_FULL) / tma_info_core_core_clks", "MetricGroup": "BvMB;MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_issueBW;tma_l3_bound_group", "MetricName": "tma_sq_full", - "MetricThreshold": "tma_sq_full > 0.3 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_sq_full > 0.3 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", "PublicDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors). Related metrics: tma_bottleneck_cache_memory_bandwidth, tma_fb_full, tma_info_system_dram_bw_use, tma_mem_bandwidth", "ScaleUnit": "100%" }, @@ -1604,8 +1603,8 @@ "MetricExpr": "EXE_ACTIVITY.BOUND_ON_STORES / tma_info_thread_clks", "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_store_bound", - "MetricThreshold": "tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", - "PublicDescription": "This metric estimates how often CPU was stalled due to RFO store memory accesses; RFO store issue a read-for-ownership request before the write. Even though store accesses do not typically stall out-of-order CPUs; there are few cases where stores can lead to actual stalls. This metric will be flagged should RFO stores be a bottleneck. Sample with: MEM_INST_RETIRED.ALL_STORES", + "MetricThreshold": "tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", + "PublicDescription": "This metric estimates how often CPU was stalled due to RFO store memory accesses; RFO store issue a read-for-ownership request before the write. Even though store accesses do not typically stall out-of-order CPUs; there are few cases where stores can lead to actual stalls. This metric will be flagged should RFO stores be a bottleneck. Sample with: MEM_INST_RETIRED.ALL_STORES_PS", "ScaleUnit": "100%" }, { @@ -1613,8 +1612,8 @@ "MetricExpr": "13 * LD_BLOCKS.STORE_FORWARD / tma_info_thread_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group", "MetricName": "tma_store_fwd_blk", - "MetricThreshold": "tma_store_fwd_blk > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", - "PublicDescription": "This metric roughly estimates fraction of cycles when the memory subsystem had loads blocked since they could not forward data from earlier (in program order) overlapping stores. To streamline memory operations in the pipeline; a load can avoid waiting for memory if a prior in-flight store is writing the data that the load wants to read (store forwarding process). However; in some cases the load may be blocked for a significant time pending the store forward. For example; when the prior store is writing a smaller region than the load is reading", + "MetricThreshold": "tma_store_fwd_blk > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric roughly estimates fraction of cycles when the memory subsystem had loads blocked since they could not forward data from earlier (in program order) overlapping stores. To streamline memory operations in the pipeline; a load can avoid waiting for memory if a prior in-flight store is writing the data that the load wants to read (store forwarding process). However; in some cases the load may be blocked for a significant time pending the store forward. For example; when the prior store is writing a smaller region than the load is reading.", "ScaleUnit": "100%" }, { @@ -1623,8 +1622,8 @@ "MetricExpr": "(L2_RQSTS.RFO_HIT * 9 * (1 - MEM_INST_RETIRED.LOCK_LOADS / MEM_INST_RETIRED.ALL_STORES) + (1 - MEM_INST_RETIRED.LOCK_LOADS / MEM_INST_RETIRED.ALL_STORES) * min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO)) / tma_info_thread_clks", "MetricGroup": "BvML;LockCont;MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_issueSL;tma_store_bound_group", "MetricName": "tma_store_latency", - "MetricThreshold": "tma_store_latency > 0.1 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", - "PublicDescription": "This metric estimates fraction of cycles the CPU spent handling L1D store misses. Store accesses usually less impact out-of-order core performance; however; holding resources for longer time can lead into undesired implications (e.g. contention on L1D fill-buffer entries - see FB_Full). Related metrics: tma_branch_resteers, tma_fb_full, tma_l3_hit_latency, tma_lock_latency", + "MetricThreshold": "tma_store_latency > 0.1 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric estimates fraction of cycles the CPU spent handling L1D store misses. Store accesses usually less impact out-of-order core performance; however; holding resources for longer time can lead into undesired implications (e.g. contention on L1D fill-buffer entries - see FB_Full). Related metrics: tma_fb_full, tma_lock_latency", "ScaleUnit": "100%" }, { @@ -1640,7 +1639,7 @@ "MetricExpr": "tma_dtlb_store - tma_store_stlb_miss", "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_store_group", "MetricName": "tma_store_stlb_hit", - "MetricThreshold": "tma_store_stlb_hit > 0.05 & tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_store_stlb_hit > 0.05 & (tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))", "ScaleUnit": "100%" }, { @@ -1648,31 +1647,31 @@ "MetricExpr": "DTLB_STORE_MISSES.WALK_ACTIVE / tma_info_core_core_clks", "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_store_group", "MetricName": "tma_store_stlb_miss", - "MetricThreshold": "tma_store_stlb_miss > 0.05 & tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_store_stlb_miss > 0.05 & (tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 1 GB pages for data store accesses", + "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 1 GB pages for data store accesses.", "MetricExpr": "tma_store_stlb_miss * DTLB_STORE_MISSES.WALK_COMPLETED_1G / (DTLB_STORE_MISSES.WALK_COMPLETED_4K + DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M + DTLB_STORE_MISSES.WALK_COMPLETED_1G)", "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_store_stlb_miss_group", "MetricName": "tma_store_stlb_miss_1g", - "MetricThreshold": "tma_store_stlb_miss_1g > 0.05 & tma_store_stlb_miss > 0.05 & tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_store_stlb_miss_1g > 0.05 & (tma_store_stlb_miss > 0.05 & (tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))))", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 2 or 4 MB pages for data store accesses", + "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 2 or 4 MB pages for data store accesses.", "MetricExpr": "tma_store_stlb_miss * DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M / (DTLB_STORE_MISSES.WALK_COMPLETED_4K + DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M + DTLB_STORE_MISSES.WALK_COMPLETED_1G)", "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_store_stlb_miss_group", "MetricName": "tma_store_stlb_miss_2m", - "MetricThreshold": "tma_store_stlb_miss_2m > 0.05 & tma_store_stlb_miss > 0.05 & tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_store_stlb_miss_2m > 0.05 & (tma_store_stlb_miss > 0.05 & (tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))))", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 4 KB pages for data store accesses", + "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 4 KB pages for data store accesses.", "MetricExpr": "tma_store_stlb_miss * DTLB_STORE_MISSES.WALK_COMPLETED_4K / (DTLB_STORE_MISSES.WALK_COMPLETED_4K + DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M + DTLB_STORE_MISSES.WALK_COMPLETED_1G)", "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_store_stlb_miss_group", "MetricName": "tma_store_stlb_miss_4k", - "MetricThreshold": "tma_store_stlb_miss_4k > 0.05 & tma_store_stlb_miss > 0.05 & tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_store_stlb_miss_4k > 0.05 & (tma_store_stlb_miss > 0.05 & (tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))))", "ScaleUnit": "100%" }, { @@ -1680,7 +1679,7 @@ "MetricExpr": "9 * BACLEARS.ANY / tma_info_thread_clks", "MetricGroup": "BigFootprint;BvBC;FetchLat;TopdownL4;tma_L4_group;tma_branch_resteers_group", "MetricName": "tma_unknown_branches", - "MetricThreshold": "tma_unknown_branches > 0.05 & tma_branch_resteers > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricThreshold": "tma_unknown_branches > 0.05 & (tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))", "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to new branch address clears. These are fetched branches the Branch Prediction Unit was unable to recognize (e.g. first time the branch is fetched or hitting BTB capacity limit) hence called Unknown Branches. Sample with: BACLEARS.ANY", "ScaleUnit": "100%" }, @@ -1689,8 +1688,8 @@ "MetricExpr": "tma_retiring * UOPS_EXECUTED.X87 / UOPS_EXECUTED.THREAD", "MetricGroup": "Compute;TopdownL4;tma_L4_group;tma_fp_arith_group", "MetricName": "tma_x87_use", - "MetricThreshold": "tma_x87_use > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6", - "PublicDescription": "This metric serves as an approximation of legacy x87 usage. It accounts for instructions beyond X87 FP arithmetic operations; hence may be used as a thermometer to avoid X87 high usage and preferably upgrade to modern ISA. See Tip under Tuning Hint", + "MetricThreshold": "tma_x87_use > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6)", + "PublicDescription": "This metric serves as an approximation of legacy x87 usage. It accounts for instructions beyond X87 FP arithmetic operations; hence may be used as a thermometer to avoid X87 high usage and preferably upgrade to modern ISA. See Tip under Tuning Hint.", "ScaleUnit": "100%" }, { diff --git a/tools/perf/pmu-events/arch/x86/skylakex/cache.json b/tools/perf/pmu-events/arch/x86/skylakex/cache.json index 2ce070629c52..7aeeb5725630 100644 --- a/tools/perf/pmu-events/arch/x86/skylakex/cache.json +++ b/tools/perf/pmu-events/arch/x86/skylakex/cache.json @@ -1,5 +1,79 @@ [ { + "BriefDescription": "CORE_SNOOP_RESPONSE.RSP_IFWDFE", + "Counter": "0,1,2,3", + "EventCode": "0xEF", + "EventName": "CORE_SNOOP_RESPONSE.RSP_IFWDFE", + "SampleAfterValue": "2000003", + "UMask": "0x20" + }, + { + "BriefDescription": "CORE_SNOOP_RESPONSE.RSP_IFWDM", + "Counter": "0,1,2,3", + "EventCode": "0xEF", + "EventName": "CORE_SNOOP_RESPONSE.RSP_IFWDM", + "SampleAfterValue": "2000003", + "UMask": "0x10" + }, + { + "BriefDescription": "CORE_SNOOP_RESPONSE.RSP_IHITFSE", + "Counter": "0,1,2,3", + "EventCode": "0xEF", + "EventName": "CORE_SNOOP_RESPONSE.RSP_IHITFSE", + "SampleAfterValue": "2000003", + "UMask": "0x2" + }, + { + "BriefDescription": "CORE_SNOOP_RESPONSE.RSP_IHITI", + "Counter": "0,1,2,3", + "EventCode": "0xEF", + "EventName": "CORE_SNOOP_RESPONSE.RSP_IHITI", + "SampleAfterValue": "2000003", + "UMask": "0x1" + }, + { + "BriefDescription": "CORE_SNOOP_RESPONSE.RSP_SFWDFE", + "Counter": "0,1,2,3", + "EventCode": "0xEF", + "EventName": "CORE_SNOOP_RESPONSE.RSP_SFWDFE", + "SampleAfterValue": "2000003", + "UMask": "0x40" + }, + { + "BriefDescription": "CORE_SNOOP_RESPONSE.RSP_SFWDM", + "Counter": "0,1,2,3", + "EventCode": "0xEF", + "EventName": "CORE_SNOOP_RESPONSE.RSP_SFWDM", + "SampleAfterValue": "2000003", + "UMask": "0x8" + }, + { + "BriefDescription": "CORE_SNOOP_RESPONSE.RSP_SHITFSE", + "Counter": "0,1,2,3", + "EventCode": "0xEF", + "EventName": "CORE_SNOOP_RESPONSE.RSP_SHITFSE", + "SampleAfterValue": "2000003", + "UMask": "0x4" + }, + { + "BriefDescription": "Counts number of cache lines that are dropped and not written back to L3 as they are deemed to be less likely to be reused shortly", + "Counter": "0,1,2,3", + "EventCode": "0xFE", + "EventName": "IDI_MISC.WB_DOWNGRADE", + "PublicDescription": "Counts number of cache lines that are dropped and not written back to L3 as they are deemed to be less likely to be reused shortly.", + "SampleAfterValue": "100003", + "UMask": "0x4" + }, + { + "BriefDescription": "Counts number of cache lines that are allocated and written back to L3 with the intention that they are more likely to be reused shortly", + "Counter": "0,1,2,3", + "EventCode": "0xFE", + "EventName": "IDI_MISC.WB_UPGRADE", + "PublicDescription": "Counts number of cache lines that are allocated and written back to L3 with the intention that they are more likely to be reused shortly.", + "SampleAfterValue": "100003", + "UMask": "0x2" + }, + { "BriefDescription": "L1D data line replacements", "Counter": "0,1,2,3", "EventCode": "0x51", diff --git a/tools/perf/pmu-events/arch/x86/skylakex/other.json b/tools/perf/pmu-events/arch/x86/skylakex/other.json index 44c820518e12..adf7b6bb5838 100644 --- a/tools/perf/pmu-events/arch/x86/skylakex/other.json +++ b/tools/perf/pmu-events/arch/x86/skylakex/other.json @@ -36,62 +36,6 @@ "UMask": "0x40" }, { - "BriefDescription": "CORE_SNOOP_RESPONSE.RSP_IFWDFE", - "Counter": "0,1,2,3", - "EventCode": "0xEF", - "EventName": "CORE_SNOOP_RESPONSE.RSP_IFWDFE", - "SampleAfterValue": "2000003", - "UMask": "0x20" - }, - { - "BriefDescription": "CORE_SNOOP_RESPONSE.RSP_IFWDM", - "Counter": "0,1,2,3", - "EventCode": "0xEF", - "EventName": "CORE_SNOOP_RESPONSE.RSP_IFWDM", - "SampleAfterValue": "2000003", - "UMask": "0x10" - }, - { - "BriefDescription": "CORE_SNOOP_RESPONSE.RSP_IHITFSE", - "Counter": "0,1,2,3", - "EventCode": "0xEF", - "EventName": "CORE_SNOOP_RESPONSE.RSP_IHITFSE", - "SampleAfterValue": "2000003", - "UMask": "0x2" - }, - { - "BriefDescription": "CORE_SNOOP_RESPONSE.RSP_IHITI", - "Counter": "0,1,2,3", - "EventCode": "0xEF", - "EventName": "CORE_SNOOP_RESPONSE.RSP_IHITI", - "SampleAfterValue": "2000003", - "UMask": "0x1" - }, - { - "BriefDescription": "CORE_SNOOP_RESPONSE.RSP_SFWDFE", - "Counter": "0,1,2,3", - "EventCode": "0xEF", - "EventName": "CORE_SNOOP_RESPONSE.RSP_SFWDFE", - "SampleAfterValue": "2000003", - "UMask": "0x40" - }, - { - "BriefDescription": "CORE_SNOOP_RESPONSE.RSP_SFWDM", - "Counter": "0,1,2,3", - "EventCode": "0xEF", - "EventName": "CORE_SNOOP_RESPONSE.RSP_SFWDM", - "SampleAfterValue": "2000003", - "UMask": "0x8" - }, - { - "BriefDescription": "CORE_SNOOP_RESPONSE.RSP_SHITFSE", - "Counter": "0,1,2,3", - "EventCode": "0xEF", - "EventName": "CORE_SNOOP_RESPONSE.RSP_SHITFSE", - "SampleAfterValue": "2000003", - "UMask": "0x4" - }, - { "BriefDescription": "Number of hardware interrupts received by the processor.", "Counter": "0,1,2,3", "EventCode": "0xCB", @@ -101,24 +45,6 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts number of cache lines that are dropped and not written back to L3 as they are deemed to be less likely to be reused shortly", - "Counter": "0,1,2,3", - "EventCode": "0xFE", - "EventName": "IDI_MISC.WB_DOWNGRADE", - "PublicDescription": "Counts number of cache lines that are dropped and not written back to L3 as they are deemed to be less likely to be reused shortly.", - "SampleAfterValue": "100003", - "UMask": "0x4" - }, - { - "BriefDescription": "Counts number of cache lines that are allocated and written back to L3 with the intention that they are more likely to be reused shortly", - "Counter": "0,1,2,3", - "EventCode": "0xFE", - "EventName": "IDI_MISC.WB_UPGRADE", - "PublicDescription": "Counts number of cache lines that are allocated and written back to L3 with the intention that they are more likely to be reused shortly.", - "SampleAfterValue": "100003", - "UMask": "0x2" - }, - { "BriefDescription": "MEMORY_DISAMBIGUATION.HISTORY_RESET", "Counter": "0,1,2,3", "EventCode": "0x09", diff --git a/tools/perf/pmu-events/arch/x86/skylakex/skx-metrics.json b/tools/perf/pmu-events/arch/x86/skylakex/skx-metrics.json index 2fe630cd4927..7cc7b076c3e2 100644 --- a/tools/perf/pmu-events/arch/x86/skylakex/skx-metrics.json +++ b/tools/perf/pmu-events/arch/x86/skylakex/skx-metrics.json @@ -295,12 +295,12 @@ "MetricExpr": "LD_BLOCKS_PARTIAL.ADDRESS_ALIAS / tma_info_thread_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group", "MetricName": "tma_4k_aliasing", - "MetricThreshold": "tma_4k_aliasing > 0.2 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", - "PublicDescription": "This metric estimates how often memory load accesses were aliased by preceding stores (in program order) with a 4K address offset. False match is possible; which incur a few cycles load re-issue. However; the short re-issue duration is often hidden by the out-of-order core and HW optimizations; hence a user may safely ignore a high value of this metric unless it manages to propagate up into parent nodes of the hierarchy (e.g. to L1_Bound)", + "MetricThreshold": "tma_4k_aliasing > 0.2 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric estimates how often memory load accesses were aliased by preceding stores (in program order) with a 4K address offset. False match is possible; which incur a few cycles load re-issue. However; the short re-issue duration is often hidden by the out-of-order core and HW optimizations; hence a user may safely ignore a high value of this metric unless it manages to propagate up into parent nodes of the hierarchy (e.g. to L1_Bound).", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution ports for ALU operations", + "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution ports for ALU operations.", "MetricExpr": "(UOPS_DISPATCHED_PORT.PORT_0 + UOPS_DISPATCHED_PORT.PORT_1 + UOPS_DISPATCHED_PORT.PORT_5 + UOPS_DISPATCHED_PORT.PORT_6) / tma_info_thread_slots", "MetricGroup": "TopdownL5;tma_L5_group;tma_ports_utilized_3m_group", "MetricName": "tma_alu_op_utilization", @@ -312,7 +312,7 @@ "MetricExpr": "34 * (FP_ASSIST.ANY + OTHER_ASSISTS.ANY) / tma_info_thread_slots", "MetricGroup": "BvIO;TopdownL4;tma_L4_group;tma_microcode_sequencer_group", "MetricName": "tma_assists", - "MetricThreshold": "tma_assists > 0.1 & tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1", + "MetricThreshold": "tma_assists > 0.1 & (tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1)", "PublicDescription": "This metric estimates fraction of slots the CPU retired uops delivered by the Microcode_Sequencer as a result of Assists. Assists are long sequences of uops that are required in certain corner-cases for operations that cannot be handled natively by the execution pipeline. For example; when working with very small floating point values (so-called Denormals); the FP units are not set up to perform these operations natively. Instead; a sequence of instructions to perform the computation on the Denormals is injected into the pipeline. Since these microcode sequences might be dozens of uops long; Assists can be extremely deleterious to performance and they can be avoided in many cases. Sample with: OTHER_ASSISTS.ANY", "ScaleUnit": "100%" }, @@ -323,7 +323,7 @@ "MetricName": "tma_backend_bound", "MetricThreshold": "tma_backend_bound > 0.2", "MetricgroupNoGroup": "TopdownL1", - "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound", + "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound.", "ScaleUnit": "100%" }, { @@ -333,12 +333,12 @@ "MetricName": "tma_bad_speculation", "MetricThreshold": "tma_bad_speculation > 0.15", "MetricgroupNoGroup": "TopdownL1", - "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example", + "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.", "ScaleUnit": "100%" }, { "BriefDescription": "Total pipeline cost of instruction fetch related bottlenecks by large code footprint programs (i-side cache; TLB and BTB misses)", - "MetricExpr": "100 * tma_fetch_latency * (tma_itlb_misses + tma_icache_misses + tma_unknown_branches) / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches)", + "MetricExpr": "100 * tma_fetch_latency * (tma_itlb_misses + tma_icache_misses + tma_unknown_branches) / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches)", "MetricGroup": "BigFootprint;BvBC;Fed;Frontend;IcMiss;MemoryTLB", "MetricName": "tma_bottleneck_big_code", "MetricThreshold": "tma_bottleneck_big_code > 20" @@ -353,7 +353,7 @@ }, { "BriefDescription": "Total pipeline cost of external Memory- or Cache-Bandwidth related bottlenecks", - "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_mem_bandwidth / (tma_mem_bandwidth + tma_mem_latency)) + tma_memory_bound * (tma_l3_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_sq_full / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_memory_bound * (tma_l1_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_fb_full / (tma_dtlb_load + tma_store_fwd_blk + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_4k_aliasing + tma_fb_full)))", + "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_mem_bandwidth / (tma_mem_bandwidth + tma_mem_latency)) + tma_memory_bound * (tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_sq_full / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_fb_full / (tma_4k_aliasing + tma_dtlb_load + tma_fb_full + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)))", "MetricGroup": "BvMB;Mem;MemoryBW;Offcore;tma_issueBW", "MetricName": "tma_bottleneck_cache_memory_bandwidth", "MetricThreshold": "tma_bottleneck_cache_memory_bandwidth > 20", @@ -361,7 +361,7 @@ }, { "BriefDescription": "Total pipeline cost of external Memory- or Cache-Latency related bottlenecks", - "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_mem_latency / (tma_mem_bandwidth + tma_mem_latency)) + tma_memory_bound * (tma_l3_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_l3_hit_latency / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_memory_bound * tma_l2_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound) + tma_memory_bound * (tma_l1_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_l1_latency_dependency / (tma_dtlb_load + tma_store_fwd_blk + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_4k_aliasing + tma_fb_full)) + tma_memory_bound * (tma_l1_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_lock_latency / (tma_dtlb_load + tma_store_fwd_blk + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_4k_aliasing + tma_fb_full)) + tma_memory_bound * (tma_l1_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_split_loads / (tma_dtlb_load + tma_store_fwd_blk + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_4k_aliasing + tma_fb_full)) + tma_memory_bound * (tma_store_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_split_stores / (tma_store_latency + tma_false_sharing + tma_split_stores + tma_dtlb_store)) + tma_memory_bound * (tma_store_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_store_latency / (tma_store_latency + tma_false_sharing + tma_split_stores + tma_dtlb_store)))", + "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_mem_latency / (tma_mem_bandwidth + tma_mem_latency)) + tma_memory_bound * (tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_l3_hit_latency / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_memory_bound * tma_l2_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) + tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_l1_latency_dependency / (tma_4k_aliasing + tma_dtlb_load + tma_fb_full + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_lock_latency / (tma_4k_aliasing + tma_dtlb_load + tma_fb_full + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_split_loads / (tma_4k_aliasing + tma_dtlb_load + tma_fb_full + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_memory_bound * (tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_split_stores / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency)) + tma_memory_bound * (tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_store_latency / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency)))", "MetricGroup": "BvML;Mem;MemoryLat;Offcore;tma_issueLat", "MetricName": "tma_bottleneck_cache_memory_latency", "MetricThreshold": "tma_bottleneck_cache_memory_latency > 20", @@ -369,22 +369,22 @@ }, { "BriefDescription": "Total pipeline cost when the execution is compute-bound - an estimation", - "MetricExpr": "100 * (tma_core_bound * tma_divider / (tma_divider + tma_serializing_operation + tma_ports_utilization) + tma_core_bound * (tma_ports_utilization / (tma_divider + tma_serializing_operation + tma_ports_utilization)) * (tma_ports_utilized_3m / (tma_ports_utilized_0 + tma_ports_utilized_1 + tma_ports_utilized_2 + tma_ports_utilized_3m)))", + "MetricExpr": "100 * (tma_core_bound * tma_divider / (tma_divider + tma_ports_utilization + tma_serializing_operation) + tma_core_bound * (tma_ports_utilization / (tma_divider + tma_ports_utilization + tma_serializing_operation)) * (tma_ports_utilized_3m / (tma_ports_utilized_0 + tma_ports_utilized_1 + tma_ports_utilized_2 + tma_ports_utilized_3m)))", "MetricGroup": "BvCB;Cor;tma_issueComp", "MetricName": "tma_bottleneck_compute_bound_est", "MetricThreshold": "tma_bottleneck_compute_bound_est > 20", - "PublicDescription": "Total pipeline cost when the execution is compute-bound - an estimation. Covers Core Bound when High ILP as well as when long-latency execution units are busy" + "PublicDescription": "Total pipeline cost when the execution is compute-bound - an estimation. Covers Core Bound when High ILP as well as when long-latency execution units are busy. Related metrics: " }, { "BriefDescription": "Total pipeline cost of instruction fetch bandwidth related bottlenecks (when the front-end could not sustain operations delivery to the back-end)", - "MetricExpr": "100 * (tma_frontend_bound - (1 - 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts) * tma_fetch_latency * tma_mispredicts_resteers / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches) - tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * tma_fetch_latency * (tma_ms_switches + tma_branch_resteers * (tma_clears_resteers + tma_mispredicts_resteers * (10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts)) / (tma_mispredicts_resteers + tma_clears_resteers + tma_unknown_branches)) / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches)) - tma_bottleneck_big_code", + "MetricExpr": "100 * (tma_frontend_bound - (1 - 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts) * tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) - tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * tma_fetch_latency * (tma_ms_switches + tma_branch_resteers * (tma_clears_resteers + tma_mispredicts_resteers * (10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts)) / (tma_clears_resteers + tma_mispredicts_resteers + tma_unknown_branches)) / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches)) - tma_bottleneck_big_code", "MetricGroup": "BvFB;Fed;FetchBW;Frontend", "MetricName": "tma_bottleneck_instruction_fetch_bw", "MetricThreshold": "tma_bottleneck_instruction_fetch_bw > 20" }, { "BriefDescription": "Total pipeline cost of irregular execution (e.g", - "MetricExpr": "100 * (tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * tma_fetch_latency * (tma_ms_switches + tma_branch_resteers * (tma_clears_resteers + tma_mispredicts_resteers * (10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts)) / (tma_mispredicts_resteers + tma_clears_resteers + tma_unknown_branches)) / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches) + 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts * tma_branch_mispredicts + tma_machine_clears * tma_other_nukes / tma_other_nukes + tma_core_bound * (tma_serializing_operation + tma_core_bound * RS_EVENTS.EMPTY_CYCLES / tma_info_thread_clks * tma_ports_utilized_0) / (tma_divider + tma_serializing_operation + tma_ports_utilization) + tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * tma_heavy_operations)", + "MetricExpr": "100 * (tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * tma_fetch_latency * (tma_ms_switches + tma_branch_resteers * (tma_clears_resteers + tma_mispredicts_resteers * (10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts)) / (tma_clears_resteers + tma_mispredicts_resteers + tma_unknown_branches)) / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) + 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts * tma_branch_mispredicts + tma_machine_clears * tma_other_nukes / tma_other_nukes + tma_core_bound * (tma_serializing_operation + tma_core_bound * RS_EVENTS.EMPTY_CYCLES / tma_info_thread_clks * tma_ports_utilized_0) / (tma_divider + tma_ports_utilization + tma_serializing_operation) + tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * tma_heavy_operations)", "MetricGroup": "Bad;BvIO;Cor;Ret;tma_issueMS", "MetricName": "tma_bottleneck_irregular_overhead", "MetricThreshold": "tma_bottleneck_irregular_overhead > 10", @@ -392,7 +392,7 @@ }, { "BriefDescription": "Total pipeline cost of Memory Address Translation related bottlenecks (data-side TLBs)", - "MetricExpr": "100 * (tma_memory_bound * (tma_l1_bound / max(tma_memory_bound, tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_dtlb_load / max(tma_l1_bound, tma_dtlb_load + tma_store_fwd_blk + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_4k_aliasing + tma_fb_full)) + tma_memory_bound * (tma_store_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_dtlb_store / (tma_store_latency + tma_false_sharing + tma_split_stores + tma_dtlb_store)))", + "MetricExpr": "100 * (tma_memory_bound * (tma_l1_bound / max(tma_memory_bound, tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_dtlb_load / max(tma_l1_bound, tma_4k_aliasing + tma_dtlb_load + tma_fb_full + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_memory_bound * (tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_dtlb_store / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency)))", "MetricGroup": "BvMT;Mem;MemoryTLB;Offcore;tma_issueTLB", "MetricName": "tma_bottleneck_memory_data_tlbs", "MetricThreshold": "tma_bottleneck_memory_data_tlbs > 20", @@ -400,7 +400,7 @@ }, { "BriefDescription": "Total pipeline cost of Memory Synchronization related bottlenecks (data transfers and coherency updates across processors)", - "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound) * (tma_mem_latency / (tma_mem_bandwidth + tma_mem_latency)) * tma_remote_cache / (tma_local_mem + tma_remote_mem + tma_remote_cache) + tma_l3_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound) * (tma_contested_accesses + tma_data_sharing) / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full) + tma_store_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound) * tma_false_sharing / (tma_store_latency + tma_false_sharing + tma_split_stores + tma_dtlb_store - tma_store_latency)) + tma_machine_clears * (1 - tma_other_nukes / tma_other_nukes))", + "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_mem_latency / (tma_mem_bandwidth + tma_mem_latency)) * tma_remote_cache / (tma_local_mem + tma_remote_cache + tma_remote_mem) + tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_contested_accesses + tma_data_sharing) / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full) + tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * tma_false_sharing / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency - tma_store_latency)) + tma_machine_clears * (1 - tma_other_nukes / tma_other_nukes))", "MetricGroup": "BvMS;LockCont;Mem;Offcore;tma_issueSyncxn", "MetricName": "tma_bottleneck_memory_synchronization", "MetricThreshold": "tma_bottleneck_memory_synchronization > 10", @@ -408,7 +408,7 @@ }, { "BriefDescription": "Total pipeline cost of Branch Misprediction related bottlenecks", - "MetricExpr": "100 * (1 - 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts) * (tma_branch_mispredicts + tma_fetch_latency * tma_mispredicts_resteers / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches))", + "MetricExpr": "100 * (1 - 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts) * (tma_branch_mispredicts + tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches))", "MetricGroup": "Bad;BadSpec;BrMispredicts;BvMP;tma_issueBM", "MetricName": "tma_bottleneck_mispredictions", "MetricThreshold": "tma_bottleneck_mispredictions > 20", @@ -420,10 +420,10 @@ "MetricGroup": "BvOB;Cor;Offcore", "MetricName": "tma_bottleneck_other_bottlenecks", "MetricThreshold": "tma_bottleneck_other_bottlenecks > 20", - "PublicDescription": "Total pipeline cost of remaining bottlenecks in the back-end. Examples include data-dependencies (Core Bound when Low ILP) and other unlisted memory-related stalls" + "PublicDescription": "Total pipeline cost of remaining bottlenecks in the back-end. Examples include data-dependencies (Core Bound when Low ILP) and other unlisted memory-related stalls." }, { - "BriefDescription": "Total pipeline cost of \"useful operations\" - the portion of Retiring category not covered by Branching_Overhead nor Irregular_Overhead", + "BriefDescription": "Total pipeline cost of \"useful operations\" - the portion of Retiring category not covered by Branching_Overhead nor Irregular_Overhead.", "MetricExpr": "100 * (tma_retiring - (BR_INST_RETIRED.ALL_BRANCHES + 2 * BR_INST_RETIRED.NEAR_CALL + INST_RETIRED.NOP) / tma_info_thread_slots - tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * tma_heavy_operations)", "MetricGroup": "BvUW;Ret", "MetricName": "tma_bottleneck_useful_work", @@ -445,8 +445,8 @@ "MetricExpr": "INT_MISC.CLEAR_RESTEER_CYCLES / tma_info_thread_clks + tma_unknown_branches", "MetricGroup": "FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group", "MetricName": "tma_branch_resteers", - "MetricThreshold": "tma_branch_resteers > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", - "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers. Branch Resteers estimates the Frontend delay in fetching operations from corrected path; following all sorts of miss-predicted branches. For example; branchy code with lots of miss-predictions might get categorized under Branch Resteers. Note the value of this node may overlap with its siblings. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_l3_hit_latency, tma_store_latency", + "MetricThreshold": "tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers. Branch Resteers estimates the Frontend delay in fetching operations from corrected path; following all sorts of miss-predicted branches. For example; branchy code with lots of miss-predictions might get categorized under Branch Resteers. Note the value of this node may overlap with its siblings. Sample with: BR_MISP_RETIRED.ALL_BRANCHES", "ScaleUnit": "100%" }, { @@ -454,8 +454,8 @@ "MetricExpr": "max(0, tma_microcode_sequencer - tma_assists)", "MetricGroup": "TopdownL4;tma_L4_group;tma_microcode_sequencer_group", "MetricName": "tma_cisc", - "MetricThreshold": "tma_cisc > 0.1 & tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1", - "PublicDescription": "This metric estimates fraction of cycles the CPU retired uops originated from CISC (complex instruction set computer) instruction. A CISC instruction has multiple uops that are required to perform the instruction's functionality as in the case of read-modify-write as an example. Since these instructions require multiple uops they may or may not imply sub-optimal use of machine resources", + "MetricThreshold": "tma_cisc > 0.1 & (tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1)", + "PublicDescription": "This metric estimates fraction of cycles the CPU retired uops originated from CISC (complex instruction set computer) instruction. A CISC instruction has multiple uops that are required to perform the instruction's functionality as in the case of read-modify-write as an example. Since these instructions require multiple uops they may or may not imply sub-optimal use of machine resources.", "ScaleUnit": "100%" }, { @@ -463,7 +463,7 @@ "MetricExpr": "(1 - BR_MISP_RETIRED.ALL_BRANCHES / (BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT)) * INT_MISC.CLEAR_RESTEER_CYCLES / tma_info_thread_clks", "MetricGroup": "BadSpec;MachineClears;TopdownL4;tma_L4_group;tma_branch_resteers_group;tma_issueMC", "MetricName": "tma_clears_resteers", - "MetricThreshold": "tma_clears_resteers > 0.05 & tma_branch_resteers > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricThreshold": "tma_clears_resteers > 0.05 & (tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))", "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Machine Clears. Sample with: INT_MISC.CLEAR_RESTEER_CYCLES. Related metrics: tma_l1_bound, tma_machine_clears, tma_microcode_sequencer, tma_ms_switches", "ScaleUnit": "100%" }, @@ -472,7 +472,7 @@ "MetricExpr": "max(0, tma_itlb_misses - tma_code_stlb_miss)", "MetricGroup": "FetchLat;MemoryTLB;TopdownL4;tma_L4_group;tma_itlb_misses_group", "MetricName": "tma_code_stlb_hit", - "MetricThreshold": "tma_code_stlb_hit > 0.05 & tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricThreshold": "tma_code_stlb_hit > 0.05 & (tma_itlb_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))", "ScaleUnit": "100%" }, { @@ -480,33 +480,33 @@ "MetricExpr": "ITLB_MISSES.WALK_ACTIVE / tma_info_thread_clks", "MetricGroup": "FetchLat;MemoryTLB;TopdownL4;tma_L4_group;tma_itlb_misses_group", "MetricName": "tma_code_stlb_miss", - "MetricThreshold": "tma_code_stlb_miss > 0.05 & tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricThreshold": "tma_code_stlb_miss > 0.05 & (tma_itlb_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 2 or 4 MB pages for (instruction) code accesses", + "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 2 or 4 MB pages for (instruction) code accesses.", "MetricExpr": "tma_code_stlb_miss * ITLB_MISSES.WALK_COMPLETED_2M_4M / (ITLB_MISSES.WALK_COMPLETED_4K + ITLB_MISSES.WALK_COMPLETED_2M_4M)", "MetricGroup": "FetchLat;MemoryTLB;TopdownL5;tma_L5_group;tma_code_stlb_miss_group", "MetricName": "tma_code_stlb_miss_2m", - "MetricThreshold": "tma_code_stlb_miss_2m > 0.05 & tma_code_stlb_miss > 0.05 & tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricThreshold": "tma_code_stlb_miss_2m > 0.05 & (tma_code_stlb_miss > 0.05 & (tma_itlb_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)))", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 4 KB pages for (instruction) code accesses", + "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 4 KB pages for (instruction) code accesses.", "MetricExpr": "tma_code_stlb_miss * ITLB_MISSES.WALK_COMPLETED_4K / (ITLB_MISSES.WALK_COMPLETED_4K + ITLB_MISSES.WALK_COMPLETED_2M_4M)", "MetricGroup": "FetchLat;MemoryTLB;TopdownL5;tma_L5_group;tma_code_stlb_miss_group", "MetricName": "tma_code_stlb_miss_4k", - "MetricThreshold": "tma_code_stlb_miss_4k > 0.05 & tma_code_stlb_miss > 0.05 & tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricThreshold": "tma_code_stlb_miss_4k > 0.05 & (tma_code_stlb_miss > 0.05 & (tma_itlb_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)))", "ScaleUnit": "100%" }, { "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses", "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "((47.5 * tma_info_system_core_frequency - 3.5 * tma_info_system_core_frequency) * (MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM * (OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.HITM_OTHER_CORE / (OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.HITM_OTHER_CORE + OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD))) + (47.5 * tma_info_system_core_frequency - 3.5 * tma_info_system_core_frequency) * MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks", + "MetricExpr": "(44 * tma_info_system_core_frequency * (MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM * (OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.HITM_OTHER_CORE / (OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.HITM_OTHER_CORE + OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD))) + 44 * tma_info_system_core_frequency * MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks", "MetricGroup": "BvMS;DataSharing;LockCont;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group", "MetricName": "tma_contested_accesses", - "MetricThreshold": "tma_contested_accesses > 0.05 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", - "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses. Contested accesses occur when data written by one Logical Processor are read by another Logical Processor on a different Physical Core. Examples of contested accesses include synchronizations such as locks; true data sharing such as modified locked variables; and false sharing. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM, MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS. Related metrics: tma_bottleneck_memory_synchronization, tma_data_sharing, tma_false_sharing, tma_machine_clears, tma_remote_cache", + "MetricThreshold": "tma_contested_accesses > 0.05 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses. Contested accesses occur when data written by one Logical Processor are read by another Logical Processor on a different Physical Core. Examples of contested accesses include synchronizations such as locks; true data sharing such as modified locked variables; and false sharing. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM_PS;MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS_PS. Related metrics: tma_bottleneck_memory_synchronization, tma_data_sharing, tma_false_sharing, tma_machine_clears, tma_remote_cache", "ScaleUnit": "100%" }, { @@ -517,25 +517,25 @@ "MetricName": "tma_core_bound", "MetricThreshold": "tma_core_bound > 0.1 & tma_backend_bound > 0.2", "MetricgroupNoGroup": "TopdownL2", - "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck. Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations)", + "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck. Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations).", "ScaleUnit": "100%" }, { "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses", "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "(47.5 * tma_info_system_core_frequency - 3.5 * tma_info_system_core_frequency) * (MEM_LOAD_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM * (1 - OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.HITM_OTHER_CORE / (OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.HITM_OTHER_CORE + OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD))) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks", + "MetricExpr": "44 * tma_info_system_core_frequency * (MEM_LOAD_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM * (1 - OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.HITM_OTHER_CORE / (OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.HITM_OTHER_CORE + OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD))) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks", "MetricGroup": "BvMS;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group", "MetricName": "tma_data_sharing", - "MetricThreshold": "tma_data_sharing > 0.05 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", - "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses. Data shared by multiple Logical Processors (even just read shared) may cause increased access latency due to cache coherency. Excessive data sharing can drastically harm multithreaded performance. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_HIT. Related metrics: tma_bottleneck_memory_synchronization, tma_contested_accesses, tma_false_sharing, tma_machine_clears, tma_remote_cache", + "MetricThreshold": "tma_data_sharing > 0.05 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses. Data shared by multiple Logical Processors (even just read shared) may cause increased access latency due to cache coherency. Excessive data sharing can drastically harm multithreaded performance. