Skip to contentSkip to conversation

perf vendor events intel: Keep json in sync

PATCH New Ian Rogers 1 participant 4 messages Sep 16, 2023

Subsystems (2)
lore
Share & tools
lore

Ian Rogers

author reviewer
#0 lore raw

PATCH 1/4 perf vendor events intel: Keep json in sync

Upstream is using the spelling "inflight" rather than "in-flight". Update to keep in sync.
Fix typo on ivybridge.
Bonnell version is v5 with typo fixes. Westmereex typo fix and version bump.

Update created using:
https://github.com/intel/perfmon/blob/main/scripts/create_perf_json.py

---
 tools/perf/pmu-events/arch/x86/haswell/memory.json           | 2 +-
 tools/perf/pmu-events/arch/x86/haswellx/memory.json          | 2 +-
 tools/perf/pmu-events/arch/x86/ivybridge/floating-point.json | 2 +-
 tools/perf/pmu-events/arch/x86/mapfile.csv                   | 4 ++--
 tools/perf/pmu-events/arch/x86/westmereex/pipeline.json      | 2 +-
 5 files changed, 6 insertions(+), 6 deletions(-)
tools/perf/pmu-events/arch/x86/haswell/memory.json +1 -1
index df44c28efeeb..2fc25e22a42a 100644
@@ -62,7 +62,7 @@
         "BriefDescription": "Counts the number of machine clears due to memory order conflicts.",
         "EventCode": "0xC3",
         "EventName": "MACHINE_CLEARS.MEMORY_ORDERING",
-        "PublicDescription": "This event counts the number of memory ordering machine clears detected. Memory ordering machine clears can result from memory address aliasing or snoops from another hardware thread or core to data in-flight in the pipeline.  Machine clears can have a significant performance impact if they are happening frequently.",
+        "PublicDescription": "This event counts the number of memory ordering machine clears detected. Memory ordering machine clears can result from memory address aliasing or snoops from another hardware thread or core to data inflight in the pipeline.  Machine clears can have a significant performance impact if they are happening frequently.",
         "SampleAfterValue": "100003",
         "UMask": "0x2"
     },
tools/perf/pmu-events/arch/x86/haswellx/memory.json +1 -1
index d66e465ce41a..2d212cf59e92 100644
@@ -62,7 +62,7 @@
         "BriefDescription": "Counts the number of machine clears due to memory order conflicts.",
         "EventCode": "0xC3",
         "EventName": "MACHINE_CLEARS.MEMORY_ORDERING",
-        "PublicDescription": "This event counts the number of memory ordering machine clears detected. Memory ordering machine clears can result from memory address aliasing or snoops from another hardware thread or core to data in-flight in the pipeline.  Machine clears can have a significant performance impact if they are happening frequently.",
+        "PublicDescription": "This event counts the number of memory ordering machine clears detected. Memory ordering machine clears can result from memory address aliasing or snoops from another hardware thread or core to data inflight in the pipeline.  Machine clears can have a significant performance impact if they are happening frequently.",
         "SampleAfterValue": "100003",
         "UMask": "0x2"
     },
tools/perf/pmu-events/arch/x86/ivybridge/floating-point.json +1 -1
index 87c958213c7a..89c6d47cc077 100644
@@ -73,7 +73,7 @@
         "UMask": "0x20"
     },
     {
-        "BriefDescription": "Number of FP Computational Uops Executed this cycle. The number of FADD, FSUB, FCOM, FMULs, integer MULsand IMULs, FDIVs, FPREMs, FSQRTS, integer DIVs, and IDIVs. This event does not distinguish an FADD used in the middle of a transcendental flow from a s",
+        "BriefDescription": "Number of FP Computational Uops Executed this cycle. The number of FADD, FSUB, FCOM, FMULs, integer MULs and IMULs, FDIVs, FPREMs, FSQRTS, integer DIVs, and IDIVs. This event does not distinguish an FADD used in the middle of a transcendental flow from a s",
         "EventCode": "0x10",
         "EventName": "FP_COMP_OPS_EXE.X87",
         "PublicDescription": "Counts number of X87 uops executed.",
tools/perf/pmu-events/arch/x86/mapfile.csv +2 -2
index 57ba7e814563..51c64ac2b9f7 100644
@@ -1,7 +1,7 @@
 Family-model,Version,Filename,EventType
 GenuineIntel-6-(97|9A|B7|BA|BF),v1.21,alderlake,core
 GenuineIntel-6-BE,v1.21,alderlaken,core
-GenuineIntel-6-(1C|26|27|35|36),v4,bonnell,core
+GenuineIntel-6-(1C|26|27|35|36),v5,bonnell,core
 GenuineIntel-6-(3D|47),v28,broadwell,core
 GenuineIntel-6-56,v11,broadwellde,core
 GenuineIntel-6-4F,v22,broadwellx,core
@@ -35,7 +35,7 @@ GenuineIntel-6-86,v1.21,snowridgex,core
 GenuineIntel-6-8[CD],v1.13,tigerlake,core
 GenuineIntel-6-2C,v5,westmereep-dp,core
 GenuineIntel-6-25,v4,westmereep-sp,core
-GenuineIntel-6-2F,v3,westmereex,core
+GenuineIntel-6-2F,v4,westmereex,core
 AuthenticAMD-23-([12][0-9A-F]|[0-9A-F]),v2,amdzen1,core
 AuthenticAMD-23-[[:xdigit:]]+,v1,amdzen2,core
 AuthenticAMD-25-([245][[:xdigit:]]|[[:xdigit:]]),v1,amdzen3,core
tools/perf/pmu-events/arch/x86/westmereex/pipeline.json +1 -1
index 1c61d18a4b5f..026236558d05 100644
@@ -45,7 +45,7 @@
         "UMask": "0x1"
     },
     {
-        "BriefDescription": "Early Branch Prediciton Unit clears",
+        "BriefDescription": "Early Branch Prediction Unit clears",
         "EventCode": "0xE8",
         "EventName": "BPU_CLEARS.EARLY",
         "SampleAfterValue": "2000000",
Signature · 1 line
2.42.0.459.ge4e396fd5e-goog
author reviewer
#1 lore raw

