perf vendor events intel update
Ian Rogers
reviewercover perf vendor events intel update
Update events to the latest on:
https://github.com/intel/perfmon
Using the converter script:
https://github.com/intel/perfmon/blob/main/scripts/create_perf_json.py
Ian Rogers (12):
perf vendor events intel: Update cascadelakex to 1.21
perf vendor events intel: Update emeraldrapids to 1.06 perf vendor events intel: Update grandridge to 1.02
perf vendor events intel: Update icelakex to 1.24
perf vendor events intel: Update lunarlake to 1.01
perf vendor events intel: Update meteorlake to 1.08
perf vendor events intel: Update sapphirerapids to 1.20 perf vendor events intel: Update sierraforest to 1.02
perf vendor events intel: Update skylakex to 1.33
perf vendor events intel: Update skylake to v58
perf vendor events intel: Update snowridgex to 1.22
perf vendor events intel: Remove info metrics erroneously in TopdownL1
.../arch/x86/broadwellx/bdx-metrics.json | 35 +++--- .../arch/x86/cascadelakex/clx-metrics.json | 85 +++++-------- .../arch/x86/cascadelakex/frontend.json | 10 +- .../arch/x86/cascadelakex/memory.json | 2 +- .../arch/x86/cascadelakex/other.json | 2 +- .../arch/x86/cascadelakex/pipeline.json | 2 +- .../x86/cascadelakex/uncore-interconnect.json | 14 +-- .../arch/x86/cascadelakex/virtual-memory.json | 2 +- .../arch/x86/emeraldrapids/frontend.json | 2 +- .../arch/x86/emeraldrapids/memory.json | 1 + .../arch/x86/emeraldrapids/pipeline.json | 3 + .../arch/x86/emeraldrapids/uncore-cache.json | 112 ++++++++++++++++- .../emeraldrapids/uncore-interconnect.json | 26 ++-- .../arch/x86/grandridge/pipeline.json | 43 ++++++- .../arch/x86/grandridge/uncore-cache.json | 28 ++++- .../arch/x86/haswellx/hsx-metrics.json | 35 +++--- .../arch/x86/icelakex/frontend.json | 2 +- .../arch/x86/icelakex/icx-metrics.json | 95 ++++++-------- .../pmu-events/arch/x86/icelakex/memory.json | 1 + .../arch/x86/icelakex/uncore-cache.json | 22 +++- .../x86/icelakex/uncore-interconnect.json | 64 +++++----- .../arch/x86/icelakex/uncore-io.json | 11 -- .../pmu-events/arch/x86/lunarlake/cache.json | 24 ++-- .../arch/x86/lunarlake/frontend.json | 2 +- .../pmu-events/arch/x86/lunarlake/memory.json | 4 +- .../pmu-events/arch/x86/lunarlake/other.json | 4 +- .../arch/x86/lunarlake/pipeline.json | 109 +++++++++++++--- tools/perf/pmu-events/arch/x86/mapfile.csv | 20 +-- .../pmu-events/arch/x86/meteorlake/cache.json | 30 +++++ .../arch/x86/meteorlake/frontend.json | 4 +- .../arch/x86/meteorlake/memory.json | 20 +++ .../pmu-events/arch/x86/meteorlake/other.json | 42 ++++++- .../arch/x86/meteorlake/pipeline.json | 44 +++++-- .../x86/meteorlake/uncore-interconnect.json | 22 +++- .../arch/x86/sapphirerapids/cache.json | 1 + .../arch/x86/sapphirerapids/frontend.json | 2 +- .../arch/x86/sapphirerapids/memory.json | 1 + .../arch/x86/sapphirerapids/pipeline.json | 19 +-- .../arch/x86/sapphirerapids/spr-metrics.json | 119 +++++++----------- .../arch/x86/sapphirerapids/uncore-cache.json | 112 ++++++++++++++++- .../sapphirerapids/uncore-interconnect.json | 26 ++-- .../arch/x86/sierraforest/pipeline.json | 36 +++++- .../pmu-events/arch/x86/skylake/frontend.json | 10 +- .../pmu-events/arch/x86/skylakex/cache.json | 9 ++ .../arch/x86/skylakex/frontend.json | 10 +- .../pmu-events/arch/x86/skylakex/memory.json | 2 +- .../pmu-events/arch/x86/skylakex/other.json | 2 +- .../arch/x86/skylakex/pipeline.json | 2 +- .../arch/x86/skylakex/skx-metrics.json | 85 +++++-------- .../x86/skylakex/uncore-interconnect.json | 14 +-- .../arch/x86/skylakex/uncore-io.json | 2 +- .../arch/x86/skylakex/virtual-memory.json | 2 +- .../arch/x86/snowridgex/uncore-cache.json | 4 +- .../x86/snowridgex/uncore-interconnect.json | 6 +- .../arch/x86/snowridgex/uncore-io.json | 11 -- 55 files changed, 911 insertions(+), 486 deletions(-)
Signature · 1 line
2.44.0.396.g6e790dbe36-goog
Ian Rogers
reviewerPATCH 1/12 perf vendor events intel: Update cascadelakex to 1.21
Update events from 1.20 to 1.21 as released in:
https://github.com/intel/perfmon/commit/fcfdba3be8f3be81ad6b509fdebf953ead92dc2c
Largely fixes spelling and descriptions.
