perf vendor events: Update Intel tigerlake

Update to v1.07, the metrics are based on TMA 4.4 full.

Use script at:
https://github.com/intel/event-converter-for-linux-perf/blob/master/download_and_gen.py

to download and generate the latest events and metrics. Manually copy
the tigerlake files into perf and update mapfile.csv.

Tested on a non-tigerlake with 'perf test':
 10: PMU events                                                      :
 10.1: PMU event table sanity                                        : Ok
 10.2: PMU event map aliases                                         : Ok
 10.3: Parsing of PMU event table metrics                            : Ok
 10.4: Parsing of PMU event table metrics with fake PMUs             : Ok

Signed-off-by: Ian Rogers <irogers@google.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Alexandre Torgue <alexandre.torgue@foss.st.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Caleb Biggers <caleb.biggers@intel.com>
Cc: James Clark <james.clark@arm.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: John Garry <john.garry@huawei.com>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Kshipra Bopardikar <kshipra.bopardikar@intel.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Maxime Coquelin <mcoquelin.stm32@gmail.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Perry Taylor <perry.taylor@intel.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Sedat Dilek <sedat.dilek@gmail.com>
Cc: Stephane Eranian <eranian@google.com>
Cc: Xing Zhengjun <zhengjun.xing@linux.intel.com>
Link: http://lore.kernel.org/lkml/20220727220832.2865794-27-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

1 files changed, 327 insertions, 51 deletions

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 00a16f1a0f44..03c97bd74ad9 100644
--- a/tools/perf/pmu-events/arch/x86/tigerlake/tgl-metrics.json
+++ b/tools/perf/pmu-events/arch/x86/tigerlake/tgl-metrics.json
@@ -1,20 +1,26 @@
 [
     {
+        "BriefDescription": "Total pipeline cost of branch related instructions (used for program control-flow including function calls)",
+        "MetricExpr": "100 * (( BR_INST_RETIRED.COND + 3 * BR_INST_RETIRED.NEAR_CALL + (BR_INST_RETIRED.NEAR_TAKEN - BR_INST_RETIRED.COND_TAKEN - 2 * BR_INST_RETIRED.NEAR_CALL) ) / TOPDOWN.SLOTS)",
+        "MetricGroup": "Ret",
+        "MetricName": "Branching_Overhead"
+    },
+    {
+        "BriefDescription": "Total pipeline cost of instruction fetch related bottlenecks by large code footprint programs (i-side cache; TLB and BTB misses)",
+        "MetricExpr": "100 * (( 5 * IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE - INT_MISC.UOP_DROPPING ) / TOPDOWN.SLOTS) * ( (ICACHE_64B.IFTAG_STALL / CPU_CLK_UNHALTED.THREAD) + (ICACHE_16B.IFDATA_STALL / CPU_CLK_UNHALTED.THREAD) + (10 * BACLEARS.ANY / CPU_CLK_UNHALTED.THREAD) ) / #(( 5 * IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE - INT_MISC.UOP_DROPPING ) / TOPDOWN.SLOTS)",
+        "MetricGroup": "BigFoot;Fed;Frontend;IcMiss;MemoryTLB",
+        "MetricName": "Big_Code"
+    },
+    {
         "BriefDescription": "Instructions Per Cycle (per Logical Processor)",
         "MetricExpr": "INST_RETIRED.ANY / CPU_CLK_UNHALTED.THREAD",
-        "MetricGroup": "Summary",
+        "MetricGroup": "Ret;Summary",
         "MetricName": "IPC"
     },
     {
-        "BriefDescription": "Instruction per taken branch",
-        "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_TAKEN",
-        "MetricGroup": "Branches;FetchBW;PGO",
-        "MetricName": "IpTB"
-    },
-    {
         "BriefDescription": "Cycles Per Instruction (per Logical Processor)",
-        "MetricExpr": "1 / IPC",
-        "MetricGroup": "Pipeline",
+        "MetricExpr": "1 / (INST_RETIRED.ANY / CPU_CLK_UNHALTED.THREAD)",
+        "MetricGroup": "Pipeline;Mem",
         "MetricName": "CPI"
     },
     {
@@ -24,28 +30,48 @@
         "MetricName": "CLKS"
     },
     {
-        "BriefDescription": "Instructions Per Cycle (per physical core)",
-        "MetricExpr": "INST_RETIRED.ANY / CPU_CLK_UNHALTED.DISTRIBUTED",
+        "BriefDescription": "Total issue-pipeline slots (per-Physical Core till ICL; per-Logical Processor ICL onward)",
+        "MetricExpr": "TOPDOWN.SLOTS",
+        "MetricGroup": "TmaL1",
+        "MetricName": "SLOTS"
+    },
+    {
+        "BriefDescription": "Fraction of Physical Core issue-slots utilized by this Logical Processor",
+        "MetricExpr": "TOPDOWN.SLOTS / ( TOPDOWN.SLOTS / 2 ) if #SMT_on else 1",
         "MetricGroup": "SMT;TmaL1",
+        "MetricName": "Slots_Utilization"
+    },
+    {
+        "BriefDescription": "The ratio of Executed- by Issued-Uops",
+        "MetricExpr": "UOPS_EXECUTED.THREAD / UOPS_ISSUED.ANY",
+        "MetricGroup": "Cor;Pipeline",
+        "MetricName": "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."