PATCH 2/4 perf vendor events intel: Update alderlake events to v1.22

v1.22 was released in:
https://github.com/intel/perfmon/commit/846bd247c6e04acc572ca56c992e9e65852bbe63

Update created using:
https://github.com/intel/perfmon/blob/main/scripts/create_perf_json.py

---
 .../arch/x86/alderlake/frontend.json          | 42 ++++++++++--
 .../pmu-events/arch/x86/alderlake/memory.json |  4 +-
 .../x86/alderlake/uncore-interconnect.json    |  2 +
 .../arch/x86/alderlaken/memory.json           |  4 +-
 .../x86/alderlaken/uncore-interconnect.json   | 66 +++++++++++++++++++
 tools/perf/pmu-events/arch/x86/mapfile.csv    |  4 +-
 6 files changed, 110 insertions(+), 12 deletions(-)
tools/perf/pmu-events/arch/x86/alderlake/frontend.json +36 -6
index 81349100fe32..542ba4a81996 100644
@@ -394,31 +394,61 @@
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "Uops not delivered by IDQ when backend of the machine is not stalled",
+        "BriefDescription": "Uops not delivered by IDQ when backend of the machine is not stalled [This event is alias to IDQ_UOPS_NOT_DELIVERED.CORE]",
+        "EventCode": "0x9c",
+        "EventName": "IDQ_BUBBLES.CORE",
+        "PublicDescription": "Counts the number of uops not delivered to by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle. [This event is alias to IDQ_UOPS_NOT_DELIVERED.CORE]",
+        "SampleAfterValue": "1000003",
+        "UMask": "0x1",
+        "Unit": "cpu_core"
+    },
+    {
+        "BriefDescription": "Cycles when no uops are not delivered by the IDQ when backend of the machine is not stalled [This event is alias to IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE]",
+        "CounterMask": "6",
+        "EventCode": "0x9c",
+        "EventName": "IDQ_BUBBLES.CYCLES_0_UOPS_DELIV.CORE",
+        "PublicDescription": "Counts the number of cycles when no uops were delivered by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle. [This event is alias to IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE]",
+        "SampleAfterValue": "1000003",
+        "UMask": "0x1",
+        "Unit": "cpu_core"
+    },
+    {
+        "BriefDescription": "Cycles when optimal number of uops was delivered to the back-end when the back-end is not stalled [This event is alias to IDQ_UOPS_NOT_DELIVERED.CYCLES_FE_WAS_OK]",
+        "CounterMask": "1",
+        "EventCode": "0x9c",
+        "EventName": "IDQ_BUBBLES.CYCLES_FE_WAS_OK",
+        "Invert": "1",
+        "PublicDescription": "Counts the number of cycles when the optimal number of uops were delivered by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle. [This event is alias to IDQ_UOPS_NOT_DELIVERED.CYCLES_FE_WAS_OK]",
+        "SampleAfterValue": "1000003",
+        "UMask": "0x1",
+        "Unit": "cpu_core"
+    },
+    {
+        "BriefDescription": "Uops not delivered by IDQ when backend of the machine is not stalled [This event is alias to IDQ_BUBBLES.CORE]",
         "EventCode": "0x9c",
         "EventName": "IDQ_UOPS_NOT_DELIVERED.CORE",
-        "PublicDescription": "Counts the number of uops not delivered to by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle.",
+        "PublicDescription": "Counts the number of uops not delivered to by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle. [This event is alias to IDQ_BUBBLES.CORE]",
         "SampleAfterValue": "1000003",
         "UMask": "0x1",
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "Cycles when no uops are not delivered by the IDQ when backend of the machine is not stalled",
+        "BriefDescription": "Cycles when no uops are not delivered by the IDQ when backend of the machine is not stalled [This event is alias to IDQ_BUBBLES.CYCLES_0_UOPS_DELIV.CORE]",
         "CounterMask": "6",
         "EventCode": "0x9c",
         "EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE",
-        "PublicDescription": "Counts the number of cycles when no uops were delivered by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle.",
+        "PublicDescription": "Counts the number of cycles when no uops were delivered by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle. [This event is alias to IDQ_BUBBLES.CYCLES_0_UOPS_DELIV.CORE]",
         "SampleAfterValue": "1000003",
         "UMask": "0x1",
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "Cycles when optimal number of uops was delivered to the back-end when the back-end is not stalled",
+        "BriefDescription": "Cycles when optimal number of uops was delivered to the back-end when the back-end is not stalled [This event is alias to IDQ_BUBBLES.CYCLES_FE_WAS_OK]",
         "CounterMask": "1",
         "EventCode": "0x9c",
         "EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_FE_WAS_OK",
         "Invert": "1",
-        "PublicDescription": "Counts the number of cycles when the optimal number of uops were delivered by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle.",
+        "PublicDescription": "Counts the number of cycles when the optimal number of uops were delivered by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle. [This event is alias to IDQ_BUBBLES.CYCLES_FE_WAS_OK]",
         "SampleAfterValue": "1000003",
         "UMask": "0x1",
         "Unit": "cpu_core"
tools/perf/pmu-events/arch/x86/alderlake/memory.json +2 -2
index 73d92d5c9f9d..23d36164433f 100644
@@ -248,7 +248,7 @@
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "Counts demand data reads that were not supplied by the L3 cache.",
+        "BriefDescription": "Counts demand data reads that were not supplied by the L3 cache. [L3_MISS_LOCAL is alias to L3_MISS]",
         "EventCode": "0xB7",
         "EventName": "OCR.DEMAND_DATA_RD.L3_MISS_LOCAL",
         "MSRIndex": "0x1a6,0x1a7",
@@ -278,7 +278,7 @@
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that were not supplied by the L3 cache.",
+        "BriefDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that were not supplied by the L3 cache. [L3_MISS_LOCAL is alias to L3_MISS]",
         "EventCode": "0xB7",
         "EventName": "OCR.DEMAND_RFO.L3_MISS_LOCAL",
         "MSRIndex": "0x1a6,0x1a7",
tools/perf/pmu-events/arch/x86/alderlake/uncore-interconnect.json +2 -0
index 34fc052d00e4..8bf020a9dfa8 100644
@@ -25,6 +25,7 @@
     },
     {
         "BriefDescription": "This event is deprecated. Refer to new event UNC_ARB_REQ_TRK_REQUEST.DRD",
+        "Deprecated": "1",
         "EventCode": "0x81",
         "EventName": "UNC_ARB_DAT_REQUESTS.RD",
         "PerPkg": "1",
@@ -33,6 +34,7 @@
     },
     {
         "BriefDescription": "This event is deprecated. Refer to new event UNC_ARB_DAT_OCCUPANCY.ALL",
+        "Deprecated": "1",
         "EventCode": "0x85",
         "EventName": "UNC_ARB_IFA_OCCUPANCY.ALL",
         "PerPkg": "1",
tools/perf/pmu-events/arch/x86/alderlaken/memory.json +2 -2
index 37259d38a222..863a3ba2b4b2 100644
@@ -59,7 +59,7 @@
         "UMask": "0x1"
     },
     {
-        "BriefDescription": "Counts demand data reads that were not supplied by the L3 cache.",
+        "BriefDescription": "Counts demand data reads that were not supplied by the L3 cache. [L3_MISS_LOCAL is alias to L3_MISS]",
         "EventCode": "0xB7",
         "EventName": "OCR.DEMAND_DATA_RD.L3_MISS_LOCAL",
         "MSRIndex": "0x1a6,0x1a7",
@@ -77,7 +77,7 @@
         "UMask": "0x1"
     },
     {
-        "BriefDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that were not supplied by the L3 cache.",
+        "BriefDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that were not supplied by the L3 cache. [L3_MISS_LOCAL is alias to L3_MISS]",
         "EventCode": "0xB7",
         "EventName": "OCR.DEMAND_RFO.L3_MISS_LOCAL",
         "MSRIndex": "0x1a6,0x1a7",
tools/perf/pmu-events/arch/x86/alderlaken/uncore-interconnect.json +66 -0