--- .../pmu-events/arch/x86/cascadelakex/frontend.json | 10 +++++----- .../pmu-events/arch/x86/cascadelakex/memory.json | 2 +- .../pmu-events/arch/x86/cascadelakex/other.json | 2 +- .../pmu-events/arch/x86/cascadelakex/pipeline.json | 2 +- .../arch/x86/cascadelakex/uncore-interconnect.json | 14 +++++++------- .../arch/x86/cascadelakex/virtual-memory.json | 2 +- tools/perf/pmu-events/arch/x86/mapfile.csv | 2 +- 7 files changed, 17 insertions(+), 17 deletions(-)
tools/perf/pmu-events/arch/x86/cascadelakex/frontend.json +5 -5
@@ -19,7 +19,7 @@ "BriefDescription": "Decode Stream Buffer (DSB)-to-MITE switches", "EventCode": "0xAB", "EventName": "DSB2MITE_SWITCHES.COUNT", - "PublicDescription": "This event counts the number of the Decode Stream Buffer (DSB)-to-MITE switches including all misses because of missing Decode Stream Buffer (DSB) cache and u-arch forced misses.\nNote: Invoking MITE requires two or three cycles delay.", + "PublicDescription": "This event counts the number of the Decode Stream Buffer (DSB)-to-MITE switches including all misses because of missing Decode Stream Buffer (DSB) cache and u-arch forced misses. Note: Invoking MITE requires two or three cycles delay.", "SampleAfterValue": "2000003", "UMask": "0x1" },
@@ -267,11 +267,11 @@ "UMask": "0x4" }, { - "BriefDescription": "Cycles Decode Stream Buffer (DSB) is delivering 4 Uops [This event is alias to IDQ.DSB_CYCLES_OK]", + "BriefDescription": "Cycles Decode Stream Buffer (DSB) is delivering 4 or more Uops [This event is alias to IDQ.DSB_CYCLES_OK]", "CounterMask": "4", "EventCode": "0x79", "EventName": "IDQ.ALL_DSB_CYCLES_4_UOPS", - "PublicDescription": "Counts the number of cycles 4 uops were delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path. Count includes uops that may 'bypass' the IDQ. [This event is alias to IDQ.DSB_CYCLES_OK]", + "PublicDescription": "Counts the number of cycles 4 or more uops were delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path. Count includes uops that may 'bypass' the IDQ. [This event is alias to IDQ.DSB_CYCLES_OK]", "SampleAfterValue": "2000003", "UMask": "0x18" },
@@ -321,11 +321,11 @@ "UMask": "0x18" }, { - "BriefDescription": "Cycles Decode Stream Buffer (DSB) is delivering 4 Uops [This event is alias to IDQ.ALL_DSB_CYCLES_4_UOPS]", + "BriefDescription": "Cycles Decode Stream Buffer (DSB) is delivering 4 or more Uops [This event is alias to IDQ.ALL_DSB_CYCLES_4_UOPS]", "CounterMask": "4", "EventCode": "0x79", "EventName": "IDQ.DSB_CYCLES_OK", - "PublicDescription": "Counts the number of cycles 4 uops were delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path. Count includes uops that may 'bypass' the IDQ. [This event is alias to IDQ.ALL_DSB_CYCLES_4_UOPS]", + "PublicDescription": "Counts the number of cycles 4 or more uops were delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path. Count includes uops that may 'bypass' the IDQ. [This event is alias to IDQ.ALL_DSB_CYCLES_4_UOPS]", "SampleAfterValue": "2000003", "UMask": "0x18" },
tools/perf/pmu-events/arch/x86/cascadelakex/memory.json +1 -1
@@ -6866,7 +6866,7 @@ "BriefDescription": "Number of times an RTM execution aborted due to any reasons (multiple categories may count as one).", "EventCode": "0xC9", "EventName": "RTM_RETIRED.ABORTED", - "PEBS": "1", + "PEBS": "2", "PublicDescription": "Number of times RTM abort was triggered.", "SampleAfterValue": "2000003", "UMask": "0x4"
tools/perf/pmu-events/arch/x86/cascadelakex/other.json +1 -1
@@ -19,7 +19,7 @@ "BriefDescription": "Core cycles where the core was running in a manner where Turbo may be clipped to the AVX512 turbo schedule.", "EventCode": "0x28", "EventName": "CORE_POWER.LVL2_TURBO_LICENSE", - "PublicDescription": "Core cycles where the core was running with power-delivery for license level 2 (introduced in Skylake Server michroarchtecture). This includes high current AVX 512-bit instructions.", + "PublicDescription": "Core cycles where the core was running with power-delivery for license level 2 (introduced in Skylake Server microarchitecture). This includes high current AVX 512-bit instructions.", "SampleAfterValue": "200003", "UMask": "0x20" },
tools/perf/pmu-events/arch/x86/cascadelakex/pipeline.json +1 -1
@@ -396,7 +396,7 @@ "Errata": "SKL091, SKL044", "EventCode": "0xC0", "EventName": "INST_RETIRED.NOP", - "PEBS": "1", + "PEBS": "2", "SampleAfterValue": "2000003", "UMask": "0x2" },
tools/perf/pmu-events/arch/x86/cascadelakex/uncore-interconnect.json +7 -7
@@ -38,7 +38,7 @@ "EventCode": "0x10", "EventName": "UNC_I_COHERENT_OPS.CLFLUSH", "PerPkg": "1", - "PublicDescription": "Counts the number of coherency related operations servied by the IRP", + "PublicDescription": "Counts the number of coherency related operations serviced by the IRP", "UMask": "0x80", "Unit": "IRP" },
@@ -47,7 +47,7 @@ "EventCode": "0x10", "EventName": "UNC_I_COHERENT_OPS.CRD", "PerPkg": "1", - "PublicDescription": "Counts the number of coherency related operations servied by the IRP", + "PublicDescription": "Counts the number of coherency related operations serviced by the IRP", "UMask": "0x2", "Unit": "IRP" },
@@ -56,7 +56,7 @@ "EventCode": "0x10", "EventName": "UNC_I_COHERENT_OPS.DRD", "PerPkg": "1", - "PublicDescription": "Counts the number of coherency related operations servied by the IRP", + "PublicDescription": "Counts the number of coherency related operations serviced by the IRP", "UMask": "0x4", "Unit": "IRP" },
@@ -65,7 +65,7 @@ "EventCode": "0x10", "EventName": "UNC_I_COHERENT_OPS.PCIDCAHINT", "PerPkg": "1", - "PublicDescription": "Counts the number of coherency related operations servied by the IRP", + "PublicDescription": "Counts the number of coherency related operations serviced by the IRP", "UMask": "0x20", "Unit": "IRP" },
