Update events from v1.23 to v1.25.
Update TMA metrics from 4.8 to 5.01.
Bring in the event updates v1.25:
https://github.com/intel/perfmon/commit/78d6273c546329052429e3a005491b58fbe1167b
https://github.com/intel/perfmon/commit/f069ed9d0b69b02d76d4b4c59dfc75b62bfb2254
The TMA 5.01 addition is from (with subsequent fixes):
https://github.com/intel/perfmon/commit/1d72913b2d938781fb28f3cc3507aaec5c22d782
Update uncore IIO events umask with the change:
https://github.com/intel/perfmon/commit/d78e8a166537c9ceab4f2e901dc96c53667a2174
which should address an issue originally raised by Michael Petlan:
Reported-by: Michael Petlan <mpetlan@redhat.com>
Closes: https://lore.kernel.org/all/alpine.LRH.2.20.2401300733310.11354@Diego/
Co-authored-by: Caleb Biggers <caleb.biggers@intel.com>
Signed-off-by: Ian Rogers <irogers@google.com>
---
tools/perf/pmu-events/arch/x86/mapfile.csv | 2 +-
.../arch/x86/sapphirerapids/cache.json | 30 +-
.../arch/x86/sapphirerapids/frontend.json | 19 -
.../arch/x86/sapphirerapids/memory.json | 15 +-
.../arch/x86/sapphirerapids/metricgroups.json | 10 +-
.../arch/x86/sapphirerapids/pipeline.json | 23 -
.../arch/x86/sapphirerapids/spr-metrics.json | 968 ++++++++++--------
.../arch/x86/sapphirerapids/uncore-io.json | 138 ++-
8 files changed, 631 insertions(+), 574 deletions(-)
diff --git a/tools/perf/pmu-events/arch/x86/mapfile.csv b/tools/perf/pmu-events/arch/x86/mapfile.csv
index 9cdd8818c087..2b0414f4b7aa 100644
--- a/tools/perf/pmu-events/arch/x86/mapfile.csv
+++ b/tools/perf/pmu-events/arch/x86/mapfile.csv
@@ -27,7 +27,7 @@ GenuineIntel-6-1[AEF],v4,nehalemep,core
GenuineIntel-6-2E,v4,nehalemex,core
GenuineIntel-6-A7,v1.04,rocketlake,core
GenuineIntel-6-2A,v19,sandybridge,core
-GenuineIntel-6-8F,v1.23,sapphirerapids,core
+GenuineIntel-6-8F,v1.25,sapphirerapids,core
GenuineIntel-6-AF,v1.04,sierraforest,core
GenuineIntel-6-(37|4A|4C|4D|5A),v15,silvermont,core
GenuineIntel-6-(4E|5E|8E|9E|A5|A6),v59,skylake,core
diff --git a/tools/perf/pmu-events/arch/x86/sapphirerapids/cache.json b/tools/perf/pmu-events/arch/x86/sapphirerapids/cache.json
index eec7bf6ebd53..e35dbb7c2ccd 100644
--- a/tools/perf/pmu-events/arch/x86/sapphirerapids/cache.json
+++ b/tools/perf/pmu-events/arch/x86/sapphirerapids/cache.json
@@ -92,11 +92,11 @@
"UMask": "0x2"
},
{
- "BriefDescription": "Non-modified cache lines that are silently dropped by L2 cache when triggered by an L2 cache fill.",
+ "BriefDescription": "Non-modified cache lines that are silently dropped by L2 cache.",
"Counter": "0,1,2,3",
"EventCode": "0x26",
"EventName": "L2_LINES_OUT.SILENT",
- "PublicDescription": "Counts the number of lines that are silently dropped by L2 cache when triggered by an L2 cache fill. These lines are typically in Shared or Exclusive state. A non-threaded event.",
+ "PublicDescription": "Counts the number of lines that are silently dropped by L2 cache. These lines are typically in Shared or Exclusive state. A non-threaded event.",
"SampleAfterValue": "200003",
"UMask": "0x1"
},
@@ -311,7 +311,6 @@
"Data_LA": "1",
"EventCode": "0xd0",
"EventName": "MEM_INST_RETIRED.ALL_LOADS",
- "PEBS": "1",
"PublicDescription": "Counts all retired load instructions. This event accounts for SW prefetch instructions of PREFETCHNTA or PREFETCHT0/1/2 or PREFETCHW.",
"SampleAfterValue": "1000003",
"UMask": "0x81"
@@ -322,7 +321,6 @@
"Data_LA": "1",
"EventCode": "0xd0",
"EventName": "MEM_INST_RETIRED.ALL_STORES",
- "PEBS": "1",
"PublicDescription": "Counts all retired store instructions.",
"SampleAfterValue": "1000003",
"UMask": "0x82"
@@ -333,7 +331,6 @@
"Data_LA": "1",
"EventCode": "0xd0",
"EventName": "MEM_INST_RETIRED.ANY",
- "PEBS": "1",
"PublicDescription": "Counts all retired memory instructions - loads and stores.",
"SampleAfterValue": "1000003",
"UMask": "0x83"
@@ -344,7 +341,6 @@
"Data_LA": "1",
"EventCode": "0xd0",
"EventName": "MEM_INST_RETIRED.LOCK_LOADS",
- "PEBS": "1",
"PublicDescription": "Counts retired load instructions with locked access.",
"SampleAfterValue": "100007",
"UMask": "0x21"
@@ -355,7 +351,6 @@
"Data_LA": "1",
"EventCode": "0xd0",
"EventName": "MEM_INST_RETIRED.SPLIT_LOADS",
- "PEBS": "1",
"PublicDescription": "Counts retired load instructions that split across a cacheline boundary.",
"SampleAfterValue": "100003",
"UMask": "0x41"
@@ -366,7 +361,6 @@
"Data_LA": "1",
"EventCode": "0xd0",
"EventName": "MEM_INST_RETIRED.SPLIT_STORES",
- "PEBS": "1",
"PublicDescription": "Counts retired store instructions that split across a cacheline boundary.",
"SampleAfterValue": "100003",
"UMask": "0x42"
@@ -377,7 +371,6 @@
"Data_LA": "1",
"EventCode": "0xd0",
"EventName": "MEM_INST_RETIRED.STLB_MISS_LOADS",
- "PEBS": "1",
"PublicDescription": "Number of retired load instructions that (start a) miss in the 2nd-level TLB (STLB).",
"SampleAfterValue": "100003",
"UMask": "0x11"
@@ -388,7 +381,6 @@
"Data_LA": "1",
"EventCode": "0xd0",
"EventName": "MEM_INST_RETIRED.STLB_MISS_STORES",
- "PEBS": "1",
"PublicDescription": "Number of retired store instructions that (start a) miss in the 2nd-level TLB (STLB).",
"SampleAfterValue": "100003",
"UMask": "0x12"
@@ -408,7 +400,6 @@
"Data_LA": "1",
"EventCode": "0xd2",
"EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD",
- "PEBS": "1",
"PublicDescription": "Counts retired load instructions whose data sources were HitM responses from shared L3.",
"SampleAfterValue": "20011",
"UMask": "0x4"
@@ -419,7 +410,6 @@
"Data_LA": "1",
"EventCode": "0xd2",
"EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS",
- "PEBS": "1",
"PublicDescription": "Counts the retired load instructions whose data sources were L3 hit and cross-core snoop missed in on-pkg core cache.",
"SampleAfterValue": "20011",
"UMask": "0x1"
@@ -430,7 +420,6 @@
"Data_LA": "1",
"EventCode": "0xd2",
"EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_NONE",
- "PEBS": "1",
"PublicDescription": "Counts retired load instructions whose data sources were hits in L3 without snoops required.",
"SampleAfterValue": "100003",
"UMask": "0x8"
@@ -441,7 +430,6 @@
"Data_LA": "1",
"EventCode": "0xd2",
"EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_NO_FWD",
- "PEBS": "1",
"PublicDescription": "Counts retired load instructions whose data sources were L3 and cross-core snoop hits in on-pkg core cache.",
"SampleAfterValue": "20011",
"UMask": "0x2"
@@ -452,7 +440,6 @@
"Data_LA": "1",
"EventCode": "0xd3",
"EventName": "MEM_LOAD_L3_MISS_RETIRED.LOCAL_DRAM",
- "PEBS": "1",
"PublicDescription": "Retired load instructions which data sources missed L3 but serviced from local DRAM.",
"SampleAfterValue": "100007",
"UMask": "0x1"
@@ -463,7 +450,6 @@
"Data_LA": "1",
"EventCode": "0xd3",
"EventName": "MEM_LOAD_L3_MISS_RETIRED.REMOTE_DRAM",
- "PEBS": "1",
"SampleAfterValue": "1000003",
"UMask": "0x2"
},
@@ -473,7 +459,6 @@
"Data_LA": "1",
"EventCode": "0xd3",
"EventName": "MEM_LOAD_L3_MISS_RETIRED.REMOTE_FWD",
- "PEBS": "1",
"PublicDescription": "Retired load instructions whose data sources was forwarded from a remote cache.",
"SampleAfterValue": "100007",
"UMask": "0x8"
@@ -484,7 +469,6 @@
"Data_LA": "1",
"EventCode": "0xd3",
"EventName": "MEM_LOAD_L3_MISS_RETIRED.REMOTE_HITM",
- "PEBS": "1",
"SampleAfterValue": "1000003",
"UMask": "0x4"
},
@@ -493,7 +477,6 @@
"Counter": "0,1,2,3",
"EventCode": "0xd3",
"EventName": "MEM_LOAD_L3_MISS_RETIRED.REMOTE_PMM",
- "PEBS": "1",
"PublicDescription": "Counts retired load instructions with remote Intel(R) Optane(TM) DC persistent memory as the data source and the data request missed L3.",
"SampleAfterValue": "100007",
"UMask": "0x10"
@@ -504,7 +487,6 @@
"Data_LA": "1",
"EventCode": "0xd4",
"EventName": "MEM_LOAD_MISC_RETIRED.UC",
- "PEBS": "1",
"PublicDescription": "Retired instructions with at least one load to uncacheable memory-type, or at least one cache-line split locked access (Bus Lock).",
"SampleAfterValue": "100007",
"UMask": "0x4"
@@ -515,7 +497,6 @@
"Data_LA": "1",
"EventCode": "0xd1",
"EventName": "MEM_LOAD_RETIRED.FB_HIT",
- "PEBS": "1",
"PublicDescription": "Counts retired load instructions with at least one uop was load missed in L1 but hit FB (Fill Buffers) due to preceding miss to the same cache line with data not ready.",
"SampleAfterValue": "100007",
"UMask": "0x40"
@@ -526,7 +507,6 @@
"Data_LA": "1",
"EventCode": "0xd1",
"EventName": "MEM_LOAD_RETIRED.L1_HIT",
- "PEBS": "1",
"PublicDescription": "Counts retired load instructions with at least one uop that hit in the L1 data cache. This event includes all SW prefetches and lock instructions regardless of the data source.",
"SampleAfterValue": "1000003",
"UMask": "0x1"
@@ -537,7 +517,6 @@
"Data_LA": "1",
"EventCode": "0xd1",
"EventName": "MEM_LOAD_RETIRED.L1_MISS",
- "PEBS": "1",
"PublicDescription": "Counts retired load instructions with at least one uop that missed in the L1 cache.",
"SampleAfterValue": "200003",
"UMask": "0x8"
@@ -548,7 +527,6 @@
"Data_LA": "1",
"EventCode": "0xd1",
"EventName": "MEM_LOAD_RETIRED.L2_HIT",
- "PEBS": "1",
"PublicDescription": "Counts retired load instructions with L2 cache hits as data sources.",
"SampleAfterValue": "200003",
"UMask": "0x2"
@@ -559,7 +537,6 @@
"Data_LA": "1",
"EventCode": "0xd1",
"EventName": "MEM_LOAD_RETIRED.L2_MISS",
- "PEBS": "1",
"PublicDescription": "Counts retired load instructions missed L2 cache as data sources.",
"SampleAfterValue": "100021",
"UMask": "0x10"
@@ -570,7 +547,6 @@
"Data_LA": "1",
"EventCode": "0xd1",
"EventName": "MEM_LOAD_RETIRED.L3_HIT",
- "PEBS": "1",
"PublicDescription": "Counts retired load instructions with at least one uop that hit in the L3 cache.",
"SampleAfterValue": "100021",
"UMask": "0x4"
@@ -581,7 +557,6 @@
"Data_LA": "1",
"EventCode": "0xd1",
"EventName": "MEM_LOAD_RETIRED.L3_MISS",
- "PEBS": "1",
"PublicDescription": "Counts retired load instructions with at least one uop that missed in the L3 cache.",
"SampleAfterValue": "50021",
"UMask": "0x20"
@@ -592,7 +567,6 @@
"Data_LA": "1",
"EventCode": "0xd1",
"EventName": "MEM_LOAD_RETIRED.LOCAL_PMM",
- "PEBS": "1",
"PublicDescription": "Counts retired load instructions with local Intel(R) Optane(TM) DC persistent memory as the data source and the data request missed L3.",
"SampleAfterValue": "1000003",
"UMask": "0x80"
diff --git a/tools/perf/pmu-events/arch/x86/sapphirerapids/frontend.json b/tools/perf/pmu-events/arch/x86/sapphirerapids/frontend.json
index f6e3e40a3b20..bf68493d4509 100644
--- a/tools/perf/pmu-events/arch/x86/sapphirerapids/frontend.json
+++ b/tools/perf/pmu-events/arch/x86/sapphirerapids/frontend.json
@@ -41,7 +41,6 @@
"EventName": "FRONTEND_RETIRED.ANY_DSB_MISS",
"MSRIndex": "0x3F7",
"MSRValue": "0x1",
- "PEBS": "1",
"PublicDescription": "Counts retired Instructions that experienced DSB (Decode stream buffer i.e. the decoded instruction-cache) miss.",
"SampleAfterValue": "100007",
"UMask": "0x1"
@@ -53,7 +52,6 @@
"EventName": "FRONTEND_RETIRED.DSB_MISS",
"MSRIndex": "0x3F7",
"MSRValue": "0x11",
- "PEBS": "1",
"PublicDescription": "Number of retired Instructions that experienced a critical DSB (Decode stream buffer i.e. the decoded instruction-cache) miss. Critical means stalls were exposed to the back-end as a result of the DSB miss.",
"SampleAfterValue": "100007",
"UMask": "0x1"
@@ -65,7 +63,6 @@
"EventName": "FRONTEND_RETIRED.ITLB_MISS",
"MSRIndex": "0x3F7",
"MSRValue": "0x14",
- "PEBS": "1",
"PublicDescription": "Counts retired Instructions that experienced iTLB (Instruction TLB) true miss.",
"SampleAfterValue": "100007",
"UMask": "0x1"
@@ -77,7 +74,6 @@
"EventName": "FRONTEND_RETIRED.L1I_MISS",
"MSRIndex": "0x3F7",
"MSRValue": "0x12",
- "PEBS": "1",
"PublicDescription": "Counts retired Instructions who experienced Instruction L1 Cache true miss.",
"SampleAfterValue": "100007",
"UMask": "0x1"
@@ -89,7 +85,6 @@
"EventName": "FRONTEND_RETIRED.L2_MISS",
"MSRIndex": "0x3F7",
"MSRValue": "0x13",
- "PEBS": "1",
"PublicDescription": "Counts retired Instructions who experienced Instruction L2 Cache true miss.",
"SampleAfterValue": "100007",
"UMask": "0x1"
@@ -101,7 +96,6 @@
"EventName": "FRONTEND_RETIRED.LATENCY_GE_1",
"MSRIndex": "0x3F7",
"MSRValue": "0x600106",
- "PEBS": "1",
"PublicDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of at least 1 cycle which was not interrupted by a back-end stall.",
"SampleAfterValue": "100007",
"UMask": "0x1"
@@ -113,7 +107,6 @@
"EventName": "FRONTEND_RETIRED.LATENCY_GE_128",
"MSRIndex": "0x3F7",
"MSRValue": "0x608006",
- "PEBS": "1",
"PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 128 cycles which was not interrupted by a back-end stall.",
"SampleAfterValue": "100007",
"UMask": "0x1"
@@ -125,7 +118,6 @@
"EventName": "FRONTEND_RETIRED.LATENCY_GE_16",
"MSRIndex": "0x3F7",
"MSRValue": "0x601006",
- "PEBS": "1",
"PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 16 cycles. During this period the front-end delivered no uops.",
"SampleAfterValue": "100007",
"UMask": "0x1"
@@ -137,7 +129,6 @@
"EventName": "FRONTEND_RETIRED.LATENCY_GE_2",
"MSRIndex": "0x3F7",
"MSRValue": "0x600206",
- "PEBS": "1",
"PublicDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of at least 2 cycles which was not interrupted by a back-end stall.",
"SampleAfterValue": "100007",
"UMask": "0x1"
@@ -149,7 +140,6 @@
"EventName": "FRONTEND_RETIRED.LATENCY_GE_256",
"MSRIndex": "0x3F7",
"MSRValue": "0x610006",
- "PEBS": "1",
"PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 256 cycles which was not interrupted by a back-end stall.",
"SampleAfterValue": "100007",
"UMask": "0x1"
@@ -161,7 +151,6 @@
"EventName": "FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1",
"MSRIndex": "0x3F7",
"MSRValue": "0x100206",
- "PEBS": "1",
"PublicDescription": "Counts retired instructions that are delivered to the back-end after the front-end had at least 1 bubble-slot for a period of 2 cycles. A bubble-slot is an empty issue-pipeline slot while there was no RAT stall.",
"SampleAfterValue": "100007",
"UMask": "0x1"
@@ -173,7 +162,6 @@
"EventName": "FRONTEND_RETIRED.LATENCY_GE_32",
"MSRIndex": "0x3F7",
"MSRValue": "0x602006",
- "PEBS": "1",
"PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 32 cycles. During this period the front-end delivered no uops.",
"SampleAfterValue": "100007",
"UMask": "0x1"
@@ -185,7 +173,6 @@
"EventName": "FRONTEND_RETIRED.LATENCY_GE_4",
"MSRIndex": "0x3F7",
"MSRValue": "0x600406",
- "PEBS": "1",
"PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 4 cycles which was not interrupted by a back-end stall.",
"SampleAfterValue": "100007",
"UMask": "0x1"
@@ -197,7 +184,6 @@
"EventName": "FRONTEND_RETIRED.LATENCY_GE_512",
"MSRIndex": "0x3F7",
"MSRValue": "0x620006",
- "PEBS": "1",
"PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 512 cycles which was not interrupted by a back-end stall.",
"SampleAfterValue": "100007",
"UMask": "0x1"
@@ -209,7 +195,6 @@
"EventName": "FRONTEND_RETIRED.LATENCY_GE_64",
"MSRIndex": "0x3F7",
"MSRValue": "0x604006",
- "PEBS": "1",
"PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 64 cycles which was not interrupted by a back-end stall.",
"SampleAfterValue": "100007",
"UMask": "0x1"
@@ -221,7 +206,6 @@
"EventName": "FRONTEND_RETIRED.LATENCY_GE_8",
"MSRIndex": "0x3F7",
"MSRValue": "0x600806",
- "PEBS": "1",
"PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 8 cycles. During this period the front-end delivered no uops.",
"SampleAfterValue": "100007",
"UMask": "0x1"
@@ -233,7 +217,6 @@
"EventName": "FRONTEND_RETIRED.MS_FLOWS",
"MSRIndex": "0x3F7",
"MSRValue": "0x8",
- "PEBS": "1",
"SampleAfterValue": "100007",
"UMask": "0x1"
},
@@ -244,7 +227,6 @@
"EventName": "FRONTEND_RETIRED.STLB_MISS",
"MSRIndex": "0x3F7",
"MSRValue": "0x15",
- "PEBS": "1",
"PublicDescription": "Counts retired Instructions that experienced STLB (2nd level TLB) true miss.",
"SampleAfterValue": "100007",
"UMask": "0x1"
@@ -256,7 +238,6 @@
"EventName": "FRONTEND_RETIRED.UNKNOWN_BRANCH",
"MSRIndex": "0x3F7",
"MSRValue": "0x17",
- "PEBS": "1",
"SampleAfterValue": "100007",
"UMask": "0x1"
},
diff --git a/tools/perf/pmu-events/arch/x86/sapphirerapids/memory.json b/tools/perf/pmu-events/arch/x86/sapphirerapids/memory.json
index 2ea19539291b..41d4120d4dae 100644
--- a/tools/perf/pmu-events/arch/x86/sapphirerapids/memory.json
+++ b/tools/perf/pmu-events/arch/x86/sapphirerapids/memory.json
@@ -63,7 +63,6 @@
"EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_1024",
"MSRIndex": "0x3F6",
"MSRValue": "0x400",
- "PEBS": "2",
"PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 1024 cycles. Reported latency may be longer than just the memory latency.",
"SampleAfterValue": "53",
"UMask": "0x1"
@@ -76,7 +75,6 @@
"EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_128",
"MSRIndex": "0x3F6",
"MSRValue": "0x80",
- "PEBS": "2",
"PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 128 cycles. Reported latency may be longer than just the memory latency.",
"SampleAfterValue": "1009",
"UMask": "0x1"
@@ -89,7 +87,6 @@
"EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_16",
"MSRIndex": "0x3F6",
"MSRValue": "0x10",
- "PEBS": "2",
"PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 16 cycles. Reported latency may be longer than just the memory latency.",
"SampleAfterValue": "20011",
"UMask": "0x1"
@@ -102,7 +99,6 @@
"EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_256",
"MSRIndex": "0x3F6",
"MSRValue": "0x100",
- "PEBS": "2",
"PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 256 cycles. Reported latency may be longer than just the memory latency.",
"SampleAfterValue": "503",
"UMask": "0x1"
@@ -115,7 +111,6 @@
"EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_32",
"MSRIndex": "0x3F6",
"MSRValue": "0x20",
- "PEBS": "2",
"PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 32 cycles. Reported latency may be longer than just the memory latency.",
"SampleAfterValue": "100007",
"UMask": "0x1"
@@ -128,7 +123,6 @@
"EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_4",
"MSRIndex": "0x3F6",
"MSRValue": "0x4",
- "PEBS": "2",
"PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 4 cycles. Reported latency may be longer than just the memory latency.",
"SampleAfterValue": "100003",
"UMask": "0x1"
@@ -141,7 +135,6 @@
"EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_512",
"MSRIndex": "0x3F6",
"MSRValue": "0x200",
- "PEBS": "2",
"PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 512 cycles. Reported latency may be longer than just the memory latency.",
"SampleAfterValue": "101",
"UMask": "0x1"
@@ -154,7 +147,6 @@
"EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_64",
"MSRIndex": "0x3F6",
"MSRValue": "0x40",
- "PEBS": "2",
"PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 64 cycles. Reported latency may be longer than just the memory latency.",
"SampleAfterValue": "2003",
"UMask": "0x1"
@@ -167,7 +159,6 @@
"EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_8",
"MSRIndex": "0x3F6",
"MSRValue": "0x8",
- "PEBS": "2",
"PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 8 cycles. Reported latency may be longer than just the memory latency.",
"SampleAfterValue": "50021",
"UMask": "0x1"
@@ -178,7 +169,6 @@
"Data_LA": "1",
"EventCode": "0xcd",
"EventName": "MEM_TRANS_RETIRED.STORE_SAMPLE",
- "PEBS": "2",
"PublicDescription": "Counts Retired memory accesses with at least 1 store operation. This PEBS event is the precisely-distributed (PDist) trigger covering all stores uops for sampling by the PEBS Store Latency Facility. The facility is described in Intel SDM Volume 3 section 19.9.8",
"SampleAfterValue": "1000003",
"UMask": "0x2"
@@ -305,17 +295,16 @@
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc9",
"EventName": "RTM_RETIRED.ABORTED",
- "PEBS": "1",
"PublicDescription": "Counts the number of times RTM abort was triggered.",
"SampleAfterValue": "100003",
"UMask": "0x4"
},
{
- "BriefDescription": "Number of times an RTM execution aborted due to none of the previous 4 categories (e.g. interrupt)",
+ "BriefDescription": "Number of times an RTM execution aborted due to none of the previous 3 categories (e.g. interrupt)",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc9",
"EventName": "RTM_RETIRED.ABORTED_EVENTS",
- "PublicDescription": "Counts the number of times an RTM execution aborted due to none of the previous 4 categories (e.g. interrupt).",
+ "PublicDescription": "Counts the number of times an RTM execution aborted due to none of the previous 3 categories (e.g. interrupt).",
"SampleAfterValue": "100003",
"UMask": "0x80"
},
diff --git a/tools/perf/pmu-events/arch/x86/sapphirerapids/metricgroups.json b/tools/perf/pmu-events/arch/x86/sapphirerapids/metricgroups.json
index e1de6c2675c4..9129fb7b7ce4 100644
--- a/tools/perf/pmu-events/arch/x86/sapphirerapids/metricgroups.json
+++ b/tools/perf/pmu-events/arch/x86/sapphirerapids/metricgroups.json
@@ -40,6 +40,7 @@
"IoBW": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
"L2Evicts": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
"LSD": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
+ "LockCont": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
"MachineClears": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
"Machine_Clears": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
"Mem": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
@@ -86,7 +87,9 @@
"tma_bad_speculation_group": "Metrics contributing to tma_bad_speculation category",
"tma_branch_mispredicts_group": "Metrics contributing to tma_branch_mispredicts category",
"tma_branch_resteers_group": "Metrics contributing to tma_branch_resteers category",
+ "tma_code_stlb_miss_group": "Metrics contributing to tma_code_stlb_miss category",
"tma_core_bound_group": "Metrics contributing to tma_core_bound category",
+ "tma_divider_group": "Metrics contributing to tma_divider category",
"tma_dram_bound_group": "Metrics contributing to tma_dram_bound category",
"tma_dtlb_load_group": "Metrics contributing to tma_dtlb_load category",
"tma_dtlb_store_group": "Metrics contributing to tma_dtlb_store category",
@@ -96,6 +99,7 @@
"tma_fp_vector_group": "Metrics contributing to tma_fp_vector category",
"tma_frontend_bound_group": "Metrics contributing to tma_frontend_bound category",
"tma_heavy_operations_group": "Metrics contributing to tma_heavy_operations category",
+ "tma_icache_misses_group": "Metrics contributing to tma_icache_misses category",
"tma_int_operations_group": "Metrics contributing to tma_int_operations category",
"tma_issue2P": "Metrics related by the issue $issue2P",
"tma_issueBM": "Metrics related by the issue $issueBM",
@@ -116,10 +120,13 @@
"tma_issueSpSt": "Metrics related by the issue $issueSpSt",
"tma_issueSyncxn": "Metrics related by the issue $issueSyncxn",
"tma_issueTLB": "Metrics related by the issue $issueTLB",
+ "tma_itlb_misses_group": "Metrics contributing to tma_itlb_misses category",
"tma_l1_bound_group": "Metrics contributing to tma_l1_bound category",
+ "tma_l2_bound_group": "Metrics contributing to tma_l2_bound category",
"tma_l3_bound_group": "Metrics contributing to tma_l3_bound category",
"tma_light_operations_group": "Metrics contributing to tma_light_operations category",
"tma_load_op_utilization_group": "Metrics contributing to tma_load_op_utilization category",
+ "tma_load_stlb_miss_group": "Metrics contributing to tma_load_stlb_miss category",
"tma_machine_clears_group": "Metrics contributing to tma_machine_clears category",
"tma_mem_bandwidth_group": "Metrics contributing to tma_mem_bandwidth category",
"tma_mem_latency_group": "Metrics contributing to tma_mem_latency category",
@@ -133,5 +140,6 @@
"tma_retiring_group": "Metrics contributing to tma_retiring category",
"tma_serializing_operation_group": "Metrics contributing to tma_serializing_operation category",
"tma_store_bound_group": "Metrics contributing to tma_store_bound category",
- "tma_store_op_utilization_group": "Metrics contributing to tma_store_op_utilization category"
+ "tma_store_op_utilization_group": "Metrics contributing to tma_store_op_utilization category",
+ "tma_store_stlb_miss_group": "Metrics contributing to tma_store_stlb_miss category"
}
diff --git a/tools/perf/pmu-events/arch/x86/sapphirerapids/pipeline.json b/tools/perf/pmu-events/arch/x86/sapphirerapids/pipeline.json
index 5d5811f26151..50cacfbbc7cf 100644
--- a/tools/perf/pmu-events/arch/x86/sapphirerapids/pipeline.json
+++ b/tools/perf/pmu-events/arch/x86/sapphirerapids/pipeline.json
@@ -62,7 +62,6 @@
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc4",
"EventName": "BR_INST_RETIRED.ALL_BRANCHES",
- "PEBS": "1",
"PublicDescription": "Counts all branch instructions retired.",
"SampleAfterValue": "400009"
},
@@ -71,7 +70,6 @@
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc4",
"EventName": "BR_INST_RETIRED.COND",
- "PEBS": "1",
"PublicDescription": "Counts conditional branch instructions retired.",
"SampleAfterValue": "400009",
"UMask": "0x11"
@@ -81,7 +79,6 @@
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc4",
"EventName": "BR_INST_RETIRED.COND_NTAKEN",
- "PEBS": "1",
"PublicDescription": "Counts not taken branch instructions retired.",
"SampleAfterValue": "400009",
"UMask": "0x10"
@@ -91,7 +88,6 @@
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc4",
"EventName": "BR_INST_RETIRED.COND_TAKEN",
- "PEBS": "1",
"PublicDescription": "Counts taken conditional branch instructions retired.",
"SampleAfterValue": "400009",
"UMask": "0x1"
@@ -101,7 +97,6 @@
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc4",
"EventName": "BR_INST_RETIRED.FAR_BRANCH",
- "PEBS": "1",
"PublicDescription": "Counts far branch instructions retired.",
"SampleAfterValue": "100007",
"UMask": "0x40"
@@ -111,7 +106,6 @@
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc4",
"EventName": "BR_INST_RETIRED.INDIRECT",
- "PEBS": "1",
"PublicDescription": "Counts near indirect branch instructions retired excluding returns. TSX abort is an indirect branch.",
"SampleAfterValue": "100003",
"UMask": "0x80"
@@ -121,7 +115,6 @@
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc4",
"EventName": "BR_INST_RETIRED.NEAR_CALL",
- "PEBS": "1",
"PublicDescription": "Counts both direct and indirect near call instructions retired.",
"SampleAfterValue": "100007",
"UMask": "0x2"
@@ -131,7 +124,6 @@
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc4",
"EventName": "BR_INST_RETIRED.NEAR_RETURN",
- "PEBS": "1",
"PublicDescription": "Counts return instructions retired.",
"SampleAfterValue": "100007",
"UMask": "0x8"
@@ -141,7 +133,6 @@
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc4",
"EventName": "BR_INST_RETIRED.NEAR_TAKEN",
- "PEBS": "1",
"PublicDescription": "Counts taken branch instructions retired.",
"SampleAfterValue": "400009",
"UMask": "0x20"
@@ -151,7 +142,6 @@
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc5",
"EventName": "BR_MISP_RETIRED.ALL_BRANCHES",
- "PEBS": "1",
"PublicDescription": "Counts all the retired branch instructions that were mispredicted by the processor. A branch misprediction occurs when the processor incorrectly predicts the destination of the branch. When the misprediction is discovered at execution, all the instructions executed in the wrong (speculative) path must be discarded, and the processor must start fetching from the correct path.",
"SampleAfterValue": "400009"
},
@@ -160,7 +150,6 @@
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc5",
"EventName": "BR_MISP_RETIRED.COND",
- "PEBS": "1",
"PublicDescription": "Counts mispredicted conditional branch instructions retired.",
"SampleAfterValue": "400009",
"UMask": "0x11"
@@ -170,7 +159,6 @@
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc5",
"EventName": "BR_MISP_RETIRED.COND_NTAKEN",
- "PEBS": "1",
"PublicDescription": "Counts the number of conditional branch instructions retired that were mispredicted and the branch direction was not taken.",
"SampleAfterValue": "400009",
"UMask": "0x10"
@@ -180,7 +168,6 @@
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc5",
"EventName": "BR_MISP_RETIRED.COND_TAKEN",
- "PEBS": "1",
"PublicDescription": "Counts taken conditional mispredicted branch instructions retired.",
"SampleAfterValue": "400009",
"UMask": "0x1"
@@ -190,7 +177,6 @@
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc5",
"EventName": "BR_MISP_RETIRED.INDIRECT",
- "PEBS": "1",
"PublicDescription": "Counts miss-predicted near indirect branch instructions retired excluding returns. TSX abort is an indirect branch.",
"SampleAfterValue": "100003",
"UMask": "0x80"
@@ -200,7 +186,6 @@
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc5",
"EventName": "BR_MISP_RETIRED.INDIRECT_CALL",
- "PEBS": "1",
"PublicDescription": "Counts retired mispredicted indirect (near taken) CALL instructions, including both register and memory indirect.",
"SampleAfterValue": "400009",
"UMask": "0x2"
@@ -210,7 +195,6 @@
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc5",
"EventName": "BR_MISP_RETIRED.NEAR_TAKEN",
- "PEBS": "1",
"PublicDescription": "Counts number of near branch instructions retired that were mispredicted and taken.",
"SampleAfterValue": "400009",
"UMask": "0x20"
@@ -220,7 +204,6 @@
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc5",
"EventName": "BR_MISP_RETIRED.RET",
- "PEBS": "1",
"PublicDescription": "This is a non-precise version (that is, does not use PEBS) of the event that counts mispredicted return instructions retired.",
"SampleAfterValue": "100007",
"UMask": "0x8"