83 lines not on this page · raw message

tools/perf/pmu-events/arch/x86/mapfile.csv +2 -2
index 51c64ac2b9f7..24f03cd804f6 100644
@@ -1,6 +1,6 @@
 Family-model,Version,Filename,EventType
-GenuineIntel-6-(97|9A|B7|BA|BF),v1.21,alderlake,core
-GenuineIntel-6-BE,v1.21,alderlaken,core
+GenuineIntel-6-(97|9A|B7|BA|BF),v1.22,alderlake,core
+GenuineIntel-6-BE,v1.22,alderlaken,core
 GenuineIntel-6-(1C|26|27|35|36),v5,bonnell,core
 GenuineIntel-6-(3D|47),v28,broadwell,core
 GenuineIntel-6-56,v11,broadwellde,core
Signature · 1 line
2.42.0.459.ge4e396fd5e-goog
author reviewer
#2 lore raw

PATCH 3/4 perf vendor events intel: Update knightslanding events to v16

In reply to Ian Rogers

v16 was released in:
https://github.com/intel/perfmon/commit/b22ca587ec8b5ac20471ea2f14924f63e63afe9d

Update created using:
https://github.com/intel/perfmon/blob/main/scripts/create_perf_json.py

---
 .../arch/x86/knightslanding/cache.json        | 39 ++++++++-----
 .../x86/knightslanding/floating-point.json    |  8 +--
 .../arch/x86/knightslanding/pipeline.json     | 55 +++++++++++--------
 .../arch/x86/knightslanding/uncore-cache.json | 26 ++++-----
 .../x86/knightslanding/virtual-memory.json    |  2 +-
 tools/perf/pmu-events/arch/x86/mapfile.csv    |  2 +-
 6 files changed, 75 insertions(+), 57 deletions(-)
tools/perf/pmu-events/arch/x86/knightslanding/cache.json +24 -15
index d9876cb06b08..8da3a5a7be73 100644
@@ -6,13 +6,19 @@
         "SampleAfterValue": "200003"
     },
     {
-        "BriefDescription": "Counts the number of core cycles the fetch stalls because of an icache miss. This is a cumulative count of core cycles the fetch stalled for all icache misses.",
+        "BriefDescription": "This event counts the number of core cycles the fetch stalls because of an icache miss. This is a cumulative count of cycles the NIP stalled for all icache misses.",
         "EventCode": "0x86",
         "EventName": "FETCH_STALL.ICACHE_FILL_PENDING_CYCLES",
-        "PublicDescription": "This event counts the number of core cycles the fetch stalls because of an icache miss. This is a cumulative count of cycles the NIP stalled for all icache misses.",
         "SampleAfterValue": "200003",
         "UMask": "0x4"
     },
+    {
+        "BriefDescription": "Counts the number of L2HWP allocated into XQ GP",
+        "EventCode": "0x3E",
+        "EventName": "L2_PREFETCHER.ALLOC_XQ",
+        "SampleAfterValue": "100007",
+        "UMask": "0x4"
+    },
     {
         "BriefDescription": "Counts the number of L2 cache misses",
         "EventCode": "0x2E",
@@ -28,7 +34,7 @@
         "UMask": "0x4f"
     },
     {
-        "BriefDescription": "Counts the number of MEC requests from the L2Q that reference a cache line (cacheable requests) excluding SW prefetches filling only to L2 cache and L1 evictions (automatically exlcudes L2HWP, UC, WC) that were rejected - Multiple repeated rejects should be counted multiple times",
+        "BriefDescription": "Counts the number of MEC requests from the L2Q that reference a cache line (cacheable requests) excluding SW prefetches filling only to L2 cache and L1 evictions (automatically excludes L2HWP, UC, WC) that were rejected - Multiple repeated rejects should be counted multiple times",
         "EventCode": "0x30",
         "EventName": "L2_REQUESTS_REJECT.ALL",
         "SampleAfterValue": "200003"
@@ -50,11 +56,12 @@
         "UMask": "0x80"
     },
     {
-        "BriefDescription": "Counts the loads retired that get the data from the other core in the same tile in M state",
+        "BriefDescription": "Counts the loads retired that get the data from the other core in the same tile in M state (Precise Event)",
         "Data_LA": "1",
         "EventCode": "0x04",
         "EventName": "MEM_UOPS_RETIRED.HITM",
         "PEBS": "1",
+        "PublicDescription": "This event counts the number of load micro-ops retired that got data from another core's cache. (Precise Event).",
         "SampleAfterValue": "200003",
         "UMask": "0x20"
     },
@@ -67,20 +74,22 @@
         "UMask": "0x1"
     },
     {
-        "BriefDescription": "Counts the number of load micro-ops retired that hit in the L2",
+        "BriefDescription": "Counts the number of load micro-ops retired that hit in the L2 (Precise Event)",
         "Data_LA": "1",
         "EventCode": "0x04",
         "EventName": "MEM_UOPS_RETIRED.L2_HIT_LOADS",
         "PEBS": "1",
+        "PublicDescription": "This event counts the number of load micro-uops retired that hit in the L2 (Precise Event)",
