| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-Id: <20230912205212.1281958-1-ilkka@os.amperecomputing.com>
Date: Tue, 12 Sep 2023 13:52:12 -0700
From: Ilkka Koskinen <ilkka@...amperecomputing.com>
To: James Clark <james.clark@....com>,
John Garry <john.g.garry@...cle.com>,
Ian Rogers <irogers@...gle.com>,
Arnaldo Carvalho de Melo <acme@...nel.org>,
Ilkka Koskinen <ilkka@...amperecomputing.com>
Cc: Will Deacon <will@...nel.org>, Mike Leach <mike.leach@...aro.org>,
Leo Yan <leo.yan@...aro.org>,
Peter Zijlstra <peterz@...radead.org>,
Ingo Molnar <mingo@...hat.com>,
Mark Rutland <mark.rutland@....com>,
Alexander Shishkin <alexander.shishkin@...ux.intel.com>,
Jiri Olsa <jolsa@...nel.org>,
Namhyung Kim <namhyung@...nel.org>,
Adrian Hunter <adrian.hunter@...el.com>,
Dave Kleikamp <dave.kleikamp@...cle.com>,
linux-arm-kernel@...ts.infradead.org,
linux-perf-users@...r.kernel.org, linux-kernel@...r.kernel.org
Subject: [PATCH] perf vendor events arm64: Fix for AmpereOne metrics
This patch addresses review comments that were given for
'commit 705ed549148f ("perf vendor events arm64: Add AmpereOne metrics")'
but didn't make it to the original patch [1][2]
Changes include: A fix for backend_memory formula, use of standard metrics
when possible, using #slots, renaming metrics to avoid spaces in the names,
and cleanup.
[1] https://lore.kernel.org/linux-perf-users/e9bdacb-a231-36af-6a2e-6918ee7effa@os.amperecomputing.com/
[2] https://lore.kernel.org/linux-perf-users/20230826192352.3043220-1-ilkka@os.amperecomputing.com/
Fixes: 705ed549148f ("perf vendor events arm64: Add AmpereOne metrics")
Signed-off-by: Ilkka Koskinen <ilkka@...amperecomputing.com>
---
.../arch/arm64/ampere/ampereone/metrics.json | 385 ++++++++++--------
1 file changed, 207 insertions(+), 178 deletions(-)
diff --git a/tools/perf/pmu-events/arch/arm64/ampere/ampereone/metrics.json b/tools/perf/pmu-events/arch/arm64/ampere/ampereone/metrics.json
index 1e7e8901a445..c3f9e03c338e 100644
--- a/tools/perf/pmu-events/arch/arm64/ampere/ampereone/metrics.json
+++ b/tools/perf/pmu-events/arch/arm64/ampere/ampereone/metrics.json
@@ -1,362 +1,391 @@
[
{
+ "MetricName": "branch_miss_pred_rate",
"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"
+ "MetricGroup": "branch",
+ "ScaleUnit": "100%"
},
{
- "MetricExpr": "BR_MIS_PRED_RETIRED / BR_RETIRED",
- "BriefDescription": "Branch predictor misprediction rate",
- "MetricGroup": "Branch Prediction",
- "MetricName": "Misprediction (retired)"
- },
- {
- "MetricExpr": "BUS_ACCESS / ( BUS_CYCLES * 1)",
+ "MetricName": "bus_utilization",
+ "MetricExpr": "((BUS_ACCESS / (BUS_CYCLES * 1)) * 100)",
"BriefDescription": "Core-to-uncore bus utilization",
"MetricGroup": "Bus",
- "MetricName": "Bus utilization"
+ "ScaleUnit": "1percent of bus cycles"
},
{
- "MetricExpr": "L1D_CACHE_REFILL / L1D_CACHE",
- "BriefDescription": "L1D cache miss rate",
- "MetricGroup": "Cache",
- "MetricName": "L1D cache miss"