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_HIT_PS. Related metrics: tma_bottleneck_memory_synchronization, tma_contested_accesses, tma_false_sharing, tma_machine_clears, tma_remote_cache", "ScaleUnit": "100%" }, { "BriefDescription": "This metric represents fraction of cycles where decoder-0 was the only active decoder", - "MetricExpr": "(cpu@INST_DECODED.DECODERS\\,cmask\\=0x1@ - cpu@INST_DECODED.DECODERS\\,cmask\\=0x2@) / tma_info_core_core_clks / 2", + "MetricExpr": "(cpu@INST_DECODED.DECODERS\\,cmask\\=1@ - cpu@INST_DECODED.DECODERS\\,cmask\\=2@) / tma_info_core_core_clks / 2", "MetricGroup": "DSBmiss;FetchBW;TopdownL4;tma_L4_group;tma_issueD0;tma_mite_group", "MetricName": "tma_decoder0_alone", - "MetricThreshold": "tma_decoder0_alone > 0.1 & tma_mite > 0.1 & tma_fetch_bandwidth > 0.2", + "MetricThreshold": "tma_decoder0_alone > 0.1 & (tma_mite > 0.1 & tma_fetch_bandwidth > 0.2)", "PublicDescription": "This metric represents fraction of cycles where decoder-0 was the only active decoder. Related metrics: tma_few_uops_instructions", "ScaleUnit": "100%" }, @@ -544,7 +544,7 @@ "MetricExpr": "ARITH.DIVIDER_ACTIVE / tma_info_thread_clks", "MetricGroup": "BvCB;TopdownL3;tma_L3_group;tma_core_bound_group", "MetricName": "tma_divider", - "MetricThreshold": "tma_divider > 0.2 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_divider > 0.2 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)", "PublicDescription": "This metric represents fraction of cycles where the Divider unit was active. Divide and square root instructions are performed by the Divider unit and can take considerably longer latency than integer or Floating Point addition; subtraction; or multiplication. Sample with: ARITH.DIVIDER_ACTIVE", "ScaleUnit": "100%" }, @@ -554,7 +554,7 @@ "MetricExpr": "CYCLE_ACTIVITY.STALLS_L3_MISS / tma_info_thread_clks + (CYCLE_ACTIVITY.STALLS_L1D_MISS - CYCLE_ACTIVITY.STALLS_L2_MISS) / tma_info_thread_clks - tma_l2_bound", "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_dram_bound", - "MetricThreshold": "tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", "PublicDescription": "This metric estimates how often the CPU was stalled on accesses to external memory (DRAM) by loads. Better caching can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L3_MISS", "ScaleUnit": "100%" }, @@ -564,7 +564,7 @@ "MetricGroup": "DSB;FetchBW;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group", "MetricName": "tma_dsb", "MetricThreshold": "tma_dsb > 0.15 & tma_fetch_bandwidth > 0.2", - "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to DSB (decoded uop cache) fetch pipeline. For example; inefficient utilization of the DSB cache structure or bank conflict when reading from it; are categorized here", + "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to DSB (decoded uop cache) fetch pipeline. For example; inefficient utilization of the DSB cache structure or bank conflict when reading from it; are categorized here.", "ScaleUnit": "100%" }, { @@ -572,27 +572,27 @@ "MetricExpr": "DSB2MITE_SWITCHES.PENALTY_CYCLES / tma_info_thread_clks", "MetricGroup": "DSBmiss;FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueFB", "MetricName": "tma_dsb_switches", - "MetricThreshold": "tma_dsb_switches > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", - "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines. The DSB (decoded i-cache) is a Uop Cache where the front-end directly delivers Uops (micro operations) avoiding heavy x86 decoding. The DSB pipeline has shorter latency and delivered higher bandwidth than the MITE (legacy instruction decode pipeline). Switching between the two pipelines can cause penalties hence this metric measures the exposed penalty. Sample with: FRONTEND_RETIRED.DSB_MISS. Related metrics: tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp", + "MetricThreshold": "tma_dsb_switches > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines. The DSB (decoded i-cache) is a Uop Cache where the front-end directly delivers Uops (micro operations) avoiding heavy x86 decoding. The DSB pipeline has shorter latency and delivered higher bandwidth than the MITE (legacy instruction decode pipeline). Switching between the two pipelines can cause penalties hence this metric measures the exposed penalty. Sample with: FRONTEND_RETIRED.DSB_MISS_PS. Related metrics: tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp", "ScaleUnit": "100%" }, { "BriefDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses", "MetricConstraint": "NO_GROUP_EVENTS_NMI", - "MetricExpr": "min(9 * cpu@DTLB_LOAD_MISSES.STLB_HIT\\,cmask\\=0x1@ + DTLB_LOAD_MISSES.WALK_ACTIVE, max(CYCLE_ACTIVITY.CYCLES_MEM_ANY - CYCLE_ACTIVITY.CYCLES_L1D_MISS, 0)) / tma_info_thread_clks", + "MetricExpr": "min(9 * cpu@DTLB_LOAD_MISSES.STLB_HIT\\,cmask\\=1@ + DTLB_LOAD_MISSES.WALK_ACTIVE, max(CYCLE_ACTIVITY.CYCLES_MEM_ANY - CYCLE_ACTIVITY.CYCLES_L1D_MISS, 0)) / tma_info_thread_clks", "MetricGroup": "BvMT;MemoryTLB;TopdownL4;tma_L4_group;tma_issueTLB;tma_l1_bound_group", "MetricName": "tma_dtlb_load", - "MetricThreshold": "tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", - "PublicDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses. TLBs (Translation Look-aside Buffers) are processor caches for recently used entries out of the Page Tables that are used to map virtual- to physical-addresses by the operating system. This metric approximates the potential delay of demand loads missing the first-level data TLB (assuming worst case scenario with back to back misses to different pages). This includes hitting in the second-level TLB (STLB) as well as performing a hardware page walk on an STLB miss. Sample with: MEM_INST_RETIRED.STLB_MISS_LOADS. Related metrics: tma_bottleneck_memory_data_tlbs, tma_dtlb_store", + "MetricThreshold": "tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses. TLBs (Translation Look-aside Buffers) are processor caches for recently used entries out of the Page Tables that are used to map virtual- to physical-addresses by the operating system. This metric approximates the potential delay of demand loads missing the first-level data TLB (assuming worst case scenario with back to back misses to different pages). This includes hitting in the second-level TLB (STLB) as well as performing a hardware page walk on an STLB miss. Sample with: MEM_INST_RETIRED.STLB_MISS_LOADS_PS. Related metrics: tma_bottleneck_memory_data_tlbs, tma_dtlb_store", "ScaleUnit": "100%" }, { "BriefDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses", - "MetricExpr": "(9 * cpu@DTLB_STORE_MISSES.STLB_HIT\\,cmask\\=0x1@ + DTLB_STORE_MISSES.WALK_ACTIVE) / tma_info_core_core_clks", + "MetricExpr": "(9 * cpu@DTLB_STORE_MISSES.STLB_HIT\\,cmask\\=1@ + DTLB_STORE_MISSES.WALK_ACTIVE) / tma_info_core_core_clks", "MetricGroup": "BvMT;MemoryTLB;TopdownL4;tma_L4_group;tma_issueTLB;tma_store_bound_group", "MetricName": "tma_dtlb_store", - "MetricThreshold": "tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", - "PublicDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses. As with ordinary data caching; focus on improving data locality and reducing working-set size to reduce DTLB overhead. Additionally; consider using profile-guided optimization (PGO) to collocate frequently-used data on the same page. Try using larger page sizes for large amounts of frequently-used data. Sample with: MEM_INST_RETIRED.STLB_MISS_STORES. Related metrics: tma_bottleneck_memory_data_tlbs, tma_dtlb_load", + "MetricThreshold": "tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses. As with ordinary data caching; focus on improving data locality and reducing working-set size to reduce DTLB overhead. Additionally; consider using profile-guided optimization (PGO) to collocate frequently-used data on the same page. Try using larger page sizes for large amounts of frequently-used data. Sample with: MEM_INST_RETIRED.STLB_MISS_STORES_PS. Related metrics: tma_bottleneck_memory_data_tlbs, tma_dtlb_load", "ScaleUnit": "100%" }, { @@ -601,18 +601,18 @@ "MetricExpr": "(110 * tma_info_system_core_frequency * (OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS.REMOTE_HITM + OFFCORE_RESPONSE.PF_L2_RFO.L3_MISS.REMOTE_HITM) + 47.5 * tma_info_system_core_frequency * (OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.HITM_OTHER_CORE + OFFCORE_RESPONSE.PF_L2_RFO.L3_HIT.HITM_OTHER_CORE)) / tma_info_thread_clks", "MetricGroup": "BvMS;DataSharing;LockCont;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_store_bound_group", "MetricName": "tma_false_sharing", - "MetricThreshold": "tma_false_sharing > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", - "PublicDescription": "This metric roughly estimates how often CPU was handling synchronizations due to False Sharing. False Sharing is a multithreading hiccup; where multiple Logical Processors contend on different data-elements mapped into the same cache line. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM, OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.HITM_OTHER_CORE. Related metrics: tma_bottleneck_memory_synchronization, tma_contested_accesses, tma_data_sharing, tma_machine_clears, tma_remote_cache", + "MetricThreshold": "tma_false_sharing > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric roughly estimates how often CPU was handling synchronizations due to False Sharing. False Sharing is a multithreading hiccup; where multiple Logical Processors contend on different data-elements mapped into the same cache line. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM_PS;OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.SNOOP_HITM. Related metrics: tma_bottleneck_memory_synchronization, tma_contested_accesses, tma_data_sharing, tma_machine_clears, tma_remote_cache", "ScaleUnit": "100%" }, { "BriefDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed", "MetricConstraint": "NO_GROUP_EVENTS_NMI", - "MetricExpr": "tma_info_memory_load_miss_real_latency * cpu@L1D_PEND_MISS.FB_FULL\\,cmask\\=0x1@ / tma_info_thread_clks", + "MetricExpr": "tma_info_memory_load_miss_real_latency * cpu@L1D_PEND_MISS.FB_FULL\\,cmask\\=1@ / tma_info_thread_clks", "MetricGroup": "BvMB;MemoryBW;TopdownL4;tma_L4_group;tma_issueBW;tma_issueSL;tma_issueSmSt;tma_l1_bound_group", "MetricName": "tma_fb_full", "MetricThreshold": "tma_fb_full > 0.3", - "PublicDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed. The higher the metric value; the deeper the memory hierarchy level the misses are satisfied from (metric values >1 are valid). Often it hints on approaching bandwidth limits (to L2 cache; L3 cache or external memory). Related metrics: tma_bottleneck_cache_memory_bandwidth, tma_info_system_dram_bw_use, tma_mem_bandwidth, tma_sq_full, tma_store_latency", + "PublicDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed. The higher the metric value; the deeper the memory hierarchy level the misses are satisfied from (metric values >1 are valid). Often it hints on approaching bandwidth limits (to L2 cache; L3 cache or external memory). Related metrics: tma_bottleneck_cache_memory_bandwidth, tma_info_system_dram_bw_use, tma_mem_bandwidth, tma_sq_full, tma_store_latency, tma_streaming_stores", "ScaleUnit": "100%" }, { @@ -622,7 +622,7 @@ "MetricName": "tma_fetch_bandwidth", "MetricThreshold": "tma_fetch_bandwidth > 0.2", "MetricgroupNoGroup": "TopdownL2", - "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues. For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Sample with: FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1, FRONTEND_RETIRED.LATENCY_GE_1, FRONTEND_RETIRED.LATENCY_GE_2. Related metrics: tma_dsb_switches, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp", + "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues. For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Sample with: FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1;FRONTEND_RETIRED.LATENCY_GE_1;FRONTEND_RETIRED.LATENCY_GE_2. Related metrics: tma_dsb_switches, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp", "ScaleUnit": "100%" }, { @@ -632,7 +632,7 @@ "MetricName": "tma_fetch_latency", "MetricThreshold": "tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", "MetricgroupNoGroup": "TopdownL2", - "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues. For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: FRONTEND_RETIRED.LATENCY_GE_16, FRONTEND_RETIRED.LATENCY_GE_8", + "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues. For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: FRONTEND_RETIRED.LATENCY_GE_16_PS;FRONTEND_RETIRED.LATENCY_GE_8_PS", "ScaleUnit": "100%" }, { @@ -652,7 +652,7 @@ "MetricGroup": "HPC;TopdownL3;tma_L3_group;tma_light_operations_group", "MetricName": "tma_fp_arith", "MetricThreshold": "tma_fp_arith > 0.2 & tma_light_operations > 0.6", - "PublicDescription": "This metric represents overall arithmetic floating-point (FP) operations fraction the CPU has executed (retired). Note this metric's value may exceed its parent due to use of \"Uops\" CountDomain and FMA double-counting", + "PublicDescription": "This metric represents overall arithmetic floating-point (FP) operations fraction the CPU has executed (retired). Note this metric's value may exceed its parent due to use of \"Uops\" CountDomain and FMA double-counting.", "ScaleUnit": "100%" }, { @@ -661,7 +661,7 @@ "MetricGroup": "HPC;TopdownL5;tma_L5_group;tma_assists_group", "MetricName": "tma_fp_assists", "MetricThreshold": "tma_fp_assists > 0.1", - "PublicDescription": "This metric roughly estimates fraction of slots the CPU retired uops as a result of handing Floating Point (FP) Assists. FP Assist may apply when working with very small floating point values (so-called Denormals)", + "PublicDescription": "This metric roughly estimates fraction of slots the CPU retired uops as a result of handing Floating Point (FP) Assists. FP Assist may apply when working with very small floating point values (so-called Denormals).", "ScaleUnit": "100%" }, { @@ -669,17 +669,17 @@ "MetricExpr": "FP_ARITH_INST_RETIRED.SCALAR / UOPS_RETIRED.RETIRE_SLOTS", "MetricGroup": "Compute;Flops;TopdownL4;tma_L4_group;tma_fp_arith_group;tma_issue2P", "MetricName": "tma_fp_scalar", - "MetricThreshold": "tma_fp_scalar > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6", + "MetricThreshold": "tma_fp_scalar > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6)", "PublicDescription": "This metric approximates arithmetic floating-point (FP) scalar uops fraction the CPU has retired. May overcount due to FMA double counting. Related metrics: tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%" }, { "BriefDescription": "This metric approximates arithmetic floating-point (FP) vector uops fraction the CPU has retired aggregated across all vector widths", "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "cpu@FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE\\,umask\\=0xFC@ / UOPS_RETIRED.RETIRE_SLOTS", + "MetricExpr": "cpu@FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE\\,umask\\=0xfc@ / UOPS_RETIRED.RETIRE_SLOTS", "MetricGroup": "Compute;Flops;TopdownL4;tma_L4_group;tma_fp_arith_group;tma_issue2P", "MetricName": "tma_fp_vector", - "MetricThreshold": "tma_fp_vector > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6", + "MetricThreshold": "tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6)", "PublicDescription": "This metric approximates arithmetic floating-point (FP) vector uops fraction the CPU has retired aggregated across all vector widths. May overcount due to FMA double counting. Related metrics: tma_fp_scalar, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%" }, @@ -688,7 +688,7 @@ "MetricExpr": "(FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE) / UOPS_RETIRED.RETIRE_SLOTS", "MetricGroup": "Compute;Flops;TopdownL5;tma_L5_group;tma_fp_vector_group;tma_issue2P", "MetricName": "tma_fp_vector_128b", - "MetricThreshold": "tma_fp_vector_128b > 0.1 & tma_fp_vector > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6", + "MetricThreshold": "tma_fp_vector_128b > 0.1 & (tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6))", "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 128-bit wide vectors. May overcount due to FMA double counting prior to LNL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%" }, @@ -697,7 +697,7 @@ "MetricExpr": "(FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE) / UOPS_RETIRED.RETIRE_SLOTS", "MetricGroup": "Compute;Flops;TopdownL5;tma_L5_group;tma_fp_vector_group;tma_issue2P", "MetricName": "tma_fp_vector_256b", - "MetricThreshold": "tma_fp_vector_256b > 0.1 & tma_fp_vector > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6", + "MetricThreshold": "tma_fp_vector_256b > 0.1 & (tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6))", "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 256-bit wide vectors. May overcount due to FMA double counting prior to LNL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%" }, @@ -706,7 +706,7 @@ "MetricExpr": "(FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE) / UOPS_RETIRED.RETIRE_SLOTS", "MetricGroup": "Compute;Flops;TopdownL5;tma_L5_group;tma_fp_vector_group;tma_issue2P", "MetricName": "tma_fp_vector_512b", - "MetricThreshold": "tma_fp_vector_512b > 0.1 & tma_fp_vector > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6", + "MetricThreshold": "tma_fp_vector_512b > 0.1 & (tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6))", "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 512-bit wide vectors. May overcount due to FMA double counting. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%" }, @@ -717,35 +717,35 @@ "MetricName": "tma_frontend_bound", "MetricThreshold": "tma_frontend_bound > 0.15", "MetricgroupNoGroup": "TopdownL1", - "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound. Sample with: FRONTEND_RETIRED.LATENCY_GE_4", + "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound. Sample with: FRONTEND_RETIRED.LATENCY_GE_4_PS", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of slots where the CPU was retiring fused instructions , where one uop can represent multiple contiguous instructions", + "BriefDescription": "This metric represents fraction of slots where the CPU was retiring fused instructions -- where one uop can represent multiple contiguous instructions", "MetricExpr": "tma_light_operations * UOPS_RETIRED.MACRO_FUSED / UOPS_RETIRED.RETIRE_SLOTS", "MetricGroup": "Branches;BvBO;Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group", "MetricName": "tma_fused_instructions", "MetricThreshold": "tma_fused_instructions > 0.1 & tma_light_operations > 0.6", - "PublicDescription": "This metric represents fraction of slots where the CPU was retiring fused instructions , where one uop can represent multiple contiguous instructions. CMP+JCC or DEC+JCC are common examples of legacy fusions. {([MTL] Note new MOV+OP and Load+OP fusions appear under Other_Light_Ops in MTL!)}", + "PublicDescription": "This metric represents fraction of slots where the CPU was retiring fused instructions -- where one uop can represent multiple contiguous instructions. CMP+JCC or DEC+JCC are common examples of legacy fusions. {([MTL] Note new MOV+OP and Load+OP fusions appear under Other_Light_Ops in MTL!)}", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations , instructions that require two or more uops or micro-coded sequences", + "BriefDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences", "MetricExpr": "(UOPS_RETIRED.RETIRE_SLOTS + UOPS_RETIRED.MACRO_FUSED - INST_RETIRED.ANY) / tma_info_thread_slots", "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_heavy_operations", "MetricThreshold": "tma_heavy_operations > 0.1", "MetricgroupNoGroup": "TopdownL2", - "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations , instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences.([ICL+] Note this may overcount due to approximation using indirect events; [ADL+])", + "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences.([ICL+] Note this may overcount due to approximation using indirect events; [ADL+])", "ScaleUnit": "100%" }, { "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to instruction cache misses", - "MetricExpr": "(ICACHE_16B.IFDATA_STALL + 2 * cpu@ICACHE_16B.IFDATA_STALL\\,cmask\\=0x1\\,edge\\=0x1@) / tma_info_thread_clks", + "MetricExpr": "(ICACHE_16B.IFDATA_STALL + 2 * cpu@ICACHE_16B.IFDATA_STALL\\,cmask\\=1\\,edge@) / tma_info_thread_clks", "MetricGroup": "BigFootprint;BvBC;FetchLat;IcMiss;TopdownL3;tma_L3_group;tma_fetch_latency_group", "MetricName": "tma_icache_misses", - "MetricThreshold": "tma_icache_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", - "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to instruction cache misses. Sample with: FRONTEND_RETIRED.L2_MISS, FRONTEND_RETIRED.L1I_MISS", + "MetricThreshold": "tma_icache_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to instruction cache misses. Sample with: FRONTEND_RETIRED.L2_MISS_PS;FRONTEND_RETIRED.L1I_MISS_PS", "ScaleUnit": "100%" }, { @@ -756,11 +756,11 @@ "PublicDescription": "Branch Misprediction Cost: Cycles representing fraction of TMA slots wasted per non-speculative branch misprediction (retired JEClear). Related metrics: tma_bottleneck_mispredictions, tma_branch_mispredicts, tma_mispredicts_resteers" }, { - "BriefDescription": "Instructions per retired Mispredicts for indirect CALL or JMP branches (lower number means higher occurrence rate)", + "BriefDescription": "Instructions per retired Mispredicts for indirect CALL or JMP branches (lower number means higher occurrence rate).", "MetricExpr": "tma_info_inst_mix_instructions / (UOPS_RETIRED.RETIRE_SLOTS / UOPS_ISSUED.ANY * BR_MISP_EXEC.INDIRECT)", "MetricGroup": "Bad;BrMispredicts", "MetricName": "tma_info_bad_spec_ipmisp_indirect", - "MetricThreshold": "tma_info_bad_spec_ipmisp_indirect < 1000" + "MetricThreshold": "tma_info_bad_spec_ipmisp_indirect < 1e3" }, { "BriefDescription": "Number of Instructions per non-speculative Branch Misprediction (JEClear) (lower number means higher occurrence rate)", @@ -785,7 +785,7 @@ }, { "BriefDescription": "Total pipeline cost of DSB (uop cache) hits - subset of the Instruction_Fetch_BW Bottleneck", - "MetricExpr": "100 * (tma_frontend_bound * (tma_fetch_bandwidth / (tma_fetch_latency + tma_fetch_bandwidth)) * (tma_dsb / (tma_mite + tma_dsb)))", + "MetricExpr": "100 * (tma_frontend_bound * (tma_fetch_bandwidth / (tma_fetch_bandwidth + tma_fetch_latency)) * (tma_dsb / (tma_dsb + tma_mite)))", "MetricGroup": "DSB;Fed;FetchBW;tma_issueFB", "MetricName": "tma_info_botlnk_l2_dsb_bandwidth", "MetricThreshold": "tma_info_botlnk_l2_dsb_bandwidth > 10", @@ -794,7 +794,7 @@ { "BriefDescription": "Total pipeline cost of DSB (uop cache) misses - subset of the Instruction_Fetch_BW Bottleneck", "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "100 * (tma_fetch_latency * tma_dsb_switches / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches) + tma_fetch_bandwidth * tma_mite / (tma_mite + tma_dsb))", + "MetricExpr": "100 * (tma_fetch_latency * tma_dsb_switches / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) + tma_fetch_bandwidth * tma_mite / (tma_dsb + tma_mite))", "MetricGroup": "DSBmiss;Fed;tma_issueFB", "MetricName": "tma_info_botlnk_l2_dsb_misses", "MetricThreshold": "tma_info_botlnk_l2_dsb_misses > 10", @@ -802,10 +802,11 @@ }, { "BriefDescription": "Total pipeline cost of Instruction Cache misses - subset of the Big_Code Bottleneck", - "MetricExpr": "100 * (tma_fetch_latency * tma_icache_misses / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches))", + "MetricExpr": "100 * (tma_fetch_latency * tma_icache_misses / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches))", "MetricGroup": "Fed;FetchLat;IcMiss;tma_issueFL", "MetricName": "tma_info_botlnk_l2_ic_misses", - "MetricThreshold": "tma_info_botlnk_l2_ic_misses > 5" + "MetricThreshold": "tma_info_botlnk_l2_ic_misses > 5", + "PublicDescription": "Total pipeline cost of Instruction Cache misses - subset of the Big_Code Bottleneck. Related metrics: " }, { "BriefDescription": "Fraction of branches that are CALL or RET", @@ -834,7 +835,7 @@ }, { "BriefDescription": "Core actual clocks when any Logical Processor is active on the Physical Core", - "MetricExpr": "(CPU_CLK_UNHALTED.THREAD_ANY / 2 if #SMT_on else tma_info_thread_clks)", + "MetricExpr": "(CPU_CLK_UNHALTED.THREAD / 2 * (1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK) if #core_wide < 1 else (CPU_CLK_UNHALTED.THREAD_ANY / 2 if #SMT_on else tma_info_thread_clks))", "MetricGroup": "SMT", "MetricName": "tma_info_core_core_clks" }, @@ -859,14 +860,14 @@ }, { "BriefDescription": "Actual per-core usage of the Floating Point non-X87 execution units (regardless of precision or vector-width)", - "MetricExpr": "(FP_ARITH_INST_RETIRED.SCALAR + cpu@FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE\\,umask\\=0xFC@) / (2 * tma_info_core_core_clks)", + "MetricExpr": "(FP_ARITH_INST_RETIRED.SCALAR + cpu@FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE\\,umask\\=0xfc@) / (2 * tma_info_core_core_clks)", "MetricGroup": "Cor;Flops;HPC", "MetricName": "tma_info_core_fp_arith_utilization", - "PublicDescription": "Actual per-core usage of the Floating Point non-X87 execution units (regardless of precision or vector-width). Values > 1 are possible due to ([BDW+] Fused-Multiply Add (FMA) counting - common; [ADL+] use all of ADD/MUL/FMA in Scalar or 128/256-bit vectors - less common)" + "PublicDescription": "Actual per-core usage of the Floating Point non-X87 execution units (regardless of precision or vector-width). Values > 1 are possible due to ([BDW+] Fused-Multiply Add (FMA) counting - common; [ADL+] use all of ADD/MUL/FMA in Scalar or 128/256-bit vectors - less common)." }, { "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is execution) per thread (logical-processor)", - "MetricExpr": "UOPS_EXECUTED.THREAD / cpu@UOPS_EXECUTED.THREAD\\,cmask\\=0x1@", + "MetricExpr": "UOPS_EXECUTED.THREAD / cpu@UOPS_EXECUTED.THREAD\\,cmask\\=1@", "MetricGroup": "Backend;Cor;Pipeline;PortsUtil", "MetricName": "tma_info_core_ilp" }, @@ -879,20 +880,20 @@ "PublicDescription": "Fraction of Uops delivered by the DSB (aka Decoded ICache; or Uop Cache). Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_inst_mix_iptb, tma_lcp" }, { - "BriefDescription": "Average number of cycles of a switch from the DSB fetch-unit to MITE fetch unit - see DSB_Switches tree node for details", + "BriefDescription": "Average number of cycles of a switch from the DSB fetch-unit to MITE fetch unit - see DSB_Switches tree node for details.", "MetricExpr": "DSB2MITE_SWITCHES.PENALTY_CYCLES / DSB2MITE_SWITCHES.COUNT", "MetricGroup": "DSBmiss", "MetricName": "tma_info_frontend_dsb_switch_cost" }, { "BriefDescription": "Average number of Uops issued by front-end when it issued something", - "MetricExpr": "UOPS_ISSUED.ANY / cpu@UOPS_ISSUED.ANY\\,cmask\\=0x1@", + "MetricExpr": "UOPS_ISSUED.ANY / cpu@UOPS_ISSUED.ANY\\,cmask\\=1@", "MetricGroup": "Fed;FetchBW", "MetricName": "tma_info_frontend_fetch_upc" }, { "BriefDescription": "Average Latency for L1 instruction cache misses", - "MetricExpr": "ICACHE_16B.IFDATA_STALL / cpu@ICACHE_16B.IFDATA_STALL\\,cmask\\=0x1\\,edge\\=0x1@ + 2", + "MetricExpr": "ICACHE_16B.IFDATA_STALL / cpu@ICACHE_16B.IFDATA_STALL\\,cmask\\=1\\,edge@ + 2", "MetricGroup": "Fed;FetchLat;IcMiss", "MetricName": "tma_info_frontend_icache_miss_latency" }, @@ -928,7 +929,7 @@ "MetricName": "tma_info_frontend_tbpc" }, { - "BriefDescription": "Branch instructions per taken branch", + "BriefDescription": "Branch instructions per taken branch.", "MetricExpr": "BR_INST_RETIRED.ALL_BRANCHES / BR_INST_RETIRED.NEAR_TAKEN", "MetricGroup": "Branches;Fed;PGO", "MetricName": "tma_info_inst_mix_bptkbranch" @@ -943,11 +944,11 @@ { "BriefDescription": "Instructions per FP Arithmetic instruction (lower number means higher occurrence rate)", "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "INST_RETIRED.ANY / (FP_ARITH_INST_RETIRED.SCALAR + cpu@FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE\\,umask\\=0xFC@)", + "MetricExpr": "INST_RETIRED.ANY / (FP_ARITH_INST_RETIRED.SCALAR + cpu@FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE\\,umask\\=0xfc@)", "MetricGroup": "Flops;InsType", "MetricName": "tma_info_inst_mix_iparith", "MetricThreshold": "tma_info_inst_mix_iparith < 10", - "PublicDescription": "Instructions per FP Arithmetic instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting. Approximated prior to BDW" + "PublicDescription": "Instructions per FP Arithmetic instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting. Approximated prior to BDW." }, { "BriefDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number means higher occurrence rate)", @@ -955,7 +956,7 @@ "MetricGroup": "Flops;FpVector;InsType", "MetricName": "tma_info_inst_mix_iparith_avx128", "MetricThreshold": "tma_info_inst_mix_iparith_avx128 < 10", - "PublicDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting" + "PublicDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting." }, { "BriefDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means higher occurrence rate)", @@ -963,7 +964,7 @@ "MetricGroup": "Flops;FpVector;InsType", "MetricName": "tma_info_inst_mix_iparith_avx256", "MetricThreshold": "tma_info_inst_mix_iparith_avx256 < 10", - "PublicDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting" + "PublicDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting." }, { "BriefDescription": "Instructions per FP Arithmetic AVX 512-bit instruction (lower number means higher occurrence rate)", @@ -971,7 +972,7 @@ "MetricGroup": "Flops;FpVector;InsType", "MetricName": "tma_info_inst_mix_iparith_avx512", "MetricThreshold": "tma_info_inst_mix_iparith_avx512 < 10", - "PublicDescription": "Instructions per FP Arithmetic AVX 512-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting" + "PublicDescription": "Instructions per FP Arithmetic AVX 512-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting." }, { "BriefDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction (lower number means higher occurrence rate)", @@ -979,7 +980,7 @@ "MetricGroup": "Flops;FpScalar;InsType", "MetricName": "tma_info_inst_mix_iparith_scalar_dp", "MetricThreshold": "tma_info_inst_mix_iparith_scalar_dp < 10", - "PublicDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting" + "PublicDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting." }, { "BriefDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction (lower number means higher occurrence rate)", @@ -987,7 +988,7 @@ "MetricGroup": "Flops;FpScalar;InsType", "MetricName": "tma_info_inst_mix_iparith_scalar_sp", "MetricThreshold": "tma_info_inst_mix_iparith_scalar_sp < 10", - "PublicDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting" + "PublicDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting." }, { "BriefDescription": "Instructions per Branch (lower number means higher occurrence rate)", @@ -1037,7 +1038,7 @@ "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_TAKEN", "MetricGroup": "Branches;Fed;FetchBW;Frontend;PGO;tma_issueFB", "MetricName": "tma_info_inst_mix_iptb", - "MetricThreshold": "tma_info_inst_mix_iptb < 4 * 2 + 1", + "MetricThreshold": "tma_info_inst_mix_iptb < 9", "PublicDescription": "Instructions per taken branch. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_lcp" }, { @@ -1224,8 +1225,8 @@ "MetricName": "tma_info_memory_tlb_store_stlb_mpki" }, { - "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is execution) per core", - "MetricExpr": "UOPS_EXECUTED.THREAD / (UOPS_EXECUTED.CORE_CYCLES_GE_1 / 2 if #SMT_on else cpu@UOPS_EXECUTED.THREAD\\,cmask\\=0x1@)", + "BriefDescription": "", + "MetricExpr": "UOPS_EXECUTED.THREAD / (UOPS_EXECUTED.CORE_CYCLES_GE_1 / 2 if #SMT_on else cpu@UOPS_EXECUTED.THREAD\\,cmask\\=1@)", "MetricGroup": "Cor;Pipeline;PortsUtil;SMT", "MetricName": "tma_info_pipeline_execute" }, @@ -1246,12 +1247,12 @@ "MetricExpr": "INST_RETIRED.ANY / (FP_ASSIST.ANY + OTHER_ASSISTS.ANY)", "MetricGroup": "MicroSeq;Pipeline;Ret;Retire", "MetricName": "tma_info_pipeline_ipassist", - "MetricThreshold": "tma_info_pipeline_ipassist < 100000", + "MetricThreshold": "tma_info_pipeline_ipassist < 100e3", "PublicDescription": "Instructions per a microcode Assist invocation. See Assists tree node for details (lower number means higher occurrence rate)" }, { - "BriefDescription": "Average number of Uops retired in cycles where at least one uop has retired", - "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / cpu@UOPS_RETIRED.RETIRE_SLOTS\\,cmask\\=0x1@", + "BriefDescription": "Average number of Uops retired in cycles where at least one uop has retired.", + "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / cpu@UOPS_RETIRED.RETIRE_SLOTS\\,cmask\\=1@", "MetricGroup": "Pipeline;Ret", "MetricName": "tma_info_pipeline_retire" }, @@ -1307,14 +1308,13 @@ "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.FAR_BRANCH:u", "MetricGroup": "Branches;OS", "MetricName": "tma_info_system_ipfarbranch", - "MetricThreshold": "tma_info_system_ipfarbranch < 1000000" + "MetricThreshold": "tma_info_system_ipfarbranch < 1e6" }, { "BriefDescription": "Cycles Per Instruction for the Operating System (OS) Kernel mode", "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P:k / INST_RETIRED.ANY_P:k", "MetricGroup": "OS", - "MetricName": "tma_info_system_kernel_cpi", - "ScaleUnit": "1per_instr" + "MetricName": "tma_info_system_kernel_cpi" }, { "BriefDescription": "Fraction of cycles spent in the Operating System (OS) Kernel mode", @@ -1332,7 +1332,7 @@ }, { "BriefDescription": "Average number of parallel data read requests to external memory", - "MetricExpr": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD / cha@UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD\\,thresh\\=0x1@", + "MetricExpr": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD / UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD@thresh\\=1@", "MetricGroup": "Mem;MemoryBW;SoC", "MetricName": "tma_info_system_mem_parallel_reads", "PublicDescription": "Average number of parallel data read requests to external memory. Accounts for demand loads and L1/L2 prefetches" @@ -1362,7 +1362,7 @@ "MetricExpr": "(CORE_POWER.LVL0_TURBO_LICENSE / 2 / tma_info_core_core_clks if #SMT_on else CORE_POWER.LVL0_TURBO_LICENSE / tma_info_core_core_clks)", "MetricGroup": "Power", "MetricName": "tma_info_system_power_license0_utilization", - "PublicDescription": "Fraction of Core cycles where the core was running with power-delivery for baseline license level 0. This includes non-AVX codes, SSE, AVX 128-bit, and low-current AVX 256-bit codes" + "PublicDescription": "Fraction of Core cycles where the core was running with power-delivery for baseline license level 0. This includes non-AVX codes, SSE, AVX 128-bit, and low-current AVX 256-bit codes." }, { "BriefDescription": "Fraction of Core cycles where the core was running with power-delivery for license level 1", @@ -1370,7 +1370,7 @@ "MetricGroup": "Power", "MetricName": "tma_info_system_power_license1_utilization", "MetricThreshold": "tma_info_system_power_license1_utilization > 0.5", - "PublicDescription": "Fraction of Core cycles where the core was running with power-delivery for license level 1. This includes high current AVX 256-bit instructions as well as low current AVX 512-bit instructions" + "PublicDescription": "Fraction of Core cycles where the core was running with power-delivery for license level 1. This includes high current AVX 256-bit instructions as well as low current AVX 512-bit instructions." }, { "BriefDescription": "Fraction of Core cycles where the core was running with power-delivery for license level 2 (introduced in SKX)", @@ -1378,7 +1378,7 @@ "MetricGroup": "Power", "MetricName": "tma_info_system_power_license2_utilization", "MetricThreshold": "tma_info_system_power_license2_utilization > 0.5", - "PublicDescription": "Fraction of Core cycles where the core was running with power-delivery for license level 2 (introduced in SKX). This includes high current AVX 512-bit instructions" + "PublicDescription": "Fraction of Core cycles where the core was running with power-delivery for license level 2 (introduced in SKX). This includes high current AVX 512-bit instructions." }, { "BriefDescription": "Fraction of cycles where both hardware Logical Processors were active", @@ -1412,7 +1412,7 @@ "MetricName": "tma_info_system_uncore_frequency" }, { - "BriefDescription": "Per-Logical Processor actual clocks when the Logical Processor is active", + "BriefDescription": "Per-Logical Processor actual clocks when the Logical Processor is active.", "MetricExpr": "CPU_CLK_UNHALTED.THREAD", "MetricGroup": "Pipeline", "MetricName": "tma_info_thread_clks" @@ -1421,15 +1421,14 @@ "BriefDescription": "Cycles Per Instruction (per Logical Processor)", "MetricExpr": "1 / tma_info_thread_ipc", "MetricGroup": "Mem;Pipeline", - "MetricName": "tma_info_thread_cpi", - "ScaleUnit": "1per_instr" + "MetricName": "tma_info_thread_cpi" }, { "BriefDescription": "The ratio of Executed- by Issued-Uops", "MetricExpr": "UOPS_EXECUTED.THREAD / UOPS_ISSUED.ANY", "MetricGroup": "Cor;Pipeline", "MetricName": "tma_info_thread_execute_per_issue", - "PublicDescription": "The ratio of Executed- by Issued-Uops. Ratio > 1 suggests high rate of uop micro-fusions. Ratio < 1 suggest high rate of \"execute\" at rename stage" + "PublicDescription": "The ratio of Executed- by Issued-Uops. Ratio > 1 suggests high rate of uop micro-fusions. Ratio < 1 suggest high rate of \"execute\" at rename stage." }, { "BriefDescription": "Instructions Per Cycle (per Logical Processor)", @@ -1455,15 +1454,15 @@ "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / BR_INST_RETIRED.NEAR_TAKEN", "MetricGroup": "Branches;Fed;FetchBW", "MetricName": "tma_info_thread_uptb", - "MetricThreshold": "tma_info_thread_uptb < 4 * 1.5" + "MetricThreshold": "tma_info_thread_uptb < 6" }, { "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to Instruction TLB (ITLB) misses", "MetricExpr": "ICACHE_TAG.STALLS / tma_info_thread_clks", "MetricGroup": "BigFootprint;BvBC;FetchLat;MemoryTLB;TopdownL3;tma_L3_group;tma_fetch_latency_group", "MetricName": "tma_itlb_misses", - "MetricThreshold": "tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", - "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Instruction TLB (ITLB) misses. Sample with: FRONTEND_RETIRED.STLB_MISS, FRONTEND_RETIRED.ITLB_MISS", + "MetricThreshold": "tma_itlb_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Instruction TLB (ITLB) misses. Sample with: FRONTEND_RETIRED.STLB_MISS_PS;FRONTEND_RETIRED.ITLB_MISS_PS", "ScaleUnit": "100%" }, { @@ -1471,7 +1470,7 @@ "MetricExpr": "max((CYCLE_ACTIVITY.STALLS_MEM_ANY - CYCLE_ACTIVITY.STALLS_L1D_MISS) / tma_info_thread_clks, 0)", "MetricGroup": "CacheHits;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_issueL1;tma_issueMC;tma_memory_bound_group", "MetricName": "tma_l1_bound", - "MetricThreshold": "tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", "PublicDescription": "This metric estimates how often the CPU was stalled without loads missing the L1 Data (L1D) cache. The L1D cache typically has the shortest latency. However; in certain cases like loads blocked on older stores; a load might suffer due to high latency even though it is being satisfied by the L1D. Another example is loads who miss in the TLB. These cases are characterized by execution unit stalls; while some non-completed demand load lives in the machine without having that demand load missing the L1 cache. Sample with: MEM_LOAD_RETIRED.L1_HIT. Related metrics: tma_clears_resteers, tma_machine_clears, tma_microcode_sequencer, tma_ms_switches, tma_ports_utilized_1", "ScaleUnit": "100%" }, @@ -1480,17 +1479,17 @@ "MetricExpr": "min(2 * (MEM_INST_RETIRED.ALL_LOADS - MEM_LOAD_RETIRED.FB_HIT - MEM_LOAD_RETIRED.L1_MISS) * 20 / 100, max(CYCLE_ACTIVITY.CYCLES_MEM_ANY - CYCLE_ACTIVITY.CYCLES_L1D_MISS, 0)) / tma_info_thread_clks", "MetricGroup": "BvML;MemoryLat;TopdownL4;tma_L4_group;tma_l1_bound_group", "MetricName": "tma_l1_latency_dependency", - "MetricThreshold": "tma_l1_latency_dependency > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_l1_latency_dependency > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", "PublicDescription": "This metric([SKL+] roughly; [LNL]) estimates fraction of cycles with demand load accesses that hit the L1D cache. The short latency of the L1D cache may be exposed in pointer-chasing memory access patterns as an example. Sample with: MEM_LOAD_RETIRED.L1_HIT", "ScaleUnit": "100%" }, { "BriefDescription": "This metric estimates how often the CPU was stalled due to L2 cache accesses by loads", "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "MEM_LOAD_RETIRED.L2_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) / (MEM_LOAD_RETIRED.L2_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) + cpu@L1D_PEND_MISS.FB_FULL\\,cmask\\=0x1@) * ((CYCLE_ACTIVITY.STALLS_L1D_MISS - CYCLE_ACTIVITY.STALLS_L2_MISS) / tma_info_thread_clks)", + "MetricExpr": "MEM_LOAD_RETIRED.L2_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) / (MEM_LOAD_RETIRED.L2_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) + cpu@L1D_PEND_MISS.FB_FULL\\,cmask\\=1@) * ((CYCLE_ACTIVITY.STALLS_L1D_MISS - CYCLE_ACTIVITY.STALLS_L2_MISS) / tma_info_thread_clks)", "MetricGroup": "BvML;CacheHits;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_l2_bound", - "MetricThreshold": "tma_l2_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_l2_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", "PublicDescription": "This metric estimates how often the CPU was stalled due to L2 cache accesses by loads. Avoiding cache misses (i.e. L1 misses/L2 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L2_HIT", "ScaleUnit": "100%" }, @@ -1499,7 +1498,7 @@ "MetricExpr": "3.5 * tma_info_system_core_frequency * MEM_LOAD_RETIRED.L2_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks", "MetricGroup": "MemoryLat;TopdownL4;tma_L4_group;tma_l2_bound_group", "MetricName": "tma_l2_hit_latency", - "MetricThreshold": "tma_l2_hit_latency > 0.05 & tma_l2_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_l2_hit_latency > 0.05 & (tma_l2_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", "PublicDescription": "This metric represents fraction of cycles with demand load accesses that hit the L2 cache under unloaded scenarios (possibly L2 latency limited). Avoiding L1 cache misses (i.e. L1 misses/L2 hits) will improve the latency. Sample with: MEM_LOAD_RETIRED.L2_HIT", "ScaleUnit": "100%" }, @@ -1508,17 +1507,17 @@ "MetricExpr": "(CYCLE_ACTIVITY.STALLS_L2_MISS - CYCLE_ACTIVITY.STALLS_L3_MISS) / tma_info_thread_clks", "MetricGroup": "CacheHits;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_l3_bound", - "MetricThreshold": "tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", - "PublicDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core. Avoiding cache misses (i.e. L2 misses/L3 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L3_HIT", + "MetricThreshold": "tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", + "PublicDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core. Avoiding cache misses (i.e. L2 misses/L3 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L3_HIT_PS", "ScaleUnit": "100%" }, { "BriefDescription": "This metric estimates fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited)", - "MetricExpr": "(20.5 * tma_info_system_core_frequency - 3.5 * tma_info_system_core_frequency) * (MEM_LOAD_RETIRED.L3_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2)) / tma_info_thread_clks", + "MetricExpr": "17 * tma_info_system_core_frequency * (MEM_LOAD_RETIRED.L3_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2)) / tma_info_thread_clks", "MetricGroup": "BvML;MemoryLat;TopdownL4;tma_L4_group;tma_issueLat;tma_l3_bound_group", "MetricName": "tma_l3_hit_latency", - "MetricThreshold": "tma_l3_hit_latency > 0.1 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", - "PublicDescription": "This metric estimates fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited). Avoiding private cache misses (i.e. L2 misses/L3 hits) will improve the latency; reduce contention with sibling physical cores and increase performance. Note the value of this node may overlap with its siblings. Sample with: MEM_LOAD_RETIRED.L3_HIT. Related metrics: tma_bottleneck_cache_memory_latency, tma_branch_resteers, tma_mem_latency, tma_store_latency", + "MetricThreshold": "tma_l3_hit_latency > 0.1 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric estimates fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited). Avoiding private cache misses (i.e. L2 misses/L3 hits) will improve the latency; reduce contention with sibling physical cores and increase performance. Note the value of this node may overlap with its siblings. Sample with: MEM_LOAD_RETIRED.L3_HIT_PS. Related metrics: tma_bottleneck_cache_memory_latency, tma_mem_latency", "ScaleUnit": "100%" }, { @@ -1526,18 +1525,18 @@ "MetricExpr": "DECODE.LCP / tma_info_thread_clks", "MetricGroup": "FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueFB", "MetricName": "tma_lcp", - "MetricThreshold": "tma_lcp > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", - "PublicDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs). Using proper compiler flags or Intel Compiler by default will certainly avoid this. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb", + "MetricThreshold": "tma_lcp > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", + "PublicDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs). Using proper compiler flags or Intel Compiler by default will certainly avoid this. #Link: Optimization Guide about LCP BKMs. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations , instructions that require no more than one uop (micro-operation)", + "BriefDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation)", "MetricExpr": "tma_retiring - tma_heavy_operations", "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_light_operations", "MetricThreshold": "tma_light_operations > 0.6", "MetricgroupNoGroup": "TopdownL2", - "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations , instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized code running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. ([ICL+] Note this may undercount due to approximation using indirect events; [ADL+] .). Sample with: INST_RETIRED.PREC_DIST", + "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized code running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. ([ICL+] Note this may undercount due to approximation using indirect events; [ADL+] .). Sample with: INST_RETIRED.PREC_DIST", "ScaleUnit": "100%" }, { @@ -1555,7 +1554,7 @@ "MetricExpr": "tma_dtlb_load - tma_load_stlb_miss", "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_load_group", "MetricName": "tma_load_stlb_hit", - "MetricThreshold": "tma_load_stlb_hit > 0.05 & tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_load_stlb_hit > 0.05 & (tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))", "ScaleUnit": "100%" }, { @@ -1563,39 +1562,39 @@ "MetricExpr": "DTLB_LOAD_MISSES.WALK_ACTIVE / tma_info_thread_clks", "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_load_group", "MetricName": "tma_load_stlb_miss", - "MetricThreshold": "tma_load_stlb_miss > 0.05 & tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_load_stlb_miss > 0.05 & (tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 1 GB pages for data load accesses", + "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 1 GB pages for data load accesses.", "MetricExpr": "tma_load_stlb_miss * DTLB_LOAD_MISSES.WALK_COMPLETED_1G / (DTLB_LOAD_MISSES.WALK_COMPLETED_4K + DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M + DTLB_LOAD_MISSES.WALK_COMPLETED_1G)", "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_load_stlb_miss_group", "MetricName": "tma_load_stlb_miss_1g", - "MetricThreshold": "tma_load_stlb_miss_1g > 0.05 & tma_load_stlb_miss > 0.05 & tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_load_stlb_miss_1g > 0.05 & (tma_load_stlb_miss > 0.05 & (tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))))", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 2 or 4 MB pages for data load accesses", + "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 2 or 4 MB pages for data load accesses.", "MetricExpr": "tma_load_stlb_miss * DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M / (DTLB_LOAD_MISSES.WALK_COMPLETED_4K + DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M + DTLB_LOAD_MISSES.WALK_COMPLETED_1G)", "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_load_stlb_miss_group", "MetricName": "tma_load_stlb_miss_2m", - "MetricThreshold": "tma_load_stlb_miss_2m > 0.05 & tma_load_stlb_miss > 0.05 & tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_load_stlb_miss_2m > 0.05 & (tma_load_stlb_miss > 0.05 & (tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))))", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 4 KB pages for data load accesses", + "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 4 KB pages for data load accesses.", "MetricExpr": "tma_load_stlb_miss * DTLB_LOAD_MISSES.WALK_COMPLETED_4K / (DTLB_LOAD_MISSES.WALK_COMPLETED_4K + DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M + DTLB_LOAD_MISSES.WALK_COMPLETED_1G)", "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_load_stlb_miss_group", "MetricName": "tma_load_stlb_miss_4k", - "MetricThreshold": "tma_load_stlb_miss_4k > 0.05 & tma_load_stlb_miss > 0.05 & tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_load_stlb_miss_4k > 0.05 & (tma_load_stlb_miss > 0.05 & (tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))))", "ScaleUnit": "100%" }, { "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from local memory", - "MetricExpr": "(80 * tma_info_system_core_frequency - 20.5 * tma_info_system_core_frequency) * MEM_LOAD_L3_MISS_RETIRED.LOCAL_DRAM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks", + "MetricExpr": "59.5 * tma_info_system_core_frequency * MEM_LOAD_L3_MISS_RETIRED.LOCAL_DRAM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks", "MetricGroup": "Server;TopdownL5;tma_L5_group;tma_mem_latency_group", "MetricName": "tma_local_mem", - "MetricThreshold": "tma_local_mem > 0.1 & tma_mem_latency > 0.1 & tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_local_mem > 0.1 & (tma_mem_latency > 0.1 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))", "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from local memory. Caching will improve the latency and increase performance. Sample with: MEM_LOAD_L3_MISS_RETIRED.LOCAL_DRAM", "ScaleUnit": "100%" }, @@ -1604,7 +1603,7 @@ "MetricExpr": "(12 * max(0, MEM_INST_RETIRED.LOCK_LOADS - L2_RQSTS.ALL_RFO) + MEM_INST_RETIRED.LOCK_LOADS / MEM_INST_RETIRED.ALL_STORES * (11 * L2_RQSTS.RFO_HIT + min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO))) / tma_info_thread_clks", "MetricGroup": "LockCont;Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_l1_bound_group", "MetricName": "tma_lock_latency", - "MetricThreshold": "tma_lock_latency > 0.2 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_lock_latency > 0.2 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", "PublicDescription": "This metric represents fraction of cycles the CPU spent handling cache misses due to lock operations. Due to the microarchitecture handling of locks; they are classified as L1_Bound regardless of what memory source satisfied them. Sample with: MEM_INST_RETIRED.LOCK_LOADS. Related metrics: tma_store_latency", "ScaleUnit": "100%" }, @@ -1621,10 +1620,10 @@ }, { "BriefDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory - DRAM ([SPR-HBM] and/or HBM)", - "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, cpu@OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD\\,cmask\\=0x4@) / tma_info_thread_clks", + "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, cpu@OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD\\,cmask\\=4@) / tma_info_thread_clks", "MetricGroup": "BvMB;MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueBW", "MetricName": "tma_mem_bandwidth", - "MetricThreshold": "tma_mem_bandwidth > 0.2 & tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_mem_bandwidth > 0.2 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", "PublicDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory - DRAM ([SPR-HBM] and/or HBM). The underlying heuristic assumes that a similar off-core traffic is generated by all IA cores. This metric does not aggregate non-data-read requests by this logical processor; requests from other IA Logical Processors/Physical Cores/sockets; or other non-IA devices like GPU; hence the maximum external memory bandwidth limits may or may not be approached when this metric is flagged (see Uncore counters for that). Related metrics: tma_bottleneck_cache_memory_bandwidth, tma_fb_full, tma_info_system_dram_bw_use, tma_sq_full", "ScaleUnit": "100%" }, @@ -1633,7 +1632,7 @@ "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD) / tma_info_thread_clks - tma_mem_bandwidth", "MetricGroup": "BvML;MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueLat", "MetricName": "tma_mem_latency", - "MetricThreshold": "tma_mem_latency > 0.1 & tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_mem_latency > 0.1 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", "PublicDescription": "This metric estimates fraction of cycles where the performance was likely hurt due to latency from external memory - DRAM ([SPR-HBM] and/or HBM). This metric does not aggregate requests from other Logical Processors/Physical Cores/sockets (see Uncore counters for that). Related metrics: tma_bottleneck_cache_memory_latency, tma_l3_hit_latency", "ScaleUnit": "100%" }, @@ -1645,11 +1644,11 @@ "MetricName": "tma_memory_bound", "MetricThreshold": "tma_memory_bound > 0.2 & tma_backend_bound > 0.2", "MetricgroupNoGroup": "TopdownL2", - "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck. Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two)", + "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck. Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two).", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of slots where the CPU was retiring memory operations , uops for memory load or store accesses", + "BriefDescription": "This metric represents fraction of slots where the CPU was retiring memory operations -- uops for memory load or store accesses.", "MetricExpr": "tma_light_operations * MEM_INST_RETIRED.ANY / INST_RETIRED.ANY", "MetricGroup": "Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group", "MetricName": "tma_memory_operations", @@ -1671,7 +1670,7 @@ "MetricExpr": "BR_MISP_RETIRED.ALL_BRANCHES / (BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT) * INT_MISC.CLEAR_RESTEER_CYCLES / tma_info_thread_clks", "MetricGroup": "BadSpec;BrMispredicts;BvMP;TopdownL4;tma_L4_group;tma_branch_resteers_group;tma_issueBM", "MetricName": "tma_mispredicts_resteers", - "MetricThreshold": "tma_mispredicts_resteers > 0.05 & tma_branch_resteers > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricThreshold": "tma_mispredicts_resteers > 0.05 & (tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))", "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Branch Misprediction at execution stage. Sample with: INT_MISC.CLEAR_RESTEER_CYCLES. Related metrics: tma_bottleneck_mispredictions, tma_branch_mispredicts, tma_info_bad_spec_branch_misprediction_cost", "ScaleUnit": "100%" }, @@ -1685,12 +1684,12 @@ "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates penalty in terms of percentage of([SKL+] injected blend uops out of all Uops Issued , the Count Domain; [ADL+] cycles)", + "BriefDescription": "This metric estimates penalty in terms of percentage of([SKL+] injected blend uops out of all Uops Issued -- the Count Domain; [ADL+] cycles)", "MetricExpr": "UOPS_ISSUED.VECTOR_WIDTH_MISMATCH / UOPS_ISSUED.ANY", "MetricGroup": "TopdownL5;tma_L5_group;tma_issueMV;tma_ports_utilized_0_group", "MetricName": "tma_mixing_vectors", "MetricThreshold": "tma_mixing_vectors > 0.05", - "PublicDescription": "This metric estimates penalty in terms of percentage of([SKL+] injected blend uops out of all Uops Issued , the Count Domain; [ADL+] cycles). Usually a Mixing_Vectors over 5% is worth investigating. Read more in Appendix B1 of the Optimizations Guide for this topic. Related metrics: tma_ms_switches", + "PublicDescription": "This metric estimates penalty in terms of percentage of([SKL+] injected blend uops out of all Uops Issued -- the Count Domain; [ADL+] cycles). Usually a Mixing_Vectors over 5% is worth investigating. Read more in Appendix B1 of the Optimizations Guide for this topic. Related metrics: tma_ms_switches", "ScaleUnit": "100%" }, { @@ -1698,7 +1697,7 @@ "MetricExpr": "2 * IDQ.MS_SWITCHES / tma_info_thread_clks", "MetricGroup": "FetchLat;MicroSeq;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueMC;tma_issueMS;tma_issueMV;tma_issueSO", "MetricName": "tma_ms_switches", - "MetricThreshold": "tma_ms_switches > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricThreshold": "tma_ms_switches > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", "PublicDescription": "This metric estimates the fraction of cycles when the CPU was stalled due to switches of uop delivery to the Microcode Sequencer (MS). Commonly used instructions are optimized for delivery by the DSB (decoded i-cache) or MITE (legacy instruction decode) pipelines. Certain operations cannot be handled natively by the execution pipeline; and must be performed by microcode (small programs injected into the execution stream). Switching to the MS too often can negatively impact performance. The MS is designated to deliver long uop flows required by CISC instructions like CPUID; or uncommon conditions like Floating Point Assists when dealing with Denormals. Sample with: IDQ.MS_SWITCHES. Related metrics: tma_bottleneck_irregular_overhead, tma_clears_resteers, tma_l1_bound, tma_machine_clears, tma_microcode_sequencer, tma_mixing_vectors, tma_serializing_operation", "ScaleUnit": "100%" }, @@ -1708,7 +1707,7 @@ "MetricGroup": "Branches;BvBO;Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group", "MetricName": "tma_non_fused_branches", "MetricThreshold": "tma_non_fused_branches > 0.1 & tma_light_operations > 0.6", - "PublicDescription": "This metric represents fraction of slots where the CPU was retiring branch instructions that were not fused. Non-conditional branches like direct JMP or CALL would count here. Can be used to examine fusible conditional jumps that were not fused", + "PublicDescription": "This metric represents fraction of slots where the CPU was retiring branch instructions that were not fused. Non-conditional branches like direct JMP or CALL would count here. Can be used to examine fusible conditional jumps that were not fused.", "ScaleUnit": "100%" }, { @@ -1716,8 +1715,8 @@ "MetricExpr": "tma_light_operations * INST_RETIRED.NOP / UOPS_RETIRED.RETIRE_SLOTS", "MetricGroup": "BvBO;Pipeline;TopdownL4;tma_L4_group;tma_other_light_ops_group", "MetricName": "tma_nop_instructions", - "MetricThreshold": "tma_nop_instructions > 0.1 & tma_other_light_ops > 0.3 & tma_light_operations > 0.6", - "PublicDescription": "This metric represents fraction of slots where the CPU was retiring NOP (no op) instructions. Compilers often use NOPs for certain address alignments - e.g. start address of a function or loop body. Sample with: INST_RETIRED.NOP", + "MetricThreshold": "tma_nop_instructions > 0.1 & (tma_other_light_ops > 0.3 & tma_light_operations > 0.6)", + "PublicDescription": "This metric represents fraction of slots where the CPU was retiring NOP (no op) instructions. Compilers often use NOPs for certain address alignments - e.g. start address of a function or loop body. Sample with: INST_RETIRED.NOP_PS", "ScaleUnit": "100%" }, { @@ -1730,19 +1729,19 @@ "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates fraction of slots the CPU was stalled due to other cases of misprediction (non-retired x86 branches or other types)", + "BriefDescription": "This metric estimates fraction of slots the CPU was stalled due to other cases of misprediction (non-retired x86 branches or other types).", "MetricExpr": "max(tma_branch_mispredicts * (1 - BR_MISP_RETIRED.ALL_BRANCHES / (INT_MISC.CLEARS_COUNT - MACHINE_CLEARS.COUNT)), 0.0001)", "MetricGroup": "BrMispredicts;BvIO;TopdownL3;tma_L3_group;tma_branch_mispredicts_group", "MetricName": "tma_other_mispredicts", - "MetricThreshold": "tma_other_mispredicts > 0.05 & tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", + "MetricThreshold": "tma_other_mispredicts > 0.05 & (tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15)", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of slots the CPU has wasted due to Nukes (Machine Clears) not related to memory ordering", + "BriefDescription": "This metric represents fraction of slots the CPU has wasted due to Nukes (Machine Clears) not related to memory ordering.", "MetricExpr": "max(tma_machine_clears * (1 - MACHINE_CLEARS.MEMORY_ORDERING / MACHINE_CLEARS.COUNT), 0.0001)", "MetricGroup": "BvIO;Machine_Clears;TopdownL3;tma_L3_group;tma_machine_clears_group", "MetricName": "tma_other_nukes", - "MetricThreshold": "tma_other_nukes > 0.05 & tma_machine_clears > 0.1 & tma_bad_speculation > 0.15", + "MetricThreshold": "tma_other_nukes > 0.05 & (tma_machine_clears > 0.1 & tma_bad_speculation > 0.15)", "ScaleUnit": "100%" }, { @@ -1751,7 +1750,7 @@ "MetricGroup": "Compute;TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P", "MetricName": "tma_port_0", "MetricThreshold": "tma_port_0 > 0.6", - "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 0 ([SNB+] ALU; [HSW+] ALU and 2nd branch). Sample with: UOPS_DISPATCHED_PORT.PORT_0. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", + "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 0 ([SNB+] ALU; [HSW+] ALU and 2nd branch). Sample with: UOPS_DISPATCHED.PORT_0. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%" }, { @@ -1760,7 +1759,7 @@ "MetricGroup": "TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P", "MetricName": "tma_port_1", "MetricThreshold": "tma_port_1 > 0.6", - "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 1 (ALU). Sample with: UOPS_DISPATCHED_PORT.PORT_1. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_5, tma_port_6, tma_ports_utilized_2", + "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 1 (ALU). Sample with: UOPS_DISPATCHED.PORT_1. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_5, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%" }, { @@ -1796,7 +1795,7 @@ "MetricGroup": "TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P", "MetricName": "tma_port_5", "MetricThreshold": "tma_port_5 > 0.6", - "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 5 ([SNB+] Branches and ALU; [HSW+] ALU). Sample with: UOPS_DISPATCHED_PORT.PORT_5. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_6, tma_ports_utilized_2", + "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 5 ([SNB+] Branches and ALU; [HSW+] ALU). Sample with: UOPS_DISPATCHED.PORT_5. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%" }, { @@ -1805,7 +1804,7 @@ "MetricGroup": "TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P", "MetricName": "tma_port_6", "MetricThreshold": "tma_port_6 > 0.6", - "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 6 ([HSW+] Primary Branch and simple ALU). Sample with: UOPS_DISPATCHED_PORT.PORT_1. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_ports_utilized_2", + "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 6 ([HSW+] Primary Branch and simple ALU). Sample with: UOPS_DISPATCHED.PORT_1. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_ports_utilized_2", "ScaleUnit": "100%" }, { @@ -1822,8 +1821,8 @@ "MetricExpr": "((tma_ports_utilized_0 * tma_info_thread_clks + (EXE_ACTIVITY.1_PORTS_UTIL + tma_retiring * EXE_ACTIVITY.2_PORTS_UTIL)) / tma_info_thread_clks if ARITH.DIVIDER_ACTIVE < CYCLE_ACTIVITY.STALLS_TOTAL - CYCLE_ACTIVITY.STALLS_MEM_ANY else (EXE_ACTIVITY.1_PORTS_UTIL + tma_retiring * EXE_ACTIVITY.2_PORTS_UTIL) / tma_info_thread_clks)", "MetricGroup": "PortsUtil;TopdownL3;tma_L3_group;tma_core_bound_group", "MetricName": "tma_ports_utilization", - "MetricThreshold": "tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", - "PublicDescription": "This metric estimates fraction of cycles the CPU performance was potentially limited due to Core computation issues (non divider-related). Two distinct categories can be attributed into this metric: (1) heavy data-dependency among contiguous instructions would manifest in this metric - such cases are often referred to as low Instruction Level Parallelism (ILP). (2) Contention on some hardware execution unit other than Divider. For example; when there are too many multiply operations", + "MetricThreshold": "tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)", + "PublicDescription": "This metric estimates fraction of cycles the CPU performance was potentially limited due to Core computation issues (non divider-related). Two distinct categories can be attributed into this metric: (1) heavy data-dependency among contiguous instructions would manifest in this metric - such cases are often referred to as low Instruction Level Parallelism (ILP). (2) Contention on some hardware execution unit other than Divider. For example; when there are too many multiply operations.", "ScaleUnit": "100%" }, { @@ -1831,8 +1830,8 @@ "MetricExpr": "EXE_ACTIVITY.EXE_BOUND_0_PORTS / tma_info_thread_clks", "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group", "MetricName": "tma_ports_utilized_0", - "MetricThreshold": "tma_ports_utilized_0 > 0.2 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", - "PublicDescription": "This metric represents fraction of cycles CPU executed no uops on any execution port (Logical Processor cycles since ICL, Physical Core cycles otherwise). Long-latency instructions like divides may contribute to this metric", + "MetricThreshold": "tma_ports_utilized_0 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric represents fraction of cycles CPU executed no uops on any execution port (Logical Processor cycles since ICL, Physical Core cycles otherwise). Long-latency instructions like divides may contribute to this metric.", "ScaleUnit": "100%" }, { @@ -1840,7 +1839,7 @@ "MetricExpr": "((UOPS_EXECUTED.CORE_CYCLES_GE_1 - UOPS_EXECUTED.CORE_CYCLES_GE_2) / 2 if #SMT_on else EXE_ACTIVITY.1_PORTS_UTIL) / tma_info_core_core_clks", "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_issueL1;tma_ports_utilization_group", "MetricName": "tma_ports_utilized_1", - "MetricThreshold": "tma_ports_utilized_1 > 0.2 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_ports_utilized_1 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", "PublicDescription": "This metric represents fraction of cycles where the CPU executed total of 1 uop per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise). This can be due to heavy data-dependency among software instructions; or over oversubscribing a particular hardware resource. In some other cases with high 1_Port_Utilized and L1_Bound; this metric can point to L1 data-cache latency bottleneck that may not necessarily manifest with complete execution starvation (due to the short L1 latency e.g. walking a linked list) - looking at the assembly can be helpful. Related metrics: tma_l1_bound", "ScaleUnit": "100%" }, @@ -1849,35 +1848,35 @@ "MetricExpr": "((UOPS_EXECUTED.CORE_CYCLES_GE_2 - UOPS_EXECUTED.CORE_CYCLES_GE_3) / 2 if #SMT_on else EXE_ACTIVITY.2_PORTS_UTIL) / tma_info_core_core_clks", "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_issue2P;tma_ports_utilization_group", "MetricName": "tma_ports_utilized_2", - "MetricThreshold": "tma_ports_utilized_2 > 0.15 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_ports_utilized_2 > 0.15 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", "PublicDescription": "This metric represents fraction of cycles CPU executed total of 2 uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise). Loop Vectorization -most compilers feature auto-Vectorization options today- reduces pressure on the execution ports as multiple elements are calculated with same uop. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of cycles CPU executed total of 3 or more uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise)", + "BriefDescription": "This metric represents fraction of cycles CPU executed total of 3 or more uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise).", "MetricExpr": "(UOPS_EXECUTED.CORE_CYCLES_GE_3 / 2 if #SMT_on else UOPS_EXECUTED.CORE_CYCLES_GE_3) / tma_info_core_core_clks", "MetricGroup": "BvCB;PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group", "MetricName": "tma_ports_utilized_3m", - "MetricThreshold": "tma_ports_utilized_3m > 0.4 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_ports_utilized_3m > 0.4 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", "ScaleUnit": "100%" }, { "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from remote cache in other sockets including synchronizations issues", "MetricConstraint": "NO_GROUP_EVENTS_NMI", - "MetricExpr": "((110 * tma_info_system_core_frequency - 20.5 * tma_info_system_core_frequency) * MEM_LOAD_L3_MISS_RETIRED.REMOTE_HITM + (110 * tma_info_system_core_frequency - 20.5 * tma_info_system_core_frequency) * MEM_LOAD_L3_MISS_RETIRED.REMOTE_FWD) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks", + "MetricExpr": "(89.5 * tma_info_system_core_frequency * MEM_LOAD_L3_MISS_RETIRED.REMOTE_HITM + 89.5 * tma_info_system_core_frequency * MEM_LOAD_L3_MISS_RETIRED.REMOTE_FWD) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks", "MetricGroup": "Offcore;Server;Snoop;TopdownL5;tma_L5_group;tma_issueSyncxn;tma_mem_latency_group", "MetricName": "tma_remote_cache", - "MetricThreshold": "tma_remote_cache > 0.05 & tma_mem_latency > 0.1 & tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", - "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from remote cache in other sockets including synchronizations issues. This is caused often due to non-optimal NUMA allocations. Sample with: MEM_LOAD_L3_MISS_RETIRED.REMOTE_HITM, MEM_LOAD_L3_MISS_RETIRED.REMOTE_FWD. Related metrics: tma_bottleneck_memory_synchronization, tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_machine_clears", + "MetricThreshold": "tma_remote_cache > 0.05 & (tma_mem_latency > 0.1 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))", + "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from remote cache in other sockets including synchronizations issues. This is caused often due to non-optimal NUMA allocations. #link to NUMA article. Sample with: MEM_LOAD_L3_MISS_RETIRED.REMOTE_HITM_PS;MEM_LOAD_L3_MISS_RETIRED.REMOTE_FWD_PS. Related metrics: tma_bottleneck_memory_synchronization, tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_machine_clears", "ScaleUnit": "100%" }, { "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from remote memory", - "MetricExpr": "(147.5 * tma_info_system_core_frequency - 20.5 * tma_info_system_core_frequency) * MEM_LOAD_L3_MISS_RETIRED.REMOTE_DRAM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks", + "MetricExpr": "127 * tma_info_system_core_frequency * MEM_LOAD_L3_MISS_RETIRED.REMOTE_DRAM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks", "MetricGroup": "Server;Snoop;TopdownL5;tma_L5_group;tma_mem_latency_group", "MetricName": "tma_remote_mem", - "MetricThreshold": "tma_remote_mem > 0.1 & tma_mem_latency > 0.1 & tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", - "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from remote memory. This is caused often due to non-optimal NUMA allocations. Sample with: MEM_LOAD_L3_MISS_RETIRED.REMOTE_DRAM", + "MetricThreshold": "tma_remote_mem > 0.1 & (tma_mem_latency > 0.1 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))", + "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from remote memory. This is caused often due to non-optimal NUMA allocations. #link to NUMA article. Sample with: MEM_LOAD_L3_MISS_RETIRED.REMOTE_DRAM_PS", "ScaleUnit": "100%" }, { @@ -1895,7 +1894,7 @@ "MetricExpr": "PARTIAL_RAT_STALLS.SCOREBOARD / tma_info_thread_clks", "MetricGroup": "BvIO;PortsUtil;TopdownL3;tma_L3_group;tma_core_bound_group;tma_issueSO", "MetricName": "tma_serializing_operation", - "MetricThreshold": "tma_serializing_operation > 0.1 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_serializing_operation > 0.1 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)", "PublicDescription": "This metric represents fraction of cycles the CPU issue-pipeline was stalled due to serializing operations. Instructions like CPUID; WRMSR or LFENCE serialize the out-of-order execution which may limit performance. Sample with: PARTIAL_RAT_STALLS.SCOREBOARD. Related metrics: tma_ms_switches", "ScaleUnit": "100%" }, @@ -1906,7 +1905,7 @@ "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group", "MetricName": "tma_split_loads", "MetricThreshold": "tma_split_loads > 0.3", - "PublicDescription": "This metric estimates fraction of cycles handling memory load split accesses - load that cross 64-byte cache line boundary. Sample with: MEM_INST_RETIRED.SPLIT_LOADS", + "PublicDescription": "This metric estimates fraction of cycles handling memory load split accesses - load that cross 64-byte cache line boundary. Sample with: MEM_INST_RETIRED.SPLIT_LOADS_PS", "ScaleUnit": "100%" }, { @@ -1914,8 +1913,8 @@ "MetricExpr": "MEM_INST_RETIRED.SPLIT_STORES / tma_info_core_core_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_issueSpSt;tma_store_bound_group", "MetricName": "tma_split_stores", - "MetricThreshold": "tma_split_stores > 0.2 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", - "PublicDescription": "This metric represents rate of split store accesses. Consider aligning your data to the 64-byte cache line granularity. Sample with: MEM_INST_RETIRED.SPLIT_STORES. Related metrics: tma_port_4", + "MetricThreshold": "tma_split_stores > 0.2 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric represents rate of split store accesses. Consider aligning your data to the 64-byte cache line granularity. Sample with: MEM_INST_RETIRED.SPLIT_STORES_PS. Related metrics: tma_port_4", "ScaleUnit": "100%" }, { @@ -1923,7 +1922,7 @@ "MetricExpr": "(OFFCORE_REQUESTS_BUFFER.SQ_FULL / 2 if #SMT_on else OFFCORE_REQUESTS_BUFFER.SQ_FULL) / tma_info_core_core_clks", "MetricGroup": "BvMB;MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_issueBW;tma_l3_bound_group", "MetricName": "tma_sq_full", - "MetricThreshold": "tma_sq_full > 0.3 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_sq_full > 0.3 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", "PublicDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors). Related metrics: tma_bottleneck_cache_memory_bandwidth, tma_fb_full, tma_info_system_dram_bw_use, tma_mem_bandwidth", "ScaleUnit": "100%" }, @@ -1932,8 +1931,8 @@ "MetricExpr": "EXE_ACTIVITY.BOUND_ON_STORES / tma_info_thread_clks", "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_store_bound", - "MetricThreshold": "tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", - "PublicDescription": "This metric estimates how often CPU was stalled due to RFO store memory accesses; RFO store issue a read-for-ownership request before the write. Even though store accesses do not typically stall out-of-order CPUs; there are few cases where stores can lead to actual stalls. This metric will be flagged should RFO stores be a bottleneck. Sample with: MEM_INST_RETIRED.ALL_STORES", + "MetricThreshold": "tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", + "PublicDescription": "This metric estimates how often CPU was stalled due to RFO store memory accesses; RFO store issue a read-for-ownership request before the write. Even though store accesses do not typically stall out-of-order CPUs; there are few cases where stores can lead to actual stalls. This metric will be flagged should RFO stores be a bottleneck. Sample with: MEM_INST_RETIRED.ALL_STORES_PS", "ScaleUnit": "100%" }, { @@ -1941,8 +1940,8 @@ "MetricExpr": "13 * LD_BLOCKS.STORE_FORWARD / tma_info_thread_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group", "MetricName": "tma_store_fwd_blk", - "MetricThreshold": "tma_store_fwd_blk > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", - "PublicDescription": "This metric roughly estimates fraction of cycles when the memory subsystem had loads blocked since they could not forward data from earlier (in program order) overlapping stores. To streamline memory operations in the pipeline; a load can avoid waiting for memory if a prior in-flight store is writing the data that the load wants to read (store forwarding process). However; in some cases the load may be blocked for a significant time pending the store forward. For example; when the prior store is writing a smaller region than the load is reading", + "MetricThreshold": "tma_store_fwd_blk > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric roughly estimates fraction of cycles when the memory subsystem had loads blocked since they could not forward data from earlier (in program order) overlapping stores. To streamline memory operations in the pipeline; a load can avoid waiting for memory if a prior in-flight store is writing the data that the load wants to read (store forwarding process). However; in some cases the load may be blocked for a significant time pending the store forward. For example; when the prior store is writing a smaller region than the load is reading.", "ScaleUnit": "100%" }, { @@ -1951,8 +1950,8 @@ "MetricExpr": "(L2_RQSTS.RFO_HIT * 11 * (1 - MEM_INST_RETIRED.LOCK_LOADS / MEM_INST_RETIRED.ALL_STORES) + (1 - MEM_INST_RETIRED.LOCK_LOADS / MEM_INST_RETIRED.ALL_STORES) * min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO)) / tma_info_thread_clks", "MetricGroup": "BvML;LockCont;MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_issueSL;tma_store_bound_group", "MetricName": "tma_store_latency", - "MetricThreshold": "tma_store_latency > 0.1 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", - "PublicDescription": "This metric estimates fraction of cycles the CPU spent handling L1D store misses. Store accesses usually less impact out-of-order core performance; however; holding resources for longer time can lead into undesired implications (e.g. contention on L1D fill-buffer entries - see FB_Full). Related metrics: tma_branch_resteers, tma_fb_full, tma_l3_hit_latency, tma_lock_latency", + "MetricThreshold": "tma_store_latency > 0.1 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric estimates fraction of cycles the CPU spent handling L1D store misses. Store accesses usually less impact out-of-order core performance; however; holding resources for longer time can lead into undesired implications (e.g. contention on L1D fill-buffer entries - see FB_Full). Related metrics: tma_fb_full, tma_lock_latency", "ScaleUnit": "100%" }, { @@ -1968,7 +1967,7 @@ "MetricExpr": "tma_dtlb_store - tma_store_stlb_miss", "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_store_group", "MetricName": "tma_store_stlb_hit", - "MetricThreshold": "tma_store_stlb_hit > 0.05 & tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_store_stlb_hit > 0.05 & (tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))", "ScaleUnit": "100%" }, { @@ -1976,31 +1975,31 @@ "MetricExpr": "DTLB_STORE_MISSES.WALK_ACTIVE / tma_info_core_core_clks", "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_store_group", "MetricName": "tma_store_stlb_miss", - "MetricThreshold": "tma_store_stlb_miss > 0.05 & tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_store_stlb_miss > 0.05 & (tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 1 GB pages for data store accesses", + "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 1 GB pages for data store accesses.", "MetricExpr": "tma_store_stlb_miss * DTLB_STORE_MISSES.WALK_COMPLETED_1G / (DTLB_STORE_MISSES.WALK_COMPLETED_4K + DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M + DTLB_STORE_MISSES.WALK_COMPLETED_1G)", "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_store_stlb_miss_group", "MetricName": "tma_store_stlb_miss_1g", - "MetricThreshold": "tma_store_stlb_miss_1g > 0.05 & tma_store_stlb_miss > 0.05 & tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_store_stlb_miss_1g > 0.05 & (tma_store_stlb_miss > 0.05 & (tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))))", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 2 or 4 MB pages for data store accesses", + "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 2 or 4 MB pages for data store accesses.", "MetricExpr": "tma_store_stlb_miss * DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M / (DTLB_STORE_MISSES.WALK_COMPLETED_4K + DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M + DTLB_STORE_MISSES.WALK_COMPLETED_1G)", "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_store_stlb_miss_group", "MetricName": "tma_store_stlb_miss_2m", - "MetricThreshold": "tma_store_stlb_miss_2m > 0.05 & tma_store_stlb_miss > 0.05 & tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_store_stlb_miss_2m > 0.05 & (tma_store_stlb_miss > 0.05 & (tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))))", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 4 KB pages for data store accesses", + "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 4 KB pages for data store accesses.", "MetricExpr": "tma_store_stlb_miss * DTLB_STORE_MISSES.WALK_COMPLETED_4K / (DTLB_STORE_MISSES.WALK_COMPLETED_4K + DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M + DTLB_STORE_MISSES.WALK_COMPLETED_1G)", "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_store_stlb_miss_group", "MetricName": "tma_store_stlb_miss_4k", - "MetricThreshold": "tma_store_stlb_miss_4k > 0.05 & tma_store_stlb_miss > 0.05 & tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_store_stlb_miss_4k > 0.05 & (tma_store_stlb_miss > 0.05 & (tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))))", "ScaleUnit": "100%" }, { @@ -2008,7 +2007,7 @@ "MetricExpr": "9 * BACLEARS.ANY / tma_info_thread_clks", "MetricGroup": "BigFootprint;BvBC;FetchLat;TopdownL4;tma_L4_group;tma_branch_resteers_group", "MetricName": "tma_unknown_branches", - "MetricThreshold": "tma_unknown_branches > 0.05 & tma_branch_resteers > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricThreshold": "tma_unknown_branches > 0.05 & (tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))", "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to new branch address clears. These are fetched branches the Branch Prediction Unit was unable to recognize (e.g. first time the branch is fetched or hitting BTB capacity limit) hence called Unknown Branches. Sample with: BACLEARS.ANY", "ScaleUnit": "100%" }, @@ -2017,8 +2016,8 @@ "MetricExpr": "tma_retiring * UOPS_EXECUTED.X87 / UOPS_EXECUTED.THREAD", "MetricGroup": "Compute;TopdownL4;tma_L4_group;tma_fp_arith_group", "MetricName": "tma_x87_use", - "MetricThreshold": "tma_x87_use > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6", - "PublicDescription": "This metric serves as an approximation of legacy x87 usage. It accounts for instructions beyond X87 FP arithmetic operations; hence may be used as a thermometer to avoid X87 high usage and preferably upgrade to modern ISA. See Tip under Tuning Hint", + "MetricThreshold": "tma_x87_use > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6)", + "PublicDescription": "This metric serves as an approximation of legacy x87 usage. It accounts for instructions beyond X87 FP arithmetic operations; hence may be used as a thermometer to avoid X87 high usage and preferably upgrade to modern ISA. See Tip under Tuning Hint.", "ScaleUnit": "100%" }, { diff --git a/tools/perf/pmu-events/arch/x86/snowridgex/cache.json b/tools/perf/pmu-events/arch/x86/snowridgex/cache.json index 7882dca9d5e1..3410caf8a57a 100644 --- a/tools/perf/pmu-events/arch/x86/snowridgex/cache.json +++ b/tools/perf/pmu-events/arch/x86/snowridgex/cache.json @@ -161,6 +161,7 @@ "EventCode": "0xd1", "EventName": "MEM_LOAD_UOPS_RETIRED.DRAM_HIT", "PEBS": "1", + "PublicDescription": "Counts the number of load uops retired that hit in DRAM. Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0x80" }, @@ -171,6 +172,7 @@ "EventCode": "0xd1", "EventName": "MEM_LOAD_UOPS_RETIRED.HITM", "PEBS": "1", + "PublicDescription": "Counts the number of load uops retired that hit in the L3 cache, in which a snoop was required and modified data was forwarded from another core or module. Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0x20" }, @@ -181,6 +183,7 @@ "EventCode": "0xd1", "EventName": "MEM_LOAD_UOPS_RETIRED.L1_HIT", "PEBS": "1", + "PublicDescription": "Counts the number of load uops retired that hit in the L1 data cache. Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0x1" }, @@ -191,6 +194,7 @@ "EventCode": "0xd1", "EventName": "MEM_LOAD_UOPS_RETIRED.L1_MISS", "PEBS": "1", + "PublicDescription": "Counts the number of load uops retired that miss in the L1 data cache. Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0x8" }, @@ -201,6 +205,7 @@ "EventCode": "0xd1", "EventName": "MEM_LOAD_UOPS_RETIRED.L2_HIT", "PEBS": "1", + "PublicDescription": "Counts the number of load uops retired that hit in the L2 cache. Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0x2" }, @@ -211,6 +216,7 @@ "EventCode": "0xd1", "EventName": "MEM_LOAD_UOPS_RETIRED.L2_MISS", "PEBS": "1", + "PublicDescription": "Counts the number of load uops retired that miss in the L2 cache. Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0x10" }, @@ -221,6 +227,7 @@ "EventCode": "0xd1", "EventName": "MEM_LOAD_UOPS_RETIRED.L3_HIT", "PEBS": "1", + "PublicDescription": "Counts the number of load uops retired that hit in the L3 cache. Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0x4" }, @@ -231,7 +238,7 @@ "EventCode": "0xd0", "EventName": "MEM_UOPS_RETIRED.ALL", "PEBS": "1", - "PublicDescription": "Counts the number of memory uops retired. A single uop that performs both a load AND a store will be counted as 1, not 2 (e.g. ADD [mem], CONST)", + "PublicDescription": "Counts the number of memory uops retired. A single uop that performs both a load AND a store will be counted as 1, not 2 (e.g. ADD [mem], CONST) Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0x83" }, @@ -242,7 +249,7 @@ "EventCode": "0xd0", "EventName": "MEM_UOPS_RETIRED.ALL_LOADS", "PEBS": "1", - "PublicDescription": "Counts the total number of load uops retired.", + "PublicDescription": "Counts the total number of load uops retired. Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0x81" }, @@ -253,7 +260,7 @@ "EventCode": "0xd0", "EventName": "MEM_UOPS_RETIRED.ALL_STORES", "PEBS": "1", - "PublicDescription": "Counts the total number of store uops retired.", + "PublicDescription": "Counts the total number of store uops retired. Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0x82" }, @@ -264,6 +271,7 @@ "EventCode": "0xd0", "EventName": "MEM_UOPS_RETIRED.LOCK_LOADS", "PEBS": "1", + "PublicDescription": "Counts the number of load uops retired that performed one or more locks. Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0x21" }, @@ -274,6 +282,7 @@ "EventCode": "0xd0", "EventName": "MEM_UOPS_RETIRED.SPLIT", "PEBS": "1", + "PublicDescription": "Counts the number of memory uops retired that were splits. Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0x43" }, @@ -284,6 +293,7 @@ "EventCode": "0xd0", "EventName": "MEM_UOPS_RETIRED.SPLIT_LOADS", "PEBS": "1", + "PublicDescription": "Counts the number of retired split load uops. Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0x41" }, @@ -294,6 +304,7 @@ "EventCode": "0xd0", "EventName": "MEM_UOPS_RETIRED.SPLIT_STORES", "PEBS": "1", + "PublicDescription": "Counts the number of retired split store uops. Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0x42" }, @@ -304,6 +315,7 @@ "EventName": "OCR.ALL_CODE_RD.L3_HIT", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x1F803C0044", + "PublicDescription": "Counts all code reads that were supplied by the L3 cache. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -314,6 +326,7 @@ "EventName": "OCR.ALL_CODE_RD.L3_HIT.SNOOP_HITM", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x10003C0044", + "PublicDescription": "Counts all code reads that were supplied by the L3 cache where a snoop was sent, the snoop hit, and modified data was forwarded. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -324,6 +337,7 @@ "EventName": "OCR.ALL_CODE_RD.L3_HIT.SNOOP_HIT_NO_FWD", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x4003C0044", + "PublicDescription": "Counts all code reads that were supplied by the L3 cache where a snoop was sent, the snoop hit, but no data was forwarded. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -334,6 +348,7 @@ "EventName": "OCR.ALL_CODE_RD.L3_HIT.SNOOP_HIT_WITH_FWD", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x8003C0044", + "PublicDescription": "Counts all code reads that were supplied by the L3 cache where a snoop was sent, the snoop hit, and non-modified data was forwarded. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -344,6 +359,7 @@ "EventName": "OCR.ALL_CODE_RD.L3_HIT.SNOOP_MISS", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x2003C0044", + "PublicDescription": "Counts all code reads that were supplied by the L3 cache where a snoop was sent but the snoop missed. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -354,6 +370,18 @@ "EventName": "OCR.ALL_CODE_RD.L3_HIT.SNOOP_NOT_NEEDED", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x1003C0044", + "PublicDescription": "Counts all code reads that were supplied by the L3 cache where no snoop was needed to satisfy the request. Available PDIST counters: 0", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts modified writebacks from L1 cache and L2 cache that have any type of response.", + "Counter": "0,1,2,3", + "EventCode": "0XB7", + "EventName": "OCR.COREWB_M.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x3000000010000", + "PublicDescription": "Counts modified writebacks from L1 cache and L2 cache that have any type of response. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -364,6 +392,29 @@ "EventName": "OCR.COREWB_M.L3_HIT", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x3001F803C0000", + "PublicDescription": "Counts modified writebacks from L1 cache and L2 cache that were supplied by the L3 cache. Available PDIST counters: 0", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts modified writebacks from L1 cache and L2 cache that have an outstanding request. Returns the number of cycles until the response is received (i.e. XQ to XQ latency).", + "Counter": "0,1,2,3", + "EventCode": "0XB7", + "EventName": "OCR.COREWB_M.OUTSTANDING", + "MSRIndex": "0x1a6", + "MSRValue": "0x8003000000000000", + "PublicDescription": "Counts modified writebacks from L1 cache and L2 cache that have an outstanding request. Returns the number of cycles until the response is received (i.e. XQ to XQ latency). Available PDIST counters: 0", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that have any type of response.", + "Counter": "0,1,2,3", + "EventCode": "0XB7", + "EventName": "OCR.DEMAND_CODE_RD.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x10004", + "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that have any type of response. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -374,6 +425,7 @@ "EventName": "OCR.DEMAND_CODE_RD.L3_HIT", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x1F803C0004", + "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were supplied by the L3 cache. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -384,6 +436,7 @@ "EventName": "OCR.DEMAND_CODE_RD.L3_HIT.SNOOP_HITM", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x10003C0004", + "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were supplied by the L3 cache where a snoop was sent, the snoop hit, and modified data was forwarded. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -394,6 +447,7 @@ "EventName": "OCR.DEMAND_CODE_RD.L3_HIT.SNOOP_HIT_NO_FWD", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x4003C0004", + "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were supplied by the L3 cache where a snoop was sent, the snoop hit, but no data was forwarded. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -404,6 +458,7 @@ "EventName": "OCR.DEMAND_CODE_RD.L3_HIT.SNOOP_HIT_WITH_FWD", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x8003C0004", + "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were supplied by the L3 cache where a snoop was sent, the snoop hit, and non-modified data was forwarded. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -414,6 +469,7 @@ "EventName": "OCR.DEMAND_CODE_RD.L3_HIT.SNOOP_MISS", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x2003C0004", + "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were supplied by the L3 cache where a snoop was sent but the snoop missed. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -424,6 +480,18 @@ "EventName": "OCR.DEMAND_CODE_RD.L3_HIT.SNOOP_NOT_NEEDED", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x1003C0004", + "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were supplied by the L3 cache where no snoop was needed to satisfy the request. Available PDIST counters: 0", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts cacheable demand data reads, L1 data cache hardware prefetches and software prefetches (except PREFETCHW) that have any type of response.", + "Counter": "0,1,2,3", + "EventCode": "0XB7", + "EventName": "OCR.DEMAND_DATA_AND_L1PF_RD.