         "SampleAfterValue": "200003",
         "UMask": "0x2"
     },
     {
-        "BriefDescription": "Counts the number of load micro-ops retired that miss in the L2",
+        "BriefDescription": "Counts the number of load micro-ops retired that miss in the L2 (Precise Event)",
         "Data_LA": "1",
         "EventCode": "0x04",
         "EventName": "MEM_UOPS_RETIRED.L2_MISS_LOADS",
         "PEBS": "1",
+        "PublicDescription": "This event counts the number of load micro-ops retired that miss in the L2 (Precise Event)",
         "SampleAfterValue": "100007",
         "UMask": "0x4"
     },
@@ -620,6 +629,15 @@
         "SampleAfterValue": "100007",
         "UMask": "0x1"
     },
+    {
+        "BriefDescription": "Accounts for responses which miss its own tile's L2.",
+        "EventCode": "0xB7",
+        "EventName": "OFFCORE_RESPONSE.ANY_REQUEST.L2_MISS",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x18001981F8",
+        "SampleAfterValue": "100007",
+        "UMask": "0x1"
+    },
     {
         "BriefDescription": "Counts any request that are outstanding, per weighted cycle, from the time of the request to when any response is received. The outstanding response should be programmed only on PMC0.",
         "EventCode": "0xB7",
@@ -1664,15 +1682,6 @@
         "SampleAfterValue": "100007",
         "UMask": "0x1"
     },
-    {
-        "BriefDescription": "Counts L2 data RFO prefetches (includes PREFETCHW instruction) that provides no supplier details",
-        "EventCode": "0xB7",
-        "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.SUPPLIER_NONE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x0000020020",
-        "SampleAfterValue": "100007",
-        "UMask": "0x1"
-    },
     {
         "BriefDescription": "Counts Software Prefetches that accounts for any response",
         "EventCode": "0xB7",
tools/perf/pmu-events/arch/x86/knightslanding/floating-point.json +4 -4
index ecc96f32f167..089aa3ef345d 100644
@@ -8,18 +8,18 @@
         "UMask": "0x4"
     },
     {
-        "BriefDescription": "Counts the number of vector SSE, AVX, AVX2, AVX-512 micro-ops retired. More specifically, it counts packed SSE, AVX, AVX2, AVX-512 micro-ops (both floating point and integer) except for loads (memory-to-register mov-type micro-ops), packed byte and word multiplies.",
+        "BriefDescription": "Counts the number of packed SSE, AVX, AVX2, AVX-512 micro-ops (both floating point and integer) except for loads (memory-to-register mov-type micro-ops), packed byte and word multiplies.",
         "EventCode": "0xC2",
         "EventName": "UOPS_RETIRED.PACKED_SIMD",
-        "PublicDescription": "This event counts the number of packed vector SSE, AVX, AVX2, and AVX-512 micro-ops retired (floating point, integer and store) except for loads (memory-to-register mov-type micro-ops), packed byte and word multiplies.",
+        "PublicDescription": "The length of the packed operation (128bits, 256bits or 512bits) is not taken into account when updating the counter; all count the same (+1). \r\nMask (k) registers are ignored. For example: a micro-op operating with a mask that only enables one element or even zero elements will still trigger this counter (+1)\r\nThis event is defined at the micro-op level and not instruction level. Most instructions are implemented with one micro-op but not all.",
         "SampleAfterValue": "200003",
         "UMask": "0x40"
     },
     {
-        "BriefDescription": "Counts the number of scalar SSE, AVX, AVX2, AVX-512 micro-ops retired. More specifically, it counts scalar SSE, AVX, AVX2, AVX-512 micro-ops except for loads (memory-to-register mov-type micro ops), division, sqrt.",
+        "BriefDescription": "Counts the number of scalar SSE, AVX, AVX2, AVX-512 micro-ops except for loads (memory-to-register mov-type micro ops), division, sqrt.",
         "EventCode": "0xC2",
         "EventName": "UOPS_RETIRED.SCALAR_SIMD",
-        "PublicDescription": "This event counts the number of scalar SSE, AVX, AVX2, AVX-512 micro-ops retired (floating point, integer and store) except for loads (memory-to-register mov-type micro ops), division, sqrt.",
+        "PublicDescription": "This event is defined at the micro-op level and not instruction level. Most instructions are implemented with one micro-op but not all.",
         "SampleAfterValue": "200003",
         "UMask": "0x20"
     }
tools/perf/pmu-events/arch/x86/knightslanding/pipeline.json +32 -23