+ "MetricName": "l1d_cache_miss_ratio",
+ "MetricExpr": "(L1D_CACHE_REFILL / L1D_CACHE)",
+ "BriefDescription": "This metric measures the ratio of level 1 data cache accesses missed to the total number of level 1 data cache accesses. This gives an indication of the effectiveness of the level 1 data cache.",
+ "MetricGroup": "Miss_Ratio;L1D_Cache_Effectiveness",
+ "ScaleUnit": "1per cache access"
},
{
- "MetricExpr": "L1D_CACHE_LMISS_RD / L1D_CACHE_RD",
- "BriefDescription": "L1D cache read miss rate",
- "MetricGroup": "Cache",
- "MetricName": "L1D cache read miss"
+ "MetricName": "l1i_cache_miss_ratio",
+ "MetricExpr": "(L1I_CACHE_REFILL / L1I_CACHE)",
+ "BriefDescription": "This metric measures the ratio of level 1 instruction cache accesses missed to the total number of level 1 instruction cache accesses. This gives an indication of the effectiveness of the level 1 instruction cache.",
+ "MetricGroup": "Miss_Ratio;L1I_Cache_Effectiveness",
+ "ScaleUnit": "1per cache access"
},
{
- "MetricExpr": "L1I_CACHE_REFILL / L1I_CACHE",
- "BriefDescription": "L1I cache miss rate",
+ "MetricName": "Miss_Ratio;l1d_cache_read_miss",
+ "MetricExpr": "L1D_CACHE_LMISS_RD / L1D_CACHE_RD",
+ "BriefDescription": "L1D cache read miss rate",
"MetricGroup": "Cache",
- "MetricName": "L1I cache miss"
+ "ScaleUnit": "1per cache read access"
},
{
- "MetricExpr": "L2D_CACHE_REFILL / L2D_CACHE",
- "BriefDescription": "L2 cache miss rate",
- "MetricGroup": "Cache",
- "MetricName": "L2 cache miss"
+ "MetricName": "l2_cache_miss_ratio",
+ "MetricExpr": "(L2D_CACHE_REFILL / L2D_CACHE)",
+ "BriefDescription": "This metric measures the ratio of level 2 cache accesses missed to the total number of level 2 cache accesses. This gives an indication of the effectiveness of the level 2 cache, which is a unified cache that stores both data and instruction. Note that cache accesses in this cache are either data memory access or instruction fetch as this is a unified cache.",
+ "MetricGroup": "Miss_Ratio;L2_Cache_Effectiveness",
+ "ScaleUnit": "1per cache access"
},
{
+ "MetricName": "l1i_cache_read_miss_rate",
"MetricExpr": "L1I_CACHE_LMISS / L1I_CACHE",
"BriefDescription": "L1I cache read miss rate",
"MetricGroup": "Cache",
- "MetricName": "L1I cache read miss"
+ "ScaleUnit": "1per cache access"
},
{
+ "MetricName": "l2d_cache_read_miss_rate",
"MetricExpr": "L2D_CACHE_LMISS_RD / L2D_CACHE_RD",
"BriefDescription": "L2 cache read miss rate",
"MetricGroup": "Cache",
- "MetricName": "L2 cache read miss"
+ "ScaleUnit": "1per cache read access"
},
{
- "MetricExpr": "(L1D_CACHE_LMISS_RD * 1000) / INST_RETIRED",
+ "MetricName": "l1d_cache_miss_mpki",
+ "MetricExpr": "(L1D_CACHE_LMISS_RD * 1e3) / INST_RETIRED",
"BriefDescription": "Misses per thousand instructions (data)",
"MetricGroup": "Cache",
- "MetricName": "MPKI data"
+ "ScaleUnit": "1MPKI"
},
{
- "MetricExpr": "(L1I_CACHE_LMISS * 1000) / INST_RETIRED",
+ "MetricName": "l1i_cache_miss_mpki",
