mirrors/linux
1
0
Fork 0
mirror of https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git synced 2026-05-01 04:53:09 -04:00
Code Issues Packages Projects Releases Wiki Activity

perf vendor events: Update/add Graniterapids events/metrics

Browse Source 
Update events from v1.02 to v1.06.
Add TMA metrics 5.02.

Bring in the event updates v1.06:
de5502e51a
79b9e512ea
bc74a895e4

The TMA 5.02 addition is from (with subsequent fixes):
1d72913b2d

Update uncore IIO events umask with the change:
d78e8a1665
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-developed-by: Caleb Biggers <caleb.biggers@intel.com>
Signed-off-by: Caleb Biggers <caleb.biggers@intel.com>
Signed-off-by: Ian Rogers <irogers@google.com>
Acked-by: Kan Liang <kan.liang@linux.intel.com>
Tested-by: Thomas Falcon <thomas.falcon@intel.com>
Link: https://lore.kernel.org/r/20250211213031.114209-12-irogers@google.com
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
This commit is contained in:
Ian Rogers
2025-02-11 13:30:18 -08:00
committed by Namhyung Kim
parent b52c4123a5
commit aaa73d778b
15 changed files with 3294 additions and 263 deletions
Download Patch File Download Diff File Expand all files Collapse all files

130
tools/perf/pmu-events/arch/x86/graniterapids/cache.json
View File

@@ -83,11 +83,11 @@
"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"
},
@@ -320,7 +320,6 @@
"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"
@@ -331,7 +330,6 @@
"Data_LA": "1",
"EventCode": "0xd0",
"EventName": "MEM_INST_RETIRED.ALL_STORES",
"PEBS": "1",
"PublicDescription": "Counts all retired store instructions.",
"SampleAfterValue": "1000003",
"UMask": "0x82"
@@ -342,7 +340,6 @@
"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"
@@ -353,7 +350,6 @@
"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"
@@ -364,7 +360,6 @@
"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"
@@ -375,7 +370,6 @@
"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"
@@ -386,7 +380,6 @@
"Data_LA": "1",
"EventCode": "0xd0",
"EventName": "MEM_INST_RETIRED.STLB_HIT_LOADS",
"PEBS": "1",
"PublicDescription": "Number of retired load instructions with a clean hit in the 2nd-level TLB (STLB).",
"SampleAfterValue": "100003",
"UMask": "0x9"
@@ -397,7 +390,6 @@
"Data_LA": "1",
"EventCode": "0xd0",
"EventName": "MEM_INST_RETIRED.STLB_HIT_STORES",
"PEBS": "1",
"PublicDescription": "Number of retired store instructions that hit in the 2nd-level TLB (STLB).",
"SampleAfterValue": "100003",
"UMask": "0xa"
@@ -408,7 +400,6 @@
"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"
@@ -419,7 +410,6 @@
"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"
@@ -439,7 +429,6 @@
"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"
@@ -450,7 +439,6 @@
"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"
@@ -461,7 +449,6 @@
"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"
@@ -472,7 +459,6 @@
"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"
@@ -483,7 +469,6 @@
"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"
@@ -494,7 +479,6 @@
"Data_LA": "1",
"EventCode": "0xd3",
"EventName": "MEM_LOAD_L3_MISS_RETIRED.REMOTE_DRAM",
"PEBS": "1",
"SampleAfterValue": "1000003",
"UMask": "0x2"
},
@@ -504,7 +488,6 @@
"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"
@@ -515,7 +498,6 @@
"Data_LA": "1",
"EventCode": "0xd3",
"EventName": "MEM_LOAD_L3_MISS_RETIRED.REMOTE_HITM",
"PEBS": "1",
"SampleAfterValue": "1000003",
"UMask": "0x4"
},
@@ -525,7 +507,6 @@
"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"
@@ -536,7 +517,6 @@
"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"
@@ -547,7 +527,6 @@
"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"
@@ -558,7 +537,6 @@
"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"
@@ -569,7 +547,6 @@
"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"
@@ -580,7 +557,6 @@
"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"
@@ -591,7 +567,6 @@
"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"
@@ -602,7 +577,6 @@
"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"
@@ -664,6 +638,16 @@
"SampleAfterValue": "100003",
"UMask": "0x1"
},
{
"BriefDescription": "Counts demand data reads that resulted in a snoop that hit in another core, which did not forward the data.",
"Counter": "0,1,2,3",
"EventCode": "0x2A,0x2B",
"EventName": "OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_NO_FWD",
"MSRIndex": "0x1a6,0x1a7",
"MSRValue": "0x4003C0001",
"SampleAfterValue": "100003",
"UMask": "0x1"
},
{
"BriefDescription": "Counts demand data reads that resulted in a snoop hit in another core's caches which forwarded the unmodified data to the requesting core.",
"Counter": "0,1,2,3",
@@ -674,6 +658,26 @@
"SampleAfterValue": "100003",
"UMask": "0x1"
},
{
"BriefDescription": "Counts demand data reads that were supplied by a cache on a remote socket where a snoop hit a modified line in another core's caches which forwarded the data.",
"Counter": "0,1,2,3",
"EventCode": "0x2A,0x2B",
"EventName": "OCR.DEMAND_DATA_RD.REMOTE_CACHE.SNOOP_HITM",
"MSRIndex": "0x1a6,0x1a7",
"MSRValue": "0x1030000001",
"SampleAfterValue": "100003",
"UMask": "0x1"
},
{
"BriefDescription": "Counts demand data reads that were supplied by a cache on a remote socket where a snoop hit in another core's caches which forwarded the unmodified data to the requesting core.",
"Counter": "0,1,2,3",
"EventCode": "0x2A,0x2B",
"EventName": "OCR.DEMAND_DATA_RD.REMOTE_CACHE.SNOOP_HIT_WITH_FWD",
"MSRIndex": "0x1a6,0x1a7",
"MSRValue": "0x830000001",
"SampleAfterValue": "100003",
"UMask": "0x1"
},
{
"BriefDescription": "Counts demand reads for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that hit in the L3 or were snooped from another core's caches on the same socket.",
"Counter": "0,1,2,3",
@@ -704,6 +708,76 @@
"SampleAfterValue": "100003",
"UMask": "0x1"
},
{
"BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that resulted in a snoop hit a modified line in another core's caches which forwarded the data.",
"Counter": "0,1,2,3",
"EventCode": "0x2A,0x2B",
"EventName": "OCR.READS_TO_CORE.L3_HIT.SNOOP_HITM",
"MSRIndex": "0x1a6,0x1a7",
"MSRValue": "0x10003C4477",
"SampleAfterValue": "100003",
"UMask": "0x1"
},
{
"BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by a cache on a remote socket where a snoop was sent and data was returned (Modified or Not Modified).",
"Counter": "0,1,2,3",
"EventCode": "0x2A,0x2B",
"EventName": "OCR.READS_TO_CORE.REMOTE_CACHE.SNOOP_FWD",
"MSRIndex": "0x1a6,0x1a7",
"MSRValue": "0x1830004477",
"SampleAfterValue": "100003",
"UMask": "0x1"
},
{
"BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by a cache on a remote socket where a snoop hit a modified line in another core's caches which forwarded the data.",
"Counter": "0,1,2,3",
"EventCode": "0x2A,0x2B",
"EventName": "OCR.READS_TO_CORE.REMOTE_CACHE.SNOOP_HITM",
"MSRIndex": "0x1a6,0x1a7",
"MSRValue": "0x1030004477",
"SampleAfterValue": "100003",
"UMask": "0x1"
},
{
"BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by a cache on a remote socket where a snoop hit in another core's caches which forwarded the unmodified data to the requesting core.",
"Counter": "0,1,2,3",
"EventCode": "0x2A,0x2B",
"EventName": "OCR.READS_TO_CORE.REMOTE_CACHE.SNOOP_HIT_WITH_FWD",
"MSRIndex": "0x1a6,0x1a7",
"MSRValue": "0x830004477",
"SampleAfterValue": "100003",
"UMask": "0x1"
},
{
"BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that hit a modified line in a distant L3 Cache or were snooped from a distant core's L1/L2 caches on this socket when the system is in SNC (sub-NUMA cluster) mode.",
"Counter": "0,1,2,3",
"EventCode": "0x2A,0x2B",
"EventName": "OCR.READS_TO_CORE.SNC_CACHE.HITM",
"MSRIndex": "0x1a6,0x1a7",
"MSRValue": "0x1008004477",
"SampleAfterValue": "100003",
"UMask": "0x1"
},
{
"BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that either hit a non-modified line in a distant L3 Cache or were snooped from a distant core's L1/L2 caches on this socket when the system is in SNC (sub-NUMA cluster) mode.",
"Counter": "0,1,2,3",
"EventCode": "0x2A,0x2B",
"EventName": "OCR.READS_TO_CORE.SNC_CACHE.HIT_WITH_FWD",
"MSRIndex": "0x1a6,0x1a7",
"MSRValue": "0x808004477",
"SampleAfterValue": "100003",
"UMask": "0x1"
},
{
"BriefDescription": "Counts demand reads for ownership (RFO), hardware prefetch RFOs (which bring data to L2), and software prefetches for exclusive ownership (PREFETCHW) that hit to a (M)odified cacheline in the L3 or snoop filter.",
"Counter": "0,1,2,3",
"EventCode": "0x2A,0x2B",
"EventName": "OCR.RFO_TO_CORE.L3_HIT_M",
"MSRIndex": "0x1a6,0x1a7",
"MSRValue": "0x1F80040022",
"SampleAfterValue": "100003",
"UMask": "0x1"
},
{
"BriefDescription": "Any memory transaction that reached the SQ.",
"Counter": "0,1,2,3",