198 lines not on this page · raw message

tools/perf/pmu-events/arch/x86/knightslanding/uncore-cache.json +13 -13
index 1b8dcfa5461c..120e4813d82a 100644
@@ -2558,7 +2558,7 @@
         "Unit": "CHA"
     },
     {
-        "BriefDescription": "REQUESTQ'' includes:  IRQ, PRQ, IPQ, RRQ, WBQ (everything except for ISMQ)",
+        "BriefDescription": "REQUESTQ includes:  IRQ, PRQ, IPQ, RRQ, WBQ (everything except for ISMQ)",
         "EventCode": "0x2A",
         "EventName": "UNC_H_INGRESS_RETRY_REQ_Q0_RETRY.AD_REQ_VN0",
         "PerPkg": "1",
@@ -2566,7 +2566,7 @@
         "Unit": "CHA"
     },
     {
-        "BriefDescription": "REQUESTQ'' includes:  IRQ, PRQ, IPQ, RRQ, WBQ (everything except for ISMQ)",
+        "BriefDescription": "REQUESTQ includes:  IRQ, PRQ, IPQ, RRQ, WBQ (everything except for ISMQ)",
         "EventCode": "0x2A",
         "EventName": "UNC_H_INGRESS_RETRY_REQ_Q0_RETRY.AD_RSP_VN0",
         "PerPkg": "1",
@@ -2574,7 +2574,7 @@
         "Unit": "CHA"
     },
     {
-        "BriefDescription": "REQUESTQ'' includes:  IRQ, PRQ, IPQ, RRQ, WBQ (everything except for ISMQ)",
+        "BriefDescription": "REQUESTQ includes:  IRQ, PRQ, IPQ, RRQ, WBQ (everything except for ISMQ)",
         "EventCode": "0x2A",
         "EventName": "UNC_H_INGRESS_RETRY_REQ_Q0_RETRY.AK_NON_UPI",
         "PerPkg": "1",
@@ -2582,7 +2582,7 @@
         "Unit": "CHA"
     },
     {
-        "BriefDescription": "REQUESTQ'' includes:  IRQ, PRQ, IPQ, RRQ, WBQ (everything except for ISMQ)",
+        "BriefDescription": "REQUESTQ includes:  IRQ, PRQ, IPQ, RRQ, WBQ (everything except for ISMQ)",
         "EventCode": "0x2A",
         "EventName": "UNC_H_INGRESS_RETRY_REQ_Q0_RETRY.BL_NCB_VN0",
         "PerPkg": "1",
@@ -2590,7 +2590,7 @@
         "Unit": "CHA"
     },
     {
-        "BriefDescription": "REQUESTQ'' includes:  IRQ, PRQ, IPQ, RRQ, WBQ (everything except for ISMQ)",
+        "BriefDescription": "REQUESTQ includes:  IRQ, PRQ, IPQ, RRQ, WBQ (everything except for ISMQ)",
         "EventCode": "0x2A",
         "EventName": "UNC_H_INGRESS_RETRY_REQ_Q0_RETRY.BL_NCS_VN0",
         "PerPkg": "1",
@@ -2598,7 +2598,7 @@
         "Unit": "CHA"
     },
     {
-        "BriefDescription": "REQUESTQ'' includes:  IRQ, PRQ, IPQ, RRQ, WBQ (everything except for ISMQ)",
+        "BriefDescription": "REQUESTQ includes:  IRQ, PRQ, IPQ, RRQ, WBQ (everything except for ISMQ)",
         "EventCode": "0x2A",
         "EventName": "UNC_H_INGRESS_RETRY_REQ_Q0_RETRY.BL_RSP_VN0",
         "PerPkg": "1",
@@ -2606,7 +2606,7 @@
         "Unit": "CHA"
     },
     {
-        "BriefDescription": "REQUESTQ'' includes:  IRQ, PRQ, IPQ, RRQ, WBQ (everything except for ISMQ)",
+        "BriefDescription": "REQUESTQ includes:  IRQ, PRQ, IPQ, RRQ, WBQ (everything except for ISMQ)",
         "EventCode": "0x2A",
         "EventName": "UNC_H_INGRESS_RETRY_REQ_Q0_RETRY.BL_WB_VN0",
         "PerPkg": "1",
@@ -2614,7 +2614,7 @@
         "Unit": "CHA"
     },
     {
-        "BriefDescription": "REQUESTQ'' includes:  IRQ, PRQ, IPQ, RRQ, WBQ (everything except for ISMQ)",
+        "BriefDescription": "REQUESTQ includes:  IRQ, PRQ, IPQ, RRQ, WBQ (everything except for ISMQ)",