+ "MetricExpr": "(L1I_CACHE_LMISS * 1e3) / INST_RETIRED",
"BriefDescription": "Misses per thousand instructions (instruction)",
"MetricGroup": "Cache",
- "MetricName": "MPKI instruction"
+ "ScaleUnit": "1MPKI"
},
{
- "MetricExpr": "ASE_SPEC / OP_SPEC",
- "BriefDescription": "Proportion of advanced SIMD data processing operations (excluding DP_SPEC/LD_SPEC) operations",
- "MetricGroup": "Instruction",
- "MetricName": "ASE mix"
+ "MetricName": "simd_percentage",
+ "MetricExpr": "((ASE_SPEC / INST_SPEC) * 100)",
+ "BriefDescription": "This metric measures advanced SIMD operations as a percentage of total operations speculatively executed.",
+ "MetricGroup": "Operation_Mix",
+ "ScaleUnit": "1percent of operations"
},
{
- "MetricExpr": "CRYPTO_SPEC / OP_SPEC",
- "BriefDescription": "Proportion of crypto data processing operations",
- "MetricGroup": "Instruction",
- "MetricName": "Crypto mix"
+ "MetricName": "crypto_percentage",
+ "MetricExpr": "((CRYPTO_SPEC / INST_SPEC) * 100)",
+ "BriefDescription": "This metric measures crypto operations as a percentage of operations speculatively executed.",
+ "MetricGroup": "Operation_Mix",
+ "ScaleUnit": "1percent of operations"
},
{
- "MetricExpr": "VFP_SPEC / (duration_time *1000000000)",
- "BriefDescription": "Giga-floating point operations per second",
- "MetricGroup": "Instruction",
- "MetricName": "GFLOPS_ISSUED"
+ "MetricName": "scalar_fp_percentage",
+ "MetricExpr": "((VFP_SPEC / INST_SPEC) * 100)",
+ "BriefDescription": "This metric measures scalar floating point operations as a percentage of operations speculatively executed.",
+ "MetricGroup": "Operation_Mix",
+ "ScaleUnit": "1percent of operations"
},
{
- "MetricExpr": "DP_SPEC / OP_SPEC",
- "BriefDescription": "Proportion of integer data processing operations",
- "MetricGroup": "Instruction",
- "MetricName": "Integer mix"
+ "MetricName": "gflops",
+ "MetricExpr": "VFP_SPEC / (duration_time * 1e9)",
+ "BriefDescription": "Giga-floating point operations per second",
+ "MetricGroup": "InstructionMix"
},
{
- "MetricExpr": "INST_RETIRED / CPU_CYCLES",
- "BriefDescription": "Instructions per cycle",
- "MetricGroup": "Instruction",
- "MetricName": "IPC"
+ "MetricName": "integer_dp_percentage",
+ "MetricExpr": "((DP_SPEC / INST_SPEC) * 100)",
+ "BriefDescription": "This metric measures scalar integer operations as a percentage of operations speculatively executed.",
+ "MetricGroup": "Operation_Mix",
+ "ScaleUnit": "1percent of operations"
},
{
- "MetricExpr": "LD_SPEC / OP_SPEC",
- "BriefDescription": "Proportion of load operations",
- "MetricGroup": "Instruction",
- "MetricName": "Load mix"
+ "MetricName": "ipc",
+ "MetricExpr": "(INST_RETIRED / CPU_CYCLES)",
+ "BriefDescription": "This metric measures the number of instructions retired per cycle.",
+ "MetricGroup": "General",
+ "ScaleUnit": "1per cycle"
},
{
- "MetricExpr": "LDST_SPEC/ OP_SPEC",
- "BriefDescription": "Proportion of load & store operations",
- "MetricGroup": "Instruction",