@@ -74,7 +74,7 @@ "EventCode": "0x10", "EventName": "UNC_I_COHERENT_OPS.PCIRDCUR", "PerPkg": "1", - "PublicDescription": "Counts the number of coherency related operations servied by the IRP", + "PublicDescription": "Counts the number of coherency related operations serviced by the IRP", "UMask": "0x1", "Unit": "IRP" },
@@ -101,7 +101,7 @@ "EventCode": "0x10", "EventName": "UNC_I_COHERENT_OPS.WBMTOI", "PerPkg": "1", - "PublicDescription": "Counts the number of coherency related operations servied by the IRP", + "PublicDescription": "Counts the number of coherency related operations serviced by the IRP", "UMask": "0x40", "Unit": "IRP" },
@@ -500,7 +500,7 @@ "EventCode": "0x11", "EventName": "UNC_I_TRANSACTIONS.WRITES", "PerPkg": "1", - "PublicDescription": "Counts the number of Inbound transactions from the IRP to the Uncore. This can be filtered based on request type in addition to the source queue. Note the special filtering equation. We do OR-reduction on the request type. If the SOURCE bit is set, then we also do AND qualification based on the source portID.; Trackes only write requests. Each write request should have a prefetch, so there is no need to explicitly track these requests. For writes that are tickled and have to retry, the counter will be incremented for each retry.", + "PublicDescription": "Counts the number of Inbound transactions from the IRP to the Uncore. This can be filtered based on request type in addition to the source queue. Note the special filtering equation. We do OR-reduction on the request type. If the SOURCE bit is set, then we also do AND qualification based on the source portID.; Tracks only write requests. Each write request should have a prefetch, so there is no need to explicitly track these requests. For writes that are tickled and have to retry, the counter will be incremented for each retry.", "UMask": "0x2", "Unit": "IRP" },
tools/perf/pmu-events/arch/x86/cascadelakex/virtual-memory.json +1 -1
@@ -205,7 +205,7 @@ "BriefDescription": "Counts 1 per cycle for each PMH that is busy with a page walk for an instruction fetch request. EPT page walk duration are excluded in Skylake.", "EventCode": "0x85", "EventName": "ITLB_MISSES.WALK_PENDING", - "PublicDescription": "Counts 1 per cycle for each PMH (Page Miss Handler) that is busy with a page walk for an instruction fetch request. EPT page walk duration are excluded in Skylake michroarchitecture.", + "PublicDescription": "Counts 1 per cycle for each PMH (Page Miss Handler) that is busy with a page walk for an instruction fetch request. EPT page walk duration are excluded in Skylake microarchitecture.", "SampleAfterValue": "100003", "UMask": "0x10" },
tools/perf/pmu-events/arch/x86/mapfile.csv +1 -1
@@ -5,7 +5,7 @@ GenuineIntel-6-(1C|26|27|35|36),v5,bonnell,core GenuineIntel-6-(3D|47),v29,broadwell,core GenuineIntel-6-56,v11,broadwellde,core GenuineIntel-6-4F,v22,broadwellx,core -GenuineIntel-6-55-[56789ABCDEF],v1.20,cascadelakex,core +GenuineIntel-6-55-[56789ABCDEF],v1.21,cascadelakex,core GenuineIntel-6-9[6C],v1.04,elkhartlake,core GenuineIntel-6-CF,v1.03,emeraldrapids,core GenuineIntel-6-5[CF],v13,goldmont,core
Signature · 1 line
2.44.0.396.g6e790dbe36-goog
Ian Rogers
reviewerPATCH 2/12 perf vendor events intel: Update emeraldrapids to 1.06
In reply to Ian RogersUpdate events from 1.03 to 1.96 as released in:
https://github.com/intel/perfmon/commit/21a8be3ea7918749141db4036fb65a2343cd865d
Fixes spelling and descriptions. Adds cache miss latency events UNC_CHA_TOR_(INSERTS|OCCUPANCY).IO_(PCIRDCUR|ITOM|ITOMCACHENEAR)_(LOCAL|REMOTE).
--- .../arch/x86/emeraldrapids/frontend.json | 2 +- .../arch/x86/emeraldrapids/memory.json | 1 + .../arch/x86/emeraldrapids/pipeline.json | 3 + .../arch/x86/emeraldrapids/uncore-cache.json | 112 +++++++++++++++++- .../emeraldrapids/uncore-interconnect.json | 26 ++-- tools/perf/pmu-events/arch/x86/mapfile.csv | 2 +- 6 files changed, 129 insertions(+), 17 deletions(-)
tools/perf/pmu-events/arch/x86/emeraldrapids/frontend.json +1 -1
@@ -267,7 +267,7 @@ "CounterMask": "6", "EventCode": "0x79", "EventName": "IDQ.DSB_CYCLES_OK", - "PublicDescription": "Counts the number of cycles where optimal number of uops was delivered to the Instruction Decode Queue (IDQ) from the MITE (legacy decode pipeline) path. During these cycles uops are not being delivered from the Decode Stream Buffer (DSB).", + "PublicDescription": "Counts the number of cycles where optimal number of uops was delivered to the Instruction Decode Queue (IDQ) from the DSB (Decode Stream Buffer) path. Count includes uops that may 'bypass' the IDQ.", "SampleAfterValue": "2000003", "UMask": "0x8" },
tools/perf/pmu-events/arch/x86/emeraldrapids/memory.json +1 -0
@@ -264,6 +264,7 @@ "BriefDescription": "Number of times an RTM execution aborted.", "EventCode": "0xc9", "EventName": "RTM_RETIRED.ABORTED", + "PEBS": "1", "PublicDescription": "Counts the number of times RTM abort was triggered.", "SampleAfterValue": "100003", "UMask": "0x4"
tools/perf/pmu-events/arch/x86/emeraldrapids/pipeline.json +3 -0
@@ -428,6 +428,7 @@ "BriefDescription": "INST_RETIRED.MACRO_FUSED", "EventCode": "0xc0", "EventName": "INST_RETIRED.MACRO_FUSED", + "PEBS": "1", "SampleAfterValue": "2000003", "UMask": "0x10" },
@@ -435,6 +436,7 @@ "BriefDescription": "Retired NOP instructions.", "EventCode": "0xc0", "EventName": "INST_RETIRED.NOP", + "PEBS": "1", "PublicDescription": "Counts all retired NOP or ENDBR32/64 instructions", "SampleAfterValue": "2000003", "UMask": "0x2"