         "EventCode": "0x2A",
         "EventName": "UNC_H_INGRESS_RETRY_REQ_Q0_RETRY.IV_NON_UPI",
         "PerPkg": "1",
@@ -2622,7 +2622,7 @@
         "Unit": "CHA"
     },
     {
-        "BriefDescription": "REQUESTQ'' includes:  IRQ, PRQ, IPQ, RRQ, WBQ (everything except for ISMQ)",
+        "BriefDescription": "REQUESTQ includes:  IRQ, PRQ, IPQ, RRQ, WBQ (everything except for ISMQ)",
         "EventCode": "0x2B",
         "EventName": "UNC_H_INGRESS_RETRY_REQ_Q1_RETRY.ALLOW_SNP",
         "PerPkg": "1",
@@ -2630,7 +2630,7 @@
         "Unit": "CHA"
     },
     {
-        "BriefDescription": "REQUESTQ'' includes:  IRQ, PRQ, IPQ, RRQ, WBQ (everything except for ISMQ)",
+        "BriefDescription": "REQUESTQ includes:  IRQ, PRQ, IPQ, RRQ, WBQ (everything except for ISMQ)",
         "EventCode": "0x2B",
         "EventName": "UNC_H_INGRESS_RETRY_REQ_Q1_RETRY.ANY_REJECT_IRQ0",
         "PerPkg": "1",
@@ -2638,7 +2638,7 @@
         "Unit": "CHA"
     },
     {
-        "BriefDescription": "REQUESTQ'' includes:  IRQ, PRQ, IPQ, RRQ, WBQ (everything except for ISMQ)",
+        "BriefDescription": "REQUESTQ includes:  IRQ, PRQ, IPQ, RRQ, WBQ (everything except for ISMQ)",
         "EventCode": "0x2B",
         "EventName": "UNC_H_INGRESS_RETRY_REQ_Q1_RETRY.PA_MATCH",
         "PerPkg": "1",
@@ -2646,7 +2646,7 @@
         "Unit": "CHA"
     },
     {
-        "BriefDescription": "REQUESTQ'' includes:  IRQ, PRQ, IPQ, RRQ, WBQ (everything except for ISMQ)",
+        "BriefDescription": "REQUESTQ includes:  IRQ, PRQ, IPQ, RRQ, WBQ (everything except for ISMQ)",
         "EventCode": "0x2B",
         "EventName": "UNC_H_INGRESS_RETRY_REQ_Q1_RETRY.SF_VICTIM",
         "PerPkg": "1",
@@ -2654,7 +2654,7 @@
         "Unit": "CHA"
     },
     {
-        "BriefDescription": "REQUESTQ'' includes:  IRQ, PRQ, IPQ, RRQ, WBQ (everything except for ISMQ)",
+        "BriefDescription": "REQUESTQ includes:  IRQ, PRQ, IPQ, RRQ, WBQ (everything except for ISMQ)",
         "EventCode": "0x2B",
         "EventName": "UNC_H_INGRESS_RETRY_REQ_Q1_RETRY.SF_WAY",
         "PerPkg": "1",
tools/perf/pmu-events/arch/x86/knightslanding/virtual-memory.json +1 -1
index 99a8fa8f19cc..9be30a33b43b 100644
@@ -1,6 +1,6 @@
 [
     {
-        "BriefDescription": "Counts the number of load micro-ops retired that cause a DTLB miss",
+        "BriefDescription": "Counts the number of load micro-ops retired that cause a DTLB miss (Precise Event)",
         "Data_LA": "1",
         "EventCode": "0x04",
         "EventName": "MEM_UOPS_RETIRED.DTLB_MISS_LOADS",
tools/perf/pmu-events/arch/x86/mapfile.csv +1 -1
index 24f03cd804f6..a97f0734099a 100644
@@ -19,7 +19,7 @@ GenuineIntel-6-6[AC],v1.21,icelakex,core
 GenuineIntel-6-3A,v24,ivybridge,core
 GenuineIntel-6-3E,v24,ivytown,core
 GenuineIntel-6-2D,v24,jaketown,core
-GenuineIntel-6-(57|85),v10,knightslanding,core
+GenuineIntel-6-(57|85),v16,knightslanding,core
 GenuineIntel-6-BD,v1.00,lunarlake,core
 GenuineIntel-6-A[AC],v1.04,meteorlake,core
 GenuineIntel-6-1[AEF],v4,nehalemep,core
Signature · 1 line
2.42.0.459.ge4e396fd5e-goog
author reviewer
#3 lore raw