24
tools/perf/pmu-events/arch/x86/graniterapids/counter.json
View File

@@ -19,6 +19,16 @@
"CountersNumFixed": "0",
"CountersNumGeneric": "4"
},
{
"Unit": "CXLCM",
"CountersNumFixed": "0",
"CountersNumGeneric": 8
},
{
"Unit": "CXLDP",
"CountersNumFixed": "0",
"CountersNumGeneric": 4
},
{
"Unit": "B2HOT",
"CountersNumFixed": "0",
@@ -52,26 +62,16 @@
{
"Unit": "PCU",
"CountersNumFixed": "0",
"CountersNumGeneric": 4
"CountersNumGeneric": "4"
},
{
"Unit": "CHACMS",
"CountersNumFixed": "0",
"CountersNumGeneric": 4
"CountersNumGeneric": "4"
},
{
"Unit": "MDF",
"CountersNumFixed": "0",
"CountersNumGeneric": "4"
},
{
"Unit": "CXLCM",
"CountersNumFixed": "0",
"CountersNumGeneric": 8
},
{
"Unit": "CXLDP",
"CountersNumFixed": "0",
"CountersNumGeneric": 4
}
]

24
tools/perf/pmu-events/arch/x86/graniterapids/frontend.json
View File

@@ -41,7 +41,6 @@
"EventName": "FRONTEND_RETIRED.ANY_ANT",
"MSRIndex": "0x3F7",
"MSRValue": "0x9",
"PEBS": "1",
"PublicDescription": "Always Not Taken (ANT) conditional retired branches (no BTB entry and not mispredicted)",
"SampleAfterValue": "100007",
"UMask": "0x3"
@@ -53,7 +52,6 @@
"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": "0x3"
@@ -65,7 +63,6 @@
"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": "0x3"
@@ -77,7 +74,6 @@
"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": "0x3"
@@ -89,7 +85,6 @@
"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": "0x3"
@@ -101,7 +96,6 @@
"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": "0x3"
@@ -113,7 +107,6 @@
"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": "0x3"
@@ -125,7 +118,6 @@
"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": "0x3"
@@ -137,7 +129,6 @@
"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": "0x3"
@@ -149,7 +140,6 @@
"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": "0x3"
@@ -161,7 +151,6 @@
"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": "0x3"
@@ -173,7 +162,6 @@
"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": "0x3"
@@ -185,7 +173,6 @@
"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": "0x3"
@@ -197,7 +184,6 @@
"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": "0x3"
@@ -209,7 +195,6 @@
"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": "0x3"
@@ -221,7 +206,6 @@
"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": "0x3"
@@ -233,7 +217,6 @@
"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": "0x3"
@@ -244,8 +227,7 @@
"EventCode": "0xc6",
"EventName": "FRONTEND_RETIRED.LATE_SWPF",
"MSRIndex": "0x3F7",
"MSRValue": "0x9",
"PEBS": "1",
"MSRValue": "0xA",
"PublicDescription": "Number of Instruction Cache demand miss in shadow of an on-going i-fetch cache-line triggered by PREFETCHIT0/1 instructions",
"SampleAfterValue": "100007",
"UMask": "0x3"
@@ -257,7 +239,6 @@
"EventName": "FRONTEND_RETIRED.MISP_ANT",
"MSRIndex": "0x3F7",
"MSRValue": "0x9",
"PEBS": "1",
"PublicDescription": "ANT retired branches that got just mispredicted",
"SampleAfterValue": "100007",
"UMask": "0x2"
@@ -269,7 +250,6 @@
"EventName": "FRONTEND_RETIRED.MS_FLOWS",
"MSRIndex": "0x3F7",
"MSRValue": "0x8",
"PEBS": "1",
"SampleAfterValue": "100007",
"UMask": "0x3"
},
@@ -280,7 +260,6 @@
"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": "0x3"
@@ -292,7 +271,6 @@
"EventName": "FRONTEND_RETIRED.UNKNOWN_BRANCH",
"MSRIndex": "0x3F7",
"MSRValue": "0x17",
"PEBS": "1",
"SampleAfterValue": "100007",
"UMask": "0x3"
},

2325
tools/perf/pmu-events/arch/x86/graniterapids/gnr-metrics.json Normal file
View File

