[PATCH 3/4] perf vendor events arm64: Add AmpereOne metrics
Ilkka Koskinen
ilkka at os.amperecomputing.com
Thu Aug 3 14:13:30 PDT 2023
This patch adds AmpereOne metrics. The metrics also work around
the issue related to some of the events.
Signed-off-by: Ilkka Koskinen <ilkka at os.amperecomputing.com>
---
.../arch/arm64/ampere/ampereone/metrics.json | 362 ++++++++++++++++++
1 file changed, 362 insertions(+)
create mode 100644 tools/perf/pmu-events/arch/arm64/ampere/ampereone/metrics.json
diff --git a/tools/perf/pmu-events/arch/arm64/ampere/ampereone/metrics.json b/tools/perf/pmu-events/arch/arm64/ampere/ampereone/metrics.json
new file mode 100644
index 000000000000..1e7e8901a445
--- /dev/null
+++ b/tools/perf/pmu-events/arch/arm64/ampere/ampereone/metrics.json
@@ -0,0 +1,362 @@
+[
+ {
+ "MetricExpr": "BR_MIS_PRED / BR_PRED",
+ "BriefDescription": "Branch predictor misprediction rate. May not count branches that are never resolved because they are in the misprediction shadow of an earlier branch",
+ "MetricGroup": "Branch Prediction",
+ "MetricName": "Misprediction"
+ },
+ {
+ "MetricExpr": "BR_MIS_PRED_RETIRED / BR_RETIRED",
+ "BriefDescription": "Branch predictor misprediction rate",
+ "MetricGroup": "Branch Prediction",
+ "MetricName": "Misprediction (retired)"
+ },
+ {
+ "MetricExpr": "BUS_ACCESS / ( BUS_CYCLES * 1)",
+ "BriefDescription": "Core-to-uncore bus utilization",
+ "MetricGroup": "Bus",
+ "MetricName": "Bus utilization"
+ },
+ {
+ "MetricExpr": "L1D_CACHE_REFILL / L1D_CACHE",
+ "BriefDescription": "L1D cache miss rate",
+ "MetricGroup": "Cache",
+ "MetricName": "L1D cache miss"
+ },
+ {
+ "MetricExpr": "L1D_CACHE_LMISS_RD / L1D_CACHE_RD",
+ "BriefDescription": "L1D cache read miss rate",
+ "MetricGroup": "Cache",
+ "MetricName": "L1D cache read miss"
+ },
+ {
+ "MetricExpr": "L1I_CACHE_REFILL / L1I_CACHE",
+ "BriefDescription": "L1I cache miss rate",
+ "MetricGroup": "Cache",
+ "MetricName": "L1I cache miss"
+ },
+ {
+ "MetricExpr": "L2D_CACHE_REFILL / L2D_CACHE",
+ "BriefDescription": "L2 cache miss rate",
+ "MetricGroup": "Cache",
+ "MetricName": "L2 cache miss"
+ },
+ {
+ "MetricExpr": "L1I_CACHE_LMISS / L1I_CACHE",
+ "BriefDescription": "L1I cache read miss rate",
+ "MetricGroup": "Cache",
+ "MetricName": "L1I cache read miss"
+ },
+ {
+ "MetricExpr": "L2D_CACHE_LMISS_RD / L2D_CACHE_RD",
+ "BriefDescription": "L2 cache read miss rate",
+ "MetricGroup": "Cache",
+ "MetricName": "L2 cache read miss"
+ },
+ {
+ "MetricExpr": "(L1D_CACHE_LMISS_RD * 1000) / INST_RETIRED",
+ "BriefDescription": "Misses per thousand instructions (data)",
+ "MetricGroup": "Cache",
+ "MetricName": "MPKI data"
+ },
+ {
+ "MetricExpr": "(L1I_CACHE_LMISS * 1000) / INST_RETIRED",
+ "BriefDescription": "Misses per thousand instructions (instruction)",
+ "MetricGroup": "Cache",
+ "MetricName": "MPKI instruction"
+ },
+ {
+ "MetricExpr": "ASE_SPEC / OP_SPEC",
+ "BriefDescription": "Proportion of advanced SIMD data processing operations (excluding DP_SPEC/LD_SPEC) operations",
+ "MetricGroup": "Instruction",
+ "MetricName": "ASE mix"
+ },
+ {
+ "MetricExpr": "CRYPTO_SPEC / OP_SPEC",
+ "BriefDescription": "Proportion of crypto data processing operations",
+ "MetricGroup": "Instruction",