PATCH 4/4 perf vendor events intel: Update meteorlake events to v1.05

In reply to Ian Rogers

v1.05 was released in:
https://github.com/intel/perfmon/commit/405d3ee987d756b5b5d9a64d8a8fa77559822ecf

Update created using:
https://github.com/intel/perfmon/blob/main/scripts/create_perf_json.py

---
 tools/perf/pmu-events/arch/x86/mapfile.csv    |  2 +-
 .../pmu-events/arch/x86/meteorlake/cache.json | 30 ++++++++++
 .../arch/x86/meteorlake/frontend.json         | 29 ++++++++--
 .../arch/x86/meteorlake/memory.json           | 28 +++++++++
 .../pmu-events/arch/x86/meteorlake/other.json | 40 +++++++++++++
 .../arch/x86/meteorlake/pipeline.json         | 57 +++++++++++++++++++
 6 files changed, 181 insertions(+), 5 deletions(-)
tools/perf/pmu-events/arch/x86/mapfile.csv +1 -1
index a97f0734099a..e57fde489425 100644
@@ -21,7 +21,7 @@ GenuineIntel-6-3E,v24,ivytown,core
 GenuineIntel-6-2D,v24,jaketown,core
 GenuineIntel-6-(57|85),v16,knightslanding,core
 GenuineIntel-6-BD,v1.00,lunarlake,core
-GenuineIntel-6-A[AC],v1.04,meteorlake,core
+GenuineIntel-6-A[AC],v1.05,meteorlake,core
 GenuineIntel-6-1[AEF],v4,nehalemep,core
 GenuineIntel-6-2E,v4,nehalemex,core
 GenuineIntel-6-A7,v1.01,rocketlake,core
tools/perf/pmu-events/arch/x86/meteorlake/cache.json +30 -0
index 1de0200b32f6..5fef87502d4b 100644
@@ -966,6 +966,16 @@
         "UMask": "0x3",
         "Unit": "cpu_core"
     },
+    {
+        "BriefDescription": "Counts demand data reads that were supplied by the L3 cache where a snoop was sent, the snoop hit, and modified data was forwarded.",
+        "EventCode": "0xB7",
+        "EventName": "OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x10003C0001",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1",
+        "Unit": "cpu_atom"
+    },
     {
         "BriefDescription": "Counts demand data reads that resulted in a snoop hit in another cores caches, data forwarding is required as the data is modified.",
         "EventCode": "0x2A,0x2B",
@@ -976,6 +986,16 @@
         "UMask": "0x1",
         "Unit": "cpu_core"
     },
+    {
+        "BriefDescription": "Counts demand data reads that were supplied by the L3 cache where a snoop was sent, the snoop hit, and non-modified data was forwarded.",
+        "EventCode": "0xB7",
+        "EventName": "OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x8003C0001",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1",
+        "Unit": "cpu_atom"
+    },
     {
         "BriefDescription": "Counts demand data reads that resulted in a snoop hit in another cores caches which forwarded the unmodified data to the requesting core.",
         "EventCode": "0x2A,0x2B",
@@ -986,6 +1006,16 @@
         "UMask": "0x1",
         "Unit": "cpu_core"
     },
+    {
+        "BriefDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that were supplied by the L3 cache where a snoop was sent, the snoop hit, and modified data was forwarded.",
+        "EventCode": "0xB7",
+        "EventName": "OCR.DEMAND_RFO.L3_HIT.SNOOP_HITM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x10003C0002",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1",
+        "Unit": "cpu_atom"
+    },
     {
         "BriefDescription": "Counts demand read for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that resulted in a snoop hit in another cores caches, data forwarding is required as the data is modified.",
         "EventCode": "0x2A,0x2B",
tools/perf/pmu-events/arch/x86/meteorlake/frontend.json +25 -4
index 8264419500a5..9da8689eda81 100644
@@ -460,6 +460,27 @@
         "UMask": "0x1",
         "Unit": "cpu_core"
     },
+    {
+        "BriefDescription": "Cycles when no uops are not delivered by the IDQ when backend of the machine is not stalled [This event is alias to IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE]",
+        "CounterMask": "6",
+        "EventCode": "0x9c",
+        "EventName": "IDQ_BUBBLES.CYCLES_0_UOPS_DELIV.CORE",
+        "PublicDescription": "Counts the number of cycles when no uops were delivered by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle. [This event is alias to IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE]",
+        "SampleAfterValue": "1000003",
+        "UMask": "0x1",
+        "Unit": "cpu_core"
+    },
+    {
+        "BriefDescription": "Cycles when optimal number of uops was delivered to the back-end when the back-end is not stalled [This event is alias to IDQ_UOPS_NOT_DELIVERED.CYCLES_FE_WAS_OK]",
+        "CounterMask": "1",
+        "EventCode": "0x9c",
+        "EventName": "IDQ_BUBBLES.CYCLES_FE_WAS_OK",
+        "Invert": "1",
+        "PublicDescription": "Counts the number of cycles when the optimal number of uops were delivered by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle. [This event is alias to IDQ_UOPS_NOT_DELIVERED.CYCLES_FE_WAS_OK]",
+        "SampleAfterValue": "1000003",
+        "UMask": "0x1",
+        "Unit": "cpu_core"
+    },
     {
         "BriefDescription": "Uops not delivered by IDQ when backend of the machine is not stalled",
         "EventCode": "0x9c",
@@ -470,22 +491,22 @@
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "Cycles when no uops are not delivered by the IDQ when backend of the machine is not stalled",