+    },
+    {
+        "BriefDescription": "Instructions Per Cycle across hyper-threads (per physical core)",
+        "MetricExpr": "INST_RETIRED.ANY / CPU_CLK_UNHALTED.DISTRIBUTED",
+        "MetricGroup": "Ret;SMT;TmaL1",
         "MetricName": "CoreIPC"
     },
     {
         "BriefDescription": "Floating Point Operations Per Cycle",
         "MetricExpr": "( 1 * ( FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE ) + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * ( FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE ) + 8 * ( FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE ) + 16 * FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE ) / CPU_CLK_UNHALTED.DISTRIBUTED",
-        "MetricGroup": "Flops",
+        "MetricGroup": "Ret;Flops",
         "MetricName": "FLOPc"
     },
     {
-        "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is at least 1 uop executed)",
-        "MetricExpr": "UOPS_EXECUTED.THREAD / ( UOPS_EXECUTED.CORE_CYCLES_GE_1 / 2 )",
-        "MetricGroup": "Pipeline;PortsUtil",
-        "MetricName": "ILP"
+        "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_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE) + (FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE) ) / ( 2 * CPU_CLK_UNHALTED.DISTRIBUTED )",
+        "MetricGroup": "Cor;Flops;HPC",
+        "MetricName": "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)."
     },
     {
-        "BriefDescription": "Number of Instructions per non-speculative Branch Misprediction (JEClear)",
-        "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.ALL_BRANCHES",
-        "MetricGroup": "BrMispredicts",
-        "MetricName": "IpMispredict"
+        "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 UOPS_EXECUTED.CORE_CYCLES_GE_1)",
+        "MetricGroup": "Backend;Cor;Pipeline;PortsUtil",
+        "MetricName": "ILP"
     },
     {
         "BriefDescription": "Core actual clocks when any Logical Processor is active on the Physical Core",
@@ -68,99 +94,279 @@
     {
         "BriefDescription": "Instructions per Branch (lower number means higher occurrence rate)",
         "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.ALL_BRANCHES",
-        "MetricGroup": "Branches;InsType",
+        "MetricGroup": "Branches;Fed;InsType",
         "MetricName": "IpBranch"
     },
     {
         "BriefDescription": "Instructions per (near) call (lower number means higher occurrence rate)",
         "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_CALL",
-        "MetricGroup": "Branches",
+        "MetricGroup": "Branches;Fed;PGO",
         "MetricName": "IpCall"
     },
     {
+        "BriefDescription": "Instruction per taken branch",
+        "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_TAKEN",
+        "MetricGroup": "Branches;Fed;FetchBW;Frontend;PGO",
+        "MetricName": "IpTB"
+    },
+    {
         "BriefDescription": "Branch instructions per taken branch. ",
         "MetricExpr": "BR_INST_RETIRED.ALL_BRANCHES / BR_INST_RETIRED.NEAR_TAKEN",
-        "MetricGroup": "Branches;PGO",
+        "MetricGroup": "Branches;Fed;PGO",
         "MetricName": "BpTkBranch"
     },
     {
         "BriefDescription": "Instructions per Floating Point (FP) Operation (lower number means higher occurrence rate)",
         "MetricExpr": "INST_RETIRED.ANY / ( 1 * ( FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE ) + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * ( FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE ) + 8 * ( FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE ) + 16 * FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE )",
-        "MetricGroup": "Flops;FpArith;InsType",
+        "MetricGroup": "Flops;InsType",
         "MetricName": "IpFLOP"
     },
     {
+        "BriefDescription": "Instructions per FP Arithmetic instruction (lower number means higher occurrence rate)",
+        "MetricExpr": "INST_RETIRED.ANY / ( (FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE) + (FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE) )",
+        "MetricGroup": "Flops;InsType",
+        "MetricName": "IpArith",
+        "PublicDescription": "Instructions per FP Arithmetic instruction (lower number means higher occurrence rate). May undercount due to FMA double counting. Approximated prior to BDW."