@@ -469,7 +452,6 @@
"BriefDescription": "Number of instructions retired. Fixed Counter - architectural event",
"Counter": "Fixed counter 0",
"EventName": "INST_RETIRED.ANY",
- "PEBS": "1",
"PublicDescription": "Counts the number of X86 instructions retired - an Architectural PerfMon event. Counting continues during hardware interrupts, traps, and inside interrupt handlers. Notes: INST_RETIRED.ANY is counted by a designated fixed counter freeing up programmable counters to count other events. INST_RETIRED.ANY_P is counted by a programmable counter.",
"SampleAfterValue": "2000003",
"UMask": "0x1"
@@ -479,7 +461,6 @@
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc0",
"EventName": "INST_RETIRED.ANY_P",
- "PEBS": "1",
"PublicDescription": "Counts the number of X86 instructions retired - an Architectural PerfMon event. Counting continues during hardware interrupts, traps, and inside interrupt handlers. Notes: INST_RETIRED.ANY is counted by a designated fixed counter freeing up programmable counters to count other events. INST_RETIRED.ANY_P is counted by a programmable counter.",
"SampleAfterValue": "2000003"
},
@@ -488,7 +469,6 @@
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc0",
"EventName": "INST_RETIRED.MACRO_FUSED",
- "PEBS": "1",
"SampleAfterValue": "2000003",
"UMask": "0x10"
},
@@ -497,7 +477,6 @@
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc0",
"EventName": "INST_RETIRED.NOP",
- "PEBS": "1",
"PublicDescription": "Counts all retired NOP or ENDBR32/64 instructions",
"SampleAfterValue": "2000003",
"UMask": "0x2"
@@ -506,7 +485,6 @@
"BriefDescription": "Precise instruction retired with PEBS precise-distribution",
"Counter": "Fixed counter 0",
"EventName": "INST_RETIRED.PREC_DIST",
- "PEBS": "1",
"PublicDescription": "A version of INST_RETIRED that allows for a precise distribution of samples across instructions retired. It utilizes the Precise Distribution of Instructions Retired (PDIR++) feature to fix bias in how retired instructions get sampled. Use on Fixed Counter 0.",
"SampleAfterValue": "2000003",
"UMask": "0x1"
@@ -516,7 +494,6 @@
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc0",
"EventName": "INST_RETIRED.REP_ITERATION",
- "PEBS": "1",
"PublicDescription": "Number of iterations of Repeat (REP) string retired instructions such as MOVS, CMPS, and SCAS. Each has a byte, word, and doubleword version and string instructions can be repeated using a repetition prefix, REP, that allows their architectural execution to be repeated a number of times as specified by the RCX register. Note the number of iterations is implementation-dependent.",
"SampleAfterValue": "2000003",
"UMask": "0x8"
diff --git a/tools/perf/pmu-events/arch/x86/sapphirerapids/spr-metrics.json b/tools/perf/pmu-events/arch/x86/sapphirerapids/spr-metrics.json
index 2b3b013ccb06..37584a8a75aa 100644
--- a/tools/perf/pmu-events/arch/x86/sapphirerapids/spr-metrics.json
+++ b/tools/perf/pmu-events/arch/x86/sapphirerapids/spr-metrics.json
@@ -34,7 +34,7 @@
"MetricName": "UNCORE_FREQ"
},
{
- "BriefDescription": "Cycles per instruction retired; indicating how much time each executed instruction took; in units of cycles.",
+ "BriefDescription": "Cycles per instruction retired; indicating how much time each executed instruction took; in units of cycles",
"MetricExpr": "CPU_CLK_UNHALTED.THREAD / INST_RETIRED.ANY",
"MetricName": "cpi",
"ScaleUnit": "1per_instr"
@@ -55,85 +55,85 @@
"BriefDescription": "Ratio of number of completed page walks (for 2 megabyte page sizes) caused by demand data loads to the total number of completed instructions",
"MetricExpr": "DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M / INST_RETIRED.ANY",
"MetricName": "dtlb_2nd_level_2mb_large_page_load_mpi",
- "PublicDescription": "Ratio of number of completed page walks (for 2 megabyte page sizes) caused by demand data loads to the total number of completed instructions. This implies it missed in the Data Translation Lookaside Buffer (DTLB) and further levels of TLB.",
+ "PublicDescription": "Ratio of number of completed page walks (for 2 megabyte page sizes) caused by demand data loads to the total number of completed instructions. This implies it missed in the Data Translation Lookaside Buffer (DTLB) and further levels of TLB",
"ScaleUnit": "1per_instr"
},
{
"BriefDescription": "Ratio of number of completed page walks (for all page sizes) caused by demand data loads to the total number of completed instructions",
"MetricExpr": "DTLB_LOAD_MISSES.WALK_COMPLETED / INST_RETIRED.ANY",
"MetricName": "dtlb_2nd_level_load_mpi",
- "PublicDescription": "Ratio of number of completed page walks (for all page sizes) caused by demand data loads to the total number of completed instructions. This implies it missed in the DTLB and further levels of TLB.",
+ "PublicDescription": "Ratio of number of completed page walks (for all page sizes) caused by demand data loads to the total number of completed instructions. This implies it missed in the DTLB and further levels of TLB",
"ScaleUnit": "1per_instr"
},
{
"BriefDescription": "Ratio of number of completed page walks (for all page sizes) caused by demand data stores to the total number of completed instructions",
"MetricExpr": "DTLB_STORE_MISSES.WALK_COMPLETED / INST_RETIRED.ANY",
"MetricName": "dtlb_2nd_level_store_mpi",
- "PublicDescription": "Ratio of number of completed page walks (for all page sizes) caused by demand data stores to the total number of completed instructions. This implies it missed in the DTLB and further levels of TLB.",
+ "PublicDescription": "Ratio of number of completed page walks (for all page sizes) caused by demand data stores to the total number of completed instructions. This implies it missed in the DTLB and further levels of TLB",
"ScaleUnit": "1per_instr"
},
{
- "BriefDescription": "Bandwidth observed by the integrated I/O traffic controller (IIO) of IO reads that are initiated by end device controllers that are requesting memory from the CPU.",
+ "BriefDescription": "Bandwidth observed by the integrated I/O traffic controller (IIO) of IO reads that are initiated by end device controllers that are requesting memory from the CPU",
"MetricExpr": "UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.ALL_PARTS * 4 / 1e6 / duration_time",
"MetricName": "iio_bandwidth_read",
"ScaleUnit": "1MB/s"
},
{
- "BriefDescription": "Bandwidth observed by the integrated I/O traffic controller (IIO) of IO writes that are initiated by end device controllers that are writing memory to the CPU.",
+ "BriefDescription": "Bandwidth observed by the integrated I/O traffic controller (IIO) of IO writes that are initiated by end device controllers that are writing memory to the CPU",
"MetricExpr": "UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.ALL_PARTS * 4 / 1e6 / duration_time",
"MetricName": "iio_bandwidth_write",
"ScaleUnit": "1MB/s"
},
{
- "BriefDescription": "Bandwidth of IO reads that are initiated by end device controllers that are requesting memory from the CPU.",
+ "BriefDescription": "Bandwidth of IO reads that are initiated by end device controllers that are requesting memory from the CPU",
"MetricExpr": "UNC_CHA_TOR_INSERTS.IO_PCIRDCUR * 64 / 1e6 / duration_time",
"MetricName": "io_bandwidth_read",
"ScaleUnit": "1MB/s"
},
{
- "BriefDescription": "Bandwidth of IO reads that are initiated by end device controllers that are requesting memory from the local CPU socket.",
+ "BriefDescription": "Bandwidth of IO reads that are initiated by end device controllers that are requesting memory from the local CPU socket",
"MetricExpr": "UNC_CHA_TOR_INSERTS.IO_PCIRDCUR_LOCAL * 64 / 1e6 / duration_time",
"MetricName": "io_bandwidth_read_local",
"ScaleUnit": "1MB/s"
},
{
- "BriefDescription": "Bandwidth of IO reads that are initiated by end device controllers that are requesting memory from a remote CPU socket.",
+ "BriefDescription": "Bandwidth of IO reads that are initiated by end device controllers that are requesting memory from a remote CPU socket",
"MetricExpr": "UNC_CHA_TOR_INSERTS.IO_PCIRDCUR_REMOTE * 64 / 1e6 / duration_time",
"MetricName": "io_bandwidth_read_remote",
"ScaleUnit": "1MB/s"
},
{
- "BriefDescription": "Bandwidth of IO writes that are initiated by end device controllers that are writing memory to the CPU.",
+ "BriefDescription": "Bandwidth of IO writes that are initiated by end device controllers that are writing memory to the CPU",
"MetricExpr": "(UNC_CHA_TOR_INSERTS.IO_ITOM + UNC_CHA_TOR_INSERTS.IO_ITOMCACHENEAR) * 64 / 1e6 / duration_time",
"MetricName": "io_bandwidth_write",
"ScaleUnit": "1MB/s"
},
{
- "BriefDescription": "Bandwidth of IO writes that are initiated by end device controllers that are writing memory to the local CPU socket.",
+ "BriefDescription": "Bandwidth of IO writes that are initiated by end device controllers that are writing memory to the local CPU socket",
"MetricExpr": "(UNC_CHA_TOR_INSERTS.IO_ITOM_LOCAL + UNC_CHA_TOR_INSERTS.IO_ITOMCACHENEAR_LOCAL) * 64 / 1e6 / duration_time",
"MetricName": "io_bandwidth_write_local",
"ScaleUnit": "1MB/s"
},
{
- "BriefDescription": "Bandwidth of IO writes that are initiated by end device controllers that are writing memory to a remote CPU socket.",
+ "BriefDescription": "Bandwidth of IO writes that are initiated by end device controllers that are writing memory to a remote CPU socket",
"MetricExpr": "(UNC_CHA_TOR_INSERTS.IO_ITOM_REMOTE + UNC_CHA_TOR_INSERTS.IO_ITOMCACHENEAR_REMOTE) * 64 / 1e6 / duration_time",
"MetricName": "io_bandwidth_write_remote",
"ScaleUnit": "1MB/s"
},
{
- "BriefDescription": "Percentage of inbound full cacheline writes initiated by end device controllers that miss the L3 cache.",
+ "BriefDescription": "Percentage of inbound full cacheline writes initiated by end device controllers that miss the L3 cache",
"MetricExpr": "UNC_CHA_TOR_INSERTS.IO_MISS_ITOM / UNC_CHA_TOR_INSERTS.IO_ITOM",
"MetricName": "io_percent_of_inbound_full_writes_that_miss_l3",
"ScaleUnit": "100%"
},
{
- "BriefDescription": "Percentage of inbound partial cacheline writes initiated by end device controllers that miss the L3 cache.",
+ "BriefDescription": "Percentage of inbound partial cacheline writes initiated by end device controllers that miss the L3 cache",
"MetricExpr": "(UNC_CHA_TOR_INSERTS.IO_MISS_ITOMCACHENEAR + UNC_CHA_TOR_INSERTS.IO_MISS_RFO) / (UNC_CHA_TOR_INSERTS.IO_ITOMCACHENEAR + UNC_CHA_TOR_INSERTS.IO_RFO)",
"MetricName": "io_percent_of_inbound_partial_writes_that_miss_l3",
"ScaleUnit": "100%"
},
{
- "BriefDescription": "Percentage of inbound reads initiated by end device controllers that miss the L3 cache.",
+ "BriefDescription": "Percentage of inbound reads initiated by end device controllers that miss the L3 cache",
"MetricExpr": "UNC_CHA_TOR_INSERTS.IO_MISS_PCIRDCUR / UNC_CHA_TOR_INSERTS.IO_PCIRDCUR",
"MetricName": "io_percent_of_inbound_reads_that_miss_l3",
"ScaleUnit": "100%"
@@ -142,14 +142,14 @@
"BriefDescription": "Ratio of number of completed page walks (for 2 megabyte and 4 megabyte page sizes) caused by a code fetch to the total number of completed instructions",
"MetricExpr": "ITLB_MISSES.WALK_COMPLETED_2M_4M / INST_RETIRED.ANY",
"MetricName": "itlb_2nd_level_large_page_mpi",
- "PublicDescription": "Ratio of number of completed page walks (for 2 megabyte and 4 megabyte page sizes) caused by a code fetch to the total number of completed instructions. This implies it missed in the Instruction Translation Lookaside Buffer (ITLB) and further levels of TLB.",
+ "PublicDescription": "Ratio of number of completed page walks (for 2 megabyte and 4 megabyte page sizes) caused by a code fetch to the total number of completed instructions. This implies it missed in the Instruction Translation Lookaside Buffer (ITLB) and further levels of TLB",
"ScaleUnit": "1per_instr"
},
{
"BriefDescription": "Ratio of number of completed page walks (for all page sizes) caused by a code fetch to the total number of completed instructions",
"MetricExpr": "ITLB_MISSES.WALK_COMPLETED / INST_RETIRED.ANY",
"MetricName": "itlb_2nd_level_mpi",
- "PublicDescription": "Ratio of number of completed page walks (for all page sizes) caused by a code fetch to the total number of completed instructions. This implies it missed in the ITLB (Instruction TLB) and further levels of TLB.",
+ "PublicDescription": "Ratio of number of completed page walks (for all page sizes) caused by a code fetch to the total number of completed instructions. This implies it missed in the ITLB (Instruction TLB) and further levels of TLB",
"ScaleUnit": "1per_instr"
},
{
@@ -237,25 +237,25 @@
"ScaleUnit": "1ns"
},
{
- "BriefDescription": "Bandwidth (MB/sec) of read requests that miss the last level cache (LLC) and go to local memory.",
+ "BriefDescription": "Bandwidth (MB/sec) of read requests that miss the last level cache (LLC) and go to local memory",
"MetricExpr": "UNC_CHA_REQUESTS.READS_LOCAL * 64 / 1e6 / duration_time",
"MetricName": "llc_miss_local_memory_bandwidth_read",
"ScaleUnit": "1MB/s"
},
{
- "BriefDescription": "Bandwidth (MB/sec) of write requests that miss the last level cache (LLC) and go to local memory.",
+ "BriefDescription": "Bandwidth (MB/sec) of write requests that miss the last level cache (LLC) and go to local memory",
"MetricExpr": "UNC_CHA_REQUESTS.WRITES_LOCAL * 64 / 1e6 / duration_time",
"MetricName": "llc_miss_local_memory_bandwidth_write",
"ScaleUnit": "1MB/s"
},
{
- "BriefDescription": "Bandwidth (MB/sec) of read requests that miss the last level cache (LLC) and go to remote memory.",
+ "BriefDescription": "Bandwidth (MB/sec) of read requests that miss the last level cache (LLC) and go to remote memory",
"MetricExpr": "UNC_CHA_REQUESTS.READS_REMOTE * 64 / 1e6 / duration_time",
"MetricName": "llc_miss_remote_memory_bandwidth_read",
"ScaleUnit": "1MB/s"
},
{
- "BriefDescription": "Bandwidth (MB/sec) of write requests that miss the last level cache (LLC) and go to remote memory.",
+ "BriefDescription": "Bandwidth (MB/sec) of write requests that miss the last level cache (LLC) and go to remote memory",
"MetricExpr": "UNC_CHA_REQUESTS.WRITES_REMOTE * 64 / 1e6 / duration_time",
"MetricName": "llc_miss_remote_memory_bandwidth_write",
"ScaleUnit": "1MB/s"
@@ -285,19 +285,19 @@
"ScaleUnit": "1MB/s"
},
{
- "BriefDescription": "Memory write bandwidth (MB/sec) caused by directory updates; includes DDR and Intel(R) Optane(TM) Persistent Memory(PMEM).",
+ "BriefDescription": "Memory write bandwidth (MB/sec) caused by directory updates; includes DDR and Intel(R) Optane(TM) Persistent Memory(PMEM)",
"MetricExpr": "(UNC_CHA_DIR_UPDATE.HA + UNC_CHA_DIR_UPDATE.TOR + UNC_M2M_DIRECTORY_UPDATE.ANY) * 64 / 1e6 / duration_time",
"MetricName": "memory_extra_write_bw_due_to_directory_updates",
"ScaleUnit": "1MB/s"
},
{
- "BriefDescription": "Memory read that miss the last level cache (LLC) addressed to local DRAM as a percentage of total memory read accesses, does not include LLC prefetches.",
+ "BriefDescription": "Memory read that miss the last level cache (LLC) addressed to local DRAM as a percentage of total memory read accesses, does not include LLC prefetches",
"MetricExpr": "(UNC_CHA_TOR_INSERTS.IA_MISS_DRD_LOCAL + UNC_CHA_TOR_INSERTS.IA_MISS_DRD_PREF_LOCAL) / (UNC_CHA_TOR_INSERTS.IA_MISS_DRD_LOCAL + UNC_CHA_TOR_INSERTS.IA_MISS_DRD_PREF_LOCAL + UNC_CHA_TOR_INSERTS.IA_MISS_DRD_REMOTE + UNC_CHA_TOR_INSERTS.IA_MISS_DRD_PREF_REMOTE)",
"MetricName": "numa_reads_addressed_to_local_dram",
"ScaleUnit": "100%"
},
{
- "BriefDescription": "Memory reads that miss the last level cache (LLC) addressed to remote DRAM as a percentage of total memory read accesses, does not include LLC prefetches.",
+ "BriefDescription": "Memory reads that miss the last level cache (LLC) addressed to remote DRAM as a percentage of total memory read accesses, does not include LLC prefetches",
"MetricExpr": "(UNC_CHA_TOR_INSERTS.IA_MISS_DRD_REMOTE + UNC_CHA_TOR_INSERTS.IA_MISS_DRD_PREF_REMOTE) / (UNC_CHA_TOR_INSERTS.IA_MISS_DRD_LOCAL + UNC_CHA_TOR_INSERTS.IA_MISS_DRD_PREF_LOCAL + UNC_CHA_TOR_INSERTS.IA_MISS_DRD_REMOTE + UNC_CHA_TOR_INSERTS.IA_MISS_DRD_PREF_REMOTE)",
"MetricName": "numa_reads_addressed_to_remote_dram",
"ScaleUnit": "100%"
@@ -360,7 +360,7 @@
"ScaleUnit": "1per_instr"
},
{
- "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution ports for ALU operations.",
+ "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution ports for ALU operations",
"MetricExpr": "(UOPS_DISPATCHED.PORT_0 + UOPS_DISPATCHED.PORT_1 + UOPS_DISPATCHED.PORT_5_11 + UOPS_DISPATCHED.PORT_6) / (5 * tma_info_core_core_clks)",
"MetricGroup": "TopdownL5;tma_L5_group;tma_ports_utilized_3m_group",
"MetricName": "tma_alu_op_utilization",
@@ -372,7 +372,7 @@
"MetricExpr": "EXE.AMX_BUSY / tma_info_core_core_clks",
"MetricGroup": "BvCB;Compute;HPC;Server;TopdownL3;tma_L3_group;tma_core_bound_group",
"MetricName": "tma_amx_busy",
- "MetricThreshold": "tma_amx_busy > 0.5 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)",
+ "MetricThreshold": "tma_amx_busy > 0.5 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
"ScaleUnit": "100%"
},
{
@@ -380,12 +380,12 @@
"MetricExpr": "78 * ASSISTS.ANY / tma_info_thread_slots",
"MetricGroup": "BvIO;TopdownL4;tma_L4_group;tma_microcode_sequencer_group",
"MetricName": "tma_assists",
- "MetricThreshold": "tma_assists > 0.1 & (tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1)",
+ "MetricThreshold": "tma_assists > 0.1 & tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1",
"PublicDescription": "This metric estimates fraction of slots the CPU retired uops delivered by the Microcode_Sequencer as a result of Assists. Assists are long sequences of uops that are required in certain corner-cases for operations that cannot be handled natively by the execution pipeline. For example; when working with very small floating point values (so-called Denormals); the FP units are not set up to perform these operations natively. Instead; a sequence of instructions to perform the computation on the Denormals is injected into the pipeline. Since these microcode sequences might be dozens of uops long; Assists can be extremely deleterious to performance and they can be avoided in many cases. Sample with: ASSISTS.ANY",
"ScaleUnit": "100%"
},
{
- "BriefDescription": "This metric estimates fraction of slots the CPU retired uops as a result of handing SSE to AVX* or AVX* to SSE transition Assists.",
+ "BriefDescription": "This metric estimates fraction of slots the CPU retired uops as a result of handing SSE to AVX* or AVX* to SSE transition Assists",
"MetricExpr": "63 * ASSISTS.SSE_AVX_MIX / tma_info_thread_slots",
"MetricGroup": "HPC;TopdownL5;tma_L5_group;tma_assists_group",
"MetricName": "tma_avx_assists",
@@ -394,35 +394,125 @@
},
{
"BriefDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend",
- "DefaultMetricgroupName": "TopdownL1",
- "MetricExpr": "topdown\\-be\\-bound / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * tma_info_thread_slots",
- "MetricGroup": "BvOB;Default;TmaL1;TopdownL1;tma_L1_group",
+ "MetricExpr": "topdown\\-be\\-bound / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * slots",
+ "MetricGroup": "BvOB;TmaL1;TopdownL1;tma_L1_group",
"MetricName": "tma_backend_bound",
"MetricThreshold": "tma_backend_bound > 0.2",
- "MetricgroupNoGroup": "TopdownL1;Default",
+ "MetricgroupNoGroup": "TopdownL1",
"PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound. Sample with: TOPDOWN.BACKEND_BOUND_SLOTS",
"ScaleUnit": "100%"
},
{
"BriefDescription": "This category represents fraction of slots wasted due to incorrect speculations",
- "DefaultMetricgroupName": "TopdownL1",
"MetricExpr": "max(1 - (tma_frontend_bound + tma_backend_bound + tma_retiring), 0)",
- "MetricGroup": "Default;TmaL1;TopdownL1;tma_L1_group",
+ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group",
"MetricName": "tma_bad_speculation",
"MetricThreshold": "tma_bad_speculation > 0.15",
- "MetricgroupNoGroup": "TopdownL1;Default",
- "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.",
+ "MetricgroupNoGroup": "TopdownL1",
+ "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example",
"ScaleUnit": "100%"
},
+ {
+ "BriefDescription": "Total pipeline cost of instruction fetch related bottlenecks by large code footprint programs (i-side cache; TLB and BTB misses)",
+ "MetricExpr": "100 * tma_fetch_latency * (tma_itlb_misses + tma_icache_misses + tma_unknown_branches) / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches)",
+ "MetricGroup": "BigFootprint;BvBC;Fed;Frontend;IcMiss;MemoryTLB",
+ "MetricName": "tma_bottleneck_big_code",
+ "MetricThreshold": "tma_bottleneck_big_code > 20"
+ },
+ {
+ "BriefDescription": "Total pipeline cost of instructions used for program control-flow - a subset of the Retiring category in TMA",
+ "MetricExpr": "100 * ((BR_INST_RETIRED.ALL_BRANCHES + 2 * BR_INST_RETIRED.NEAR_CALL + INST_RETIRED.NOP) / tma_info_thread_slots)",
+ "MetricGroup": "BvBO;Ret",
+ "MetricName": "tma_bottleneck_branching_overhead",
+ "MetricThreshold": "tma_bottleneck_branching_overhead > 5",
+ "PublicDescription": "Total pipeline cost of instructions used for program control-flow - a subset of the Retiring category in TMA. Examples include function calls; loops and alignments. (A lower bound)"
+ },
+ {
+ "BriefDescription": "Total pipeline cost of external Memory- or Cache-Bandwidth related bottlenecks",
+ "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_mem_bandwidth / (tma_mem_bandwidth + tma_mem_latency)) + tma_memory_bound * (tma_l3_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_sq_full / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_memory_bound * (tma_l1_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_fb_full / (tma_dtlb_load + tma_store_fwd_blk + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_fb_full)))",
+ "MetricGroup": "BvMB;Mem;MemoryBW;Offcore;tma_issueBW",
+ "MetricName": "tma_bottleneck_cache_memory_bandwidth",
+ "MetricThreshold": "tma_bottleneck_cache_memory_bandwidth > 20",
+ "PublicDescription": "Total pipeline cost of external Memory- or Cache-Bandwidth related bottlenecks. Related metrics: tma_fb_full, tma_info_system_dram_bw_use, tma_mem_bandwidth, tma_sq_full"
+ },
+ {
+ "BriefDescription": "Total pipeline cost of external Memory- or Cache-Latency related bottlenecks",
+ "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_mem_latency / (tma_mem_bandwidth + tma_mem_latency)) + tma_memory_bound * (tma_l3_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_l3_hit_latency / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_memory_bound * tma_l2_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound) + tma_memory_bound * (tma_l1_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_l1_latency_dependency / (tma_dtlb_load + tma_store_fwd_blk + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_fb_full)) + tma_memory_bound * (tma_l1_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_lock_latency / (tma_dtlb_load + tma_store_fwd_blk + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_fb_full)) + tma_memory_bound * (tma_l1_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_split_loads / (tma_dtlb_load + tma_store_fwd_blk + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_fb_full)) + tma_memory_bound * (tma_store_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_split_stores / (tma_store_latency + tma_false_sharing + tma_split_stores + tma_streaming_stores + tma_dtlb_store)) + tma_memory_bound * (tma_store_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_store_latency / (tma_store_latency + tma_false_sharing + tma_split_stores + tma_streaming_stores + tma_dtlb_store)))",
+ "MetricGroup": "BvML;Mem;MemoryLat;Offcore;tma_issueLat",
+ "MetricName": "tma_bottleneck_cache_memory_latency",
+ "MetricThreshold": "tma_bottleneck_cache_memory_latency > 20",
+ "PublicDescription": "Total pipeline cost of external Memory- or Cache-Latency related bottlenecks. Related metrics: tma_l3_hit_latency, tma_mem_latency"
+ },
+ {
+ "BriefDescription": "Total pipeline cost when the execution is compute-bound - an estimation",
+ "MetricExpr": "100 * (tma_core_bound * tma_divider / (tma_divider + tma_serializing_operation + tma_amx_busy + tma_ports_utilization) + tma_core_bound * tma_amx_busy / (tma_divider + tma_serializing_operation + tma_amx_busy + tma_ports_utilization) + tma_core_bound * (tma_ports_utilization / (tma_divider + tma_serializing_operation + tma_amx_busy + tma_ports_utilization)) * (tma_ports_utilized_3m / (tma_ports_utilized_0 + tma_ports_utilized_1 + tma_ports_utilized_2 + tma_ports_utilized_3m)))",
+ "MetricGroup": "BvCB;Cor;tma_issueComp",
+ "MetricName": "tma_bottleneck_compute_bound_est",
+ "MetricThreshold": "tma_bottleneck_compute_bound_est > 20",
+ "PublicDescription": "Total pipeline cost when the execution is compute-bound - an estimation. Covers Core Bound when High ILP as well as when long-latency execution units are busy"
+ },
+ {
+ "BriefDescription": "Total pipeline cost of instruction fetch bandwidth related bottlenecks (when the front-end could not sustain operations delivery to the back-end)",
+ "MetricExpr": "100 * (tma_frontend_bound - (1 - 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts) * tma_fetch_latency * tma_mispredicts_resteers / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches) - (1 - INST_RETIRED.REP_ITERATION / cpu@UOPS_RETIRED.MS\\,cmask\\=0x1@) * (tma_fetch_latency * (tma_ms_switches + tma_branch_resteers * (tma_clears_resteers + tma_mispredicts_resteers * tma_other_mispredicts / tma_branch_mispredicts) / (tma_mispredicts_resteers + tma_clears_resteers + tma_unknown_branches)) / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches) + tma_fetch_bandwidth * tma_ms / (tma_mite + tma_dsb + tma_ms))) - tma_bottleneck_big_code",
+ "MetricGroup": "BvFB;Fed;FetchBW;Frontend",
+ "MetricName": "tma_bottleneck_instruction_fetch_bw",
+ "MetricThreshold": "tma_bottleneck_instruction_fetch_bw > 20"
+ },
+ {
+ "BriefDescription": "Total pipeline cost of irregular execution (e.g",
+ "MetricExpr": "100 * ((1 - INST_RETIRED.REP_ITERATION / cpu@UOPS_RETIRED.MS\\,cmask\\=0x1@) * (tma_fetch_latency * (tma_ms_switches + tma_branch_resteers * (tma_clears_resteers + tma_mispredicts_resteers * tma_other_mispredicts / tma_branch_mispredicts) / (tma_mispredicts_resteers + tma_clears_resteers + tma_unknown_branches)) / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches) + tma_fetch_bandwidth * tma_ms / (tma_mite + tma_dsb + tma_ms)) + 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts * tma_branch_mispredicts + tma_machine_clears * tma_other_nukes / tma_other_nukes + tma_core_bound * (tma_serializing_operation + RS.EMPTY_RESOURCE / tma_info_thread_clks * tma_ports_utilized_0) / (tma_divider + tma_serializing_operation + tma_amx_busy + tma_ports_utilization) + tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * tma_heavy_operations)",
+ "MetricGroup": "Bad;BvIO;Cor;Ret;tma_issueMS",
+ "MetricName": "tma_bottleneck_irregular_overhead",
+ "MetricThreshold": "tma_bottleneck_irregular_overhead > 10",
+ "PublicDescription": "Total pipeline cost of irregular execution (e.g. FP-assists in HPC, Wait time with work imbalance multithreaded workloads, overhead in system services or virtualized environments). Related metrics: tma_microcode_sequencer, tma_ms_switches"
+ },
+ {
+ "BriefDescription": "Total pipeline cost of Memory Address Translation related bottlenecks (data-side TLBs)",
+ "MetricExpr": "100 * (tma_memory_bound * (tma_l1_bound / max(tma_memory_bound, tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_dtlb_load / max(tma_l1_bound, tma_dtlb_load + tma_store_fwd_blk + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_fb_full)) + tma_memory_bound * (tma_store_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_dtlb_store / (tma_store_latency + tma_false_sharing + tma_split_stores + tma_streaming_stores + tma_dtlb_store)))",
+ "MetricGroup": "BvMT;Mem;MemoryTLB;Offcore;tma_issueTLB",
+ "MetricName": "tma_bottleneck_memory_data_tlbs",
+ "MetricThreshold": "tma_bottleneck_memory_data_tlbs > 20",
+ "PublicDescription": "Total pipeline cost of Memory Address Translation related bottlenecks (data-side TLBs). Related metrics: tma_dtlb_load, tma_dtlb_store"
+ },
+ {
+ "BriefDescription": "Total pipeline cost of Memory Synchronization related bottlenecks (data transfers and coherency updates across processors)",
+ "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound) * (tma_mem_latency / (tma_mem_bandwidth + tma_mem_latency)) * tma_remote_cache / (tma_local_mem + tma_remote_mem + tma_remote_cache) + tma_l3_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound) * (tma_contested_accesses + tma_data_sharing) / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full) + tma_store_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound) * tma_false_sharing / (tma_store_latency + tma_false_sharing + tma_split_stores + tma_streaming_stores + tma_dtlb_store - tma_store_latency)) + tma_machine_clears * (1 - tma_other_nukes / tma_other_nukes))",
+ "MetricGroup": "BvMS;LockCont;Mem;Offcore;tma_issueSyncxn",
+ "MetricName": "tma_bottleneck_memory_synchronization",
+ "MetricThreshold": "tma_bottleneck_memory_synchronization > 10",