+ "MetricName": "Crypto mix"
+ },
+ {
+ "MetricExpr": "VFP_SPEC / (duration_time *1000000000)",
+ "BriefDescription": "Giga-floating point operations per second",
+ "MetricGroup": "Instruction",
+ "MetricName": "GFLOPS_ISSUED"
+ },
+ {
+ "MetricExpr": "DP_SPEC / OP_SPEC",
+ "BriefDescription": "Proportion of integer data processing operations",
+ "MetricGroup": "Instruction",
+ "MetricName": "Integer mix"
+ },
+ {
+ "MetricExpr": "INST_RETIRED / CPU_CYCLES",
+ "BriefDescription": "Instructions per cycle",
+ "MetricGroup": "Instruction",
+ "MetricName": "IPC"
+ },
+ {
+ "MetricExpr": "LD_SPEC / OP_SPEC",
+ "BriefDescription": "Proportion of load operations",
+ "MetricGroup": "Instruction",
+ "MetricName": "Load mix"
+ },
+ {
+ "MetricExpr": "LDST_SPEC/ OP_SPEC",
+ "BriefDescription": "Proportion of load & store operations",
+ "MetricGroup": "Instruction",
+ "MetricName": "Load-store mix"
+ },
+ {
+ "MetricExpr": "INST_RETIRED / (duration_time * 1000000)",
+ "BriefDescription": "Millions of instructions per second",
+ "MetricGroup": "Instruction",
+ "MetricName": "MIPS_RETIRED"
+ },
+ {
+ "MetricExpr": "INST_SPEC / (duration_time * 1000000)",
+ "BriefDescription": "Millions of instructions per second",
+ "MetricGroup": "Instruction",
+ "MetricName": "MIPS_UTILIZATION"
+ },
+ {
+ "MetricExpr": "PC_WRITE_SPEC / OP_SPEC",
+ "BriefDescription": "Proportion of software change of PC operations",
+ "MetricGroup": "Instruction",
+ "MetricName": "PC write mix"
+ },
+ {
+ "MetricExpr": "ST_SPEC / OP_SPEC",
+ "BriefDescription": "Proportion of store operations",
+ "MetricGroup": "Instruction",
+ "MetricName": "Store mix"
+ },
+ {
+ "MetricExpr": "VFP_SPEC / OP_SPEC",
+ "BriefDescription": "Proportion of FP operations",
+ "MetricGroup": "Instruction",
+ "MetricName": "VFP mix"
+ },
+ {
+ "MetricExpr": "1 - (OP_RETIRED/ (CPU_CYCLES * 4))",
+ "BriefDescription": "Proportion of slots lost",
+ "MetricGroup": "Speculation / TDA",
+ "MetricName": "CPU lost"
+ },
+ {
+ "MetricExpr": "OP_RETIRED/ (CPU_CYCLES * 4)",
+ "BriefDescription": "Proportion of slots retiring",
+ "MetricGroup": "Speculation / TDA",
+ "MetricName": "CPU utilization"
+ },
+ {
+ "MetricExpr": "OP_RETIRED - OP_SPEC",
+ "BriefDescription": "Operations lost due to misspeculation",
+ "MetricGroup": "Speculation / TDA",
+ "MetricName": "Operations lost"
+ },
+ {
+ "MetricExpr": "1 - (OP_RETIRED / OP_SPEC)",
+ "BriefDescription": "Proportion of operations lost",
+ "MetricGroup": "Speculation / TDA",
+ "MetricName": "Operations lost (ratio)"
+ },
+ {
+ "MetricExpr": "OP_RETIRED / OP_SPEC",
+ "BriefDescription": "Proportion of operations retired",
+ "MetricGroup": "Speculation / TDA",
+ "MetricName": "Operations retired"
+ },
+ {
+ "MetricExpr": "STALL_BACKEND_CACHE / CPU_CYCLES",
+ "BriefDescription": "Proportion of cycles stalled and no operations issued to backend and cache miss",
+ "MetricGroup": "Stall",
+ "MetricName": "Stall backend cache cycles"
+ },
+ {
+ "MetricExpr": "STALL_BACKEND_RESOURCE / CPU_CYCLES",
+ "BriefDescription": "Proportion of cycles stalled and no operations issued to backend and resource full",
+ "MetricGroup": "Stall",
+ "MetricName": "Stall backend resource cycles"
+ },
+ {