+    },
+    {
+        "BriefDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction (lower number means higher occurrence rate)",
+        "MetricExpr": "INST_RETIRED.ANY / FP_ARITH_INST_RETIRED.SCALAR_SINGLE",
+        "MetricGroup": "Flops;FpScalar;InsType",
+        "MetricName": "IpArith_Scalar_SP",
+        "PublicDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction (lower number means higher occurrence rate). May undercount due to FMA double counting."
+    },
+    {
+        "BriefDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction (lower number means higher occurrence rate)",
+        "MetricExpr": "INST_RETIRED.ANY / FP_ARITH_INST_RETIRED.SCALAR_DOUBLE",
+        "MetricGroup": "Flops;FpScalar;InsType",
+        "MetricName": "IpArith_Scalar_DP",
+        "PublicDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction (lower number means higher occurrence rate). May undercount due to FMA double counting."
+    },
+    {
+        "BriefDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number means higher occurrence rate)",
+        "MetricExpr": "INST_RETIRED.ANY / ( FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE )",
+        "MetricGroup": "Flops;FpVector;InsType",
+        "MetricName": "IpArith_AVX128",
+        "PublicDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number means higher occurrence rate). May undercount due to FMA double counting."
+    },
+    {
+        "BriefDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means higher occurrence rate)",
+        "MetricExpr": "INST_RETIRED.ANY / ( FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE )",
+        "MetricGroup": "Flops;FpVector;InsType",
+        "MetricName": "IpArith_AVX256",
+        "PublicDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means higher occurrence rate). May undercount due to FMA double counting."
+    },
+    {
+        "BriefDescription": "Instructions per FP Arithmetic AVX 512-bit instruction (lower number means higher occurrence rate)",
+        "MetricExpr": "INST_RETIRED.ANY / ( FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE )",
+        "MetricGroup": "Flops;FpVector;InsType",
+        "MetricName": "IpArith_AVX512",
+        "PublicDescription": "Instructions per FP Arithmetic AVX 512-bit instruction (lower number means higher occurrence rate). May undercount due to FMA double counting."
+    },
+    {
+        "BriefDescription": "Instructions per Software prefetch instruction (of any type: NTA/T0/T1/T2/Prefetch) (lower number means higher occurrence rate)",
+        "MetricExpr": "INST_RETIRED.ANY / cpu@SW_PREFETCH_ACCESS.T0\\,umask\\=0xF@",
+        "MetricGroup": "Prefetches",
+        "MetricName": "IpSWPF"
+    },
+    {
         "BriefDescription": "Total number of retired Instructions, Sample with: INST_RETIRED.PREC_DIST",
         "MetricExpr": "INST_RETIRED.ANY",
         "MetricGroup": "Summary;TmaL1",
         "MetricName": "Instructions"
     },
     {
+        "BriefDescription": "",
+        "MetricExpr": "UOPS_EXECUTED.THREAD / cpu@UOPS_EXECUTED.THREAD\\,cmask\\=1@",
+        "MetricGroup": "Cor;Pipeline;PortsUtil;SMT",
+        "MetricName": "Execute"
+    },
+    {
+        "BriefDescription": "Average number of Uops issued by front-end when it issued something",
+        "MetricExpr": "UOPS_ISSUED.ANY / cpu@UOPS_ISSUED.ANY\\,cmask\\=1@",
+        "MetricGroup": "Fed;FetchBW",
+        "MetricName": "Fetch_UpC"
+    },
+    {
         "BriefDescription": "Fraction of Uops delivered by the LSD (Loop Stream Detector; aka Loop Cache)",
         "MetricExpr": "LSD.UOPS / (IDQ.DSB_UOPS + LSD.UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS)",
