summaryrefslogtreecommitdiff
path: root/tools/perf/pmu-events/arch/x86/ivytown/ivt-metrics.json
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2017-11-13 13:05:08 -0800
committerLinus Torvalds <torvalds@linux-foundation.org>2017-11-13 13:05:08 -0800
commit31486372a1e9a66ec2e9e2903b8792bba7e503e1 (patch)
tree84f61e0758695e6fbee8d2b7d7b9bc4a5ce6e03b /tools/perf/pmu-events/arch/x86/ivytown/ivt-metrics.json
parent8e9a2dba8686187d8c8179e5b86640e653963889 (diff)
parentfcdfafcb73be8fa45909327bbddca46fb362a675 (diff)
Merge branch 'perf-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Pull perf updates from Ingo Molnar: "The main changes in this cycle were: Kernel: - kprobes updates: use better W^X patterns for code modifications, improve optprobes, remove jprobes. (Masami Hiramatsu, Kees Cook) - core fixes: event timekeeping (enabled/running times statistics) fixes, perf_event_read() locking fixes and cleanups, etc. (Peter Zijlstra) - Extend x86 Intel free-running PEBS support and support x86 user-register sampling in perf record and perf script. (Andi Kleen) Tooling: - Completely rework the way inline frames are handled. Instead of querying for the inline nodes on-demand in the individual tools, we now create proper callchain nodes for inlined frames. (Milian Wolff) - 'perf trace' updates (Arnaldo Carvalho de Melo) - Implement a way to print formatted output to per-event files in 'perf script' to facilitate generate flamegraphs, elliminating the need to write scripts to do that separation (yuzhoujian, Arnaldo Carvalho de Melo) - Update vendor events JSON metrics for Intel's Broadwell, Broadwell Server, Haswell, Haswell Server, IvyBridge, IvyTown, JakeTown, Sandy Bridge, Skylake, SkyLake Server - and Goldmont Plus V1 (Andi Kleen, Kan Liang) - Multithread the synthesizing of PERF_RECORD_ events for pre-existing threads in 'perf top', speeding up that phase, greatly improving the user experience in systems such as Intel's Knights Mill (Kan Liang) - Introduce the concept of weak groups in 'perf stat': try to set up a group, but if it's not schedulable fallback to not using a group. That gives us the best of both worlds: groups if they work, but still a usable fallback if they don't. E.g: (Andi Kleen) - perf sched timehist enhancements (David Ahern) - ... various other enhancements, updates, cleanups and fixes" * 'perf-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (139 commits) kprobes: Don't spam the build log with deprecation warnings arm/kprobes: Remove jprobe test case arm/kprobes: Fix kretprobe test to check correct counter perf srcline: Show correct function name for srcline of callchains perf srcline: Fix memory leak in addr2inlines() perf trace beauty kcmp: Beautify arguments perf trace beauty: Implement pid_fd beautifier tools include uapi: Grab a copy of linux/kcmp.h perf callchain: Fix double mapping al->addr for children without self period perf stat: Make --per-thread update shadow stats to show metrics perf stat: Move the shadow stats scale computation in perf_stat__update_shadow_stats perf tools: Add perf_data_file__write function perf tools: Add struct perf_data_file perf tools: Rename struct perf_data_file to perf_data perf script: Print information about per-event-dump files perf trace beauty prctl: Generate 'option' string table from kernel headers tools include uapi: Grab a copy of linux/prctl.h perf script: Allow creating per-event dump files perf evsel: Restore evsel->priv as a tool private area perf script: Use event_format__fprintf() ...
Diffstat (limited to 'tools/perf/pmu-events/arch/x86/ivytown/ivt-metrics.json')
-rw-r--r--tools/perf/pmu-events/arch/x86/ivytown/ivt-metrics.json164
1 files changed, 164 insertions, 0 deletions
diff --git a/tools/perf/pmu-events/arch/x86/ivytown/ivt-metrics.json b/tools/perf/pmu-events/arch/x86/ivytown/ivt-metrics.json
new file mode 100644
index 000000000000..7c2679514efb
--- /dev/null
+++ b/tools/perf/pmu-events/arch/x86/ivytown/ivt-metrics.json
@@ -0,0 +1,164 @@
+[
+ {
+ "BriefDescription": "Instructions Per Cycle (per logical thread)",
+ "MetricExpr": "INST_RETIRED.ANY / CPU_CLK_UNHALTED.THREAD",
+ "MetricGroup": "TopDownL1",
+ "MetricName": "IPC"
+ },
+ {
+ "BriefDescription": "Uops Per Instruction",
+ "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY",
+ "MetricGroup": "Pipeline",
+ "MetricName": "UPI"
+ },
+ {
+ "BriefDescription": "Rough Estimation of fraction of fetched lines bytes that were likely consumed by program instructions",
+ "MetricExpr": "min( 1 , UOPS_ISSUED.ANY / ( (UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY) * 32 * ( ICACHE.HIT + ICACHE.MISSES ) / 4) )",
+ "MetricGroup": "Frontend",
+ "MetricName": "IFetch_Line_Utilization"
+ },
+ {
+ "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; Frontend_Bandwidth",