File diff suppressed because it is too large Load Diff

121
tools/perf/pmu-events/arch/x86/graniterapids/memory.json
View File

@@ -72,7 +72,6 @@
"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"
@@ -85,7 +84,6 @@
"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"
@@ -98,7 +96,6 @@
"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"
@@ -111,7 +108,6 @@
"EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_2048",
"MSRIndex": "0x3F6",
"MSRValue": "0x800",
"PEBS": "2",
"PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 2048 cycles. Reported latency may be longer than just the memory latency.",
"SampleAfterValue": "23",
"UMask": "0x1"
@@ -124,7 +120,6 @@
"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"
@@ -137,7 +132,6 @@
"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"
@@ -150,7 +144,6 @@
"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"
@@ -163,7 +156,6 @@
"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"
@@ -176,7 +168,6 @@
"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"
@@ -189,7 +180,6 @@
"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"
@@ -200,7 +190,6 @@
"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"
@@ -245,6 +234,26 @@
"SampleAfterValue": "100003",
"UMask": "0x1"
},
{
"BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were not supplied by the local socket's L1, L2, or L3 caches and the cacheline is homed locally.",
"Counter": "0,1,2,3",
"EventCode": "0x2A,0x2B",
"EventName": "OCR.READS_TO_CORE.L3_MISS_LOCAL",
"MSRIndex": "0x1a6,0x1a7",
"MSRValue": "0x3F04C04477",
"SampleAfterValue": "100003",
"UMask": "0x1"
},
{
"BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that missed the L3 Cache and were supplied by the local socket (DRAM or PMM), whether or not in Sub NUMA Cluster(SNC) Mode. In SNC Mode counts PMM or DRAM accesses that are controlled by the close or distant SNC Cluster. It does not count misses to the L3 which go to Local CXL Type 2 Memory or Local Non DRAM.",
"Counter": "0,1,2,3",
"EventCode": "0x2A,0x2B",
"EventName": "OCR.READS_TO_CORE.L3_MISS_LOCAL_SOCKET",
"MSRIndex": "0x1a6,0x1a7",
"MSRValue": "0x70CC04477",
"SampleAfterValue": "100003",
"UMask": "0x1"
},
{
"BriefDescription": "Counts demand data read requests that miss the L3 cache.",
"Counter": "0,1,2,3",
@@ -271,5 +280,95 @@
"PublicDescription": "For every cycle, increments by the number of demand data read requests pending that are known to have missed the L3 cache. Note that this does not capture all elapsed cycles while requests are outstanding - only cycles from when the requests were known by the requesting core to have missed the L3 cache.",
"SampleAfterValue": "2000003",
"UMask": "0x10"
},
{
"BriefDescription": "Number of times an RTM execution aborted.",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc9",
"EventName": "RTM_RETIRED.ABORTED",
"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 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 3 categories (e.g. interrupt).",
"SampleAfterValue": "100003",
"UMask": "0x80"
},
{
"BriefDescription": "Number of times an RTM execution aborted due to various memory events (e.g. read/write capacity and conflicts)",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc9",
"EventName": "RTM_RETIRED.ABORTED_MEM",
"PublicDescription": "Counts the number of times an RTM execution aborted due to various memory events (e.g. read/write capacity and conflicts).",
"SampleAfterValue": "100003",
"UMask": "0x8"
},
{
"BriefDescription": "Number of times an RTM execution aborted due to incompatible memory type",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc9",
"EventName": "RTM_RETIRED.ABORTED_MEMTYPE",
"PublicDescription": "Counts the number of times an RTM execution aborted due to incompatible memory type.",
"SampleAfterValue": "100003",
"UMask": "0x40"
},
{
"BriefDescription": "Number of times an RTM execution aborted due to HLE-unfriendly instructions",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc9",
"EventName": "RTM_RETIRED.ABORTED_UNFRIENDLY",
"PublicDescription": "Counts the number of times an RTM execution aborted due to HLE-unfriendly instructions.",
"SampleAfterValue": "100003",
"UMask": "0x20"
},
{
"BriefDescription": "Number of times an RTM execution successfully committed",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc9",
"EventName": "RTM_RETIRED.COMMIT",
"PublicDescription": "Counts the number of times RTM commit succeeded.",
"SampleAfterValue": "100003",
"UMask": "0x2"
},
{
"BriefDescription": "Number of times an RTM execution started.",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc9",
"EventName": "RTM_RETIRED.START",
"PublicDescription": "Counts the number of times we entered an RTM region. Does not count nested transactions.",
"SampleAfterValue": "100003",
"UMask": "0x1"
},
{
"BriefDescription": "Speculatively counts the number of TSX aborts due to a data capacity limitation for transactional reads",
"Counter": "0,1,2,3",
"EventCode": "0x54",
"EventName": "TX_MEM.ABORT_CAPACITY_READ",
"PublicDescription": "Speculatively counts the number of Transactional Synchronization Extensions (TSX) aborts due to a data capacity limitation for transactional reads",
"SampleAfterValue": "100003",
"UMask": "0x80"
},
{
"BriefDescription": "Speculatively counts the number of TSX aborts due to a data capacity limitation for transactional writes.",
"Counter": "0,1,2,3",
"EventCode": "0x54",
"EventName": "TX_MEM.ABORT_CAPACITY_WRITE",
"PublicDescription": "Speculatively counts the number of Transactional Synchronization Extensions (TSX) aborts due to a data capacity limitation for transactional writes.",
"SampleAfterValue": "100003",
"UMask": "0x2"
},
{
"BriefDescription": "Number of times a transactional abort was signaled due to a data conflict on a transactionally accessed address",
"Counter": "0,1,2,3",
"EventCode": "0x54",
"EventName": "TX_MEM.ABORT_CONFLICT",
"PublicDescription": "Counts the number of times a TSX line had a cache conflict.",
"SampleAfterValue": "100003",
"UMask": "0x1"
}
]

145
tools/perf/pmu-events/arch/x86/graniterapids/metricgroups.json Normal file
View File