+ "MetricExpr": "STALL_BACKEND_TLB / CPU_CYCLES",
+ "BriefDescription": "Proportion of cycles stalled and no operations issued to backend and TLB miss",
+ "MetricGroup": "Stall",
+ "MetricName": "Stall backend tlb cycles"
+ },
+ {
+ "MetricExpr": "STALL_FRONTEND_CACHE / CPU_CYCLES",
+ "BriefDescription": "Proportion of cycles stalled and no ops delivered from frontend and cache miss",
+ "MetricGroup": "Stall",
+ "MetricName": "Stall frontend cache cycles"
+ },
+ {
+ "MetricExpr": "STALL_FRONTEND_TLB / CPU_CYCLES",
+ "BriefDescription": "Proportion of cycles stalled and no ops delivered from frontend and TLB miss",
+ "MetricGroup": "Stall",
+ "MetricName": "Stall frontend tlb cycles"
+ },
+ {
+ "MetricExpr": "DTLB_WALK / L1D_TLB",
+ "BriefDescription": "D-side walk per d-side translation request",
+ "MetricGroup": "TLB",
+ "MetricName": "DTLB walks"
+ },
+ {
+ "MetricExpr": "ITLB_WALK / L1I_TLB",
+ "BriefDescription": "I-side walk per i-side translation request",
+ "MetricGroup": "TLB",
+ "MetricName": "ITLB walks"
+ },
+ {
+ "MetricExpr": "STALL_SLOT_BACKEND / (CPU_CYCLES * 4)",
+ "BriefDescription": "Fraction of slots backend bound",
+ "MetricGroup": "TopDownL1",
+ "MetricName": "backend"
+ },
+ {
+ "MetricExpr": "1 - (retiring + lost + backend)",
+ "BriefDescription": "Fraction of slots frontend bound",
+ "MetricGroup": "TopDownL1",
+ "MetricName": "frontend"
+ },
+ {
+ "MetricExpr": "((OP_SPEC - OP_RETIRED) / (CPU_CYCLES * 4))",
+ "BriefDescription": "Fraction of slots lost due to misspeculation",
+ "MetricGroup": "TopDownL1",
+ "MetricName": "lost"
+ },
+ {
+ "MetricExpr": "(OP_RETIRED / (CPU_CYCLES * 4))",
+ "BriefDescription": "Fraction of slots retiring, useful work",
+ "MetricGroup": "TopDownL1",
+ "MetricName": "retiring"
+ },
+ {
+ "MetricExpr": "backend - backend_memory",
+ "BriefDescription": "Fraction of slots the CPU was stalled due to backend non-memory subsystem issues",
+ "MetricGroup": "TopDownL2",
+ "MetricName": "backend_core"
+ },
+ {
+ "MetricExpr": "(STALL_BACKEND_TLB + STALL_BACKEND_CACHE + STALL_BACKEND_MEM) / CPU_CYCLES ",
+ "BriefDescription": "Fraction of slots the CPU was stalled due to backend memory subsystem issues (cache/tlb miss)",
+ "MetricGroup": "TopDownL2",
+ "MetricName": "backend_memory"
+ },
+ {
+ "MetricExpr": " (BR_MIS_PRED_RETIRED / GPC_FLUSH) * lost",
+ "BriefDescription": "Fraction of slots lost due to branch misprediciton",
+ "MetricGroup": "TopDownL2",
+ "MetricName": "branch_mispredict"
+ },
+ {
+ "MetricExpr": "frontend - frontend_latency",
+ "BriefDescription": "Fraction of slots the CPU did not dispatch at full bandwidth - able to dispatch partial slots only (1, 2, or 3 uops)",
+ "MetricGroup": "TopDownL2",
+ "MetricName": "frontend_bandwidth"
+ },
+ {
+ "MetricExpr": "(STALL_FRONTEND - ((STALL_SLOT_FRONTEND - (frontend * CPU_CYCLES * 4)) / 4)) / CPU_CYCLES",
+ "BriefDescription": "Fraction of slots the CPU was stalled due to frontend latency issues (cache/tlb miss); nothing to dispatch",
+ "MetricGroup": "TopDownL2",
+ "MetricName": "frontend_latency"
+ },
+ {
+ "MetricExpr": "lost - branch_mispredict",
+ "BriefDescription": "Fraction of slots lost due to other/non-branch misprediction misspeculation",
