[tip:perf/core] perf vendor events: Add JSON metrics for Broadwell

From: tip-bot for Andi Kleen
Date: Fri Sep 22 2017 - 12:39:20 EST


Commit-ID: cf97962308ba6b6afdeb038505032c7c0972bdfa
Gitweb: http://git.kernel.org/tip/cf97962308ba6b6afdeb038505032c7c0972bdfa
Author: Andi Kleen <ak@xxxxxxxxxxxxxxx>
AuthorDate: Sun, 23 Jul 2017 21:53:25 -0700
Committer: Arnaldo Carvalho de Melo <acme@xxxxxxxxxx>
CommitDate: Wed, 13 Sep 2017 09:49:16 -0300

perf vendor events: Add JSON metrics for Broadwell

Add JSON metrics for Broadwell.

Commiter testing:

# uname -a
Linux jouet 4.13.0-rc7+ #3 SMP Sat Sep 2 09:04:44 -03 2017 x86_64 x86_64 x86_64 GNU/Linux
# grep "model name" /proc/cpuinfo | head -1
model name : Intel(R) Core(TM) i7-5600U CPU @ 2.60GHz
# perf list metricgroup

List of pre-defined events (to be used in -e):

Metric Groups:

DSB
FLOPS
Frontend
Frontend_Bandwidth
Memory_BW
Memory_Bound
Memory_Lat
Pipeline
Ports_Utilization
Power
SMT
Summary
TLB
TopDownL1
Unknown_Branches
# 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
1.1 0.0 0.0 0.0 0.0 0.0 0.0 0.0

1.003502904 seconds time elapsed

#
# perf stat -M Memory_BW --metric-only -a sleep 1

Performance counter stats for 'system wide':

MLP
1.7

1.001364525 seconds time elapsed

#
# perf stat -M TLB --metric-only -a sleep 1

Performance counter stats for 'system wide':

Page_Walks_Utilization
0.1

1.005962198 seconds time elapsed

#
# perf stat -M Summary --metric-only -a sleep 1

Performance counter stats for 'system wide':

Instructions CPI CLKS CPU_Utilization GFLOPs SMT_2T_Utilization Kernel_Utilization
7281856697.0 0.0 11150898087.0 1.0 0.0 1.0 0.7

1.012134025 seconds time elapsed

#

Running in verbose mode shows which counters and expressions are being
used:

# perf stat -v -M Summary --metric-only -a sleep 1
Using CPUID GenuineIntel-6-3D
metric expr 1 / inst_retired.any / cycles for CPI
found event inst_retired.any
found event cycles
metric expr cpu_clk_unhalted.thread for CLKS
found event cpu_clk_unhalted.thread
metric expr inst_retired.any for Instructions
found event inst_retired.any
metric expr cpu_clk_unhalted.ref_tsc / msr@tsc@ for CPU_Utilization
found event cpu_clk_unhalted.ref_tsc
found event msr/tsc/
metric expr ( 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 ) / 1000000000 / duration_time for GFLOPs
found event fp_arith_inst_retired.scalar_single
found event fp_arith_inst_retired.scalar_double
found event fp_arith_inst_retired.128b_packed_double
found event fp_arith_inst_retired.128b_packed_single
found event fp_arith_inst_retired.256b_packed_double
found event fp_arith_inst_retired.256b_packed_single
found event duration_time
metric expr 1 - cpu_clk_thread_unhalted.one_thread_active / ( cpu_clk_thread_unhalted.ref_xclk_any / 2 ) if #smt_on else 0 for SMT_2T_Utilization
found event cpu_clk_thread_unhalted.one_thread_active
found event cpu_clk_thread_unhalted.ref_xclk_any
metric expr cpu_clk_unhalted.ref_tsc:u / cpu_clk_unhalted.ref_tsc for Kernel_Utilization
found event cpu_clk_unhalted.ref_tsc:u
found event cpu_clk_unhalted.ref_tsc
adding {inst_retired.any,cycles}:W,{cpu_clk_unhalted.thread}:W,{inst_retired.any}:W,{cpu_clk_unhalted.ref_tsc,msr/tsc/}:W,{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,duration_time}:W,{cpu_clk_thread_unhalted.one_thread_active,cpu_clk_thread_unhalted.ref_xclk_any}:W,{cpu_clk_unhalted.ref_tsc:u,cpu_clk_unhalted.ref_tsc}:W
inst_retired.any -> cpu/event=0xc0/
cpu_clk_unhalted.thread -> cpu/event=0x3c/
inst_retired.any -> cpu/event=0xc0/
cpu_clk_unhalted.ref_tsc -> cpu/umask=0x3,period=2000003,event=0/
fp_arith_inst_retired.scalar_single -> cpu/umask=0x2,period=2000003,event=0xc7/
fp_arith_inst_retired.scalar_double -> cpu/umask=0x1,period=2000003,event=0xc7/
fp_arith_inst_retired.128b_packed_double -> cpu/umask=0x4,period=2000003,event=0xc7/
fp_arith_inst_retired.128b_packed_single -> cpu/umask=0x8,period=2000003,event=0xc7/
fp_arith_inst_retired.256b_packed_double -> cpu/umask=0x10,period=2000003,event=0xc7/
fp_arith_inst_retired.256b_packed_single -> cpu/umask=0x20,period=2000003,event=0xc7/
cpu_clk_thread_unhalted.one_thread_active -> cpu/umask=0x2,period=2000003,event=0x3c/
cpu_clk_thread_unhalted.ref_xclk_any -> cpu/umask=0x1,any=1,period=2000003,event=0x3c/
cpu_clk_unhalted.ref_tsc -> cpu/umask=0x3,period=2000003,event=0/
cpu_clk_unhalted.ref_tsc -> cpu/umask=0x3,period=2000003,event=0/
Weak group for fp_arith_inst_retired.scalar_single/7 failed
Weak group for cpu_clk_unhalted.ref_tsc:u/2 failed
inst_retired.any: 8704146437 4026374016 619883741
cycles: 11180800018 4026374016 619883741
cpu_clk_unhalted.thread: 11140030295 4026323772 931621933
inst_retired.any: 8643115117 4026260510 1243595906
cpu_clk_unhalted.ref_tsc: 10201638510 4026184297 1247351077
msr/tsc/: 10378022785 4026184297 1247351077
fp_arith_inst_retired.scalar_single: 134697 4026102728 1559210545
fp_arith_inst_retired.scalar_double: 274339 4026007348 1870014984
fp_arith_inst_retired.128b_packed_double: 1639 4025886054 1866736918
fp_arith_inst_retired.128b_packed_single: 0 4025776614 2175106569
fp_arith_inst_retired.256b_packed_double: 0 4025681734 1235551129
fp_arith_inst_retired.256b_packed_single: 0 4025582962 1232398454
duration_time: 0 4025552913 4025552913
cpu_clk_thread_unhalted.one_thread_active: 10505 4025474649 923893076
cpu_clk_thread_unhalted.ref_xclk_any: 394992110 4025474649 923893076
cpu_clk_unhalted.ref_tsc:u: 5341421014 4025360315 1231634198
cpu_clk_unhalted.ref_tsc: 10258278508 4025252611 307909362

