From 97dca6715d0a058a6af028a3019432740b4a0011 Mon Sep 17 00:00:00 2001 From: Andi Kleen Date: Sun, 23 Jul 2017 21:50:34 -0700 Subject: [PATCH] perf vendor events: Add JSON metrics for Sandy Bridge Add JSON metrics for Sandy Bridge. Committer testing: # grep "model name" /proc/cpuinfo | head -1 model name : Intel(R) Core(TM) i5-2400 CPU @ 3.10GHz # perf list metricgroup List of pre-defined events (to be used in -e): Metric Groups: DSB FLOPS Frontend Frontend_Bandwidth Pipeline Ports_Utilization Power SMT Summary TopDownL1 # perf stat -M Power --metric-only -a sleep 1 Performance counter stats for 'system wide': Turbo_Utilization C3_Core_Residency C6_Core_Residency C7_Core_Residency C2_Pkg_Residency C3_Pkg_Residency C6_Pkg_Residency C7_Pkg_Residency 0.8 0.0 98.1 0.0 0.0 0.0 23.4 0.0 1.001153658 seconds time elapsed # perf stat -v -M Power --metric-only -a sleep 1 Using CPUID GenuineIntel-6-2A metric expr cpu_clk_unhalted.thread / cpu_clk_unhalted.ref_tsc for Turbo_Utilization found event cpu_clk_unhalted.thread found event cpu_clk_unhalted.ref_tsc metric expr (cstate_core@c3\-residency@ / msr@tsc@) * 100 for C3_Core_Residency found event cstate_core/c3-residency/ found event msr/tsc/ metric expr (cstate_core@c6\-residency@ / msr@tsc@) * 100 for C6_Core_Residency found event cstate_core/c6-residency/ found event msr/tsc/ metric expr (cstate_core@c7\-residency@ / msr@tsc@) * 100 for C7_Core_Residency found event cstate_core/c7-residency/ found event msr/tsc/ metric expr (cstate_pkg@c2\-residency@ / msr@tsc@) * 100 for C2_Pkg_Residency found event cstate_pkg/c2-residency/ found event msr/tsc/ metric expr (cstate_pkg@c3\-residency@ / msr@tsc@) * 100 for C3_Pkg_Residency found event cstate_pkg/c3-residency/ found event msr/tsc/ metric expr (cstate_pkg@c6\-residency@ / msr@tsc@) * 100 for C6_Pkg_Residency found event cstate_pkg/c6-residency/ found event msr/tsc/ metric expr (cstate_pkg@c7\-residency@ / msr@tsc@) * 100 for C7_Pkg_Residency found event cstate_pkg/c7-residency/ found event msr/tsc/ adding {cpu_clk_unhalted.thread,cpu_clk_unhalted.ref_tsc}:W,{cstate_core/c3-residency/,msr/tsc/}:W,{cstate_core/c6-residency/,msr/tsc/}:W,{cstate_core/c7-residency/,msr/tsc/}:W,{cstate_pkg/c2-residency/,msr/tsc/}:W,{cstate_pkg/c3-residency/,msr/tsc/}:W,{cstate_pkg/c6-residency/,msr/tsc/}:W,{cstate_pkg/c7-residency/,msr/tsc/}:W cpu_clk_unhalted.thread -> cpu/event=0x3c/ cpu_clk_unhalted.ref_tsc -> cpu/umask=0x3,period=2000003,event=0/ Weak group for cstate_pkg/c2-residency//2 failed Weak group for cstate_pkg/c3-residency//2 failed Weak group for cstate_pkg/c6-residency//2 failed Weak group for cstate_pkg/c7-residency//2 failed cpu_clk_unhalted.thread: 5564185 4002833569 4002833569 cpu_clk_unhalted.ref_tsc: 7325424 4002833569 4002833569 cstate_core/c3-residency/: 68293 4003027101 4003027101 msr/tsc/: 12451294472 4003027101 4003027101 cstate_core/c6-residency/: 12238830163 4003260984 4003260984 msr/tsc/: 12452017806 4003260984 4003260984 cstate_core/c7-residency/: 0 4003489648 4003489648 msr/tsc/: 12452725162 4003489648 4003489648 cstate_pkg/c2-residency/: 1830054 1000913138 1000913138 msr/tsc/: 12453441079 4003717513 4003717513 cstate_pkg/c3-residency/: 0 1000973570 1000973570 msr/tsc/: 12454177865 4003954758 4003954758 cstate_pkg/c6-residency/: 2940448859 1001032370 1001032370 msr/tsc/: 12454833890 4004166118 4004166118 cstate_pkg/c7-residency/: 0 1001049818 1001049818 msr/tsc/: 12454919470 4004194204 4004194204 Performance counter stats for 'system wide': Turbo_Utilization C3_Core_Residency C6_Core_Residency C7_Core_Residency C2_Pkg_Residency C3_Pkg_Residency C6_Pkg_Residency C7_Pkg_Residency 0.8 0.0 98.3 0.0 0.0 0.0 23.6 0.0 1.001126519 seconds time elapsed # Signed-off-by: Andi Kleen Tested-by: Arnaldo Carvalho de Melo Cc: Jiri Olsa Link: http://lkml.kernel.org/r/20170905195235.GW2482@two.firstfloor.org Signed-off-by: Arnaldo Carvalho de Melo --- .../arch/x86/sandybridge/snb-metrics.json | 140 ++++++++++++++++++ 1 file changed, 140 insertions(+) create mode 100644 tools/perf/pmu-events/arch/x86/sandybridge/snb-metrics.json diff --git a/tools/perf/pmu-events/arch/x86/sandybridge/snb-metrics.json b/tools/perf/pmu-events/arch/x86/sandybridge/snb-metrics.json new file mode 100644 index 000000000000..b35b1c153c8a --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/sandybridge/snb-metrics.json @@ -0,0 +1,140 @@ +[ + { + "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_DISPATCHED.THREAD / ( cpu@UOPS_DISPATCHED.CORE\\,cmask\\=1@ / 2) if #SMT_on else cpu@UOPS_DISPATCHED.CORE\\,cmask\\=1@", + "MetricGroup": "Pipeline;Ports_Utilization", + "MetricName": "ILP" + }, + { + "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": "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" + } +] -- GitLab