-        "MetricGroup": "LSD",
+        "MetricGroup": "Fed;LSD",
         "MetricName": "LSD_Coverage"
     },
     {
         "BriefDescription": "Fraction of Uops delivered by the DSB (aka Decoded ICache; or Uop Cache)",
         "MetricExpr": "IDQ.DSB_UOPS / (IDQ.DSB_UOPS + LSD.UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS)",
-        "MetricGroup": "DSB;FetchBW",
+        "MetricGroup": "DSB;Fed;FetchBW",
         "MetricName": "DSB_Coverage"
     },
     {
-        "BriefDescription": "Actual Average Latency for L1 data-cache miss demand loads (in core cycles)",
+        "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": "DSB_Switch_Cost"
+    },
+    {
+        "BriefDescription": "Number of Instructions per non-speculative DSB miss (lower number means higher occurrence rate)",
+        "MetricExpr": "INST_RETIRED.ANY / FRONTEND_RETIRED.ANY_DSB_MISS",
+        "MetricGroup": "DSBmiss;Fed",
+        "MetricName": "IpDSB_Miss_Ret"
+    },
+    {
+        "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": "IpMispredict"
+    },
+    {
+        "BriefDescription": "Fraction of branches that are non-taken conditionals",
+        "MetricExpr": "BR_INST_RETIRED.COND_NTAKEN / BR_INST_RETIRED.ALL_BRANCHES",
+        "MetricGroup": "Bad;Branches;CodeGen;PGO",
+        "MetricName": "Cond_NT"
+    },
+    {
+        "BriefDescription": "Fraction of branches that are taken conditionals",
+        "MetricExpr": "BR_INST_RETIRED.COND_TAKEN / BR_INST_RETIRED.ALL_BRANCHES",
+        "MetricGroup": "Bad;Branches;CodeGen;PGO",
+        "MetricName": "Cond_TK"
+    },
+    {
+        "BriefDescription": "Fraction of branches that are CALL or RET",
+        "MetricExpr": "( BR_INST_RETIRED.NEAR_CALL + BR_INST_RETIRED.NEAR_RETURN ) / BR_INST_RETIRED.ALL_BRANCHES",
+        "MetricGroup": "Bad;Branches",
+        "MetricName": "CallRet"
+    },
+    {
+        "BriefDescription": "Fraction of branches that are unconditional (direct or indirect) jumps",
+        "MetricExpr": "(BR_INST_RETIRED.NEAR_TAKEN - BR_INST_RETIRED.COND_TAKEN - 2 * BR_INST_RETIRED.NEAR_CALL) / BR_INST_RETIRED.ALL_BRANCHES",
+        "MetricGroup": "Bad;Branches",
+        "MetricName": "Jump"
+    },
+    {
+        "BriefDescription": "Fraction of branches of other types (not individually covered by other metrics in Info.Branches group)",
+        "MetricExpr": "1 - ( (BR_INST_RETIRED.COND_NTAKEN / BR_INST_RETIRED.ALL_BRANCHES) + (BR_INST_RETIRED.COND_TAKEN / BR_INST_RETIRED.ALL_BRANCHES) + (( BR_INST_RETIRED.NEAR_CALL + BR_INST_RETIRED.NEAR_RETURN ) / BR_INST_RETIRED.ALL_BRANCHES) + ((BR_INST_RETIRED.NEAR_TAKEN - BR_INST_RETIRED.COND_TAKEN - 2 * BR_INST_RETIRED.NEAR_CALL) / BR_INST_RETIRED.ALL_BRANCHES) )",
+        "MetricGroup": "Bad;Branches",
+        "MetricName": "Other_Branches"
+    },
+    {
+        "BriefDescription": "Actual Average Latency for L1 data-cache miss demand load operations (in core cycles)",
         "MetricExpr": "L1D_PEND_MISS.PENDING / ( MEM_LOAD_RETIRED.L1_MISS + MEM_LOAD_RETIRED.FB_HIT )",
-        "MetricGroup": "MemoryBound;MemoryLat",
+        "MetricGroup": "Mem;MemoryBound;MemoryLat",
         "MetricName": "Load_Miss_Real_Latency"
     },
     {
         "BriefDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least one such miss. Per-Logical Processor)",
         "MetricExpr": "L1D_PEND_MISS.PENDING / L1D_PEND_MISS.PENDING_CYCLES",
-        "MetricGroup": "MemoryBound;MemoryBW",
+        "MetricGroup": "Mem;MemoryBound;MemoryBW",
         "MetricName": "MLP"
     },
     {