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x10001", + "PublicDescription": "Counts cacheable demand data reads, L1 data cache hardware prefetches and software prefetches (except PREFETCHW) that have any type of response. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -434,6 +502,7 @@ "EventName": "OCR.DEMAND_DATA_AND_L1PF_RD.L3_HIT", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x1F803C0001", + "PublicDescription": "Counts cacheable demand data reads, L1 data cache hardware prefetches and software prefetches (except PREFETCHW) that were supplied by the L3 cache. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -444,6 +513,7 @@ "EventName": "OCR.DEMAND_DATA_AND_L1PF_RD.L3_HIT.SNOOP_HITM", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x10003C0001", + "PublicDescription": "Counts cacheable demand data reads, L1 data cache hardware prefetches and software prefetches (except PREFETCHW) that were supplied by the L3 cache where a snoop was sent, the snoop hit, and modified data was forwarded. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -454,6 +524,7 @@ "EventName": "OCR.DEMAND_DATA_AND_L1PF_RD.L3_HIT.SNOOP_HIT_NO_FWD", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x4003C0001", + "PublicDescription": "Counts cacheable demand data reads, L1 data cache hardware prefetches and software prefetches (except PREFETCHW) that were supplied by the L3 cache where a snoop was sent, the snoop hit, but no data was forwarded. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -464,6 +535,7 @@ "EventName": "OCR.DEMAND_DATA_AND_L1PF_RD.L3_HIT.SNOOP_HIT_WITH_FWD", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x8003C0001", + "PublicDescription": "Counts cacheable demand data reads, L1 data cache hardware prefetches and software prefetches (except PREFETCHW) that were supplied by the L3 cache where a snoop was sent, the snoop hit, and non-modified data was forwarded. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -474,6 +546,7 @@ "EventName": "OCR.DEMAND_DATA_AND_L1PF_RD.L3_HIT.SNOOP_MISS", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x2003C0001", + "PublicDescription": "Counts cacheable demand data reads, L1 data cache hardware prefetches and software prefetches (except PREFETCHW) that were supplied by the L3 cache where a snoop was sent but the snoop missed. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -484,6 +557,30 @@ "EventName": "OCR.DEMAND_DATA_AND_L1PF_RD.L3_HIT.SNOOP_NOT_NEEDED", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x1003C0001", + "PublicDescription": "Counts cacheable demand data reads, L1 data cache hardware prefetches and software prefetches (except PREFETCHW) that were supplied by the L3 cache where no snoop was needed to satisfy the request. Available PDIST counters: 0", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts cacheable demand data reads, L1 data cache hardware prefetches and software prefetches (except PREFETCHW) that have an outstanding request. Returns the number of cycles until the response is received (i.e. XQ to XQ latency).", + "Counter": "0,1,2,3", + "EventCode": "0XB7", + "EventName": "OCR.DEMAND_DATA_AND_L1PF_RD.OUTSTANDING", + "MSRIndex": "0x1a6", + "MSRValue": "0x8000000000000001", + "PublicDescription": "Counts cacheable demand data reads, L1 data cache hardware prefetches and software prefetches (except PREFETCHW) that have an outstanding request. Returns the number of cycles until the response is received (i.e. XQ to XQ latency). Available PDIST counters: 0", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event OCR.DEMAND_DATA_AND_L1PF_RD.ANY_RESPONSE", + "Counter": "0,1,2,3", + "Deprecated": "1", + "EventCode": "0XB7", + "EventName": "OCR.DEMAND_DATA_RD.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x10001", + "PublicDescription": "This event is deprecated. Refer to new event OCR.DEMAND_DATA_AND_L1PF_RD.ANY_RESPONSE Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -495,6 +592,7 @@ "EventName": "OCR.DEMAND_DATA_RD.L3_HIT", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x1F803C0001", + "PublicDescription": "This event is deprecated. Refer to new event OCR.DEMAND_DATA_AND_L1PF_RD.L3_HIT Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -506,6 +604,7 @@ "EventName": "OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x10003C0001", + "PublicDescription": "This event is deprecated. Refer to new event OCR.DEMAND_DATA_AND_L1PF_RD.L3_HIT.SNOOP_HITM Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -517,6 +616,7 @@ "EventName": "OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_NO_FWD", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x4003C0001", + "PublicDescription": "This event is deprecated. Refer to new event OCR.DEMAND_DATA_AND_L1PF_RD.L3_HIT.SNOOP_HIT_NO_FWD Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -528,6 +628,7 @@ "EventName": "OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x8003C0001", + "PublicDescription": "This event is deprecated. Refer to new event OCR.DEMAND_DATA_AND_L1PF_RD.L3_HIT.SNOOP_HIT_WITH_FWD Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -539,6 +640,7 @@ "EventName": "OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_MISS", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x2003C0001", + "PublicDescription": "This event is deprecated. Refer to new event OCR.DEMAND_DATA_AND_L1PF_RD.L3_HIT.SNOOP_MISS Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -550,6 +652,30 @@ "EventName": "OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_NOT_NEEDED", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x1003C0001", + "PublicDescription": "This event is deprecated. Refer to new event OCR.DEMAND_DATA_AND_L1PF_RD.L3_HIT.SNOOP_NOT_NEEDED Available PDIST counters: 0", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event OCR.DEMAND_DATA_AND_L1PF_RD.OUTSTANDING", + "Counter": "0,1,2,3", + "Deprecated": "1", + "EventCode": "0XB7", + "EventName": "OCR.DEMAND_DATA_RD.OUTSTANDING", + "MSRIndex": "0x1a6", + "MSRValue": "0x8000000000000001", + "PublicDescription": "This event is deprecated. Refer to new event OCR.DEMAND_DATA_AND_L1PF_RD.OUTSTANDING Available PDIST counters: 0", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that have any type of response.", + "Counter": "0,1,2,3", + "EventCode": "0XB7", + "EventName": "OCR.DEMAND_RFO.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x10002", + "PublicDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that have any type of response. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -560,6 +686,7 @@ "EventName": "OCR.DEMAND_RFO.L3_HIT", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x1F803C0002", + "PublicDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that were supplied by the L3 cache. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -570,6 +697,7 @@ "EventName": "OCR.DEMAND_RFO.L3_HIT.SNOOP_HITM", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x10003C0002", + "PublicDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that were supplied by the L3 cache where a snoop was sent, the snoop hit, and modified data was forwarded. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -580,6 +708,7 @@ "EventName": "OCR.DEMAND_RFO.L3_HIT.SNOOP_HIT_NO_FWD", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x4003C0002", + "PublicDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that were supplied by the L3 cache where a snoop was sent, the snoop hit, but no data was forwarded. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -590,6 +719,7 @@ "EventName": "OCR.DEMAND_RFO.L3_HIT.SNOOP_HIT_WITH_FWD", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x8003C0002", + "PublicDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that were supplied by the L3 cache where a snoop was sent, the snoop hit, and non-modified data was forwarded. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -600,6 +730,7 @@ "EventName": "OCR.DEMAND_RFO.L3_HIT.SNOOP_MISS", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x2003C0002", + "PublicDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that were supplied by the L3 cache where a snoop was sent but the snoop missed. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -610,6 +741,18 @@ "EventName": "OCR.DEMAND_RFO.L3_HIT.SNOOP_NOT_NEEDED", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x1003C0002", + "PublicDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that were supplied by the L3 cache where no snoop was needed to satisfy the request. Available PDIST counters: 0", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that have an outstanding request. Returns the number of cycles until the response is received (i.e. XQ to XQ latency).", + "Counter": "0,1,2,3", + "EventCode": "0XB7", + "EventName": "OCR.DEMAND_RFO.OUTSTANDING", + "MSRIndex": "0x1a6", + "MSRValue": "0x8000000000000002", + "PublicDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that have an outstanding request. Returns the number of cycles until the response is received (i.e. XQ to XQ latency). Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -620,6 +763,18 @@ "EventName": "OCR.FULL_STREAMING_WR.L3_HIT", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x801F803C0000", + "PublicDescription": "Counts streaming stores which modify a full 64 byte cacheline that were supplied by the L3 cache. Available PDIST counters: 0", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts L1 data cache hardware prefetches and software prefetches (except PREFETCHW and PFRFO) that have any type of response.", + "Counter": "0,1,2,3", + "EventCode": "0XB7", + "EventName": "OCR.HWPF_L1D_AND_SWPF.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x10400", + "PublicDescription": "Counts L1 data cache hardware prefetches and software prefetches (except PREFETCHW and PFRFO) that have any type of response. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -630,6 +785,18 @@ "EventName": "OCR.HWPF_L1D_AND_SWPF.L3_HIT.SNOOP_HITM", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x10003C0400", + "PublicDescription": "Counts L1 data cache hardware prefetches and software prefetches (except PREFETCHW and PFRFO) that were supplied by the L3 cache where a snoop was sent, the snoop hit, and modified data was forwarded. Available PDIST counters: 0", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts L2 cache hardware prefetch code reads (written to the L2 cache only) that have any type of response.", + "Counter": "0,1,2,3", + "EventCode": "0XB7", + "EventName": "OCR.HWPF_L2_CODE_RD.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x10040", + "PublicDescription": "Counts L2 cache hardware prefetch code reads (written to the L2 cache only) that have any type of response. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -640,6 +807,7 @@ "EventName": "OCR.HWPF_L2_CODE_RD.L3_HIT", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x1F803C0040", + "PublicDescription": "Counts L2 cache hardware prefetch code reads (written to the L2 cache only) that were supplied by the L3 cache. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -650,6 +818,7 @@ "EventName": "OCR.HWPF_L2_CODE_RD.L3_HIT.SNOOP_HITM", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x10003C0040", + "PublicDescription": "Counts L2 cache hardware prefetch code reads (written to the L2 cache only) that were supplied by the L3 cache where a snoop was sent, the snoop hit, and modified data was forwarded. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -660,6 +829,7 @@ "EventName": "OCR.HWPF_L2_CODE_RD.L3_HIT.SNOOP_HIT_NO_FWD", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x4003C0040", + "PublicDescription": "Counts L2 cache hardware prefetch code reads (written to the L2 cache only) that were supplied by the L3 cache where a snoop was sent, the snoop hit, but no data was forwarded. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -670,6 +840,7 @@ "EventName": "OCR.HWPF_L2_CODE_RD.L3_HIT.SNOOP_HIT_WITH_FWD", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x8003C0040", + "PublicDescription": "Counts L2 cache hardware prefetch code reads (written to the L2 cache only) that were supplied by the L3 cache where a snoop was sent, the snoop hit, and non-modified data was forwarded. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -680,6 +851,7 @@ "EventName": "OCR.HWPF_L2_CODE_RD.L3_HIT.SNOOP_MISS", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x2003C0040", + "PublicDescription": "Counts L2 cache hardware prefetch code reads (written to the L2 cache only) that were supplied by the L3 cache where a snoop was sent but the snoop missed. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -690,6 +862,29 @@ "EventName": "OCR.HWPF_L2_CODE_RD.L3_HIT.SNOOP_NOT_NEEDED", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x1003C0040", + "PublicDescription": "Counts L2 cache hardware prefetch code reads (written to the L2 cache only) that were supplied by the L3 cache where no snoop was needed to satisfy the request. Available PDIST counters: 0", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts L2 cache hardware prefetch code reads (written to the L2 cache only) that have an outstanding request. Returns the number of cycles until the response is received (i.e. XQ to XQ latency).", + "Counter": "0,1,2,3", + "EventCode": "0XB7", + "EventName": "OCR.HWPF_L2_CODE_RD.OUTSTANDING", + "MSRIndex": "0x1a6", + "MSRValue": "0x8000000000000040", + "PublicDescription": "Counts L2 cache hardware prefetch code reads (written to the L2 cache only) that have an outstanding request. Returns the number of cycles until the response is received (i.e. XQ to XQ latency). Available PDIST counters: 0", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts L2 cache hardware prefetch data reads (written to the L2 cache only) that have any type of response.", + "Counter": "0,1,2,3", + "EventCode": "0XB7", + "EventName": "OCR.HWPF_L2_DATA_RD.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x10010", + "PublicDescription": "Counts L2 cache hardware prefetch data reads (written to the L2 cache only) that have any type of response. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -700,6 +895,7 @@ "EventName": "OCR.HWPF_L2_DATA_RD.L3_HIT", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x1F803C0010", + "PublicDescription": "Counts L2 cache hardware prefetch data reads (written to the L2 cache only) that were supplied by the L3 cache. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -710,6 +906,7 @@ "EventName": "OCR.HWPF_L2_DATA_RD.L3_HIT.SNOOP_HITM", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x10003C0010", + "PublicDescription": "Counts L2 cache hardware prefetch data reads (written to the L2 cache only) that were supplied by the L3 cache where a snoop was sent, the snoop hit, and modified data was forwarded. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -720,6 +917,7 @@ "EventName": "OCR.HWPF_L2_DATA_RD.L3_HIT.SNOOP_HIT_NO_FWD", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x4003C0010", + "PublicDescription": "Counts L2 cache hardware prefetch data reads (written to the L2 cache only) that were supplied by the L3 cache where a snoop was sent, the snoop hit, but no data was forwarded. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -730,6 +928,7 @@ "EventName": "OCR.HWPF_L2_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x8003C0010", + "PublicDescription": "Counts L2 cache hardware prefetch data reads (written to the L2 cache only) that were supplied by the L3 cache where a snoop was sent, the snoop hit, and non-modified data was forwarded. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -740,6 +939,7 @@ "EventName": "OCR.HWPF_L2_DATA_RD.L3_HIT.SNOOP_MISS", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x2003C0010", + "PublicDescription": "Counts L2 cache hardware prefetch data reads (written to the L2 cache only) that were supplied by the L3 cache where a snoop was sent but the snoop missed. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -750,6 +950,18 @@ "EventName": "OCR.HWPF_L2_DATA_RD.L3_HIT.SNOOP_NOT_NEEDED", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x1003C0010", + "PublicDescription": "Counts L2 cache hardware prefetch data reads (written to the L2 cache only) that were supplied by the L3 cache where no snoop was needed to satisfy the request. Available PDIST counters: 0", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts L2 cache hardware prefetch RFOs (written to the L2 cache only) that have any type of response.", + "Counter": "0,1,2,3", + "EventCode": "0XB7", + "EventName": "OCR.HWPF_L2_RFO.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x10020", + "PublicDescription": "Counts L2 cache hardware prefetch RFOs (written to the L2 cache only) that have any type of response. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -760,6 +972,7 @@ "EventName": "OCR.HWPF_L2_RFO.L3_HIT", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x1F803C0020", + "PublicDescription": "Counts L2 cache hardware prefetch RFOs (written to the L2 cache only) that were supplied by the L3 cache. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -770,6 +983,7 @@ "EventName": "OCR.HWPF_L2_RFO.L3_HIT.SNOOP_HITM", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x10003C0020", + "PublicDescription": "Counts L2 cache hardware prefetch RFOs (written to the L2 cache only) that were supplied by the L3 cache where a snoop was sent, the snoop hit, and modified data was forwarded. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -780,6 +994,7 @@ "EventName": "OCR.HWPF_L2_RFO.L3_HIT.SNOOP_HIT_NO_FWD", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x4003C0020", + "PublicDescription": "Counts L2 cache hardware prefetch RFOs (written to the L2 cache only) that were supplied by the L3 cache where a snoop was sent, the snoop hit, but no data was forwarded. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -790,6 +1005,7 @@ "EventName": "OCR.HWPF_L2_RFO.L3_HIT.SNOOP_HIT_WITH_FWD", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x8003C0020", + "PublicDescription": "Counts L2 cache hardware prefetch RFOs (written to the L2 cache only) that were supplied by the L3 cache where a snoop was sent, the snoop hit, and non-modified data was forwarded. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -800,6 +1016,7 @@ "EventName": "OCR.HWPF_L2_RFO.L3_HIT.SNOOP_MISS", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x2003C0020", + "PublicDescription": "Counts L2 cache hardware prefetch RFOs (written to the L2 cache only) that were supplied by the L3 cache where a snoop was sent but the snoop missed. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -810,6 +1027,29 @@ "EventName": "OCR.HWPF_L2_RFO.L3_HIT.SNOOP_NOT_NEEDED", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x1003C0020", + "PublicDescription": "Counts L2 cache hardware prefetch RFOs (written to the L2 cache only) that were supplied by the L3 cache where no snoop was needed to satisfy the request. Available PDIST counters: 0", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts L2 cache hardware prefetch RFOs (written to the L2 cache only) that have an outstanding request. Returns the number of cycles until the response is received (i.e. XQ to XQ latency).", + "Counter": "0,1,2,3", + "EventCode": "0XB7", + "EventName": "OCR.HWPF_L2_RFO.OUTSTANDING", + "MSRIndex": "0x1a6", + "MSRValue": "0x8000000000000020", + "PublicDescription": "Counts L2 cache hardware prefetch RFOs (written to the L2 cache only) that have an outstanding request. Returns the number of cycles until the response is received (i.e. XQ to XQ latency). Available PDIST counters: 0", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts modified writebacks from L1 cache that miss the L2 cache that have any type of response.", + "Counter": "0,1,2,3", + "EventCode": "0XB7", + "EventName": "OCR.L1WB_M.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x1000000010000", + "PublicDescription": "Counts modified writebacks from L1 cache that miss the L2 cache that have any type of response. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -820,6 +1060,18 @@ "EventName": "OCR.L1WB_M.L3_HIT", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x1001F803C0000", + "PublicDescription": "Counts modified writebacks from L1 cache that miss the L2 cache that were supplied by the L3 cache. Available PDIST counters: 0", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts modified writeBacks from L2 cache that miss the L3 cache that have any type of response.", + "Counter": "0,1,2,3", + "EventCode": "0XB7", + "EventName": "OCR.L2WB_M.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x2000000010000", + "PublicDescription": "Counts modified writeBacks from L2 cache that miss the L3 cache that have any type of response. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -830,6 +1082,7 @@ "EventName": "OCR.L2WB_M.L3_HIT", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x2001F803C0000", + "PublicDescription": "Counts modified writeBacks from L2 cache that miss the L3 cache that were supplied by the L3 cache. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -840,6 +1093,18 @@ "EventName": "OCR.PARTIAL_STREAMING_WR.L3_HIT", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x401F803C0000", + "PublicDescription": "Counts streaming stores which modify only part of a 64 byte cacheline that were supplied by the L3 cache. Available PDIST counters: 0", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts all data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that have any type of response.", + "Counter": "0,1,2,3", + "EventCode": "0XB7", + "EventName": "OCR.READS_TO_CORE.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x10477", + "PublicDescription": "Counts all data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that have any type of response. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -850,6 +1115,7 @@ "EventName": "OCR.READS_TO_CORE.L3_HIT", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x1F803C0477", + "PublicDescription": "Counts all data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by the L3 cache. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -860,6 +1126,7 @@ "EventName": "OCR.READS_TO_CORE.L3_HIT.SNOOP_HITM", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x10003C0477", + "PublicDescription": "Counts all data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by the L3 cache where a snoop was sent, the snoop hit, and modified data was forwarded. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -870,6 +1137,7 @@ "EventName": "OCR.READS_TO_CORE.L3_HIT.SNOOP_HIT_NO_FWD", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x4003C0477", + "PublicDescription": "Counts all data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by the L3 cache where a snoop was sent, the snoop hit, but no data was forwarded. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -880,6 +1148,7 @@ "EventName": "OCR.READS_TO_CORE.L3_HIT.SNOOP_HIT_WITH_FWD", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x8003C0477", + "PublicDescription": "Counts all data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by the L3 cache where a snoop was sent, the snoop hit, and non-modified data was forwarded. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -890,6 +1159,7 @@ "EventName": "OCR.READS_TO_CORE.L3_HIT.SNOOP_MISS", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x2003C0477", + "PublicDescription": "Counts all data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by the L3 cache where a snoop was sent but the snoop missed. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -900,6 +1170,18 @@ "EventName": "OCR.READS_TO_CORE.L3_HIT.SNOOP_NOT_NEEDED", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x1003C0477", + "PublicDescription": "Counts all data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by the L3 cache where no snoop was needed to satisfy the request. Available PDIST counters: 0", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts all data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that have an outstanding request. Returns the number of cycles until the response is received (i.e. XQ to XQ latency).", + "Counter": "0,1,2,3", + "EventCode": "0XB7", + "EventName": "OCR.READS_TO_CORE.OUTSTANDING", + "MSRIndex": "0x1a6", + "MSRValue": "0x8000000000000477", + "PublicDescription": "Counts all data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that have an outstanding request. Returns the number of cycles until the response is received (i.e. XQ to XQ latency). Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -910,6 +1192,7 @@ "EventName": "OCR.STREAMING_WR.L3_HIT", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x1F803C0800", + "PublicDescription": "Counts streaming stores that were supplied by the L3 cache. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -920,6 +1203,7 @@ "EventName": "OCR.UC_RD.L3_HIT", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x101F803C0000", + "PublicDescription": "Counts uncached memory reads that were supplied by the L3 cache. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -930,6 +1214,7 @@ "EventName": "OCR.UC_RD.L3_HIT.SNOOP_HITM", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x1010003C0000", + "PublicDescription": "Counts uncached memory reads that were supplied by the L3 cache where a snoop was sent, the snoop hit, and modified data was forwarded. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -940,6 +1225,7 @@ "EventName": "OCR.UC_RD.L3_HIT.SNOOP_HIT_NO_FWD", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x1004003C0000", + "PublicDescription": "Counts uncached memory reads that were supplied by the L3 cache where a snoop was sent, the snoop hit, but no data was forwarded. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -950,6 +1236,7 @@ "EventName": "OCR.UC_RD.L3_HIT.SNOOP_HIT_WITH_FWD", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x1008003C0000", + "PublicDescription": "Counts uncached memory reads that were supplied by the L3 cache where a snoop was sent, the snoop hit, and non-modified data was forwarded. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -960,6 +1247,7 @@ "EventName": "OCR.UC_RD.L3_HIT.SNOOP_MISS", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x1002003C0000", + "PublicDescription": "Counts uncached memory reads that were supplied by the L3 cache where a snoop was sent but the snoop missed. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -970,6 +1258,7 @@ "EventName": "OCR.UC_RD.L3_HIT.SNOOP_NOT_NEEDED", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x1001003C0000", + "PublicDescription": "Counts uncached memory reads that were supplied by the L3 cache where no snoop was needed to satisfy the request. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -980,6 +1269,7 @@ "EventName": "OCR.UC_WR.L3_HIT", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x201F803C0000", + "PublicDescription": "Counts uncached memory writes that were supplied by the L3 cache. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, diff --git a/tools/perf/pmu-events/arch/x86/snowridgex/floating-point.json b/tools/perf/pmu-events/arch/x86/snowridgex/floating-point.json index 79a4beba4b78..f47d97dfe0d9 100644 --- a/tools/perf/pmu-events/arch/x86/snowridgex/floating-point.json +++ b/tools/perf/pmu-events/arch/x86/snowridgex/floating-point.json @@ -23,6 +23,7 @@ "EventCode": "0xc2", "EventName": "UOPS_RETIRED.FPDIV", "PEBS": "1", + "PublicDescription": "Counts the number of floating point divide uops retired (x87 and SSE, including x87 sqrt). Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x8" } diff --git a/tools/perf/pmu-events/arch/x86/snowridgex/memory.json b/tools/perf/pmu-events/arch/x86/snowridgex/memory.json index 34306ec24e9b..417cd78fc048 100644 --- a/tools/perf/pmu-events/arch/x86/snowridgex/memory.json +++ b/tools/perf/pmu-events/arch/x86/snowridgex/memory.json @@ -13,6 +13,7 @@ "EventCode": "0x13", "EventName": "MISALIGN_MEM_REF.LOAD_PAGE_SPLIT", "PEBS": "1", + "PublicDescription": "Counts the number of misaligned load uops that are 4K page splits. Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0x2" }, @@ -22,16 +23,29 @@ "EventCode": "0x13", "EventName": "MISALIGN_MEM_REF.STORE_PAGE_SPLIT", "PEBS": "1", + "PublicDescription": "Counts the number of misaligned store uops that are 4K page splits. Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0x4" }, { + "BriefDescription": "Counts all code reads that were supplied by DRAM.", + "Counter": "0,1,2,3", + "EventCode": "0XB7", + "EventName": "OCR.ALL_CODE_RD.DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x184000044", + "PublicDescription": "Counts all code reads that were supplied by DRAM. Available PDIST counters: 0", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { "BriefDescription": "Counts all code reads that were not supplied by the L3 cache.", "Counter": "0,1,2,3", "EventCode": "0XB7", "EventName": "OCR.ALL_CODE_RD.L3_MISS", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x2184000044", + "PublicDescription": "Counts all code reads that were not supplied by the L3 cache. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -42,6 +56,18 @@ "EventName": "OCR.ALL_CODE_RD.L3_MISS_LOCAL", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x2184000044", + "PublicDescription": "Counts all code reads that were not supplied by the L3 cache. Available PDIST counters: 0", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts all code reads that were supplied by DRAM.", + "Counter": "0,1,2,3", + "EventCode": "0XB7", + "EventName": "OCR.ALL_CODE_RD.LOCAL_DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x184000044", + "PublicDescription": "Counts all code reads that were supplied by DRAM. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -52,6 +78,7 @@ "EventName": "OCR.COREWB_M.L3_MISS", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x3002184000000", + "PublicDescription": "Counts modified writebacks from L1 cache and L2 cache that were not supplied by the L3 cache. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -62,6 +89,18 @@ "EventName": "OCR.COREWB_M.L3_MISS_LOCAL", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x3002184000000", + "PublicDescription": "Counts modified writebacks from L1 cache and L2 cache that were not supplied by the L3 cache. Available PDIST counters: 0", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were supplied by DRAM.", + "Counter": "0,1,2,3", + "EventCode": "0XB7", + "EventName": "OCR.DEMAND_CODE_RD.DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x184000004", + "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were supplied by DRAM. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -72,6 +111,7 @@ "EventName": "OCR.DEMAND_CODE_RD.L3_MISS", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x2184000004", + "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were not supplied by the L3 cache. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -82,6 +122,29 @@ "EventName": "OCR.DEMAND_CODE_RD.L3_MISS_LOCAL", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x2184000004", + "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were not supplied by the L3 cache. Available PDIST counters: 0", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were supplied by DRAM.", + "Counter": "0,1,2,3", + "EventCode": "0XB7", + "EventName": "OCR.DEMAND_CODE_RD.LOCAL_DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x184000004", + "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were supplied by DRAM. Available PDIST counters: 0", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts cacheable demand data reads, L1 data cache hardware prefetches and software prefetches (except PREFETCHW) that were supplied by DRAM.", + "Counter": "0,1,2,3", + "EventCode": "0XB7", + "EventName": "OCR.DEMAND_DATA_AND_L1PF_RD.DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x184000001", + "PublicDescription": "Counts cacheable demand data reads, L1 data cache hardware prefetches and software prefetches (except PREFETCHW) that were supplied by DRAM. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -92,6 +155,7 @@ "EventName": "OCR.DEMAND_DATA_AND_L1PF_RD.L3_MISS", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x2184000001", + "PublicDescription": "Counts cacheable demand data reads, L1 data cache hardware prefetches and software prefetches (except PREFETCHW) that were not supplied by the L3 cache. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -102,6 +166,30 @@ "EventName": "OCR.DEMAND_DATA_AND_L1PF_RD.L3_MISS_LOCAL", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x2184000001", + "PublicDescription": "Counts cacheable demand data reads, L1 data cache hardware prefetches and software prefetches (except PREFETCHW) that were not supplied by the L3 cache. Available PDIST counters: 0", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts cacheable demand data reads, L1 data cache hardware prefetches and software prefetches (except PREFETCHW) that were supplied by DRAM.", + "Counter": "0,1,2,3", + "EventCode": "0XB7", + "EventName": "OCR.DEMAND_DATA_AND_L1PF_RD.LOCAL_DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x184000001", + "PublicDescription": "Counts cacheable demand data reads, L1 data cache hardware prefetches and software prefetches (except PREFETCHW) that were supplied by DRAM. Available PDIST counters: 0", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event OCR.DEMAND_DATA_AND_L1PF_RD.DRAM", + "Counter": "0,1,2,3", + "Deprecated": "1", + "EventCode": "0XB7", + "EventName": "OCR.DEMAND_DATA_RD.DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x184000001", + "PublicDescription": "This event is deprecated. Refer to new event OCR.DEMAND_DATA_AND_L1PF_RD.DRAM Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -113,6 +201,7 @@ "EventName": "OCR.DEMAND_DATA_RD.L3_MISS", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x2184000001", + "PublicDescription": "This event is deprecated. Refer to new event OCR.DEMAND_DATA_AND_L1PF_RD.L3_MISS Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -124,6 +213,30 @@ "EventName": "OCR.DEMAND_DATA_RD.L3_MISS_LOCAL", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x2184000001", + "PublicDescription": "This event is deprecated. Refer to new event OCR.DEMAND_DATA_AND_L1PF_RD.L3_MISS_LOCAL Available PDIST counters: 0", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event OCR.DEMAND_DATA_AND_L1PF_RD.LOCAL_DRAM", + "Counter": "0,1,2,3", + "Deprecated": "1", + "EventCode": "0XB7", + "EventName": "OCR.DEMAND_DATA_RD.LOCAL_DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x184000001", + "PublicDescription": "This event is deprecated. Refer to new event OCR.DEMAND_DATA_AND_L1PF_RD.LOCAL_DRAM Available PDIST counters: 0", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that were supplied by DRAM.", + "Counter": "0,1,2,3", + "EventCode": "0XB7", + "EventName": "OCR.DEMAND_RFO.DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x184000002", + "PublicDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that were supplied by DRAM. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -134,6 +247,7 @@ "EventName": "OCR.DEMAND_RFO.L3_MISS", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x2184000002", + "PublicDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that were not supplied by the L3 cache. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -144,6 +258,18 @@ "EventName": "OCR.DEMAND_RFO.L3_MISS_LOCAL", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x2184000002", + "PublicDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that were not supplied by the L3 cache. Available PDIST counters: 0", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that were supplied by DRAM.", + "Counter": "0,1,2,3", + "EventCode": "0XB7", + "EventName": "OCR.DEMAND_RFO.LOCAL_DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x184000002", + "PublicDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that were supplied by DRAM. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -154,6 +280,7 @@ "EventName": "OCR.FULL_STREAMING_WR.L3_MISS", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x802184000000", + "PublicDescription": "Counts streaming stores which modify a full 64 byte cacheline that were not supplied by the L3 cache. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -164,6 +291,18 @@ "EventName": "OCR.FULL_STREAMING_WR.L3_MISS_LOCAL", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x802184000000", + "PublicDescription": "Counts streaming stores which modify a full 64 byte cacheline that were not supplied by the L3 cache. Available PDIST counters: 0", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts L2 cache hardware prefetch code reads (written to the L2 cache only) that were supplied by DRAM.", + "Counter": "0,1,2,3", + "EventCode": "0XB7", + "EventName": "OCR.HWPF_L2_CODE_RD.DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x184000040", + "PublicDescription": "Counts L2 cache hardware prefetch code reads (written to the L2 cache only) that were supplied by DRAM. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -174,6 +313,7 @@ "EventName": "OCR.HWPF_L2_CODE_RD.L3_MISS", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x2184000040", + "PublicDescription": "Counts L2 cache hardware prefetch code reads (written to the L2 cache only) that were not supplied by the L3 cache. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -184,6 +324,29 @@ "EventName": "OCR.HWPF_L2_CODE_RD.L3_MISS_LOCAL", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x2184000040", + "PublicDescription": "Counts L2 cache hardware prefetch code reads (written to the L2 cache only) that were not supplied by the L3 cache. Available PDIST counters: 0", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts L2 cache hardware prefetch code reads (written to the L2 cache only) that were supplied by DRAM.", + "Counter": "0,1,2,3", + "EventCode": "0XB7", + "EventName": "OCR.HWPF_L2_CODE_RD.LOCAL_DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x184000040", + "PublicDescription": "Counts L2 cache hardware prefetch code reads (written to the L2 cache only) that were supplied by DRAM. Available PDIST counters: 0", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts L2 cache hardware prefetch data reads (written to the L2 cache only) that were supplied by DRAM.", + "Counter": "0,1,2,3", + "EventCode": "0XB7", + "EventName": "OCR.HWPF_L2_DATA_RD.DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x184000010", + "PublicDescription": "Counts L2 cache hardware prefetch data reads (written to the L2 cache only) that were supplied by DRAM. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -194,6 +357,7 @@ "EventName": "OCR.HWPF_L2_DATA_RD.L3_MISS", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x2184000010", + "PublicDescription": "Counts L2 cache hardware prefetch data reads (written to the L2 cache only) that were not supplied by the L3 cache. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -204,6 +368,29 @@ "EventName": "OCR.HWPF_L2_DATA_RD.L3_MISS_LOCAL", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x2184000010", + "PublicDescription": "Counts L2 cache hardware prefetch data reads (written to the L2 cache only) that were not supplied by the L3 cache. Available PDIST counters: 0", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts L2 cache hardware prefetch data reads (written to the L2 cache only) that were supplied by DRAM.", + "Counter": "0,1,2,3", + "EventCode": "0XB7", + "EventName": "OCR.HWPF_L2_DATA_RD.LOCAL_DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x184000010", + "PublicDescription": "Counts L2 cache hardware prefetch data reads (written to the L2 cache only) that were supplied by DRAM. Available PDIST counters: 0", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts L2 cache hardware prefetch RFOs (written to the L2 cache only) that were supplied by DRAM.", + "Counter": "0,1,2,3", + "EventCode": "0XB7", + "EventName": "OCR.HWPF_L2_RFO.DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x184000020", + "PublicDescription": "Counts L2 cache hardware prefetch RFOs (written to the L2 cache only) that were supplied by DRAM. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -214,6 +401,7 @@ "EventName": "OCR.HWPF_L2_RFO.L3_MISS", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x2184000020", + "PublicDescription": "Counts L2 cache hardware prefetch RFOs (written to the L2 cache only) that were not supplied by the L3 cache. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -224,6 +412,18 @@ "EventName": "OCR.HWPF_L2_RFO.L3_MISS_LOCAL", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x2184000020", + "PublicDescription": "Counts L2 cache hardware prefetch RFOs (written to the L2 cache only) that were not supplied by the L3 cache. Available PDIST counters: 0", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts L2 cache hardware prefetch RFOs (written to the L2 cache only) that were supplied by DRAM.", + "Counter": "0,1,2,3", + "EventCode": "0XB7", + "EventName": "OCR.HWPF_L2_RFO.LOCAL_DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x184000020", + "PublicDescription": "Counts L2 cache hardware prefetch RFOs (written to the L2 cache only) that were supplied by DRAM. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -234,6 +434,7 @@ "EventName": "OCR.L1WB_M.L3_MISS", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x1002184000000", + "PublicDescription": "Counts modified writebacks from L1 cache that miss the L2 cache that were not supplied by the L3 cache. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -244,6 +445,7 @@ "EventName": "OCR.L1WB_M.L3_MISS_LOCAL", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x1002184000000", + "PublicDescription": "Counts modified writebacks from L1 cache that miss the L2 cache that were not supplied by the L3 cache. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -254,6 +456,7 @@ "EventName": "OCR.L2WB_M.L3_MISS", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x2002184000000", + "PublicDescription": "Counts modified writeBacks from L2 cache that miss the L3 cache that were not supplied by the L3 cache. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -264,6 +467,7 @@ "EventName": "OCR.L2WB_M.L3_MISS_LOCAL", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x2002184000000", + "PublicDescription": "Counts modified writeBacks from L2 cache that miss the L3 cache that were not supplied by the L3 cache. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -274,6 +478,7 @@ "EventName": "OCR.OTHER.L3_MISS", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x2184008000", + "PublicDescription": "Counts miscellaneous requests, such as I/O accesses, that were not supplied by the L3 cache. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -284,6 +489,7 @@ "EventName": "OCR.OTHER.L3_MISS_LOCAL", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x2184008000", + "PublicDescription": "Counts miscellaneous requests, such as I/O accesses, that were not supplied by the L3 cache. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -294,6 +500,7 @@ "EventName": "OCR.PARTIAL_STREAMING_WR.L3_MISS", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x402184000000", + "PublicDescription": "Counts streaming stores which modify only part of a 64 byte cacheline that were not supplied by the L3 cache. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -304,6 +511,7 @@ "EventName": "OCR.PARTIAL_STREAMING_WR.L3_MISS_LOCAL", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x402184000000", + "PublicDescription": "Counts streaming stores which modify only part of a 64 byte cacheline that were not supplied by the L3 cache. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -314,6 +522,18 @@ "EventName": "OCR.PREFETCHES.L3_MISS", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x2184000470", + "PublicDescription": "Counts all hardware and software prefetches that were not supplied by the L3 cache. Available PDIST counters: 0", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts all data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by DRAM.", + "Counter": "0,1,2,3", + "EventCode": "0XB7", + "EventName": "OCR.READS_TO_CORE.DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x184000477", + "PublicDescription": "Counts all data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by DRAM. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -324,6 +544,7 @@ "EventName": "OCR.READS_TO_CORE.L3_MISS", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x2184000477", + "PublicDescription": "Counts all data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were not supplied by the L3 cache. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -334,6 +555,18 @@ "EventName": "OCR.READS_TO_CORE.L3_MISS_LOCAL", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x2184000477", + "PublicDescription": "Counts all data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were not supplied by the L3 cache. Available PDIST counters: 0", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts all data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by DRAM.", + "Counter": "0,1,2,3", + "EventCode": "0XB7", + "EventName": "OCR.READS_TO_CORE.LOCAL_DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x184000477", + "PublicDescription": "Counts all data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by DRAM. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -344,6 +577,7 @@ "EventName": "OCR.STREAMING_WR.L3_MISS", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x2184000800", + "PublicDescription": "Counts streaming stores that were not supplied by the L3 cache. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -354,6 +588,18 @@ "EventName": "OCR.STREAMING_WR.L3_MISS_LOCAL", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x2184000800", + "PublicDescription": "Counts streaming stores that were not supplied by the L3 cache. Available PDIST counters: 0", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts uncached memory reads that were supplied by DRAM.", + "Counter": "0,1,2,3", + "EventCode": "0XB7", + "EventName": "OCR.UC_RD.DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x100184000000", + "PublicDescription": "Counts uncached memory reads that were supplied by DRAM. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -364,6 +610,7 @@ "EventName": "OCR.UC_RD.L3_MISS", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x102184000000", + "PublicDescription": "Counts uncached memory reads that were not supplied by the L3 cache. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -374,6 +621,18 @@ "EventName": "OCR.UC_RD.L3_MISS_LOCAL", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x102184000000", + "PublicDescription": "Counts uncached memory reads that were not supplied by the L3 cache. Available PDIST counters: 0", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts uncached memory reads that were supplied by DRAM.", + "Counter": "0,1,2,3", + "EventCode": "0XB7", + "EventName": "OCR.UC_RD.LOCAL_DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x100184000000", + "PublicDescription": "Counts uncached memory reads that were supplied by DRAM. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -384,6 +643,7 @@ "EventName": "OCR.UC_WR.L3_MISS", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x202184000000", + "PublicDescription": "Counts uncached memory writes that were not supplied by the L3 cache. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -394,6 +654,7 @@ "EventName": "OCR.UC_WR.L3_MISS_LOCAL", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x202184000000", + "PublicDescription": "Counts uncached memory writes that were not supplied by the L3 cache. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" } diff --git a/tools/perf/pmu-events/arch/x86/snowridgex/other.json b/tools/perf/pmu-events/arch/x86/snowridgex/other.json index 57613207f7ad..2cdc6b64f31d 100644 --- a/tools/perf/pmu-events/arch/x86/snowridgex/other.json +++ b/tools/perf/pmu-events/arch/x86/snowridgex/other.json @@ -113,26 +113,7 @@ "EventName": "OCR.ALL_CODE_RD.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x10044", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts all code reads that were supplied by DRAM.", - "Counter": "0,1,2,3", - "EventCode": "0XB7", - "EventName": "OCR.ALL_CODE_RD.DRAM", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x184000044", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts all code reads that were supplied by DRAM.", - "Counter": "0,1,2,3", - "EventCode": "0XB7", - "EventName": "OCR.ALL_CODE_RD.LOCAL_DRAM", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x184000044", + "PublicDescription": "Counts all code reads that have any type of response. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -143,180 +124,7 @@ "EventName": "OCR.ALL_CODE_RD.OUTSTANDING", "MSRIndex": "0x1a6", "MSRValue": "0x8000000000000044", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts modified writebacks from L1 cache and L2 cache that have any type of response.", - "Counter": "0,1,2,3", - "EventCode": "0XB7", - "EventName": "OCR.COREWB_M.ANY_RESPONSE", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x3000000010000", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts modified writebacks from L1 cache and L2 cache that have an outstanding request. Returns the number of cycles until the response is received (i.e. XQ to XQ latency).", - "Counter": "0,1,2,3", - "EventCode": "0XB7", - "EventName": "OCR.COREWB_M.OUTSTANDING", - "MSRIndex": "0x1a6", - "MSRValue": "0x8003000000000000", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that have any type of response.", - "Counter": "0,1,2,3", - "EventCode": "0XB7", - "EventName": "OCR.DEMAND_CODE_RD.ANY_RESPONSE", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x10004", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were supplied by DRAM.", - "Counter": "0,1,2,3", - "EventCode": "0XB7", - "EventName": "OCR.DEMAND_CODE_RD.DRAM", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x184000004", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were supplied by DRAM.", - "Counter": "0,1,2,3", - "EventCode": "0XB7", - "EventName": "OCR.DEMAND_CODE_RD.LOCAL_DRAM", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x184000004", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts cacheable demand data reads, L1 data cache hardware prefetches and software prefetches (except PREFETCHW) that have any type of response.", - "Counter": "0,1,2,3", - "EventCode": "0XB7", - "EventName": "OCR.DEMAND_DATA_AND_L1PF_RD.ANY_RESPONSE", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x10001", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts cacheable demand data reads, L1 data cache hardware prefetches and software prefetches (except PREFETCHW) that were supplied by DRAM.", - "Counter": "0,1,2,3", - "EventCode": "0XB7", - "EventName": "OCR.DEMAND_DATA_AND_L1PF_RD.DRAM", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x184000001", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts cacheable demand data reads, L1 data cache hardware prefetches and software prefetches (except PREFETCHW) that were supplied by DRAM.", - "Counter": "0,1,2,3", - "EventCode": "0XB7", - "EventName": "OCR.DEMAND_DATA_AND_L1PF_RD.LOCAL_DRAM", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x184000001", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts cacheable demand data reads, L1 data cache hardware prefetches and software prefetches (except PREFETCHW) that have an outstanding request. Returns the number of cycles until the response is received (i.e. XQ to XQ latency).", - "Counter": "0,1,2,3", - "EventCode": "0XB7", - "EventName": "OCR.DEMAND_DATA_AND_L1PF_RD.OUTSTANDING", - "MSRIndex": "0x1a6", - "MSRValue": "0x8000000000000001", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event OCR.DEMAND_DATA_AND_L1PF_RD.ANY_RESPONSE", - "Counter": "0,1,2,3", - "Deprecated": "1", - "EventCode": "0XB7", - "EventName": "OCR.DEMAND_DATA_RD.ANY_RESPONSE", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x10001", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event OCR.DEMAND_DATA_AND_L1PF_RD.DRAM", - "Counter": "0,1,2,3", - "Deprecated": "1", - "EventCode": "0XB7", - "EventName": "OCR.DEMAND_DATA_RD.DRAM", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x184000001", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event OCR.DEMAND_DATA_AND_L1PF_RD.LOCAL_DRAM", - "Counter": "0,1,2,3", - "Deprecated": "1", - "EventCode": "0XB7", - "EventName": "OCR.DEMAND_DATA_RD.LOCAL_DRAM", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x184000001", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event OCR.DEMAND_DATA_AND_L1PF_RD.OUTSTANDING", - "Counter": "0,1,2,3", - "Deprecated": "1", - "EventCode": "0XB7", - "EventName": "OCR.DEMAND_DATA_RD.OUTSTANDING", - "MSRIndex": "0x1a6", - "MSRValue": "0x8000000000000001", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that have any type of response.", - "Counter": "0,1,2,3", - "EventCode": "0XB7", - "EventName": "OCR.DEMAND_RFO.ANY_RESPONSE", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x10002", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that were supplied by DRAM.", - "Counter": "0,1,2,3", - "EventCode": "0XB7", - "EventName": "OCR.DEMAND_RFO.DRAM", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x184000002", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that were supplied by DRAM.", - "Counter": "0,1,2,3", - "EventCode": "0XB7", - "EventName": "OCR.DEMAND_RFO.LOCAL_DRAM", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x184000002", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that have an outstanding request. Returns the number of cycles until the response is received (i.e. XQ to XQ latency).", - "Counter": "0,1,2,3", - "EventCode": "0XB7", - "EventName": "OCR.DEMAND_RFO.OUTSTANDING", - "MSRIndex": "0x1a6", - "MSRValue": "0x8000000000000002", + "PublicDescription": "Counts all code reads that have an outstanding request. Returns the number of cycles until the response is received (i.e. XQ to XQ latency). Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -327,146 +135,7 @@ "EventName": "OCR.FULL_STREAMING_WR.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x800000010000", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts L1 data cache hardware prefetches and software prefetches (except PREFETCHW and PFRFO) that have any type of response.", - "Counter": "0,1,2,3", - "EventCode": "0XB7", - "EventName": "OCR.HWPF_L1D_AND_SWPF.ANY_RESPONSE", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x10400", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts L2 cache hardware prefetch code reads (written to the L2 cache only) that have any type of response.", - "Counter": "0,1,2,3", - "EventCode": "0XB7", - "EventName": "OCR.HWPF_L2_CODE_RD.ANY_RESPONSE", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x10040", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts L2 cache hardware prefetch code reads (written to the L2 cache only) that were supplied by DRAM.", - "Counter": "0,1,2,3", - "EventCode": "0XB7", - "EventName": "OCR.HWPF_L2_CODE_RD.DRAM", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x184000040", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts L2 cache hardware prefetch code reads (written to the L2 cache only) that were supplied by DRAM.", - "Counter": "0,1,2,3", - "EventCode": "0XB7", - "EventName": "OCR.HWPF_L2_CODE_RD.LOCAL_DRAM", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x184000040", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts L2 cache hardware prefetch code reads (written to the L2 cache only) that have an outstanding request. Returns the number of cycles until the response is received (i.e. XQ to XQ latency).", - "Counter": "0,1,2,3", - "EventCode": "0XB7", - "EventName": "OCR.HWPF_L2_CODE_RD.OUTSTANDING", - "MSRIndex": "0x1a6", - "MSRValue": "0x8000000000000040", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts L2 cache hardware prefetch data reads (written to the L2 cache only) that have any type of response.", - "Counter": "0,1,2,3", - "EventCode": "0XB7", - "EventName": "OCR.HWPF_L2_DATA_RD.ANY_RESPONSE", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x10010", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts L2 cache hardware prefetch data reads (written to the L2 cache only) that were supplied by DRAM.", - "Counter": "0,1,2,3", - "EventCode": "0XB7", - "EventName": "OCR.HWPF_L2_DATA_RD.DRAM", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x184000010", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts L2 cache hardware prefetch data reads (written to the L2 cache only) that were supplied by DRAM.", - "Counter": "0,1,2,3", - "EventCode": "0XB7", - "EventName": "OCR.HWPF_L2_DATA_RD.LOCAL_DRAM", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x184000010", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts L2 cache hardware prefetch RFOs (written to the L2 cache only) that have any type of response.", - "Counter": "0,1,2,3", - "EventCode": "0XB7", - "EventName": "OCR.HWPF_L2_RFO.ANY_RESPONSE", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x10020", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts L2 cache hardware prefetch RFOs (written to the L2 cache only) that were supplied by DRAM.", - "Counter": "0,1,2,3", - "EventCode": "0XB7", - "EventName": "OCR.HWPF_L2_RFO.DRAM", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x184000020", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts L2 cache hardware prefetch RFOs (written to the L2 cache only) that were supplied by DRAM.", - "Counter": "0,1,2,3", - "EventCode": "0XB7", - "EventName": "OCR.HWPF_L2_RFO.LOCAL_DRAM", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x184000020", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts L2 cache hardware prefetch RFOs (written to the L2 cache only) that have an outstanding request. Returns the number of cycles until the response is received (i.e. XQ to XQ latency).", - "Counter": "0,1,2,3", - "EventCode": "0XB7", - "EventName": "OCR.HWPF_L2_RFO.OUTSTANDING", - "MSRIndex": "0x1a6", - "MSRValue": "0x8000000000000020", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts modified writebacks from L1 cache that miss the L2 cache that have any type of response.", - "Counter": "0,1,2,3", - "EventCode": "0XB7", - "EventName": "OCR.L1WB_M.ANY_RESPONSE", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x1000000010000", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts modified writeBacks from L2 cache that miss the L3 cache that have any type of response.", - "Counter": "0,1,2,3", - "EventCode": "0XB7", - "EventName": "OCR.L2WB_M.ANY_RESPONSE", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x2000000010000", + "PublicDescription": "Counts streaming stores which modify a full 64 byte cacheline that have any type of response. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -477,6 +146,7 @@ "EventName": "OCR.OTHER.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x18000", + "PublicDescription": "Counts miscellaneous requests, such as I/O accesses, that have any type of response. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -487,6 +157,7 @@ "EventName": "OCR.PARTIAL_STREAMING_WR.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x400000010000", + "PublicDescription": "Counts streaming stores which modify only part of a 64 byte cacheline that have any type of response. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -497,46 +168,7 @@ "EventName": "OCR.PREFETCHES.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x10470", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts all data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that have any type of response.", - "Counter": "0,1,2,3", - "EventCode": "0XB7", - "EventName": "OCR.READS_TO_CORE.ANY_RESPONSE", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x10477", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts all data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by DRAM.", - "Counter": "0,1,2,3", - "EventCode": "0XB7", - "EventName": "OCR.READS_TO_CORE.DRAM", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x184000477", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts all data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by DRAM.", - "Counter": "0,1,2,3", - "EventCode": "0XB7", - "EventName": "OCR.READS_TO_CORE.LOCAL_DRAM", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x184000477", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts all data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that have an outstanding request. Returns the number of cycles until the response is received (i.e. XQ to XQ latency).", - "Counter": "0,1,2,3", - "EventCode": "0XB7", - "EventName": "OCR.READS_TO_CORE.OUTSTANDING", - "MSRIndex": "0x1a6", - "MSRValue": "0x8000000000000477", + "PublicDescription": "Counts all hardware and software prefetches that have any type of response. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -547,6 +179,7 @@ "EventName": "OCR.STREAMING_WR.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x10800", + "PublicDescription": "Counts streaming stores that have any type of response. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -557,26 +190,7 @@ "EventName": "OCR.UC_RD.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x100000010000", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts uncached memory reads that were supplied by DRAM.", - "Counter": "0,1,2,3", - "EventCode": "0XB7", - "EventName": "OCR.UC_RD.DRAM", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x100184000000", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts uncached memory reads that were supplied by DRAM.", - "Counter": "0,1,2,3", - "EventCode": "0XB7", - "EventName": "OCR.UC_RD.LOCAL_DRAM", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x100184000000", + "PublicDescription": "Counts uncached memory reads that have any type of response. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -587,6 +201,7 @@ "EventName": "OCR.UC_RD.OUTSTANDING", "MSRIndex": "0x1a6", "MSRValue": "0x8000100000000000", + "PublicDescription": "Counts uncached memory reads that have an outstanding request. Returns the number of cycles until the response is received (i.e. XQ to XQ latency). Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -597,6 +212,7 @@ "EventName": "OCR.UC_WR.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7", "MSRValue": "0x200000010000", + "PublicDescription": "Counts uncached memory writes that have any type of response. Available PDIST counters: 0", "SampleAfterValue": "100003", "UMask": "0x1" } diff --git a/tools/perf/pmu-events/arch/x86/snowridgex/pipeline.json b/tools/perf/pmu-events/arch/x86/snowridgex/pipeline.json index e4e7902c1162..0fc2e821b14a 100644 --- a/tools/perf/pmu-events/arch/x86/snowridgex/pipeline.json +++ b/tools/perf/pmu-events/arch/x86/snowridgex/pipeline.json @@ -5,7 +5,7 @@ "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.ALL_BRANCHES", "PEBS": "1", - "PublicDescription": "Counts the total number of instructions in which the instruction pointer (IP) of the processor is resteered due to a branch instruction and the branch instruction successfully retires. All branch type instructions are accounted for.", + "PublicDescription": "Counts the total number of instructions in which the instruction pointer (IP) of the processor is resteered due to a branch instruction and the branch instruction successfully retires. All branch type instructions are accounted for. Available PDIST counters: 0", "SampleAfterValue": "200003" }, { @@ -14,6 +14,7 @@ "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.CALL", "PEBS": "1", + "PublicDescription": "Counts the number of near CALL branch instructions retired. Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0xf9" }, @@ -23,6 +24,7 @@ "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.FAR_BRANCH", "PEBS": "1", + "PublicDescription": "Counts the number of far branch instructions retired, includes far jump, far call and return, and interrupt call and return. Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0xbf" }, @@ -32,6 +34,7 @@ "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.IND_CALL", "PEBS": "1", + "PublicDescription": "Counts the number of near indirect CALL branch instructions retired. Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0xfb" }, @@ -41,6 +44,7 @@ "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.JCC", "PEBS": "1", + "PublicDescription": "Counts the number of retired JCC (Jump on Conditional Code) branch instructions retired, includes both taken and not taken branches. Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0x7e" }, @@ -50,6 +54,7 @@ "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.NON_RETURN_IND", "PEBS": "1", + "PublicDescription": "Counts the number of near indirect JMP and near indirect CALL branch instructions retired. Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0xeb" }, @@ -59,6 +64,7 @@ "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.REL_CALL", "PEBS": "1", + "PublicDescription": "Counts the number of near relative CALL branch instructions retired. Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0xfd" }, @@ -68,6 +74,7 @@ "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.RETURN", "PEBS": "1", + "PublicDescription": "Counts the number of near RET branch instructions retired. Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0xf7" }, @@ -77,6 +84,7 @@ "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.TAKEN_JCC", "PEBS": "1", + "PublicDescription": "Counts the number of taken JCC (Jump on Conditional Code) branch instructions retired. Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0xfe" }, @@ -86,7 +94,7 @@ "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.ALL_BRANCHES", "PEBS": "1", - "PublicDescription": "Counts the total number of mispredicted branch instructions retired. All branch type instructions are accounted for. Prediction of the branch target address enables the processor to begin executing instructions before the non-speculative execution path is known. The branch prediction unit (BPU) predicts the target address based on the instruction pointer (IP) of the branch and on the execution path through which execution reached this IP. A branch misprediction occurs when the prediction is wrong, and results in discarding all instructions executed in the speculative path and re-fetching from the correct path.", + "PublicDescription": "Counts the total number of mispredicted branch instructions retired. All branch type instructions are accounted for. Prediction of the branch target address enables the processor to begin executing instructions before the non-speculative execution path is known. The branch prediction unit (BPU) predicts the target address based on the instruction pointer (IP) of the branch and on the execution path through which execution reached this IP. A branch misprediction occurs when the prediction is wrong, and results in discarding all instructions executed in the speculative path and re-fetching from the correct path. Available PDIST counters: 0", "SampleAfterValue": "200003" }, { @@ -95,6 +103,7 @@ "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.IND_CALL", "PEBS": "1", + "PublicDescription": "Counts the number of mispredicted near indirect CALL branch instructions retired. Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0xfb" }, @@ -104,6 +113,7 @@ "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.JCC", "PEBS": "1", + "PublicDescription": "Counts the number of mispredicted JCC (Jump on Conditional Code) branch instructions retired. Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0x7e" }, @@ -113,6 +123,7 @@ "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.NON_RETURN_IND", "PEBS": "1", + "PublicDescription": "Counts the number of mispredicted near indirect JMP and near indirect CALL branch instructions retired. Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0xeb" }, @@ -122,6 +133,7 @@ "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.RETURN", "PEBS": "1", + "PublicDescription": "Counts the number of mispredicted near RET branch instructions retired. Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0xf7" }, @@ -131,6 +143,7 @@ "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.TAKEN_JCC", "PEBS": "1", + "PublicDescription": "Counts the number of mispredicted taken JCC (Jump on Conditional Code) branch instructions retired. Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0xfe" }, @@ -206,7 +219,7 @@ "Counter": "Fixed counter 0", "EventName": "INST_RETIRED.ANY", "PEBS": "1", - "PublicDescription": "Counts the total number of instructions that retired. For instructions that consist of multiple uops, this event counts the retirement of the last uop of the instruction. This event continues counting during hardware interrupts, traps, and inside interrupt handlers. This event uses fixed counter 0.", + "PublicDescription": "Counts the total number of instructions that retired. For instructions that consist of multiple uops, this event counts the retirement of the last uop of the instruction. This event continues counting during hardware interrupts, traps, and inside interrupt handlers. This event uses fixed counter 0. Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x1" }, @@ -216,7 +229,7 @@ "EventCode": "0xc0", "EventName": "INST_RETIRED.ANY_P", "PEBS": "1", - "PublicDescription": "Counts the total number of instructions that retired. For instructions that consist of multiple uops, this event counts the retirement of the last uop of the instruction. This event continues counting during hardware interrupts, traps, and inside interrupt handlers. This event uses a programmable general purpose performance counter.", + "PublicDescription": "Counts the total number of instructions that retired. For instructions that consist of multiple uops, this event counts the retirement of the last uop of the instruction. This event continues counting during hardware interrupts, traps, and inside interrupt handlers. This event uses a programmable general purpose performance counter. Available PDIST counters: 0", "SampleAfterValue": "2000003" }, { @@ -225,6 +238,7 @@ "EventCode": "0x03", "EventName": "LD_BLOCKS.4K_ALIAS", "PEBS": "1", + "PublicDescription": "Counts the number of retired loads that are blocked because it initially appears to be store forward blocked, but subsequently is shown not to be blocked based on 4K alias check. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x4" }, @@ -234,6 +248,7 @@ "EventCode": "0x03", "EventName": "LD_BLOCKS.ALL", "PEBS": "1", + "PublicDescription": "Counts the number of retired loads that are blocked for any of the following reasons: DTLB miss, address alias, store forward or data unknown (includes memory disambiguation blocks and ESP consuming load blocks). Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x10" }, @@ -243,6 +258,7 @@ "EventCode": "0x03", "EventName": "LD_BLOCKS.DATA_UNKNOWN", "PEBS": "1", + "PublicDescription": "Counts the number of retired loads that are blocked because its address exactly matches an older store whose data is not ready. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x1" }, @@ -252,6 +268,7 @@ "EventCode": "0x03", "EventName": "LD_BLOCKS.STORE_FORWARD", "PEBS": "1", + "PublicDescription": "Counts the number of retired loads that are blocked because its address partially overlapped with an older store. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x2" }, @@ -464,6 +481,7 @@ "EventCode": "0xc2", "EventName": "TOPDOWN_RETIRING.ALL", "PEBS": "1", + "PublicDescription": "Counts the total number of consumed retirement slots. Available PDIST counters: 0", "SampleAfterValue": "1000003" }, { @@ -480,6 +498,7 @@ "EventCode": "0xc2", "EventName": "UOPS_RETIRED.ALL", "PEBS": "1", + "PublicDescription": "Counts the total number of uops retired. Available PDIST counters: 0", "SampleAfterValue": "2000003" }, { @@ -488,6 +507,7 @@ "EventCode": "0xc2", "EventName": "UOPS_RETIRED.IDIV", "PEBS": "1", + "PublicDescription": "Counts the number of integer divide uops retired. Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x10" }, @@ -497,7 +517,7 @@ "EventCode": "0xc2", "EventName": "UOPS_RETIRED.MS", "PEBS": "1", - "PublicDescription": "Counts the number of uops that are from complex flows issued by the Microcode Sequencer (MS). This includes uops from flows due to complex instructions, faults, assists, and inserted flows.", + "PublicDescription": "Counts the number of uops that are from complex flows issued by the Microcode Sequencer (MS). This includes uops from flows due to complex instructions, faults, assists, and inserted flows. Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x1" }, @@ -507,6 +527,7 @@ "EventCode": "0xc2", "EventName": "UOPS_RETIRED.X87", "PEBS": "1", + "PublicDescription": "Counts the number of x87 uops retired, includes those in MS flows. Available PDIST counters: 0", "SampleAfterValue": "2000003", "UMask": "0x2" } diff --git a/tools/perf/pmu-events/arch/x86/snowridgex/virtual-memory.json b/tools/perf/pmu-events/arch/x86/snowridgex/virtual-memory.json index f9a6caed8776..bf56d72bb4a7 100644 --- a/tools/perf/pmu-events/arch/x86/snowridgex/virtual-memory.json +++ b/tools/perf/pmu-events/arch/x86/snowridgex/virtual-memory.json @@ -242,6 +242,7 @@ "EventCode": "0x03", "EventName": "LD_BLOCKS.DTLB_MISS", "PEBS": "1", + "PublicDescription": "Counts the number of retired loads that are blocked due to a first level TLB miss. Available PDIST counters: 0", "SampleAfterValue": "1000003", "UMask": "0x8" }, @@ -252,6 +253,7 @@ "EventCode": "0xd0", "EventName": "MEM_UOPS_RETIRED.DTLB_MISS", "PEBS": "1", + "PublicDescription": "Counts the number of memory uops retired that missed in the second level TLB. Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0x13" }, @@ -262,6 +264,7 @@ "EventCode": "0xd0", "EventName": "MEM_UOPS_RETIRED.DTLB_MISS_LOADS", "PEBS": "1", + "PublicDescription": "Counts the number of load uops retired that miss in the second Level TLB. Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0x11" }, @@ -272,6 +275,7 @@ "EventCode": "0xd0", "EventName": "MEM_UOPS_RETIRED.DTLB_MISS_STORES", "PEBS": "1", + "PublicDescription": "Counts the number of store uops retired that miss in the second level TLB. Available PDIST counters: 0", "SampleAfterValue": "200003", "UMask": "0x12" } diff --git a/tools/perf/pmu-events/arch/x86/tigerlake/tgl-metrics.json b/tools/perf/pmu-events/arch/x86/tigerlake/tgl-metrics.json index 8c0cd6e63a2a..2db7a70f7a07 100644 --- a/tools/perf/pmu-events/arch/x86/tigerlake/tgl-metrics.json +++ b/tools/perf/pmu-events/arch/x86/tigerlake/tgl-metrics.json @@ -89,12 +89,12 @@ "MetricExpr": "LD_BLOCKS_PARTIAL.ADDRESS_ALIAS / tma_info_thread_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group", "MetricName": "tma_4k_aliasing", - "MetricThreshold": "tma_4k_aliasing > 0.2 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", - "PublicDescription": "This metric estimates how often memory load accesses were aliased by preceding stores (in program order) with a 4K address offset. False match is possible; which incur a few cycles load re-issue. However; the short re-issue duration is often hidden by the out-of-order core and HW optimizations; hence a user may safely ignore a high value of this metric unless it manages to propagate up into parent nodes of the hierarchy (e.g. to L1_Bound)", + "MetricThreshold": "tma_4k_aliasing > 0.2 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric estimates how often memory load accesses were aliased by preceding stores (in program order) with a 4K address offset. False match is possible; which incur a few cycles load re-issue. However; the short re-issue duration is often hidden by the out-of-order core and HW optimizations; hence a user may safely ignore a high value of this metric unless it manages to propagate up into parent nodes of the hierarchy (e.g. to L1_Bound).", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution ports for ALU operations", + "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution ports for ALU operations.", "MetricExpr": "(UOPS_DISPATCHED.PORT_0 + UOPS_DISPATCHED.PORT_1 + UOPS_DISPATCHED.PORT_5 + UOPS_DISPATCHED.PORT_6) / (4 * tma_info_core_core_clks)", "MetricGroup": "TopdownL5;tma_L5_group;tma_ports_utilized_3m_group", "MetricName": "tma_alu_op_utilization", @@ -106,7 +106,7 @@ "MetricExpr": "34 * ASSISTS.ANY / tma_info_thread_slots", "MetricGroup": "BvIO;TopdownL4;tma_L4_group;tma_microcode_sequencer_group", "MetricName": "tma_assists", - "MetricThreshold": "tma_assists > 0.1 & tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1", + "MetricThreshold": "tma_assists > 0.1 & (tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1)", "PublicDescription": "This metric estimates fraction of slots the CPU retired uops delivered by the Microcode_Sequencer as a result of Assists. Assists are long sequences of uops that are required in certain corner-cases for operations that cannot be handled natively by the execution pipeline. For example; when working with very small floating point values (so-called Denormals); the FP units are not set up to perform these operations natively. Instead; a sequence of instructions to perform the computation on the Denormals is injected into the pipeline. Since these microcode sequences might be dozens of uops long; Assists can be extremely deleterious to performance and they can be avoided in many cases. Sample with: ASSISTS.ANY", "ScaleUnit": "100%" }, @@ -129,12 +129,12 @@ "MetricName": "tma_bad_speculation", "MetricThreshold": "tma_bad_speculation > 0.15", "MetricgroupNoGroup": "TopdownL1;Default", - "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example", + "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.", "ScaleUnit": "100%" }, { "BriefDescription": "Total pipeline cost of instruction fetch related bottlenecks by large code footprint programs (i-side cache; TLB and BTB misses)", - "MetricExpr": "100 * tma_fetch_latency * (tma_itlb_misses + tma_icache_misses + tma_unknown_branches) / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches)", + "MetricExpr": "100 * tma_fetch_latency * (tma_itlb_misses + tma_icache_misses + tma_unknown_branches) / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches)", "MetricGroup": "BigFootprint;BvBC;Fed;Frontend;IcMiss;MemoryTLB", "MetricName": "tma_bottleneck_big_code", "MetricThreshold": "tma_bottleneck_big_code > 20" @@ -149,7 +149,7 @@ }, { "BriefDescription": "Total pipeline cost of external Memory- or Cache-Bandwidth related bottlenecks", - "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_mem_bandwidth / (tma_mem_bandwidth + tma_mem_latency)) + tma_memory_bound * (tma_l3_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_sq_full / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_memory_bound * (tma_l1_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_fb_full / (tma_dtlb_load + tma_store_fwd_blk + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_4k_aliasing + tma_fb_full)))", + "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_mem_bandwidth / (tma_mem_bandwidth + tma_mem_latency)) + tma_memory_bound * (tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_sq_full / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_fb_full / (tma_4k_aliasing + tma_dtlb_load + tma_fb_full + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)))", "MetricGroup": "BvMB;Mem;MemoryBW;Offcore;tma_issueBW", "MetricName": "tma_bottleneck_cache_memory_bandwidth", "MetricThreshold": "tma_bottleneck_cache_memory_bandwidth > 20", @@ -157,7 +157,7 @@ }, { "BriefDescription": "Total pipeline cost of external Memory- or Cache-Latency related bottlenecks", - "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_mem_latency / (tma_mem_bandwidth + tma_mem_latency)) + tma_memory_bound * (tma_l3_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_l3_hit_latency / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_memory_bound * tma_l2_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound) + tma_memory_bound * (tma_l1_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_l1_latency_dependency / (tma_dtlb_load + tma_store_fwd_blk + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_4k_aliasing + tma_fb_full)) + tma_memory_bound * (tma_l1_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_lock_latency / (tma_dtlb_load + tma_store_fwd_blk + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_4k_aliasing + tma_fb_full)) + tma_memory_bound * (tma_l1_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_split_loads / (tma_dtlb_load + tma_store_fwd_blk + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_4k_aliasing + tma_fb_full)) + tma_memory_bound * (tma_store_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_split_stores / (tma_store_latency + tma_false_sharing + tma_split_stores + tma_streaming_stores + tma_dtlb_store)) + tma_memory_bound * (tma_store_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_store_latency / (tma_store_latency + tma_false_sharing + tma_split_stores + tma_streaming_stores + tma_dtlb_store)))", + "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_mem_latency / (tma_mem_bandwidth + tma_mem_latency)) + tma_memory_bound * (tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_l3_hit_latency / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_memory_bound * tma_l2_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) + tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_l1_latency_dependency / (tma_4k_aliasing + tma_dtlb_load + tma_fb_full + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_lock_latency / (tma_4k_aliasing + tma_dtlb_load + tma_fb_full + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_split_loads / (tma_4k_aliasing + tma_dtlb_load + tma_fb_full + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_memory_bound * (tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_split_stores / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency + tma_streaming_stores)) + tma_memory_bound * (tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_store_latency / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency + tma_streaming_stores)))", "MetricGroup": "BvML;Mem;MemoryLat;Offcore;tma_issueLat", "MetricName": "tma_bottleneck_cache_memory_latency", "MetricThreshold": "tma_bottleneck_cache_memory_latency > 20", @@ -165,22 +165,22 @@ }, { "BriefDescription": "Total pipeline cost when the execution is compute-bound - an estimation", - "MetricExpr": "100 * (tma_core_bound * tma_divider / (tma_divider + tma_serializing_operation + tma_ports_utilization) + tma_core_bound * (tma_ports_utilization / (tma_divider + tma_serializing_operation + tma_ports_utilization)) * (tma_ports_utilized_3m / (tma_ports_utilized_0 + tma_ports_utilized_1 + tma_ports_utilized_2 + tma_ports_utilized_3m)))", + "MetricExpr": "100 * (tma_core_bound * tma_divider / (tma_divider + tma_ports_utilization + tma_serializing_operation) + tma_core_bound * (tma_ports_utilization / (tma_divider + tma_ports_utilization + tma_serializing_operation)) * (tma_ports_utilized_3m / (tma_ports_utilized_0 + tma_ports_utilized_1 + tma_ports_utilized_2 + tma_ports_utilized_3m)))", "MetricGroup": "BvCB;Cor;tma_issueComp", "MetricName": "tma_bottleneck_compute_bound_est", "MetricThreshold": "tma_bottleneck_compute_bound_est > 20", - "PublicDescription": "Total pipeline cost when the execution is compute-bound - an estimation. Covers Core Bound when High ILP as well as when long-latency execution units are busy" + "PublicDescription": "Total pipeline cost when the execution is compute-bound - an estimation. Covers Core Bound when High ILP as well as when long-latency execution units are busy. Related metrics: " }, { "BriefDescription": "Total pipeline cost of instruction fetch bandwidth related bottlenecks (when the front-end could not sustain operations delivery to the back-end)", - "MetricExpr": "100 * (tma_frontend_bound - (1 - 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts) * tma_fetch_latency * tma_mispredicts_resteers / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches) - tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * (tma_fetch_latency * (tma_ms_switches + tma_branch_resteers * (tma_clears_resteers + 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts * tma_mispredicts_resteers) / (tma_mispredicts_resteers + tma_clears_resteers + tma_unknown_branches)) / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches) + tma_fetch_bandwidth * tma_ms / (tma_mite + tma_dsb + tma_lsd + tma_ms))) - tma_bottleneck_big_code", + "MetricExpr": "100 * (tma_frontend_bound - (1 - 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts) * tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) - tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * (tma_fetch_latency * (tma_ms_switches + tma_branch_resteers * (tma_clears_resteers + 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts * tma_mispredicts_resteers) / (tma_clears_resteers + tma_mispredicts_resteers + tma_unknown_branches)) / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) + tma_fetch_bandwidth * tma_ms / (tma_dsb + tma_lsd + tma_mite + tma_ms))) - tma_bottleneck_big_code", "MetricGroup": "BvFB;Fed;FetchBW;Frontend", "MetricName": "tma_bottleneck_instruction_fetch_bw", "MetricThreshold": "tma_bottleneck_instruction_fetch_bw > 20" }, { "BriefDescription": "Total pipeline cost of irregular execution (e.g", - "MetricExpr": "100 * (tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * (tma_fetch_latency * (tma_ms_switches + tma_branch_resteers * (tma_clears_resteers + 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts * tma_mispredicts_resteers) / (tma_mispredicts_resteers + tma_clears_resteers + tma_unknown_branches)) / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches) + tma_fetch_bandwidth * tma_ms / (tma_mite + tma_dsb + tma_lsd + tma_ms)) + 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts * tma_branch_mispredicts + tma_machine_clears * tma_other_nukes / tma_other_nukes + tma_core_bound * (tma_serializing_operation + tma_core_bound * RS_EVENTS.EMPTY_CYCLES / tma_info_thread_clks * tma_ports_utilized_0) / (tma_divider + tma_serializing_operation + tma_ports_utilization) + tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * tma_heavy_operations)", + "MetricExpr": "100 * (tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * (tma_fetch_latency * (tma_ms_switches + tma_branch_resteers * (tma_clears_resteers + 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts * tma_mispredicts_resteers) / (tma_clears_resteers + tma_mispredicts_resteers + tma_unknown_branches)) / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) + tma_fetch_bandwidth * tma_ms / (tma_dsb + tma_lsd + tma_mite + tma_ms)) + 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts * tma_branch_mispredicts + tma_machine_clears * tma_other_nukes / tma_other_nukes + tma_core_bound * (tma_serializing_operation + tma_core_bound * RS_EVENTS.EMPTY_CYCLES / tma_info_thread_clks * tma_ports_utilized_0) / (tma_divider + tma_ports_utilization + tma_serializing_operation) + tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * tma_heavy_operations)", "MetricGroup": "Bad;BvIO;Cor;Ret;tma_issueMS", "MetricName": "tma_bottleneck_irregular_overhead", "MetricThreshold": "tma_bottleneck_irregular_overhead > 10", @@ -188,7 +188,7 @@ }, { "BriefDescription": "Total pipeline cost of Memory Address Translation related bottlenecks (data-side TLBs)", - "MetricExpr": "100 * (tma_memory_bound * (tma_l1_bound / max(tma_memory_bound, tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_dtlb_load / max(tma_l1_bound, tma_dtlb_load + tma_store_fwd_blk + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_4k_aliasing + tma_fb_full)) + tma_memory_bound * (tma_store_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_dtlb_store / (tma_store_latency + tma_false_sharing + tma_split_stores + tma_streaming_stores + tma_dtlb_store)))", + "MetricExpr": "100 * (tma_memory_bound * (tma_l1_bound / max(tma_memory_bound, tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_dtlb_load / max(tma_l1_bound, tma_4k_aliasing + tma_dtlb_load + tma_fb_full + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_memory_bound * (tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_dtlb_store / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency + tma_streaming_stores)))", "MetricGroup": "BvMT;Mem;MemoryTLB;Offcore;tma_issueTLB", "MetricName": "tma_bottleneck_memory_data_tlbs", "MetricThreshold": "tma_bottleneck_memory_data_tlbs > 20", @@ -196,15 +196,15 @@ }, { "BriefDescription": "Total pipeline cost of Memory Synchronization related bottlenecks (data transfers and coherency updates across processors)", - "MetricExpr": "100 * (tma_memory_bound * (tma_l3_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound) * (tma_contested_accesses + tma_data_sharing) / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full) + tma_store_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound) * tma_false_sharing / (tma_store_latency + tma_false_sharing + tma_split_stores + tma_streaming_stores + tma_dtlb_store - tma_store_latency)) + tma_machine_clears * (1 - tma_other_nukes / tma_other_nukes))", + "MetricExpr": "100 * (tma_memory_bound * (tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_contested_accesses + tma_data_sharing) / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full) + tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * tma_false_sharing / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency + tma_streaming_stores - tma_store_latency)) + tma_machine_clears * (1 - tma_other_nukes / tma_other_nukes))", "MetricGroup": "BvMS;LockCont;Mem;Offcore;tma_issueSyncxn", "MetricName": "tma_bottleneck_memory_synchronization", "MetricThreshold": "tma_bottleneck_memory_synchronization > 10", - "PublicDescription": "Total pipeline cost of Memory Synchronization related bottlenecks (data transfers and coherency updates across processors). Related metrics: tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_machine_clears" + "PublicDescription": "Total pipeline cost of Memory Synchronization related bottlenecks (data transfers and coherency updates across processors). Related metrics: tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_machine_clears, tma_remote_cache" }, { "BriefDescription": "Total pipeline cost of Branch Misprediction related bottlenecks", - "MetricExpr": "100 * (1 - 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts) * (tma_branch_mispredicts + tma_fetch_latency * tma_mispredicts_resteers / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches))", + "MetricExpr": "100 * (1 - 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts) * (tma_branch_mispredicts + tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches))", "MetricGroup": "Bad;BadSpec;BrMispredicts;BvMP;tma_issueBM", "MetricName": "tma_bottleneck_mispredictions", "MetricThreshold": "tma_bottleneck_mispredictions > 20", @@ -216,17 +216,17 @@ "MetricGroup": "BvOB;Cor;Offcore", "MetricName": "tma_bottleneck_other_bottlenecks", "MetricThreshold": "tma_bottleneck_other_bottlenecks > 20", - "PublicDescription": "Total pipeline cost of remaining bottlenecks in the back-end. Examples include data-dependencies (Core Bound when Low ILP) and other unlisted memory-related stalls" + "PublicDescription": "Total pipeline cost of remaining bottlenecks in the back-end. Examples include data-dependencies (Core Bound when Low ILP) and other unlisted memory-related stalls." }, { - "BriefDescription": "Total pipeline cost of \"useful operations\" - the portion of Retiring category not covered by Branching_Overhead nor Irregular_Overhead", + "BriefDescription": "Total pipeline cost of \"useful operations\" - the portion of Retiring category not covered by Branching_Overhead nor Irregular_Overhead.", "MetricExpr": "100 * (tma_retiring - (BR_INST_RETIRED.ALL_BRANCHES + 2 * BR_INST_RETIRED.NEAR_CALL + INST_RETIRED.NOP) / tma_info_thread_slots - tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * tma_heavy_operations)", "MetricGroup": "BvUW;Ret", "MetricName": "tma_bottleneck_useful_work", "MetricThreshold": "tma_bottleneck_useful_work > 20" }, { - "BriefDescription": "This metric represents fraction of slots where the CPU was retiring branch instructions", + "BriefDescription": "This metric represents fraction of slots where the CPU was retiring branch instructions.", "MetricExpr": "tma_light_operations * BR_INST_RETIRED.ALL_BRANCHES / (tma_retiring * tma_info_thread_slots)", "MetricGroup": "Branches;BvBO;Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group", "MetricName": "tma_branch_instructions", @@ -248,8 +248,8 @@ "MetricExpr": "INT_MISC.CLEAR_RESTEER_CYCLES / tma_info_thread_clks + tma_unknown_branches", "MetricGroup": "FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group", "MetricName": "tma_branch_resteers", - "MetricThreshold": "tma_branch_resteers > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", - "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers. Branch Resteers estimates the Frontend delay in fetching operations from corrected path; following all sorts of miss-predicted branches. For example; branchy code with lots of miss-predictions might get categorized under Branch Resteers. Note the value of this node may overlap with its siblings. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_l3_hit_latency, tma_store_latency", + "MetricThreshold": "tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers. Branch Resteers estimates the Frontend delay in fetching operations from corrected path; following all sorts of miss-predicted branches. For example; branchy code with lots of miss-predictions might get categorized under Branch Resteers. Note the value of this node may overlap with its siblings. Sample with: BR_MISP_RETIRED.ALL_BRANCHES", "ScaleUnit": "100%" }, { @@ -257,8 +257,8 @@ "MetricExpr": "max(0, tma_microcode_sequencer - tma_assists)", "MetricGroup": "TopdownL4;tma_L4_group;tma_microcode_sequencer_group", "MetricName": "tma_cisc", - "MetricThreshold": "tma_cisc > 0.1 & tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1", - "PublicDescription": "This metric estimates fraction of cycles the CPU retired uops originated from CISC (complex instruction set computer) instruction. A CISC instruction has multiple uops that are required to perform the instruction's functionality as in the case of read-modify-write as an example. Since these instructions require multiple uops they may or may not imply sub-optimal use of machine resources", + "MetricThreshold": "tma_cisc > 0.1 & (tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1)", + "PublicDescription": "This metric estimates fraction of cycles the CPU retired uops originated from CISC (complex instruction set computer) instruction. A CISC instruction has multiple uops that are required to perform the instruction's functionality as in the case of read-modify-write as an example. Since these instructions require multiple uops they may or may not imply sub-optimal use of machine resources.", "ScaleUnit": "100%" }, { @@ -266,24 +266,24 @@ "MetricExpr": "(1 - BR_MISP_RETIRED.ALL_BRANCHES / (BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT)) * INT_MISC.CLEAR_RESTEER_CYCLES / tma_info_thread_clks", "MetricGroup": "BadSpec;MachineClears;TopdownL4;tma_L4_group;tma_branch_resteers_group;tma_issueMC", "MetricName": "tma_clears_resteers", - "MetricThreshold": "tma_clears_resteers > 0.05 & tma_branch_resteers > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricThreshold": "tma_clears_resteers > 0.05 & (tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))", "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Machine Clears. Sample with: INT_MISC.CLEAR_RESTEER_CYCLES. Related metrics: tma_l1_bound, tma_machine_clears, tma_microcode_sequencer, tma_ms_switches", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates fraction of cycles the CPU was stalled due to instruction cache misses that hit in the L2 cache", + "BriefDescription": "This metric estimates fraction of cycles the CPU was stalled due to instruction cache misses that hit in the L2 cache.", "MetricExpr": "max(0, tma_icache_misses - tma_code_l2_miss)", "MetricGroup": "FetchLat;IcMiss;Offcore;TopdownL4;tma_L4_group;tma_icache_misses_group", "MetricName": "tma_code_l2_hit", - "MetricThreshold": "tma_code_l2_hit > 0.05 & tma_icache_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricThreshold": "tma_code_l2_hit > 0.05 & (tma_icache_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates fraction of cycles the CPU was stalled due to instruction cache misses that miss in the L2 cache", + "BriefDescription": "This metric estimates fraction of cycles the CPU was stalled due to instruction cache misses that miss in the L2 cache.", "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_CODE_RD / tma_info_thread_clks", "MetricGroup": "FetchLat;IcMiss;Offcore;TopdownL4;tma_L4_group;tma_icache_misses_group", "MetricName": "tma_code_l2_miss", - "MetricThreshold": "tma_code_l2_miss > 0.05 & tma_icache_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricThreshold": "tma_code_l2_miss > 0.05 & (tma_icache_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))", "ScaleUnit": "100%" }, { @@ -291,7 +291,7 @@ "MetricExpr": "max(0, tma_itlb_misses - tma_code_stlb_miss)", "MetricGroup": "FetchLat;MemoryTLB;TopdownL4;tma_L4_group;tma_itlb_misses_group", "MetricName": "tma_code_stlb_hit", - "MetricThreshold": "tma_code_stlb_hit > 0.05 & tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricThreshold": "tma_code_stlb_hit > 0.05 & (tma_itlb_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))", "ScaleUnit": "100%" }, { @@ -299,33 +299,33 @@ "MetricExpr": "ITLB_MISSES.WALK_ACTIVE / tma_info_thread_clks", "MetricGroup": "FetchLat;MemoryTLB;TopdownL4;tma_L4_group;tma_itlb_misses_group", "MetricName": "tma_code_stlb_miss", - "MetricThreshold": "tma_code_stlb_miss > 0.05 & tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricThreshold": "tma_code_stlb_miss > 0.05 & (tma_itlb_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 2 or 4 MB pages for (instruction) code accesses", + "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 2 or 4 MB pages for (instruction) code accesses.", "MetricExpr": "tma_code_stlb_miss * ITLB_MISSES.WALK_COMPLETED_2M_4M / (ITLB_MISSES.WALK_COMPLETED_4K + ITLB_MISSES.WALK_COMPLETED_2M_4M)", "MetricGroup": "FetchLat;MemoryTLB;TopdownL5;tma_L5_group;tma_code_stlb_miss_group", "MetricName": "tma_code_stlb_miss_2m", - "MetricThreshold": "tma_code_stlb_miss_2m > 0.05 & tma_code_stlb_miss > 0.05 & tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricThreshold": "tma_code_stlb_miss_2m > 0.05 & (tma_code_stlb_miss > 0.05 & (tma_itlb_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)))", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 4 KB pages for (instruction) code accesses", + "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 4 KB pages for (instruction) code accesses.", "MetricExpr": "tma_code_stlb_miss * ITLB_MISSES.WALK_COMPLETED_4K / (ITLB_MISSES.WALK_COMPLETED_4K + ITLB_MISSES.WALK_COMPLETED_2M_4M)", "MetricGroup": "FetchLat;MemoryTLB;TopdownL5;tma_L5_group;tma_code_stlb_miss_group", "MetricName": "tma_code_stlb_miss_4k", - "MetricThreshold": "tma_code_stlb_miss_4k > 0.05 & tma_code_stlb_miss > 0.05 & tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricThreshold": "tma_code_stlb_miss_4k > 0.05 & (tma_code_stlb_miss > 0.05 & (tma_itlb_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)))", "ScaleUnit": "100%" }, { "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses", "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "((54 * tma_info_system_core_frequency - 5 * tma_info_system_core_frequency) * (MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD * (OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM / (OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM + OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD))) + (53 * tma_info_system_core_frequency - 5 * tma_info_system_core_frequency) * MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks", + "MetricExpr": "(49 * tma_info_system_core_frequency * (MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD * (OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM / (OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM + OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD))) + 48 * tma_info_system_core_frequency * MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks", "MetricGroup": "BvMS;DataSharing;LockCont;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group", "MetricName": "tma_contested_accesses", - "MetricThreshold": "tma_contested_accesses > 0.05 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", - "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses. Contested accesses occur when data written by one Logical Processor are read by another Logical Processor on a different Physical Core. Examples of contested accesses include synchronizations such as locks; true data sharing such as modified locked variables; and false sharing. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD, MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS. Related metrics: tma_bottleneck_memory_synchronization, tma_data_sharing, tma_false_sharing, tma_machine_clears", + "MetricThreshold": "tma_contested_accesses > 0.05 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses. Contested accesses occur when data written by one Logical Processor are read by another Logical Processor on a different Physical Core. Examples of contested accesses include synchronizations such as locks; true data sharing such as modified locked variables; and false sharing. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD;MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS. Related metrics: tma_bottleneck_memory_synchronization, tma_data_sharing, tma_false_sharing, tma_machine_clears, tma_remote_cache", "ScaleUnit": "100%" }, { @@ -335,25 +335,25 @@ "MetricName": "tma_core_bound", "MetricThreshold": "tma_core_bound > 0.1 & tma_backend_bound > 0.2", "MetricgroupNoGroup": "TopdownL2", - "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck. Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations)", + "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck. Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations).", "ScaleUnit": "100%" }, { "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses", "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "(53 * tma_info_system_core_frequency - 5 * tma_info_system_core_frequency) * (MEM_LOAD_L3_HIT_RETIRED.XSNP_NO_FWD + MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD * (1 - OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM / (OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM + OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD))) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks", + "MetricExpr": "48 * tma_info_system_core_frequency * (MEM_LOAD_L3_HIT_RETIRED.XSNP_NO_FWD + MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD * (1 - OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM / (OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM + OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD))) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks", "MetricGroup": "BvMS;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group", "MetricName": "tma_data_sharing", - "MetricThreshold": "tma_data_sharing > 0.05 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", - "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses. Data shared by multiple Logical Processors (even just read shared) may cause increased access latency due to cache coherency. Excessive data sharing can drastically harm multithreaded performance. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_NO_FWD. Related metrics: tma_bottleneck_memory_synchronization, tma_contested_accesses, tma_false_sharing, tma_machine_clears", + "MetricThreshold": "tma_data_sharing > 0.05 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses. Data shared by multiple Logical Processors (even just read shared) may cause increased access latency due to cache coherency. Excessive data sharing can drastically harm multithreaded performance. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_NO_FWD. Related metrics: tma_bottleneck_memory_synchronization, tma_contested_accesses, tma_false_sharing, tma_machine_clears, tma_remote_cache", "ScaleUnit": "100%" }, { "BriefDescription": "This metric represents fraction of cycles where decoder-0 was the only active decoder", - "MetricExpr": "(cpu@INST_DECODED.DECODERS\\,cmask\\=0x1@ - cpu@INST_DECODED.DECODERS\\,cmask\\=0x2@) / tma_info_core_core_clks / 2", + "MetricExpr": "(cpu@INST_DECODED.DECODERS\\,cmask\\=1@ - cpu@INST_DECODED.DECODERS\\,cmask\\=2@) / tma_info_core_core_clks / 2", "MetricGroup": "DSBmiss;FetchBW;TopdownL4;tma_L4_group;tma_issueD0;tma_mite_group", "MetricName": "tma_decoder0_alone", - "MetricThreshold": "tma_decoder0_alone > 0.1 & tma_mite > 0.1 & tma_fetch_bandwidth > 0.2", + "MetricThreshold": "tma_decoder0_alone > 0.1 & (tma_mite > 0.1 & tma_fetch_bandwidth > 0.2)", "PublicDescription": "This metric represents fraction of cycles where decoder-0 was the only active decoder. Related metrics: tma_few_uops_instructions", "ScaleUnit": "100%" }, @@ -362,7 +362,7 @@ "MetricExpr": "ARITH.DIVIDER_ACTIVE / tma_info_thread_clks", "MetricGroup": "BvCB;TopdownL3;tma_L3_group;tma_core_bound_group", "MetricName": "tma_divider", - "MetricThreshold": "tma_divider > 0.2 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_divider > 0.2 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)", "PublicDescription": "This metric represents fraction of cycles where the Divider unit was active. Divide and square root instructions are performed by the Divider unit and can take considerably longer latency than integer or Floating Point addition; subtraction; or multiplication. Sample with: ARITH.DIVIDER_ACTIVE", "ScaleUnit": "100%" }, @@ -372,7 +372,7 @@ "MetricExpr": "CYCLE_ACTIVITY.STALLS_L3_MISS / tma_info_thread_clks + (CYCLE_ACTIVITY.STALLS_L1D_MISS - CYCLE_ACTIVITY.STALLS_L2_MISS) / tma_info_thread_clks - tma_l2_bound", "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_dram_bound", - "MetricThreshold": "tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", "PublicDescription": "This metric estimates how often the CPU was stalled on accesses to external memory (DRAM) by loads. Better caching can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L3_MISS", "ScaleUnit": "100%" }, @@ -382,7 +382,7 @@ "MetricGroup": "DSB;FetchBW;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group", "MetricName": "tma_dsb", "MetricThreshold": "tma_dsb > 0.15 & tma_fetch_bandwidth > 0.2", - "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to DSB (decoded uop cache) fetch pipeline. For example; inefficient utilization of the DSB cache structure or bank conflict when reading from it; are categorized here", + "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to DSB (decoded uop cache) fetch pipeline. For example; inefficient utilization of the DSB cache structure or bank conflict when reading from it; are categorized here.", "ScaleUnit": "100%" }, { @@ -390,26 +390,26 @@ "MetricExpr": "DSB2MITE_SWITCHES.PENALTY_CYCLES / tma_info_thread_clks", "MetricGroup": "DSBmiss;FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueFB", "MetricName": "tma_dsb_switches", - "MetricThreshold": "tma_dsb_switches > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", - "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines. The DSB (decoded i-cache) is a Uop Cache where the front-end directly delivers Uops (micro operations) avoiding heavy x86 decoding. The DSB pipeline has shorter latency and delivered higher bandwidth than the MITE (legacy instruction decode pipeline). Switching between the two pipelines can cause penalties hence this metric measures the exposed penalty. Sample with: FRONTEND_RETIRED.DSB_MISS. Related metrics: tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp", + "MetricThreshold": "tma_dsb_switches > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines. The DSB (decoded i-cache) is a Uop Cache where the front-end directly delivers Uops (micro operations) avoiding heavy x86 decoding. The DSB pipeline has shorter latency and delivered higher bandwidth than the MITE (legacy instruction decode pipeline). Switching between the two pipelines can cause penalties hence this metric measures the exposed penalty. Sample with: FRONTEND_RETIRED.DSB_MISS_PS. Related metrics: tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp", "ScaleUnit": "100%" }, { "BriefDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses", - "MetricExpr": "min(7 * cpu@DTLB_LOAD_MISSES.STLB_HIT\\,cmask\\=0x1@ + DTLB_LOAD_MISSES.WALK_ACTIVE, max(CYCLE_ACTIVITY.CYCLES_MEM_ANY - CYCLE_ACTIVITY.CYCLES_L1D_MISS, 0)) / tma_info_thread_clks", + "MetricExpr": "min(7 * cpu@DTLB_LOAD_MISSES.STLB_HIT\\,cmask\\=1@ + DTLB_LOAD_MISSES.WALK_ACTIVE, max(CYCLE_ACTIVITY.CYCLES_MEM_ANY - CYCLE_ACTIVITY.CYCLES_L1D_MISS, 0)) / tma_info_thread_clks", "MetricGroup": "BvMT;MemoryTLB;TopdownL4;tma_L4_group;tma_issueTLB;tma_l1_bound_group", "MetricName": "tma_dtlb_load", - "MetricThreshold": "tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", - "PublicDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses. TLBs (Translation Look-aside Buffers) are processor caches for recently used entries out of the Page Tables that are used to map virtual- to physical-addresses by the operating system. This metric approximates the potential delay of demand loads missing the first-level data TLB (assuming worst case scenario with back to back misses to different pages). This includes hitting in the second-level TLB (STLB) as well as performing a hardware page walk on an STLB miss. Sample with: MEM_INST_RETIRED.STLB_MISS_LOADS. Related metrics: tma_bottleneck_memory_data_tlbs, tma_dtlb_store", + "MetricThreshold": "tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses. TLBs (Translation Look-aside Buffers) are processor caches for recently used entries out of the Page Tables that are used to map virtual- to physical-addresses by the operating system. This metric approximates the potential delay of demand loads missing the first-level data TLB (assuming worst case scenario with back to back misses to different pages). This includes hitting in the second-level TLB (STLB) as well as performing a hardware page walk on an STLB miss. Sample with: MEM_INST_RETIRED.STLB_MISS_LOADS_PS. Related metrics: tma_bottleneck_memory_data_tlbs, tma_dtlb_store", "ScaleUnit": "100%" }, { "BriefDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses", - "MetricExpr": "(7 * cpu@DTLB_STORE_MISSES.STLB_HIT\\,cmask\\=0x1@ + DTLB_STORE_MISSES.WALK_ACTIVE) / tma_info_core_core_clks", + "MetricExpr": "(7 * cpu@DTLB_STORE_MISSES.STLB_HIT\\,cmask\\=1@ + DTLB_STORE_MISSES.WALK_ACTIVE) / tma_info_core_core_clks", "MetricGroup": "BvMT;MemoryTLB;TopdownL4;tma_L4_group;tma_issueTLB;tma_store_bound_group", "MetricName": "tma_dtlb_store", - "MetricThreshold": "tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", - "PublicDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses. As with ordinary data caching; focus on improving data locality and reducing working-set size to reduce DTLB overhead. Additionally; consider using profile-guided optimization (PGO) to collocate frequently-used data on the same page. Try using larger page sizes for large amounts of frequently-used data. Sample with: MEM_INST_RETIRED.STLB_MISS_STORES. Related metrics: tma_bottleneck_memory_data_tlbs, tma_dtlb_load", + "MetricThreshold": "tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses. As with ordinary data caching; focus on improving data locality and reducing working-set size to reduce DTLB overhead. Additionally; consider using profile-guided optimization (PGO) to collocate frequently-used data on the same page. Try using larger page sizes for large amounts of frequently-used data. Sample with: MEM_INST_RETIRED.STLB_MISS_STORES_PS. Related metrics: tma_bottleneck_memory_data_tlbs, tma_dtlb_load", "ScaleUnit": "100%" }, { @@ -417,8 +417,8 @@ "MetricExpr": "54 * tma_info_system_core_frequency * OCR.DEMAND_RFO.L3_HIT.SNOOP_HITM / tma_info_thread_clks", "MetricGroup": "BvMS;DataSharing;LockCont;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_store_bound_group", "MetricName": "tma_false_sharing", - "MetricThreshold": "tma_false_sharing > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", - "PublicDescription": "This metric roughly estimates how often CPU was handling synchronizations due to False Sharing. False Sharing is a multithreading hiccup; where multiple Logical Processors contend on different data-elements mapped into the same cache line. Sample with: OCR.DEMAND_RFO.L3_HIT.SNOOP_HITM. Related metrics: tma_bottleneck_memory_synchronization, tma_contested_accesses, tma_data_sharing, tma_machine_clears", + "MetricThreshold": "tma_false_sharing > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric roughly estimates how often CPU was handling synchronizations due to False Sharing. False Sharing is a multithreading hiccup; where multiple Logical Processors contend on different data-elements mapped into the same cache line. Sample with: OCR.DEMAND_RFO.L3_HIT.SNOOP_HITM. Related metrics: tma_bottleneck_memory_synchronization, tma_contested_accesses, tma_data_sharing, tma_machine_clears, tma_remote_cache", "ScaleUnit": "100%" }, { @@ -437,7 +437,7 @@ "MetricName": "tma_fetch_bandwidth", "MetricThreshold": "tma_fetch_bandwidth > 0.2", "MetricgroupNoGroup": "TopdownL2", - "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues. For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Sample with: FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1, FRONTEND_RETIRED.LATENCY_GE_1, FRONTEND_RETIRED.LATENCY_GE_2. Related metrics: tma_dsb_switches, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp", + "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues. For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Sample with: FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1;FRONTEND_RETIRED.LATENCY_GE_1;FRONTEND_RETIRED.LATENCY_GE_2. Related metrics: tma_dsb_switches, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp", "ScaleUnit": "100%" }, { @@ -447,7 +447,7 @@ "MetricName": "tma_fetch_latency", "MetricThreshold": "tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", "MetricgroupNoGroup": "TopdownL2", - "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues. For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: FRONTEND_RETIRED.LATENCY_GE_16, FRONTEND_RETIRED.LATENCY_GE_8", + "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues. For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: FRONTEND_RETIRED.LATENCY_GE_16_PS;FRONTEND_RETIRED.LATENCY_GE_8_PS", "ScaleUnit": "100%" }, { @@ -465,7 +465,7 @@ "MetricGroup": "HPC;TopdownL3;tma_L3_group;tma_light_operations_group", "MetricName": "tma_fp_arith", "MetricThreshold": "tma_fp_arith > 0.2 & tma_light_operations > 0.6", - "PublicDescription": "This metric represents overall arithmetic floating-point (FP) operations fraction the CPU has executed (retired). Note this metric's value may exceed its parent due to use of \"Uops\" CountDomain and FMA double-counting", + "PublicDescription": "This metric represents overall arithmetic floating-point (FP) operations fraction the CPU has executed (retired). Note this metric's value may exceed its parent due to use of \"Uops\" CountDomain and FMA double-counting.", "ScaleUnit": "100%" }, { @@ -474,15 +474,15 @@ "MetricGroup": "HPC;TopdownL5;tma_L5_group;tma_assists_group", "MetricName": "tma_fp_assists", "MetricThreshold": "tma_fp_assists > 0.1", - "PublicDescription": "This metric roughly estimates fraction of slots the CPU retired uops as a result of handing Floating Point (FP) Assists. FP Assist may apply when working with very small floating point values (so-called Denormals)", + "PublicDescription": "This metric roughly estimates fraction of slots the CPU retired uops as a result of handing Floating Point (FP) Assists. FP Assist may apply when working with very small floating point values (so-called Denormals).", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of cycles where the Floating-Point Divider unit was active", + "BriefDescription": "This metric represents fraction of cycles where the Floating-Point Divider unit was active.", "MetricExpr": "ARITH.FP_DIVIDER_ACTIVE / tma_info_thread_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_divider_group", "MetricName": "tma_fp_divider", - "MetricThreshold": "tma_fp_divider > 0.2 & tma_divider > 0.2 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_fp_divider > 0.2 & (tma_divider > 0.2 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", "ScaleUnit": "100%" }, { @@ -490,7 +490,7 @@ "MetricExpr": "FP_ARITH_INST_RETIRED.SCALAR / (tma_retiring * tma_info_thread_slots)", "MetricGroup": "Compute;Flops;TopdownL4;tma_L4_group;tma_fp_arith_group;tma_issue2P", "MetricName": "tma_fp_scalar", - "MetricThreshold": "tma_fp_scalar > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6", + "MetricThreshold": "tma_fp_scalar > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6)", "PublicDescription": "This metric approximates arithmetic floating-point (FP) scalar uops fraction the CPU has retired. May overcount due to FMA double counting. Related metrics: tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%" }, @@ -499,7 +499,7 @@ "MetricExpr": "FP_ARITH_INST_RETIRED.VECTOR / (tma_retiring * tma_info_thread_slots)", "MetricGroup": "Compute;Flops;TopdownL4;tma_L4_group;tma_fp_arith_group;tma_issue2P", "MetricName": "tma_fp_vector", - "MetricThreshold": "tma_fp_vector > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6", + "MetricThreshold": "tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6)", "PublicDescription": "This metric approximates arithmetic floating-point (FP) vector uops fraction the CPU has retired aggregated across all vector widths. May overcount due to FMA double counting. Related metrics: tma_fp_scalar, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%" }, @@ -508,7 +508,7 @@ "MetricExpr": "(FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE) / (tma_retiring * tma_info_thread_slots)", "MetricGroup": "Compute;Flops;TopdownL5;tma_L5_group;tma_fp_vector_group;tma_issue2P", "MetricName": "tma_fp_vector_128b", - "MetricThreshold": "tma_fp_vector_128b > 0.1 & tma_fp_vector > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6", + "MetricThreshold": "tma_fp_vector_128b > 0.1 & (tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6))", "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 128-bit wide vectors. May overcount due to FMA double counting prior to LNL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%" }, @@ -517,7 +517,7 @@ "MetricExpr": "(FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE) / (tma_retiring * tma_info_thread_slots)", "MetricGroup": "Compute;Flops;TopdownL5;tma_L5_group;tma_fp_vector_group;tma_issue2P", "MetricName": "tma_fp_vector_256b", - "MetricThreshold": "tma_fp_vector_256b > 0.1 & tma_fp_vector > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6", + "MetricThreshold": "tma_fp_vector_256b > 0.1 & (tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6))", "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 256-bit wide vectors. May overcount due to FMA double counting prior to LNL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%" }, @@ -526,7 +526,7 @@ "MetricExpr": "(FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE) / (tma_retiring * tma_info_thread_slots)", "MetricGroup": "Compute;Flops;TopdownL5;tma_L5_group;tma_fp_vector_group;tma_issue2P", "MetricName": "tma_fp_vector_512b", - "MetricThreshold": "tma_fp_vector_512b > 0.1 & tma_fp_vector > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6", + "MetricThreshold": "tma_fp_vector_512b > 0.1 & (tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6))", "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 512-bit wide vectors. May overcount due to FMA double counting. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%" }, @@ -538,17 +538,17 @@ "MetricName": "tma_frontend_bound", "MetricThreshold": "tma_frontend_bound > 0.15", "MetricgroupNoGroup": "TopdownL1;Default", - "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound. Sample with: FRONTEND_RETIRED.LATENCY_GE_4", + "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound. Sample with: FRONTEND_RETIRED.LATENCY_GE_4_PS", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations , instructions that require two or more uops or micro-coded sequences", - "MetricExpr": "tma_microcode_sequencer + tma_retiring * (UOPS_DECODED.DEC0 - cpu@UOPS_DECODED.DEC0\\,cmask\\=0x1@) / IDQ.MITE_UOPS", + "BriefDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences", + "MetricExpr": "tma_microcode_sequencer + tma_retiring * (UOPS_DECODED.DEC0 - cpu@UOPS_DECODED.DEC0\\,cmask\\=1@) / IDQ.MITE_UOPS", "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_heavy_operations", "MetricThreshold": "tma_heavy_operations > 0.1", "MetricgroupNoGroup": "TopdownL2", - "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations , instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences.([ICL+] Note this may overcount due to approximation using indirect events; [ADL+])", + "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences.([ICL+] Note this may overcount due to approximation using indirect events; [ADL+])", "ScaleUnit": "100%" }, { @@ -556,8 +556,8 @@ "MetricExpr": "ICACHE_DATA.STALLS / tma_info_thread_clks", "MetricGroup": "BigFootprint;BvBC;FetchLat;IcMiss;TopdownL3;tma_L3_group;tma_fetch_latency_group", "MetricName": "tma_icache_misses", - "MetricThreshold": "tma_icache_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", - "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to instruction cache misses. Sample with: FRONTEND_RETIRED.L2_MISS, FRONTEND_RETIRED.L1I_MISS", + "MetricThreshold": "tma_icache_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to instruction cache misses. Sample with: FRONTEND_RETIRED.L2_MISS_PS;FRONTEND_RETIRED.L1I_MISS_PS", "ScaleUnit": "100%" }, { @@ -569,28 +569,28 @@ "PublicDescription": "Branch Misprediction Cost: Cycles representing fraction of TMA slots wasted per non-speculative branch misprediction (retired JEClear). Related metrics: tma_bottleneck_mispredictions, tma_branch_mispredicts, tma_mispredicts_resteers" }, { - "BriefDescription": "Instructions per retired Mispredicts for conditional non-taken branches (lower number means higher occurrence rate)", + "BriefDescription": "Instructions per retired Mispredicts for conditional non-taken branches (lower number means higher occurrence rate).", "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.COND_NTAKEN", "MetricGroup": "Bad;BrMispredicts", "MetricName": "tma_info_bad_spec_ipmisp_cond_ntaken", "MetricThreshold": "tma_info_bad_spec_ipmisp_cond_ntaken < 200" }, { - "BriefDescription": "Instructions per retired Mispredicts for conditional taken branches (lower number means higher occurrence rate)", + "BriefDescription": "Instructions per retired Mispredicts for conditional taken branches (lower number means higher occurrence rate).", "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.COND_TAKEN", "MetricGroup": "Bad;BrMispredicts", "MetricName": "tma_info_bad_spec_ipmisp_cond_taken", "MetricThreshold": "tma_info_bad_spec_ipmisp_cond_taken < 200" }, { - "BriefDescription": "Instructions per retired Mispredicts for indirect CALL or JMP branches (lower number means higher occurrence rate)", + "BriefDescription": "Instructions per retired Mispredicts for indirect CALL or JMP branches (lower number means higher occurrence rate).", "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.INDIRECT", "MetricGroup": "Bad;BrMispredicts", "MetricName": "tma_info_bad_spec_ipmisp_indirect", - "MetricThreshold": "tma_info_bad_spec_ipmisp_indirect < 1000" + "MetricThreshold": "tma_info_bad_spec_ipmisp_indirect < 1e3" }, { - "BriefDescription": "Instructions per retired Mispredicts for return branches (lower number means higher occurrence rate)", + "BriefDescription": "Instructions per retired Mispredicts for return branches (lower number means higher occurrence rate).", "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.RET", "MetricGroup": "Bad;BrMispredicts", "MetricName": "tma_info_bad_spec_ipmisp_ret", @@ -619,7 +619,7 @@ }, { "BriefDescription": "Total pipeline cost of DSB (uop cache) hits - subset of the Instruction_Fetch_BW Bottleneck", - "MetricExpr": "100 * (tma_frontend_bound * (tma_fetch_bandwidth / (tma_fetch_latency + tma_fetch_bandwidth)) * (tma_dsb / (tma_mite + tma_dsb + tma_lsd + tma_ms)))", + "MetricExpr": "100 * (tma_frontend_bound * (tma_fetch_bandwidth / (tma_fetch_bandwidth + tma_fetch_latency)) * (tma_dsb / (tma_dsb + tma_lsd + tma_mite + tma_ms)))", "MetricGroup": "DSB;Fed;FetchBW;tma_issueFB", "MetricName": "tma_info_botlnk_l2_dsb_bandwidth", "MetricThreshold": "tma_info_botlnk_l2_dsb_bandwidth > 10", @@ -628,7 +628,7 @@ { "BriefDescription": "Total pipeline cost of DSB (uop cache) misses - subset of the Instruction_Fetch_BW Bottleneck", "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "100 * (tma_fetch_latency * tma_dsb_switches / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches) + tma_fetch_bandwidth * tma_mite / (tma_mite + tma_dsb + tma_lsd + tma_ms))", + "MetricExpr": "100 * (tma_fetch_latency * tma_dsb_switches / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) + tma_fetch_bandwidth * tma_mite / (tma_dsb + tma_lsd + tma_mite + tma_ms))", "MetricGroup": "DSBmiss;Fed;tma_issueFB", "MetricName": "tma_info_botlnk_l2_dsb_misses", "MetricThreshold": "tma_info_botlnk_l2_dsb_misses > 10", @@ -637,10 +637,11 @@ { "BriefDescription": "Total pipeline cost of Instruction Cache misses - subset of the Big_Code Bottleneck", "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "100 * (tma_fetch_latency * tma_icache_misses / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches))", + "MetricExpr": "100 * (tma_fetch_latency * tma_icache_misses / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches))", "MetricGroup": "Fed;FetchLat;IcMiss;tma_issueFL", "MetricName": "tma_info_botlnk_l2_ic_misses", - "MetricThreshold": "tma_info_botlnk_l2_ic_misses > 5" + "MetricThreshold": "tma_info_botlnk_l2_ic_misses > 5", + "PublicDescription": "Total pipeline cost of Instruction Cache misses - subset of the Big_Code Bottleneck. Related metrics: " }, { "BriefDescription": "Fraction of branches that are CALL or RET", @@ -701,11 +702,11 @@ "MetricExpr": "(FP_ARITH_INST_RETIRED.SCALAR + FP_ARITH_INST_RETIRED.VECTOR) / (2 * tma_info_core_core_clks)", "MetricGroup": "Cor;Flops;HPC", "MetricName": "tma_info_core_fp_arith_utilization", - "PublicDescription": "Actual per-core usage of the Floating Point non-X87 execution units (regardless of precision or vector-width). Values > 1 are possible due to ([BDW+] Fused-Multiply Add (FMA) counting - common; [ADL+] use all of ADD/MUL/FMA in Scalar or 128/256-bit vectors - less common)" + "PublicDescription": "Actual per-core usage of the Floating Point non-X87 execution units (regardless of precision or vector-width). Values > 1 are possible due to ([BDW+] Fused-Multiply Add (FMA) counting - common; [ADL+] use all of ADD/MUL/FMA in Scalar or 128/256-bit vectors - less common)." }, { "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is execution) per thread (logical-processor)", - "MetricExpr": "UOPS_EXECUTED.THREAD / cpu@UOPS_EXECUTED.THREAD\\,cmask\\=0x1@", + "MetricExpr": "UOPS_EXECUTED.THREAD / cpu@UOPS_EXECUTED.THREAD\\,cmask\\=1@", "MetricGroup": "Backend;Cor;Pipeline;PortsUtil", "MetricName": "tma_info_core_ilp" }, @@ -718,20 +719,20 @@ "PublicDescription": "Fraction of Uops delivered by the DSB (aka Decoded ICache; or Uop Cache). Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_inst_mix_iptb, tma_lcp" }, { - "BriefDescription": "Average number of cycles of a switch from the DSB fetch-unit to MITE fetch unit - see DSB_Switches tree node for details", - "MetricExpr": "DSB2MITE_SWITCHES.PENALTY_CYCLES / cpu@DSB2MITE_SWITCHES.PENALTY_CYCLES\\,cmask\\=0x1\\,edge\\=0x1@", + "BriefDescription": "Average number of cycles of a switch from the DSB fetch-unit to MITE fetch unit - see DSB_Switches tree node for details.", + "MetricExpr": "DSB2MITE_SWITCHES.PENALTY_CYCLES / cpu@DSB2MITE_SWITCHES.PENALTY_CYCLES\\,cmask\\=1\\,edge@", "MetricGroup": "DSBmiss", "MetricName": "tma_info_frontend_dsb_switch_cost" }, { "BriefDescription": "Average number of Uops issued by front-end when it issued something", - "MetricExpr": "UOPS_ISSUED.ANY / cpu@UOPS_ISSUED.ANY\\,cmask\\=0x1@", + "MetricExpr": "UOPS_ISSUED.ANY / cpu@UOPS_ISSUED.ANY\\,cmask\\=1@", "MetricGroup": "Fed;FetchBW", "MetricName": "tma_info_frontend_fetch_upc" }, { "BriefDescription": "Average Latency for L1 instruction cache misses", - "MetricExpr": "ICACHE_16B.IFDATA_STALL / cpu@ICACHE_16B.IFDATA_STALL\\,cmask\\=0x1\\,edge\\=0x1@", + "MetricExpr": "ICACHE_16B.IFDATA_STALL / cpu@ICACHE_16B.IFDATA_STALL\\,cmask\\=1\\,edge@", "MetricGroup": "Fed;FetchLat;IcMiss", "MetricName": "tma_info_frontend_icache_miss_latency" }, @@ -773,7 +774,7 @@ "MetricName": "tma_info_frontend_tbpc" }, { - "BriefDescription": "Branch instructions per taken branch", + "BriefDescription": "Branch instructions per taken branch.", "MetricExpr": "BR_INST_RETIRED.ALL_BRANCHES / BR_INST_RETIRED.NEAR_TAKEN", "MetricGroup": "Branches;Fed;PGO", "MetricName": "tma_info_inst_mix_bptkbranch" @@ -791,7 +792,7 @@ "MetricGroup": "Flops;InsType", "MetricName": "tma_info_inst_mix_iparith", "MetricThreshold": "tma_info_inst_mix_iparith < 10", - "PublicDescription": "Instructions per FP Arithmetic instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting. Approximated prior to BDW" + "PublicDescription": "Instructions per FP Arithmetic instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting. Approximated prior to BDW." }, { "BriefDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number means higher occurrence rate)", @@ -799,7 +800,7 @@ "MetricGroup": "Flops;FpVector;InsType", "MetricName": "tma_info_inst_mix_iparith_avx128", "MetricThreshold": "tma_info_inst_mix_iparith_avx128 < 10", - "PublicDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting" + "PublicDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting." }, { "BriefDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means higher occurrence rate)", @@ -807,7 +808,7 @@ "MetricGroup": "Flops;FpVector;InsType", "MetricName": "tma_info_inst_mix_iparith_avx256", "MetricThreshold": "tma_info_inst_mix_iparith_avx256 < 10", - "PublicDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting" + "PublicDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting." }, { "BriefDescription": "Instructions per FP Arithmetic AVX 512-bit instruction (lower number means higher occurrence rate)", @@ -815,7 +816,7 @@ "MetricGroup": "Flops;FpVector;InsType", "MetricName": "tma_info_inst_mix_iparith_avx512", "MetricThreshold": "tma_info_inst_mix_iparith_avx512 < 10", - "PublicDescription": "Instructions per FP Arithmetic AVX 512-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting" + "PublicDescription": "Instructions per FP Arithmetic AVX 512-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting." }, { "BriefDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction (lower number means higher occurrence rate)", @@ -823,7 +824,7 @@ "MetricGroup": "Flops;FpScalar;InsType", "MetricName": "tma_info_inst_mix_iparith_scalar_dp", "MetricThreshold": "tma_info_inst_mix_iparith_scalar_dp < 10", - "PublicDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting" + "PublicDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting." }, { "BriefDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction (lower number means higher occurrence rate)", @@ -831,7 +832,7 @@ "MetricGroup": "Flops;FpScalar;InsType", "MetricName": "tma_info_inst_mix_iparith_scalar_sp", "MetricThreshold": "tma_info_inst_mix_iparith_scalar_sp < 10", - "PublicDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting" + "PublicDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting." }, { "BriefDescription": "Instructions per Branch (lower number means higher occurrence rate)", @@ -886,7 +887,7 @@ "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_TAKEN", "MetricGroup": "Branches;Fed;FetchBW;Frontend;PGO;tma_issueFB", "MetricName": "tma_info_inst_mix_iptb", - "MetricThreshold": "tma_info_inst_mix_iptb < 5 * 2 + 1", + "MetricThreshold": "tma_info_inst_mix_iptb < 11", "PublicDescription": "Instructions per taken branch. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_lcp" }, { @@ -1011,7 +1012,7 @@ }, { "BriefDescription": "Average Parallel L2 cache miss demand Loads", - "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD / cpu@OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD\\,cmask\\=0x1@", + "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD / cpu@OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD\\,cmask\\=1@", "MetricGroup": "Memory_BW;Offcore", "MetricName": "tma_info_memory_latency_load_l2_mlp" }, @@ -1074,7 +1075,7 @@ }, { "BriefDescription": "", - "MetricExpr": "UOPS_EXECUTED.THREAD / (UOPS_EXECUTED.CORE_CYCLES_GE_1 / 2 if #SMT_on else cpu@UOPS_EXECUTED.THREAD\\,cmask\\=0x1@)", + "MetricExpr": "UOPS_EXECUTED.THREAD / (UOPS_EXECUTED.CORE_CYCLES_GE_1 / 2 if #SMT_on else cpu@UOPS_EXECUTED.THREAD\\,cmask\\=1@)", "MetricGroup": "Cor;Pipeline;PortsUtil;SMT", "MetricName": "tma_info_pipeline_execute" }, @@ -1101,12 +1102,12 @@ "MetricExpr": "INST_RETIRED.ANY / ASSISTS.ANY", "MetricGroup": "MicroSeq;Pipeline;Ret;Retire", "MetricName": "tma_info_pipeline_ipassist", - "MetricThreshold": "tma_info_pipeline_ipassist < 100000", + "MetricThreshold": "tma_info_pipeline_ipassist < 100e3", "PublicDescription": "Instructions per a microcode Assist invocation. See Assists tree node for details (lower number means higher occurrence rate)" }, { - "BriefDescription": "Average number of Uops retired in cycles where at least one uop has retired", - "MetricExpr": "tma_retiring * tma_info_thread_slots / cpu@UOPS_RETIRED.SLOTS\\,cmask\\=0x1@", + "BriefDescription": "Average number of Uops retired in cycles where at least one uop has retired.", + "MetricExpr": "tma_retiring * tma_info_thread_slots / cpu@UOPS_RETIRED.SLOTS\\,cmask\\=1@", "MetricGroup": "Pipeline;Ret", "MetricName": "tma_info_pipeline_retire" }, @@ -1147,14 +1148,13 @@ "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.FAR_BRANCH:u", "MetricGroup": "Branches;OS", "MetricName": "tma_info_system_ipfarbranch", - "MetricThreshold": "tma_info_system_ipfarbranch < 1000000" + "MetricThreshold": "tma_info_system_ipfarbranch < 1e6" }, { "BriefDescription": "Cycles Per Instruction for the Operating System (OS) Kernel mode", "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P:k / INST_RETIRED.ANY_P:k", "MetricGroup": "OS", - "MetricName": "tma_info_system_kernel_cpi", - "ScaleUnit": "1per_instr" + "MetricName": "tma_info_system_kernel_cpi" }, { "BriefDescription": "Fraction of cycles spent in the Operating System (OS) Kernel mode", @@ -1195,7 +1195,7 @@ "MetricExpr": "CORE_POWER.LVL0_TURBO_LICENSE / tma_info_core_core_clks", "MetricGroup": "Power", "MetricName": "tma_info_system_power_license0_utilization", - "PublicDescription": "Fraction of Core cycles where the core was running with power-delivery for baseline license level 0. This includes non-AVX codes, SSE, AVX 128-bit, and low-current AVX 256-bit codes" + "PublicDescription": "Fraction of Core cycles where the core was running with power-delivery for baseline license level 0. This includes non-AVX codes, SSE, AVX 128-bit, and low-current AVX 256-bit codes." }, { "BriefDescription": "Fraction of Core cycles where the core was running with power-delivery for license level 1", @@ -1203,7 +1203,7 @@ "MetricGroup": "Power", "MetricName": "tma_info_system_power_license1_utilization", "MetricThreshold": "tma_info_system_power_license1_utilization > 0.5", - "PublicDescription": "Fraction of Core cycles where the core was running with power-delivery for license level 1. This includes high current AVX 256-bit instructions as well as low current AVX 512-bit instructions" + "PublicDescription": "Fraction of Core cycles where the core was running with power-delivery for license level 1. This includes high current AVX 256-bit instructions as well as low current AVX 512-bit instructions." }, { "BriefDescription": "Fraction of Core cycles where the core was running with power-delivery for license level 2 (introduced in SKX)", @@ -1211,7 +1211,7 @@ "MetricGroup": "Power", "MetricName": "tma_info_system_power_license2_utilization", "MetricThreshold": "tma_info_system_power_license2_utilization > 0.5", - "PublicDescription": "Fraction of Core cycles where the core was running with power-delivery for license level 2 (introduced in SKX). This includes high current AVX 512-bit instructions" + "PublicDescription": "Fraction of Core cycles where the core was running with power-delivery for license level 2 (introduced in SKX). This includes high current AVX 512-bit instructions." }, { "BriefDescription": "Fraction of cycles where both hardware Logical Processors were active", @@ -1239,7 +1239,7 @@ "MetricName": "tma_info_system_turbo_utilization" }, { - "BriefDescription": "Per-Logical Processor actual clocks when the Logical Processor is active", + "BriefDescription": "Per-Logical Processor actual clocks when the Logical Processor is active.", "MetricExpr": "CPU_CLK_UNHALTED.THREAD", "MetricGroup": "Pipeline", "MetricName": "tma_info_thread_clks" @@ -1248,15 +1248,14 @@ "BriefDescription": "Cycles Per Instruction (per Logical Processor)", "MetricExpr": "1 / tma_info_thread_ipc", "MetricGroup": "Mem;Pipeline", - "MetricName": "tma_info_thread_cpi", - "ScaleUnit": "1per_instr" + "MetricName": "tma_info_thread_cpi" }, { "BriefDescription": "The ratio of Executed- by Issued-Uops", "MetricExpr": "UOPS_EXECUTED.THREAD / UOPS_ISSUED.ANY", "MetricGroup": "Cor;Pipeline", "MetricName": "tma_info_thread_execute_per_issue", - "PublicDescription": "The ratio of Executed- by Issued-Uops. Ratio > 1 suggests high rate of uop micro-fusions. Ratio < 1 suggest high rate of \"execute\" at rename stage" + "PublicDescription": "The ratio of Executed- by Issued-Uops. Ratio > 1 suggests high rate of uop micro-fusions. Ratio < 1 suggest high rate of \"execute\" at rename stage." }, { "BriefDescription": "Instructions Per Cycle (per Logical Processor)", @@ -1266,13 +1265,13 @@ }, { "BriefDescription": "Total issue-pipeline slots (per-Physical Core till ICL; per-Logical Processor ICL onward)", - "MetricExpr": "slots", + "MetricExpr": "TOPDOWN.SLOTS", "MetricGroup": "TmaL1;tma_L1_group", "MetricName": "tma_info_thread_slots" }, { "BriefDescription": "Fraction of Physical Core issue-slots utilized by this Logical Processor", - "MetricExpr": "(tma_info_thread_slots / (slots / 2) if #SMT_on else 1)", + "MetricExpr": "(tma_info_thread_slots / (TOPDOWN.SLOTS / 2) if #SMT_on else 1)", "MetricGroup": "SMT;TmaL1;tma_L1_group", "MetricName": "tma_info_thread_slots_utilization" }, @@ -1288,14 +1287,14 @@ "MetricExpr": "tma_retiring * tma_info_thread_slots / BR_INST_RETIRED.NEAR_TAKEN", "MetricGroup": "Branches;Fed;FetchBW", "MetricName": "tma_info_thread_uptb", - "MetricThreshold": "tma_info_thread_uptb < 5 * 1.5" + "MetricThreshold": "tma_info_thread_uptb < 7.5" }, { - "BriefDescription": "This metric represents fraction of cycles where the Integer Divider unit was active", + "BriefDescription": "This metric represents fraction of cycles where the Integer Divider unit was active.", "MetricExpr": "tma_divider - tma_fp_divider", "MetricGroup": "TopdownL4;tma_L4_group;tma_divider_group", "MetricName": "tma_int_divider", - "MetricThreshold": "tma_int_divider > 0.2 & tma_divider > 0.2 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_int_divider > 0.2 & (tma_divider > 0.2 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", "ScaleUnit": "100%" }, { @@ -1303,8 +1302,8 @@ "MetricExpr": "ICACHE_TAG.STALLS / tma_info_thread_clks", "MetricGroup": "BigFootprint;BvBC;FetchLat;MemoryTLB;TopdownL3;tma_L3_group;tma_fetch_latency_group", "MetricName": "tma_itlb_misses", - "MetricThreshold": "tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", - "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Instruction TLB (ITLB) misses. Sample with: FRONTEND_RETIRED.STLB_MISS, FRONTEND_RETIRED.ITLB_MISS", + "MetricThreshold": "tma_itlb_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Instruction TLB (ITLB) misses. Sample with: FRONTEND_RETIRED.STLB_MISS_PS;FRONTEND_RETIRED.ITLB_MISS_PS", "ScaleUnit": "100%" }, { @@ -1312,7 +1311,7 @@ "MetricExpr": "max((CYCLE_ACTIVITY.STALLS_MEM_ANY - CYCLE_ACTIVITY.STALLS_L1D_MISS) / tma_info_thread_clks, 0)", "MetricGroup": "CacheHits;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_issueL1;tma_issueMC;tma_memory_bound_group", "MetricName": "tma_l1_bound", - "MetricThreshold": "tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", "PublicDescription": "This metric estimates how often the CPU was stalled without loads missing the L1 Data (L1D) cache. The L1D cache typically has the shortest latency. However; in certain cases like loads blocked on older stores; a load might suffer due to high latency even though it is being satisfied by the L1D. Another example is loads who miss in the TLB. These cases are characterized by execution unit stalls; while some non-completed demand load lives in the machine without having that demand load missing the L1 cache. Sample with: MEM_LOAD_RETIRED.L1_HIT. Related metrics: tma_clears_resteers, tma_machine_clears, tma_microcode_sequencer, tma_ms_switches, tma_ports_utilized_1", "ScaleUnit": "100%" }, @@ -1321,7 +1320,7 @@ "MetricExpr": "min(2 * (MEM_INST_RETIRED.ALL_LOADS - MEM_LOAD_RETIRED.FB_HIT - MEM_LOAD_RETIRED.L1_MISS) * 20 / 100, max(CYCLE_ACTIVITY.CYCLES_MEM_ANY - CYCLE_ACTIVITY.CYCLES_L1D_MISS, 0)) / tma_info_thread_clks", "MetricGroup": "BvML;MemoryLat;TopdownL4;tma_L4_group;tma_l1_bound_group", "MetricName": "tma_l1_latency_dependency", - "MetricThreshold": "tma_l1_latency_dependency > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_l1_latency_dependency > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", "PublicDescription": "This metric([SKL+] roughly; [LNL]) estimates fraction of cycles with demand load accesses that hit the L1D cache. The short latency of the L1D cache may be exposed in pointer-chasing memory access patterns as an example. Sample with: MEM_LOAD_RETIRED.L1_HIT", "ScaleUnit": "100%" }, @@ -1331,7 +1330,7 @@ "MetricExpr": "MEM_LOAD_RETIRED.L2_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) / (MEM_LOAD_RETIRED.L2_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) + L1D_PEND_MISS.FB_FULL_PERIODS) * ((CYCLE_ACTIVITY.STALLS_L1D_MISS - CYCLE_ACTIVITY.STALLS_L2_MISS) / tma_info_thread_clks)", "MetricGroup": "BvML;CacheHits;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_l2_bound", - "MetricThreshold": "tma_l2_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_l2_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", "PublicDescription": "This metric estimates how often the CPU was stalled due to L2 cache accesses by loads. Avoiding cache misses (i.e. L1 misses/L2 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L2_HIT", "ScaleUnit": "100%" }, @@ -1340,7 +1339,7 @@ "MetricExpr": "5 * tma_info_system_core_frequency * MEM_LOAD_RETIRED.L2_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks", "MetricGroup": "MemoryLat;TopdownL4;tma_L4_group;tma_l2_bound_group", "MetricName": "tma_l2_hit_latency", - "MetricThreshold": "tma_l2_hit_latency > 0.05 & tma_l2_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_l2_hit_latency > 0.05 & (tma_l2_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", "PublicDescription": "This metric represents fraction of cycles with demand load accesses that hit the L2 cache under unloaded scenarios (possibly L2 latency limited). Avoiding L1 cache misses (i.e. L1 misses/L2 hits) will improve the latency. Sample with: MEM_LOAD_RETIRED.L2_HIT", "ScaleUnit": "100%" }, @@ -1350,17 +1349,17 @@ "MetricExpr": "(CYCLE_ACTIVITY.STALLS_L2_MISS - CYCLE_ACTIVITY.STALLS_L3_MISS) / tma_info_thread_clks", "MetricGroup": "CacheHits;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_l3_bound", - "MetricThreshold": "tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", - "PublicDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core. Avoiding cache misses (i.e. L2 misses/L3 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L3_HIT", + "MetricThreshold": "tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", + "PublicDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core. Avoiding cache misses (i.e. L2 misses/L3 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L3_HIT_PS", "ScaleUnit": "100%" }, { "BriefDescription": "This metric estimates fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited)", - "MetricExpr": "(22.5 * tma_info_system_core_frequency - 5 * tma_info_system_core_frequency) * (MEM_LOAD_RETIRED.L3_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2)) / tma_info_thread_clks", + "MetricExpr": "17.5 * tma_info_system_core_frequency * (MEM_LOAD_RETIRED.L3_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2)) / tma_info_thread_clks", "MetricGroup": "BvML;MemoryLat;TopdownL4;tma_L4_group;tma_issueLat;tma_l3_bound_group", "MetricName": "tma_l3_hit_latency", - "MetricThreshold": "tma_l3_hit_latency > 0.1 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", - "PublicDescription": "This metric estimates fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited). Avoiding private cache misses (i.e. L2 misses/L3 hits) will improve the latency; reduce contention with sibling physical cores and increase performance. Note the value of this node may overlap with its siblings. Sample with: MEM_LOAD_RETIRED.L3_HIT. Related metrics: tma_bottleneck_cache_memory_latency, tma_branch_resteers, tma_mem_latency, tma_store_latency", + "MetricThreshold": "tma_l3_hit_latency > 0.1 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric estimates fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited). Avoiding private cache misses (i.e. L2 misses/L3 hits) will improve the latency; reduce contention with sibling physical cores and increase performance. Note the value of this node may overlap with its siblings. Sample with: MEM_LOAD_RETIRED.L3_HIT_PS. Related metrics: tma_bottleneck_cache_memory_latency, tma_mem_latency", "ScaleUnit": "100%" }, { @@ -1368,18 +1367,18 @@ "MetricExpr": "DECODE.LCP / tma_info_thread_clks", "MetricGroup": "FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueFB", "MetricName": "tma_lcp", - "MetricThreshold": "tma_lcp > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", - "PublicDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs). Using proper compiler flags or Intel Compiler by default will certainly avoid this. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb", + "MetricThreshold": "tma_lcp > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", + "PublicDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs). Using proper compiler flags or Intel Compiler by default will certainly avoid this. #Link: Optimization Guide about LCP BKMs. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations , instructions that require no more than one uop (micro-operation)", + "BriefDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation)", "MetricExpr": "max(0, tma_retiring - tma_heavy_operations)", "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_light_operations", "MetricThreshold": "tma_light_operations > 0.6", "MetricgroupNoGroup": "TopdownL2", - "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations , instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized code running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. ([ICL+] Note this may undercount due to approximation using indirect events; [ADL+] .). Sample with: INST_RETIRED.PREC_DIST", + "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized code running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. ([ICL+] Note this may undercount due to approximation using indirect events; [ADL+] .). Sample with: INST_RETIRED.PREC_DIST", "ScaleUnit": "100%" }, { @@ -1396,7 +1395,7 @@ "MetricExpr": "tma_dtlb_load - tma_load_stlb_miss", "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_load_group", "MetricName": "tma_load_stlb_hit", - "MetricThreshold": "tma_load_stlb_hit > 0.05 & tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_load_stlb_hit > 0.05 & (tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))", "ScaleUnit": "100%" }, { @@ -1404,31 +1403,31 @@ "MetricExpr": "DTLB_LOAD_MISSES.WALK_ACTIVE / tma_info_thread_clks", "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_load_group", "MetricName": "tma_load_stlb_miss", - "MetricThreshold": "tma_load_stlb_miss > 0.05 & tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_load_stlb_miss > 0.05 & (tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 1 GB pages for data load accesses", + "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 1 GB pages for data load accesses.", "MetricExpr": "tma_load_stlb_miss * DTLB_LOAD_MISSES.WALK_COMPLETED_1G / (DTLB_LOAD_MISSES.WALK_COMPLETED_4K + DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M + DTLB_LOAD_MISSES.WALK_COMPLETED_1G)", "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_load_stlb_miss_group", "MetricName": "tma_load_stlb_miss_1g", - "MetricThreshold": "tma_load_stlb_miss_1g > 0.05 & tma_load_stlb_miss > 0.05 & tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_load_stlb_miss_1g > 0.05 & (tma_load_stlb_miss > 0.05 & (tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))))", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 2 or 4 MB pages for data load accesses", + "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 2 or 4 MB pages for data load accesses.", "MetricExpr": "tma_load_stlb_miss * DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M / (DTLB_LOAD_MISSES.WALK_COMPLETED_4K + DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M + DTLB_LOAD_MISSES.WALK_COMPLETED_1G)", "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_load_stlb_miss_group", "MetricName": "tma_load_stlb_miss_2m", - "MetricThreshold": "tma_load_stlb_miss_2m > 0.05 & tma_load_stlb_miss > 0.05 & tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_load_stlb_miss_2m > 0.05 & (tma_load_stlb_miss > 0.05 & (tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))))", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 4 KB pages for data load accesses", + "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 4 KB pages for data load accesses.", "MetricExpr": "tma_load_stlb_miss * DTLB_LOAD_MISSES.WALK_COMPLETED_4K / (DTLB_LOAD_MISSES.WALK_COMPLETED_4K + DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M + DTLB_LOAD_MISSES.WALK_COMPLETED_1G)", "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_load_stlb_miss_group", "MetricName": "tma_load_stlb_miss_4k", - "MetricThreshold": "tma_load_stlb_miss_4k > 0.05 & tma_load_stlb_miss > 0.05 & tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_load_stlb_miss_4k > 0.05 & (tma_load_stlb_miss > 0.05 & (tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))))", "ScaleUnit": "100%" }, { @@ -1437,7 +1436,7 @@ "MetricExpr": "(16 * max(0, MEM_INST_RETIRED.LOCK_LOADS - L2_RQSTS.ALL_RFO) + MEM_INST_RETIRED.LOCK_LOADS / MEM_INST_RETIRED.ALL_STORES * (10 * L2_RQSTS.RFO_HIT + min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO))) / tma_info_thread_clks", "MetricGroup": "LockCont;Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_l1_bound_group", "MetricName": "tma_lock_latency", - "MetricThreshold": "tma_lock_latency > 0.2 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_lock_latency > 0.2 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", "PublicDescription": "This metric represents fraction of cycles the CPU spent handling cache misses due to lock operations. Due to the microarchitecture handling of locks; they are classified as L1_Bound regardless of what memory source satisfied them. Sample with: MEM_INST_RETIRED.LOCK_LOADS. Related metrics: tma_store_latency", "ScaleUnit": "100%" }, @@ -1447,7 +1446,7 @@ "MetricGroup": "FetchBW;LSD;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group", "MetricName": "tma_lsd", "MetricThreshold": "tma_lsd > 0.15 & tma_fetch_bandwidth > 0.2", - "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to LSD (Loop Stream Detector) unit. LSD typically does well sustaining Uop supply. However; in some rare cases; optimal uop-delivery could not be reached for small loops whose size (in terms of number of uops) does not suit well the LSD structure", + "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to LSD (Loop Stream Detector) unit. LSD typically does well sustaining Uop supply. However; in some rare cases; optimal uop-delivery could not be reached for small loops whose size (in terms of number of uops) does not suit well the LSD structure.", "ScaleUnit": "100%" }, { @@ -1457,15 +1456,15 @@ "MetricName": "tma_machine_clears", "MetricThreshold": "tma_machine_clears > 0.1 & tma_bad_speculation > 0.15", "MetricgroupNoGroup": "TopdownL2", - "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears. These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT. Related metrics: tma_bottleneck_memory_synchronization, tma_clears_resteers, tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_l1_bound, tma_microcode_sequencer, tma_ms_switches", + "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears. These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT. Related metrics: tma_bottleneck_memory_synchronization, tma_clears_resteers, tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_l1_bound, tma_microcode_sequencer, tma_ms_switches, tma_remote_cache", "ScaleUnit": "100%" }, { "BriefDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory - DRAM ([SPR-HBM] and/or HBM)", - "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, cpu@OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD\\,cmask\\=0x4@) / tma_info_thread_clks", + "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, cpu@OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD\\,cmask\\=4@) / tma_info_thread_clks", "MetricGroup": "BvMB;MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueBW", "MetricName": "tma_mem_bandwidth", - "MetricThreshold": "tma_mem_bandwidth > 0.2 & tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_mem_bandwidth > 0.2 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", "PublicDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory - DRAM ([SPR-HBM] and/or HBM). The underlying heuristic assumes that a similar off-core traffic is generated by all IA cores. This metric does not aggregate non-data-read requests by this logical processor; requests from other IA Logical Processors/Physical Cores/sockets; or other non-IA devices like GPU; hence the maximum external memory bandwidth limits may or may not be approached when this metric is flagged (see Uncore counters for that). Related metrics: tma_bottleneck_cache_memory_bandwidth, tma_fb_full, tma_info_system_dram_bw_use, tma_sq_full", "ScaleUnit": "100%" }, @@ -1474,7 +1473,7 @@ "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD) / tma_info_thread_clks - tma_mem_bandwidth", "MetricGroup": "BvML;MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueLat", "MetricName": "tma_mem_latency", - "MetricThreshold": "tma_mem_latency > 0.1 & tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_mem_latency > 0.1 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", "PublicDescription": "This metric estimates fraction of cycles where the performance was likely hurt due to latency from external memory - DRAM ([SPR-HBM] and/or HBM). This metric does not aggregate requests from other Logical Processors/Physical Cores/sockets (see Uncore counters for that). Related metrics: tma_bottleneck_cache_memory_latency, tma_l3_hit_latency", "ScaleUnit": "100%" }, @@ -1485,11 +1484,11 @@ "MetricName": "tma_memory_bound", "MetricThreshold": "tma_memory_bound > 0.2 & tma_backend_bound > 0.2", "MetricgroupNoGroup": "TopdownL2", - "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck. Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two)", + "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck. Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two).", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of slots where the CPU was retiring memory operations , uops for memory load or store accesses", + "BriefDescription": "This metric represents fraction of slots where the CPU was retiring memory operations -- uops for memory load or store accesses.", "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "tma_light_operations * MEM_INST_RETIRED.ANY / INST_RETIRED.ANY", "MetricGroup": "Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group", @@ -1511,7 +1510,7 @@ "MetricExpr": "BR_MISP_RETIRED.ALL_BRANCHES / (BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT) * INT_MISC.CLEAR_RESTEER_CYCLES / tma_info_thread_clks", "MetricGroup": "BadSpec;BrMispredicts;BvMP;TopdownL4;tma_L4_group;tma_branch_resteers_group;tma_issueBM", "MetricName": "tma_mispredicts_resteers", - "MetricThreshold": "tma_mispredicts_resteers > 0.05 & tma_branch_resteers > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricThreshold": "tma_mispredicts_resteers > 0.05 & (tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))", "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Branch Misprediction at execution stage. Sample with: INT_MISC.CLEAR_RESTEER_CYCLES. Related metrics: tma_bottleneck_mispredictions, tma_branch_mispredicts, tma_info_bad_spec_branch_misprediction_cost", "ScaleUnit": "100%" }, @@ -1526,24 +1525,24 @@ }, { "BriefDescription": "This metric represents fraction of cycles where (only) 4 uops were delivered by the MITE pipeline", - "MetricExpr": "(cpu@IDQ.MITE_UOPS\\,cmask\\=0x4@ - cpu@IDQ.MITE_UOPS\\,cmask\\=0x5@) / tma_info_thread_clks", + "MetricExpr": "(cpu@IDQ.MITE_UOPS\\,cmask\\=4@ - cpu@IDQ.MITE_UOPS\\,cmask\\=5@) / tma_info_thread_clks", "MetricGroup": "DSBmiss;FetchBW;TopdownL4;tma_L4_group;tma_mite_group", "MetricName": "tma_mite_4wide", - "MetricThreshold": "tma_mite_4wide > 0.05 & tma_mite > 0.1 & tma_fetch_bandwidth > 0.2", + "MetricThreshold": "tma_mite_4wide > 0.05 & (tma_mite > 0.1 & tma_fetch_bandwidth > 0.2)", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates penalty in terms of percentage of([SKL+] injected blend uops out of all Uops Issued , the Count Domain; [ADL+] cycles)", + "BriefDescription": "This metric estimates penalty in terms of percentage of([SKL+] injected blend uops out of all Uops Issued -- the Count Domain; [ADL+] cycles)", "MetricExpr": "UOPS_ISSUED.VECTOR_WIDTH_MISMATCH / UOPS_ISSUED.ANY", "MetricGroup": "TopdownL5;tma_L5_group;tma_issueMV;tma_ports_utilized_0_group", "MetricName": "tma_mixing_vectors", "MetricThreshold": "tma_mixing_vectors > 0.05", - "PublicDescription": "This metric estimates penalty in terms of percentage of([SKL+] injected blend uops out of all Uops Issued , the Count Domain; [ADL+] cycles). Usually a Mixing_Vectors over 5% is worth investigating. Read more in Appendix B1 of the Optimizations Guide for this topic. Related metrics: tma_ms_switches", + "PublicDescription": "This metric estimates penalty in terms of percentage of([SKL+] injected blend uops out of all Uops Issued -- the Count Domain; [ADL+] cycles). Usually a Mixing_Vectors over 5% is worth investigating. Read more in Appendix B1 of the Optimizations Guide for this topic. Related metrics: tma_ms_switches", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to the Microcode Sequencer (MS) unit - see Microcode_Sequencer node for details", - "MetricExpr": "cpu@IDQ.MS_UOPS\\,cmask\\=0x1@ / tma_info_core_core_clks / 2", + "BriefDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to the Microcode Sequencer (MS) unit - see Microcode_Sequencer node for details.", + "MetricExpr": "cpu@IDQ.MS_UOPS\\,cmask\\=1@ / tma_info_core_core_clks / 2", "MetricGroup": "MicroSeq;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group", "MetricName": "tma_ms", "MetricThreshold": "tma_ms > 0.05 & tma_fetch_bandwidth > 0.2", @@ -1554,7 +1553,7 @@ "MetricExpr": "3 * IDQ.MS_SWITCHES / tma_info_thread_clks", "MetricGroup": "FetchLat;MicroSeq;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueMC;tma_issueMS;tma_issueMV;tma_issueSO", "MetricName": "tma_ms_switches", - "MetricThreshold": "tma_ms_switches > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricThreshold": "tma_ms_switches > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", "PublicDescription": "This metric estimates the fraction of cycles when the CPU was stalled due to switches of uop delivery to the Microcode Sequencer (MS). Commonly used instructions are optimized for delivery by the DSB (decoded i-cache) or MITE (legacy instruction decode) pipelines. Certain operations cannot be handled natively by the execution pipeline; and must be performed by microcode (small programs injected into the execution stream). Switching to the MS too often can negatively impact performance. The MS is designated to deliver long uop flows required by CISC instructions like CPUID; or uncommon conditions like Floating Point Assists when dealing with Denormals. Sample with: IDQ.MS_SWITCHES. Related metrics: tma_bottleneck_irregular_overhead, tma_clears_resteers, tma_l1_bound, tma_machine_clears, tma_microcode_sequencer, tma_mixing_vectors, tma_serializing_operation", "ScaleUnit": "100%" }, @@ -1563,7 +1562,7 @@ "MetricExpr": "tma_light_operations * INST_RETIRED.NOP / (tma_retiring * tma_info_thread_slots)", "MetricGroup": "BvBO;Pipeline;TopdownL4;tma_L4_group;tma_other_light_ops_group", "MetricName": "tma_nop_instructions", - "MetricThreshold": "tma_nop_instructions > 0.1 & tma_other_light_ops > 0.3 & tma_light_operations > 0.6", + "MetricThreshold": "tma_nop_instructions > 0.1 & (tma_other_light_ops > 0.3 & tma_light_operations > 0.6)", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring NOP (no op) instructions. Compilers often use NOPs for certain address alignments - e.g. start address of a function or loop body. Sample with: INST_RETIRED.NOP", "ScaleUnit": "100%" }, @@ -1578,19 +1577,19 @@ "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates fraction of slots the CPU was stalled due to other cases of misprediction (non-retired x86 branches or other types)", + "BriefDescription": "This metric estimates fraction of slots the CPU was stalled due to other cases of misprediction (non-retired x86 branches or other types).", "MetricExpr": "max(tma_branch_mispredicts * (1 - BR_MISP_RETIRED.ALL_BRANCHES / (INT_MISC.CLEARS_COUNT - MACHINE_CLEARS.COUNT)), 0.0001)", "MetricGroup": "BrMispredicts;BvIO;TopdownL3;tma_L3_group;tma_branch_mispredicts_group", "MetricName": "tma_other_mispredicts", - "MetricThreshold": "tma_other_mispredicts > 0.05 & tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", + "MetricThreshold": "tma_other_mispredicts > 0.05 & (tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15)", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of slots the CPU has wasted due to Nukes (Machine Clears) not related to memory ordering", + "BriefDescription": "This metric represents fraction of slots the CPU has wasted due to Nukes (Machine Clears) not related to memory ordering.", "MetricExpr": "max(tma_machine_clears * (1 - MACHINE_CLEARS.MEMORY_ORDERING / MACHINE_CLEARS.COUNT), 0.0001)", "MetricGroup": "BvIO;Machine_Clears;TopdownL3;tma_L3_group;tma_machine_clears_group", "MetricName": "tma_other_nukes", - "MetricThreshold": "tma_other_nukes > 0.05 & tma_machine_clears > 0.1 & tma_bad_speculation > 0.15", + "MetricThreshold": "tma_other_nukes > 0.05 & (tma_machine_clears > 0.1 & tma_bad_speculation > 0.15)", "ScaleUnit": "100%" }, { @@ -1634,8 +1633,8 @@ "MetricExpr": "((tma_ports_utilized_0 * tma_info_thread_clks + (EXE_ACTIVITY.1_PORTS_UTIL + tma_retiring * EXE_ACTIVITY.2_PORTS_UTIL)) / tma_info_thread_clks if ARITH.DIVIDER_ACTIVE < CYCLE_ACTIVITY.STALLS_TOTAL - CYCLE_ACTIVITY.STALLS_MEM_ANY else (EXE_ACTIVITY.1_PORTS_UTIL + tma_retiring * EXE_ACTIVITY.2_PORTS_UTIL) / tma_info_thread_clks)", "MetricGroup": "PortsUtil;TopdownL3;tma_L3_group;tma_core_bound_group", "MetricName": "tma_ports_utilization", - "MetricThreshold": "tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", - "PublicDescription": "This metric estimates fraction of cycles the CPU performance was potentially limited due to Core computation issues (non divider-related). Two distinct categories can be attributed into this metric: (1) heavy data-dependency among contiguous instructions would manifest in this metric - such cases are often referred to as low Instruction Level Parallelism (ILP). (2) Contention on some hardware execution unit other than Divider. For example; when there are too many multiply operations", + "MetricThreshold": "tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)", + "PublicDescription": "This metric estimates fraction of cycles the CPU performance was potentially limited due to Core computation issues (non divider-related). Two distinct categories can be attributed into this metric: (1) heavy data-dependency among contiguous instructions would manifest in this metric - such cases are often referred to as low Instruction Level Parallelism (ILP). (2) Contention on some hardware execution unit other than Divider. For example; when there are too many multiply operations.", "ScaleUnit": "100%" }, { @@ -1643,8 +1642,8 @@ "MetricExpr": "EXE_ACTIVITY.EXE_BOUND_0_PORTS / tma_info_thread_clks", "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group", "MetricName": "tma_ports_utilized_0", - "MetricThreshold": "tma_ports_utilized_0 > 0.2 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", - "PublicDescription": "This metric represents fraction of cycles CPU executed no uops on any execution port (Logical Processor cycles since ICL, Physical Core cycles otherwise). Long-latency instructions like divides may contribute to this metric", + "MetricThreshold": "tma_ports_utilized_0 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric represents fraction of cycles CPU executed no uops on any execution port (Logical Processor cycles since ICL, Physical Core cycles otherwise). Long-latency instructions like divides may contribute to this metric.", "ScaleUnit": "100%" }, { @@ -1652,7 +1651,7 @@ "MetricExpr": "EXE_ACTIVITY.1_PORTS_UTIL / tma_info_thread_clks", "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_issueL1;tma_ports_utilization_group", "MetricName": "tma_ports_utilized_1", - "MetricThreshold": "tma_ports_utilized_1 > 0.2 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_ports_utilized_1 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", "PublicDescription": "This metric represents fraction of cycles where the CPU executed total of 1 uop per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise). This can be due to heavy data-dependency among software instructions; or over oversubscribing a particular hardware resource. In some other cases with high 1_Port_Utilized and L1_Bound; this metric can point to L1 data-cache latency bottleneck that may not necessarily manifest with complete execution starvation (due to the short L1 latency e.g. walking a linked list) - looking at the assembly can be helpful. Sample with: EXE_ACTIVITY.1_PORTS_UTIL. Related metrics: tma_l1_bound", "ScaleUnit": "100%" }, @@ -1661,7 +1660,7 @@ "MetricExpr": "EXE_ACTIVITY.2_PORTS_UTIL / tma_info_thread_clks", "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_issue2P;tma_ports_utilization_group", "MetricName": "tma_ports_utilized_2", - "MetricThreshold": "tma_ports_utilized_2 > 0.15 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_ports_utilized_2 > 0.15 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", "PublicDescription": "This metric represents fraction of cycles CPU executed total of 2 uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise). Loop Vectorization -most compilers feature auto-Vectorization options today- reduces pressure on the execution ports as multiple elements are calculated with same uop. Sample with: EXE_ACTIVITY.2_PORTS_UTIL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6", "ScaleUnit": "100%" }, @@ -1670,14 +1669,14 @@ "MetricExpr": "UOPS_EXECUTED.CYCLES_GE_3 / tma_info_thread_clks", "MetricGroup": "BvCB;PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group", "MetricName": "tma_ports_utilized_3m", - "MetricThreshold": "tma_ports_utilized_3m > 0.4 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_ports_utilized_3m > 0.4 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", "PublicDescription": "This metric represents fraction of cycles CPU executed total of 3 or more uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise). Sample with: UOPS_EXECUTED.CYCLES_GE_3", "ScaleUnit": "100%" }, { "BriefDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired", "DefaultMetricgroupName": "TopdownL1", - "MetricExpr": "topdown\\-retiring / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * slots", + "MetricExpr": "topdown\\-retiring / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * tma_info_thread_slots", "MetricGroup": "BvUW;Default;TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_retiring", "MetricThreshold": "tma_retiring > 0.7 | tma_heavy_operations > 0.1", @@ -1690,7 +1689,7 @@ "MetricExpr": "RESOURCE_STALLS.SCOREBOARD / tma_info_thread_clks", "MetricGroup": "BvIO;PortsUtil;TopdownL3;tma_L3_group;tma_core_bound_group;tma_issueSO", "MetricName": "tma_serializing_operation", - "MetricThreshold": "tma_serializing_operation > 0.1 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_serializing_operation > 0.1 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)", "PublicDescription": "This metric represents fraction of cycles the CPU issue-pipeline was stalled due to serializing operations. Instructions like CPUID; WRMSR or LFENCE serialize the out-of-order execution which may limit performance. Sample with: RESOURCE_STALLS.SCOREBOARD. Related metrics: tma_ms_switches", "ScaleUnit": "100%" }, @@ -1699,7 +1698,7 @@ "MetricExpr": "140 * MISC_RETIRED.PAUSE_INST / tma_info_thread_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_serializing_operation_group", "MetricName": "tma_slow_pause", - "MetricThreshold": "tma_slow_pause > 0.05 & tma_serializing_operation > 0.1 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_slow_pause > 0.05 & (tma_serializing_operation > 0.1 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to PAUSE Instructions. Sample with: MISC_RETIRED.PAUSE_INST", "ScaleUnit": "100%" }, @@ -1709,7 +1708,7 @@ "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group", "MetricName": "tma_split_loads", "MetricThreshold": "tma_split_loads > 0.3", - "PublicDescription": "This metric estimates fraction of cycles handling memory load split accesses - load that cross 64-byte cache line boundary. Sample with: MEM_INST_RETIRED.SPLIT_LOADS", + "PublicDescription": "This metric estimates fraction of cycles handling memory load split accesses - load that cross 64-byte cache line boundary. Sample with: MEM_INST_RETIRED.SPLIT_LOADS_PS", "ScaleUnit": "100%" }, { @@ -1718,8 +1717,8 @@ "MetricExpr": "MEM_INST_RETIRED.SPLIT_STORES / tma_info_core_core_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_issueSpSt;tma_store_bound_group", "MetricName": "tma_split_stores", - "MetricThreshold": "tma_split_stores > 0.2 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", - "PublicDescription": "This metric represents rate of split store accesses. Consider aligning your data to the 64-byte cache line granularity. Sample with: MEM_INST_RETIRED.SPLIT_STORES", + "MetricThreshold": "tma_split_stores > 0.2 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric represents rate of split store accesses. Consider aligning your data to the 64-byte cache line granularity. Sample with: MEM_INST_RETIRED.SPLIT_STORES_PS. Related metrics: tma_port_4", "ScaleUnit": "100%" }, { @@ -1727,7 +1726,7 @@ "MetricExpr": "L1D_PEND_MISS.L2_STALL / tma_info_thread_clks", "MetricGroup": "BvMB;MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_issueBW;tma_l3_bound_group", "MetricName": "tma_sq_full", - "MetricThreshold": "tma_sq_full > 0.3 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_sq_full > 0.3 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", "PublicDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors). Related metrics: tma_bottleneck_cache_memory_bandwidth, tma_fb_full, tma_info_system_dram_bw_use, tma_mem_bandwidth", "ScaleUnit": "100%" }, @@ -1736,8 +1735,8 @@ "MetricExpr": "EXE_ACTIVITY.BOUND_ON_STORES / tma_info_thread_clks", "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_store_bound", - "MetricThreshold": "tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", - "PublicDescription": "This metric estimates how often CPU was stalled due to RFO store memory accesses; RFO store issue a read-for-ownership request before the write. Even though store accesses do not typically stall out-of-order CPUs; there are few cases where stores can lead to actual stalls. This metric will be flagged should RFO stores be a bottleneck. Sample with: MEM_INST_RETIRED.ALL_STORES", + "MetricThreshold": "tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", + "PublicDescription": "This metric estimates how often CPU was stalled due to RFO store memory accesses; RFO store issue a read-for-ownership request before the write. Even though store accesses do not typically stall out-of-order CPUs; there are few cases where stores can lead to actual stalls. This metric will be flagged should RFO stores be a bottleneck. Sample with: MEM_INST_RETIRED.ALL_STORES_PS", "ScaleUnit": "100%" }, { @@ -1746,8 +1745,8 @@ "MetricExpr": "13 * LD_BLOCKS.STORE_FORWARD / tma_info_thread_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group", "MetricName": "tma_store_fwd_blk", - "MetricThreshold": "tma_store_fwd_blk > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", - "PublicDescription": "This metric roughly estimates fraction of cycles when the memory subsystem had loads blocked since they could not forward data from earlier (in program order) overlapping stores. To streamline memory operations in the pipeline; a load can avoid waiting for memory if a prior in-flight store is writing the data that the load wants to read (store forwarding process). However; in some cases the load may be blocked for a significant time pending the store forward. For example; when the prior store is writing a smaller region than the load is reading", + "MetricThreshold": "tma_store_fwd_blk > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric roughly estimates fraction of cycles when the memory subsystem had loads blocked since they could not forward data from earlier (in program order) overlapping stores. To streamline memory operations in the pipeline; a load can avoid waiting for memory if a prior in-flight store is writing the data that the load wants to read (store forwarding process). However; in some cases the load may be blocked for a significant time pending the store forward. For example; when the prior store is writing a smaller region than the load is reading.", "ScaleUnit": "100%" }, { @@ -1755,8 +1754,8 @@ "MetricExpr": "(L2_RQSTS.RFO_HIT * 10 * (1 - MEM_INST_RETIRED.LOCK_LOADS / MEM_INST_RETIRED.ALL_STORES) + (1 - MEM_INST_RETIRED.LOCK_LOADS / MEM_INST_RETIRED.ALL_STORES) * min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO)) / tma_info_thread_clks", "MetricGroup": "BvML;LockCont;MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_issueSL;tma_store_bound_group", "MetricName": "tma_store_latency", - "MetricThreshold": "tma_store_latency > 0.1 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", - "PublicDescription": "This metric estimates fraction of cycles the CPU spent handling L1D store misses. Store accesses usually less impact out-of-order core performance; however; holding resources for longer time can lead into undesired implications (e.g. contention on L1D fill-buffer entries - see FB_Full). Related metrics: tma_branch_resteers, tma_fb_full, tma_l3_hit_latency, tma_lock_latency", + "MetricThreshold": "tma_store_latency > 0.1 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric estimates fraction of cycles the CPU spent handling L1D store misses. Store accesses usually less impact out-of-order core performance; however; holding resources for longer time can lead into undesired implications (e.g. contention on L1D fill-buffer entries - see FB_Full). Related metrics: tma_fb_full, tma_lock_latency", "ScaleUnit": "100%" }, { @@ -1773,7 +1772,7 @@ "MetricExpr": "tma_dtlb_store - tma_store_stlb_miss", "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_store_group", "MetricName": "tma_store_stlb_hit", - "MetricThreshold": "tma_store_stlb_hit > 0.05 & tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_store_stlb_hit > 0.05 & (tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))", "ScaleUnit": "100%" }, { @@ -1781,31 +1780,31 @@ "MetricExpr": "DTLB_STORE_MISSES.WALK_ACTIVE / tma_info_core_core_clks", "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_store_group", "MetricName": "tma_store_stlb_miss", - "MetricThreshold": "tma_store_stlb_miss > 0.05 & tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_store_stlb_miss > 0.05 & (tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 1 GB pages for data store accesses", + "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 1 GB pages for data store accesses.", "MetricExpr": "tma_store_stlb_miss * DTLB_STORE_MISSES.WALK_COMPLETED_1G / (DTLB_STORE_MISSES.WALK_COMPLETED_4K + DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M + DTLB_STORE_MISSES.WALK_COMPLETED_1G)", "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_store_stlb_miss_group", "MetricName": "tma_store_stlb_miss_1g", - "MetricThreshold": "tma_store_stlb_miss_1g > 0.05 & tma_store_stlb_miss > 0.05 & tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_store_stlb_miss_1g > 0.05 & (tma_store_stlb_miss > 0.05 & (tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))))", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 2 or 4 MB pages for data store accesses", + "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 2 or 4 MB pages for data store accesses.", "MetricExpr": "tma_store_stlb_miss * DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M / (DTLB_STORE_MISSES.WALK_COMPLETED_4K + DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M + DTLB_STORE_MISSES.WALK_COMPLETED_1G)", "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_store_stlb_miss_group", "MetricName": "tma_store_stlb_miss_2m", - "MetricThreshold": "tma_store_stlb_miss_2m > 0.05 & tma_store_stlb_miss > 0.05 & tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_store_stlb_miss_2m > 0.05 & (tma_store_stlb_miss > 0.05 & (tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))))", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 4 KB pages for data store accesses", + "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 4 KB pages for data store accesses.", "MetricExpr": "tma_store_stlb_miss * DTLB_STORE_MISSES.WALK_COMPLETED_4K / (DTLB_STORE_MISSES.WALK_COMPLETED_4K + DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M + DTLB_STORE_MISSES.WALK_COMPLETED_1G)", "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_store_stlb_miss_group", "MetricName": "tma_store_stlb_miss_4k", - "MetricThreshold": "tma_store_stlb_miss_4k > 0.05 & tma_store_stlb_miss > 0.05 & tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_store_stlb_miss_4k > 0.05 & (tma_store_stlb_miss > 0.05 & (tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))))", "ScaleUnit": "100%" }, { @@ -1813,7 +1812,7 @@ "MetricExpr": "9 * OCR.STREAMING_WR.ANY_RESPONSE / tma_info_thread_clks", "MetricGroup": "MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_issueSmSt;tma_store_bound_group", "MetricName": "tma_streaming_stores", - "MetricThreshold": "tma_streaming_stores > 0.2 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "tma_streaming_stores > 0.2 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", "PublicDescription": "This metric estimates how often CPU was stalled due to Streaming store memory accesses; Streaming store optimize out a read request required by RFO stores. Even though store accesses do not typically stall out-of-order CPUs; there are few cases where stores can lead to actual stalls. This metric will be flagged should Streaming stores be a bottleneck. Sample with: OCR.STREAMING_WR.ANY_RESPONSE. Related metrics: tma_fb_full", "ScaleUnit": "100%" }, @@ -1822,7 +1821,7 @@ "MetricExpr": "10 * BACLEARS.ANY / tma_info_thread_clks", "MetricGroup": "BigFootprint;BvBC;FetchLat;TopdownL4;tma_L4_group;tma_branch_resteers_group", "MetricName": "tma_unknown_branches", - "MetricThreshold": "tma_unknown_branches > 0.05 & tma_branch_resteers > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricThreshold": "tma_unknown_branches > 0.05 & (tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))", "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to new branch address clears. These are fetched branches the Branch Prediction Unit was unable to recognize (e.g. first time the branch is fetched or hitting BTB capacity limit) hence called Unknown Branches. Sample with: BACLEARS.ANY", "ScaleUnit": "100%" }, @@ -1831,8 +1830,8 @@ "MetricExpr": "tma_retiring * UOPS_EXECUTED.X87 / UOPS_EXECUTED.THREAD", "MetricGroup": "Compute;TopdownL4;tma_L4_group;tma_fp_arith_group", "MetricName": "tma_x87_use", - "MetricThreshold": "tma_x87_use > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6", - "PublicDescription": "This metric serves as an approximation of legacy x87 usage. It accounts for instructions beyond X87 FP arithmetic operations; hence may be used as a thermometer to avoid X87 high usage and preferably upgrade to modern ISA. See Tip under Tuning Hint", + "MetricThreshold": "tma_x87_use > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6)", + "PublicDescription": "This metric serves as an approximation of legacy x87 usage. It accounts for instructions beyond X87 FP