- "MetricName": "Load-store mix"
+ "MetricName": "load_percentage",
+ "MetricExpr": "((LD_SPEC / INST_SPEC) * 100)",
+ "BriefDescription": "This metric measures load operations as a percentage of operations speculatively executed.",
+ "MetricGroup": "Operation_Mix",
+ "ScaleUnit": "1percent of operations"
},
{
- "MetricExpr": "INST_RETIRED / (duration_time * 1000000)",
- "BriefDescription": "Millions of instructions per second",
- "MetricGroup": "Instruction",
- "MetricName": "MIPS_RETIRED"
+ "MetricName": "load_store_spec_rate",
+ "MetricExpr": "((LDST_SPEC / INST_SPEC) * 100)",
+ "BriefDescription": "The rate of load or store instructions speculatively executed to overall instructions speclatively executed",
+ "MetricGroup": "Operation_Mix",
+ "ScaleUnit": "1percent of operations"
},
{
- "MetricExpr": "INST_SPEC / (duration_time * 1000000)",
+ "MetricName": "retired_mips",
+ "MetricExpr": "INST_RETIRED / (duration_time * 1e6)",
"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"
+ "MetricGroup": "InstructionMix"
},
{
- "MetricExpr": "ST_SPEC / OP_SPEC",
- "BriefDescription": "Proportion of store operations",
- "MetricGroup": "Instruction",
- "MetricName": "Store mix"
+ "MetricName": "spec_utilization_mips",
+ "MetricExpr": "INST_SPEC / (duration_time * 1e6)",
+ "BriefDescription": "Millions of instructions per second",
+ "MetricGroup": "PEutilization"
},
{
- "MetricExpr": "VFP_SPEC / OP_SPEC",
- "BriefDescription": "Proportion of FP operations",
- "MetricGroup": "Instruction",
- "MetricName": "VFP mix"
+ "MetricName": "pc_write_spec_rate",
+ "MetricExpr": "((PC_WRITE_SPEC / INST_SPEC) * 100)",
+ "BriefDescription": "The rate of software change of the PC speculatively executed to overall instructions speclatively executed",
+ "MetricGroup": "Operation_Mix",
+ "ScaleUnit": "1percent of operations"
},
{
- "MetricExpr": "1 - (OP_RETIRED/ (CPU_CYCLES * 4))",
- "BriefDescription": "Proportion of slots lost",
- "MetricGroup": "Speculation / TDA",
- "MetricName": "CPU lost"
+ "MetricName": "store_percentage",
+ "MetricExpr": "((ST_SPEC / INST_SPEC) * 100)",
+ "BriefDescription": "This metric measures store operations as a percentage of operations speculatively executed.",
+ "MetricGroup": "Operation_Mix",
+ "ScaleUnit": "1percent of operations"
},
{
- "MetricExpr": "OP_RETIRED/ (CPU_CYCLES * 4)",
- "BriefDescription": "Proportion of slots retiring",
- "MetricGroup": "Speculation / TDA",
- "MetricName": "CPU utilization"
+ "MetricName": "scalar_fp_percentage",
+ "MetricExpr": "((VFP_SPEC / INST_SPEC) * 100)",
+ "BriefDescription": "This metric measures scalar floating point operations as a percentage of operations speculatively executed.",
+ "MetricGroup": "Operation_Mix",
+ "ScaleUnit": "1percent of operations"
},
{
- "MetricExpr": "OP_RETIRED - OP_SPEC",
- "BriefDescription": "Operations lost due to misspeculation",
- "MetricGroup": "Speculation / TDA",
- "MetricName": "Operations lost"