+        "BriefDescription": "Cycles when no uops are not delivered by the IDQ when backend of the machine is not stalled [This event is alias to IDQ_BUBBLES.CYCLES_0_UOPS_DELIV.CORE]",
         "CounterMask": "6",
         "EventCode": "0x9c",
         "EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE",
-        "PublicDescription": "Counts the number of cycles when no uops were delivered by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle.",
+        "PublicDescription": "Counts the number of cycles when no uops were delivered by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle. [This event is alias to IDQ_BUBBLES.CYCLES_0_UOPS_DELIV.CORE]",
         "SampleAfterValue": "1000003",
         "UMask": "0x1",
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "Cycles when optimal number of uops was delivered to the back-end when the back-end is not stalled",
+        "BriefDescription": "Cycles when optimal number of uops was delivered to the back-end when the back-end is not stalled [This event is alias to IDQ_BUBBLES.CYCLES_FE_WAS_OK]",
         "CounterMask": "1",
         "EventCode": "0x9c",
         "EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_FE_WAS_OK",
         "Invert": "1",
-        "PublicDescription": "Counts the number of cycles when the optimal number of uops were delivered by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle.",
+        "PublicDescription": "Counts the number of cycles when the optimal number of uops were delivered by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle. [This event is alias to IDQ_BUBBLES.CYCLES_FE_WAS_OK]",
         "SampleAfterValue": "1000003",
         "UMask": "0x1",
         "Unit": "cpu_core"
tools/perf/pmu-events/arch/x86/meteorlake/memory.json +28 -0
index 2605e1d0ba9f..1c1a2cf8d9ac 100644
@@ -66,6 +66,14 @@
         "UMask": "0x84",
         "Unit": "cpu_atom"
     },
+    {
+        "BriefDescription": "Counts the number of machine clears due to memory ordering caused by a snoop from an external agent. Does not count internally generated machine clears such as those due to memory disambiguation.",
+        "EventCode": "0xc3",
+        "EventName": "MACHINE_CLEARS.MEMORY_ORDERING",
+        "SampleAfterValue": "20003",
+        "UMask": "0x2",
+        "Unit": "cpu_atom"
+    },
     {
         "BriefDescription": "Number of machine clears due to memory ordering conflicts.",
         "EventCode": "0xc3",
@@ -279,6 +287,26 @@
         "UMask": "0x4",
         "Unit": "cpu_atom"
     },
+    {
+        "BriefDescription": "Counts demand data reads that were not supplied by the L3 cache.",
+        "EventCode": "0x2A,0x2B",
+        "EventName": "OCR.DEMAND_DATA_RD.L3_MISS",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x3FBFC00001",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1",
+        "Unit": "cpu_core"
+    },
+    {
+        "BriefDescription": "Counts demand read for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that were not supplied by the L3 cache.",
+        "EventCode": "0x2A,0x2B",
+        "EventName": "OCR.DEMAND_RFO.L3_MISS",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x3FBFC00002",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1",
+        "Unit": "cpu_core"
+    },
     {
         "BriefDescription": "Counts demand data read requests that miss the L3 cache.",
         "EventCode": "0x21",
tools/perf/pmu-events/arch/x86/meteorlake/other.json +40 -0
index f4c603599df4..d55e792c0c43 100644
@@ -7,6 +7,46 @@
         "UMask": "0x8",
         "Unit": "cpu_core"
     },
+    {
+        "BriefDescription": "Counts demand data reads that have any type of response.",
+        "EventCode": "0x2A,0x2B",
+        "EventName": "OCR.DEMAND_DATA_RD.ANY_RESPONSE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x10001",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1",
+        "Unit": "cpu_core"
+    },
+    {
+        "BriefDescription": "Counts demand data reads that were supplied by DRAM.",
+        "EventCode": "0x2A,0x2B",
+        "EventName": "OCR.DEMAND_DATA_RD.DRAM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x184000001",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1",
+        "Unit": "cpu_core"
+    },
+    {
+        "BriefDescription": "Counts demand read for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that have any type of response.",
+        "EventCode": "0x2A,0x2B",
+        "EventName": "OCR.DEMAND_RFO.ANY_RESPONSE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x10002",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1",
+        "Unit": "cpu_core"
+    },
+    {
+        "BriefDescription": "Counts streaming stores that have any type of response.",
+        "EventCode": "0xB7",
+        "EventName": "OCR.STREAMING_WR.ANY_RESPONSE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x10800",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1",
+        "Unit": "cpu_atom"
+    },
     {
         "BriefDescription": "Counts streaming stores that have any type of response.",
         "EventCode": "0x2A,0x2B",
tools/perf/pmu-events/arch/x86/meteorlake/pipeline.json +57 -0

93 lines not on this page · raw message

Signature · 1 line
2.42.0.459.ge4e396fd5e-goog