@@ -451,6 +453,7 @@ "BriefDescription": "Iterations of Repeat string retired instructions.", "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"
tools/perf/pmu-events/arch/x86/emeraldrapids/uncore-cache.json +110 -2
148 lines not on this page · raw message
tools/perf/pmu-events/arch/x86/emeraldrapids/uncore-interconnect.json +13 -13
@@ -4888,7 +4888,7 @@ "Unit": "MDF" }, { - "BriefDescription": "Number of cycles incoming messages from the vertical ring that are bounced at the SBO\r\nIngress (V-EMIB) (AD)", + "BriefDescription": "Number of cycles incoming messages from the vertical ring that are bounced at the SBO Ingress (V-EMIB) (AD)", "EventCode": "0x4B", "EventName": "UNC_MDF_CRS_TxR_V_BOUNCES.AD", "PerPkg": "1",
@@ -4897,7 +4897,7 @@ "Unit": "MDF" }, { - "BriefDescription": "Number of cycles incoming messages from the vertical ring that are bounced at the SBO\r\nIngress (V-EMIB) (AK)", + "BriefDescription": "Number of cycles incoming messages from the vertical ring that are bounced at the SBO Ingress (V-EMIB) (AK)", "EventCode": "0x4B", "EventName": "UNC_MDF_CRS_TxR_V_BOUNCES.AK", "PerPkg": "1",
@@ -4906,7 +4906,7 @@ "Unit": "MDF" }, { - "BriefDescription": "Number of cycles incoming messages from the vertical ring that are bounced at the SBO\r\nIngress (V-EMIB) (AKC)", + "BriefDescription": "Number of cycles incoming messages from the vertical ring that are bounced at the SBO Ingress (V-EMIB) (AKC)", "EventCode": "0x4B", "EventName": "UNC_MDF_CRS_TxR_V_BOUNCES.AKC", "PerPkg": "1",
@@ -4915,7 +4915,7 @@ "Unit": "MDF" }, { - "BriefDescription": "Number of cycles incoming messages from the vertical ring that are bounced at the SBO\r\nIngress (V-EMIB) (BL)", + "BriefDescription": "Number of cycles incoming messages from the vertical ring that are bounced at the SBO Ingress (V-EMIB) (BL)", "EventCode": "0x4B", "EventName": "UNC_MDF_CRS_TxR_V_BOUNCES.BL", "PerPkg": "1",
@@ -4924,7 +4924,7 @@ "Unit": "MDF" }, { - "BriefDescription": "Number of cycles incoming messages from the vertical ring that are bounced at the SBO\r\nIngress (V-EMIB) (IV)", + "BriefDescription": "Number of cycles incoming messages from the vertical ring that are bounced at the SBO Ingress (V-EMIB) (IV)", "EventCode": "0x4B", "EventName": "UNC_MDF_CRS_TxR_V_BOUNCES.IV", "PerPkg": "1",
@@ -5291,7 +5291,7 @@ "EventCode": "0x05", "EventName": "UNC_UPI_RxL_BASIC_HDR_MATCH.NCB", "PerPkg": "1", - "PublicDescription": "Matches on Receive path of a UPI Port : Non-Coherent Bypass : Matches on Receive path of a UPI port.\r\nMatch based on UMask specific bits:\r\nZ: Message Class (3-bit)\r\nY: Message Class Enable\r\nW: Opcode (4-bit)\r\nV: Opcode Enable\r\nU: Local Enable\r\nT: Remote Enable\r\nS: Data Hdr Enable\r\nR: Non-Data Hdr Enable\r\nQ: Dual Slot Hdr Enable\r\nP: Single Slot Hdr Enable\r\nLink Layer control types are excluded (LL CTRL, slot NULL, LLCRD) even under specific opcode match_en cases.\r\nNote: If Message Class is disabled, we expect opcode to also be disabled.", + "PublicDescription": "Matches on Receive path of a UPI Port : Non-Coherent Bypass : Matches on Receive path of a UPI port. Match based on UMask specific bits: Z: Message Class (3-bit) Y: Message Class Enable W: Opcode (4-bit) V: Opcode Enable U: Local Enable T: Remote Enable S: Data Hdr Enable R: Non-Data Hdr Enable Q: Dual Slot Hdr Enable P: Single Slot Hdr Enable Link Layer control types are excluded (LL CTRL, slot NULL, LLCRD) even under specific opcode match_en cases. Note: If Message Class is disabled, we expect opcode to also be disabled.", "UMask": "0xe", "Unit": "UPI" },
@@ -5300,7 +5300,7 @@ "EventCode": "0x05", "EventName": "UNC_UPI_RxL_BASIC_HDR_MATCH.NCB_OPC", "PerPkg": "1", - "PublicDescription": "Matches on Receive path of a UPI Port : Non-Coherent Bypass, Match Opcode : Matches on Receive path of a UPI port.\r\nMatch based on UMask specific bits:\r\nZ: Message Class (3-bit)\r\nY: Message Class Enable\r\nW: Opcode (4-bit)\r\nV: Opcode Enable\r\nU: Local Enable\r\nT: Remote Enable\r\nS: Data Hdr Enable\r\nR: Non-Data Hdr Enable\r\nQ: Dual Slot Hdr Enable\r\nP: Single Slot Hdr Enable\r\nLink Layer control types are excluded (LL CTRL, slot NULL, LLCRD) even under specific opcode match_en cases.\r\nNote: If Message Class is disabled, we expect opcode to also be disabled.", + "PublicDescription": "Matches on Receive path of a UPI Port : Non-Coherent Bypass, Match Opcode : Matches on Receive path of a UPI port. Match based on UMask specific bits: Z: Message Class (3-bit) Y: Message Class Enable W: Opcode (4-bit) V: Opcode Enable U: Local Enable T: Remote Enable S: Data Hdr Enable R: Non-Data Hdr Enable Q: Dual Slot Hdr Enable P: Single Slot Hdr Enable Link Layer control types are excluded (LL CTRL, slot NULL, LLCRD) even under specific opcode match_en cases. Note: If Message Class is disabled, we expect opcode to also be disabled.", "UMask": "0x10e", "Unit": "UPI" },
@@ -5309,7 +5309,7 @@ "EventCode": "0x05", "EventName": "UNC_UPI_RxL_BASIC_HDR_MATCH.NCS", "PerPkg": "1", - "PublicDescription": "Matches on Receive path of a UPI Port : Non-Coherent Standard : Matches on Receive path of a UPI port.\r\nMatch based on UMask specific bits:\r\nZ: Message Class (3-bit)\r\nY: Message Class Enable\r\nW: Opcode (4-bit)\r\nV: Opcode Enable\r\nU: Local Enable\r\nT: Remote Enable\r\nS: Data Hdr Enable\r\nR: Non-Data Hdr Enable\r\nQ: Dual Slot Hdr Enable\r\nP: Single Slot Hdr Enable\r\nLink Layer control types are excluded (LL CTRL, slot NULL, LLCRD) even under specific opcode match_en cases.\r\nNote: If Message Class is disabled, we expect opcode to also be disabled.", + "PublicDescription": "Matches on Receive path of a UPI Port : Non-Coherent Standard : Matches on Receive path of a UPI port. Match based on UMask specific bits: Z: Message Class (3-bit) Y: Message Class Enable W: Opcode (4-bit) V: Opcode Enable U: Local Enable T: Remote Enable S: Data Hdr Enable R: Non-Data Hdr Enable Q: Dual Slot Hdr Enable P: Single Slot Hdr Enable Link Layer control types are excluded (LL CTRL, slot NULL, LLCRD) even under specific opcode match_en cases. Note: If Message Class is disabled, we expect opcode to also be disabled.", "UMask": "0xf", "Unit": "UPI" },