@@ -0,0 +1,145 @@
{
"Backend": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
"Bad": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
"BadSpec": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
"BigFootprint": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
"BrMispredicts": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
"Branches": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
"BvBC": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
"BvBO": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
"BvCB": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
"BvFB": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
"BvIO": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
"BvMB": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
"BvML": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
"BvMP": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
"BvMS": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
"BvMT": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
"BvOB": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
"BvUW": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
"C0Wait": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
"CacheHits": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
"CacheMisses": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
"CodeGen": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
"Compute": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
"Cor": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
"DSB": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
"DSBmiss": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
"DataSharing": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
"Fed": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
"FetchBW": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
"FetchLat": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
"Flops": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
"FpScalar": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
"FpVector": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
"Frontend": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
"HPC": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
"IcMiss": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
"InsType": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
"IntVector": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
"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",
"MemOffcore": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
"MemoryBW": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
"MemoryBound": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
"MemoryLat": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
"MemoryTLB": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
"Memory_BW": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
"Memory_Lat": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
"MicroSeq": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
"OS": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
"Offcore": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
"PGO": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
"Pipeline": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
"PortsUtil": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
"Power": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
"Prefetches": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
"Ret": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
"Retire": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
"SMT": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
"Server": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
"Snoop": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
"SoC": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
"Summary": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
"TmaL1": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
"TmaL2": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
"TmaL3mem": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
"TopdownL1": "Metrics for top-down breakdown at level 1",
"TopdownL2": "Metrics for top-down breakdown at level 2",
"TopdownL3": "Metrics for top-down breakdown at level 3",
"TopdownL4": "Metrics for top-down breakdown at level 4",
"TopdownL5": "Metrics for top-down breakdown at level 5",
"TopdownL6": "Metrics for top-down breakdown at level 6",
"tma_L1_group": "Metrics for top-down breakdown at level 1",
"tma_L2_group": "Metrics for top-down breakdown at level 2",
"tma_L3_group": "Metrics for top-down breakdown at level 3",
"tma_L4_group": "Metrics for top-down breakdown at level 4",
"tma_L5_group": "Metrics for top-down breakdown at level 5",
"tma_L6_group": "Metrics for top-down breakdown at level 6",
"tma_alu_op_utilization_group": "Metrics contributing to tma_alu_op_utilization category",
"tma_assists_group": "Metrics contributing to tma_assists category",
"tma_backend_bound_group": "Metrics contributing to tma_backend_bound category",
"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",
"tma_fetch_bandwidth_group": "Metrics contributing to tma_fetch_bandwidth category",
"tma_fetch_latency_group": "Metrics contributing to tma_fetch_latency category",
"tma_fp_arith_group": "Metrics contributing to tma_fp_arith category",
"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",
"tma_issueBW": "Metrics related by the issue $issueBW",
"tma_issueComp": "Metrics related by the issue $issueComp",
"tma_issueD0": "Metrics related by the issue $issueD0",
"tma_issueFB": "Metrics related by the issue $issueFB",
"tma_issueFL": "Metrics related by the issue $issueFL",
"tma_issueL1": "Metrics related by the issue $issueL1",
"tma_issueLat": "Metrics related by the issue $issueLat",
"tma_issueMC": "Metrics related by the issue $issueMC",
"tma_issueMS": "Metrics related by the issue $issueMS",
"tma_issueMV": "Metrics related by the issue $issueMV",
"tma_issueRFO": "Metrics related by the issue $issueRFO",
"tma_issueSL": "Metrics related by the issue $issueSL",
"tma_issueSO": "Metrics related by the issue $issueSO",
"tma_issueSmSt": "Metrics related by the issue $issueSmSt",
"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",
"tma_memory_bound_group": "Metrics contributing to tma_memory_bound category",
"tma_microcode_sequencer_group": "Metrics contributing to tma_microcode_sequencer category",
"tma_mite_group": "Metrics contributing to tma_mite category",
"tma_other_light_ops_group": "Metrics contributing to tma_other_light_ops category",
"tma_ports_utilization_group": "Metrics contributing to tma_ports_utilization category",
"tma_ports_utilized_0_group": "Metrics contributing to tma_ports_utilized_0 category",
"tma_ports_utilized_3m_group": "Metrics contributing to tma_ports_utilized_3m category",
"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_stlb_miss_group": "Metrics contributing to tma_store_stlb_miss category"
}

109
tools/perf/pmu-events/arch/x86/graniterapids/other.json
View File

@@ -1,4 +1,13 @@
[
{
"BriefDescription": "Count all other hardware assists or traps that are not necessarily architecturally exposed (through a software handler) beyond FP; SSE-AVX mix and A/D assists who are counted by dedicated sub-events. the event also counts for Machine Ordering count.",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc1",
"EventName": "ASSISTS.HARDWARE",
"PublicDescription": "Count all other hardware assists or traps that are not necessarily architecturally exposed (through a software handler) beyond FP; SSE-AVX mix and A/D assists who are counted by dedicated sub-events. This includes, but not limited to, assists at EXE or MEM uop writeback like AVX* load/store/gather/scatter (non-FP GSSE-assist ) , assists generated by ROB like PEBS and RTIT, Uncore trap, RAR (Remote Action Request) and CET (Control flow Enforcement Technology) assists. the event also counts for Machine Ordering count.",
"SampleAfterValue": "100003",
"UMask": "0x4"
},
{
"BriefDescription": "ASSISTS.PAGE_FAULT",
"Counter": "0,1,2,3,4,5,6,7",
@@ -65,6 +74,36 @@
"SampleAfterValue": "100003",
"UMask": "0x1"
},
{
"BriefDescription": "Counts demand data reads that were supplied by DRAM attached to this socket, unless in Sub NUMA Cluster(SNC) Mode. In SNC Mode counts only those DRAM accesses that are controlled by the close SNC Cluster.",
"Counter": "0,1,2,3",
"EventCode": "0x2A,0x2B",
"EventName": "OCR.DEMAND_DATA_RD.LOCAL_DRAM",
"MSRIndex": "0x1a6,0x1a7",
"MSRValue": "0x104000001",
"SampleAfterValue": "100003",
"UMask": "0x1"
},
{
"BriefDescription": "Counts demand data reads that were supplied by DRAM attached to another socket.",
"Counter": "0,1,2,3",
"EventCode": "0x2A,0x2B",
"EventName": "OCR.DEMAND_DATA_RD.REMOTE_DRAM",
"MSRIndex": "0x1a6,0x1a7",
"MSRValue": "0x730000001",
"SampleAfterValue": "100003",
"UMask": "0x1"
},
{
"BriefDescription": "Counts demand reads for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that have any type of response.",
"Counter": "0,1,2,3",
"EventCode": "0x2A,0x2B",
"EventName": "OCR.DEMAND_RFO.ANY_RESPONSE",
"MSRIndex": "0x1a6,0x1a7",
"MSRValue": "0x3F3FFC0002",
"SampleAfterValue": "100003",
"UMask": "0x1"
},
{
"BriefDescription": "Counts demand reads for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that were supplied by DRAM.",
"Counter": "0,1,2,3",
@@ -115,6 +154,66 @@
"SampleAfterValue": "100003",
"UMask": "0x1"
},
{
"BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by DRAM attached to this socket, unless in Sub NUMA Cluster(SNC) Mode. In SNC Mode counts only those DRAM accesses that are controlled by the close SNC Cluster.",
"Counter": "0,1,2,3",
"EventCode": "0x2A,0x2B",
"EventName": "OCR.READS_TO_CORE.LOCAL_DRAM",
"MSRIndex": "0x1a6,0x1a7",
"MSRValue": "0x104004477",
"SampleAfterValue": "100003",
"UMask": "0x1"
},
{
"BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by DRAM attached to this socket, whether or not in Sub NUMA Cluster(SNC) Mode. In SNC Mode counts DRAM accesses that are controlled by the close or distant SNC Cluster.",
"Counter": "0,1,2,3",
"EventCode": "0x2A,0x2B",
"EventName": "OCR.READS_TO_CORE.LOCAL_SOCKET_DRAM",
"MSRIndex": "0x1a6,0x1a7",
"MSRValue": "0x70C004477",
"SampleAfterValue": "100003",
"UMask": "0x1"
},
{
"BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were not supplied by the local socket's L1, L2, or L3 caches and were supplied by a remote socket.",
"Counter": "0,1,2,3",
"EventCode": "0x2A,0x2B",
"EventName": "OCR.READS_TO_CORE.REMOTE",
"MSRIndex": "0x1a6,0x1a7",
"MSRValue": "0x3F33004477",
"SampleAfterValue": "100003",
"UMask": "0x1"
},
{
"BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by DRAM attached to another socket.",
"Counter": "0,1,2,3",
"EventCode": "0x2A,0x2B",
"EventName": "OCR.READS_TO_CORE.REMOTE_DRAM",
"MSRIndex": "0x1a6,0x1a7",
"MSRValue": "0x730004477",
"SampleAfterValue": "100003",
"UMask": "0x1"
},
{
"BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by DRAM or PMM attached to another socket.",
"Counter": "0,1,2,3",
"EventCode": "0x2A,0x2B",
"EventName": "OCR.READS_TO_CORE.REMOTE_MEMORY",
"MSRIndex": "0x1a6,0x1a7",
"MSRValue": "0x733004477",
"SampleAfterValue": "100003",
"UMask": "0x1"
},
{
"BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by DRAM on a distant memory controller of this socket when the system is in SNC (sub-NUMA cluster) mode.",
"Counter": "0,1,2,3",
"EventCode": "0x2A,0x2B",
"EventName": "OCR.READS_TO_CORE.SNC_DRAM",
"MSRIndex": "0x1a6,0x1a7",
"MSRValue": "0x708004477",
"SampleAfterValue": "100003",
"UMask": "0x1"
},
{
"BriefDescription": "Counts streaming stores that have any type of response.",
"Counter": "0,1,2,3",
@@ -125,6 +224,16 @@
"SampleAfterValue": "100003",
"UMask": "0x1"
},
{
"BriefDescription": "Counts Demand RFOs, ItoM's, PREFECTHW's, Hardware RFO Prefetches to the L1/L2 and Streaming stores that likely resulted in a store to Memory (DRAM or PMM)",
"Counter": "0,1,2,3",
"EventCode": "0x2A,0x2B",
"EventName": "OCR.WRITE_ESTIMATE.MEMORY",
"MSRIndex": "0x1a6,0x1a7",
"MSRValue": "0xFBFF80822",
"SampleAfterValue": "100003",
"UMask": "0x1"
},
{
"BriefDescription": "Cycles when Reservation Station (RS) is empty for the thread.",
"Counter": "0,1,2,3,4,5,6,7",