+ "MetricName": "DSB_Coverage"
+ },
+ {
+ "BriefDescription": "Cycles Per Instruction (threaded)",
+ "MetricExpr": "1 / (INST_RETIRED.ANY / cycles)",
+ "MetricGroup": "Pipeline;Summary",
+ "MetricName": "CPI"
+ },
+ {
+ "BriefDescription": "Per-thread actual clocks when the logical processor is active. This is called 'Clockticks' in VTune.",
+ "MetricExpr": "CPU_CLK_UNHALTED.THREAD",
+ "MetricGroup": "Summary",
+ "MetricName": "CLKS"
+ },
+ {
+ "BriefDescription": "Total issue-pipeline slots",
+ "MetricExpr": "4*(( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles)",
+ "MetricGroup": "TopDownL1",
+ "MetricName": "SLOTS"
+ },
+ {
+ "BriefDescription": "Total number of retired Instructions",
+ "MetricExpr": "INST_RETIRED.ANY",
+ "MetricGroup": "Summary",
+ "MetricName": "Instructions"
+ },
+ {
+ "BriefDescription": "Instructions Per Cycle (per physical core)",
+ "MetricExpr": "INST_RETIRED.ANY / (( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles)",
+ "MetricGroup": "SMT",
+ "MetricName": "CoreIPC"
+ },
+ {
+ "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is at least 1 uop executed)",
+ "MetricExpr": "UOPS_EXECUTED.THREAD / (( cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ / 2) if #SMT_on else UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC)",
+ "MetricGroup": "Pipeline;Ports_Utilization",
+ "MetricName": "ILP"
+ },
+ {
+ "BriefDescription": "Average Branch Address Clear Cost (fraction of cycles)",
+ "MetricExpr": "2* (( RS_EVENTS.EMPTY_CYCLES - ICACHE.IFETCH_STALL ) / RS_EVENTS.EMPTY_END)",
+ "MetricGroup": "Unknown_Branches",
+ "MetricName": "BAClear_Cost"
+ },
+ {
+ "BriefDescription": "Core actual clocks when any thread is active on the physical core",
+ "MetricExpr": "( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else CPU_CLK_UNHALTED.THREAD",
+ "MetricGroup": "SMT",
+ "MetricName": "CORE_CLKS"
+ },
+ {
+ "BriefDescription": "Actual Average Latency for L1 data-cache miss demand loads",
+ "MetricExpr": "L1D_PEND_MISS.PENDING / ( MEM_LOAD_UOPS_RETIRED.L1_MISS + mem_load_uops_retired.hit_lfb )",
+ "MetricGroup": "Memory_Bound;Memory_Lat",
+ "MetricName": "Load_Miss_Real_Latency"
+ },
+ {
+ "BriefDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least 1 such miss)",
+ "MetricExpr": "L1D_PEND_MISS.PENDING / (( cpu@l1d_pend_miss.pending_cycles\\,any\\=1@ / 2) if #SMT_on else L1D_PEND_MISS.PENDING_CYCLES)",
+ "MetricGroup": "Memory_Bound;Memory_BW",
+ "MetricName": "MLP"
+ },
+ {
+ "BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses",
+ "MetricExpr": "( ITLB_MISSES.WALK_DURATION + DTLB_LOAD_MISSES.WALK_DURATION + DTLB_STORE_MISSES.WALK_DURATION ) / (( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles)",
+ "MetricGroup": "TLB",
+ "MetricName": "Page_Walks_Utilization"
+ },
+ {
+ "BriefDescription": "Average CPU Utilization",
+ "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / msr@tsc@",
+ "MetricGroup": "Summary",
+ "MetricName": "CPU_Utilization"
+ },
+ {
+ "BriefDescription": "Giga Floating Point Operations Per Second",
+ "MetricExpr": "(( 1*( 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 )) / 1000000000 / duration_time",
+ "MetricGroup": "FLOPS;Summary",
+ "MetricName": "GFLOPs"
+ },
+ {
+ "BriefDescription": "Average Frequency Utilization relative nominal frequency",
+ "MetricExpr": "CPU_CLK_UNHALTED.THREAD / CPU_CLK_UNHALTED.REF_TSC",
+ "MetricGroup": "Power",
+ "MetricName": "Turbo_Utilization"
+ },
+ {
+ "BriefDescription": "Fraction of cycles where both hardware threads were active",
+ "MetricExpr": "1 - CPU_CLK_THREAD_UNHALTED.ONE_THREAD_ACTIVE / ( CPU_CLK_THREAD_UNHALTED.REF_XCLK_ANY / 2 ) if #SMT_on else 0",
+ "MetricGroup": "SMT;Summary",
+ "MetricName": "SMT_2T_Utilization"
+ },
+ {
+ "BriefDescription": "Fraction of cycles spent in Kernel mode",
+ "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC:u / CPU_CLK_UNHALTED.REF_TSC",
+ "MetricGroup": "Summary",
+ "MetricName": "Kernel_Utilization"
+ },
+ {
+ "BriefDescription": "C3 residency percent per core",
+ "MetricExpr": "(cstate_core@c3\\-residency@ / msr@tsc@) * 100",
+ "MetricGroup": "Power",
+ "MetricName": "C3_Core_Residency"
+ },
+ {
+ "BriefDescription": "C6 residency percent per core",
+ "MetricExpr": "(cstate_core@c6\\-residency@ / msr@tsc@) * 100",
+ "MetricGroup": "Power",
+ "MetricName": "C6_Core_Residency"
+ },
+ {
+ "BriefDescription": "C7 residency percent per core",
+ "MetricExpr": "(cstate_core@c7\\-residency@ / msr@tsc@) * 100",
+ "MetricGroup": "Power",
+ "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",
+ "MetricName": "C6_Pkg_Residency"
+ },
+ {
+ "BriefDescription": "C7 residency percent per package",
+ "MetricExpr": "(cstate_pkg@c7\\-residency@ / msr@tsc@) * 100",
+ "MetricGroup": "Power",
+ "MetricName": "C7_Pkg_Residency"
+ }
+]