+        "BriefDescription": "L1 cache true misses per kilo instruction for retired demand loads",
+        "MetricExpr": "1000 * MEM_LOAD_RETIRED.L1_MISS / INST_RETIRED.ANY",
+        "MetricGroup": "Mem;CacheMisses",
+        "MetricName": "L1MPKI"
+    },
+    {
+        "BriefDescription": "L1 cache true misses per kilo instruction for all demand loads (including speculative)",
+        "MetricExpr": "1000 * L2_RQSTS.ALL_DEMAND_DATA_RD / INST_RETIRED.ANY",
+        "MetricGroup": "Mem;CacheMisses",
+        "MetricName": "L1MPKI_Load"
+    },
+    {
+        "BriefDescription": "L2 cache true misses per kilo instruction for retired demand loads",
+        "MetricExpr": "1000 * MEM_LOAD_RETIRED.L2_MISS / INST_RETIRED.ANY",
+        "MetricGroup": "Mem;Backend;CacheMisses",
+        "MetricName": "L2MPKI"
+    },
+    {
+        "BriefDescription": "L2 cache ([RKL+] true) misses per kilo instruction for all request types (including speculative)",
+        "MetricExpr": "1000 * L2_RQSTS.MISS / INST_RETIRED.ANY",
+        "MetricGroup": "Mem;CacheMisses;Offcore",
+        "MetricName": "L2MPKI_All"
+    },
+    {
+        "BriefDescription": "L2 cache ([RKL+] true) misses per kilo instruction for all demand loads  (including speculative)",
+        "MetricExpr": "1000 * L2_RQSTS.DEMAND_DATA_RD_MISS / INST_RETIRED.ANY",
+        "MetricGroup": "Mem;CacheMisses",
+        "MetricName": "L2MPKI_Load"
+    },
+    {
+        "BriefDescription": "L2 cache hits per kilo instruction for all request types (including speculative)",
+        "MetricExpr": "1000 * ( L2_RQSTS.REFERENCES - L2_RQSTS.MISS ) / INST_RETIRED.ANY",
+        "MetricGroup": "Mem;CacheMisses",
+        "MetricName": "L2HPKI_All"
+    },
+    {
+        "BriefDescription": "L2 cache hits per kilo instruction for all demand loads  (including speculative)",
+        "MetricExpr": "1000 * L2_RQSTS.DEMAND_DATA_RD_HIT / INST_RETIRED.ANY",
+        "MetricGroup": "Mem;CacheMisses",
+        "MetricName": "L2HPKI_Load"
+    },
+    {
+        "BriefDescription": "L3 cache true misses per kilo instruction for retired demand loads",
+        "MetricExpr": "1000 * MEM_LOAD_RETIRED.L3_MISS / INST_RETIRED.ANY",
+        "MetricGroup": "Mem;CacheMisses",
+        "MetricName": "L3MPKI"
+    },
+    {
+        "BriefDescription": "Fill Buffer (FB) hits per kilo instructions for retired demand loads (L1D misses that merge into ongoing miss-handling entries)",
+        "MetricExpr": "1000 * MEM_LOAD_RETIRED.FB_HIT / INST_RETIRED.ANY",
+        "MetricGroup": "Mem;CacheMisses",
+        "MetricName": "FB_HPKI"
+    },
+    {
         "BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses",
         "MetricConstraint": "NO_NMI_WATCHDOG",
-        "MetricExpr": "( ITLB_MISSES.WALK_PENDING + DTLB_LOAD_MISSES.WALK_PENDING + DTLB_STORE_MISSES.WALK_PENDING ) / ( 2 * CORE_CLKS )",
-        "MetricGroup": "MemoryTLB",
+        "MetricExpr": "( ITLB_MISSES.WALK_PENDING + DTLB_LOAD_MISSES.WALK_PENDING + DTLB_STORE_MISSES.WALK_PENDING ) / ( 2 * CPU_CLK_UNHALTED.DISTRIBUTED )",
+        "MetricGroup": "Mem;MemoryTLB",
         "MetricName": "Page_Walks_Utilization"
     },
     {
-        "BriefDescription": "Average data fill bandwidth to the L1 data cache [GB / sec]",
+        "BriefDescription": "Average per-core data fill bandwidth to the L1 data cache [GB / sec]",
         "MetricExpr": "64 * L1D.REPLACEMENT / 1000000000 / duration_time",
-        "MetricGroup": "MemoryBW",
+        "MetricGroup": "Mem;MemoryBW",
         "MetricName": "L1D_Cache_Fill_BW"
     },
     {
-        "BriefDescription": "Average data fill bandwidth to the L2 cache [GB / sec]",