40
tools/perf/pmu-events/arch/x86/graniterapids/pipeline.json
View File

@@ -32,7 +32,6 @@
"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"
},
@@ -41,7 +40,6 @@
"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"
@@ -51,7 +49,6 @@
"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"
@@ -61,7 +58,6 @@
"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"
@@ -71,7 +67,6 @@
"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"
@@ -81,7 +76,6 @@
"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"
@@ -91,7 +85,6 @@
"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"
@@ -101,7 +94,6 @@
"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"
@@ -111,7 +103,6 @@
"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"
@@ -121,7 +112,6 @@
"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"
},
@@ -130,7 +120,6 @@
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc5",
"EventName": "BR_MISP_RETIRED.ALL_BRANCHES_COST",
"PEBS": "1",
"SampleAfterValue": "400009",
"UMask": "0x44"
},
@@ -139,7 +128,6 @@
"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"
@@ -149,7 +137,6 @@
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc5",
"EventName": "BR_MISP_RETIRED.COND_COST",
"PEBS": "1",
"SampleAfterValue": "400009",
"UMask": "0x51"
},
@@ -158,7 +145,6 @@
"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"
@@ -168,7 +154,6 @@
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc5",
"EventName": "BR_MISP_RETIRED.COND_NTAKEN_COST",
"PEBS": "1",
"SampleAfterValue": "400009",
"UMask": "0x50"
},
@@ -177,7 +162,6 @@
"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"
@@ -187,7 +171,6 @@
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc5",
"EventName": "BR_MISP_RETIRED.COND_TAKEN_COST",
"PEBS": "1",
"SampleAfterValue": "400009",
"UMask": "0x41"
},
@@ -196,7 +179,6 @@
"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"
@@ -206,7 +188,6 @@
"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"
@@ -216,7 +197,6 @@
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc5",
"EventName": "BR_MISP_RETIRED.INDIRECT_CALL_COST",
"PEBS": "1",
"SampleAfterValue": "400009",
"UMask": "0x42"
},
@@ -225,7 +205,6 @@
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc5",
"EventName": "BR_MISP_RETIRED.INDIRECT_COST",
"PEBS": "1",
"SampleAfterValue": "100003",
"UMask": "0xc0"
},
@@ -234,7 +213,6 @@
"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"
@@ -244,7 +222,6 @@
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc5",
"EventName": "BR_MISP_RETIRED.NEAR_TAKEN_COST",
"PEBS": "1",
"SampleAfterValue": "400009",
"UMask": "0x60"
},
@@ -253,7 +230,6 @@
"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"
@@ -263,7 +239,6 @@
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc5",
"EventName": "BR_MISP_RETIRED.RET_COST",
"PEBS": "1",
"SampleAfterValue": "100007",
"UMask": "0x48"
},
@@ -511,7 +486,6 @@
"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"
@@ -521,7 +495,6 @@
"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"
},
@@ -530,7 +503,6 @@
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc0",
"EventName": "INST_RETIRED.MACRO_FUSED",
"PEBS": "1",
"SampleAfterValue": "2000003",
"UMask": "0x10"
},
@@ -539,7 +511,6 @@
"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 or PREFETCHIT0/1 instructions",
"SampleAfterValue": "2000003",
"UMask": "0x2"
@@ -548,7 +519,6 @@
"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"
@@ -558,7 +528,6 @@
"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"
@@ -788,6 +757,15 @@
"SampleAfterValue": "100003",
"UMask": "0x20"
},
{
"BriefDescription": "Cycles stalled due to no store buffers available. (not including draining form sync).",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xa2",
"EventName": "RESOURCE_STALLS.SB",
"PublicDescription": "Counts allocation stall cycles caused by the store buffer (SB) being full. This counts cycles that the pipeline back-end blocked uop delivery from the front-end.",
"SampleAfterValue": "100003",
"UMask": "0x8"
},
{
"BriefDescription": "Counts cycles where the pipeline is stalled due to serializing operations.",
"Counter": "0,1,2,3,4,5,6,7",