@@ -5318,7 +5318,7 @@ "EventCode": "0x05", "EventName": "UNC_UPI_RxL_BASIC_HDR_MATCH.NCS_OPC", "PerPkg": "1", - "PublicDescription": "Matches on Receive path of a UPI Port : Non-Coherent Standard, Match Opcode : Matches on Receive path of a UPI port.\r\nMatch based on UMask specific bits:\r\nZ: Message Class (3-bit)\r\nY: Message Class Enable\r\nW: Opcode (4-bit)\r\nV: Opcode Enable\r\nU: Local Enable\r\nT: Remote Enable\r\nS: Data Hdr Enable\r\nR: Non-Data Hdr Enable\r\nQ: Dual Slot Hdr Enable\r\nP: Single Slot Hdr Enable\r\nLink Layer control types are excluded (LL CTRL, slot NULL, LLCRD) even under specific opcode match_en cases.\r\nNote: If Message Class is disabled, we expect opcode to also be disabled.", + "PublicDescription": "Matches on Receive path of a UPI Port : Non-Coherent Standard, Match Opcode : Matches on Receive path of a UPI port. Match based on UMask specific bits: Z: Message Class (3-bit) Y: Message Class Enable W: Opcode (4-bit) V: Opcode Enable U: Local Enable T: Remote Enable S: Data Hdr Enable R: Non-Data Hdr Enable Q: Dual Slot Hdr Enable P: Single Slot Hdr Enable Link Layer control types are excluded (LL CTRL, slot NULL, LLCRD) even under specific opcode match_en cases. Note: If Message Class is disabled, we expect opcode to also be disabled.", "UMask": "0x10f", "Unit": "UPI" },
@@ -5763,7 +5763,7 @@ "EventCode": "0x04", "EventName": "UNC_UPI_TxL_BASIC_HDR_MATCH.NCB", "PerPkg": "1", - "PublicDescription": "Matches on Transmit path of a UPI Port : Non-Coherent Bypass : Matches on Transmit path of a UPI port.\r\nMatch based on UMask specific bits:\r\nZ: Message Class (3-bit)\r\nY: Message Class Enable\r\nW: Opcode (4-bit)\r\nV: Opcode Enable\r\nU: Local Enable\r\nT: Remote Enable\r\nS: Data Hdr Enable\r\nR: Non-Data Hdr Enable\r\nQ: Dual Slot Hdr Enable\r\nP: Single Slot Hdr Enable\r\nLink Layer control types are excluded (LL CTRL, slot NULL, LLCRD) even under specific opcode match_en cases.\r\nNote: If Message Class is disabled, we expect opcode to also be disabled.", + "PublicDescription": "Matches on Transmit path of a UPI Port : Non-Coherent Bypass : Matches on Transmit path of a UPI port. Match based on UMask specific bits: Z: Message Class (3-bit) Y: Message Class Enable W: Opcode (4-bit) V: Opcode Enable U: Local Enable T: Remote Enable S: Data Hdr Enable R: Non-Data Hdr Enable Q: Dual Slot Hdr Enable P: Single Slot Hdr Enable Link Layer control types are excluded (LL CTRL, slot NULL, LLCRD) even under specific opcode match_en cases. Note: If Message Class is disabled, we expect opcode to also be disabled.", "UMask": "0xe", "Unit": "UPI" },
@@ -5772,7 +5772,7 @@ "EventCode": "0x04", "EventName": "UNC_UPI_TxL_BASIC_HDR_MATCH.NCB_OPC", "PerPkg": "1", - "PublicDescription": "Matches on Transmit path of a UPI Port : Non-Coherent Bypass, Match Opcode : Matches on Transmit path of a UPI port.\r\nMatch based on UMask specific bits:\r\nZ: Message Class (3-bit)\r\nY: Message Class Enable\r\nW: Opcode (4-bit)\r\nV: Opcode Enable\r\nU: Local Enable\r\nT: Remote Enable\r\nS: Data Hdr Enable\r\nR: Non-Data Hdr Enable\r\nQ: Dual Slot Hdr Enable\r\nP: Single Slot Hdr Enable\r\nLink Layer control types are excluded (LL CTRL, slot NULL, LLCRD) even under specific opcode match_en cases.\r\nNote: If Message Class is disabled, we expect opcode to also be disabled.", + "PublicDescription": "Matches on Transmit path of a UPI Port : Non-Coherent Bypass, Match Opcode : Matches on Transmit path of a UPI port. Match based on UMask specific bits: Z: Message Class (3-bit) Y: Message Class Enable W: Opcode (4-bit) V: Opcode Enable U: Local Enable T: Remote Enable S: Data Hdr Enable R: Non-Data Hdr Enable Q: Dual Slot Hdr Enable P: Single Slot Hdr Enable Link Layer control types are excluded (LL CTRL, slot NULL, LLCRD) even under specific opcode match_en cases. Note: If Message Class is disabled, we expect opcode to also be disabled.", "UMask": "0x10e", "Unit": "UPI" },
@@ -5781,7 +5781,7 @@ "EventCode": "0x04", "EventName": "UNC_UPI_TxL_BASIC_HDR_MATCH.NCS", "PerPkg": "1", - "PublicDescription": "Matches on Transmit path of a UPI Port : Non-Coherent Standard : Matches on Transmit path of a UPI port.\r\nMatch based on UMask specific bits:\r\nZ: Message Class (3-bit)\r\nY: Message Class Enable\r\nW: Opcode (4-bit)\r\nV: Opcode Enable\r\nU: Local Enable\r\nT: Remote Enable\r\nS: Data Hdr Enable\r\nR: Non-Data Hdr Enable\r\nQ: Dual Slot Hdr Enable\r\nP: Single Slot Hdr Enable\r\nLink Layer control types are excluded (LL CTRL, slot NULL, LLCRD) even under specific opcode match_en cases.\r\nNote: If Message Class is disabled, we expect opcode to also be disabled.", + "PublicDescription": "Matches on Transmit path of a UPI Port : Non-Coherent Standard : Matches on Transmit path of a UPI port. Match based on UMask specific bits: Z: Message Class (3-bit) Y: Message Class Enable W: Opcode (4-bit) V: Opcode Enable U: Local Enable T: Remote Enable S: Data Hdr Enable R: Non-Data Hdr Enable Q: Dual Slot Hdr Enable P: Single Slot Hdr Enable Link Layer control types are excluded (LL CTRL, slot NULL, LLCRD) even under specific opcode match_en cases. Note: If Message Class is disabled, we expect opcode to also be disabled.", "UMask": "0xf", "Unit": "UPI" },