arithmetic operations; hence may be used as a thermometer to avoid X87 high usage and preferably upgrade to modern ISA. See Tip under Tuning Hint.", "ScaleUnit": "100%" }, { diff --git a/tools/perf/pmu-events/arch/x86/westmereep-dp/cache.json b/tools/perf/pmu-events/arch/x86/westmereep-dp/cache.json index 30845c7dbf08..f6f95f3ff301 100644 --- a/tools/perf/pmu-events/arch/x86/westmereep-dp/cache.json +++ b/tools/perf/pmu-events/arch/x86/westmereep-dp/cache.json @@ -120,6 +120,38 @@ "UMask": "0x2" }, { + "BriefDescription": "L1I instruction fetch stall cycles", + "Counter": "0,1,2,3", + "EventCode": "0x80", + "EventName": "L1I.CYCLES_STALLED", + "SampleAfterValue": "2000000", + "UMask": "0x4" + }, + { + "BriefDescription": "L1I instruction fetch hits", + "Counter": "0,1,2,3", + "EventCode": "0x80", + "EventName": "L1I.HITS", + "SampleAfterValue": "2000000", + "UMask": "0x1" + }, + { + "BriefDescription": "L1I instruction fetch misses", + "Counter": "0,1,2,3", + "EventCode": "0x80", + "EventName": "L1I.MISSES", + "SampleAfterValue": "2000000", + "UMask": "0x2" + }, + { + "BriefDescription": "L1I Instruction fetches", + "Counter": "0,1,2,3", + "EventCode": "0x80", + "EventName": "L1I.READS", + "SampleAfterValue": "2000000", + "UMask": "0x3" + }, + { "BriefDescription": "All L2 data requests", "Counter": "0,1,2,3", "EventCode": "0x26", diff --git a/tools/perf/pmu-events/arch/x86/westmereep-dp/other.json b/tools/perf/pmu-events/arch/x86/westmereep-dp/other.json index bcf5bcf637c0..c0cf8bae8074 100644 --- a/tools/perf/pmu-events/arch/x86/westmereep-dp/other.json +++ b/tools/perf/pmu-events/arch/x86/westmereep-dp/other.json @@ -16,46 +16,6 @@ "UMask": "0x1" }, { - "BriefDescription": "L1I instruction fetch stall cycles", - "Counter": "0,1,2,3", - "EventCode": "0x80", - "EventName": "L1I.CYCLES_STALLED", - "SampleAfterValue": "2000000", - "UMask": "0x4" - }, - { - "BriefDescription": "L1I instruction fetch hits", - "Counter": "0,1,2,3", - "EventCode": "0x80", - "EventName": "L1I.HITS", - "SampleAfterValue": "2000000", - "UMask": "0x1" - }, - { - "BriefDescription": "L1I instruction fetch misses", - "Counter": "0,1,2,3", - "EventCode": "0x80", - "EventName": "L1I.MISSES", - "SampleAfterValue": "2000000", - "UMask": "0x2" - }, - { - "BriefDescription": "L1I Instruction fetches", - "Counter": "0,1,2,3", - "EventCode": "0x80", - "EventName": "L1I.READS", - "SampleAfterValue": "2000000", - "UMask": "0x3" - }, - { - "BriefDescription": "Large ITLB hit", - "Counter": "0,1,2,3", - "EventCode": "0x82", - "EventName": "LARGE_ITLB.HIT", - "SampleAfterValue": "200000", - "UMask": "0x1" - }, - { "BriefDescription": "Loads that partially overlap an earlier store", "Counter": "0,1,2,3", "EventCode": "0x3", diff --git a/tools/perf/pmu-events/arch/x86/westmereep-dp/virtual-memory.json b/tools/perf/pmu-events/arch/x86/westmereep-dp/virtual-memory.json index 53d7f76325a3..84c920637b12 100644 --- a/tools/perf/pmu-events/arch/x86/westmereep-dp/virtual-memory.json +++ b/tools/perf/pmu-events/arch/x86/westmereep-dp/virtual-memory.json @@ -153,6 +153,14 @@ "UMask": "0x20" }, { + "BriefDescription": "Large ITLB hit", + "Counter": "0,1,2,3", + "EventCode": "0x82", + "EventName": "LARGE_ITLB.HIT", + "SampleAfterValue": "200000", + "UMask": "0x1" + }, + { "BriefDescription": "Retired loads that miss the DTLB (Precise Event)", "Counter": "0,1,2,3", "EventCode": "0xCB", diff --git a/tools/perf/pmu-events/arch/x86/westmereep-sp/cache.json b/tools/perf/pmu-events/arch/x86/westmereep-sp/cache.json index 90cb367f5798..0cd571472dca 100644 --- a/tools/perf/pmu-events/arch/x86/westmereep-sp/cache.json +++ b/tools/perf/pmu-events/arch/x86/westmereep-sp/cache.json @@ -120,6 +120,38 @@ "UMask": "0x2" }, { + "BriefDescription": "L1I instruction fetch stall cycles", + "Counter": "0,1,2,3", + "EventCode": "0x80", + "EventName": "L1I.CYCLES_STALLED", + "SampleAfterValue": "2000000", + "UMask": "0x4" + }, + { + "BriefDescription": "L1I instruction fetch hits", + "Counter": "0,1,2,3", + "EventCode": "0x80", + "EventName": "L1I.HITS", + "SampleAfterValue": "2000000", + "UMask": "0x1" + }, + { + "BriefDescription": "L1I instruction fetch misses", + "Counter": "0,1,2,3", + "EventCode": "0x80", + "EventName": "L1I.MISSES", + "SampleAfterValue": "2000000", + "UMask": "0x2" + }, + { + "BriefDescription": "L1I Instruction fetches", + "Counter": "0,1,2,3", + "EventCode": "0x80", + "EventName": "L1I.READS", + "SampleAfterValue": "2000000", + "UMask": "0x3" + }, + { "BriefDescription": "All L2 data requests", "Counter": "0,1,2,3", "EventCode": "0x26", diff --git a/tools/perf/pmu-events/arch/x86/westmereep-sp/other.json b/tools/perf/pmu-events/arch/x86/westmereep-sp/other.json index bcf5bcf637c0..c0cf8bae8074 100644 --- a/tools/perf/pmu-events/arch/x86/westmereep-sp/other.json +++ b/tools/perf/pmu-events/arch/x86/westmereep-sp/other.json @@ -16,46 +16,6 @@ "UMask": "0x1" }, { - "BriefDescription": "L1I instruction fetch stall cycles", - "Counter": "0,1,2,3", - "EventCode": "0x80", - "EventName": "L1I.CYCLES_STALLED", - "SampleAfterValue": "2000000", - "UMask": "0x4" - }, - { - "BriefDescription": "L1I instruction fetch hits", - "Counter": "0,1,2,3", - "EventCode": "0x80", - "EventName": "L1I.HITS", - "SampleAfterValue": "2000000", - "UMask": "0x1" - }, - { - "BriefDescription": "L1I instruction fetch misses", - "Counter": "0,1,2,3", - "EventCode": "0x80", - "EventName": "L1I.MISSES", - "SampleAfterValue": "2000000", - "UMask": "0x2" - }, - { - "BriefDescription": "L1I Instruction fetches", - "Counter": "0,1,2,3", - "EventCode": "0x80", - "EventName": "L1I.READS", - "SampleAfterValue": "2000000", - "UMask": "0x3" - }, - { - "BriefDescription": "Large ITLB hit", - "Counter": "0,1,2,3", - "EventCode": "0x82", - "EventName": "LARGE_ITLB.HIT", - "SampleAfterValue": "200000", - "UMask": "0x1" - }, - { "BriefDescription": "Loads that partially overlap an earlier store", "Counter": "0,1,2,3", "EventCode": "0x3", diff --git a/tools/perf/pmu-events/arch/x86/westmereep-sp/virtual-memory.json b/tools/perf/pmu-events/arch/x86/westmereep-sp/virtual-memory.json index e7affdf7f41b..a1b22c82a9bf 100644 --- a/tools/perf/pmu-events/arch/x86/westmereep-sp/virtual-memory.json +++ b/tools/perf/pmu-events/arch/x86/westmereep-sp/virtual-memory.json @@ -129,6 +129,14 @@ "UMask": "0x20" }, { + "BriefDescription": "Large ITLB hit", + "Counter": "0,1,2,3", + "EventCode": "0x82", + "EventName": "LARGE_ITLB.HIT", + "SampleAfterValue": "200000", + "UMask": "0x1" + }, + { "BriefDescription": "Retired loads that miss the DTLB (Precise Event)", "Counter": "0,1,2,3", "EventCode": "0xCB", diff --git a/tools/perf/pmu-events/arch/x86/westmereex/cache.json b/tools/perf/pmu-events/arch/x86/westmereex/cache.json index 9f922370ee8b..2a677d10f688 100644 --- a/tools/perf/pmu-events/arch/x86/westmereex/cache.json +++ b/tools/perf/pmu-events/arch/x86/westmereex/cache.json @@ -120,6 +120,38 @@ "UMask": "0x2" }, { + "BriefDescription": "L1I instruction fetch stall cycles", + "Counter": "0,1,2,3", + "EventCode": "0x80", + "EventName": "L1I.CYCLES_STALLED", + "SampleAfterValue": "2000000", + "UMask": "0x4" + }, + { + "BriefDescription": "L1I instruction fetch hits", + "Counter": "0,1,2,3", + "EventCode": "0x80", + "EventName": "L1I.HITS", + "SampleAfterValue": "2000000", + "UMask": "0x1" + }, + { + "BriefDescription": "L1I instruction fetch misses", + "Counter": "0,1,2,3", + "EventCode": "0x80", + "EventName": "L1I.MISSES", + "SampleAfterValue": "2000000", + "UMask": "0x2" + }, + { + "BriefDescription": "L1I Instruction fetches", + "Counter": "0,1,2,3", + "EventCode": "0x80", + "EventName": "L1I.READS", + "SampleAfterValue": "2000000", + "UMask": "0x3" + }, + { "BriefDescription": "All L2 data requests", "Counter": "0,1,2,3", "EventCode": "0x26", diff --git a/tools/perf/pmu-events/arch/x86/westmereex/other.json b/tools/perf/pmu-events/arch/x86/westmereex/other.json index bcf5bcf637c0..c0cf8bae8074 100644 --- a/tools/perf/pmu-events/arch/x86/westmereex/other.json +++ b/tools/perf/pmu-events/arch/x86/westmereex/other.json @@ -16,46 +16,6 @@ "UMask": "0x1" }, { - "BriefDescription": "L1I instruction fetch stall cycles", - "Counter": "0,1,2,3", - "EventCode": "0x80", - "EventName": "L1I.CYCLES_STALLED", - "SampleAfterValue": "2000000", - "UMask": "0x4" - }, - { - "BriefDescription": "L1I instruction fetch hits", - "Counter": "0,1,2,3", - "EventCode": "0x80", - "EventName": "L1I.HITS", - "SampleAfterValue": "2000000", - "UMask": "0x1" - }, - { - "BriefDescription": "L1I instruction fetch misses", - "Counter": "0,1,2,3", - "EventCode": "0x80", - "EventName": "L1I.MISSES", - "SampleAfterValue": "2000000", - "UMask": "0x2" - }, - { - "BriefDescription": "L1I Instruction fetches", - "Counter": "0,1,2,3", - "EventCode": "0x80", - "EventName": "L1I.READS", - "SampleAfterValue": "2000000", - "UMask": "0x3" - }, - { - "BriefDescription": "Large ITLB hit", - "Counter": "0,1,2,3", - "EventCode": "0x82", - "EventName": "LARGE_ITLB.HIT", - "SampleAfterValue": "200000", - "UMask": "0x1" - }, - { "BriefDescription": "Loads that partially overlap an earlier store", "Counter": "0,1,2,3", "EventCode": "0x3", diff --git a/tools/perf/pmu-events/arch/x86/westmereex/virtual-memory.json b/tools/perf/pmu-events/arch/x86/westmereex/virtual-memory.json index 0c3501e6e5a3..1800c6ecbf80 100644 --- a/tools/perf/pmu-events/arch/x86/westmereex/virtual-memory.json +++ b/tools/perf/pmu-events/arch/x86/westmereex/virtual-memory.json @@ -153,6 +153,14 @@ "UMask": "0x20" }, { + "BriefDescription": "Large ITLB hit", + "Counter": "0,1,2,3", + "EventCode": "0x82", + "EventName": "LARGE_ITLB.HIT", + "SampleAfterValue": "200000", + "UMask": "0x1" + }, + { "BriefDescription": "Retired loads that miss the DTLB (Precise Event)", "Counter": "0,1,2,3", "EventCode": "0xCB", diff --git a/tools/perf/pmu-events/empty-pmu-events.c b/tools/perf/pmu-events/empty-pmu-events.c index 0cb7ba7912e8..d4017007a991 100644 --- a/tools/perf/pmu-events/empty-pmu-events.c +++ b/tools/perf/pmu-events/empty-pmu-events.c @@ -20,73 +20,73 @@ struct pmu_table_entry { static const char *const big_c_string = /* offset=0 */ "tool\000" -/* offset=5 */ "duration_time\000tool\000Wall clock interval time in nanoseconds\000config=1\000\00000\000\000" -/* offset=78 */ "user_time\000tool\000User (non-kernel) time in nanoseconds\000config=2\000\00000\000\000" -/* offset=145 */ "system_time\000tool\000System/kernel time in nanoseconds\000config=3\000\00000\000\000" -/* offset=210 */ "has_pmem\000tool\0001 if persistent memory installed otherwise 0\000config=4\000\00000\000\000" -/* offset=283 */ "num_cores\000tool\000Number of cores. A core consists of 1 or more thread, with each thread being associated with a logical Linux CPU\000config=5\000\00000\000\000" -/* offset=425 */ "num_cpus\000tool\000Number of logical Linux CPUs. There may be multiple such CPUs on a core\000config=6\000\00000\000\000" -/* offset=525 */ "num_cpus_online\000tool\000Number of online logical Linux CPUs. There may be multiple such CPUs on a core\000config=7\000\00000\000\000" -/* offset=639 */ "num_dies\000tool\000Number of dies. Each die has 1 or more cores\000config=8\000\00000\000\000" -/* offset=712 */ "num_packages\000tool\000Number of packages. Each package has 1 or more die\000config=9\000\00000\000\000" -/* offset=795 */ "slots\000tool\000Number of functional units that in parallel can execute parts of an instruction\000config=0xa\000\00000\000\000" -/* offset=902 */ "smt_on\000tool\0001 if simultaneous multithreading (aka hyperthreading) is enable otherwise 0\000config=0xb\000\00000\000\000" -/* offset=1006 */ "system_tsc_freq\000tool\000The amount a Time Stamp Counter (TSC) increases per second\000config=0xc\000\00000\000\000" -/* offset=1102 */ "default_core\000" -/* offset=1115 */ "bp_l1_btb_correct\000branch\000L1 BTB Correction\000event=0x8a\000\00000\000\000" -/* offset=1174 */ "bp_l2_btb_correct\000branch\000L2 BTB Correction\000event=0x8b\000\00000\000\000" -/* offset=1233 */ "l3_cache_rd\000cache\000L3 cache access, read\000event=0x40\000\00000\000Attributable Level 3 cache access, read\000" -/* offset=1328 */ "segment_reg_loads.any\000other\000Number of segment register loads\000event=6,period=200000,umask=0x80\000\00000\000\000" -/* offset=1427 */ "dispatch_blocked.any\000other\000Memory cluster signals to block micro-op dispatch for any reason\000event=9,period=200000,umask=0x20\000\00000\000\000" -/* offset=1557 */ "eist_trans\000other\000Number of Enhanced Intel SpeedStep(R) Technology (EIST) transitions\000event=0x3a,period=200000\000\00000\000\000" -/* offset=1672 */ "hisi_sccl,ddrc\000" -/* offset=1687 */ "uncore_hisi_ddrc.flux_wcmd\000uncore\000DDRC write commands\000event=2\000\00000\000DDRC write commands\000" -/* offset=1773 */ "uncore_cbox\000" -/* offset=1785 */ "unc_cbo_xsnp_response.miss_eviction\000uncore\000A cross-core snoop resulted from L3 Eviction which misses in some processor core\000event=0x22,umask=0x81\000\00000\000A cross-core snoop resulted from L3 Eviction which misses in some processor core\000" -/* offset=2016 */ "event-hyphen\000uncore\000UNC_CBO_HYPHEN\000event=0xe0\000\00000\000UNC_CBO_HYPHEN\000" -/* offset=2081 */ "event-two-hyph\000uncore\000UNC_CBO_TWO_HYPH\000event=0xc0\000\00000\000UNC_CBO_TWO_HYPH\000" -/* offset=2152 */ "hisi_sccl,l3c\000" -/* offset=2166 */ "uncore_hisi_l3c.rd_hit_cpipe\000uncore\000Total read hits\000event=7\000\00000\000Total read hits\000" -/* offset=2246 */ "uncore_imc_free_running\000" -/* offset=2270 */ "uncore_imc_free_running.cache_miss\000uncore\000Total cache misses\000event=0x12\000\00000\000Total cache misses\000" -/* offset=2365 */ "uncore_imc\000" -/* offset=2376 */ "uncore_imc.cache_hits\000uncore\000Total cache hits\000event=0x34\000\00000\000Total cache hits\000" -/* offset=2454 */ "uncore_sys_ddr_pmu\000" -/* offset=2473 */ "sys_ddr_pmu.write_cycles\000uncore\000ddr write-cycles event\000event=0x2b\000v8\00000\000\000" -/* offset=2546 */ "uncore_sys_ccn_pmu\000" -/* offset=2565 */ "sys_ccn_pmu.read_cycles\000uncore\000ccn read-cycles event\000config=0x2c\0000x01\00000\000\000" -/* offset=2639 */ "uncore_sys_cmn_pmu\000" -/* offset=2658 */ "sys_cmn_pmu.hnf_cache_miss\000uncore\000Counts total cache misses in first lookup result (high priority)\000eventid=1,type=5\000(434|436|43c|43a).*\00000\000\000" -/* offset=2798 */ "CPI\000\0001 / IPC\000\000\000\000\000\000\000\00000" -/* offset=2820 */ "IPC\000group1\000inst_retired.any / cpu_clk_unhalted.thread\000\000\000\000\000\000\000\00000" -/* offset=2883 */ "Frontend_Bound_SMT\000\000idq_uops_not_delivered.core / (4 * (cpu_clk_unhalted.thread / 2 * (1 + cpu_clk_unhalted.one_thread_active / cpu_clk_unhalted.ref_xclk)))\000\000\000\000\000\000\000\00000" -/* offset=3049 */ "dcache_miss_cpi\000\000l1d\\-loads\\-misses / inst_retired.any\000\000\000\000\000\000\000\00000" -/* offset=3113 */ "icache_miss_cycles\000\000l1i\\-loads\\-misses / inst_retired.any\000\000\000\000\000\000\000\00000" -/* offset=3180 */ "cache_miss_cycles\000group1\000dcache_miss_cpi + icache_miss_cycles\000\000\000\000\000\000\000\00000" -/* offset=3251 */ "DCache_L2_All_Hits\000\000l2_rqsts.demand_data_rd_hit + l2_rqsts.pf_hit + l2_rqsts.rfo_hit\000\000\000\000\000\000\000\00000" -/* offset=3345 */ "DCache_L2_All_Miss\000\000max(l2_rqsts.all_demand_data_rd - l2_rqsts.demand_data_rd_hit, 0) + l2_rqsts.pf_miss + l2_rqsts.rfo_miss\000\000\000\000\000\000\000\00000" -/* offset=3479 */ "DCache_L2_All\000\000DCache_L2_All_Hits + DCache_L2_All_Miss\000\000\000\000\000\000\000\00000" -/* offset=3543 */ "DCache_L2_Hits\000\000d_ratio(DCache_L2_All_Hits, DCache_L2_All)\000\000\000\000\000\000\000\00000" -/* offset=3611 */ "DCache_L2_Misses\000\000d_ratio(DCache_L2_All_Miss, DCache_L2_All)\000\000\000\000\000\000\000\00000" -/* offset=3681 */ "M1\000\000ipc + M2\000\000\000\000\000\000\000\00000" -/* offset=3703 */ "M2\000\000ipc + M1\000\000\000\000\000\000\000\00000" -/* offset=3725 */ "M3\000\0001 / M3\000\000\000\000\000\000\000\00000" -/* offset=3745 */ "L1D_Cache_Fill_BW\000\00064 * l1d.replacement / 1e9 / duration_time\000\000\000\000\000\000\000\00000" +/* offset=5 */ "duration_time\000tool\000Wall clock interval time in nanoseconds\000config=1\000\00000\000\000\000\000\000" +/* offset=81 */ "user_time\000tool\000User (non-kernel) time in nanoseconds\000config=2\000\00000\000\000\000\000\000" +/* offset=151 */ "system_time\000tool\000System/kernel time in nanoseconds\000config=3\000\00000\000\000\000\000\000" +/* offset=219 */ "has_pmem\000tool\0001 if persistent memory installed otherwise 0\000config=4\000\00000\000\000\000\000\000" +/* offset=295 */ "num_cores\000tool\000Number of cores. A core consists of 1 or more thread, with each thread being associated with a logical Linux CPU\000config=5\000\00000\000\000\000\000\000" +/* offset=440 */ "num_cpus\000tool\000Number of logical Linux CPUs. There may be multiple such CPUs on a core\000config=6\000\00000\000\000\000\000\000" +/* offset=543 */ "num_cpus_online\000tool\000Number of online logical Linux CPUs. There may be multiple such CPUs on a core\000config=7\000\00000\000\000\000\000\000" +/* offset=660 */ "num_dies\000tool\000Number of dies. Each die has 1 or more cores\000config=8\000\00000\000\000\000\000\000" +/* offset=736 */ "num_packages\000tool\000Number of packages. Each package has 1 or more die\000config=9\000\00000\000\000\000\000\000" +/* offset=822 */ "slots\000tool\000Number of functional units that in parallel can execute parts of an instruction\000config=0xa\000\00000\000\000\000\000\000" +/* offset=932 */ "smt_on\000tool\0001 if simultaneous multithreading (aka hyperthreading) is enable otherwise 0\000config=0xb\000\00000\000\000\000\000\000" +/* offset=1039 */ "system_tsc_freq\000tool\000The amount a Time Stamp Counter (TSC) increases per second\000config=0xc\000\00000\000\000\000\000\000" +/* offset=1138 */ "default_core\000" +/* offset=1151 */ "bp_l1_btb_correct\000branch\000L1 BTB Correction\000event=0x8a\000\00000\000\000\000\000\000" +/* offset=1213 */ "bp_l2_btb_correct\000branch\000L2 BTB Correction\000event=0x8b\000\00000\000\000\000\000\000" +/* offset=1275 */ "l3_cache_rd\000cache\000L3 cache access, read\000event=0x40\000\00000\000\000\000\000Attributable Level 3 cache access, read\000" +/* offset=1373 */ "segment_reg_loads.any\000other\000Number of segment register loads\000event=6,period=200000,umask=0x80\000\00000\000\000\000\000\000" +/* offset=1475 */ "dispatch_blocked.any\000other\000Memory cluster signals to block micro-op dispatch for any reason\000event=9,period=200000,umask=0x20\000\00000\000\000\000\000\000" +/* offset=1608 */ "eist_trans\000other\000Number of Enhanced Intel SpeedStep(R) Technology (EIST) transitions\000event=0x3a,period=200000\000\00000\000\000\000\000\000" +/* offset=1726 */ "hisi_sccl,ddrc\000" +/* offset=1741 */ "uncore_hisi_ddrc.flux_wcmd\000uncore\000DDRC write commands\000event=2\000\00000\000\000\000\000DDRC write commands\000" +/* offset=1830 */ "uncore_cbox\000" +/* offset=1842 */ "unc_cbo_xsnp_response.miss_eviction\000uncore\000A cross-core snoop resulted from L3 Eviction which misses in some processor core\000event=0x22,umask=0x81\000\00000\000\000\000\000A cross-core snoop resulted from L3 Eviction which misses in some processor core\000" +/* offset=2076 */ "event-hyphen\000uncore\000UNC_CBO_HYPHEN\000event=0xe0\000\00000\000\000\000\000UNC_CBO_HYPHEN\000" +/* offset=2144 */ "event-two-hyph\000uncore\000UNC_CBO_TWO_HYPH\000event=0xc0\000\00000\000\000\000\000UNC_CBO_TWO_HYPH\000" +/* offset=2218 */ "hisi_sccl,l3c\000" +/* offset=2232 */ "uncore_hisi_l3c.rd_hit_cpipe\000uncore\000Total read hits\000event=7\000\00000\000\000\000\000Total read hits\000" +/* offset=2315 */ "uncore_imc_free_running\000" +/* offset=2339 */ "uncore_imc_free_running.cache_miss\000uncore\000Total cache misses\000event=0x12\000\00000\000\000\000\000Total cache misses\000" +/* offset=2437 */ "uncore_imc\000" +/* offset=2448 */ "uncore_imc.cache_hits\000uncore\000Total cache hits\000event=0x34\000\00000\000\000\000\000Total cache hits\000" +/* offset=2529 */ "uncore_sys_ddr_pmu\000" +/* offset=2548 */ "sys_ddr_pmu.write_cycles\000uncore\000ddr write-cycles event\000event=0x2b\000v8\00000\000\000\000\000\000" +/* offset=2624 */ "uncore_sys_ccn_pmu\000" +/* offset=2643 */ "sys_ccn_pmu.read_cycles\000uncore\000ccn read-cycles event\000config=0x2c\0000x01\00000\000\000\000\000\000" +/* offset=2720 */ "uncore_sys_cmn_pmu\000" +/* offset=2739 */ "sys_cmn_pmu.hnf_cache_miss\000uncore\000Counts total cache misses in first lookup result (high priority)\000eventid=1,type=5\000(434|436|43c|43a).*\00000\000\000\000\000\000" +/* offset=2882 */ "CPI\000\0001 / IPC\000\000\000\000\000\000\000\00000" +/* offset=2904 */ "IPC\000group1\000inst_retired.any / cpu_clk_unhalted.thread\000\000\000\000\000\000\000\00000" +/* offset=2967 */ "Frontend_Bound_SMT\000\000idq_uops_not_delivered.core / (4 * (cpu_clk_unhalted.thread / 2 * (1 + cpu_clk_unhalted.one_thread_active / cpu_clk_unhalted.ref_xclk)))\000\000\000\000\000\000\000\00000" +/* offset=3133 */ "dcache_miss_cpi\000\000l1d\\-loads\\-misses / inst_retired.any\000\000\000\000\000\000\000\00000" +/* offset=3197 */ "icache_miss_cycles\000\000l1i\\-loads\\-misses / inst_retired.any\000\000\000\000\000\000\000\00000" +/* offset=3264 */ "cache_miss_cycles\000group1\000dcache_miss_cpi + icache_miss_cycles\000\000\000\000\000\000\000\00000" +/* offset=3335 */ "DCache_L2_All_Hits\000\000l2_rqsts.demand_data_rd_hit + l2_rqsts.pf_hit + l2_rqsts.rfo_hit\000\000\000\000\000\000\000\00000" +/* offset=3429 */ "DCache_L2_All_Miss\000\000max(l2_rqsts.all_demand_data_rd - l2_rqsts.demand_data_rd_hit, 0) + l2_rqsts.pf_miss + l2_rqsts.rfo_miss\000\000\000\000\000\000\000\00000" +/* offset=3563 */ "DCache_L2_All\000\000DCache_L2_All_Hits + DCache_L2_All_Miss\000\000\000\000\000\000\000\00000" +/* offset=3627 */ "DCache_L2_Hits\000\000d_ratio(DCache_L2_All_Hits, DCache_L2_All)\000\000\000\000\000\000\000\00000" +/* offset=3695 */ "DCache_L2_Misses\000\000d_ratio(DCache_L2_All_Miss, DCache_L2_All)\000\000\000\000\000\000\000\00000" +/* offset=3765 */ "M1\000\000ipc + M2\000\000\000\000\000\000\000\00000" +/* offset=3787 */ "M2\000\000ipc + M1\000\000\000\000\000\000\000\00000" +/* offset=3809 */ "M3\000\0001 / M3\000\000\000\000\000\000\000\00000" +/* offset=3829 */ "L1D_Cache_Fill_BW\000\00064 * l1d.replacement / 1e9 / duration_time\000\000\000\000\000\000\000\00000" ; static const struct compact_pmu_event pmu_events__common_tool[] = { -{ 5 }, /* duration_time\000tool\000Wall clock interval time in nanoseconds\000config=1\000\00000\000\000 */ -{ 210 }, /* has_pmem\000tool\0001 if persistent memory installed otherwise 0\000config=4\000\00000\000\000 */ -{ 283 }, /* num_cores\000tool\000Number of cores. A core consists of 1 or more thread, with each thread being associated with a logical Linux CPU\000config=5\000\00000\000\000 */ -{ 425 }, /* num_cpus\000tool\000Number of logical Linux CPUs. There may be multiple such CPUs on a core\000config=6\000\00000\000\000 */ -{ 525 }, /* num_cpus_online\000tool\000Number of online logical Linux CPUs. There may be multiple such CPUs on a core\000config=7\000\00000\000\000 */ -{ 639 }, /* num_dies\000tool\000Number of dies. Each die has 1 or more cores\000config=8\000\00000\000\000 */ -{ 712 }, /* num_packages\000tool\000Number of packages. Each package has 1 or more die\000config=9\000\00000\000\000 */ -{ 795 }, /* slots\000tool\000Number of functional units that in parallel can execute parts of an instruction\000config=0xa\000\00000\000\000 */ -{ 902 }, /* smt_on\000tool\0001 if simultaneous multithreading (aka hyperthreading) is enable otherwise 0\000config=0xb\000\00000\000\000 */ -{ 145 }, /* system_time\000tool\000System/kernel time in nanoseconds\000config=3\000\00000\000\000 */ -{ 1006 }, /* system_tsc_freq\000tool\000The amount a Time Stamp Counter (TSC) increases per second\000config=0xc\000\00000\000\000 */ -{ 78 }, /* user_time\000tool\000User (non-kernel) time in nanoseconds\000config=2\000\00000\000\000 */ +{ 5 }, /* duration_time\000tool\000Wall clock interval time in nanoseconds\000config=1\000\00000\000\000\000\000\000 */ +{ 219 }, /* has_pmem\000tool\0001 if persistent memory installed otherwise 0\000config=4\000\00000\000\000\000\000\000 */ +{ 295 }, /* num_cores\000tool\000Number of cores. A core consists of 1 or more thread, with each thread being associated with a logical Linux CPU\000config=5\000\00000\000\000\000\000\000 */ +{ 440 }, /* num_cpus\000tool\000Number of logical Linux CPUs. There may be multiple such CPUs on a core\000config=6\000\00000\000\000\000\000\000 */ +{ 543 }, /* num_cpus_online\000tool\000Number of online logical Linux CPUs. There may be multiple such CPUs on a core\000config=7\000\00000\000\000\000\000\000 */ +{ 660 }, /* num_dies\000tool\000Number of dies. Each die has 1 or more cores\000config=8\000\00000\000\000\000\000\000 */ +{ 736 }, /* num_packages\000tool\000Number of packages. Each package has 1 or more die\000config=9\000\00000\000\000\000\000\000 */ +{ 822 }, /* slots\000tool\000Number of functional units that in parallel can execute parts of an instruction\000config=0xa\000\00000\000\000\000\000\000 */ +{ 932 }, /* smt_on\000tool\0001 if simultaneous multithreading (aka hyperthreading) is enable otherwise 0\000config=0xb\000\00000\000\000\000\000\000 */ +{ 151 }, /* system_time\000tool\000System/kernel time in nanoseconds\000config=3\000\00000\000\000\000\000\000 */ +{ 1039 }, /* system_tsc_freq\000tool\000The amount a Time Stamp Counter (TSC) increases per second\000config=0xc\000\00000\000\000\000\000\000 */ +{ 81 }, /* user_time\000tool\000User (non-kernel) time in nanoseconds\000config=2\000\00000\000\000\000\000\000 */ }; @@ -99,29 +99,29 @@ const struct pmu_table_entry pmu_events__common[] = { }; static const struct compact_pmu_event pmu_events__test_soc_cpu_default_core[] = { -{ 1115 }, /* bp_l1_btb_correct\000branch\000L1 BTB Correction\000event=0x8a\000\00000\000\000 */ -{ 1174 }, /* bp_l2_btb_correct\000branch\000L2 BTB Correction\000event=0x8b\000\00000\000\000 */ -{ 1427 }, /* dispatch_blocked.any\000other\000Memory cluster signals to block micro-op dispatch for any reason\000event=9,period=200000,umask=0x20\000\00000\000\000 */ -{ 1557 }, /* eist_trans\000other\000Number of Enhanced Intel SpeedStep(R) Technology (EIST) transitions\000event=0x3a,period=200000\000\00000\000\000 */ -{ 1233 }, /* l3_cache_rd\000cache\000L3 cache access, read\000event=0x40\000\00000\000Attributable Level 3 cache access, read\000 */ -{ 1328 }, /* segment_reg_loads.any\000other\000Number of segment register loads\000event=6,period=200000,umask=0x80\000\00000\000\000 */ +{ 1151 }, /* bp_l1_btb_correct\000branch\000L1 BTB Correction\000event=0x8a\000\00000\000\000\000\000\000 */ +{ 1213 }, /* bp_l2_btb_correct\000branch\000L2 BTB Correction\000event=0x8b\000\00000\000\000\000\000\000 */ +{ 1475 }, /* dispatch_blocked.any\000other\000Memory cluster signals to block micro-op dispatch for any reason\000event=9,period=200000,umask=0x20\000\00000\000\000\000\000\000 */ +{ 1608 }, /* eist_trans\000other\000Number of Enhanced Intel SpeedStep(R) Technology (EIST) transitions\000event=0x3a,period=200000\000\00000\000\000\000\000\000 */ +{ 1275 }, /* l3_cache_rd\000cache\000L3 cache access, read\000event=0x40\000\00000\000\000\000\000Attributable Level 3 cache access, read\000 */ +{ 1373 }, /* segment_reg_loads.any\000other\000Number of segment register loads\000event=6,period=200000,umask=0x80\000\00000\000\000\000\000\000 */ }; static const struct compact_pmu_event pmu_events__test_soc_cpu_hisi_sccl_ddrc[] = { -{ 1687 }, /* uncore_hisi_ddrc.flux_wcmd\000uncore\000DDRC write commands\000event=2\000\00000\000DDRC write commands\000 */ +{ 1741 }, /* uncore_hisi_ddrc.flux_wcmd\000uncore\000DDRC write commands\000event=2\000\00000\000\000\000\000DDRC write commands\000 */ }; static const struct compact_pmu_event pmu_events__test_soc_cpu_hisi_sccl_l3c[] = { -{ 2166 }, /* uncore_hisi_l3c.rd_hit_cpipe\000uncore\000Total read hits\000event=7\000\00000\000Total read hits\000 */ +{ 2232 }, /* uncore_hisi_l3c.rd_hit_cpipe\000uncore\000Total read hits\000event=7\000\00000\000\000\000\000Total read hits\000 */ }; static const struct compact_pmu_event pmu_events__test_soc_cpu_uncore_cbox[] = { -{ 2016 }, /* event-hyphen\000uncore\000UNC_CBO_HYPHEN\000event=0xe0\000\00000\000UNC_CBO_HYPHEN\000 */ -{ 2081 }, /* event-two-hyph\000uncore\000UNC_CBO_TWO_HYPH\000event=0xc0\000\00000\000UNC_CBO_TWO_HYPH\000 */ -{ 1785 }, /* unc_cbo_xsnp_response.miss_eviction\000uncore\000A cross-core snoop resulted from L3 Eviction which misses in some processor core\000event=0x22,umask=0x81\000\00000\000A cross-core snoop resulted from L3 Eviction which misses in some processor core\000 */ +{ 2076 }, /* event-hyphen\000uncore\000UNC_CBO_HYPHEN\000event=0xe0\000\00000\000\000\000\000UNC_CBO_HYPHEN\000 */ +{ 2144 }, /* event-two-hyph\000uncore\000UNC_CBO_TWO_HYPH\000event=0xc0\000\00000\000\000\000\000UNC_CBO_TWO_HYPH\000 */ +{ 1842 }, /* unc_cbo_xsnp_response.miss_eviction\000uncore\000A cross-core snoop resulted from L3 Eviction which misses in some processor core\000event=0x22,umask=0x81\000\00000\000\000\000\000A cross-core snoop resulted from L3 Eviction which misses in some processor core\000 */ }; static const struct compact_pmu_event pmu_events__test_soc_cpu_uncore_imc[] = { -{ 2376 }, /* uncore_imc.cache_hits\000uncore\000Total cache hits\000event=0x34\000\00000\000Total cache hits\000 */ +{ 2448 }, /* uncore_imc.cache_hits\000uncore\000Total cache hits\000event=0x34\000\00000\000\000\000\000Total cache hits\000 */ }; static const struct compact_pmu_event pmu_events__test_soc_cpu_uncore_imc_free_running[] = { -{ 2270 }, /* uncore_imc_free_running.cache_miss\000uncore\000Total cache misses\000event=0x12\000\00000\000Total cache misses\000 */ +{ 2339 }, /* uncore_imc_free_running.cache_miss\000uncore\000Total cache misses\000event=0x12\000\00000\000\000\000\000Total cache misses\000 */ }; @@ -129,51 +129,51 @@ const struct pmu_table_entry pmu_events__test_soc_cpu[] = { { .entries = pmu_events__test_soc_cpu_default_core, .num_entries = ARRAY_SIZE(pmu_events__test_soc_cpu_default_core), - .pmu_name = { 1102 /* default_core\000 */ }, + .pmu_name = { 1138 /* default_core\000 */ }, }, { .entries = pmu_events__test_soc_cpu_hisi_sccl_ddrc, .num_entries = ARRAY_SIZE(pmu_events__test_soc_cpu_hisi_sccl_ddrc), - .pmu_name = { 1672 /* hisi_sccl,ddrc\000 */ }, + .pmu_name = { 1726 /* hisi_sccl,ddrc\000 */ }, }, { .entries = pmu_events__test_soc_cpu_hisi_sccl_l3c, .num_entries = ARRAY_SIZE(pmu_events__test_soc_cpu_hisi_sccl_l3c), - .pmu_name = { 2152 /* hisi_sccl,l3c\000 */ }, + .pmu_name = { 2218 /* hisi_sccl,l3c\000 */ }, }, { .entries = pmu_events__test_soc_cpu_uncore_cbox, .num_entries = ARRAY_SIZE(pmu_events__test_soc_cpu_uncore_cbox), - .pmu_name = { 1773 /* uncore_cbox\000 */ }, + .pmu_name = { 1830 /* uncore_cbox\000 */ }, }, { .entries = pmu_events__test_soc_cpu_uncore_imc, .num_entries = ARRAY_SIZE(pmu_events__test_soc_cpu_uncore_imc), - .pmu_name = { 2365 /* uncore_imc\000 */ }, + .pmu_name = { 2437 /* uncore_imc\000 */ }, }, { .entries = pmu_events__test_soc_cpu_uncore_imc_free_running, .num_entries = ARRAY_SIZE(pmu_events__test_soc_cpu_uncore_imc_free_running), - .pmu_name = { 2246 /* uncore_imc_free_running\000 */ }, + .pmu_name = { 2315 /* uncore_imc_free_running\000 */ }, }, }; static const struct compact_pmu_event pmu_metrics__test_soc_cpu_default_core[] = { -{ 2798 }, /* CPI\000\0001 / IPC\000\000\000\000\000\000\000\00000 */ -{ 3479 }, /* DCache_L2_All\000\000DCache_L2_All_Hits + DCache_L2_All_Miss\000\000\000\000\000\000\000\00000 */ -{ 3251 }, /* DCache_L2_All_Hits\000\000l2_rqsts.demand_data_rd_hit + l2_rqsts.pf_hit + l2_rqsts.rfo_hit\000\000\000\000\000\000\000\00000 */ -{ 3345 }, /* DCache_L2_All_Miss\000\000max(l2_rqsts.all_demand_data_rd - l2_rqsts.demand_data_rd_hit, 0) + l2_rqsts.pf_miss + l2_rqsts.rfo_miss\000\000\000\000\000\000\000\00000 */ -{ 3543 }, /* DCache_L2_Hits\000\000d_ratio(DCache_L2_All_Hits, DCache_L2_All)\000\000\000\000\000\000\000\00000 */ -{ 3611 }, /* DCache_L2_Misses\000\000d_ratio(DCache_L2_All_Miss, DCache_L2_All)\000\000\000\000\000\000\000\00000 */ -{ 2883 }, /* Frontend_Bound_SMT\000\000idq_uops_not_delivered.core / (4 * (cpu_clk_unhalted.thread / 2 * (1 + cpu_clk_unhalted.one_thread_active / cpu_clk_unhalted.ref_xclk)))\000\000\000\000\000\000\000\00000 */ -{ 2820 }, /* IPC\000group1\000inst_retired.any / cpu_clk_unhalted.thread\000\000\000\000\000\000\000\00000 */ -{ 3745 }, /* L1D_Cache_Fill_BW\000\00064 * l1d.replacement / 1e9 / duration_time\000\000\000\000\000\000\000\00000 */ -{ 3681 }, /* M1\000\000ipc + M2\000\000\000\000\000\000\000\00000 */ -{ 3703 }, /* M2\000\000ipc + M1\000\000\000\000\000\000\000\00000 */ -{ 3725 }, /* M3\000\0001 / M3\000\000\000\000\000\000\000\00000 */ -{ 3180 }, /* cache_miss_cycles\000group1\000dcache_miss_cpi + icache_miss_cycles\000\000\000\000\000\000\000\00000 */ -{ 3049 }, /* dcache_miss_cpi\000\000l1d\\-loads\\-misses / inst_retired.any\000\000\000\000\000\000\000\00000 */ -{ 3113 }, /* icache_miss_cycles\000\000l1i\\-loads\\-misses / inst_retired.any\000\000\000\000\000\000\000\00000 */ +{ 2882 }, /* CPI\000\0001 / IPC\000\000\000\000\000\000\000\00000 */ +{ 3563 }, /* DCache_L2_All\000\000DCache_L2_All_Hits + DCache_L2_All_Miss\000\000\000\000\000\000\000\00000 */ +{ 3335 }, /* DCache_L2_All_Hits\000\000l2_rqsts.demand_data_rd_hit + l2_rqsts.pf_hit + l2_rqsts.rfo_hit\000\000\000\000\000\000\000\00000 */ +{ 3429 }, /* DCache_L2_All_Miss\000\000max(l2_rqsts.all_demand_data_rd - l2_rqsts.demand_data_rd_hit, 0) + l2_rqsts.pf_miss + l2_rqsts.rfo_miss\000\000\000\000\000\000\000\00000 */ +{ 3627 }, /* DCache_L2_Hits\000\000d_ratio(DCache_L2_All_Hits, DCache_L2_All)\000\000\000\000\000\000\000\00000 */ +{ 3695 }, /* DCache_L2_Misses\000\000d_ratio(DCache_L2_All_Miss, DCache_L2_All)\000\000\000\000\000\000\000\00000 */ +{ 2967 }, /* Frontend_Bound_SMT\000\000idq_uops_not_delivered.core / (4 * (cpu_clk_unhalted.thread / 2 * (1 + cpu_clk_unhalted.one_thread_active / cpu_clk_unhalted.ref_xclk)))\000\000\000\000\000\000\000\00000 */ +{ 2904 }, /* IPC\000group1\000inst_retired.any / cpu_clk_unhalted.thread\000\000\000\000\000\000\000\00000 */ +{ 3829 }, /* L1D_Cache_Fill_BW\000\00064 * l1d.replacement / 1e9 / duration_time\000\000\000\000\000\000\000\00000 */ +{ 3765 }, /* M1\000\000ipc + M2\000\000\000\000\000\000\000\00000 */ +{ 3787 }, /* M2\000\000ipc + M1\000\000\000\000\000\000\000\00000 */ +{ 3809 }, /* M3\000\0001 / M3\000\000\000\000\000\000\000\00000 */ +{ 3264 }, /* cache_miss_cycles\000group1\000dcache_miss_cpi + icache_miss_cycles\000\000\000\000\000\000\000\00000 */ +{ 3133 }, /* dcache_miss_cpi\000\000l1d\\-loads\\-misses / inst_retired.any\000\000\000\000\000\000\000\00000 */ +{ 3197 }, /* icache_miss_cycles\000\000l1i\\-loads\\-misses / inst_retired.any\000\000\000\000\000\000\000\00000 */ }; @@ -181,18 +181,18 @@ const struct pmu_table_entry pmu_metrics__test_soc_cpu[] = { { .entries = pmu_metrics__test_soc_cpu_default_core, .num_entries = ARRAY_SIZE(pmu_metrics__test_soc_cpu_default_core), - .pmu_name = { 1102 /* default_core\000 */ }, + .pmu_name = { 1138 /* default_core\000 */ }, }, }; static const struct compact_pmu_event pmu_events__test_soc_sys_uncore_sys_ccn_pmu[] = { -{ 2565 }, /* sys_ccn_pmu.read_cycles\000uncore\000ccn read-cycles event\000config=0x2c\0000x01\00000\000\000 */ +{ 2643 }, /* sys_ccn_pmu.read_cycles\000uncore\000ccn read-cycles event\000config=0x2c\0000x01\00000\000\000\000\000\000 */ }; static const struct compact_pmu_event pmu_events__test_soc_sys_uncore_sys_cmn_pmu[] = { -{ 2658 }, /* sys_cmn_pmu.hnf_cache_miss\000uncore\000Counts total cache misses in first lookup result (high priority)\000eventid=1,type=5\000(434|436|43c|43a).*\00000\000\000 */ +{ 2739 }, /* sys_cmn_pmu.hnf_cache_miss\000uncore\000Counts total cache misses in first lookup result (high priority)\000eventid=1,type=5\000(434|436|43c|43a).*\00000\000\000\000\000\000 */ }; static const struct compact_pmu_event pmu_events__test_soc_sys_uncore_sys_ddr_pmu[] = { -{ 2473 }, /* sys_ddr_pmu.write_cycles\000uncore\000ddr write-cycles event\000event=0x2b\000v8\00000\000\000 */ +{ 2548 }, /* sys_ddr_pmu.write_cycles\000uncore\000ddr write-cycles event\000event=0x2b\000v8\00000\000\000\000\000\000 */ }; @@ -200,17 +200,17 @@ const struct pmu_table_entry pmu_events__test_soc_sys[] = { { .entries = pmu_events__test_soc_sys_uncore_sys_ccn_pmu, .num_entries = ARRAY_SIZE(pmu_events__test_soc_sys_uncore_sys_ccn_pmu), - .pmu_name = { 2546 /* uncore_sys_ccn_pmu\000 */ }, + .pmu_name = { 2624 /* uncore_sys_ccn_pmu\000 */ }, }, { .entries = pmu_events__test_soc_sys_uncore_sys_cmn_pmu, .num_entries = ARRAY_SIZE(pmu_events__test_soc_sys_uncore_sys_cmn_pmu), - .pmu_name = { 2639 /* uncore_sys_cmn_pmu\000 */ }, + .pmu_name = { 2720 /* uncore_sys_cmn_pmu\000 */ }, }, { .entries = pmu_events__test_soc_sys_uncore_sys_ddr_pmu, .num_entries = ARRAY_SIZE(pmu_events__test_soc_sys_uncore_sys_ddr_pmu), - .pmu_name = { 2454 /* uncore_sys_ddr_pmu\000 */ }, + .pmu_name = { 2529 /* uncore_sys_ddr_pmu\000 */ }, }, }; @@ -316,6 +316,12 @@ static void decompress_event(int offset, struct pmu_event *pe) p++; pe->unit = (*p == '\0' ? NULL : p); while (*p++); + pe->retirement_latency_mean = (*p == '\0' ? NULL : p); + while (*p++); + pe->retirement_latency_min = (*p == '\0' ? NULL : p); + while (*p++); + pe->retirement_latency_max = (*p == '\0' ? NULL : p); + while (*p++); pe->long_desc = (*p == '\0' ? NULL : p); } @@ -443,7 +449,7 @@ int pmu_events_table__find_event(const struct pmu_events_table *table, const char *pmu_name = &big_c_string[table_pmu->pmu_name.offset]; int ret; - if (!perf_pmu__name_wildcard_match(pmu, pmu_name)) + if (pmu && !perf_pmu__name_wildcard_match(pmu, pmu_name)) continue; ret = pmu_events_table__find_event_pmu(table, table_pmu, name, fn, data); @@ -489,6 +495,49 @@ static int pmu_metrics_table__for_each_metric_pmu(const struct pmu_metrics_table return 0; } +static int pmu_metrics_table__find_metric_pmu(const struct pmu_metrics_table *table, + const struct pmu_table_entry *pmu, + const char *metric, + pmu_metric_iter_fn fn, + void *data) +{ + struct pmu_metric pm = { + .pmu = &big_c_string[pmu->pmu_name.offset], + }; + int low = 0, high = pmu->num_entries - 1; + + while (low <= high) { + int cmp, mid = (low + high) / 2; + + decompress_metric(pmu->entries[mid].offset, &pm); + + if (!pm.metric_name && !metric) + goto do_call; + + if (!pm.metric_name && metric) { + low = mid + 1; + continue; + } + if (pm.metric_name && !metric) { + high = mid - 1; + continue; + } + + cmp = strcmp(pm.metric_name, metric); + if (cmp < 0) { + low = mid + 1; + continue; + } + if (cmp > 0) { + high = mid - 1; + continue; + } + do_call: + return fn ? fn(&pm, table, data) : 0; + } + return PMU_METRICS__NOT_FOUND; +} + int pmu_metrics_table__for_each_metric(const struct pmu_metrics_table *table, pmu_metric_iter_fn fn, void *data) @@ -503,6 +552,27 @@ int pmu_metrics_table__for_each_metric(const struct pmu_metrics_table *table, return 0; } +int pmu_metrics_table__find_metric(const struct pmu_metrics_table *table, + struct perf_pmu *pmu, + const char *metric, + pmu_metric_iter_fn fn, + void *data) +{ + for (size_t i = 0; i < table->num_pmus; i++) { + const struct pmu_table_entry *table_pmu = &table->pmus[i]; + const char *pmu_name = &big_c_string[table_pmu->pmu_name.offset]; + int ret; + + if (pmu && !perf_pmu__name_wildcard_match(pmu, pmu_name)) + continue; + + ret = pmu_metrics_table__find_metric_pmu(table, table_pmu, metric, fn, data); + if (ret != PMU_METRICS__NOT_FOUND) + return ret; + } + return PMU_METRICS__NOT_FOUND; +} + static const struct pmu_events_map *map_for_cpu(struct perf_cpu cpu) { static struct { diff --git a/tools/perf/pmu-events/jevents.py b/tools/perf/pmu-events/jevents.py index 7499a35bfadd..a1899f35ec74 100755 --- a/tools/perf/pmu-events/jevents.py +++ b/tools/perf/pmu-events/jevents.py @@ -47,6 +47,9 @@ _json_event_attributes = [ 'event', # Short things in alphabetical order. 'compat', 'deprecated', 'perpkg', 'unit', + # Retirement latency specific to Intel granite rapids currently. + 'retirement_latency_mean', 'retirement_latency_min', + 'retirement_latency_max', # Longer things (the last won't be iterated over during decompress). 'long_desc' ] @@ -341,6 +344,9 @@ class JsonEvent: self.perpkg = jd.get('PerPkg') self.aggr_mode = convert_aggr_mode(jd.get('AggregationMode')) self.deprecated = jd.get('Deprecated') + self.retirement_latency_mean = jd.get('RetirementLatencyMean') + self.retirement_latency_min = jd.get('RetirementLatencyMin') + self.retirement_latency_max = jd.get('RetirementLatencyMax') self.metric_name = jd.get('MetricName') self.metric_group = jd.get('MetricGroup') self.metricgroup_no_group = jd.get('MetricgroupNoGroup') @@ -966,7 +972,7 @@ int pmu_events_table__find_event(const struct pmu_events_table *table, const char *pmu_name = &big_c_string[table_pmu->pmu_name.offset]; int ret; - if (!perf_pmu__name_wildcard_match(pmu, pmu_name)) + if (pmu && !perf_pmu__name_wildcard_match(pmu, pmu_name)) continue; ret = pmu_events_table__find_event_pmu(table, table_pmu, name, fn, data); @@ -1012,6 +1018,49 @@ static int pmu_metrics_table__for_each_metric_pmu(const struct pmu_metrics_table return 0; } +static int pmu_metrics_table__find_metric_pmu(const struct pmu_metrics_table *table, + const struct pmu_table_entry *pmu, + const char *metric, + pmu_metric_iter_fn fn, + void *data) +{ + struct pmu_metric pm = { + .pmu = &big_c_string[pmu->pmu_name.offset], + }; + int low = 0, high = pmu->num_entries - 1; + + while (low <= high) { + int cmp, mid = (low + high) / 2; + + decompress_metric(pmu->entries[mid].offset, &pm); + + if (!pm.metric_name && !metric) + goto do_call; + + if (!pm.metric_name && metric) { + low = mid + 1; + continue; + } + if (pm.metric_name && !metric) { + high = mid - 1; + continue; + } + + cmp = strcmp(pm.metric_name, metric); + if (cmp < 0) { + low = mid + 1; + continue; + } + if (cmp > 0) { + high = mid - 1; + continue; + } + do_call: + return fn ? fn(&pm, table, data) : 0; + } + return PMU_METRICS__NOT_FOUND; +} + int pmu_metrics_table__for_each_metric(const struct pmu_metrics_table *table, pmu_metric_iter_fn fn, void *data) @@ -1026,6 +1075,27 @@ int pmu_metrics_table__for_each_metric(const struct pmu_metrics_table *table, return 0; } +int pmu_metrics_table__find_metric(const struct pmu_metrics_table *table, + struct perf_pmu *pmu, + const char *metric, + pmu_metric_iter_fn fn, + void *data) +{ + for (size_t i = 0; i < table->num_pmus; i++) { + const struct pmu_table_entry *table_pmu = &table->pmus[i]; + const char *pmu_name = &big_c_string[table_pmu->pmu_name.offset]; + int ret; + + if (pmu && !perf_pmu__name_wildcard_match(pmu, pmu_name)) + continue; + + ret = pmu_metrics_table__find_metric_pmu(table, table_pmu, metric, fn, data); + if (ret != PMU_METRICS__NOT_FOUND) + return ret; + } + return PMU_METRICS__NOT_FOUND; +} + static const struct pmu_events_map *map_for_cpu(struct perf_cpu cpu) { static struct { diff --git a/tools/perf/pmu-events/pmu-events.h b/tools/perf/pmu-events/pmu-events.h index 675562e6f770..a523936846e0 100644 --- a/tools/perf/pmu-events/pmu-events.h +++ b/tools/perf/pmu-events/pmu-events.h @@ -47,6 +47,9 @@ struct pmu_event { const char *long_desc; const char *pmu; const char *unit; + const char *retirement_latency_mean; + const char *retirement_latency_min; + const char *retirement_latency_max; bool perpkg; bool deprecated; }; @@ -71,6 +74,7 @@ struct pmu_events_table; struct pmu_metrics_table; #define PMU_EVENTS__NOT_FOUND -1000 +#define PMU_METRICS__NOT_FOUND -1000 typedef int (*pmu_event_iter_fn)(const struct pmu_event *pe, const struct pmu_events_table *table, @@ -85,11 +89,11 @@ int pmu_events_table__for_each_event(const struct pmu_events_table *table, pmu_event_iter_fn fn, void *data); /* - * Search for table and entry matching with pmu__name_match. Each matching event - * has fn called on it. 0 implies to success/continue the search while non-zero - * means to terminate. The special value PMU_EVENTS__NOT_FOUND is used to - * indicate no event was found in one of the tables which doesn't terminate the - * search of all tables. + * Search for a table and entry matching with pmu__name_wildcard_match or any + * tables if pmu is NULL. Each matching event has fn called on it. 0 implies to + * success/continue the search while non-zero means to terminate. The special + * value PMU_EVENTS__NOT_FOUND is used to indicate no event was found in one of + * the tables which doesn't terminate the search of all tables. */ int pmu_events_table__find_event(const struct pmu_events_table *table, struct perf_pmu *pmu, @@ -101,6 +105,18 @@ size_t pmu_events_table__num_events(const struct pmu_events_table *table, int pmu_metrics_table__for_each_metric(const struct pmu_metrics_table *table, pmu_metric_iter_fn fn, void *data); +/* + * Search for a table and entry matching with pmu__name_wildcard_match or any + * tables if pmu is NULL. Each matching metric has fn called on it. 0 implies to + * success/continue the search while non-zero means to terminate. The special + * value PMU_METRICS__NOT_FOUND is used to indicate no metric was found in one + * of the tables which doesn't terminate the search of all tables. + */ +int pmu_metrics_table__find_metric(const struct pmu_metrics_table *table, + struct perf_pmu *pmu, + const char *metric, + pmu_metric_iter_fn fn, + void *data); const struct pmu_events_table *perf_pmu__find_events_table(struct perf_pmu *pmu); const struct pmu_metrics_table *pmu_metrics_table__find(void); |