+ "MetricName": "retired_rate",
+ "MetricExpr": "OP_RETIRED / OP_SPEC",
+ "BriefDescription": "Of all the micro-operations issued, what percentage are retired(committed)",
+ "MetricGroup": "General",
+ "ScaleUnit": "100%"
},
{
- "MetricExpr": "1 - (OP_RETIRED / OP_SPEC)",
- "BriefDescription": "Proportion of operations lost",
- "MetricGroup": "Speculation / TDA",
- "MetricName": "Operations lost (ratio)"
+ "MetricName": "wasted",
+ "MetricExpr": "1 - (OP_RETIRED / (CPU_CYCLES * #slots))",
+ "BriefDescription": "Of all the micro-operations issued, what proportion are lost",
+ "MetricGroup": "General",
+ "ScaleUnit": "100%"
},
{
- "MetricExpr": "OP_RETIRED / OP_SPEC",
- "BriefDescription": "Proportion of operations retired",
- "MetricGroup": "Speculation / TDA",
- "MetricName": "Operations retired"
+ "MetricName": "wasted_rate",
+ "MetricExpr": "1 - OP_RETIRED / OP_SPEC",
+ "BriefDescription": "Of all the micro-operations issued, what percentage are not retired(committed)",
+ "MetricGroup": "General",
+ "ScaleUnit": "100%"
},
{
- "MetricExpr": "STALL_BACKEND_CACHE / CPU_CYCLES",
+ "MetricName": "stall_backend_cache_rate",
+ "MetricExpr": "((STALL_BACKEND_CACHE / CPU_CYCLES) * 100)",
"BriefDescription": "Proportion of cycles stalled and no operations issued to backend and cache miss",
"MetricGroup": "Stall",
- "MetricName": "Stall backend cache cycles"
+ "ScaleUnit": "1percent of cycles"
},
{
- "MetricExpr": "STALL_BACKEND_RESOURCE / CPU_CYCLES",
+ "MetricName": "stall_backend_resource_rate",
+ "MetricExpr": "((STALL_BACKEND_RESOURCE / CPU_CYCLES) * 100)",
"BriefDescription": "Proportion of cycles stalled and no operations issued to backend and resource full",
"MetricGroup": "Stall",
- "MetricName": "Stall backend resource cycles"
+ "ScaleUnit": "1percent of cycles"
},
{
- "MetricExpr": "STALL_BACKEND_TLB / CPU_CYCLES",
+ "MetricName": "stall_backend_tlb_rate",
+ "MetricExpr": "((STALL_BACKEND_TLB / CPU_CYCLES) * 100)",
"BriefDescription": "Proportion of cycles stalled and no operations issued to backend and TLB miss",
"MetricGroup": "Stall",
- "MetricName": "Stall backend tlb cycles"
+ "ScaleUnit": "1percent of cycles"
},
{
- "MetricExpr": "STALL_FRONTEND_CACHE / CPU_CYCLES",
+ "MetricName": "stall_frontend_cache_rate",
+ "MetricExpr": "((STALL_FRONTEND_CACHE / CPU_CYCLES) * 100)",
"BriefDescription": "Proportion of cycles stalled and no ops delivered from frontend and cache miss",
"MetricGroup": "Stall",
- "MetricName": "Stall frontend cache cycles"
+ "ScaleUnit": "1percent of cycles"
},
{
- "MetricExpr": "STALL_FRONTEND_TLB / CPU_CYCLES",
+ "MetricName": "stall_frontend_tlb_rate",
+ "MetricExpr": "((STALL_FRONTEND_TLB / CPU_CYCLES) * 100)",
"BriefDescription": "Proportion of cycles stalled and no ops delivered from frontend and TLB miss",
"MetricGroup": "Stall",
- "MetricName": "Stall frontend tlb cycles"
+ "ScaleUnit": "1percent of cycles"
},
{
- "MetricExpr": "DTLB_WALK / L1D_TLB",