+ "PublicDescription": "Total pipeline cost of Memory Synchronization related bottlenecks (data transfers and coherency updates across processors). Related metrics: tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_machine_clears, tma_remote_cache"
+ },
+ {
+ "BriefDescription": "Total pipeline cost of Branch Misprediction related bottlenecks",
+ "MetricExpr": "100 * (1 - 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts) * (tma_branch_mispredicts + tma_fetch_latency * tma_mispredicts_resteers / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches))",
+ "MetricGroup": "Bad;BadSpec;BrMispredicts;BvMP;tma_issueBM",
+ "MetricName": "tma_bottleneck_mispredictions",
+ "MetricThreshold": "tma_bottleneck_mispredictions > 20",
+ "PublicDescription": "Total pipeline cost of Branch Misprediction related bottlenecks. Related metrics: tma_branch_mispredicts, tma_info_bad_spec_branch_misprediction_cost, tma_mispredicts_resteers"
+ },
+ {
+ "BriefDescription": "Total pipeline cost of remaining bottlenecks in the back-end",
+ "MetricExpr": "100 - (tma_bottleneck_big_code + tma_bottleneck_instruction_fetch_bw + tma_bottleneck_mispredictions + tma_bottleneck_cache_memory_bandwidth + tma_bottleneck_cache_memory_latency + tma_bottleneck_memory_data_tlbs + tma_bottleneck_memory_synchronization + tma_bottleneck_compute_bound_est + tma_bottleneck_irregular_overhead + tma_bottleneck_branching_overhead + tma_bottleneck_useful_work)",
+ "MetricGroup": "BvOB;Cor;Offcore",
+ "MetricName": "tma_bottleneck_other_bottlenecks",
+ "MetricThreshold": "tma_bottleneck_other_bottlenecks > 20",
+ "PublicDescription": "Total pipeline cost of remaining bottlenecks in the back-end. Examples include data-dependencies (Core Bound when Low ILP) and other unlisted memory-related stalls"
+ },
+ {
+ "BriefDescription": "Total pipeline cost of \"useful operations\" - the portion of Retiring category not covered by Branching_Overhead nor Irregular_Overhead",
+ "MetricExpr": "100 * (tma_retiring - (BR_INST_RETIRED.ALL_BRANCHES + 2 * BR_INST_RETIRED.NEAR_CALL + INST_RETIRED.NOP) / tma_info_thread_slots - tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * tma_heavy_operations)",
+ "MetricGroup": "BvUW;Ret",
+ "MetricName": "tma_bottleneck_useful_work",
+ "MetricThreshold": "tma_bottleneck_useful_work > 20"
+ },
{
"BriefDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction",
- "DefaultMetricgroupName": "TopdownL2",
- "MetricExpr": "topdown\\-br\\-mispredict / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * tma_info_thread_slots",
- "MetricGroup": "BadSpec;BrMispredicts;BvMP;Default;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueBM",
+ "MetricExpr": "topdown\\-br\\-mispredict / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * slots",
+ "MetricGroup": "BadSpec;BrMispredicts;BvMP;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueBM",
"MetricName": "tma_branch_mispredicts",
"MetricThreshold": "tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15",
- "MetricgroupNoGroup": "TopdownL2;Default",
- "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction. These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: TOPDOWN.BR_MISPREDICT_SLOTS. Related metrics: tma_info_bad_spec_branch_misprediction_cost, tma_info_bottleneck_mispredictions, tma_mispredicts_resteers",
+ "MetricgroupNoGroup": "TopdownL2",
+ "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction. These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: TOPDOWN.BR_MISPREDICT_SLOTS. Related metrics: tma_bottleneck_mispredictions, tma_info_bad_spec_branch_misprediction_cost, tma_mispredicts_resteers",
"ScaleUnit": "100%"
},
{
@@ -430,24 +520,24 @@
"MetricExpr": "INT_MISC.CLEAR_RESTEER_CYCLES / tma_info_thread_clks + tma_unknown_branches",
"MetricGroup": "FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group",
"MetricName": "tma_branch_resteers",
- "MetricThreshold": "tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)",
- "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers. Branch Resteers estimates the Frontend delay in fetching operations from corrected path; following all sorts of miss-predicted branches. For example; branchy code with lots of miss-predictions might get categorized under Branch Resteers. Note the value of this node may overlap with its siblings. Sample with: BR_MISP_RETIRED.ALL_BRANCHES",
+ "MetricThreshold": "tma_branch_resteers > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+ "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers. Branch Resteers estimates the Frontend delay in fetching operations from corrected path; following all sorts of miss-predicted branches. For example; branchy code with lots of miss-predictions might get categorized under Branch Resteers. Note the value of this node may overlap with its siblings. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_l3_hit_latency, tma_store_latency",
"ScaleUnit": "100%"
},
{
- "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due staying in C0.1 power-performance optimized state (Faster wakeup time; Smaller power savings).",
+ "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due staying in C0.1 power-performance optimized state (Faster wakeup time; Smaller power savings)",
"MetricExpr": "CPU_CLK_UNHALTED.C01 / tma_info_thread_clks",
"MetricGroup": "C0Wait;TopdownL4;tma_L4_group;tma_serializing_operation_group",
"MetricName": "tma_c01_wait",
- "MetricThreshold": "tma_c01_wait > 0.05 & (tma_serializing_operation > 0.1 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))",
+ "MetricThreshold": "tma_c01_wait > 0.05 & tma_serializing_operation > 0.1 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
"ScaleUnit": "100%"
},
{
- "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due staying in C0.2 power-performance optimized state (Slower wakeup time; Larger power savings).",
+ "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due staying in C0.2 power-performance optimized state (Slower wakeup time; Larger power savings)",
"MetricExpr": "CPU_CLK_UNHALTED.C02 / tma_info_thread_clks",
"MetricGroup": "C0Wait;TopdownL4;tma_L4_group;tma_serializing_operation_group",
"MetricName": "tma_c02_wait",
- "MetricThreshold": "tma_c02_wait > 0.05 & (tma_serializing_operation > 0.1 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))",
+ "MetricThreshold": "tma_c02_wait > 0.05 & tma_serializing_operation > 0.1 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
"ScaleUnit": "100%"
},
{
@@ -455,7 +545,7 @@
"MetricExpr": "max(0, tma_microcode_sequencer - tma_assists)",
"MetricGroup": "TopdownL4;tma_L4_group;tma_microcode_sequencer_group",
"MetricName": "tma_cisc",
- "MetricThreshold": "tma_cisc > 0.1 & (tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1)",
+ "MetricThreshold": "tma_cisc > 0.1 & tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1",
"PublicDescription": "This metric estimates fraction of cycles the CPU retired uops originated from CISC (complex instruction set computer) instruction. A CISC instruction has multiple uops that are required to perform the instruction's functionality as in the case of read-modify-write as an example. Since these instructions require multiple uops they may or may not imply sub-optimal use of machine resources. Sample with: FRONTEND_RETIRED.MS_FLOWS",
"ScaleUnit": "100%"
},
@@ -464,45 +554,92 @@
"MetricExpr": "(1 - tma_branch_mispredicts / tma_bad_speculation) * INT_MISC.CLEAR_RESTEER_CYCLES / tma_info_thread_clks",
"MetricGroup": "BadSpec;MachineClears;TopdownL4;tma_L4_group;tma_branch_resteers_group;tma_issueMC",
"MetricName": "tma_clears_resteers",
- "MetricThreshold": "tma_clears_resteers > 0.05 & (tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))",
+ "MetricThreshold": "tma_clears_resteers > 0.05 & tma_branch_resteers > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
"PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Machine Clears. Sample with: INT_MISC.CLEAR_RESTEER_CYCLES. Related metrics: tma_l1_bound, tma_machine_clears, tma_microcode_sequencer, tma_ms_switches",
"ScaleUnit": "100%"
},
+ {
+ "BriefDescription": "This metric estimates fraction of cycles the CPU was stalled due to instruction cache misses that hit in the L2 cache",
+ "MetricExpr": "max(0, tma_icache_misses - tma_code_l2_miss)",
+ "MetricGroup": "FetchLat;IcMiss;Offcore;TopdownL4;tma_L4_group;tma_icache_misses_group",
+ "MetricName": "tma_code_l2_hit",
+ "MetricThreshold": "tma_code_l2_hit > 0.05 & tma_icache_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+ "ScaleUnit": "100%"
+ },
+ {
+ "BriefDescription": "This metric estimates fraction of cycles the CPU was stalled due to instruction cache misses that miss in the L2 cache",
+ "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_CODE_RD / tma_info_thread_clks",
+ "MetricGroup": "FetchLat;IcMiss;Offcore;TopdownL4;tma_L4_group;tma_icache_misses_group",
+ "MetricName": "tma_code_l2_miss",
+ "MetricThreshold": "tma_code_l2_miss > 0.05 & tma_icache_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+ "ScaleUnit": "100%"
+ },
+ {
+ "BriefDescription": "This metric roughly estimates the fraction of cycles where the (first level) ITLB was missed by instructions fetches, that later on hit in second-level TLB (STLB)",
+ "MetricExpr": "max(0, tma_itlb_misses - tma_code_stlb_miss)",
+ "MetricGroup": "FetchLat;MemoryTLB;TopdownL4;tma_L4_group;tma_itlb_misses_group",
+ "MetricName": "tma_code_stlb_hit",
+ "MetricThreshold": "tma_code_stlb_hit > 0.05 & tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+ "ScaleUnit": "100%"
+ },
+ {
+ "BriefDescription": "This metric estimates the fraction of cycles where the Second-level TLB (STLB) was missed by instruction fetches, performing a hardware page walk",
+ "MetricExpr": "ITLB_MISSES.WALK_ACTIVE / tma_info_thread_clks",
+ "MetricGroup": "FetchLat;MemoryTLB;TopdownL4;tma_L4_group;tma_itlb_misses_group",
+ "MetricName": "tma_code_stlb_miss",
+ "MetricThreshold": "tma_code_stlb_miss > 0.05 & tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+ "ScaleUnit": "100%"
+ },
+ {
+ "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 2 or 4 MB pages for (instruction) code accesses",
+ "MetricExpr": "tma_code_stlb_miss * ITLB_MISSES.WALK_COMPLETED_2M_4M / (ITLB_MISSES.WALK_COMPLETED_4K + ITLB_MISSES.WALK_COMPLETED_2M_4M)",
+ "MetricGroup": "FetchLat;MemoryTLB;TopdownL5;tma_L5_group;tma_code_stlb_miss_group",
+ "MetricName": "tma_code_stlb_miss_2m",
+ "MetricThreshold": "tma_code_stlb_miss_2m > 0.05 & tma_code_stlb_miss > 0.05 & tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+ "ScaleUnit": "100%"
+ },
+ {
+ "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 4 KB pages for (instruction) code accesses",
+ "MetricExpr": "tma_code_stlb_miss * ITLB_MISSES.WALK_COMPLETED_4K / (ITLB_MISSES.WALK_COMPLETED_4K + ITLB_MISSES.WALK_COMPLETED_2M_4M)",
+ "MetricGroup": "FetchLat;MemoryTLB;TopdownL5;tma_L5_group;tma_code_stlb_miss_group",
+ "MetricName": "tma_code_stlb_miss_4k",
+ "MetricThreshold": "tma_code_stlb_miss_4k > 0.05 & tma_code_stlb_miss > 0.05 & tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+ "ScaleUnit": "100%"
+ },
{
"BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses",
- "MetricExpr": "(76.6 * tma_info_system_core_frequency * (MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD * (OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM / (OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM + OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD))) + 74.6 * tma_info_system_core_frequency * MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks",
- "MetricGroup": "BvMS;DataSharing;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group",
+ "MetricExpr": "((81 * tma_info_system_core_frequency - 4.4 * tma_info_system_core_frequency) * (MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD * (OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM / (OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM + OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD))) + (79 * tma_info_system_core_frequency - 4.4 * tma_info_system_core_frequency) * MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks",
+ "MetricGroup": "BvMS;DataSharing;LockCont;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group",
"MetricName": "tma_contested_accesses",
- "MetricThreshold": "tma_contested_accesses > 0.05 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
- "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses. Contested accesses occur when data written by one Logical Processor are read by another Logical Processor on a different Physical Core. Examples of contested accesses include synchronizations such as locks; true data sharing such as modified locked variables; and false sharing. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD;MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS. Related metrics: tma_data_sharing, tma_false_sharing, tma_machine_clears, tma_remote_cache",
+ "MetricThreshold": "tma_contested_accesses > 0.05 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+ "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses. Contested accesses occur when data written by one Logical Processor are read by another Logical Processor on a different Physical Core. Examples of contested accesses include synchronizations such as locks; true data sharing such as modified locked variables; and false sharing. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD, MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS. Related metrics: tma_bottleneck_memory_synchronization, tma_data_sharing, tma_false_sharing, tma_machine_clears, tma_remote_cache",
"ScaleUnit": "100%"
},
{
"BriefDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck",
- "DefaultMetricgroupName": "TopdownL2",
"MetricExpr": "max(0, tma_backend_bound - tma_memory_bound)",
- "MetricGroup": "Backend;Compute;Default;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group",
+ "MetricGroup": "Backend;Compute;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group",
"MetricName": "tma_core_bound",
"MetricThreshold": "tma_core_bound > 0.1 & tma_backend_bound > 0.2",
- "MetricgroupNoGroup": "TopdownL2;Default",
- "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck. Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations).",
+ "MetricgroupNoGroup": "TopdownL2",
+ "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck. Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations)",
"ScaleUnit": "100%"
},
{
"BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses",
- "MetricExpr": "74.6 * tma_info_system_core_frequency * (MEM_LOAD_L3_HIT_RETIRED.XSNP_NO_FWD + MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD * (1 - OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM / (OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM + OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD))) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks",
+ "MetricExpr": "(79 * tma_info_system_core_frequency - 4.4 * tma_info_system_core_frequency) * (MEM_LOAD_L3_HIT_RETIRED.XSNP_NO_FWD + MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD * (1 - OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM / (OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM + OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD))) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks",
"MetricGroup": "BvMS;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group",
"MetricName": "tma_data_sharing",
- "MetricThreshold": "tma_data_sharing > 0.05 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
- "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses. Data shared by multiple Logical Processors (even just read shared) may cause increased access latency due to cache coherency. Excessive data sharing can drastically harm multithreaded performance. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_NO_FWD. Related metrics: tma_contested_accesses, tma_false_sharing, tma_machine_clears, tma_remote_cache",
+ "MetricThreshold": "tma_data_sharing > 0.05 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+ "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses. Data shared by multiple Logical Processors (even just read shared) may cause increased access latency due to cache coherency. Excessive data sharing can drastically harm multithreaded performance. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_NO_FWD. Related metrics: tma_bottleneck_memory_synchronization, tma_contested_accesses, tma_false_sharing, tma_machine_clears, tma_remote_cache",
"ScaleUnit": "100%"
},
{
"BriefDescription": "This metric represents fraction of cycles where decoder-0 was the only active decoder",
- "MetricExpr": "(cpu@INST_DECODED.DECODERS\\,cmask\\=1@ - cpu@INST_DECODED.DECODERS\\,cmask\\=2@) / tma_info_core_core_clks / 2",
+ "MetricExpr": "(cpu@INST_DECODED.DECODERS\\,cmask\\=0x1@ - cpu@INST_DECODED.DECODERS\\,cmask\\=0x2@) / tma_info_core_core_clks / 2",
"MetricGroup": "DSBmiss;FetchBW;TopdownL4;tma_L4_group;tma_issueD0;tma_mite_group",
"MetricName": "tma_decoder0_alone",
- "MetricThreshold": "tma_decoder0_alone > 0.1 & (tma_mite > 0.1 & tma_fetch_bandwidth > 0.2)",
+ "MetricThreshold": "tma_decoder0_alone > 0.1 & tma_mite > 0.1 & tma_fetch_bandwidth > 0.2",
"PublicDescription": "This metric represents fraction of cycles where decoder-0 was the only active decoder. Related metrics: tma_few_uops_instructions",
"ScaleUnit": "100%"
},
@@ -511,17 +648,17 @@
"MetricExpr": "ARITH.DIV_ACTIVE / tma_info_thread_clks",
"MetricGroup": "BvCB;TopdownL3;tma_L3_group;tma_core_bound_group",
"MetricName": "tma_divider",
- "MetricThreshold": "tma_divider > 0.2 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)",
+ "MetricThreshold": "tma_divider > 0.2 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
"PublicDescription": "This metric represents fraction of cycles where the Divider unit was active. Divide and square root instructions are performed by the Divider unit and can take considerably longer latency than integer or Floating Point addition; subtraction; or multiplication. Sample with: ARITH.DIVIDER_ACTIVE",
"ScaleUnit": "100%"
},
{
"BriefDescription": "This metric estimates how often the CPU was stalled on accesses to external memory (DRAM) by loads",
- "MetricExpr": "(MEMORY_ACTIVITY.STALLS_L3_MISS / tma_info_thread_clks - tma_pmm_bound if #has_pmem > 0 else MEMORY_ACTIVITY.STALLS_L3_MISS / tma_info_thread_clks)",
+ "MetricExpr": "MEMORY_ACTIVITY.STALLS_L3_MISS / tma_info_thread_clks",
"MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group",
"MetricName": "tma_dram_bound",
- "MetricThreshold": "tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)",
- "PublicDescription": "This metric estimates how often the CPU was stalled on accesses to external memory (DRAM) by loads. Better caching can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L3_MISS_PS",
+ "MetricThreshold": "tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+ "PublicDescription": "This metric estimates how often the CPU was stalled on accesses to external memory (DRAM) by loads. Better caching can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L3_MISS",
"ScaleUnit": "100%"
},
{
@@ -530,7 +667,7 @@
"MetricGroup": "DSB;FetchBW;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group",
"MetricName": "tma_dsb",
"MetricThreshold": "tma_dsb > 0.15 & tma_fetch_bandwidth > 0.2",
- "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to DSB (decoded uop cache) fetch pipeline. For example; inefficient utilization of the DSB cache structure or bank conflict when reading from it; are categorized here.",
+ "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to DSB (decoded uop cache) fetch pipeline. For example; inefficient utilization of the DSB cache structure or bank conflict when reading from it; are categorized here",
"ScaleUnit": "100%"
},
{
@@ -538,75 +675,73 @@
"MetricExpr": "DSB2MITE_SWITCHES.PENALTY_CYCLES / tma_info_thread_clks",
"MetricGroup": "DSBmiss;FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueFB",
"MetricName": "tma_dsb_switches",
- "MetricThreshold": "tma_dsb_switches > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)",
- "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines. The DSB (decoded i-cache) is a Uop Cache where the front-end directly delivers Uops (micro operations) avoiding heavy x86 decoding. The DSB pipeline has shorter latency and delivered higher bandwidth than the MITE (legacy instruction decode pipeline). Switching between the two pipelines can cause penalties hence this metric measures the exposed penalty. Sample with: FRONTEND_RETIRED.DSB_MISS_PS. Related metrics: tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp",
+ "MetricThreshold": "tma_dsb_switches > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+ "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines. The DSB (decoded i-cache) is a Uop Cache where the front-end directly delivers Uops (micro operations) avoiding heavy x86 decoding. The DSB pipeline has shorter latency and delivered higher bandwidth than the MITE (legacy instruction decode pipeline). Switching between the two pipelines can cause penalties hence this metric measures the exposed penalty. Sample with: FRONTEND_RETIRED.DSB_MISS. Related metrics: tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp",
"ScaleUnit": "100%"
},
{
"BriefDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses",
- "MetricExpr": "min(7 * cpu@DTLB_LOAD_MISSES.STLB_HIT\\,cmask\\=1@ + DTLB_LOAD_MISSES.WALK_ACTIVE, max(CYCLE_ACTIVITY.CYCLES_MEM_ANY - MEMORY_ACTIVITY.CYCLES_L1D_MISS, 0)) / tma_info_thread_clks",
+ "MetricExpr": "min(7 * cpu@DTLB_LOAD_MISSES.STLB_HIT\\,cmask\\=0x1@ + DTLB_LOAD_MISSES.WALK_ACTIVE, max(CYCLE_ACTIVITY.CYCLES_MEM_ANY - MEMORY_ACTIVITY.CYCLES_L1D_MISS, 0)) / tma_info_thread_clks",
"MetricGroup": "BvMT;MemoryTLB;TopdownL4;tma_L4_group;tma_issueTLB;tma_l1_bound_group",
"MetricName": "tma_dtlb_load",
- "MetricThreshold": "tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
- "PublicDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses. TLBs (Translation Look-aside Buffers) are processor caches for recently used entries out of the Page Tables that are used to map virtual- to physical-addresses by the operating system. This metric approximates the potential delay of demand loads missing the first-level data TLB (assuming worst case scenario with back to back misses to different pages). This includes hitting in the second-level TLB (STLB) as well as performing a hardware page walk on an STLB miss. Sample with: MEM_INST_RETIRED.STLB_MISS_LOADS_PS. Related metrics: tma_dtlb_store, tma_info_bottleneck_memory_data_tlbs, tma_info_bottleneck_memory_synchronization",
+ "MetricThreshold": "tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+ "PublicDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses. TLBs (Translation Look-aside Buffers) are processor caches for recently used entries out of the Page Tables that are used to map virtual- to physical-addresses by the operating system. This metric approximates the potential delay of demand loads missing the first-level data TLB (assuming worst case scenario with back to back misses to different pages). This includes hitting in the second-level TLB (STLB) as well as performing a hardware page walk on an STLB miss. Sample with: MEM_INST_RETIRED.STLB_MISS_LOADS. Related metrics: tma_bottleneck_memory_data_tlbs, tma_dtlb_store",
"ScaleUnit": "100%"
},
{
"BriefDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses",
- "MetricExpr": "(7 * cpu@DTLB_STORE_MISSES.STLB_HIT\\,cmask\\=1@ + DTLB_STORE_MISSES.WALK_ACTIVE) / tma_info_core_core_clks",
+ "MetricExpr": "(7 * cpu@DTLB_STORE_MISSES.STLB_HIT\\,cmask\\=0x1@ + DTLB_STORE_MISSES.WALK_ACTIVE) / tma_info_core_core_clks",
"MetricGroup": "BvMT;MemoryTLB;TopdownL4;tma_L4_group;tma_issueTLB;tma_store_bound_group",
"MetricName": "tma_dtlb_store",
- "MetricThreshold": "tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
- "PublicDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses. As with ordinary data caching; focus on improving data locality and reducing working-set size to reduce DTLB overhead. Additionally; consider using profile-guided optimization (PGO) to collocate frequently-used data on the same page. Try using larger page sizes for large amounts of frequently-used data. Sample with: MEM_INST_RETIRED.STLB_MISS_STORES_PS. Related metrics: tma_dtlb_load, tma_info_bottleneck_memory_data_tlbs, tma_info_bottleneck_memory_synchronization",
+ "MetricThreshold": "tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+ "PublicDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses. As with ordinary data caching; focus on improving data locality and reducing working-set size to reduce DTLB overhead. Additionally; consider using profile-guided optimization (PGO) to collocate frequently-used data on the same page. Try using larger page sizes for large amounts of frequently-used data. Sample with: MEM_INST_RETIRED.STLB_MISS_STORES. Related metrics: tma_bottleneck_memory_data_tlbs, tma_dtlb_load",
"ScaleUnit": "100%"
},
{
"BriefDescription": "This metric roughly estimates how often CPU was handling synchronizations due to False Sharing",
- "MetricExpr": "81 * tma_info_system_core_frequency * OCR.DEMAND_RFO.L3_HIT.SNOOP_HITM / tma_info_thread_clks",
- "MetricGroup": "BvMS;DataSharing;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_store_bound_group",
+ "MetricExpr": "(170 * tma_info_system_core_frequency * cpu@OCR.DEMAND_RFO.L3_MISS\\,offcore_rsp\\=0x103b800002@ + 81 * tma_info_system_core_frequency * OCR.DEMAND_RFO.L3_HIT.SNOOP_HITM) / tma_info_thread_clks",
+ "MetricGroup": "BvMS;DataSharing;LockCont;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_store_bound_group",
"MetricName": "tma_false_sharing",
- "MetricThreshold": "tma_false_sharing > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
- "PublicDescription": "This metric roughly estimates how often CPU was handling synchronizations due to False Sharing. False Sharing is a multithreading hiccup; where multiple Logical Processors contend on different data-elements mapped into the same cache line. Sample with: OCR.DEMAND_RFO.L3_HIT.SNOOP_HITM. Related metrics: tma_contested_accesses, tma_data_sharing, tma_machine_clears, tma_remote_cache",
+ "MetricThreshold": "tma_false_sharing > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+ "PublicDescription": "This metric roughly estimates how often CPU was handling synchronizations due to False Sharing. False Sharing is a multithreading hiccup; where multiple Logical Processors contend on different data-elements mapped into the same cache line. Sample with: OCR.DEMAND_RFO.L3_HIT.SNOOP_HITM. Related metrics: tma_bottleneck_memory_synchronization, tma_contested_accesses, tma_data_sharing, tma_machine_clears, tma_remote_cache",
"ScaleUnit": "100%"
},
{
"BriefDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed",
"MetricExpr": "L1D_PEND_MISS.FB_FULL / tma_info_thread_clks",
- "MetricGroup": "BvMS;MemoryBW;TopdownL4;tma_L4_group;tma_issueBW;tma_issueSL;tma_issueSmSt;tma_l1_bound_group",
+ "MetricGroup": "BvMB;MemoryBW;TopdownL4;tma_L4_group;tma_issueBW;tma_issueSL;tma_issueSmSt;tma_l1_bound_group",
"MetricName": "tma_fb_full",
"MetricThreshold": "tma_fb_full > 0.3",
- "PublicDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed. The higher the metric value; the deeper the memory hierarchy level the misses are satisfied from (metric values >1 are valid). Often it hints on approaching bandwidth limits (to L2 cache; L3 cache or external memory). Related metrics: tma_info_bottleneck_cache_memory_bandwidth, tma_info_system_dram_bw_use, tma_mem_bandwidth, tma_sq_full, tma_store_latency, tma_streaming_stores",
+ "PublicDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed. The higher the metric value; the deeper the memory hierarchy level the misses are satisfied from (metric values >1 are valid). Often it hints on approaching bandwidth limits (to L2 cache; L3 cache or external memory). Related metrics: tma_bottleneck_cache_memory_bandwidth, tma_info_system_dram_bw_use, tma_mem_bandwidth, tma_sq_full, tma_store_latency, tma_streaming_stores",
"ScaleUnit": "100%"
},
{
"BriefDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues",
- "DefaultMetricgroupName": "TopdownL2",
"MetricExpr": "max(0, tma_frontend_bound - tma_fetch_latency)",
- "MetricGroup": "Default;FetchBW;Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group;tma_issueFB",
+ "MetricGroup": "FetchBW;Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group;tma_issueFB",
"MetricName": "tma_fetch_bandwidth",
"MetricThreshold": "tma_fetch_bandwidth > 0.2",
- "MetricgroupNoGroup": "TopdownL2;Default",
- "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues. For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Sample with: FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1_PS;FRONTEND_RETIRED.LATENCY_GE_1_PS;FRONTEND_RETIRED.LATENCY_GE_2_PS. Related metrics: tma_dsb_switches, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp",
+ "MetricgroupNoGroup": "TopdownL2",
+ "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues. For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Sample with: FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1, FRONTEND_RETIRED.LATENCY_GE_1, FRONTEND_RETIRED.LATENCY_GE_2. Related metrics: tma_dsb_switches, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp",