+ "MetricGroup": "TopDownL2",
+ "MetricName": "other_clears"
+ },
+ {
+ "MetricExpr": "(IXU_NUM_UOPS_ISSUED + FSU_ISSUED) / (CPU_CYCLES * 6)",
+ "BriefDescription": "Fraction of execute slots utilized",
+ "MetricGroup": "TopDownL2",
+ "MetricName": "pipe_utilization"
+ },
+ {
+ "MetricExpr": "STALL_BACKEND_MEM / CPU_CYCLES",
+ "BriefDescription": "Fraction of cycles the CPU was stalled due to data L2 cache miss",
+ "MetricGroup": "TopDownL3",
+ "MetricName": "d_cache_l2_miss"
+ },
+ {
+ "MetricExpr": "STALL_BACKEND_CACHE / CPU_CYCLES",
+ "BriefDescription": "Fraction of cycles the CPU was stalled due to data cache miss",
+ "MetricGroup": "TopDownL3",
+ "MetricName": "d_cache_miss"
+ },
+ {
+ "MetricExpr": "STALL_BACKEND_TLB / CPU_CYCLES",
+ "BriefDescription": "Fraction of cycles the CPU was stalled due to data TLB miss",
+ "MetricGroup": "TopDownL3",
+ "MetricName": "d_tlb_miss"
+ },
+ {
+ "MetricExpr": "FSU_ISSUED / (CPU_CYCLES * 2)",
+ "BriefDescription": "Fraction of FSU execute slots utilized",
+ "MetricGroup": "TopDownL3",
+ "MetricName": "fsu_pipe_utilization"
+ },
+ {
+ "MetricExpr": "STALL_FRONTEND_CACHE / CPU_CYCLES",
+ "BriefDescription": "Fraction of cycles the CPU was stalled due to instruction cache miss",
+ "MetricGroup": "TopDownL3",
+ "MetricName": "i_cache_miss"
+ },
+ {
+ "MetricExpr": " STALL_FRONTEND_TLB / CPU_CYCLES ",
+ "BriefDescription": "Fraction of cycles the CPU was stalled due to instruction TLB miss",
+ "MetricGroup": "TopDownL3",
+ "MetricName": "i_tlb_miss"
+ },
+ {
+ "MetricExpr": "IXU_NUM_UOPS_ISSUED / (CPU_CYCLES / 4)",
+ "BriefDescription": "Fraction of IXU execute slots utilized",
+ "MetricGroup": "TopDownL3",
+ "MetricName": "ixu_pipe_utilization"
+ },
+ {
+ "MetricExpr": "IDR_STALL_FLUSH / CPU_CYCLES",
+ "BriefDescription": "Fraction of cycles the CPU was stalled due to flush recovery",
+ "MetricGroup": "TopDownL3",
+ "MetricName": "recovery"
+ },
+ {
+ "MetricExpr": "STALL_BACKEND_RESOURCE / CPU_CYCLES",
+ "BriefDescription": "Fraction of cycles the CPU was stalled due to core resource shortage",
+ "MetricGroup": "TopDownL3",
+ "MetricName": "resource"
+ },
+ {
+ "MetricExpr": "IDR_STALL_FSU_SCHED / CPU_CYCLES ",
+ "BriefDescription": "Fraction of cycles the CPU was stalled and FSU was full",
+ "MetricGroup": "TopDownL4",
+ "MetricName": "stall_fsu_sched"
+ },
+ {
+ "MetricExpr": "IDR_STALL_IXU_SCHED / CPU_CYCLES ",
+ "BriefDescription": "Fraction of cycles the CPU was stalled and IXU was full",
+ "MetricGroup": "TopDownL4",
+ "MetricName": "stall_ixu_sched"
+ },
+ {
+ "MetricExpr": "IDR_STALL_LOB_ID / CPU_CYCLES ",
+ "BriefDescription": "Fraction of cycles the CPU was stalled and LOB was full",
+ "MetricGroup": "TopDownL4",
+ "MetricName": "stall_lob_id"
+ },
+ {
+ "MetricExpr": "IDR_STALL_ROB_ID / CPU_CYCLES",
+ "BriefDescription": "Fraction of cycles the CPU was stalled and ROB was full",
+ "MetricGroup": "TopDownL4",
+ "MetricName": "stall_rob_id"
+ },
+ {
+ "MetricExpr": "IDR_STALL_SOB_ID / CPU_CYCLES ",
+ "BriefDescription": "Fraction of cycles the CPU was stalled and SOB was full",
+ "MetricGroup": "TopDownL4",
+ "MetricName": "stall_sob_id"
+ }
+]
--
2.40.1
More information about the linux-arm-kernel
mailing list