- "BriefDescription": "D-side walk per d-side translation request",
- "MetricGroup": "TLB",
- "MetricName": "DTLB walks"
+ "MetricName": "dtlb_walk_ratio",
+ "MetricExpr": "(DTLB_WALK / L1D_TLB)",
+ "BriefDescription": "This metric measures the ratio of data TLB Walks to the total number of data TLB accesses. This gives an indication of the effectiveness of the data TLB accesses.",
+ "MetricGroup": "Miss_Ratio;DTLB_Effectiveness",
+ "ScaleUnit": "1per TLB access"
},
{
- "MetricExpr": "ITLB_WALK / L1I_TLB",
- "BriefDescription": "I-side walk per i-side translation request",
- "MetricGroup": "TLB",
- "MetricName": "ITLB walks"
+ "MetricName": "itlb_walk_ratio",
+ "MetricExpr": "(ITLB_WALK / L1I_TLB)",
+ "BriefDescription": "This metric measures the ratio of instruction TLB Walks to the total number of instruction TLB accesses. This gives an indication of the effectiveness of the instruction TLB accesses.",
+ "MetricGroup": "Miss_Ratio;ITLB_Effectiveness",
+ "ScaleUnit": "1per TLB access"
},
{
- "MetricExpr": "STALL_SLOT_BACKEND / (CPU_CYCLES * 4)",
- "BriefDescription": "Fraction of slots backend bound",
- "MetricGroup": "TopDownL1",
- "MetricName": "backend"
+ "ArchStdEvent": "backend_bound"
},
{
- "MetricExpr": "1 - (retiring + lost + backend)",
- "BriefDescription": "Fraction of slots frontend bound",
- "MetricGroup": "TopDownL1",
- "MetricName": "frontend"
+ "ArchStdEvent": "frontend_bound",
+ "MetricExpr": "1 - (retired_fraction + slots_lost_misspeculation_fraction + backend_bound)"
},
{
- "MetricExpr": "((OP_SPEC - OP_RETIRED) / (CPU_CYCLES * 4))",
+ "MetricName": "slots_lost_misspeculation_fraction",
+ "MetricExpr": "100 * ((OP_SPEC - OP_RETIRED) / (CPU_CYCLES * #slots))",
"BriefDescription": "Fraction of slots lost due to misspeculation",
- "MetricGroup": "TopDownL1",
- "MetricName": "lost"
+ "MetricGroup": "Default;TopDownL1",
+ "ScaleUnit": "1percent of slots"
},
{
- "MetricExpr": "(OP_RETIRED / (CPU_CYCLES * 4))",
+ "MetricName": "retired_fraction",
+ "MetricExpr": "100 * (OP_RETIRED / (CPU_CYCLES * #slots))",
"BriefDescription": "Fraction of slots retiring, useful work",
- "MetricGroup": "TopDownL1",
- "MetricName": "retiring"
+ "MetricGroup": "Default;TopDownL1",
+ "ScaleUnit": "1percent of slots"
},
{
- "MetricExpr": "backend - backend_memory",
+ "MetricName": "backend_core",
+ "MetricExpr": "backend_bound - backend_memory",
"BriefDescription": "Fraction of slots the CPU was stalled due to backend non-memory subsystem issues",
"MetricGroup": "TopDownL2",
- "MetricName": "backend_core"
+ "ScaleUnit": "100%"
},
{
- "MetricExpr": "(STALL_BACKEND_TLB + STALL_BACKEND_CACHE + STALL_BACKEND_MEM) / CPU_CYCLES ",
+ "MetricName": "backend_memory",
+ "MetricExpr": "(STALL_BACKEND_TLB + STALL_BACKEND_CACHE) / CPU_CYCLES",
"BriefDescription": "Fraction of slots the CPU was stalled due to backend memory subsystem issues (cache/tlb miss)",
"MetricGroup": "TopDownL2",
- "MetricName": "backend_memory"
+ "ScaleUnit": "100%"
},
{