"ScaleUnit": "100%"
},
{
"BriefDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues",
- "DefaultMetricgroupName": "TopdownL2",
"MetricExpr": "topdown\\-fetch\\-lat / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) - INT_MISC.UOP_DROPPING / tma_info_thread_slots",
- "MetricGroup": "Default;Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group",
+ "MetricGroup": "Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group",
"MetricName": "tma_fetch_latency",
"MetricThreshold": "tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
- "MetricgroupNoGroup": "TopdownL2;Default",
- "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues. For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: FRONTEND_RETIRED.LATENCY_GE_16_PS;FRONTEND_RETIRED.LATENCY_GE_8_PS",
+ "MetricgroupNoGroup": "TopdownL2",
+ "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues. For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: FRONTEND_RETIRED.LATENCY_GE_16, FRONTEND_RETIRED.LATENCY_GE_8",
"ScaleUnit": "100%"
},
{
- "BriefDescription": "This metric represents fraction of slots where the CPU was retiring instructions that that are decoder into two or up to ([SNB+] four; [ADL+] five) uops",
+ "BriefDescription": "This metric represents fraction of slots where the CPU was retiring instructions that that are decoder into two or more uops",
"MetricExpr": "max(0, tma_heavy_operations - tma_microcode_sequencer)",
"MetricGroup": "TopdownL3;tma_L3_group;tma_heavy_operations_group;tma_issueD0",
"MetricName": "tma_few_uops_instructions",
"MetricThreshold": "tma_few_uops_instructions > 0.05 & tma_heavy_operations > 0.1",
- "PublicDescription": "This metric represents fraction of slots where the CPU was retiring instructions that that are decoder into two or up to ([SNB+] four; [ADL+] five) uops. This highly-correlates with the number of uops in such instructions. Related metrics: tma_decoder0_alone",
+ "PublicDescription": "This metric represents fraction of slots where the CPU was retiring instructions that that are decoder into two or more uops. This highly-correlates with the number of uops in such instructions. Related metrics: tma_decoder0_alone",
"ScaleUnit": "100%"
},
{
@@ -615,7 +750,7 @@
"MetricGroup": "HPC;TopdownL3;tma_L3_group;tma_light_operations_group",
"MetricName": "tma_fp_arith",
"MetricThreshold": "tma_fp_arith > 0.2 & tma_light_operations > 0.6",
- "PublicDescription": "This metric represents overall arithmetic floating-point (FP) operations fraction the CPU has executed (retired). Note this metric's value may exceed its parent due to use of \"Uops\" CountDomain and FMA double-counting.",
+ "PublicDescription": "This metric represents overall arithmetic floating-point (FP) operations fraction the CPU has executed (retired). Note this metric's value may exceed its parent due to use of \"Uops\" CountDomain and FMA double-counting",
"ScaleUnit": "100%"
},
{
@@ -624,7 +759,15 @@
"MetricGroup": "HPC;TopdownL5;tma_L5_group;tma_assists_group",
"MetricName": "tma_fp_assists",
"MetricThreshold": "tma_fp_assists > 0.1",
- "PublicDescription": "This metric roughly estimates fraction of slots the CPU retired uops as a result of handing Floating Point (FP) Assists. FP Assist may apply when working with very small floating point values (so-called Denormals).",
+ "PublicDescription": "This metric roughly estimates fraction of slots the CPU retired uops as a result of handing Floating Point (FP) Assists. FP Assist may apply when working with very small floating point values (so-called Denormals)",
+ "ScaleUnit": "100%"
+ },
+ {
+ "BriefDescription": "This metric represents fraction of cycles where the Floating-Point Divider unit was active",
+ "MetricExpr": "ARITH.FPDIV_ACTIVE / tma_info_thread_clks",
+ "MetricGroup": "TopdownL4;tma_L4_group;tma_divider_group",
+ "MetricName": "tma_fp_divider",
+ "MetricThreshold": "tma_fp_divider > 0.2 & tma_divider > 0.2 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
"ScaleUnit": "100%"
},
{
@@ -632,8 +775,8 @@
"MetricExpr": "(FP_ARITH_INST_RETIRED.SCALAR + FP_ARITH_INST_RETIRED2.SCALAR) / (tma_retiring * tma_info_thread_slots)",
"MetricGroup": "Compute;Flops;TopdownL4;tma_L4_group;tma_fp_arith_group;tma_issue2P",
"MetricName": "tma_fp_scalar",
- "MetricThreshold": "tma_fp_scalar > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6)",
- "PublicDescription": "This metric approximates arithmetic floating-point (FP) scalar uops fraction the CPU has retired. May overcount due to FMA double counting. Related metrics: tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2",
+ "MetricThreshold": "tma_fp_scalar > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6",
+ "PublicDescription": "This metric approximates arithmetic floating-point (FP) scalar uops fraction the CPU has retired. May overcount due to FMA double counting. Related metrics: tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_6, tma_ports_utilized_2",
"ScaleUnit": "100%"
},
{
@@ -641,8 +784,8 @@
"MetricExpr": "(FP_ARITH_INST_RETIRED.VECTOR + FP_ARITH_INST_RETIRED2.VECTOR) / (tma_retiring * tma_info_thread_slots)",
"MetricGroup": "Compute;Flops;TopdownL4;tma_L4_group;tma_fp_arith_group;tma_issue2P",
"MetricName": "tma_fp_vector",
- "MetricThreshold": "tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6)",
- "PublicDescription": "This metric approximates arithmetic floating-point (FP) vector uops fraction the CPU has retired aggregated across all vector widths. May overcount due to FMA double counting. Related metrics: tma_fp_scalar, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2",
+ "MetricThreshold": "tma_fp_vector > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6",
+ "PublicDescription": "This metric approximates arithmetic floating-point (FP) vector uops fraction the CPU has retired aggregated across all vector widths. May overcount due to FMA double counting. Related metrics: tma_fp_scalar, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_6, tma_ports_utilized_2",
"ScaleUnit": "100%"
},
{
@@ -650,8 +793,8 @@
"MetricExpr": "(FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED2.128B_PACKED_HALF) / (tma_retiring * tma_info_thread_slots)",
"MetricGroup": "Compute;Flops;TopdownL5;tma_L5_group;tma_fp_vector_group;tma_issue2P",
"MetricName": "tma_fp_vector_128b",
- "MetricThreshold": "tma_fp_vector_128b > 0.1 & (tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6))",
- "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 128-bit wide vectors. May overcount due to FMA double counting. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2",
+ "MetricThreshold": "tma_fp_vector_128b > 0.1 & tma_fp_vector > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6",
+ "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 128-bit wide vectors. May overcount due to FMA double counting prior to LNL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_6, tma_ports_utilized_2",
"ScaleUnit": "100%"
},
{
@@ -659,8 +802,8 @@
"MetricExpr": "(FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE + FP_ARITH_INST_RETIRED2.256B_PACKED_HALF) / (tma_retiring * tma_info_thread_slots)",
"MetricGroup": "Compute;Flops;TopdownL5;tma_L5_group;tma_fp_vector_group;tma_issue2P",
"MetricName": "tma_fp_vector_256b",
- "MetricThreshold": "tma_fp_vector_256b > 0.1 & (tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6))",
- "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 256-bit wide vectors. May overcount due to FMA double counting. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2",
+ "MetricThreshold": "tma_fp_vector_256b > 0.1 & tma_fp_vector > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6",
+ "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 256-bit wide vectors. May overcount due to FMA double counting prior to LNL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_6, tma_ports_utilized_2",
"ScaleUnit": "100%"
},
{
@@ -668,39 +811,37 @@
"MetricExpr": "(FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE + FP_ARITH_INST_RETIRED2.512B_PACKED_HALF) / (tma_retiring * tma_info_thread_slots)",
"MetricGroup": "Compute;Flops;TopdownL5;tma_L5_group;tma_fp_vector_group;tma_issue2P",
"MetricName": "tma_fp_vector_512b",
- "MetricThreshold": "tma_fp_vector_512b > 0.1 & (tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6))",
- "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 512-bit wide vectors. May overcount due to FMA double counting. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2",
+ "MetricThreshold": "tma_fp_vector_512b > 0.1 & tma_fp_vector > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6",
+ "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 512-bit wide vectors. May overcount due to FMA double counting. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_6, tma_ports_utilized_2",
"ScaleUnit": "100%"
},
{
"BriefDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend",
- "DefaultMetricgroupName": "TopdownL1",
"MetricExpr": "topdown\\-fe\\-bound / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) - INT_MISC.UOP_DROPPING / tma_info_thread_slots",
- "MetricGroup": "BvFB;BvIO;Default;PGO;TmaL1;TopdownL1;tma_L1_group",
+ "MetricGroup": "BvFB;BvIO;PGO;TmaL1;TopdownL1;tma_L1_group",
"MetricName": "tma_frontend_bound",
"MetricThreshold": "tma_frontend_bound > 0.15",
- "MetricgroupNoGroup": "TopdownL1;Default",
- "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound. Sample with: FRONTEND_RETIRED.LATENCY_GE_4_PS",
+ "MetricgroupNoGroup": "TopdownL1",
+ "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound. Sample with: FRONTEND_RETIRED.LATENCY_GE_4",
"ScaleUnit": "100%"
},
{
- "BriefDescription": "This metric represents fraction of slots where the CPU was retiring fused instructions -- where one uop can represent multiple contiguous instructions",
+ "BriefDescription": "This metric represents fraction of slots where the CPU was retiring fused instructions , where one uop can represent multiple contiguous instructions",
"MetricExpr": "tma_light_operations * INST_RETIRED.MACRO_FUSED / (tma_retiring * tma_info_thread_slots)",
"MetricGroup": "Branches;BvBO;Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group",
"MetricName": "tma_fused_instructions",
"MetricThreshold": "tma_fused_instructions > 0.1 & tma_light_operations > 0.6",
- "PublicDescription": "This metric represents fraction of slots where the CPU was retiring fused instructions -- where one uop can represent multiple contiguous instructions. CMP+JCC or DEC+JCC are common examples of legacy fusions. {([MTL] Note new MOV+OP and Load+OP fusions appear under Other_Light_Ops in MTL!)}",
+ "PublicDescription": "This metric represents fraction of slots where the CPU was retiring fused instructions , where one uop can represent multiple contiguous instructions. CMP+JCC or DEC+JCC are common examples of legacy fusions. {([MTL] Note new MOV+OP and Load+OP fusions appear under Other_Light_Ops in MTL!)}",
"ScaleUnit": "100%"
},
{
- "BriefDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences",
- "DefaultMetricgroupName": "TopdownL2",
- "MetricExpr": "topdown\\-heavy\\-ops / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * tma_info_thread_slots",
- "MetricGroup": "Default;Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group",
+ "BriefDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations , instructions that require two or more uops or micro-coded sequences",
+ "MetricExpr": "topdown\\-heavy\\-ops / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * slots",
+ "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group",
"MetricName": "tma_heavy_operations",
"MetricThreshold": "tma_heavy_operations > 0.1",
- "MetricgroupNoGroup": "TopdownL2;Default",
- "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences. ([ICL+] Note this may overcount due to approximation using indirect events; [ADL+] .). Sample with: UOPS_RETIRED.HEAVY",
+ "MetricgroupNoGroup": "TopdownL2",
+ "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations , instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences.([ICL+] Note this may overcount due to approximation using indirect events; [ADL+]). Sample with: UOPS_RETIRED.HEAVY",
"ScaleUnit": "100%"
},
{
@@ -708,40 +849,40 @@
"MetricExpr": "ICACHE_DATA.STALLS / tma_info_thread_clks",
"MetricGroup": "BigFootprint;BvBC;FetchLat;IcMiss;TopdownL3;tma_L3_group;tma_fetch_latency_group",
"MetricName": "tma_icache_misses",
- "MetricThreshold": "tma_icache_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)",
- "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to instruction cache misses. Sample with: FRONTEND_RETIRED.L2_MISS_PS;FRONTEND_RETIRED.L1I_MISS_PS",
+ "MetricThreshold": "tma_icache_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+ "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to instruction cache misses. Sample with: FRONTEND_RETIRED.L2_MISS, FRONTEND_RETIRED.L1I_MISS",
"ScaleUnit": "100%"
},
{
- "BriefDescription": "Branch Misprediction Cost: Fraction of TMA slots wasted per non-speculative branch misprediction (retired JEClear)",
- "MetricExpr": "tma_info_bottleneck_mispredictions * tma_info_thread_slots / BR_MISP_RETIRED.ALL_BRANCHES / 100",
+ "BriefDescription": "Branch Misprediction Cost: Cycles representing fraction of TMA slots wasted per non-speculative branch misprediction (retired JEClear)",
+ "MetricExpr": "tma_bottleneck_mispredictions * tma_info_thread_slots / 6 / BR_MISP_RETIRED.ALL_BRANCHES / 100",
"MetricGroup": "Bad;BrMispredicts;tma_issueBM",
"MetricName": "tma_info_bad_spec_branch_misprediction_cost",
- "PublicDescription": "Branch Misprediction Cost: Fraction of TMA slots wasted per non-speculative branch misprediction (retired JEClear). Related metrics: tma_branch_mispredicts, tma_info_bottleneck_mispredictions, tma_mispredicts_resteers"
+ "PublicDescription": "Branch Misprediction Cost: Cycles representing fraction of TMA slots wasted per non-speculative branch misprediction (retired JEClear). Related metrics: tma_bottleneck_mispredictions, tma_branch_mispredicts, tma_mispredicts_resteers"
},
{
- "BriefDescription": "Instructions per retired mispredicts for conditional non-taken branches (lower number means higher occurrence rate).",
+ "BriefDescription": "Instructions per retired Mispredicts for conditional non-taken branches (lower number means higher occurrence rate)",
"MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.COND_NTAKEN",
"MetricGroup": "Bad;BrMispredicts",
"MetricName": "tma_info_bad_spec_ipmisp_cond_ntaken",
"MetricThreshold": "tma_info_bad_spec_ipmisp_cond_ntaken < 200"
},
{
- "BriefDescription": "Instructions per retired mispredicts for conditional taken branches (lower number means higher occurrence rate).",
+ "BriefDescription": "Instructions per retired Mispredicts for conditional taken branches (lower number means higher occurrence rate)",
"MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.COND_TAKEN",
"MetricGroup": "Bad;BrMispredicts",
"MetricName": "tma_info_bad_spec_ipmisp_cond_taken",
"MetricThreshold": "tma_info_bad_spec_ipmisp_cond_taken < 200"
},
{
- "BriefDescription": "Instructions per retired mispredicts for indirect CALL or JMP branches (lower number means higher occurrence rate).",
+ "BriefDescription": "Instructions per retired Mispredicts for indirect CALL or JMP branches (lower number means higher occurrence rate)",
"MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.INDIRECT",
"MetricGroup": "Bad;BrMispredicts",
"MetricName": "tma_info_bad_spec_ipmisp_indirect",
- "MetricThreshold": "tma_info_bad_spec_ipmisp_indirect < 1e3"
+ "MetricThreshold": "tma_info_bad_spec_ipmisp_indirect < 1000"
},
{
- "BriefDescription": "Instructions per retired mispredicts for return branches (lower number means higher occurrence rate).",
+ "BriefDescription": "Instructions per retired Mispredicts for return branches (lower number means higher occurrence rate)",
"MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.RET",
"MetricGroup": "Bad;BrMispredicts",
"MetricName": "tma_info_bad_spec_ipmisp_ret",
@@ -755,7 +896,7 @@
"MetricThreshold": "tma_info_bad_spec_ipmispredict < 200"
},
{
- "BriefDescription": "Speculative to Retired ratio of all clears (covering mispredicts and nukes)",
+ "BriefDescription": "Speculative to Retired ratio of all clears (covering Mispredicts and nukes)",
"MetricExpr": "INT_MISC.CLEARS_COUNT / (BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT)",
"MetricGroup": "BrMispredicts",
"MetricName": "tma_info_bad_spec_spec_clears_ratio"
@@ -769,15 +910,15 @@
},
{
"BriefDescription": "Total pipeline cost of DSB (uop cache) hits - subset of the Instruction_Fetch_BW Bottleneck",
- "MetricExpr": "100 * (tma_frontend_bound * (tma_fetch_bandwidth / (tma_fetch_bandwidth + tma_fetch_latency)) * (tma_dsb / (tma_dsb + tma_mite)))",
- "MetricGroup": "DSB;FetchBW;tma_issueFB",
+ "MetricExpr": "100 * (tma_frontend_bound * (tma_fetch_bandwidth / (tma_fetch_latency + tma_fetch_bandwidth)) * (tma_dsb / (tma_mite + tma_dsb + tma_ms)))",
+ "MetricGroup": "DSB;Fed;FetchBW;tma_issueFB",
"MetricName": "tma_info_botlnk_l2_dsb_bandwidth",
"MetricThreshold": "tma_info_botlnk_l2_dsb_bandwidth > 10",
"PublicDescription": "Total pipeline cost of DSB (uop cache) hits - subset of the Instruction_Fetch_BW Bottleneck. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp"
},
{
"BriefDescription": "Total pipeline cost of DSB (uop cache) misses - subset of the Instruction_Fetch_BW Bottleneck",
- "MetricExpr": "100 * (tma_fetch_latency * tma_dsb_switches / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) + tma_fetch_bandwidth * tma_mite / (tma_dsb + tma_mite))",
+ "MetricExpr": "100 * (tma_fetch_latency * tma_dsb_switches / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches) + tma_fetch_bandwidth * tma_mite / (tma_mite + tma_dsb + tma_ms))",
"MetricGroup": "DSBmiss;Fed;tma_issueFB",
"MetricName": "tma_info_botlnk_l2_dsb_misses",
"MetricThreshold": "tma_info_botlnk_l2_dsb_misses > 10",
@@ -785,104 +926,10 @@
},
{
"BriefDescription": "Total pipeline cost of Instruction Cache misses - subset of the Big_Code Bottleneck",
- "MetricExpr": "100 * (tma_fetch_latency * tma_icache_misses / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches))",
+ "MetricExpr": "100 * (tma_fetch_latency * tma_icache_misses / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches))",
"MetricGroup": "Fed;FetchLat;IcMiss;tma_issueFL",
"MetricName": "tma_info_botlnk_l2_ic_misses",
- "MetricThreshold": "tma_info_botlnk_l2_ic_misses > 5",
- "PublicDescription": "Total pipeline cost of Instruction Cache misses - subset of the Big_Code Bottleneck. Related metrics: "
- },
- {
- "BriefDescription": "Total pipeline cost of instruction fetch related bottlenecks by large code footprint programs (i-side cache; TLB and BTB misses)",
- "MetricExpr": "100 * tma_fetch_latency * (tma_itlb_misses + tma_icache_misses + tma_unknown_branches) / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches)",
- "MetricGroup": "BigFootprint;BvBC;Fed;Frontend;IcMiss;MemoryTLB",
- "MetricName": "tma_info_bottleneck_big_code",
- "MetricThreshold": "tma_info_bottleneck_big_code > 20"
- },
- {
- "BriefDescription": "Total pipeline cost of instructions used for program control-flow - a subset of the Retiring category in TMA",
- "MetricExpr": "100 * ((BR_INST_RETIRED.ALL_BRANCHES + 2 * BR_INST_RETIRED.NEAR_CALL + INST_RETIRED.NOP) / tma_info_thread_slots)",
- "MetricGroup": "BvBO;Ret",
- "MetricName": "tma_info_bottleneck_branching_overhead",
- "MetricThreshold": "tma_info_bottleneck_branching_overhead > 5",
- "PublicDescription": "Total pipeline cost of instructions used for program control-flow - a subset of the Retiring category in TMA. Examples include function calls; loops and alignments. (A lower bound)"
- },
- {
- "BriefDescription": "Total pipeline cost of external Memory- or Cache-Bandwidth related bottlenecks",
- "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_pmm_bound + tma_store_bound)) * (tma_mem_bandwidth / (tma_mem_bandwidth + tma_mem_latency)) + tma_memory_bound * (tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_pmm_bound + tma_store_bound)) * (tma_sq_full / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_pmm_bound + tma_store_bound)) * (tma_fb_full / (tma_dtlb_load + tma_fb_full + tma_l1_hit_latency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)))",
- "MetricGroup": "BvMB;Mem;MemoryBW;Offcore;tma_issueBW",
- "MetricName": "tma_info_bottleneck_cache_memory_bandwidth",
- "MetricThreshold": "tma_info_bottleneck_cache_memory_bandwidth > 20",
- "PublicDescription": "Total pipeline cost of external Memory- or Cache-Bandwidth related bottlenecks. Related metrics: tma_fb_full, tma_info_system_dram_bw_use, tma_mem_bandwidth, tma_sq_full"
- },
- {
- "BriefDescription": "Total pipeline cost of external Memory- or Cache-Latency related bottlenecks",
- "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_pmm_bound + tma_store_bound)) * (tma_mem_latency / (tma_mem_bandwidth + tma_mem_latency)) + tma_memory_bound * (tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_pmm_bound + tma_store_bound)) * (tma_l3_hit_latency / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_memory_bound * tma_l2_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_pmm_bound + tma_store_bound) + tma_memory_bound * (tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_pmm_bound + tma_store_bound)) * (tma_store_latency / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency + tma_streaming_stores)) + tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_pmm_bound + tma_store_bound)) * (tma_l1_hit_latency / (tma_dtlb_load + tma_fb_full + tma_l1_hit_latency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)))",
- "MetricGroup": "BvML;Mem;MemoryLat;Offcore;tma_issueLat",
- "MetricName": "tma_info_bottleneck_cache_memory_latency",
- "MetricThreshold": "tma_info_bottleneck_cache_memory_latency > 20",
- "PublicDescription": "Total pipeline cost of external Memory- or Cache-Latency related bottlenecks. Related metrics: tma_l3_hit_latency, tma_mem_latency"
- },
- {
- "BriefDescription": "Total pipeline cost when the execution is compute-bound - an estimation",
- "MetricExpr": "100 * (tma_core_bound * tma_divider / (tma_amx_busy + tma_divider + tma_ports_utilization + tma_serializing_operation) + tma_core_bound * tma_amx_busy / (tma_amx_busy + tma_divider + tma_ports_utilization + tma_serializing_operation) + tma_core_bound * (tma_ports_utilization / (tma_amx_busy + tma_divider + tma_ports_utilization + tma_serializing_operation)) * (tma_ports_utilized_3m / (tma_ports_utilized_0 + tma_ports_utilized_1 + tma_ports_utilized_2 + tma_ports_utilized_3m)))",
- "MetricGroup": "BvCB;Cor;tma_issueComp",
- "MetricName": "tma_info_bottleneck_compute_bound_est",
- "MetricThreshold": "tma_info_bottleneck_compute_bound_est > 20",
- "PublicDescription": "Total pipeline cost when the execution is compute-bound - an estimation. Covers Core Bound when High ILP as well as when long-latency execution units are busy. Related metrics: "
- },
- {
- "BriefDescription": "Total pipeline cost of instruction fetch bandwidth related bottlenecks (when the front-end could not sustain operations delivery to the back-end)",
- "MetricExpr": "100 * (tma_frontend_bound - (1 - 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts) * tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) - (1 - INST_RETIRED.REP_ITERATION / cpu@UOPS_RETIRED.MS\\,cmask\\=1@) * (tma_fetch_latency * (tma_ms_switches + tma_branch_resteers * (tma_clears_resteers + tma_mispredicts_resteers * tma_other_mispredicts / tma_branch_mispredicts) / (tma_clears_resteers + tma_mispredicts_resteers + tma_unknown_branches)) / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches))) - tma_info_bottleneck_big_code",
- "MetricGroup": "BvFB;Fed;FetchBW;Frontend",
- "MetricName": "tma_info_bottleneck_instruction_fetch_bw",
- "MetricThreshold": "tma_info_bottleneck_instruction_fetch_bw > 20"
- },
- {
- "BriefDescription": "Total pipeline cost of irregular execution (e.g",
- "MetricExpr": "100 * ((1 - INST_RETIRED.REP_ITERATION / cpu@UOPS_RETIRED.MS\\,cmask\\=1@) * (tma_fetch_latency * (tma_ms_switches + tma_branch_resteers * (tma_clears_resteers + tma_mispredicts_resteers * tma_other_mispredicts / tma_branch_mispredicts) / (tma_clears_resteers + tma_mispredicts_resteers + tma_unknown_branches)) / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches)) + 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts * tma_branch_mispredicts + tma_machine_clears * tma_other_nukes / tma_other_nukes + tma_core_bound * (tma_serializing_operation + cpu@RS.EMPTY\\,umask\\=1@ / tma_info_thread_clks * tma_ports_utilized_0) / (tma_amx_busy + tma_divider + tma_ports_utilization + tma_serializing_operation) + tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * tma_heavy_operations)",
- "MetricGroup": "Bad;BvIO;Cor;Ret;tma_issueMS",
- "MetricName": "tma_info_bottleneck_irregular_overhead",
- "MetricThreshold": "tma_info_bottleneck_irregular_overhead > 10",
- "PublicDescription": "Total pipeline cost of irregular execution (e.g. FP-assists in HPC, Wait time with work imbalance multithreaded workloads, overhead in system services or virtualized environments). Related metrics: tma_microcode_sequencer, tma_ms_switches"
- },
- {
- "BriefDescription": "Total pipeline cost of Memory Address Translation related bottlenecks (data-side TLBs)",
- "MetricExpr": "100 * (tma_memory_bound * (tma_l1_bound / max(tma_memory_bound, tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_pmm_bound + tma_store_bound)) * (tma_dtlb_load / max(tma_l1_bound, tma_dtlb_load + tma_fb_full + tma_l1_hit_latency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_memory_bound * (tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_pmm_bound + tma_store_bound)) * (tma_dtlb_store / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency + tma_streaming_stores)))",
- "MetricGroup": "BvMT;Mem;MemoryTLB;Offcore;tma_issueTLB",
- "MetricName": "tma_info_bottleneck_memory_data_tlbs",
- "MetricThreshold": "tma_info_bottleneck_memory_data_tlbs > 20",
- "PublicDescription": "Total pipeline cost of Memory Address Translation related bottlenecks (data-side TLBs). Related metrics: tma_dtlb_load, tma_dtlb_store, tma_info_bottleneck_memory_synchronization"
- },
- {
- "BriefDescription": "Total pipeline cost of Memory Synchronization related bottlenecks (data transfers and coherency updates across processors)",
- "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_pmm_bound + tma_store_bound) * (tma_mem_latency / (tma_mem_bandwidth + tma_mem_latency)) * tma_remote_cache / (tma_local_mem + tma_remote_cache + tma_remote_mem) + tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_pmm_bound + tma_store_bound) * (tma_contested_accesses + tma_data_sharing) / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full) + tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_pmm_bound + tma_store_bound) * tma_false_sharing / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency + tma_streaming_stores - tma_store_latency)) + tma_machine_clears * (1 - tma_other_nukes / tma_other_nukes))",
- "MetricGroup": "BvMS;Mem;Offcore;tma_issueTLB",
- "MetricName": "tma_info_bottleneck_memory_synchronization",
- "MetricThreshold": "tma_info_bottleneck_memory_synchronization > 10",
- "PublicDescription": "Total pipeline cost of Memory Synchronization related bottlenecks (data transfers and coherency updates across processors). Related metrics: tma_dtlb_load, tma_dtlb_store, tma_info_bottleneck_memory_data_tlbs"
- },
- {
- "BriefDescription": "Total pipeline cost of Branch Misprediction related bottlenecks",
- "MetricExpr": "100 * (1 - 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts) * (tma_branch_mispredicts + tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches))",
- "MetricGroup": "Bad;BadSpec;BrMispredicts;BvMP;tma_issueBM",
- "MetricName": "tma_info_bottleneck_mispredictions",
- "MetricThreshold": "tma_info_bottleneck_mispredictions > 20",
- "PublicDescription": "Total pipeline cost of Branch Misprediction related bottlenecks. Related metrics: tma_branch_mispredicts, tma_info_bad_spec_branch_misprediction_cost, tma_mispredicts_resteers"
- },
- {
- "BriefDescription": "Total pipeline cost of remaining bottlenecks in the back-end",
- "MetricExpr": "100 - (tma_info_bottleneck_big_code + tma_info_bottleneck_instruction_fetch_bw + tma_info_bottleneck_mispredictions + tma_info_bottleneck_cache_memory_bandwidth + tma_info_bottleneck_cache_memory_latency + tma_info_bottleneck_memory_data_tlbs + tma_info_bottleneck_memory_synchronization + tma_info_bottleneck_compute_bound_est + tma_info_bottleneck_irregular_overhead + tma_info_bottleneck_branching_overhead + tma_info_bottleneck_useful_work)",
- "MetricGroup": "BvOB;Cor;Offcore",
- "MetricName": "tma_info_bottleneck_other_bottlenecks",
- "MetricThreshold": "tma_info_bottleneck_other_bottlenecks > 20",
- "PublicDescription": "Total pipeline cost of remaining bottlenecks in the back-end. Examples include data-dependencies (Core Bound when Low ILP) and other unlisted memory-related stalls."