48
tools/perf/pmu-events/arch/x86/graniterapids/uncore-cache.json
View File

@@ -9,6 +9,16 @@
"PublicDescription": "UNC_CHACMS_CLOCKTICKS",
"Unit": "CHACMS"
},
{
"BriefDescription": "Counts the number of cycles FAST trigger is received from the global FAST distress wire.",
"Counter": "0,1,2,3",
"EventCode": "0x34",
"EventName": "UNC_CHACMS_RING_SRC_THRTL",
"Experimental": "1",
"PerPkg": "1",
"PortMask": "0x000",
"Unit": "CHACMS"
},
{
"BriefDescription": "Number of CHA clock cycles while the event is enabled",
"Counter": "0,1,2,3",
@@ -843,6 +853,16 @@
"UMask": "0x8",
"Unit": "CHA"
},
{
"BriefDescription": "Ingress (from CMS) Occupancy : IRQ : Counts number of entries in the specified Ingress queue in each cycle.",
"Counter": "0",
"EventCode": "0x11",
"EventName": "UNC_CHA_RxC_OCCUPANCY.IRQ",
"Experimental": "1",
"PerPkg": "1",
"UMask": "0x1",
"Unit": "CHA"
},
{
"BriefDescription": "All TOR Inserts",
"Counter": "0,1,2,3",
@@ -1056,7 +1076,7 @@
"Unit": "CHA"
},
{
"BriefDescription": "Code read from local IA that miss the cache",
"BriefDescription": "Code read from local IA",
"Counter": "0,1,2,3",
"EventCode": "0x35",
"EventName": "UNC_CHA_TOR_INSERTS.IA_CRD",
@@ -1076,7 +1096,7 @@
"Unit": "CHA"
},
{
"BriefDescription": "Data read from local IA that miss the cache",
"BriefDescription": "Data read from local IA",
"Counter": "0,1,2,3",
"EventCode": "0x35",
"EventName": "UNC_CHA_TOR_INSERTS.IA_DRD",
@@ -1096,7 +1116,7 @@
"Unit": "CHA"
},
{
"BriefDescription": "Data read prefetch from local IA that miss the cache",
"BriefDescription": "Data read prefetch from local IA",
"Counter": "0,1,2,3",
"EventCode": "0x35",
"EventName": "UNC_CHA_TOR_INSERTS.IA_DRD_PREF",
@@ -1276,7 +1296,7 @@
"Unit": "CHA"
},
{
"BriefDescription": "Last level cache prefetch read for ownership from local IA that miss the cache",
"BriefDescription": "Last level cache prefetch read for ownership from local IA",
"Counter": "0,1,2,3",
"EventCode": "0x35",
"EventName": "UNC_CHA_TOR_INSERTS.IA_LLCPREFRFO",
@@ -1405,7 +1425,7 @@
"Unit": "CHA"
},
{
"BriefDescription": "Data read from local IA that miss the cache",
"BriefDescription": "Data read from local IA that miss the cache and targets local memory",
"Counter": "0,1,2,3",
"EventCode": "0x35",
"EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_DRD_LOCAL",
@@ -1476,7 +1496,7 @@
"Unit": "CHA"
},
{
"BriefDescription": "Data read prefetch from local IA that miss the cache",
"BriefDescription": "Data read prefetch from local IA that miss the cache and targets local memory",
"Counter": "0,1,2,3",
"EventCode": "0x35",
"EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_DRD_PREF_LOCAL",
@@ -1518,7 +1538,7 @@
"Unit": "CHA"
},
{
"BriefDescription": "Data read prefetch from local IA that miss the cache",
"BriefDescription": "Data read prefetch from local IA that miss the cache and targets remote memory",
"Counter": "0,1,2,3",
"EventCode": "0x35",
"EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_DRD_PREF_REMOTE",
@@ -1549,7 +1569,7 @@
"Unit": "CHA"
},
{
"BriefDescription": "Data read from local IA that miss the cache",
"BriefDescription": "Data read from local IA that miss the cache and targets remote memory",
"Counter": "0,1,2,3",
"EventCode": "0x35",
"EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_DRD_REMOTE",
@@ -1741,7 +1761,7 @@
"Unit": "CHA"
},
{
"BriefDescription": "Read for ownership from local IA that miss the cache",
"BriefDescription": "Read for ownership from local IA that miss the LLC targeting local memory",
"Counter": "0,1,2,3",
"EventCode": "0x35",
"EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_RFO_LOCAL",
@@ -1770,7 +1790,7 @@
"Unit": "CHA"
},
{
"BriefDescription": "Read for ownership prefetch from local IA that miss the cache",
"BriefDescription": "Read for ownership prefetch from local IA that miss the LLC targeting local memory",
"Counter": "0,1,2,3",
"EventCode": "0x35",
"EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_RFO_PREF_LOCAL",
@@ -1780,7 +1800,7 @@
"Unit": "CHA"
},
{
"BriefDescription": "Read for ownership prefetch from local IA that miss the cache",
"BriefDescription": "Read for ownership prefetch from local IA that miss the LLC targeting remote memory",
"Counter": "0,1,2,3",
"EventCode": "0x35",
"EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_RFO_PREF_REMOTE",
@@ -1790,7 +1810,7 @@
"Unit": "CHA"
},
{
"BriefDescription": "Read for ownership from local IA that miss the cache",
"BriefDescription": "Read for ownership from local IA that miss the LLC targeting remote memory",
"Counter": "0,1,2,3",
"EventCode": "0x35",
"EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_RFO_REMOTE",
@@ -1882,7 +1902,7 @@
"Unit": "CHA"
},
{
"BriefDescription": "Read for ownership from local IA that miss the cache",
"BriefDescription": "Read for ownership from local IA",
"Counter": "0,1,2,3",
"EventCode": "0x35",
"EventName": "UNC_CHA_TOR_INSERTS.IA_RFO",
@@ -1892,7 +1912,7 @@
"Unit": "CHA"
},
{
"BriefDescription": "Read for ownership prefetch from local IA that miss the cache",
"BriefDescription": "Read for ownership prefetch from local IA",
"Counter": "0,1,2,3",
"EventCode": "0x35",
"EventName": "UNC_CHA_TOR_INSERTS.IA_RFO_PREF",

2
tools/perf/pmu-events/arch/x86/graniterapids/uncore-cxl.json
View File

@@ -13,7 +13,6 @@
"Counter": "4,5,6,7",
"EventCode": "0x41",
"EventName": "UNC_CXLCM_RxC_PACK_BUF_INSERTS.MEM_DATA",
"Experimental": "1",
"PerPkg": "1",
"UMask": "0x10",
"Unit": "CXLCM"
@@ -23,7 +22,6 @@
"Counter": "0,1,2,3",
"EventCode": "0x02",
"EventName": "UNC_CXLDP_TxC_AGF_INSERTS.M2S_DATA",
"Experimental": "1",
"PerPkg": "1",
"UMask": "0x20",
"Unit": "CXLDP"

87
tools/perf/pmu-events/arch/x86/graniterapids/uncore-interconnect.json
View File