- "MetricExpr": " (BR_MIS_PRED_RETIRED / GPC_FLUSH) * lost",
+ "MetricName": "branch_mispredict",
+ "MetricExpr": "(BR_MIS_PRED_RETIRED / GPC_FLUSH) * slots_lost_misspeculation_fraction",
"BriefDescription": "Fraction of slots lost due to branch misprediciton",
"MetricGroup": "TopDownL2",
- "MetricName": "branch_mispredict"
+ "ScaleUnit": "1percent of slots"
},
{
- "MetricExpr": "frontend - frontend_latency",
+ "MetricName": "frontend_bandwidth",
+ "MetricExpr": "frontend_bound - 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"
+ "ScaleUnit": "1percent of slots"
},
{
- "MetricExpr": "(STALL_FRONTEND - ((STALL_SLOT_FRONTEND - (frontend * CPU_CYCLES * 4)) / 4)) / CPU_CYCLES",
+ "MetricName": "frontend_latency",
+ "MetricExpr": "(STALL_FRONTEND - ((STALL_SLOT_FRONTEND - (frontend_bound * CPU_CYCLES * #slots)) / #slots)) / 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"
+ "ScaleUnit": "1percent of slots"
},
{
- "MetricExpr": "lost - branch_mispredict",
+ "MetricName": "other_miss_pred",
+ "MetricExpr": "slots_lost_misspeculation_fraction - branch_mispredict",
"BriefDescription": "Fraction of slots lost due to other/non-branch misprediction misspeculation",
"MetricGroup": "TopDownL2",
- "MetricName": "other_clears"
+ "ScaleUnit": "1percent of slots"
},
{
- "MetricExpr": "(IXU_NUM_UOPS_ISSUED + FSU_ISSUED) / (CPU_CYCLES * 6)",
+ "MetricName": "pipe_utilization",
+ "MetricExpr": "100 * ((IXU_NUM_UOPS_ISSUED + FSU_ISSUED) / (CPU_CYCLES * 6))",
"BriefDescription": "Fraction of execute slots utilized",
"MetricGroup": "TopDownL2",
- "MetricName": "pipe_utilization"
+ "ScaleUnit": "1percent of slots"
},
{
- "MetricExpr": "STALL_BACKEND_MEM / CPU_CYCLES",
+ "MetricName": "d_cache_l2_miss_rate",
+ "MetricExpr": "((STALL_BACKEND_MEM / CPU_CYCLES) * 100)",
"BriefDescription": "Fraction of cycles the CPU was stalled due to data L2 cache miss",
"MetricGroup": "TopDownL3",
- "MetricName": "d_cache_l2_miss"
+ "ScaleUnit": "1percent of cycles"
},
{
- "MetricExpr": "STALL_BACKEND_CACHE / CPU_CYCLES",
+ "MetricName": "d_cache_miss_rate",
+ "MetricExpr": "((STALL_BACKEND_CACHE / CPU_CYCLES) * 100)",
"BriefDescription": "Fraction of cycles the CPU was stalled due to data cache miss",
"MetricGroup": "TopDownL3",
- "MetricName": "d_cache_miss"
+ "ScaleUnit": "1percent of cycles"
},
{
- "MetricExpr": "STALL_BACKEND_TLB / CPU_CYCLES",
+ "MetricName": "d_tlb_miss_rate",
+ "MetricExpr": "((STALL_BACKEND_TLB / CPU_CYCLES) * 100)",
"BriefDescription": "Fraction of cycles the CPU was stalled due to data TLB miss",
"MetricGroup": "TopDownL3",
- "MetricName": "d_tlb_miss"
+ "ScaleUnit": "1percent of cycles"
},
{
- "MetricExpr": "FSU_ISSUED / (CPU_CYCLES * 2)",
+ "MetricName": "fsu_pipe_utilization",
+ "MetricExpr": "((FSU_ISSUED / (CPU_CYCLES * 2)) * 100)",
"BriefDescription": "Fraction of FSU execute slots utilized",
"MetricGroup": "TopDownL3",
- "MetricName": "fsu_pipe_utilization"
+ "ScaleUnit": "1percent of slots"
},
{