+        "BriefDescription": "Average per-core data fill bandwidth to the L2 cache [GB / sec]",
         "MetricExpr": "64 * L2_LINES_IN.ALL / 1000000000 / duration_time",
-        "MetricGroup": "MemoryBW",
+        "MetricGroup": "Mem;MemoryBW",
         "MetricName": "L2_Cache_Fill_BW"
     },
     {
+        "BriefDescription": "Average per-core data fill bandwidth to the L3 cache [GB / sec]",
+        "MetricExpr": "64 * LONGEST_LAT_CACHE.MISS / 1000000000 / duration_time",
+        "MetricGroup": "Mem;MemoryBW",
+        "MetricName": "L3_Cache_Fill_BW"
+    },
+    {
         "BriefDescription": "Average per-core data access bandwidth to the L3 cache [GB / sec]",
         "MetricExpr": "64 * OFFCORE_REQUESTS.ALL_REQUESTS / 1000000000 / duration_time",
-        "MetricGroup": "MemoryBW;Offcore",
+        "MetricGroup": "Mem;MemoryBW;Offcore",
         "MetricName": "L3_Cache_Access_BW"
     },
     {
-        "BriefDescription": "L1 cache true misses per kilo instruction for retired demand loads",
-        "MetricExpr": "1000 * MEM_LOAD_RETIRED.L1_MISS / INST_RETIRED.ANY",
-        "MetricGroup": "CacheMisses",
-        "MetricName": "L1MPKI"
+        "BriefDescription": "Average per-thread data fill bandwidth to the L1 data cache [GB / sec]",
+        "MetricExpr": "(64 * L1D.REPLACEMENT / 1000000000 / duration_time)",
+        "MetricGroup": "Mem;MemoryBW",
+        "MetricName": "L1D_Cache_Fill_BW_1T"
     },
     {
-        "BriefDescription": "L2 cache true misses per kilo instruction for retired demand loads",
-        "MetricExpr": "1000 * MEM_LOAD_RETIRED.L2_MISS / INST_RETIRED.ANY",
-        "MetricGroup": "CacheMisses",
-        "MetricName": "L2MPKI"
+        "BriefDescription": "Average per-thread data fill bandwidth to the L2 cache [GB / sec]",
+        "MetricExpr": "(64 * L2_LINES_IN.ALL / 1000000000 / duration_time)",
+        "MetricGroup": "Mem;MemoryBW",
+        "MetricName": "L2_Cache_Fill_BW_1T"
     },
     {
-        "BriefDescription": "L3 cache true misses per kilo instruction for retired demand loads",
-        "MetricExpr": "1000 * MEM_LOAD_RETIRED.L3_MISS / INST_RETIRED.ANY",
-        "MetricGroup": "CacheMisses",
-        "MetricName": "L3MPKI"
+        "BriefDescription": "Average per-thread data fill bandwidth to the L3 cache [GB / sec]",
+        "MetricExpr": "(64 * LONGEST_LAT_CACHE.MISS / 1000000000 / duration_time)",
+        "MetricGroup": "Mem;MemoryBW",
+        "MetricName": "L3_Cache_Fill_BW_1T"
+    },
+    {
+        "BriefDescription": "Average per-thread data access bandwidth to the L3 cache [GB / sec]",
+        "MetricExpr": "(64 * OFFCORE_REQUESTS.ALL_REQUESTS / 1000000000 / duration_time)",
+        "MetricGroup": "Mem;MemoryBW;Offcore",
+        "MetricName": "L3_Cache_Access_BW_1T"
     },
     {
         "BriefDescription": "Average CPU Utilization",
@@ -177,8 +383,9 @@
     {
         "BriefDescription": "Giga Floating Point Operations Per Second",
         "MetricExpr": "( ( 1 * ( FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE ) + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * ( FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE ) + 8 * ( FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE ) + 16 * FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE ) / 1000000000 ) / duration_time",
-        "MetricGroup": "Flops;HPC",
-        "MetricName": "GFLOPs"
+        "MetricGroup": "Cor;Flops;HPC",
+        "MetricName": "GFLOPs",
+        "PublicDescription": "Giga Floating Point Operations Per Second. Aggregate across all supported options of: FP precisions, scalar and vector instructions, vector-width and AMX engine."