- },
- {
- "BriefDescription": "Total pipeline cost of \"useful operations\" - the portion of Retiring category not covered by Branching_Overhead nor Irregular_Overhead.",
- "MetricExpr": "100 * (tma_retiring - (BR_INST_RETIRED.ALL_BRANCHES + 2 * BR_INST_RETIRED.NEAR_CALL + INST_RETIRED.NOP) / tma_info_thread_slots - tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * tma_heavy_operations)",
- "MetricGroup": "BvUW;Ret",
- "MetricName": "tma_info_bottleneck_useful_work",
- "MetricThreshold": "tma_info_bottleneck_useful_work > 20"
+ "MetricThreshold": "tma_info_botlnk_l2_ic_misses > 5"
},
{
"BriefDescription": "Fraction of branches that are CALL or RET",
@@ -943,11 +990,11 @@
"MetricExpr": "(FP_ARITH_DISPATCHED.PORT_0 + FP_ARITH_DISPATCHED.PORT_1 + FP_ARITH_DISPATCHED.PORT_5) / (2 * tma_info_core_core_clks)",
"MetricGroup": "Cor;Flops;HPC",
"MetricName": "tma_info_core_fp_arith_utilization",
- "PublicDescription": "Actual per-core usage of the Floating Point non-X87 execution units (regardless of precision or vector-width). Values > 1 are possible due to ([BDW+] Fused-Multiply Add (FMA) counting - common; [ADL+] use all of ADD/MUL/FMA in Scalar or 128/256-bit vectors - less common)."
+ "PublicDescription": "Actual per-core usage of the Floating Point non-X87 execution units (regardless of precision or vector-width). Values > 1 are possible due to ([BDW+] Fused-Multiply Add (FMA) counting - common; [ADL+] use all of ADD/MUL/FMA in Scalar or 128/256-bit vectors - less common)"
},
{
"BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is execution) per thread (logical-processor)",
- "MetricExpr": "UOPS_EXECUTED.THREAD / cpu@UOPS_EXECUTED.THREAD\\,cmask\\=1@",
+ "MetricExpr": "UOPS_EXECUTED.THREAD / cpu@UOPS_EXECUTED.THREAD\\,cmask\\=0x1@",
"MetricGroup": "Backend;Cor;Pipeline;PortsUtil",
"MetricName": "tma_info_core_ilp"
},
@@ -960,20 +1007,20 @@
"PublicDescription": "Fraction of Uops delivered by the DSB (aka Decoded ICache; or Uop Cache). Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_inst_mix_iptb, tma_lcp"
},
{
- "BriefDescription": "Average number of cycles of a switch from the DSB fetch-unit to MITE fetch unit - see DSB_Switches tree node for details.",
- "MetricExpr": "DSB2MITE_SWITCHES.PENALTY_CYCLES / cpu@DSB2MITE_SWITCHES.PENALTY_CYCLES\\,cmask\\=1\\,edge@",
+ "BriefDescription": "Average number of cycles of a switch from the DSB fetch-unit to MITE fetch unit - see DSB_Switches tree node for details",
+ "MetricExpr": "DSB2MITE_SWITCHES.PENALTY_CYCLES / cpu@DSB2MITE_SWITCHES.PENALTY_CYCLES\\,cmask\\=0x1\\,edge\\=0x1@",
"MetricGroup": "DSBmiss",
"MetricName": "tma_info_frontend_dsb_switch_cost"
},
{
"BriefDescription": "Average number of Uops issued by front-end when it issued something",
- "MetricExpr": "UOPS_ISSUED.ANY / cpu@UOPS_ISSUED.ANY\\,cmask\\=1@",
+ "MetricExpr": "UOPS_ISSUED.ANY / cpu@UOPS_ISSUED.ANY\\,cmask\\=0x1@",
"MetricGroup": "Fed;FetchBW",
"MetricName": "tma_info_frontend_fetch_upc"
},
{
"BriefDescription": "Average Latency for L1 instruction cache misses",
- "MetricExpr": "ICACHE_DATA.STALLS / cpu@ICACHE_DATA.STALLS\\,cmask\\=1\\,edge@",
+ "MetricExpr": "ICACHE_DATA.STALLS / cpu@ICACHE_DATA.STALLS\\,cmask\\=0x1\\,edge\\=0x1@",
"MetricGroup": "Fed;FetchLat;IcMiss",
"MetricName": "tma_info_frontend_icache_miss_latency"
},
@@ -1002,15 +1049,21 @@
"MetricGroup": "IcMiss",
"MetricName": "tma_info_frontend_l2mpki_code_all"
},
+ {
+ "BriefDescription": "Taken Branches retired Per Cycle",
+ "MetricExpr": "BR_INST_RETIRED.NEAR_TAKEN / tma_info_thread_clks",
+ "MetricGroup": "Branches;FetchBW",
+ "MetricName": "tma_info_frontend_tbpc"
+ },
{
"BriefDescription": "Average number of cycles the front-end was delayed due to an Unknown Branch detection",
- "MetricExpr": "INT_MISC.UNKNOWN_BRANCH_CYCLES / cpu@INT_MISC.UNKNOWN_BRANCH_CYCLES\\,cmask\\=1\\,edge@",
+ "MetricExpr": "INT_MISC.UNKNOWN_BRANCH_CYCLES / cpu@INT_MISC.UNKNOWN_BRANCH_CYCLES\\,cmask\\=0x1\\,edge\\=0x1@",
"MetricGroup": "Fed",
"MetricName": "tma_info_frontend_unknown_branch_cost",
- "PublicDescription": "Average number of cycles the front-end was delayed due to an Unknown Branch detection. See Unknown_Branches node."
+ "PublicDescription": "Average number of cycles the front-end was delayed due to an Unknown Branch detection. See Unknown_Branches node"
},
{
- "BriefDescription": "Branch instructions per taken branch.",
+ "BriefDescription": "Branch instructions per taken branch",
"MetricExpr": "BR_INST_RETIRED.ALL_BRANCHES / BR_INST_RETIRED.NEAR_TAKEN",
"MetricGroup": "Branches;Fed;PGO",
"MetricName": "tma_info_inst_mix_bptkbranch"
@@ -1028,7 +1081,7 @@
"MetricGroup": "Flops;InsType",
"MetricName": "tma_info_inst_mix_iparith",
"MetricThreshold": "tma_info_inst_mix_iparith < 10",
- "PublicDescription": "Instructions per FP Arithmetic instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting. Approximated prior to BDW."
+ "PublicDescription": "Instructions per FP Arithmetic instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting. Approximated prior to BDW"
},
{
"BriefDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number means higher occurrence rate)",
@@ -1036,7 +1089,7 @@
"MetricGroup": "Flops;FpVector;InsType",
"MetricName": "tma_info_inst_mix_iparith_avx128",
"MetricThreshold": "tma_info_inst_mix_iparith_avx128 < 10",
- "PublicDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting."
+ "PublicDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting"
},
{
"BriefDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means higher occurrence rate)",
@@ -1044,7 +1097,7 @@
"MetricGroup": "Flops;FpVector;InsType",
"MetricName": "tma_info_inst_mix_iparith_avx256",
"MetricThreshold": "tma_info_inst_mix_iparith_avx256 < 10",
- "PublicDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting."
+ "PublicDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting"
},
{
"BriefDescription": "Instructions per FP Arithmetic AVX 512-bit instruction (lower number means higher occurrence rate)",
@@ -1052,7 +1105,7 @@
"MetricGroup": "Flops;FpVector;InsType",
"MetricName": "tma_info_inst_mix_iparith_avx512",
"MetricThreshold": "tma_info_inst_mix_iparith_avx512 < 10",
- "PublicDescription": "Instructions per FP Arithmetic AVX 512-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting."
+ "PublicDescription": "Instructions per FP Arithmetic AVX 512-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting"
},
{
"BriefDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction (lower number means higher occurrence rate)",
@@ -1060,7 +1113,7 @@
"MetricGroup": "Flops;FpScalar;InsType",
"MetricName": "tma_info_inst_mix_iparith_scalar_dp",
"MetricThreshold": "tma_info_inst_mix_iparith_scalar_dp < 10",
- "PublicDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting."
+ "PublicDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting"
},
{
"BriefDescription": "Instructions per FP Arithmetic Scalar Half-Precision instruction (lower number means higher occurrence rate)",
@@ -1068,7 +1121,7 @@
"MetricGroup": "Flops;FpScalar;InsType;Server",
"MetricName": "tma_info_inst_mix_iparith_scalar_hp",
"MetricThreshold": "tma_info_inst_mix_iparith_scalar_hp < 10",
- "PublicDescription": "Instructions per FP Arithmetic Scalar Half-Precision instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting."
+ "PublicDescription": "Instructions per FP Arithmetic Scalar Half-Precision instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting"
},
{
"BriefDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction (lower number means higher occurrence rate)",
@@ -1076,7 +1129,7 @@
"MetricGroup": "Flops;FpScalar;InsType",
"MetricName": "tma_info_inst_mix_iparith_scalar_sp",
"MetricThreshold": "tma_info_inst_mix_iparith_scalar_sp < 10",
- "PublicDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting."
+ "PublicDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting"
},
{
"BriefDescription": "Instructions per Branch (lower number means higher occurrence rate)",
@@ -1121,7 +1174,7 @@
},
{
"BriefDescription": "Instructions per Software prefetch instruction (of any type: NTA/T0/T1/T2/Prefetch) (lower number means higher occurrence rate)",
- "MetricExpr": "INST_RETIRED.ANY / cpu@SW_PREFETCH_ACCESS.T0\\,umask\\=0xF@",
+ "MetricExpr": "INST_RETIRED.ANY / SW_PREFETCH_ACCESS.ANY",
"MetricGroup": "Prefetches",
"MetricName": "tma_info_inst_mix_ipswpf",
"MetricThreshold": "tma_info_inst_mix_ipswpf < 100"
@@ -1131,7 +1184,7 @@
"MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_TAKEN",
"MetricGroup": "Branches;Fed;FetchBW;Frontend;PGO;tma_issueFB",
"MetricName": "tma_info_inst_mix_iptb",
- "MetricThreshold": "tma_info_inst_mix_iptb < 13",
+ "MetricThreshold": "tma_info_inst_mix_iptb < 6 * 2 + 1",
"PublicDescription": "Instructions per taken branch. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_lcp"
},
{
@@ -1178,7 +1231,7 @@
},
{
"BriefDescription": "Average per-thread data fill bandwidth to the L1 data cache [GB / sec]",
- "MetricExpr": "64 * L1D.REPLACEMENT / 1e9 / duration_time",
+ "MetricExpr": "64 * L1D.REPLACEMENT / 1e9 / tma_info_system_time",
"MetricGroup": "Mem;MemoryBW",
"MetricName": "tma_info_memory_l1d_cache_fill_bw"
},
@@ -1196,7 +1249,7 @@
},
{
"BriefDescription": "Average per-thread data fill bandwidth to the L2 cache [GB / sec]",
- "MetricExpr": "64 * L2_LINES_IN.ALL / 1e9 / duration_time",
+ "MetricExpr": "64 * L2_LINES_IN.ALL / 1e9 / tma_info_system_time",
"MetricGroup": "Mem;MemoryBW",
"MetricName": "tma_info_memory_l2_cache_fill_bw"
},
@@ -1238,13 +1291,13 @@
},
{
"BriefDescription": "Average per-thread data access bandwidth to the L3 cache [GB / sec]",
- "MetricExpr": "64 * OFFCORE_REQUESTS.ALL_REQUESTS / 1e9 / duration_time",
+ "MetricExpr": "64 * OFFCORE_REQUESTS.ALL_REQUESTS / 1e9 / tma_info_system_time",
"MetricGroup": "Mem;MemoryBW;Offcore",
"MetricName": "tma_info_memory_l3_cache_access_bw"
},
{
"BriefDescription": "Average per-thread data fill bandwidth to the L3 cache [GB / sec]",
- "MetricExpr": "64 * LONGEST_LAT_CACHE.MISS / 1e9 / duration_time",
+ "MetricExpr": "64 * LONGEST_LAT_CACHE.MISS / 1e9 / tma_info_system_time",
"MetricGroup": "Mem;MemoryBW",
"MetricName": "tma_info_memory_l3_cache_fill_bw"
},
@@ -1263,12 +1316,12 @@
{
"BriefDescription": "Average Latency for L2 cache miss demand Loads",
"MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD / OFFCORE_REQUESTS.DEMAND_DATA_RD",
- "MetricGroup": "Memory_Lat;Offcore",
+ "MetricGroup": "LockCont;Memory_Lat;Offcore",
"MetricName": "tma_info_memory_latency_load_l2_miss_latency"
},
{
"BriefDescription": "Average Parallel L2 cache miss demand Loads",
- "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD / cpu@OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD\\,cmask\\=1@",
+ "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD / cpu@OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD\\,cmask\\=0x1@",
"MetricGroup": "Memory_BW;Offcore",
"MetricName": "tma_info_memory_latency_load_l2_mlp"
},
@@ -1321,26 +1374,33 @@
"MetricName": "tma_info_memory_mlp",
"PublicDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least one such miss. Per-Logical Processor)"
},
+ {
+ "BriefDescription": "Rate of L2 HW prefetched lines that were not used by demand accesses",
+ "MetricExpr": "L2_LINES_OUT.USELESS_HWPF / (L2_LINES_OUT.SILENT + L2_LINES_OUT.NON_SILENT)",
+ "MetricGroup": "Prefetches",
+ "MetricName": "tma_info_memory_prefetches_useless_hwpf",
+ "MetricThreshold": "tma_info_memory_prefetches_useless_hwpf > 0.15"
+ },
{
"BriefDescription": "Average DRAM BW for Reads-to-Core (R2C) covering for memory attached to local- and remote-socket",
- "MetricExpr": "64 * OCR.READS_TO_CORE.DRAM / 1e9 / duration_time",
+ "MetricExpr": "64 * OCR.READS_TO_CORE.DRAM / 1e9 / tma_info_system_time",
"MetricGroup": "HPC;Mem;MemoryBW;SoC",
"MetricName": "tma_info_memory_soc_r2c_dram_bw",
- "PublicDescription": "Average DRAM BW for Reads-to-Core (R2C) covering for memory attached to local- and remote-socket. See R2C_Offcore_BW."
+ "PublicDescription": "Average DRAM BW for Reads-to-Core (R2C) covering for memory attached to local- and remote-socket. See R2C_Offcore_BW"
},
{
"BriefDescription": "Average L3-cache miss BW for Reads-to-Core (R2C)",
- "MetricExpr": "64 * OCR.READS_TO_CORE.L3_MISS / 1e9 / duration_time",
+ "MetricExpr": "64 * OCR.READS_TO_CORE.L3_MISS / 1e9 / tma_info_system_time",
"MetricGroup": "HPC;Mem;MemoryBW;SoC",
"MetricName": "tma_info_memory_soc_r2c_l3m_bw",
- "PublicDescription": "Average L3-cache miss BW for Reads-to-Core (R2C). This covering going to DRAM or other memory off-chip memory tears. See R2C_Offcore_BW."
+ "PublicDescription": "Average L3-cache miss BW for Reads-to-Core (R2C). This covering going to DRAM or other memory off-chip memory tears. See R2C_Offcore_BW"
},
{
"BriefDescription": "Average Off-core access BW for Reads-to-Core (R2C)",
- "MetricExpr": "64 * OCR.READS_TO_CORE.ANY_RESPONSE / 1e9 / duration_time",
+ "MetricExpr": "64 * OCR.READS_TO_CORE.ANY_RESPONSE / 1e9 / tma_info_system_time",
"MetricGroup": "HPC;Mem;MemoryBW;SoC",
"MetricName": "tma_info_memory_soc_r2c_offcore_bw",
- "PublicDescription": "Average Off-core access BW for Reads-to-Core (R2C). R2C account for demand or prefetch load/RFO/code access that fill data into the Core caches."
+ "PublicDescription": "Average Off-core access BW for Reads-to-Core (R2C). R2C account for demand or prefetch load/RFO/code access that fill data into the Core caches"
},
{
"BriefDescription": "STLB (2nd level TLB) code speculative misses per kilo instruction (misses of any page-size that complete the page walk)",
@@ -1369,7 +1429,7 @@
},
{
"BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is execution) per core",
- "MetricExpr": "UOPS_EXECUTED.THREAD / (UOPS_EXECUTED.CORE_CYCLES_GE_1 / 2 if #SMT_on else cpu@UOPS_EXECUTED.THREAD\\,cmask\\=1@)",
+ "MetricExpr": "UOPS_EXECUTED.THREAD / (UOPS_EXECUTED.CORE_CYCLES_GE_1 / 2 if #SMT_on else cpu@UOPS_EXECUTED.THREAD\\,cmask\\=0x1@)",
"MetricGroup": "Cor;Pipeline;PortsUtil;SMT",
"MetricName": "tma_info_pipeline_execute"
},
@@ -1390,18 +1450,18 @@
"MetricExpr": "INST_RETIRED.ANY / ASSISTS.ANY",
"MetricGroup": "MicroSeq;Pipeline;Ret;Retire",
"MetricName": "tma_info_pipeline_ipassist",
- "MetricThreshold": "tma_info_pipeline_ipassist < 100e3",
+ "MetricThreshold": "tma_info_pipeline_ipassist < 100000",
"PublicDescription": "Instructions per a microcode Assist invocation. See Assists tree node for details (lower number means higher occurrence rate)"
},
{
- "BriefDescription": "Average number of Uops retired in cycles where at least one uop has retired.",
- "MetricExpr": "tma_retiring * tma_info_thread_slots / cpu@UOPS_RETIRED.SLOTS\\,cmask\\=1@",
+ "BriefDescription": "Average number of Uops retired in cycles where at least one uop has retired",
+ "MetricExpr": "tma_retiring * tma_info_thread_slots / cpu@UOPS_RETIRED.SLOTS\\,cmask\\=0x1@",
"MetricGroup": "Pipeline;Ret",
"MetricName": "tma_info_pipeline_retire"
},
{
"BriefDescription": "Estimated fraction of retirement-cycles dealing with repeat instructions",
- "MetricExpr": "INST_RETIRED.REP_ITERATION / cpu@UOPS_RETIRED.SLOTS\\,cmask\\=1@",
+ "MetricExpr": "INST_RETIRED.REP_ITERATION / cpu@UOPS_RETIRED.SLOTS\\,cmask\\=0x1@",
"MetricGroup": "MicroSeq;Pipeline;Ret",
"MetricName": "tma_info_pipeline_strings_cycles",
"MetricThreshold": "tma_info_pipeline_strings_cycles > 0.1"
@@ -1415,7 +1475,7 @@
},
{
"BriefDescription": "Measured Average Core Frequency for unhalted processors [GHz]",
- "MetricExpr": "tma_info_system_turbo_utilization * TSC / 1e9 / duration_time",
+ "MetricExpr": "tma_info_system_turbo_utilization * TSC / 1e9 / tma_info_system_time",
"MetricGroup": "Power;Summary",
"MetricName": "tma_info_system_core_frequency"
},
@@ -1433,28 +1493,28 @@
},
{
"BriefDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]",
- "MetricExpr": "64 * (UNC_M_CAS_COUNT.RD + UNC_M_CAS_COUNT.WR) / 1e9 / duration_time",
+ "MetricExpr": "64 * (UNC_M_CAS_COUNT.RD + UNC_M_CAS_COUNT.WR) / 1e9 / tma_info_system_time",
"MetricGroup": "HPC;MemOffcore;MemoryBW;SoC;tma_issueBW",
"MetricName": "tma_info_system_dram_bw_use",
- "PublicDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]. Related metrics: tma_fb_full, tma_info_bottleneck_cache_memory_bandwidth, tma_mem_bandwidth, tma_sq_full"
+ "PublicDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]. Related metrics: tma_bottleneck_cache_memory_bandwidth, tma_fb_full, tma_mem_bandwidth, tma_sq_full"
},
{
"BriefDescription": "Giga Floating Point Operations Per Second",
- "MetricExpr": "(FP_ARITH_INST_RETIRED.SCALAR + FP_ARITH_INST_RETIRED2.SCALAR_HALF + 2 * (FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED2.COMPLEX_SCALAR_HALF) + 4 * FP_ARITH_INST_RETIRED.4_FLOPS + 8 * (FP_ARITH_INST_RETIRED2.128B_PACKED_HALF + FP_ARITH_INST_RETIRED.8_FLOPS) + 16 * (FP_ARITH_INST_RETIRED2.256B_PACKED_HALF + FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE) + 32 * FP_ARITH_INST_RETIRED2.512B_PACKED_HALF) / 1e9 / duration_time",
+ "MetricExpr": "(FP_ARITH_INST_RETIRED.SCALAR + FP_ARITH_INST_RETIRED2.SCALAR_HALF + 2 * (FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED2.COMPLEX_SCALAR_HALF) + 4 * FP_ARITH_INST_RETIRED.4_FLOPS + 8 * (FP_ARITH_INST_RETIRED2.128B_PACKED_HALF + FP_ARITH_INST_RETIRED.8_FLOPS) + 16 * (FP_ARITH_INST_RETIRED2.256B_PACKED_HALF + FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE) + 32 * FP_ARITH_INST_RETIRED2.512B_PACKED_HALF) / 1e9 / tma_info_system_time",
"MetricGroup": "Cor;Flops;HPC",
"MetricName": "tma_info_system_gflops",
"PublicDescription": "Giga Floating Point Operations Per Second. Aggregate across all supported options of: FP precisions, scalar and vector instructions, vector-width"
},
{
"BriefDescription": "Average IO (network or disk) Bandwidth Use for Reads [GB / sec]",
- "MetricExpr": "UNC_CHA_TOR_INSERTS.IO_PCIRDCUR * 64 / 1e9 / duration_time",
+ "MetricExpr": "UNC_CHA_TOR_INSERTS.IO_PCIRDCUR * 64 / 1e9 / tma_info_system_time",
"MetricGroup": "IoBW;MemOffcore;Server;SoC",
"MetricName": "tma_info_system_io_read_bw",
"PublicDescription": "Average IO (network or disk) Bandwidth Use for Reads [GB / sec]. Bandwidth of IO reads that are initiated by end device controllers that are requesting memory from the CPU"
},
{
"BriefDescription": "Average IO (network or disk) Bandwidth Use for Writes [GB / sec]",
- "MetricExpr": "(UNC_CHA_TOR_INSERTS.IO_ITOM + UNC_CHA_TOR_INSERTS.IO_ITOMCACHENEAR) * 64 / 1e9 / duration_time",
+ "MetricExpr": "(UNC_CHA_TOR_INSERTS.IO_ITOM + UNC_CHA_TOR_INSERTS.IO_ITOMCACHENEAR) * 64 / 1e9 / tma_info_system_time",
"MetricGroup": "IoBW;MemOffcore;Server;SoC",
"MetricName": "tma_info_system_io_write_bw",
"PublicDescription": "Average IO (network or disk) Bandwidth Use for Writes [GB / sec]. Bandwidth of IO writes that are initiated by end device controllers that are writing memory to the CPU"
@@ -1464,13 +1524,14 @@
"MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.FAR_BRANCH:u",
"MetricGroup": "Branches;OS",
"MetricName": "tma_info_system_ipfarbranch",
- "MetricThreshold": "tma_info_system_ipfarbranch < 1e6"
+ "MetricThreshold": "tma_info_system_ipfarbranch < 1000000"
},
{
"BriefDescription": "Cycles Per Instruction for the Operating System (OS) Kernel mode",
"MetricExpr": "CPU_CLK_UNHALTED.THREAD_P:k / INST_RETIRED.ANY_P:k",
"MetricGroup": "OS",
- "MetricName": "tma_info_system_kernel_cpi"
+ "MetricName": "tma_info_system_kernel_cpi",
+ "ScaleUnit": "1per_instr"
},
{
"BriefDescription": "Fraction of cycles spent in the Operating System (OS) Kernel mode",
@@ -1481,44 +1542,45 @@
},
{
"BriefDescription": "Average latency of data read request to external DRAM memory [in nanoseconds]",
- "MetricExpr": "1e9 * (UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_DDR / UNC_CHA_TOR_INSERTS.IA_MISS_DRD_DDR) / uncore_cha_0@event\\=0x1@",
+ "MetricExpr": "1e9 * (UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_DDR / UNC_CHA_TOR_INSERTS.IA_MISS_DRD_DDR) / cha_0@event\\=0x0@",
"MetricGroup": "MemOffcore;MemoryLat;Server;SoC",
"MetricName": "tma_info_system_mem_dram_read_latency",
"PublicDescription": "Average latency of data read request to external DRAM memory [in nanoseconds]. Accounts for demand loads and L1/L2 data-read prefetches"
},
+ {
+ "BriefDescription": "Fraction of Uncore cycles where requests got rejected due to duplicate address already in IRQ ingress queue in the cache homing agent",
+ "MetricExpr": "UNC_CHA_RxC_IRQ1_REJECT.PA_MATCH / UNC_CHA_CLOCKTICKS",
+ "MetricGroup": "LockCont;MemOffcore;Server;SoC",
+ "MetricName": "tma_info_system_mem_irq_duplicate_address",
+ "MetricThreshold": "(tma_info_system_mem_irq_duplicate_address > 0.1)"
+ },
{
"BriefDescription": "Average number of parallel data read requests to external memory",
- "MetricExpr": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD / UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD@thresh\\=1@",
+ "MetricExpr": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD / cha@UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD\\,thresh\\=0x1@",
"MetricGroup": "Mem;MemoryBW;SoC",
"MetricName": "tma_info_system_mem_parallel_reads",
"PublicDescription": "Average number of parallel data read requests to external memory. Accounts for demand loads and L1/L2 prefetches"
},
- {
- "BriefDescription": "Average latency of data read request to external 3D X-Point memory [in nanoseconds]",
- "MetricExpr": "(1e9 * (UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_PMM / UNC_CHA_TOR_INSERTS.IA_MISS_DRD_PMM) / uncore_cha_0@event\\=0x1@ if #has_pmem > 0 else 0)",
- "MetricGroup": "MemOffcore;MemoryLat;Server;SoC",
- "MetricName": "tma_info_system_mem_pmm_read_latency",
- "PublicDescription": "Average latency of data read request to external 3D X-Point memory [in nanoseconds]. Accounts for demand loads and L1/L2 data-read prefetches"
- },
{
"BriefDescription": "Average latency of data read request to external memory (in nanoseconds)",
"MetricConstraint": "NO_GROUP_EVENTS",
- "MetricExpr": "1e9 * (UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD / UNC_CHA_TOR_INSERTS.IA_MISS_DRD) / (tma_info_system_socket_clks / duration_time)",
+ "MetricExpr": "1e9 * (UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD / UNC_CHA_TOR_INSERTS.IA_MISS_DRD) / (tma_info_system_socket_clks / tma_info_system_time)",
"MetricGroup": "Mem;MemoryLat;SoC",
"MetricName": "tma_info_system_mem_read_latency",
"PublicDescription": "Average latency of data read request to external memory (in nanoseconds). Accounts for demand loads and L1/L2 prefetches. ([RKL+]memory-controller only)"
},
{
- "BriefDescription": "Average 3DXP Memory Bandwidth Use for reads [GB / sec]",
- "MetricExpr": "(64 * UNC_M_PMM_RPQ_INSERTS / 1e9 / duration_time if #has_pmem > 0 else 0)",
- "MetricGroup": "MemOffcore;MemoryBW;Server;SoC",
- "MetricName": "tma_info_system_pmm_read_bw"
+ "BriefDescription": "PerfMon Event Multiplexing accuracy indicator",
+ "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P / CPU_CLK_UNHALTED.THREAD",
+ "MetricGroup": "Summary",
+ "MetricName": "tma_info_system_mux",
+ "MetricThreshold": "tma_info_system_mux > 1.1 | tma_info_system_mux < 0.9"
},
{
- "BriefDescription": "Average 3DXP Memory Bandwidth Use for Writes [GB / sec]",
- "MetricExpr": "(64 * UNC_M_PMM_WPQ_INSERTS / 1e9 / duration_time if #has_pmem > 0 else 0)",
- "MetricGroup": "MemOffcore;MemoryBW;Server;SoC",
- "MetricName": "tma_info_system_pmm_write_bw"
+ "BriefDescription": "Total package Power in Watts",
+ "MetricExpr": "(power@energy\\-pkg@ * 61 + 15.6 * power@energy\\-ram@) / (duration_time * 1e6)",
+ "MetricGroup": "Power;SoC",
+ "MetricName": "tma_info_system_power"
},
{
"BriefDescription": "Fraction of cycles where both hardware Logical Processors were active",
@@ -1528,10 +1590,17 @@
},
{
"BriefDescription": "Socket actual clocks when any core is active on that socket",
- "MetricExpr": "uncore_cha_0@event\\=0x1@",
+ "MetricExpr": "cha_0@event\\=0x0@",
"MetricGroup": "SoC",
"MetricName": "tma_info_system_socket_clks"
},
+ {
+ "BriefDescription": "Run duration time in seconds",
+ "MetricExpr": "duration_time",
+ "MetricGroup": "Summary",
+ "MetricName": "tma_info_system_time",
+ "MetricThreshold": "tma_info_system_time < 1"
+ },
{
"BriefDescription": "Average Frequency Utilization relative nominal frequency",
"MetricExpr": "tma_info_thread_clks / CPU_CLK_UNHALTED.REF_TSC",
@@ -1540,7 +1609,7 @@
},
{
"BriefDescription": "Measured Average Uncore Frequency for the SoC [GHz]",
- "MetricExpr": "tma_info_system_socket_clks / 1e9 / duration_time",
+ "MetricExpr": "tma_info_system_socket_clks / 1e9 / tma_info_system_time",
"MetricGroup": "SoC",
"MetricName": "tma_info_system_uncore_frequency"
},
@@ -1551,7 +1620,7 @@
"MetricName": "tma_info_system_upi_data_transmit_bw"
},
{
- "BriefDescription": "Per-Logical Processor actual clocks when the Logical Processor is active.",
+ "BriefDescription": "Per-Logical Processor actual clocks when the Logical Processor is active",
"MetricExpr": "CPU_CLK_UNHALTED.THREAD",
"MetricGroup": "Pipeline",
"MetricName": "tma_info_thread_clks"
@@ -1560,14 +1629,15 @@
"BriefDescription": "Cycles Per Instruction (per Logical Processor)",
"MetricExpr": "1 / tma_info_thread_ipc",
"MetricGroup": "Mem;Pipeline",
- "MetricName": "tma_info_thread_cpi"
+ "MetricName": "tma_info_thread_cpi",
+ "ScaleUnit": "1per_instr"
},
{
"BriefDescription": "The ratio of Executed- by Issued-Uops",
"MetricExpr": "UOPS_EXECUTED.THREAD / UOPS_ISSUED.ANY",
"MetricGroup": "Cor;Pipeline",
"MetricName": "tma_info_thread_execute_per_issue",
- "PublicDescription": "The ratio of Executed- by Issued-Uops. Ratio > 1 suggests high rate of uop micro-fusions. Ratio < 1 suggest high rate of \"execute\" at rename stage."