Performance counter stats for 'system wide':

Instructions CPI CLKS CPU_Utilization GFLOPs SMT_2T_Utilization Kernel_Utilization
8704146437.0 0.0 11140030295.0 1.0 0.0 1.0 0.5

1.006783654 seconds time elapsed

#

Signed-off-by: Andi Kleen <ak@xxxxxxxxxxxxxxx>
Tested-by: Arnaldo Carvalho de Melo <acme@xxxxxxxxxx>
Cc: Jiri Olsa <jolsa@xxxxxxxxxx>
Link: http://lkml.kernel.org/r/20170905195235.GW2482@xxxxxxxxxxxxxxxxxx
Signed-off-by: Arnaldo Carvalho de Melo <acme@xxxxxxxxxx>
---
.../pmu-events/arch/x86/broadwell/bdw-metrics.json | 164 +++++++++++++++++++++
1 file changed, 164 insertions(+)

diff --git a/tools/perf/pmu-events/arch/x86/broadwell/bdw-metrics.json b/tools/perf/pmu-events/arch/x86/broadwell/bdw-metrics.json
new file mode 100644
index 0000000..49c5f12
--- /dev/null
+++ b/tools/perf/pmu-events/arch/x86/broadwell/bdw-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 , IDQ.MITE_UOPS / ( UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY * 16 * ( ICACHE.HIT + ICACHE.MISSES ) / 4.0 ) )",
+ "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@xxxxxxxxxxxxxxxxxx\\,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.IFDATA_STALL - ( 14 * ITLB_MISSES.STLB_HIT + cpu@xxxxxxxxxxxxxxxxxxxxxxxxx\\,cmask\\=1@ + 7* ITLB_MISSES.WALK_COMPLETED ) ) / 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@xxxxxxxxxxxxxxxxxxxxxxxxxxxx\\,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": "( cpu@xxxxxxxxxxxxxxxxxxxxxxxxx\\,cmask\\=1@ + cpu@xxxxxxxxxxxxxxxxxxxxxxxxxxxxxx\\,cmask\\=1@ + cpu@xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx\\,cmask\\=1@ + 7*(DTLB_STORE_MISSES.WALK_COMPLETED+DTLB_LOAD_MISSES.WALK_COMPLETED+ITLB_MISSES.WALK_COMPLETED)) / ( 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_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 ) / 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"
+ }
+]