@@ -5790,7 +5790,7 @@ "EventCode": "0x04", "EventName": "UNC_UPI_TxL_BASIC_HDR_MATCH.NCS_OPC", "PerPkg": "1", - "PublicDescription": "Matches on Transmit path of a UPI Port : Non-Coherent Standard, Match Opcode : Matches on Transmit path of a UPI port.\r\nMatch based on UMask specific bits:\r\nZ: Message Class (3-bit)\r\nY: Message Class Enable\r\nW: Opcode (4-bit)\r\nV: Opcode Enable\r\nU: Local Enable\r\nT: Remote Enable\r\nS: Data Hdr Enable\r\nR: Non-Data Hdr Enable\r\nQ: Dual Slot Hdr Enable\r\nP: Single Slot Hdr Enable\r\nLink Layer control types are excluded (LL CTRL, slot NULL, LLCRD) even under specific opcode match_en cases.\r\nNote: If Message Class is disabled, we expect opcode to also be disabled.", + "PublicDescription": "Matches on Transmit path of a UPI Port : Non-Coherent Standard, Match Opcode : Matches on Transmit path of a UPI port. Match based on UMask specific bits: Z: Message Class (3-bit) Y: Message Class Enable W: Opcode (4-bit) V: Opcode Enable U: Local Enable T: Remote Enable S: Data Hdr Enable R: Non-Data Hdr Enable Q: Dual Slot Hdr Enable P: Single Slot Hdr Enable Link Layer control types are excluded (LL CTRL, slot NULL, LLCRD) even under specific opcode match_en cases. Note: If Message Class is disabled, we expect opcode to also be disabled.", "UMask": "0x10f", "Unit": "UPI" },
tools/perf/pmu-events/arch/x86/mapfile.csv +1 -1
@@ -7,7 +7,7 @@ GenuineIntel-6-56,v11,broadwellde,core GenuineIntel-6-4F,v22,broadwellx,core GenuineIntel-6-55-[56789ABCDEF],v1.21,cascadelakex,core GenuineIntel-6-9[6C],v1.04,elkhartlake,core -GenuineIntel-6-CF,v1.03,emeraldrapids,core +GenuineIntel-6-CF,v1.06,emeraldrapids,core GenuineIntel-6-5[CF],v13,goldmont,core GenuineIntel-6-7A,v1.01,goldmontplus,core GenuineIntel-6-B6,v1.01,grandridge,core
Signature · 1 line
2.44.0.396.g6e790dbe36-goog
Ian Rogers
reviewerPATCH 3/12 perf vendor events intel: Update grandridge to 1.02
In reply to Ian RogersUpdate events from 1.01 to 1.02 as released in:
https://github.com/intel/perfmon/commit/b2a81e803add1ba0af68a442c975683d226d868c
Fixes spelling and descriptions. Adds topdown events and uncore cache UNC_CHA_TOR_OCCUPANCY.IA_HIT_DRD_OPT, UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_OPT, UNC_CHA_TOR_OCCUPANCY.IA_DRD_OPT.
--- .../arch/x86/grandridge/pipeline.json | 43 ++++++++++++++++--- .../arch/x86/grandridge/uncore-cache.json | 28 +++++++++++- tools/perf/pmu-events/arch/x86/mapfile.csv | 2 +- 3 files changed, 66 insertions(+), 7 deletions(-)
tools/perf/pmu-events/arch/x86/grandridge/pipeline.json +38 -5
@@ -249,10 +249,17 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts the number of issue slots that were not consumed by the backend because allocation is stalled due to a mispredicted jump or a machine clear.", + "BriefDescription": "Counts the number of issue slots that were not consumed by the backend because allocation is stalled due to a mispredicted jump or a machine clear. [This event is alias to TOPDOWN_BAD_SPECULATION.ALL_P]", "EventCode": "0x73", "EventName": "TOPDOWN_BAD_SPECULATION.ALL", - "PublicDescription": "Counts the total number of issue slots that were not consumed by the backend because allocation is stalled due to a mispredicted jump or a machine clear. Only issue slots wasted due to fast nukes such as memory ordering nukes are counted. Other nukes are not accounted for. Counts all issue slots blocked during this recovery window, including relevant microcode flows, and while uops are not yet available in the instruction queue (IQ) or until an FE_BOUND event occurs besides OTHER and CISC. Also includes the issue slots that were consumed by the backend but were thrown away because they were younger than the mispredict or machine clear.", + "PublicDescription": "Counts the total number of issue slots that were not consumed by the backend because allocation is stalled due to a mispredicted jump or a machine clear. Only issue slots wasted due to fast nukes such as memory ordering nukes are counted. Other nukes are not accounted for. Counts all issue slots blocked during this recovery window, including relevant microcode flows, and while uops are not yet available in the instruction queue (IQ) or until an FE_BOUND event occurs besides OTHER and CISC. Also includes the issue slots that were consumed by the backend but were thrown away because they were younger than the mispredict or machine clear. [This event is alias to TOPDOWN_BAD_SPECULATION.ALL_P]", + "SampleAfterValue": "1000003" + }, + { + "BriefDescription": "Counts the number of issue slots that were not consumed by the backend because allocation is stalled due to a mispredicted jump or a machine clear. [This event is alias to TOPDOWN_BAD_SPECULATION.ALL]", + "EventCode": "0x73", + "EventName": "TOPDOWN_BAD_SPECULATION.ALL_P", + "PublicDescription": "Counts the total number of issue slots that were not consumed by the backend because allocation is stalled due to a mispredicted jump or a machine clear. Only issue slots wasted due to fast nukes such as memory ordering nukes are counted. Other nukes are not accounted for. Counts all issue slots blocked during this recovery window, including relevant microcode flows, and while uops are not yet available in the instruction queue (IQ) or until an FE_BOUND event occurs besides OTHER and CISC. Also includes the issue slots that were consumed by the backend but were thrown away because they were younger than the mispredict or machine clear. [This event is alias to TOPDOWN_BAD_SPECULATION.ALL]", "SampleAfterValue": "1000003" }, {