+ "PublicDescription": "The ratio of Executed- by Issued-Uops. Ratio > 1 suggests high rate of uop micro-fusions. Ratio < 1 suggest high rate of \"execute\" at rename stage"
},
{
"BriefDescription": "Instructions Per Cycle (per Logical Processor)",
@@ -1577,13 +1647,13 @@
},
{
"BriefDescription": "Total issue-pipeline slots (per-Physical Core till ICL; per-Logical Processor ICL onward)",
- "MetricExpr": "TOPDOWN.SLOTS",
+ "MetricExpr": "slots",
"MetricGroup": "TmaL1;tma_L1_group",
"MetricName": "tma_info_thread_slots"
},
{
"BriefDescription": "Fraction of Physical Core issue-slots utilized by this Logical Processor",
- "MetricExpr": "(tma_info_thread_slots / (TOPDOWN.SLOTS / 2) if #SMT_on else 1)",
+ "MetricExpr": "(tma_info_thread_slots / (slots / 2) if #SMT_on else 1)",
"MetricGroup": "SMT;TmaL1;tma_L1_group",
"MetricName": "tma_info_thread_slots_utilization"
},
@@ -1599,7 +1669,15 @@
"MetricExpr": "tma_retiring * tma_info_thread_slots / BR_INST_RETIRED.NEAR_TAKEN",
"MetricGroup": "Branches;Fed;FetchBW",
"MetricName": "tma_info_thread_uptb",
- "MetricThreshold": "tma_info_thread_uptb < 9"
+ "MetricThreshold": "tma_info_thread_uptb < 6 * 1.5"
+ },
+ {
+ "BriefDescription": "This metric represents fraction of cycles where the Integer Divider unit was active",
+ "MetricExpr": "tma_divider - tma_fp_divider",
+ "MetricGroup": "TopdownL4;tma_L4_group;tma_divider_group",
+ "MetricName": "tma_int_divider",
+ "MetricThreshold": "tma_int_divider > 0.2 & tma_divider > 0.2 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
+ "ScaleUnit": "100%"
},
{
"BriefDescription": "This metric represents overall Integer (Int) select operations fraction the CPU has executed (retired)",
@@ -1607,7 +1685,7 @@
"MetricGroup": "Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group",
"MetricName": "tma_int_operations",
"MetricThreshold": "tma_int_operations > 0.1 & tma_light_operations > 0.6",
- "PublicDescription": "This metric represents overall Integer (Int) select operations fraction the CPU has executed (retired). Vector/Matrix Int operations and shuffles are counted. Note this metric's value may exceed its parent due to use of \"Uops\" CountDomain.",
+ "PublicDescription": "This metric represents overall Integer (Int) select operations fraction the CPU has executed (retired). Vector/Matrix Int operations and shuffles are counted. Note this metric's value may exceed its parent due to use of \"Uops\" CountDomain",
"ScaleUnit": "100%"
},
{
@@ -1615,8 +1693,8 @@
"MetricExpr": "(INT_VEC_RETIRED.ADD_128 + INT_VEC_RETIRED.VNNI_128) / (tma_retiring * tma_info_thread_slots)",
"MetricGroup": "Compute;IntVector;Pipeline;TopdownL4;tma_L4_group;tma_int_operations_group;tma_issue2P",
"MetricName": "tma_int_vector_128b",
- "MetricThreshold": "tma_int_vector_128b > 0.1 & (tma_int_operations > 0.1 & tma_light_operations > 0.6)",
- "PublicDescription": "This metric represents 128-bit vector Integer ADD/SUB/SAD or VNNI (Vector Neural Network Instructions) uops fraction the CPU has retired. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2",
+ "MetricThreshold": "tma_int_vector_128b > 0.1 & tma_int_operations > 0.1 & tma_light_operations > 0.6",
+ "PublicDescription": "This metric represents 128-bit vector Integer ADD/SUB/SAD or VNNI (Vector Neural Network Instructions) uops fraction the CPU has retired. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_6, tma_ports_utilized_2",
"ScaleUnit": "100%"
},
{
@@ -1624,8 +1702,8 @@
"MetricExpr": "(INT_VEC_RETIRED.ADD_256 + INT_VEC_RETIRED.MUL_256 + INT_VEC_RETIRED.VNNI_256) / (tma_retiring * tma_info_thread_slots)",
"MetricGroup": "Compute;IntVector;Pipeline;TopdownL4;tma_L4_group;tma_int_operations_group;tma_issue2P",
"MetricName": "tma_int_vector_256b",
- "MetricThreshold": "tma_int_vector_256b > 0.1 & (tma_int_operations > 0.1 & tma_light_operations > 0.6)",
- "PublicDescription": "This metric represents 256-bit vector Integer ADD/SUB/SAD/MUL or VNNI (Vector Neural Network Instructions) uops fraction the CPU has retired. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2",
+ "MetricThreshold": "tma_int_vector_256b > 0.1 & tma_int_operations > 0.1 & tma_light_operations > 0.6",
+ "PublicDescription": "This metric represents 256-bit vector Integer ADD/SUB/SAD/MUL or VNNI (Vector Neural Network Instructions) uops fraction the CPU has retired. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_port_0, tma_port_1, tma_port_6, tma_ports_utilized_2",
"ScaleUnit": "100%"
},
{
@@ -1633,26 +1711,26 @@
"MetricExpr": "ICACHE_TAG.STALLS / tma_info_thread_clks",
"MetricGroup": "BigFootprint;BvBC;FetchLat;MemoryTLB;TopdownL3;tma_L3_group;tma_fetch_latency_group",
"MetricName": "tma_itlb_misses",
- "MetricThreshold": "tma_itlb_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)",
- "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Instruction TLB (ITLB) misses. Sample with: FRONTEND_RETIRED.STLB_MISS_PS;FRONTEND_RETIRED.ITLB_MISS_PS",
+ "MetricThreshold": "tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+ "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Instruction TLB (ITLB) misses. Sample with: FRONTEND_RETIRED.STLB_MISS, FRONTEND_RETIRED.ITLB_MISS",
"ScaleUnit": "100%"
},
{
- "BriefDescription": "This metric estimates how often the CPU was stalled without loads missing the L1 data cache",
+ "BriefDescription": "This metric estimates how often the CPU was stalled without loads missing the L1 Data (L1D) cache",
"MetricExpr": "max((EXE_ACTIVITY.BOUND_ON_LOADS - MEMORY_ACTIVITY.STALLS_L1D_MISS) / tma_info_thread_clks, 0)",
"MetricGroup": "CacheHits;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_issueL1;tma_issueMC;tma_memory_bound_group",
"MetricName": "tma_l1_bound",
- "MetricThreshold": "tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)",
- "PublicDescription": "This metric estimates how often the CPU was stalled without loads missing the L1 data cache. The L1 data cache typically has the shortest latency. However; in certain cases like loads blocked on older stores; a load might suffer due to high latency even though it is being satisfied by the L1. Another example is loads who miss in the TLB. These cases are characterized by execution unit stalls; while some non-completed demand load lives in the machine without having that demand load missing the L1 cache. Sample with: MEM_LOAD_RETIRED.L1_HIT_PS;MEM_LOAD_RETIRED.FB_HIT_PS. Related metrics: tma_clears_resteers, tma_machine_clears, tma_microcode_sequencer, tma_ms_switches, tma_ports_utilized_1",
+ "MetricThreshold": "tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+ "PublicDescription": "This metric estimates how often the CPU was stalled without loads missing the L1 Data (L1D) cache. The L1D cache typically has the shortest latency. However; in certain cases like loads blocked on older stores; a load might suffer due to high latency even though it is being satisfied by the L1D. Another example is loads who miss in the TLB. These cases are characterized by execution unit stalls; while some non-completed demand load lives in the machine without having that demand load missing the L1 cache. Sample with: MEM_LOAD_RETIRED.L1_HIT. Related metrics: tma_clears_resteers, tma_machine_clears, tma_microcode_sequencer, tma_ms_switches, tma_ports_utilized_1",
"ScaleUnit": "100%"
},
{
- "BriefDescription": "This metric roughly estimates fraction of cycles with demand load accesses that hit the L1 cache",
+ "BriefDescription": "This metric([SKL+] roughly; [LNL]) estimates fraction of cycles with demand load accesses that hit the L1D cache",
"MetricExpr": "min(2 * (MEM_INST_RETIRED.ALL_LOADS - MEM_LOAD_RETIRED.FB_HIT - MEM_LOAD_RETIRED.L1_MISS) * 20 / 100, max(CYCLE_ACTIVITY.CYCLES_MEM_ANY - MEMORY_ACTIVITY.CYCLES_L1D_MISS, 0)) / tma_info_thread_clks",
"MetricGroup": "BvML;MemoryLat;TopdownL4;tma_L4_group;tma_l1_bound_group",
- "MetricName": "tma_l1_hit_latency",
- "MetricThreshold": "tma_l1_hit_latency > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
- "PublicDescription": "This metric roughly estimates fraction of cycles with demand load accesses that hit the L1 cache. The short latency of the L1 data cache may be exposed in pointer-chasing memory access patterns as an example. Sample with: MEM_LOAD_RETIRED.L1_HIT",
+ "MetricName": "tma_l1_latency_dependency",
+ "MetricThreshold": "tma_l1_latency_dependency > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+ "PublicDescription": "This metric([SKL+] roughly; [LNL]) estimates fraction of cycles with demand load accesses that hit the L1D cache. The short latency of the L1D cache may be exposed in pointer-chasing memory access patterns as an example. Sample with: MEM_LOAD_RETIRED.L1_HIT",
"ScaleUnit": "100%"
},
{
@@ -1660,8 +1738,17 @@
"MetricExpr": "(MEMORY_ACTIVITY.STALLS_L1D_MISS - MEMORY_ACTIVITY.STALLS_L2_MISS) / tma_info_thread_clks",
"MetricGroup": "BvML;CacheHits;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group",
"MetricName": "tma_l2_bound",
- "MetricThreshold": "tma_l2_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)",
- "PublicDescription": "This metric estimates how often the CPU was stalled due to L2 cache accesses by loads. Avoiding cache misses (i.e. L1 misses/L2 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L2_HIT_PS",
+ "MetricThreshold": "tma_l2_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+ "PublicDescription": "This metric estimates how often the CPU was stalled due to L2 cache accesses by loads. Avoiding cache misses (i.e. L1 misses/L2 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L2_HIT",
+ "ScaleUnit": "100%"
+ },
+ {
+ "BriefDescription": "This metric represents fraction of cycles with demand load accesses that hit the L2 cache under unloaded scenarios (possibly L2 latency limited)",
+ "MetricExpr": "4.4 * tma_info_system_core_frequency * MEM_LOAD_RETIRED.L2_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks",
+ "MetricGroup": "MemoryLat;TopdownL4;tma_L4_group;tma_l2_bound_group",
+ "MetricName": "tma_l2_hit_latency",
+ "MetricThreshold": "tma_l2_hit_latency > 0.05 & tma_l2_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+ "PublicDescription": "This metric represents fraction of cycles with demand load accesses that hit the L2 cache under unloaded scenarios (possibly L2 latency limited). Avoiding L1 cache misses (i.e. L1 misses/L2 hits) will improve the latency. Sample with: MEM_LOAD_RETIRED.L2_HIT",
"ScaleUnit": "100%"
},
{
@@ -1669,17 +1756,17 @@
"MetricExpr": "(MEMORY_ACTIVITY.STALLS_L2_MISS - MEMORY_ACTIVITY.STALLS_L3_MISS) / tma_info_thread_clks",
"MetricGroup": "CacheHits;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group",
"MetricName": "tma_l3_bound",
- "MetricThreshold": "tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)",
- "PublicDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core. Avoiding cache misses (i.e. L2 misses/L3 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L3_HIT_PS",
+ "MetricThreshold": "tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+ "PublicDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core. Avoiding cache misses (i.e. L2 misses/L3 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L3_HIT",
"ScaleUnit": "100%"
},
{
"BriefDescription": "This metric estimates fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited)",
- "MetricExpr": "32.6 * tma_info_system_core_frequency * (MEM_LOAD_RETIRED.L3_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2)) / tma_info_thread_clks",
+ "MetricExpr": "(37 * tma_info_system_core_frequency - 4.4 * tma_info_system_core_frequency) * (MEM_LOAD_RETIRED.L3_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2)) / tma_info_thread_clks",
"MetricGroup": "BvML;MemoryLat;TopdownL4;tma_L4_group;tma_issueLat;tma_l3_bound_group",
"MetricName": "tma_l3_hit_latency",
- "MetricThreshold": "tma_l3_hit_latency > 0.1 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
- "PublicDescription": "This metric estimates fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited). Avoiding private cache misses (i.e. L2 misses/L3 hits) will improve the latency; reduce contention with sibling physical cores and increase performance. Note the value of this node may overlap with its siblings. Sample with: MEM_LOAD_RETIRED.L3_HIT_PS. Related metrics: tma_info_bottleneck_cache_memory_latency, tma_mem_latency",
+ "MetricThreshold": "tma_l3_hit_latency > 0.1 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+ "PublicDescription": "This metric estimates fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited). Avoiding private cache misses (i.e. L2 misses/L3 hits) will improve the latency; reduce contention with sibling physical cores and increase performance. Note the value of this node may overlap with its siblings. Sample with: MEM_LOAD_RETIRED.L3_HIT. Related metrics: tma_bottleneck_cache_memory_latency, tma_branch_resteers, tma_mem_latency, tma_store_latency",
"ScaleUnit": "100%"
},
{
@@ -1687,19 +1774,18 @@
"MetricExpr": "DECODE.LCP / tma_info_thread_clks",
"MetricGroup": "FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueFB",
"MetricName": "tma_lcp",
- "MetricThreshold": "tma_lcp > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)",
- "PublicDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs). Using proper compiler flags or Intel Compiler by default will certainly avoid this. #Link: Optimization Guide about LCP BKMs. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb",
+ "MetricThreshold": "tma_lcp > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+ "PublicDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs). Using proper compiler flags or Intel Compiler by default will certainly avoid this. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb",
"ScaleUnit": "100%"
},
{
- "BriefDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation)",
- "DefaultMetricgroupName": "TopdownL2",
+ "BriefDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations , instructions that require no more than one uop (micro-operation)",
"MetricExpr": "max(0, tma_retiring - tma_heavy_operations)",
- "MetricGroup": "Default;Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group",
+ "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group",
"MetricName": "tma_light_operations",
"MetricThreshold": "tma_light_operations > 0.6",
- "MetricgroupNoGroup": "TopdownL2;Default",
- "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized code running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. ([ICL+] Note this may undercount due to approximation using indirect events; [ADL+] .). Sample with: INST_RETIRED.PREC_DIST",
+ "MetricgroupNoGroup": "TopdownL2",
+ "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations , instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized code running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. ([ICL+] Note this may undercount due to approximation using indirect events; [ADL+] .). Sample with: INST_RETIRED.PREC_DIST",
"ScaleUnit": "100%"
},
{
@@ -1716,7 +1802,7 @@
"MetricExpr": "tma_dtlb_load - tma_load_stlb_miss",
"MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_load_group",
"MetricName": "tma_load_stlb_hit",
- "MetricThreshold": "tma_load_stlb_hit > 0.05 & (tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))",
+ "MetricThreshold": "tma_load_stlb_hit > 0.05 & tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
"ScaleUnit": "100%"
},
{
@@ -1724,53 +1810,76 @@
"MetricExpr": "DTLB_LOAD_MISSES.WALK_ACTIVE / tma_info_thread_clks",
"MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_load_group",
"MetricName": "tma_load_stlb_miss",
- "MetricThreshold": "tma_load_stlb_miss > 0.05 & (tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))",
+ "MetricThreshold": "tma_load_stlb_miss > 0.05 & tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+ "ScaleUnit": "100%"
+ },
+ {
+ "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 1 GB pages for data load accesses",
+ "MetricExpr": "tma_load_stlb_miss * DTLB_LOAD_MISSES.WALK_COMPLETED_1G / (DTLB_LOAD_MISSES.WALK_COMPLETED_4K + DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M + DTLB_LOAD_MISSES.WALK_COMPLETED_1G)",
+ "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_load_stlb_miss_group",
+ "MetricName": "tma_load_stlb_miss_1g",
+ "MetricThreshold": "tma_load_stlb_miss_1g > 0.05 & tma_load_stlb_miss > 0.05 & tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+ "ScaleUnit": "100%"
+ },
+ {
+ "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 2 or 4 MB pages for data load accesses",
+ "MetricExpr": "tma_load_stlb_miss * DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M / (DTLB_LOAD_MISSES.WALK_COMPLETED_4K + DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M + DTLB_LOAD_MISSES.WALK_COMPLETED_1G)",
+ "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_load_stlb_miss_group",
+ "MetricName": "tma_load_stlb_miss_2m",
+ "MetricThreshold": "tma_load_stlb_miss_2m > 0.05 & tma_load_stlb_miss > 0.05 & tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+ "ScaleUnit": "100%"
+ },
+ {
+ "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 4 KB pages for data load accesses",
+ "MetricExpr": "tma_load_stlb_miss * DTLB_LOAD_MISSES.WALK_COMPLETED_4K / (DTLB_LOAD_MISSES.WALK_COMPLETED_4K + DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M + DTLB_LOAD_MISSES.WALK_COMPLETED_1G)",
+ "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_load_stlb_miss_group",
+ "MetricName": "tma_load_stlb_miss_4k",
+ "MetricThreshold": "tma_load_stlb_miss_4k > 0.05 & tma_load_stlb_miss > 0.05 & tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
"ScaleUnit": "100%"
},
{
"BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from local memory",
- "MetricExpr": "72 * tma_info_system_core_frequency * MEM_LOAD_L3_MISS_RETIRED.LOCAL_DRAM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks",
+ "MetricExpr": "(109 * tma_info_system_core_frequency - 37 * tma_info_system_core_frequency) * MEM_LOAD_L3_MISS_RETIRED.LOCAL_DRAM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks",
"MetricGroup": "Server;TopdownL5;tma_L5_group;tma_mem_latency_group",
"MetricName": "tma_local_mem",
- "MetricThreshold": "tma_local_mem > 0.1 & (tma_mem_latency > 0.1 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))",
+ "MetricThreshold": "tma_local_mem > 0.1 & tma_mem_latency > 0.1 & tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
"PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from local memory. Caching will improve the latency and increase performance. Sample with: MEM_LOAD_L3_MISS_RETIRED.LOCAL_DRAM",
"ScaleUnit": "100%"
},
{
"BriefDescription": "This metric represents fraction of cycles the CPU spent handling cache misses due to lock operations",
"MetricExpr": "(16 * max(0, MEM_INST_RETIRED.LOCK_LOADS - L2_RQSTS.ALL_RFO) + MEM_INST_RETIRED.LOCK_LOADS / MEM_INST_RETIRED.ALL_STORES * (10 * L2_RQSTS.RFO_HIT + min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO))) / tma_info_thread_clks",
- "MetricGroup": "Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_l1_bound_group",
+ "MetricGroup": "LockCont;Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_l1_bound_group",
"MetricName": "tma_lock_latency",
- "MetricThreshold": "tma_lock_latency > 0.2 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+ "MetricThreshold": "tma_lock_latency > 0.2 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
"PublicDescription": "This metric represents fraction of cycles the CPU spent handling cache misses due to lock operations. Due to the microarchitecture handling of locks; they are classified as L1_Bound regardless of what memory source satisfied them. Sample with: MEM_INST_RETIRED.LOCK_LOADS. Related metrics: tma_store_latency",
"ScaleUnit": "100%"
},
{
"BriefDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears",
- "DefaultMetricgroupName": "TopdownL2",
"MetricExpr": "max(0, tma_bad_speculation - tma_branch_mispredicts)",
- "MetricGroup": "BadSpec;BvMS;Default;MachineClears;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueMC;tma_issueSyncxn",
+ "MetricGroup": "BadSpec;BvMS;MachineClears;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueMC;tma_issueSyncxn",
"MetricName": "tma_machine_clears",
"MetricThreshold": "tma_machine_clears > 0.1 & tma_bad_speculation > 0.15",
- "MetricgroupNoGroup": "TopdownL2;Default",
- "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears. These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT. Related metrics: tma_clears_resteers, tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_l1_bound, tma_microcode_sequencer, tma_ms_switches, tma_remote_cache",
+ "MetricgroupNoGroup": "TopdownL2",
+ "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears. These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT. Related metrics: tma_bottleneck_memory_synchronization, tma_clears_resteers, tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_l1_bound, tma_microcode_sequencer, tma_ms_switches, tma_remote_cache",
"ScaleUnit": "100%"
},
{
- "BriefDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to memory bandwidth Allocation feature (RDT's memory bandwidth throttling).",
+ "BriefDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to memory bandwidth Allocation feature (RDT's memory bandwidth throttling)",
"MetricExpr": "INT_MISC.MBA_STALLS / tma_info_thread_clks",
"MetricGroup": "MemoryBW;Offcore;Server;TopdownL5;tma_L5_group;tma_mem_bandwidth_group",
"MetricName": "tma_mba_stalls",
- "MetricThreshold": "tma_mba_stalls > 0.1 & (tma_mem_bandwidth > 0.2 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))",
+ "MetricThreshold": "tma_mba_stalls > 0.1 & tma_mem_bandwidth > 0.2 & tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
"ScaleUnit": "100%"
},
{
"BriefDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory - DRAM ([SPR-HBM] and/or HBM)",
- "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, cpu@OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD\\,cmask\\=4@) / tma_info_thread_clks",
- "MetricGroup": "BvMS;MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueBW",
+ "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, cpu@OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD\\,cmask\\=0x4@) / tma_info_thread_clks",
+ "MetricGroup": "BvMB;MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueBW",
"MetricName": "tma_mem_bandwidth",
- "MetricThreshold": "tma_mem_bandwidth > 0.2 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
- "PublicDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory - DRAM ([SPR-HBM] and/or HBM). The underlying heuristic assumes that a similar off-core traffic is generated by all IA cores. This metric does not aggregate non-data-read requests by this logical processor; requests from other IA Logical Processors/Physical Cores/sockets; or other non-IA devices like GPU; hence the maximum external memory bandwidth limits may or may not be approached when this metric is flagged (see Uncore counters for that). Related metrics: tma_fb_full, tma_info_bottleneck_cache_memory_bandwidth, tma_info_system_dram_bw_use, tma_sq_full",
+ "MetricThreshold": "tma_mem_bandwidth > 0.2 & tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+ "PublicDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory - DRAM ([SPR-HBM] and/or HBM). The underlying heuristic assumes that a similar off-core traffic is generated by all IA cores. This metric does not aggregate non-data-read requests by this logical processor; requests from other IA Logical Processors/Physical Cores/sockets; or other non-IA devices like GPU; hence the maximum external memory bandwidth limits may or may not be approached when this metric is flagged (see Uncore counters for that). Related metrics: tma_bottleneck_cache_memory_bandwidth, tma_fb_full, tma_info_system_dram_bw_use, tma_sq_full",
"ScaleUnit": "100%"
},
{
@@ -1778,32 +1887,31 @@
"MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD) / tma_info_thread_clks - tma_mem_bandwidth",
"MetricGroup": "BvML;MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueLat",
"MetricName": "tma_mem_latency",
- "MetricThreshold": "tma_mem_latency > 0.1 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
- "PublicDescription": "This metric estimates fraction of cycles where the performance was likely hurt due to latency from external memory - DRAM ([SPR-HBM] and/or HBM). This metric does not aggregate requests from other Logical Processors/Physical Cores/sockets (see Uncore counters for that). Related metrics: tma_info_bottleneck_cache_memory_latency, tma_l3_hit_latency",
+ "MetricThreshold": "tma_mem_latency > 0.1 & tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+ "PublicDescription": "This metric estimates fraction of cycles where the performance was likely hurt due to latency from external memory - DRAM ([SPR-HBM] and/or HBM). This metric does not aggregate requests from other Logical Processors/Physical Cores/sockets (see Uncore counters for that). Related metrics: tma_bottleneck_cache_memory_latency, tma_l3_hit_latency",
"ScaleUnit": "100%"
},
{
"BriefDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck",
- "DefaultMetricgroupName": "TopdownL2",
- "MetricExpr": "topdown\\-mem\\-bound / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * tma_info_thread_slots",
- "MetricGroup": "Backend;Default;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group",
+ "MetricExpr": "topdown\\-mem\\-bound / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * slots",
+ "MetricGroup": "Backend;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group",
"MetricName": "tma_memory_bound",
"MetricThreshold": "tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
- "MetricgroupNoGroup": "TopdownL2;Default",
- "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck. Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two).",
+ "MetricgroupNoGroup": "TopdownL2",
+ "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck. Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two)",
"ScaleUnit": "100%"
},
{
- "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to LFENCE Instructions.",
+ "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to LFENCE Instructions",
"MetricConstraint": "NO_GROUP_EVENTS_NMI",
"MetricExpr": "13 * MISC2_RETIRED.LFENCE / tma_info_thread_clks",
"MetricGroup": "TopdownL4;tma_L4_group;tma_serializing_operation_group",
"MetricName": "tma_memory_fence",
- "MetricThreshold": "tma_memory_fence > 0.05 & (tma_serializing_operation > 0.1 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))",
+ "MetricThreshold": "tma_memory_fence > 0.05 & tma_serializing_operation > 0.1 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
"ScaleUnit": "100%"
},
{
- "BriefDescription": "This metric represents fraction of slots where the CPU was retiring memory operations -- uops for memory load or store accesses.",
+ "BriefDescription": "This metric represents fraction of slots where the CPU was retiring memory operations , uops for memory load or store accesses",
"MetricExpr": "tma_light_operations * MEM_UOP_RETIRED.ANY / (tma_retiring * tma_info_thread_slots)",
"MetricGroup": "Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group",
"MetricName": "tma_memory_operations",
@@ -1816,7 +1924,7 @@
"MetricGroup": "MicroSeq;TopdownL3;tma_L3_group;tma_heavy_operations_group;tma_issueMC;tma_issueMS",
"MetricName": "tma_microcode_sequencer",
"MetricThreshold": "tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1",
- "PublicDescription": "This metric represents fraction of slots the CPU was retiring uops fetched by the Microcode Sequencer (MS) unit. The MS is used for CISC instructions not supported by the default decoders (like repeat move strings; or CPUID); or by microcode assists used to address some operation modes (like in Floating Point assists). These cases can often be avoided. Sample with: UOPS_RETIRED.MS. Related metrics: tma_clears_resteers, tma_info_bottleneck_irregular_overhead, tma_l1_bound, tma_machine_clears, tma_ms_switches",
+ "PublicDescription": "This metric represents fraction of slots the CPU was retiring uops fetched by the Microcode Sequencer (MS) unit. The MS is used for CISC instructions not supported by the default decoders (like repeat move strings; or CPUID); or by microcode assists used to address some operation modes (like in Floating Point assists). These cases can often be avoided. Sample with: UOPS_RETIRED.MS. Related metrics: tma_bottleneck_irregular_overhead, tma_clears_resteers, tma_l1_bound, tma_machine_clears, tma_ms_switches",
"ScaleUnit": "100%"
},
{
@@ -1824,8 +1932,8 @@
"MetricExpr": "tma_branch_mispredicts / tma_bad_speculation * INT_MISC.CLEAR_RESTEER_CYCLES / tma_info_thread_clks",
"MetricGroup": "BadSpec;BrMispredicts;BvMP;TopdownL4;tma_L4_group;tma_branch_resteers_group;tma_issueBM",
"MetricName": "tma_mispredicts_resteers",
- "MetricThreshold": "tma_mispredicts_resteers > 0.05 & (tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))",
- "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Branch Misprediction at execution stage. Sample with: INT_MISC.CLEAR_RESTEER_CYCLES. Related metrics: tma_branch_mispredicts, tma_info_bad_spec_branch_misprediction_cost, tma_info_bottleneck_mispredictions",