@@ -808,6 +808,26 @@
"PerPkg": "1",
"Unit": "IRP"
},
{
"BriefDescription": "Counts Timeouts - Set 0 : Fastpath Rejects",
"Counter": "0,1,2,3",
"EventCode": "0x1E",
"EventName": "UNC_I_MISC0.FAST_REJ",
"Experimental": "1",
"PerPkg": "1",
"UMask": "0x2",
"Unit": "IRP"
},
{
"BriefDescription": "Counts Timeouts - Set 0 : Fastpath Requests",
"Counter": "0,1,2,3",
"EventCode": "0x1E",
"EventName": "UNC_I_MISC0.FAST_REQ",
"Experimental": "1",
"PerPkg": "1",
"UMask": "0x1",
"Unit": "IRP"
},
{
"BriefDescription": "Misc Events - Set 1 : Lost Forward : Snoop pulled away ownership before a write was committed",
"Counter": "0,1,2,3",
@@ -818,6 +838,46 @@
"UMask": "0x10",
"Unit": "IRP"
},
{
"BriefDescription": "Snoop Hit E/S responses",
"Counter": "0,1,2,3",
"EventCode": "0x12",
"EventName": "UNC_I_SNOOP_RESP.ALL_HIT_ES",
"Experimental": "1",
"PerPkg": "1",
"UMask": "0x74",
"Unit": "IRP"
},
{
"BriefDescription": "Snoop Hit I responses",
"Counter": "0,1,2,3",
"EventCode": "0x12",
"EventName": "UNC_I_SNOOP_RESP.ALL_HIT_I",
"Experimental": "1",
"PerPkg": "1",
"UMask": "0x72",
"Unit": "IRP"
},
{
"BriefDescription": "Snoop Hit M responses",
"Counter": "0,1,2,3",
"EventCode": "0x12",
"EventName": "UNC_I_SNOOP_RESP.ALL_HIT_M",
"Experimental": "1",
"PerPkg": "1",
"UMask": "0x78",
"Unit": "IRP"
},
{
"BriefDescription": "Snoop miss responses",
"Counter": "0,1,2,3",
"EventCode": "0x12",
"EventName": "UNC_I_SNOOP_RESP.ALL_MISS",
"Experimental": "1",
"PerPkg": "1",
"UMask": "0x71",
"Unit": "IRP"
},
{
"BriefDescription": "Inbound write (fast path) requests to coherent memory, received by the IRP resulting in write ownership requests issued by IRP to the mesh.",
"Counter": "0,1,2,3",
@@ -1550,6 +1610,33 @@
"UMask": "0x4",
"Unit": "UPI"
},
{
"BriefDescription": "Cycles in L0p",
"Counter": "0,1,2,3",
"EventCode": "0x27",
"EventName": "UNC_UPI_TxL0P_POWER_CYCLES",
"Experimental": "1",
"PerPkg": "1",
"Unit": "UPI"
},
{
"BriefDescription": "UNC_UPI_TxL0P_POWER_CYCLES_LL_ENTER",
"Counter": "0,1,2,3",
"EventCode": "0x28",
"EventName": "UNC_UPI_TxL0P_POWER_CYCLES_LL_ENTER",
"Experimental": "1",
"PerPkg": "1",
"Unit": "UPI"
},
{
"BriefDescription": "UNC_UPI_TxL0P_POWER_CYCLES_M3_EXIT",
"Counter": "0,1,2,3",
"EventCode": "0x29",
"EventName": "UNC_UPI_TxL0P_POWER_CYCLES_M3_EXIT",
"Experimental": "1",
"PerPkg": "1",
"Unit": "UPI"
},
{
"BriefDescription": "Matches on Transmit path of a UPI Port : Non-Coherent Bypass",
"Counter": "0,1,2,3",

280
tools/perf/pmu-events/arch/x86/graniterapids/uncore-io.json
View File

File diff suppressed because it is too large Load Diff

122
tools/perf/pmu-events/arch/x86/graniterapids/uncore-memory.json
View File

@@ -169,7 +169,7 @@
"Unit": "IMC"
},
{
"BriefDescription": "Number of DRAM DCLK clock cycles while the event is enabled",
"BriefDescription": "Number of DRAM DCLK clock cycles while the event is enabled. DCLK is 1/4 of DRAM data rate.",
"Counter": "0,1,2,3",
"EventCode": "0x01",
"EventName": "UNC_M_CLOCKTICKS",
@@ -188,6 +188,104 @@
"PublicDescription": "DRAM Clockticks",
"Unit": "IMC"
},
{
"BriefDescription": "# of cycles a given rank is in Power Down Mode",
"Counter": "0,1,2,3",
"EventCode": "0x47",
"EventName": "UNC_M_POWERDOWN_CYCLES.SCH0_RANK0",
"Experimental": "1",
"PerPkg": "1",
"PublicDescription": "-",
"UMask": "0x1",
"Unit": "IMC"
},
{
"BriefDescription": "# of cycles a given rank is in Power Down Mode",
"Counter": "0,1,2,3",
"EventCode": "0x47",
"EventName": "UNC_M_POWERDOWN_CYCLES.SCH0_RANK1",
"Experimental": "1",
"PerPkg": "1",
"PublicDescription": "-",
"UMask": "0x2",
"Unit": "IMC"
},
{
"BriefDescription": "# of cycles a given rank is in Power Down Mode",
"Counter": "0,1,2,3",
"EventCode": "0x47",
"EventName": "UNC_M_POWERDOWN_CYCLES.SCH0_RANK2",
"Experimental": "1",
"PerPkg": "1",
"PublicDescription": "-",
"UMask": "0x4",
"Unit": "IMC"
},
{
"BriefDescription": "# of cycles a given rank is in Power Down Mode",
"Counter": "0,1,2,3",
"EventCode": "0x47",
"EventName": "UNC_M_POWERDOWN_CYCLES.SCH0_RANK3",
"Experimental": "1",
"PerPkg": "1",
"PublicDescription": "-",
"UMask": "0x8",
"Unit": "IMC"
},
{
"BriefDescription": "# of cycles a given rank is in Power Down Mode",
"Counter": "0,1,2,3",
"EventCode": "0x47",
"EventName": "UNC_M_POWERDOWN_CYCLES.SCH1_RANK0",
"Experimental": "1",
"PerPkg": "1",
"PublicDescription": "-",
"UMask": "0x10",
"Unit": "IMC"
},
{
"BriefDescription": "# of cycles a given rank is in Power Down Mode",
"Counter": "0,1,2,3",
"EventCode": "0x47",
"EventName": "UNC_M_POWERDOWN_CYCLES.SCH1_RANK1",
"Experimental": "1",
"PerPkg": "1",
"PublicDescription": "-",
"UMask": "0x20",
"Unit": "IMC"
},
{
"BriefDescription": "# of cycles a given rank is in Power Down Mode",
"Counter": "0,1,2,3",
"EventCode": "0x47",
"EventName": "UNC_M_POWERDOWN_CYCLES.SCH1_RANK2",
"Experimental": "1",
"PerPkg": "1",
"PublicDescription": "-",
"UMask": "0x40",
"Unit": "IMC"
},
{
"BriefDescription": "# of cycles a given rank is in Power Down Mode",
"Counter": "0,1,2,3",
"EventCode": "0x47",
"EventName": "UNC_M_POWERDOWN_CYCLES.SCH1_RANK3",
"Experimental": "1",
"PerPkg": "1",
"PublicDescription": "-",
"UMask": "0x80",
"Unit": "IMC"
},
{
"BriefDescription": "# of cycles a given rank is in Power Down Mode and all pages are closed",
"Counter": "0,1,2,3",
"EventCode": "0x88",
"EventName": "UNC_M_POWER_CHANNEL_PPD_CYCLES",
"Experimental": "1",
"PerPkg": "1",
"PublicDescription": "-",
"Unit": "IMC"
},
{
"BriefDescription": "DRAM Precharge commands. : Counts the number of DRAM Precharge commands sent on this channel.",
"Counter": "0,1,2,3",
@@ -358,6 +456,28 @@
"PerPkg": "1",
"Unit": "IMC"
},
{
"BriefDescription": "subevent0 - # of cycles all ranks were in SR subevent1 - # of times all ranks went into SR subevent2 -# of times ps_sr_active asserted (SRE) subevent3 - # of times ps_sr_active deasserted (SRX) subevent4 - # of times PS-&>Refresh ps_sr_req asserted (SRE) subevent5 - # of times PS-&>Refresh ps_sr_req deasserted (SRX) subevent6 - # of cycles PSCtrlr FSM was in FATAL",
"Counter": "0,1,2,3",
"EventCode": "0x43",
"EventName": "UNC_M_SELF_REFRESH.ENTER_SUCCESS",
"Experimental": "1",
"PerPkg": "1",
"PublicDescription": "UNC_M_SELF_REFRESH.ENTER_SUCCESS",
"UMask": "0x2",
"Unit": "IMC"
},
{
"BriefDescription": "# of cycles all ranks were in SR",
"Counter": "0,1,2,3",
"EventCode": "0x43",
"EventName": "UNC_M_SELF_REFRESH.ENTER_SUCCESS_CYCLES",
"Experimental": "1",
"PerPkg": "1",
"PublicDescription": "-",
"UMask": "0x1",
"Unit": "IMC"
},
{
"BriefDescription": "Write Pending Queue Allocations",
"Counter": "0,1,2,3",