@@ -284,7 +291,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts the number of retirement slots not consumed due to backend stalls", + "BriefDescription": "Counts the number of retirement slots not consumed due to backend stalls [This event is alias to TOPDOWN_BE_BOUND.ALL_P]", "EventCode": "0x74", "EventName": "TOPDOWN_BE_BOUND.ALL", "SampleAfterValue": "1000003"
@@ -296,6 +303,12 @@ "SampleAfterValue": "1000003", "UMask": "0x1" }, + { + "BriefDescription": "Counts the number of retirement slots not consumed due to backend stalls [This event is alias to TOPDOWN_BE_BOUND.ALL]", + "EventCode": "0x74", + "EventName": "TOPDOWN_BE_BOUND.ALL_P", + "SampleAfterValue": "1000003" + }, { "BriefDescription": "Counts the number of issue slots every cycle that were not consumed by the backend due to memory reservation stall (scheduler not being able to accept another uop). This could be caused by RSV full or load/store buffer block.", "EventCode": "0x74",
@@ -317,6 +330,13 @@ "SampleAfterValue": "1000003", "UMask": "0x20" }, + { + "BriefDescription": "Counts the number of issue slots every cycle that were not consumed by the backend due to ROB full", + "EventCode": "0x74", + "EventName": "TOPDOWN_BE_BOUND.REORDER_BUFFER", + "SampleAfterValue": "1000003", + "UMask": "0x40" + }, { "BriefDescription": "Counts the number of issue slots every cycle that were not consumed by the backend due to iq/jeu scoreboards or ms scb", "EventCode": "0x74",
@@ -325,11 +345,17 @@ "UMask": "0x10" }, { - "BriefDescription": "Counts the number of retirement slots not consumed due to front end stalls", + "BriefDescription": "Counts the number of retirement slots not consumed due to front end stalls [This event is alias to TOPDOWN_FE_BOUND.ALL_P]", "EventCode": "0x71", "EventName": "TOPDOWN_FE_BOUND.ALL", "SampleAfterValue": "1000003" }, + { + "BriefDescription": "Counts the number of retirement slots not consumed due to front end stalls [This event is alias to TOPDOWN_FE_BOUND.ALL]", + "EventCode": "0x71", + "EventName": "TOPDOWN_FE_BOUND.ALL_P", + "SampleAfterValue": "1000003" + }, { "BriefDescription": "Counts the number of issue slots every cycle that were not delivered by the frontend due to BAClear", "EventCode": "0x71",
@@ -402,12 +428,19 @@ "UMask": "0x4" }, { - "BriefDescription": "Counts the number of consumed retirement slots. Similar to UOPS_RETIRED.ALL", + "BriefDescription": "Counts the number of consumed retirement slots. Similar to UOPS_RETIRED.ALL [This event is alias to TOPDOWN_RETIRING.ALL_P]", "EventCode": "0x72", "EventName": "TOPDOWN_RETIRING.ALL", "PEBS": "1", "SampleAfterValue": "1000003" }, + { + "BriefDescription": "Counts the number of consumed retirement slots. Similar to UOPS_RETIRED.ALL [This event is alias to TOPDOWN_RETIRING.ALL]", + "EventCode": "0x72", + "EventName": "TOPDOWN_RETIRING.ALL_P", + "PEBS": "1", + "SampleAfterValue": "1000003" + }, { "BriefDescription": "Counts the number of uops issued by the front end every cycle.", "EventCode": "0x0e",
tools/perf/pmu-events/arch/x86/grandridge/uncore-cache.json +27 -1
@@ -5,7 +5,6 @@ "EventName": "UNC_CHACMS_CLOCKTICKS", "PerPkg": "1", "PortMask": "0x000", - "PublicDescription": "UNC_CHACMS_CLOCKTICKS", "Unit": "CHACMS" }, {
@@ -1216,6 +1215,15 @@ "UMask": "0xc88fff01", "Unit": "CHA" }, + { + "BriefDescription": "TOR Occupancy for Data read opt from local IA that miss the cache", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_DRD_OPT", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : DRd_Opts issued by iA Cores", + "UMask": "0xc827ff01", + "Unit": "CHA" + }, { "BriefDescription": "TOR Occupancy for Data read opt prefetch from local IA that miss the cache", "EventCode": "0x36",
@@ -1252,6 +1260,15 @@ "UMask": "0xc88ffd01", "Unit": "CHA" }, + { + "BriefDescription": "TOR Occupancy for Data read opt from local IA that hit the cache", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_HIT_DRD_OPT", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : DRd_Opts issued by iA Cores that hit the LLC", + "UMask": "0xc827fd01", + "Unit": "CHA" + }, { "BriefDescription": "TOR Occupancy for Data read opt prefetch from local IA that hit the cache", "EventCode": "0x36",
@@ -1405,6 +1422,15 @@ "UMask": "0xc88efe01", "Unit": "CHA" }, + { + "BriefDescription": "TOR Occupancy for Data read opt from local IA that miss the cache", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_OPT", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : DRd_Opt issued by iA Cores that missed the LLC", + "UMask": "0xc827fe01", + "Unit": "CHA" + }, { "BriefDescription": "TOR Occupancy for Data read opt prefetch from local IA that miss the cache", "EventCode": "0x36",
tools/perf/pmu-events/arch/x86/mapfile.csv +1 -1
@@ -10,7 +10,7 @@ GenuineIntel-6-9[6C],v1.04,elkhartlake,core GenuineIntel-6-CF,v1.06,emeraldrapids,core GenuineIntel-6-5[CF],v13,goldmont,core GenuineIntel-6-7A,v1.01,goldmontplus,core -GenuineIntel-6-B6,v1.01,grandridge,core +GenuineIntel-6-B6,v1.02,grandridge,core GenuineIntel-6-A[DE],v1.01,graniterapids,core GenuineIntel-6-(3C|45|46),v35,haswell,core GenuineIntel-6-3F,v28,haswellx,core
Signature · 1 line
2.44.0.396.g6e790dbe36-goog
Ian Rogers
reviewerPATCH 4/12 perf vendor events intel: Update icelakex to 1.24
In reply to Ian RogersUpdate events from 1.23 to 1.24 as released in:
https://github.com/intel/perfmon/commit/d883888ae60882028e387b6fe1ebf683beb693fa
Fixes spelling and descriptions. Adds the uncore events UNC_CHA_TOR_INSERTS.IO_PCIRDCUR_LOCAL and UNC_CHA_TOR_INSERTS.IO_PCIRDCUR_REMOTE, while removing UNC_IIO_NUM_REQ_FROM_CPU.IRP.