+ "MetricThreshold": "tma_mispredicts_resteers > 0.05 & tma_branch_resteers > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+ "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Branch Misprediction at execution stage. Sample with: INT_MISC.CLEAR_RESTEER_CYCLES. Related metrics: tma_bottleneck_mispredictions, tma_branch_mispredicts, tma_info_bad_spec_branch_misprediction_cost",
"ScaleUnit": "100%"
},
{
@@ -1838,21 +1946,29 @@
"ScaleUnit": "100%"
},
{
- "BriefDescription": "This metric estimates penalty in terms of percentage of([SKL+] injected blend uops out of all Uops Issued -- the Count Domain; [ADL+] cycles)",
+ "BriefDescription": "This metric estimates penalty in terms of percentage of([SKL+] injected blend uops out of all Uops Issued , the Count Domain; [ADL+] cycles)",
"MetricExpr": "160 * ASSISTS.SSE_AVX_MIX / tma_info_thread_clks",
"MetricGroup": "TopdownL5;tma_L5_group;tma_issueMV;tma_ports_utilized_0_group",
"MetricName": "tma_mixing_vectors",
"MetricThreshold": "tma_mixing_vectors > 0.05",
- "PublicDescription": "This metric estimates penalty in terms of percentage of([SKL+] injected blend uops out of all Uops Issued -- the Count Domain; [ADL+] cycles). Usually a Mixing_Vectors over 5% is worth investigating. Read more in Appendix B1 of the Optimizations Guide for this topic. Related metrics: tma_ms_switches",
+ "PublicDescription": "This metric estimates penalty in terms of percentage of([SKL+] injected blend uops out of all Uops Issued , the Count Domain; [ADL+] cycles). Usually a Mixing_Vectors over 5% is worth investigating. Read more in Appendix B1 of the Optimizations Guide for this topic. Related metrics: tma_ms_switches",
+ "ScaleUnit": "100%"
+ },
+ {
+ "BriefDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to the Microcode Sequencer (MS) unit - see Microcode_Sequencer node for details",
+ "MetricExpr": "max(IDQ.MS_CYCLES_ANY, cpu@UOPS_RETIRED.MS\\,cmask\\=0x1@ / (UOPS_RETIRED.SLOTS / UOPS_ISSUED.ANY)) / tma_info_core_core_clks / 2",
+ "MetricGroup": "MicroSeq;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group",
+ "MetricName": "tma_ms",
+ "MetricThreshold": "tma_ms > 0.05 & tma_fetch_bandwidth > 0.2",
"ScaleUnit": "100%"
},
{
"BriefDescription": "This metric estimates the fraction of cycles when the CPU was stalled due to switches of uop delivery to the Microcode Sequencer (MS)",
- "MetricExpr": "3 * cpu@UOPS_RETIRED.MS\\,cmask\\=1\\,edge@ / (UOPS_RETIRED.SLOTS / UOPS_ISSUED.ANY) / tma_info_thread_clks",
+ "MetricExpr": "3 * cpu@UOPS_RETIRED.MS\\,cmask\\=0x1\\,edge\\=0x1@ / (UOPS_RETIRED.SLOTS / UOPS_ISSUED.ANY) / tma_info_thread_clks",
"MetricGroup": "FetchLat;MicroSeq;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueMC;tma_issueMS;tma_issueMV;tma_issueSO",
"MetricName": "tma_ms_switches",
- "MetricThreshold": "tma_ms_switches > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)",
- "PublicDescription": "This metric estimates the fraction of cycles when the CPU was stalled due to switches of uop delivery to the Microcode Sequencer (MS). Commonly used instructions are optimized for delivery by the DSB (decoded i-cache) or MITE (legacy instruction decode) pipelines. Certain operations cannot be handled natively by the execution pipeline; and must be performed by microcode (small programs injected into the execution stream). Switching to the MS too often can negatively impact performance. The MS is designated to deliver long uop flows required by CISC instructions like CPUID; or uncommon conditions like Floating Point Assists when dealing with Denormals. Sample with: FRONTEND_RETIRED.MS_FLOWS. Related metrics: tma_clears_resteers, tma_info_bottleneck_irregular_overhead, tma_l1_bound, tma_machine_clears, tma_microcode_sequencer, tma_mixing_vectors, tma_serializing_operation",
+ "MetricThreshold": "tma_ms_switches > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+ "PublicDescription": "This metric estimates the fraction of cycles when the CPU was stalled due to switches of uop delivery to the Microcode Sequencer (MS). Commonly used instructions are optimized for delivery by the DSB (decoded i-cache) or MITE (legacy instruction decode) pipelines. Certain operations cannot be handled natively by the execution pipeline; and must be performed by microcode (small programs injected into the execution stream). Switching to the MS too often can negatively impact performance. The MS is designated to deliver long uop flows required by CISC instructions like CPUID; or uncommon conditions like Floating Point Assists when dealing with Denormals. Sample with: FRONTEND_RETIRED.MS_FLOWS. Related metrics: tma_bottleneck_irregular_overhead, tma_clears_resteers, tma_l1_bound, tma_machine_clears, tma_microcode_sequencer, tma_mixing_vectors, tma_serializing_operation",
"ScaleUnit": "100%"
},
{
@@ -1861,7 +1977,7 @@
"MetricGroup": "Branches;BvBO;Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group",
"MetricName": "tma_non_fused_branches",
"MetricThreshold": "tma_non_fused_branches > 0.1 & tma_light_operations > 0.6",
- "PublicDescription": "This metric represents fraction of slots where the CPU was retiring branch instructions that were not fused. Non-conditional branches like direct JMP or CALL would count here. Can be used to examine fusible conditional jumps that were not fused.",
+ "PublicDescription": "This metric represents fraction of slots where the CPU was retiring branch instructions that were not fused. Non-conditional branches like direct JMP or CALL would count here. Can be used to examine fusible conditional jumps that were not fused",
"ScaleUnit": "100%"
},
{
@@ -1869,7 +1985,7 @@
"MetricExpr": "tma_light_operations * INST_RETIRED.NOP / (tma_retiring * tma_info_thread_slots)",
"MetricGroup": "BvBO;Pipeline;TopdownL4;tma_L4_group;tma_other_light_ops_group",
"MetricName": "tma_nop_instructions",
- "MetricThreshold": "tma_nop_instructions > 0.1 & (tma_other_light_ops > 0.3 & tma_light_operations > 0.6)",
+ "MetricThreshold": "tma_nop_instructions > 0.1 & tma_other_light_ops > 0.3 & tma_light_operations > 0.6",
"PublicDescription": "This metric represents fraction of slots where the CPU was retiring NOP (no op) instructions. Compilers often use NOPs for certain address alignments - e.g. start address of a function or loop body. Sample with: INST_RETIRED.NOP",
"ScaleUnit": "100%"
},
@@ -1883,19 +1999,19 @@
"ScaleUnit": "100%"
},
{
- "BriefDescription": "This metric estimates fraction of slots the CPU was stalled due to other cases of misprediction (non-retired x86 branches or other types).",
+ "BriefDescription": "This metric estimates fraction of slots the CPU was stalled due to other cases of misprediction (non-retired x86 branches or other types)",
"MetricExpr": "max(tma_branch_mispredicts * (1 - BR_MISP_RETIRED.ALL_BRANCHES / (INT_MISC.CLEARS_COUNT - MACHINE_CLEARS.COUNT)), 0.0001)",
"MetricGroup": "BrMispredicts;BvIO;TopdownL3;tma_L3_group;tma_branch_mispredicts_group",
"MetricName": "tma_other_mispredicts",
- "MetricThreshold": "tma_other_mispredicts > 0.05 & (tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15)",
+ "MetricThreshold": "tma_other_mispredicts > 0.05 & tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15",
"ScaleUnit": "100%"
},
{
- "BriefDescription": "This metric represents fraction of slots the CPU has wasted due to Nukes (Machine Clears) not related to memory ordering.",
+ "BriefDescription": "This metric represents fraction of slots the CPU has wasted due to Nukes (Machine Clears) not related to memory ordering",
"MetricExpr": "max(tma_machine_clears * (1 - MACHINE_CLEARS.MEMORY_ORDERING / MACHINE_CLEARS.COUNT), 0.0001)",
"MetricGroup": "BvIO;Machine_Clears;TopdownL3;tma_L3_group;tma_machine_clears_group",
"MetricName": "tma_other_nukes",
- "MetricThreshold": "tma_other_nukes > 0.05 & (tma_machine_clears > 0.1 & tma_bad_speculation > 0.15)",
+ "MetricThreshold": "tma_other_nukes > 0.05 & tma_machine_clears > 0.1 & tma_bad_speculation > 0.15",
"ScaleUnit": "100%"
},
{
@@ -1904,16 +2020,7 @@
"MetricGroup": "TopdownL5;tma_L5_group;tma_assists_group",
"MetricName": "tma_page_faults",
"MetricThreshold": "tma_page_faults > 0.05",
- "PublicDescription": "This metric roughly estimates fraction of slots the CPU retired uops as a result of handing Page Faults. A Page Fault may apply on first application access to a memory page. Note operating system handling of page faults accounts for the majority of its cost.",
- "ScaleUnit": "100%"
- },
- {
- "BriefDescription": "This metric roughly estimates (based on idle latencies) how often the CPU was stalled on accesses to external 3D-Xpoint (Crystal Ridge, a.k.a",
- "MetricExpr": "(((1 - (19 * (MEM_LOAD_L3_MISS_RETIRED.REMOTE_DRAM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS)) + 10 * (MEM_LOAD_L3_MISS_RETIRED.LOCAL_DRAM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) + MEM_LOAD_L3_MISS_RETIRED.REMOTE_FWD * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) + MEM_LOAD_L3_MISS_RETIRED.REMOTE_HITM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS))) / (19 * (MEM_LOAD_L3_MISS_RETIRED.REMOTE_DRAM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS)) + 10 * (MEM_LOAD_L3_MISS_RETIRED.LOCAL_DRAM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) + MEM_LOAD_L3_MISS_RETIRED.REMOTE_FWD * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) + MEM_LOAD_L3_MISS_RETIRED.REMOTE_HITM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS)) + (25 * (MEM_LOAD_RETIRED.LOCAL_PMM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS)) + 33 * (MEM_LOAD_L3_MISS_RETIRED.REMOTE_PMM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS))))) * (MEMORY_ACTIVITY.STALLS_L3_MISS / tma_info_thread_clks) if 1e6 * (MEM_LOAD_L3_MISS_RETIRED.REMOTE_PMM + MEM_LOAD_RETIRED.LOCAL_PMM) > MEM_LOAD_RETIRED.L1_MISS else 0) if #has_pmem > 0 else 0)",
- "MetricGroup": "MemoryBound;Server;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group",
- "MetricName": "tma_pmm_bound",
- "MetricThreshold": "tma_pmm_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)",
- "PublicDescription": "This metric roughly estimates (based on idle latencies) how often the CPU was stalled on accesses to external 3D-Xpoint (Crystal Ridge, a.k.a. IXP) memory by loads, PMM stands for Persistent Memory Module.",
+ "PublicDescription": "This metric roughly estimates fraction of slots the CPU retired uops as a result of handing Page Faults. A Page Fault may apply on first application access to a memory page. Note operating system handling of page faults accounts for the majority of its cost",
"ScaleUnit": "100%"
},
{
@@ -1922,7 +2029,7 @@
"MetricGroup": "Compute;TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P",
"MetricName": "tma_port_0",
"MetricThreshold": "tma_port_0 > 0.6",
- "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 0 ([SNB+] ALU; [HSW+] ALU and 2nd branch). Sample with: UOPS_DISPATCHED.PORT_0. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2",
+ "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 0 ([SNB+] ALU; [HSW+] ALU and 2nd branch). Sample with: UOPS_DISPATCHED.PORT_0. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_1, tma_port_6, tma_ports_utilized_2",
"ScaleUnit": "100%"
},
{
@@ -1931,7 +2038,7 @@
"MetricGroup": "TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P",
"MetricName": "tma_port_1",
"MetricThreshold": "tma_port_1 > 0.6",
- "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 1 (ALU). Sample with: UOPS_DISPATCHED.PORT_1. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_5, tma_port_6, tma_ports_utilized_2",
+ "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 1 (ALU). Sample with: UOPS_DISPATCHED.PORT_1. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_6, tma_ports_utilized_2",
"ScaleUnit": "100%"
},
{
@@ -1940,25 +2047,25 @@
"MetricGroup": "TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P",
"MetricName": "tma_port_6",
"MetricThreshold": "tma_port_6 > 0.6",
- "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 6 ([HSW+] Primary Branch and simple ALU). Sample with: UOPS_DISPATCHED.PORT_6. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_ports_utilized_2",
+ "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 6 ([HSW+] Primary Branch and simple ALU). Sample with: UOPS_DISPATCHED.PORT_1. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_ports_utilized_2",
"ScaleUnit": "100%"
},
{
"BriefDescription": "This metric estimates fraction of cycles the CPU performance was potentially limited due to Core computation issues (non divider-related)",
- "MetricExpr": "((tma_ports_utilized_0 * tma_info_thread_clks + (EXE_ACTIVITY.1_PORTS_UTIL + tma_retiring * cpu@EXE_ACTIVITY.2_PORTS_UTIL\\,umask\\=0xc@)) / tma_info_thread_clks if ARITH.DIV_ACTIVE < CYCLE_ACTIVITY.STALLS_TOTAL - EXE_ACTIVITY.BOUND_ON_LOADS else (EXE_ACTIVITY.1_PORTS_UTIL + tma_retiring * cpu@EXE_ACTIVITY.2_PORTS_UTIL\\,umask\\=0xc@) / tma_info_thread_clks)",
+ "MetricExpr": "((tma_ports_utilized_0 * tma_info_thread_clks + (EXE_ACTIVITY.1_PORTS_UTIL + tma_retiring * EXE_ACTIVITY.2_3_PORTS_UTIL)) / tma_info_thread_clks if ARITH.DIV_ACTIVE < CYCLE_ACTIVITY.STALLS_TOTAL - EXE_ACTIVITY.BOUND_ON_LOADS else (EXE_ACTIVITY.1_PORTS_UTIL + tma_retiring * EXE_ACTIVITY.2_3_PORTS_UTIL) / tma_info_thread_clks)",
"MetricGroup": "PortsUtil;TopdownL3;tma_L3_group;tma_core_bound_group",
"MetricName": "tma_ports_utilization",
- "MetricThreshold": "tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)",
- "PublicDescription": "This metric estimates fraction of cycles the CPU performance was potentially limited due to Core computation issues (non divider-related). Two distinct categories can be attributed into this metric: (1) heavy data-dependency among contiguous instructions would manifest in this metric - such cases are often referred to as low Instruction Level Parallelism (ILP). (2) Contention on some hardware execution unit other than Divider. For example; when there are too many multiply operations.",
+ "MetricThreshold": "tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
+ "PublicDescription": "This metric estimates fraction of cycles the CPU performance was potentially limited due to Core computation issues (non divider-related). Two distinct categories can be attributed into this metric: (1) heavy data-dependency among contiguous instructions would manifest in this metric - such cases are often referred to as low Instruction Level Parallelism (ILP). (2) Contention on some hardware execution unit other than Divider. For example; when there are too many multiply operations",
"ScaleUnit": "100%"
},
{
"BriefDescription": "This metric represents fraction of cycles CPU executed no uops on any execution port (Logical Processor cycles since ICL, Physical Core cycles otherwise)",
- "MetricExpr": "(EXE_ACTIVITY.EXE_BOUND_0_PORTS + max(cpu@RS.EMPTY\\,umask\\=1@ - RESOURCE_STALLS.SCOREBOARD, 0)) / tma_info_thread_clks * (CYCLE_ACTIVITY.STALLS_TOTAL - EXE_ACTIVITY.BOUND_ON_LOADS) / tma_info_thread_clks",
+ "MetricExpr": "(EXE_ACTIVITY.EXE_BOUND_0_PORTS + max(RS.EMPTY_RESOURCE - RESOURCE_STALLS.SCOREBOARD, 0)) / tma_info_thread_clks * (CYCLE_ACTIVITY.STALLS_TOTAL - EXE_ACTIVITY.BOUND_ON_LOADS) / tma_info_thread_clks",
"MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group",
"MetricName": "tma_ports_utilized_0",
- "MetricThreshold": "tma_ports_utilized_0 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))",
- "PublicDescription": "This metric represents fraction of cycles CPU executed no uops on any execution port (Logical Processor cycles since ICL, Physical Core cycles otherwise). Long-latency instructions like divides may contribute to this metric.",
+ "MetricThreshold": "tma_ports_utilized_0 > 0.2 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
+ "PublicDescription": "This metric represents fraction of cycles CPU executed no uops on any execution port (Logical Processor cycles since ICL, Physical Core cycles otherwise). Long-latency instructions like divides may contribute to this metric",
"ScaleUnit": "100%"
},
{
@@ -1966,7 +2073,7 @@
"MetricExpr": "EXE_ACTIVITY.1_PORTS_UTIL / tma_info_thread_clks",
"MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_issueL1;tma_ports_utilization_group",
"MetricName": "tma_ports_utilized_1",
- "MetricThreshold": "tma_ports_utilized_1 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))",
+ "MetricThreshold": "tma_ports_utilized_1 > 0.2 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
"PublicDescription": "This metric represents fraction of cycles where the CPU executed total of 1 uop per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise). This can be due to heavy data-dependency among software instructions; or over oversubscribing a particular hardware resource. In some other cases with high 1_Port_Utilized and L1_Bound; this metric can point to L1 data-cache latency bottleneck that may not necessarily manifest with complete execution starvation (due to the short L1 latency e.g. walking a linked list) - looking at the assembly can be helpful. Sample with: EXE_ACTIVITY.1_PORTS_UTIL. Related metrics: tma_l1_bound",
"ScaleUnit": "100%"
},
@@ -1976,8 +2083,8 @@
"MetricExpr": "EXE_ACTIVITY.2_PORTS_UTIL / tma_info_thread_clks",
"MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_issue2P;tma_ports_utilization_group",
"MetricName": "tma_ports_utilized_2",
- "MetricThreshold": "tma_ports_utilized_2 > 0.15 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))",
- "PublicDescription": "This metric represents fraction of cycles CPU executed total of 2 uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise). Loop Vectorization -most compilers feature auto-Vectorization options today- reduces pressure on the execution ports as multiple elements are calculated with same uop. Sample with: EXE_ACTIVITY.2_PORTS_UTIL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_port_6",
+ "MetricThreshold": "tma_ports_utilized_2 > 0.15 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
+ "PublicDescription": "This metric represents fraction of cycles CPU executed total of 2 uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise). Loop Vectorization -most compilers feature auto-Vectorization options today- reduces pressure on the execution ports as multiple elements are calculated with same uop. Sample with: EXE_ACTIVITY.2_PORTS_UTIL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_6",
"ScaleUnit": "100%"
},
{
@@ -1986,36 +2093,35 @@
"MetricExpr": "UOPS_EXECUTED.CYCLES_GE_3 / tma_info_thread_clks",
"MetricGroup": "BvCB;PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group",
"MetricName": "tma_ports_utilized_3m",
- "MetricThreshold": "tma_ports_utilized_3m > 0.4 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))",
+ "MetricThreshold": "tma_ports_utilized_3m > 0.4 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
"PublicDescription": "This metric represents fraction of cycles CPU executed total of 3 or more uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise). Sample with: UOPS_EXECUTED.CYCLES_GE_3",
"ScaleUnit": "100%"
},
{
"BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from remote cache in other sockets including synchronizations issues",
- "MetricExpr": "(133 * tma_info_system_core_frequency * MEM_LOAD_L3_MISS_RETIRED.REMOTE_HITM + 133 * tma_info_system_core_frequency * MEM_LOAD_L3_MISS_RETIRED.REMOTE_FWD) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks",
+ "MetricExpr": "((170 * tma_info_system_core_frequency - 37 * tma_info_system_core_frequency) * MEM_LOAD_L3_MISS_RETIRED.REMOTE_HITM + (170 * tma_info_system_core_frequency - 37 * tma_info_system_core_frequency) * MEM_LOAD_L3_MISS_RETIRED.REMOTE_FWD) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks",
"MetricGroup": "Offcore;Server;Snoop;TopdownL5;tma_L5_group;tma_issueSyncxn;tma_mem_latency_group",
"MetricName": "tma_remote_cache",
- "MetricThreshold": "tma_remote_cache > 0.05 & (tma_mem_latency > 0.1 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))",
- "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from remote cache in other sockets including synchronizations issues. This is caused often due to non-optimal NUMA allocations. #link to NUMA article. Sample with: MEM_LOAD_L3_MISS_RETIRED.REMOTE_HITM_PS;MEM_LOAD_L3_MISS_RETIRED.REMOTE_FWD_PS. Related metrics: tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_machine_clears",
+ "MetricThreshold": "tma_remote_cache > 0.05 & tma_mem_latency > 0.1 & tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+ "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from remote cache in other sockets including synchronizations issues. This is caused often due to non-optimal NUMA allocations. Sample with: MEM_LOAD_L3_MISS_RETIRED.REMOTE_HITM, MEM_LOAD_L3_MISS_RETIRED.REMOTE_FWD. Related metrics: tma_bottleneck_memory_synchronization, tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_machine_clears",
"ScaleUnit": "100%"
},
{
"BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from remote memory",
- "MetricExpr": "153 * tma_info_system_core_frequency * MEM_LOAD_L3_MISS_RETIRED.REMOTE_DRAM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks",
+ "MetricExpr": "(190 * tma_info_system_core_frequency - 37 * tma_info_system_core_frequency) * MEM_LOAD_L3_MISS_RETIRED.REMOTE_DRAM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks",
"MetricGroup": "Server;Snoop;TopdownL5;tma_L5_group;tma_mem_latency_group",
"MetricName": "tma_remote_mem",
- "MetricThreshold": "tma_remote_mem > 0.1 & (tma_mem_latency > 0.1 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))",
- "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from remote memory. This is caused often due to non-optimal NUMA allocations. #link to NUMA article. Sample with: MEM_LOAD_L3_MISS_RETIRED.REMOTE_DRAM_PS",
+ "MetricThreshold": "tma_remote_mem > 0.1 & tma_mem_latency > 0.1 & tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+ "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from remote memory. This is caused often due to non-optimal NUMA allocations. Sample with: MEM_LOAD_L3_MISS_RETIRED.REMOTE_DRAM",
"ScaleUnit": "100%"
},
{
"BriefDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired",
- "DefaultMetricgroupName": "TopdownL1",
- "MetricExpr": "topdown\\-retiring / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * tma_info_thread_slots",
- "MetricGroup": "BvUW;Default;TmaL1;TopdownL1;tma_L1_group",
+ "MetricExpr": "topdown\\-retiring / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * slots",
+ "MetricGroup": "BvUW;TmaL1;TopdownL1;tma_L1_group",
"MetricName": "tma_retiring",
"MetricThreshold": "tma_retiring > 0.7 | tma_heavy_operations > 0.1",
- "MetricgroupNoGroup": "TopdownL1;Default",
+ "MetricgroupNoGroup": "TopdownL1",
"PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum Pipeline_Width throughput was achieved. Maximizing Retiring typically increases the Instructions-per-cycle (see IPC metric). Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Heavy-operations or Microcode Assists are categorized under Retiring. They often indicate suboptimal performance and can often be optimized or avoided. Sample with: UOPS_RETIRED.SLOTS",
"ScaleUnit": "100%"
},
@@ -2024,7 +2130,7 @@
"MetricExpr": "RESOURCE_STALLS.SCOREBOARD / tma_info_thread_clks + tma_c02_wait",
"MetricGroup": "BvIO;PortsUtil;TopdownL3;tma_L3_group;tma_core_bound_group;tma_issueSO",
"MetricName": "tma_serializing_operation",
- "MetricThreshold": "tma_serializing_operation > 0.1 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)",
+ "MetricThreshold": "tma_serializing_operation > 0.1 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
"PublicDescription": "This metric represents fraction of cycles the CPU issue-pipeline was stalled due to serializing operations. Instructions like CPUID; WRMSR or LFENCE serialize the out-of-order execution which may limit performance. Sample with: RESOURCE_STALLS.SCOREBOARD. Related metrics: tma_ms_switches",
"ScaleUnit": "100%"
},
@@ -2033,8 +2139,8 @@
"MetricExpr": "tma_light_operations * INT_VEC_RETIRED.SHUFFLES / (tma_retiring * tma_info_thread_slots)",
"MetricGroup": "HPC;Pipeline;TopdownL4;tma_L4_group;tma_other_light_ops_group",
"MetricName": "tma_shuffles_256b",
- "MetricThreshold": "tma_shuffles_256b > 0.1 & (tma_other_light_ops > 0.3 & tma_light_operations > 0.6)",
- "PublicDescription": "This metric represents fraction of slots where the CPU was retiring Shuffle operations of 256-bit vector size (FP or Integer). Shuffles may incur slow cross \"vector lane\" data transfers.",
+ "MetricThreshold": "tma_shuffles_256b > 0.1 & tma_other_light_ops > 0.3 & tma_light_operations > 0.6",
+ "PublicDescription": "This metric represents fraction of slots where the CPU was retiring Shuffle operations of 256-bit vector size (FP or Integer). Shuffles may incur slow cross \"vector lane\" data transfers",
"ScaleUnit": "100%"
},
{
@@ -2043,7 +2149,7 @@
"MetricExpr": "CPU_CLK_UNHALTED.PAUSE / tma_info_thread_clks",
"MetricGroup": "TopdownL4;tma_L4_group;tma_serializing_operation_group",
"MetricName": "tma_slow_pause",
- "MetricThreshold": "tma_slow_pause > 0.05 & (tma_serializing_operation > 0.1 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))",
+ "MetricThreshold": "tma_slow_pause > 0.05 & tma_serializing_operation > 0.1 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
"PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to PAUSE Instructions. Sample with: CPU_CLK_UNHALTED.PAUSE_INST",
"ScaleUnit": "100%"
},
@@ -2052,8 +2158,8 @@
"MetricExpr": "tma_info_memory_load_miss_real_latency * LD_BLOCKS.NO_SR / tma_info_thread_clks",
"MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group",
"MetricName": "tma_split_loads",
- "MetricThreshold": "tma_split_loads > 0.2 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
- "PublicDescription": "This metric estimates fraction of cycles handling memory load split accesses - load that cross 64-byte cache line boundary. Sample with: MEM_INST_RETIRED.SPLIT_LOADS_PS",
+ "MetricThreshold": "tma_split_loads > 0.3",
+ "PublicDescription": "This metric estimates fraction of cycles handling memory load split accesses - load that cross 64-byte cache line boundary. Sample with: MEM_INST_RETIRED.SPLIT_LOADS",
"ScaleUnit": "100%"
},
{
@@ -2061,17 +2167,17 @@
"MetricExpr": "MEM_INST_RETIRED.SPLIT_STORES / tma_info_core_core_clks",
"MetricGroup": "TopdownL4;tma_L4_group;tma_issueSpSt;tma_store_bound_group",
"MetricName": "tma_split_stores",
- "MetricThreshold": "tma_split_stores > 0.2 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
- "PublicDescription": "This metric represents rate of split store accesses. Consider aligning your data to the 64-byte cache line granularity. Sample with: MEM_INST_RETIRED.SPLIT_STORES_PS. Related metrics: tma_port_4",
+ "MetricThreshold": "tma_split_stores > 0.2 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+ "PublicDescription": "This metric represents rate of split store accesses. Consider aligning your data to the 64-byte cache line granularity. Sample with: MEM_INST_RETIRED.SPLIT_STORES",
"ScaleUnit": "100%"
},
{
"BriefDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors)",
"MetricExpr": "(XQ.FULL_CYCLES + L1D_PEND_MISS.L2_STALLS) / tma_info_thread_clks",
- "MetricGroup": "BvMS;MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_issueBW;tma_l3_bound_group",
+ "MetricGroup": "BvMB;MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_issueBW;tma_l3_bound_group",
"MetricName": "tma_sq_full",
- "MetricThreshold": "tma_sq_full > 0.3 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
- "PublicDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors). Related metrics: tma_fb_full, tma_info_bottleneck_cache_memory_bandwidth, tma_info_system_dram_bw_use, tma_mem_bandwidth",
+ "MetricThreshold": "tma_sq_full > 0.3 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+ "PublicDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors). Related metrics: tma_bottleneck_cache_memory_bandwidth, tma_fb_full, tma_info_system_dram_bw_use, tma_mem_bandwidth",
"ScaleUnit": "100%"
},
{
@@ -2079,8 +2185,8 @@
"MetricExpr": "EXE_ACTIVITY.BOUND_ON_STORES / tma_info_thread_clks",
"MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group",
"MetricName": "tma_store_bound",
- "MetricThreshold": "tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)",
- "PublicDescription": "This metric estimates how often CPU was stalled due to RFO store memory accesses; RFO store issue a read-for-ownership request before the write. Even though store accesses do not typically stall out-of-order CPUs; there are few cases where stores can lead to actual stalls. This metric will be flagged should RFO stores be a bottleneck. Sample with: MEM_INST_RETIRED.ALL_STORES_PS",
+ "MetricThreshold": "tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+ "PublicDescription": "This metric estimates how often CPU was stalled due to RFO store memory accesses; RFO store issue a read-for-ownership request before the write. Even though store accesses do not typically stall out-of-order CPUs; there are few cases where stores can lead to actual stalls. This metric will be flagged should RFO stores be a bottleneck. Sample with: MEM_INST_RETIRED.ALL_STORES",
"ScaleUnit": "100%"
},
{
@@ -2088,17 +2194,17 @@
"MetricExpr": "13 * LD_BLOCKS.STORE_FORWARD / tma_info_thread_clks",
"MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group",
"MetricName": "tma_store_fwd_blk",