     },
     {
         "BriefDescription": "Average Frequency Utilization relative nominal frequency",
@@ -187,8 +394,29 @@
         "MetricName": "Turbo_Utilization"
     },
     {
+        "BriefDescription": "Fraction of Core cycles where the core was running with power-delivery for baseline license level 0",
+        "MetricExpr": "CORE_POWER.LVL0_TURBO_LICENSE / CPU_CLK_UNHALTED.DISTRIBUTED",
+        "MetricGroup": "Power",
+        "MetricName": "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."
+    },
+    {
+        "BriefDescription": "Fraction of Core cycles where the core was running with power-delivery for license level 1",
+        "MetricExpr": "CORE_POWER.LVL1_TURBO_LICENSE / CPU_CLK_UNHALTED.DISTRIBUTED",
+        "MetricGroup": "Power",
+        "MetricName": "Power_License1_Utilization",
+        "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)",
+        "MetricExpr": "CORE_POWER.LVL2_TURBO_LICENSE / CPU_CLK_UNHALTED.DISTRIBUTED",
+        "MetricGroup": "Power",
+        "MetricName": "Power_License2_Utilization",
+        "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",
-        "MetricExpr": "1 - CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_DISTRIBUTED",
+        "MetricExpr": "1 - CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_DISTRIBUTED if #SMT_on else 0",
         "MetricGroup": "SMT",
         "MetricName": "SMT_2T_Utilization"
     },
@@ -199,6 +427,24 @@
         "MetricName": "Kernel_Utilization"
     },
     {
+        "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": "Kernel_CPI"
+    },
+    {
+        "BriefDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]",
+        "MetricExpr": "64 * ( arb@event\\=0x81\\,umask\\=0x1@ + arb@event\\=0x84\\,umask\\=0x1@ ) / 1000000 / duration_time / 1000",
+        "MetricGroup": "HPC;Mem;MemoryBW;SoC",
+        "MetricName": "DRAM_BW_Use"
+    },
+    {
+        "BriefDescription": "Average number of parallel requests to external memory. Accounts for all requests",
+        "MetricExpr": "UNC_ARB_TRK_OCCUPANCY.ALL / arb@event\\=0x81\\,umask\\=0x1@",
+        "MetricGroup": "Mem;SoC",
+        "MetricName": "MEM_Parallel_Requests"
+    },
+    {
         "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": "INST_RETIRED.ANY / BR_INST_RETIRED.FAR_BRANCH:u",
         "MetricGroup": "Branches;OS",
@@ -217,6 +463,18 @@
         "MetricName": "C7_Core_Residency"
     },
     {
+        "BriefDescription": "C2 residency percent per package",
+        "MetricExpr": "(cstate_pkg@c2\\-residency@ / msr@tsc@) * 100",
+        "MetricGroup": "Power",
+        "MetricName": "C2_Pkg_Residency"
+    },
+    {
+        "BriefDescription": "C3 residency percent per package",
+        "MetricExpr": "(cstate_pkg@c3\\-residency@ / msr@tsc@) * 100",
+        "MetricGroup": "Power",
+        "MetricName": "C3_Pkg_Residency"
+    },
+    {
         "BriefDescription": "C6 residency percent per package",
         "MetricExpr": "(cstate_pkg@c6\\-residency@ / msr@tsc@) * 100",
         "MetricGroup": "Power",
@@ -227,5 +485,23 @@
         "MetricExpr": "(cstate_pkg@c7\\-residency@ / msr@tsc@) * 100",
         "MetricGroup": "Power",
         "MetricName": "C7_Pkg_Residency"
+    },
+    {
+        "BriefDescription": "C8 residency percent per package",
+        "MetricExpr": "(cstate_pkg@c8\\-residency@ / msr@tsc@) * 100",
+        "MetricGroup": "Power",
+        "MetricName": "C8_Pkg_Residency"
+    },
+    {
+        "BriefDescription": "C9 residency percent per package",
+        "MetricExpr": "(cstate_pkg@c9\\-residency@ / msr@tsc@) * 100",
+        "MetricGroup": "Power",
+        "MetricName": "C9_Pkg_Residency"
+    },
+    {
+        "BriefDescription": "C10 residency percent per package",
+        "MetricExpr": "(cstate_pkg@c10\\-residency@ / msr@tsc@) * 100",
+        "MetricGroup": "Power",
+        "MetricName": "C10_Pkg_Residency"
     }
 ]