- "MetricExpr": "STALL_FRONTEND_CACHE / CPU_CYCLES",
+ "MetricName": "i_cache_miss_rate",
+ "MetricExpr": "((STALL_FRONTEND_CACHE / CPU_CYCLES) * 100)",
"BriefDescription": "Fraction of cycles the CPU was stalled due to instruction cache miss",
"MetricGroup": "TopDownL3",
- "MetricName": "i_cache_miss"
+ "ScaleUnit": "1percent of slots"
},
{
- "MetricExpr": " STALL_FRONTEND_TLB / CPU_CYCLES ",
+ "MetricName": "i_tlb_miss_rate",
+ "MetricExpr": "((STALL_FRONTEND_TLB / CPU_CYCLES) * 100)",
"BriefDescription": "Fraction of cycles the CPU was stalled due to instruction TLB miss",
"MetricGroup": "TopDownL3",
- "MetricName": "i_tlb_miss"
+ "ScaleUnit": "1percent of slots"
},
{
- "MetricExpr": "IXU_NUM_UOPS_ISSUED / (CPU_CYCLES / 4)",
+ "MetricName": "ixu_pipe_utilization",
+ "MetricExpr": "((IXU_NUM_UOPS_ISSUED / (CPU_CYCLES * #slots)) * 100)",
"BriefDescription": "Fraction of IXU execute slots utilized",
"MetricGroup": "TopDownL3",
- "MetricName": "ixu_pipe_utilization"
+ "ScaleUnit": "1percent of slots"
},
{
- "MetricExpr": "IDR_STALL_FLUSH / CPU_CYCLES",
+ "MetricName": "stall_recovery_rate",
+ "MetricExpr": "((IDR_STALL_FLUSH / CPU_CYCLES) * 100)",
"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"
+ "ScaleUnit": "1percent of slots"
},
{
- "MetricExpr": "IDR_STALL_FSU_SCHED / CPU_CYCLES ",
+ "MetricName": "stall_fsu_sched_rate",
+ "MetricExpr": "((IDR_STALL_FSU_SCHED / CPU_CYCLES) * 100)",
"BriefDescription": "Fraction of cycles the CPU was stalled and FSU was full",
"MetricGroup": "TopDownL4",
- "MetricName": "stall_fsu_sched"
+ "ScaleUnit": "1percent of cycles"
},
{
- "MetricExpr": "IDR_STALL_IXU_SCHED / CPU_CYCLES ",
+ "MetricName": "stall_ixu_sched_rate",
+ "MetricExpr": "((IDR_STALL_IXU_SCHED / CPU_CYCLES) * 100)",
"BriefDescription": "Fraction of cycles the CPU was stalled and IXU was full",
"MetricGroup": "TopDownL4",
- "MetricName": "stall_ixu_sched"
+ "ScaleUnit": "1percent of cycles"
},
{
- "MetricExpr": "IDR_STALL_LOB_ID / CPU_CYCLES ",
+ "MetricName": "stall_lob_id_rate",
+ "MetricExpr": "((IDR_STALL_LOB_ID / CPU_CYCLES) * 100)",
"BriefDescription": "Fraction of cycles the CPU was stalled and LOB was full",
"MetricGroup": "TopDownL4",
- "MetricName": "stall_lob_id"
+ "ScaleUnit": "1percent of cycles"
},
{
- "MetricExpr": "IDR_STALL_ROB_ID / CPU_CYCLES",
+ "MetricName": "stall_rob_id_rate",
+ "MetricExpr": "((IDR_STALL_ROB_ID / CPU_CYCLES) * 100)",
"BriefDescription": "Fraction of cycles the CPU was stalled and ROB was full",
"MetricGroup": "TopDownL4",
- "MetricName": "stall_rob_id"
+ "ScaleUnit": "1percent of cycles"
},
{
- "MetricExpr": "IDR_STALL_SOB_ID / CPU_CYCLES ",
+ "MetricName": "stall_sob_id_rate",
+ "MetricExpr": "((IDR_STALL_SOB_ID / CPU_CYCLES) * 100)",
"BriefDescription": "Fraction of cycles the CPU was stalled and SOB was full",
"MetricGroup": "TopDownL4",
- "MetricName": "stall_sob_id"
+ "ScaleUnit": "1percent of cycles"
}
]
--
2.40.1
Powered by blists - more mailing lists