- "MetricThreshold": "tma_store_fwd_blk > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
- "PublicDescription": "This metric roughly estimates fraction of cycles when the memory subsystem had loads blocked since they could not forward data from earlier (in program order) overlapping stores. To streamline memory operations in the pipeline; a load can avoid waiting for memory if a prior in-flight store is writing the data that the load wants to read (store forwarding process). However; in some cases the load may be blocked for a significant time pending the store forward. For example; when the prior store is writing a smaller region than the load is reading.",
+ "MetricThreshold": "tma_store_fwd_blk > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+ "PublicDescription": "This metric roughly estimates fraction of cycles when the memory subsystem had loads blocked since they could not forward data from earlier (in program order) overlapping stores. To streamline memory operations in the pipeline; a load can avoid waiting for memory if a prior in-flight store is writing the data that the load wants to read (store forwarding process). However; in some cases the load may be blocked for a significant time pending the store forward. For example; when the prior store is writing a smaller region than the load is reading",
"ScaleUnit": "100%"
},
{
"BriefDescription": "This metric estimates fraction of cycles the CPU spent handling L1D store misses",
"MetricExpr": "(MEM_STORE_RETIRED.L2_HIT * 10 * (1 - MEM_INST_RETIRED.LOCK_LOADS / MEM_INST_RETIRED.ALL_STORES) + (1 - MEM_INST_RETIRED.LOCK_LOADS / MEM_INST_RETIRED.ALL_STORES) * min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO)) / tma_info_thread_clks",
- "MetricGroup": "BvML;MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_issueSL;tma_store_bound_group",
+ "MetricGroup": "BvML;LockCont;MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_issueSL;tma_store_bound_group",
"MetricName": "tma_store_latency",
- "MetricThreshold": "tma_store_latency > 0.1 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
- "PublicDescription": "This metric estimates fraction of cycles the CPU spent handling L1D store misses. Store accesses usually less impact out-of-order core performance; however; holding resources for longer time can lead into undesired implications (e.g. contention on L1D fill-buffer entries - see FB_Full). Related metrics: tma_fb_full, tma_lock_latency",
+ "MetricThreshold": "tma_store_latency > 0.1 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+ "PublicDescription": "This metric estimates fraction of cycles the CPU spent handling L1D store misses. Store accesses usually less impact out-of-order core performance; however; holding resources for longer time can lead into undesired implications (e.g. contention on L1D fill-buffer entries - see FB_Full). Related metrics: tma_branch_resteers, tma_fb_full, tma_l3_hit_latency, tma_lock_latency",
"ScaleUnit": "100%"
},
{
@@ -2115,7 +2221,7 @@
"MetricExpr": "tma_dtlb_store - tma_store_stlb_miss",
"MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_store_group",
"MetricName": "tma_store_stlb_hit",
- "MetricThreshold": "tma_store_stlb_hit > 0.05 & (tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))",
+ "MetricThreshold": "tma_store_stlb_hit > 0.05 & tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
"ScaleUnit": "100%"
},
{
@@ -2123,7 +2229,31 @@
"MetricExpr": "DTLB_STORE_MISSES.WALK_ACTIVE / tma_info_core_core_clks",
"MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_store_group",
"MetricName": "tma_store_stlb_miss",
- "MetricThreshold": "tma_store_stlb_miss > 0.05 & (tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))",
+ "MetricThreshold": "tma_store_stlb_miss > 0.05 & tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+ "ScaleUnit": "100%"
+ },
+ {
+ "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 1 GB pages for data store accesses",
+ "MetricExpr": "tma_store_stlb_miss * DTLB_STORE_MISSES.WALK_COMPLETED_1G / (DTLB_STORE_MISSES.WALK_COMPLETED_4K + DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M + DTLB_STORE_MISSES.WALK_COMPLETED_1G)",
+ "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_store_stlb_miss_group",
+ "MetricName": "tma_store_stlb_miss_1g",
+ "MetricThreshold": "tma_store_stlb_miss_1g > 0.05 & tma_store_stlb_miss > 0.05 & tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+ "ScaleUnit": "100%"
+ },
+ {
+ "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 2 or 4 MB pages for data store accesses",
+ "MetricExpr": "tma_store_stlb_miss * DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M / (DTLB_STORE_MISSES.WALK_COMPLETED_4K + DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M + DTLB_STORE_MISSES.WALK_COMPLETED_1G)",
+ "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_store_stlb_miss_group",
+ "MetricName": "tma_store_stlb_miss_2m",
+ "MetricThreshold": "tma_store_stlb_miss_2m > 0.05 & tma_store_stlb_miss > 0.05 & tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+ "ScaleUnit": "100%"
+ },
+ {
+ "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 4 KB pages for data store accesses",
+ "MetricExpr": "tma_store_stlb_miss * DTLB_STORE_MISSES.WALK_COMPLETED_4K / (DTLB_STORE_MISSES.WALK_COMPLETED_4K + DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M + DTLB_STORE_MISSES.WALK_COMPLETED_1G)",
+ "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_store_stlb_miss_group",
+ "MetricName": "tma_store_stlb_miss_4k",
+ "MetricThreshold": "tma_store_stlb_miss_4k > 0.05 & tma_store_stlb_miss > 0.05 & tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
"ScaleUnit": "100%"
},
{
@@ -2131,7 +2261,7 @@
"MetricExpr": "9 * OCR.STREAMING_WR.ANY_RESPONSE / tma_info_thread_clks",
"MetricGroup": "MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_issueSmSt;tma_store_bound_group",
"MetricName": "tma_streaming_stores",
- "MetricThreshold": "tma_streaming_stores > 0.2 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+ "MetricThreshold": "tma_streaming_stores > 0.2 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
"PublicDescription": "This metric estimates how often CPU was stalled due to Streaming store memory accesses; Streaming store optimize out a read request required by RFO stores. Even though store accesses do not typically stall out-of-order CPUs; there are few cases where stores can lead to actual stalls. This metric will be flagged should Streaming stores be a bottleneck. Sample with: OCR.STREAMING_WR.ANY_RESPONSE. Related metrics: tma_fb_full",
"ScaleUnit": "100%"
},
@@ -2140,7 +2270,7 @@
"MetricExpr": "INT_MISC.UNKNOWN_BRANCH_CYCLES / tma_info_thread_clks",
"MetricGroup": "BigFootprint;BvBC;FetchLat;TopdownL4;tma_L4_group;tma_branch_resteers_group",
"MetricName": "tma_unknown_branches",
- "MetricThreshold": "tma_unknown_branches > 0.05 & (tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))",
+ "MetricThreshold": "tma_unknown_branches > 0.05 & tma_branch_resteers > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
"PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to new branch address clears. These are fetched branches the Branch Prediction Unit was unable to recognize (e.g. first time the branch is fetched or hitting BTB capacity limit) hence called Unknown Branches. Sample with: FRONTEND_RETIRED.UNKNOWN_BRANCH",
"ScaleUnit": "100%"
},
@@ -2149,8 +2279,8 @@
"MetricExpr": "tma_retiring * UOPS_EXECUTED.X87 / UOPS_EXECUTED.THREAD",
"MetricGroup": "Compute;TopdownL4;tma_L4_group;tma_fp_arith_group",
"MetricName": "tma_x87_use",
- "MetricThreshold": "tma_x87_use > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6)",
- "PublicDescription": "This metric serves as an approximation of legacy x87 usage. It accounts for instructions beyond X87 FP arithmetic operations; hence may be used as a thermometer to avoid X87 high usage and preferably upgrade to modern ISA. See Tip under Tuning Hint.",
+ "MetricThreshold": "tma_x87_use > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6",
+ "PublicDescription": "This metric serves as an approximation of legacy x87 usage. It accounts for instructions beyond X87 FP arithmetic operations; hence may be used as a thermometer to avoid X87 high usage and preferably upgrade to modern ISA. See Tip under Tuning Hint",
"ScaleUnit": "100%"
},
{
diff --git a/tools/perf/pmu-events/arch/x86/sapphirerapids/uncore-io.json b/tools/perf/pmu-events/arch/x86/sapphirerapids/uncore-io.json
index 91013ced74aa..aab082ff9402 100644
--- a/tools/perf/pmu-events/arch/x86/sapphirerapids/uncore-io.json
+++ b/tools/perf/pmu-events/arch/x86/sapphirerapids/uncore-io.json
@@ -201,7 +201,7 @@
"PerPkg": "1",
"PortMask": "0x0001",
"PublicDescription": "PCIe Completion Buffer Inserts of completions with data : Part 0 : x16 card plugged in to Lane 0/1/2/3, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0",
- "UMask": "0x7001004",
+ "UMask": "0x4",
"Unit": "IIO"
},
{
@@ -214,7 +214,7 @@
"PerPkg": "1",
"PortMask": "0x0002",
"PublicDescription": "PCIe Completion Buffer Inserts of completions with data : Part 1 : x16 card plugged in to Lane 0/1/2/3, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 1",
- "UMask": "0x7002004",
+ "UMask": "0x4",
"Unit": "IIO"
},
{
@@ -227,7 +227,7 @@
"PerPkg": "1",
"PortMask": "0x0004",
"PublicDescription": "PCIe Completion Buffer Inserts of completions with data : Part 2 : x16 card plugged in to Lane 0/1/2/3, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 2",
- "UMask": "0x7004004",
+ "UMask": "0x4",
"Unit": "IIO"
},
{
@@ -240,7 +240,7 @@
"PerPkg": "1",
"PortMask": "0x0008",
"PublicDescription": "PCIe Completion Buffer Inserts of completions with data : Part 2 : x16 card plugged in to Lane 0/1/2/3, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 3",
- "UMask": "0x7008004",
+ "UMask": "0x4",
"Unit": "IIO"
},
{
@@ -253,7 +253,7 @@
"PerPkg": "1",
"PortMask": "0x0010",
"PublicDescription": "PCIe Completion Buffer Inserts of completions with data : Part 0 : x16 card plugged in to Lane 0/1/2/3, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 4",
- "UMask": "0x7010004",
+ "UMask": "0x4",
"Unit": "IIO"
},
{
@@ -266,7 +266,7 @@
"PerPkg": "1",
"PortMask": "0x0020",
"PublicDescription": "PCIe Completion Buffer Inserts of completions with data : Part 1 : x16 card plugged in to Lane 0/1/2/3, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 5",
- "UMask": "0x7020004",
+ "UMask": "0x4",
"Unit": "IIO"
},
{
@@ -279,7 +279,7 @@
"PerPkg": "1",
"PortMask": "0x0040",
"PublicDescription": "PCIe Completion Buffer Inserts of completions with data : Part 2 : x16 card plugged in to Lane 0/1/2/3, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 6",
- "UMask": "0x7040004",
+ "UMask": "0x4",
"Unit": "IIO"
},
{
@@ -292,7 +292,7 @@
"PerPkg": "1",
"PortMask": "0x0080",
"PublicDescription": "PCIe Completion Buffer Inserts of completions with data : Part 2 : x16 card plugged in to Lane 0/1/2/3, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 7",
- "UMask": "0x7080004",
+ "UMask": "0x4",
"Unit": "IIO"
},
{
@@ -316,7 +316,7 @@
"PerPkg": "1",
"PortMask": "0x0000",
"PublicDescription": "x16 card plugged in to stack, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0",
- "UMask": "0x7000001",
+ "UMask": "0x1",
"Unit": "IIO"
},
{
@@ -329,7 +329,7 @@
"PerPkg": "1",
"PortMask": "0x0000",
"PublicDescription": "x4 card is plugged in to slot 1",
- "UMask": "0x7000002",
+ "UMask": "0x2",
"Unit": "IIO"
},
{
@@ -342,7 +342,7 @@
"PerPkg": "1",
"PortMask": "0x0000",
"PublicDescription": "x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 1",
- "UMask": "0x7000004",
+ "UMask": "0x4",
"Unit": "IIO"
},
{
@@ -355,7 +355,7 @@
"PerPkg": "1",
"PortMask": "0x0000",
"PublicDescription": "x4 card is plugged in to slot 3",
- "UMask": "0x7000008",
+ "UMask": "0x8",
"Unit": "IIO"
},
{
@@ -368,7 +368,7 @@
"PerPkg": "1",
"PortMask": "0x0000",
"PublicDescription": "x16 card plugged in to stack, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0",
- "UMask": "0x7000010",
+ "UMask": "0x10",
"Unit": "IIO"
},
{
@@ -381,7 +381,7 @@
"PerPkg": "1",
"PortMask": "0x0000",
"PublicDescription": "x4 card is plugged in to slot 1",
- "UMask": "0x7000020",
+ "UMask": "0x20",
"Unit": "IIO"
},
{
@@ -394,7 +394,7 @@
"PerPkg": "1",
"PortMask": "0x0000",
"PublicDescription": "x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 1",
- "UMask": "0x7000040",
+ "UMask": "0x40",
"Unit": "IIO"
},
{
@@ -407,7 +407,7 @@
"PerPkg": "1",
"PortMask": "0x0000",
"PublicDescription": "x4 card is plugged in to slot 3",
- "UMask": "0x7000080",
+ "UMask": "0x80",
"Unit": "IIO"
},
{
@@ -431,7 +431,7 @@
"PerPkg": "1",
"PortMask": "0x0001",
"PublicDescription": "Data requested by the CPU : Core reading from Card's MMIO space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x16 card plugged in to stack, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0",
- "UMask": "0x7001004",
+ "UMask": "0x4",
"Unit": "IIO"
},
{
@@ -443,7 +443,7 @@
"PerPkg": "1",
"PortMask": "0x0002",
"PublicDescription": "Data requested by the CPU : Core reading from Card's MMIO space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 1",
- "UMask": "0x7002004",
+ "UMask": "0x4",
"Unit": "IIO"
},
{
@@ -455,7 +455,7 @@
"PerPkg": "1",
"PortMask": "0x0004",
"PublicDescription": "Data requested by the CPU : Core reading from Card's MMIO space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 1",
- "UMask": "0x7004004",
+ "UMask": "0x4",
"Unit": "IIO"
},
{
@@ -467,7 +467,7 @@
"PerPkg": "1",
"PortMask": "0x0008",
"PublicDescription": "Data requested by the CPU : Core reading from Card's MMIO space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 3",
- "UMask": "0x7008004",
+ "UMask": "0x4",
"Unit": "IIO"
},
{
@@ -479,7 +479,7 @@
"PerPkg": "1",
"PortMask": "0x0010",
"PublicDescription": "Data requested by the CPU : Core reading from Cards MMIO space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x16 card plugged in to stack, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0",
- "UMask": "0x7010004",
+ "UMask": "0x4",
"Unit": "IIO"
},
{
@@ -491,7 +491,7 @@
"PerPkg": "1",
"PortMask": "0x0020",
"PublicDescription": "Data requested by the CPU : Core reading from Cards MMIO space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 1",
- "UMask": "0x7020004",
+ "UMask": "0x4",
"Unit": "IIO"
},
{
@@ -503,7 +503,7 @@
"PerPkg": "1",
"PortMask": "0x0040",
"PublicDescription": "Data requested by the CPU : Core reading from Cards MMIO space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 1",
- "UMask": "0x7040004",
+ "UMask": "0x4",
"Unit": "IIO"
},
{
@@ -515,7 +515,7 @@
"PerPkg": "1",
"PortMask": "0x0080",
"PublicDescription": "Data requested by the CPU : Core reading from Cards MMIO space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 3",
- "UMask": "0x7080004",
+ "UMask": "0x4",
"Unit": "IIO"
},
{
@@ -662,7 +662,7 @@
"PerPkg": "1",
"PortMask": "0x0001",
"PublicDescription": "Data requested by the CPU : Another card (different IIO stack) reading from this card. : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x16 card plugged in to stack, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0",
- "UMask": "0x7001008",
+ "UMask": "0x8",
"Unit": "IIO"
},
{
@@ -675,7 +675,7 @@
"PerPkg": "1",
"PortMask": "0x0002",
"PublicDescription": "Data requested by the CPU : Another card (different IIO stack) reading from this card. : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 1",
- "UMask": "0x7002008",
+ "UMask": "0x8",
"Unit": "IIO"
},
{
@@ -688,7 +688,7 @@
"PerPkg": "1",
"PortMask": "0x0004",
"PublicDescription": "Data requested by the CPU : Another card (different IIO stack) reading from this card. : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 1",
- "UMask": "0x7004008",
+ "UMask": "0x8",
"Unit": "IIO"
},
{
@@ -701,7 +701,7 @@
"PerPkg": "1",
"PortMask": "0x0008",
"PublicDescription": "Data requested by the CPU : Another card (different IIO stack) reading from this card. : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 3",
- "UMask": "0x7008008",
+ "UMask": "0x8",
"Unit": "IIO"
},
{
@@ -714,7 +714,7 @@
"PerPkg": "1",
"PortMask": "0x0010",
"PublicDescription": "Data requested by the CPU : Another card (different IIO stack) reading from this card. : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x16 card plugged in to stack, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0",
- "UMask": "0x7010008",
+ "UMask": "0x8",
"Unit": "IIO"
},
{
@@ -727,7 +727,7 @@
"PerPkg": "1",
"PortMask": "0x0020",
"PublicDescription": "Data requested by the CPU : Another card (different IIO stack) reading from this card. : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 1",
- "UMask": "0x7020008",
+ "UMask": "0x8",
"Unit": "IIO"
},
{
@@ -740,7 +740,7 @@
"PerPkg": "1",
"PortMask": "0x0040",
"PublicDescription": "Data requested by the CPU : Another card (different IIO stack) reading from this card. : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 1",
- "UMask": "0x7040008",
+ "UMask": "0x8",
"Unit": "IIO"
},
{
@@ -753,7 +753,7 @@
"PerPkg": "1",
"PortMask": "0x0080",
"PublicDescription": "Data requested by the CPU : Another card (different IIO stack) reading from this card. : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 3",
- "UMask": "0x7080008",
+ "UMask": "0x8",
"Unit": "IIO"
},
{
@@ -766,7 +766,7 @@
"PerPkg": "1",
"PortMask": "0x0001",
"PublicDescription": "Data requested by the CPU : Another card (different IIO stack) writing to this card. : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x16 card plugged in to stack, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0",
- "UMask": "0x7001002",
+ "UMask": "0x2",
"Unit": "IIO"
},
{
@@ -779,7 +779,7 @@
"PerPkg": "1",
"PortMask": "0x0002",
"PublicDescription": "Data requested by the CPU : Another card (different IIO stack) writing to this card. : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 1",
- "UMask": "0x7002002",
+ "UMask": "0x2",
"Unit": "IIO"
},
{
@@ -792,7 +792,7 @@
"PerPkg": "1",
"PortMask": "0x0004",
"PublicDescription": "Data requested by the CPU : Another card (different IIO stack) writing to this card. : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 1",
- "UMask": "0x7004002",
+ "UMask": "0x2",
"Unit": "IIO"
},
{
@@ -805,7 +805,7 @@
"PerPkg": "1",
"PortMask": "0x0008",
"PublicDescription": "Data requested by the CPU : Another card (different IIO stack) writing to this card. : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 3",
- "UMask": "0x7008002",
+ "UMask": "0x2",
"Unit": "IIO"
},
{
@@ -818,7 +818,7 @@
"PerPkg": "1",
"PortMask": "0x0010",
"PublicDescription": "Data requested by the CPU : Another card (different IIO stack) writing to this card. : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x16 card plugged in to stack, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0",
- "UMask": "0x7010002",
+ "UMask": "0x2",
"Unit": "IIO"
},
{
@@ -831,7 +831,7 @@
"PerPkg": "1",
"PortMask": "0x0020",
"PublicDescription": "Data requested by the CPU : Another card (different IIO stack) writing to this card. : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 1",
- "UMask": "0x7020002",
+ "UMask": "0x2",
"Unit": "IIO"
},
{
@@ -844,7 +844,7 @@
"PerPkg": "1",
"PortMask": "0x0040",
"PublicDescription": "Data requested by the CPU : Another card (different IIO stack) writing to this card. : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 1",
- "UMask": "0x7040002",
+ "UMask": "0x2",
"Unit": "IIO"
},
{
@@ -857,7 +857,7 @@
"PerPkg": "1",
"PortMask": "0x0080",
"PublicDescription": "Data requested by the CPU : Another card (different IIO stack) writing to this card. : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 3",
- "UMask": "0x7080002",
+ "UMask": "0x2",
"Unit": "IIO"
},
{
@@ -974,7 +974,6 @@
"Counter": "0,1",
"EventCode": "0x83",
"EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.ALL_PARTS",
- "Experimental": "1",
"FCMask": "0x07",
"PerPkg": "1",
"PortMask": "0x00ff",
@@ -1082,7 +1081,6 @@
"Counter": "0,1",
"EventCode": "0x83",
"EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.ALL_PARTS",
- "Experimental": "1",
"FCMask": "0x07",
"PerPkg": "1",
"PortMask": "0x00ff",
@@ -1299,7 +1297,7 @@
"PerPkg": "1",
"PortMask": "0x00FF",
"PublicDescription": "Incoming arbitration requests : Passing data to be written : How often different queues (e.g. channel / fc) ask to send request into pipeline : Only for posted requests",
- "UMask": "0x70ff020",
+ "UMask": "0x20",
"Unit": "IIO"
},
{
@@ -1351,7 +1349,7 @@
"PerPkg": "1",
"PortMask": "0x00FF",
"PublicDescription": "Incoming arbitration requests : Request Ownership : How often different queues (e.g. channel / fc) ask to send request into pipeline : Only for posted requests",
- "UMask": "0x70ff004",
+ "UMask": "0x4",
"Unit": "IIO"
},
{
@@ -1364,7 +1362,7 @@
"PerPkg": "1",
"PortMask": "0x00FF",
"PublicDescription": "Incoming arbitration requests : Writing line : How often different queues (e.g. channel / fc) ask to send request into pipeline : Only for posted requests",
- "UMask": "0x70ff010",
+ "UMask": "0x10",
"Unit": "IIO"
},
{
@@ -1377,7 +1375,7 @@
"PerPkg": "1",
"PortMask": "0x00FF",
"PublicDescription": "Incoming arbitration requests granted : Passing data to be written : How often different queues (e.g. channel / fc) are allowed to send request into pipeline : Only for posted requests",
- "UMask": "0x70ff020",
+ "UMask": "0x20",
"Unit": "IIO"
},
{
@@ -1390,7 +1388,7 @@
"PerPkg": "1",
"PortMask": "0x00FF",
"PublicDescription": "Incoming arbitration requests granted : Issuing final read or write of line : How often different queues (e.g. channel / fc) are allowed to send request into pipeline",
- "UMask": "0x70ff008",
+ "UMask": "0x8",
"Unit": "IIO"
},
{
@@ -1403,7 +1401,7 @@
"PerPkg": "1",
"PortMask": "0x00FF",
"PublicDescription": "Incoming arbitration requests granted : Processing response from IOMMU : How often different queues (e.g. channel / fc) are allowed to send request into pipeline",
- "UMask": "0x70ff002",
+ "UMask": "0x2",
"Unit": "IIO"
},
{
@@ -1416,7 +1414,7 @@
"PerPkg": "1",
"PortMask": "0x00FF",
"PublicDescription": "Incoming arbitration requests granted : Issuing to IOMMU : How often different queues (e.g. channel / fc) are allowed to send request into pipeline",
- "UMask": "0x70ff001",
+ "UMask": "0x1",
"Unit": "IIO"
},
{
@@ -1429,7 +1427,7 @@
"PerPkg": "1",
"PortMask": "0x00FF",
"PublicDescription": "Incoming arbitration requests granted : Request Ownership : How often different queues (e.g. channel / fc) are allowed to send request into pipeline : Only for posted requests",
- "UMask": "0x70ff004",
+ "UMask": "0x4",
"Unit": "IIO"
},
{
@@ -1442,7 +1440,7 @@
"PerPkg": "1",
"PortMask": "0x00FF",
"PublicDescription": "Incoming arbitration requests granted : Writing line : How often different queues (e.g. channel / fc) are allowed to send request into pipeline : Only for posted requests",
- "UMask": "0x70ff010",
+ "UMask": "0x10",
"Unit": "IIO"
},
{
@@ -1962,7 +1960,7 @@
"PerPkg": "1",
"PortMask": "0x00FF",
"PublicDescription": "Request Ownership : PCIe Request complete : Only for posted requests : Each PCIe request is broken down into a series of cacheline granular requests and each cacheline size request may need to make multiple passes through the pipeline (e.g. for posted interrupts or multi-cast). Each time a single PCIe request completes all its cacheline granular requests, it advances pointer.",
- "UMask": "0x70ff020",
+ "UMask": "0x20",
"Unit": "IIO"
},
{
@@ -1975,7 +1973,7 @@
"PerPkg": "1",
"PortMask": "0x00FF",
"PublicDescription": "Request Ownership : Writing line : Only for posted requests : Only for posted requests",
- "UMask": "0x70ff008",
+ "UMask": "0x8",
"Unit": "IIO"
},
{
@@ -1988,7 +1986,7 @@
"PerPkg": "1",
"PortMask": "0x00FF",
"PublicDescription": "Request Ownership : Issuing final read or write of line : Only for posted requests",
- "UMask": "0x70ff004",
+ "UMask": "0x4",
"Unit": "IIO"
},
{
@@ -2001,7 +1999,7 @@
"PerPkg": "1",
"PortMask": "0x00FF",
"PublicDescription": "Request Ownership : Passing data to be written : Only for posted requests : Only for posted requests",
- "UMask": "0x70ff010",
+ "UMask": "0x10",
"Unit": "IIO"
},
{
@@ -2014,7 +2012,7 @@
"PerPkg": "1",
"PortMask": "0x00FF",
"PublicDescription": "Processing response from IOMMU : Passing data to be written : Only for posted requests",
- "UMask": "0x70ff008",
+ "UMask": "0x8",
"Unit": "IIO"
},
{
@@ -2026,7 +2024,7 @@
"FCMask": "0x07",
"PerPkg": "1",
"PortMask": "0x00FF",
- "UMask": "0x70ff002",
+ "UMask": "0x2",
"Unit": "IIO"
},
{
@@ -2039,7 +2037,7 @@
"PerPkg": "1",
"PortMask": "0x00FF",
"PublicDescription": "Processing response from IOMMU : Request Ownership : Only for posted requests",
- "UMask": "0x70ff001",
+ "UMask": "0x1",
"Unit": "IIO"
},
{
@@ -2052,7 +2050,7 @@
"PerPkg": "1",
"PortMask": "0x00FF",
"PublicDescription": "Processing response from IOMMU : Writing line : Only for posted requests",
- "UMask": "0x70ff004",
+ "UMask": "0x4",
"Unit": "IIO"
},
{
@@ -2065,7 +2063,7 @@
"PerPkg": "1",
"PortMask": "0x00FF",
"PublicDescription": "PCIe Request - pass complete : Passing data to be written : Each PCIe request is broken down into a series of cacheline granular requests and each cacheline size request may need to make multiple passes through the pipeline (e.g. for posted interrupts or multi-cast). Each time a cacheline completes a single pass (e.g. posts a write to single multi-cast target) it advances state : Only for posted requests",
- "UMask": "0x70ff020",
+ "UMask": "0x20",
"Unit": "IIO"
},
{
@@ -2091,7 +2089,7 @@
"PerPkg": "1",
"PortMask": "0x00FF",
"PublicDescription": "PCIe Request - pass complete : Request Ownership : Each PCIe request is broken down into a series of cacheline granular requests and each cacheline size request may need to make multiple passes through the pipeline (e.g. for posted interrupts or multi-cast). Each time a cacheline completes a single pass (e.g. posts a write to single multi-cast target) it advances state : Only for posted requests",
- "UMask": "0x70ff004",
+ "UMask": "0x4",
"Unit": "IIO"
},
{
@@ -2104,7 +2102,7 @@
"PerPkg": "1",
"PortMask": "0x00FF",
"PublicDescription": "PCIe Request - pass complete : Writing line : Each PCIe request is broken down into a series of cacheline granular requests and each cacheline size request may need to make multiple passes through the pipeline (e.g. for posted interrupts or multi-cast). Each time a cacheline completes a single pass (e.g. posts a write to single multi-cast target) it advances state : Only for posted requests",
- "UMask": "0x70ff010",
+ "UMask": "0x10",
"Unit": "IIO"
},
{
@@ -2309,7 +2307,7 @@
"PerPkg": "1",
"PortMask": "0x0001",
"PublicDescription": "Number Transactions requested by the CPU : Another card (different IIO stack) writing to this card. : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x16 card plugged in to Lane 0/1/2/3, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0",
- "UMask": "0x7001002",
+ "UMask": "0x2",
"Unit": "IIO"
},
{
@@ -2322,7 +2320,7 @@
"PerPkg": "1",
"PortMask": "0x0002",
"PublicDescription": "Number Transactions requested by the CPU : Another card (different IIO stack) writing to this card. : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 1",
- "UMask": "0x7002002",
+ "UMask": "0x2",
"Unit": "IIO"
},
{
@@ -2335,7 +2333,7 @@
"PerPkg": "1",
"PortMask": "0x0004",
"PublicDescription": "Number Transactions requested by the CPU : Another card (different IIO stack) writing to this card. : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 2",
- "UMask": "0x7004002",
+ "UMask": "0x2",
"Unit": "IIO"
},
{
@@ -2348,7 +2346,7 @@
"PerPkg": "1",
"PortMask": "0x0008",
"PublicDescription": "Number Transactions requested by the CPU : Another card (different IIO stack) writing to this card. : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 3",
- "UMask": "0x7008002",
+ "UMask": "0x2",
"Unit": "IIO"
},
{
@@ -2361,7 +2359,7 @@
"PerPkg": "1",
"PortMask": "0x0010",
"PublicDescription": "Number Transactions requested by the CPU : Another card (different IIO stack) writing to this card. : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x16 card plugged in to Lane 4/5/6/7, Or x8 card plugged in to Lane 4/5, Or x4 card is plugged in to slot 4",
- "UMask": "0x7010002",
+ "UMask": "0x2",
"Unit": "IIO"
},
{
@@ -2374,7 +2372,7 @@
"PerPkg": "1",
"PortMask": "0x0020",
"PublicDescription": "Number Transactions requested by the CPU : Another card (different IIO stack) writing to this card. : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 5",
- "UMask": "0x7020002",
+ "UMask": "0x2",
"Unit": "IIO"
},
{
@@ -2387,7 +2385,7 @@
"PerPkg": "1",
"PortMask": "0x0040",
"PublicDescription": "Number Transactions requested by the CPU : Another card (different IIO stack) writing to this card. : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x8 card plugged in to Lane 6/7, Or x4 card is plugged in to slot 6",
- "UMask": "0x7040002",
+ "UMask": "0x2",
"Unit": "IIO"
},
{
@@ -2400,7 +2398,7 @@
"PerPkg": "1",
"PortMask": "0x0080",
"PublicDescription": "Number Transactions requested by the CPU : Another card (different IIO stack) writing to this card. : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 7",
- "UMask": "0x7080002",
+ "UMask": "0x2",
"Unit": "IIO"
},
{
--
2.47.1.545.g3c1d2e2a6a-goog© 2016 - 2024 Red Hat, Inc.