98
tools/perf/pmu-events/arch/x86/graniterapids/uncore-power.json
View File

@@ -7,5 +7,103 @@
"PerPkg": "1",
"PublicDescription": "PCU Clockticks: The PCU runs off a fixed 1 GHz clock. This event counts the number of pclk cycles measured while the counter was enabled. The pclk, like the Memory Controller's dclk, counts at a constant rate making it a good measure of actual wall time.",
"Unit": "PCU"
},
{
"BriefDescription": "Thermal Strongest Upper Limit Cycles",
"Counter": "0,1,2,3",
"EventCode": "0x04",
"EventName": "UNC_P_FREQ_MAX_LIMIT_THERMAL_CYCLES",
"Experimental": "1",
"PerPkg": "1",
"PublicDescription": "Thermal Strongest Upper Limit Cycles : Number of cycles any frequency is reduced due to a thermal limit. Count only if throttling is occurring.",
"Unit": "PCU"
},
{
"BriefDescription": "Power Strongest Upper Limit Cycles",
"Counter": "0,1,2,3",
"EventCode": "0x05",
"EventName": "UNC_P_FREQ_MAX_POWER_CYCLES",
"Experimental": "1",
"PerPkg": "1",
"PublicDescription": "Power Strongest Upper Limit Cycles : Counts the number of cycles when power is the upper limit on frequency.",
"Unit": "PCU"
},
{
"BriefDescription": "Cycles spent changing Frequency",
"Counter": "0,1,2,3",
"EventCode": "0x74",
"EventName": "UNC_P_FREQ_TRANS_CYCLES",
"Experimental": "1",
"PerPkg": "1",
"PublicDescription": "Cycles spent changing Frequency : Counts the number of cycles when the system is changing frequency. This can not be filtered by thread ID. One can also use it with the occupancy counter that monitors number of threads in C0 to estimate the performance impact that frequency transitions had on the system.",
"Unit": "PCU"
},
{
"BriefDescription": "Package C State Residency - C2E",
"Counter": "0,1,2,3",
"EventCode": "0x2b",
"EventName": "UNC_P_PKG_RESIDENCY_C2E_CYCLES",
"Experimental": "1",
"PerPkg": "1",
"PublicDescription": "Package C State Residency - C2E : Counts the number of cycles when the package was in C2E. This event can be used in conjunction with edge detect to count C2E entrances (or exits using invert). Residency events do not include transition times.",
"Unit": "PCU"
},
{
"BriefDescription": "Package C State Residency - C6",
"Counter": "0,1,2,3",
"EventCode": "0x2d",
"EventName": "UNC_P_PKG_RESIDENCY_C6_CYCLES",
"Experimental": "1",
"PerPkg": "1",
"PublicDescription": "Package C State Residency - C6 : Counts the number of cycles when the package was in C6. This event can be used in conjunction with edge detect to count C6 entrances (or exits using invert). Residency events do not include transition times.",
"Unit": "PCU"
},
{
"BriefDescription": "Number of cores in C0",
"Counter": "0,1,2,3",
"EventCode": "0x35",
"EventName": "UNC_P_POWER_STATE_OCCUPANCY_CORES_C0",
"PerPkg": "1",
"PublicDescription": "Number of cores in C0 : This is an occupancy event that tracks the number of cores that are in the chosen C-State. It can be used by itself to get the average number of cores in that C-state with thresholding to generate histograms, or with other PCU events and occupancy triggering to capture other details.",
"Unit": "PCU"
},
{
"BriefDescription": "Number of cores in C3",
"Counter": "0,1,2,3",
"EventCode": "0x36",
"EventName": "UNC_P_POWER_STATE_OCCUPANCY_CORES_C3",
"Experimental": "1",
"PerPkg": "1",
"PublicDescription": "Number of cores in C3 : This is an occupancy event that tracks the number of cores that are in the chosen C-State. It can be used by itself to get the average number of cores in that C-state with thresholding to generate histograms, or with other PCU events and occupancy triggering to capture other details.",
"Unit": "PCU"
},
{
"BriefDescription": "Number of cores in C6",
"Counter": "0,1,2,3",
"EventCode": "0x37",
"EventName": "UNC_P_POWER_STATE_OCCUPANCY_CORES_C6",
"PerPkg": "1",
"PublicDescription": "Number of cores in C6 : This is an occupancy event that tracks the number of cores that are in the chosen C-State. It can be used by itself to get the average number of cores in that C-state with thresholding to generate histograms, or with other PCU events and occupancy triggering to capture other details.",
"Unit": "PCU"
},
{
"BriefDescription": "External Prochot",
"Counter": "0,1,2,3",
"EventCode": "0x0a",
"EventName": "UNC_P_PROCHOT_EXTERNAL_CYCLES",
"Experimental": "1",
"PerPkg": "1",
"PublicDescription": "External Prochot : Counts the number of cycles that we are in external PROCHOT mode. This mode is triggered when a sensor off the die determines that something off-die (like DRAM) is too hot and must throttle to avoid damaging the chip.",
"Unit": "PCU"
},
{
"BriefDescription": "Internal Prochot",
"Counter": "0,1,2,3",
"EventCode": "0x09",
"EventName": "UNC_P_PROCHOT_INTERNAL_CYCLES",
"Experimental": "1",
"PerPkg": "1",
"PublicDescription": "Internal Prochot : Counts the number of cycles that we are in Internal PROCHOT mode. This mode is triggered when a sensor on the die determines that we are too hot and must throttle to avoid damaging the chip.",
"Unit": "PCU"
}
]

2
tools/perf/pmu-events/arch/x86/mapfile.csv
View File

@@ -13,7 +13,7 @@ GenuineIntel-6-CF,v1.11,emeraldrapids,core
GenuineIntel-6-5[CF],v13,goldmont,core
GenuineIntel-6-7A,v1.01,goldmontplus,core
GenuineIntel-6-B6,v1.05,grandridge,core
GenuineIntel-6-A[DE],v1.02,graniterapids,core
GenuineIntel-6-A[DE],v1.06,graniterapids,core
GenuineIntel-6-(3C|45|46),v35,haswell,core
GenuineIntel-6-3F,v28,haswellx,core
GenuineIntel-6-7[DE],v1.22,icelake,core
1 Family-model Version Filename EventType
13 GenuineIntel-6-5[CF] v13 goldmont core
14 GenuineIntel-6-7A v1.01 goldmontplus core
15 GenuineIntel-6-B6 v1.05 grandridge core
16 GenuineIntel-6-A[DE] v1.02 v1.06 graniterapids core
17 GenuineIntel-6-(3C|45|46) v35 haswell core
18 GenuineIntel-6-3F v28 haswellx core
19 GenuineIntel-6-7[DE] v1.22 icelake core