--- .../arch/x86/icelakex/frontend.json | 2 +- .../pmu-events/arch/x86/icelakex/memory.json | 1 + .../arch/x86/icelakex/uncore-cache.json | 22 ++++++- .../x86/icelakex/uncore-interconnect.json | 64 +++++++++---------- .../arch/x86/icelakex/uncore-io.json | 11 ---- tools/perf/pmu-events/arch/x86/mapfile.csv | 2 +- 6 files changed, 55 insertions(+), 47 deletions(-)
tools/perf/pmu-events/arch/x86/icelakex/frontend.json +1 -1
@@ -282,7 +282,7 @@ "CounterMask": "5", "EventCode": "0x79", "EventName": "IDQ.DSB_CYCLES_OK", - "PublicDescription": "Counts the number of cycles where optimal number of uops was delivered to the Instruction Decode Queue (IDQ) from the MITE (legacy decode pipeline) path. During these cycles uops are not being delivered from the Decode Stream Buffer (DSB).", + "PublicDescription": "Counts the number of cycles where optimal number of uops was delivered to the Instruction Decode Queue (IDQ) from the DSB (Decode Stream Buffer) path. Count includes uops that may 'bypass' the IDQ.", "SampleAfterValue": "2000003", "UMask": "0x8" },
tools/perf/pmu-events/arch/x86/icelakex/memory.json +1 -0
@@ -319,6 +319,7 @@ "BriefDescription": "Number of times an RTM execution aborted.", "EventCode": "0xc9", "EventName": "RTM_RETIRED.ABORTED", + "PEBS": "1", "PublicDescription": "Counts the number of times RTM abort was triggered.", "SampleAfterValue": "100003", "UMask": "0x4"
tools/perf/pmu-events/arch/x86/icelakex/uncore-cache.json +20 -2
@@ -1580,7 +1580,7 @@ "Unit": "CHA" }, { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_LLC_LOOKUP.CODE_READ", + "BriefDescription": "This event is deprecated.", "Deprecated": "1", "EventCode": "0x34", "EventName": "UNC_CHA_LLC_LOOKUP.CODE",
@@ -1677,7 +1677,7 @@ "Unit": "CHA" }, { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_LLC_LOOKUP.DATA_READ", + "BriefDescription": "This event is deprecated.", "Deprecated": "1", "EventCode": "0x34", "EventName": "UNC_CHA_LLC_LOOKUP.DATA_READ_ALL",
@@ -6782,6 +6782,24 @@ "UMask": "0xc8f3ff04", "Unit": "CHA" }, + { + "BriefDescription": "PCIRDCUR (read) transactions from an IO device that addresses memory on the local socket", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IO_PCIRDCUR_LOCAL", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : PCIRdCurs issued by IO Devices and targets local memory : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc8f2ff04", + "Unit": "CHA" + }, + { + "BriefDescription": "PCIRDCUR (read) transactions from an IO device that addresses memory on a remote socket", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IO_PCIRDCUR_REMOTE", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : PCIRdCurs issued by IO Devices and targets remote memory : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc8f37f04", + "Unit": "CHA" + }, { "BriefDescription": "TOR Inserts : RFOs issued by IO Devices", "EventCode": "0x35",
tools/perf/pmu-events/arch/x86/icelakex/uncore-interconnect.json +32 -32
256 lines not on this page · raw message
tools/perf/pmu-events/arch/x86/icelakex/uncore-io.json +0 -11
@@ -2476,17 +2476,6 @@ "UMask": "0x10", "Unit": "IIO" }, - { - "BriefDescription": "Number requests sent to PCIe from main die : From IRP", - "EventCode": "0xC2", - "EventName": "UNC_IIO_NUM_REQ_FROM_CPU.IRP", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0xFF", - "PublicDescription": "Number requests sent to PCIe from main die : From IRP : Captures Posted/Non-posted allocations from IRP. i.e. either non-confined P2P traffic or from the CPU", - "UMask": "0x1", - "Unit": "IIO" - }, { "BriefDescription": "Number requests sent to PCIe from main die : From ITC", "EventCode": "0xC2",
tools/perf/pmu-events/arch/x86/mapfile.csv +1 -1
@@ -15,7 +15,7 @@ GenuineIntel-6-A[DE],v1.01,graniterapids,core GenuineIntel-6-(3C|45|46),v35,haswell,core GenuineIntel-6-3F,v28,haswellx,core GenuineIntel-6-7[DE],v1.21,icelake,core -GenuineIntel-6-6[AC],v1.23,icelakex,core +GenuineIntel-6-6[AC],v1.24,icelakex,core GenuineIntel-6-3A,v24,ivybridge,core GenuineIntel-6-3E,v24,ivytown,core GenuineIntel-6-2D,v24,jaketown,core
Signature · 1 line
2.44.0.396.g6e790dbe36-goog
Ian Rogers
reviewerPATCH 5/12 perf vendor events intel: Update lunarlake to 1.01
In reply to Ian RogersUpdate events from 1.00 to 1.01 as released in:
https://github.com/intel/perfmon/commit/56ab8d837ac566d51a4d8748b6b4b817a22c9b84
Various encoding and description updates. Adds the events CPU_CLK_UNHALTED.CORE, CPU_CLK_UNHALTED.CORE_P, CPU_CLK_UNHALTED.REF_TSC_P, CPU_CLK_UNHALTED.THREAD, MISC_RETIRED.LBR_INSERTS, TOPDOWN_BAD_SPECULATION.ALL_P, TOPDOWN_BE_BOUND.ALL_P, TOPDOWN_FE_BOUND.ALL_P, TOPDOWN_RETIRING.ALL_P.
--- .../pmu-events/arch/x86/lunarlake/cache.json | 24 ++-- .../arch/x86/lunarlake/frontend.json | 2 +- .../pmu-events/arch/x86/lunarlake/memory.json | 4 +- .../pmu-events/arch/x86/lunarlake/other.json | 4 +- .../arch/x86/lunarlake/pipeline.json | 109 +++++++++++++++--- tools/perf/pmu-events/arch/x86/mapfile.csv | 2 +- 6 files changed, 113 insertions(+), 32 deletions(-)
tools/perf/pmu-events/arch/x86/lunarlake/cache.json +12 -12
@@ -31,7 +31,7 @@ "EventCode": "0x2e", "EventName": "LONGEST_LAT_CACHE.REFERENCE", "PublicDescription": "Counts the number of cacheable memory requests that access the Last Level Cache (LLC). Requests include demand loads, reads for ownership (RFO), instruction fetches and L1 HW prefetches. If the platform has an L3 cache, the LLC is the L3 cache, otherwise it is the L2 cache. Counts on a per core basis.", - "SampleAfterValue": "1000003", + "SampleAfterValue": "200003", "UMask": "0x4f", "Unit": "cpu_atom" },
@@ -94,7 +94,7 @@ "MSRIndex": "0x3F6", "MSRValue": "0x400", "PEBS": "2", - "SampleAfterValue": "1000003", + "SampleAfterValue": "200003", "UMask": "0x5", "Unit": "cpu_atom" },
@@ -106,7 +106,7 @@ "MSRIndex": "0x3F6", "MSRValue": "0x80", "PEBS": "2", - "SampleAfterValue": "1000003", + "SampleAfterValue": "200003", "UMask": "0x5", "Unit": "cpu_atom" },
@@ -118,7 +118,7 @@ "MSRIndex": "0x3F6", "MSRValue": "0x10", "PEBS": "2", - "SampleAfterValue": "1000003", + "SampleAfterValue": "200003", "UMask": "0x5", "Unit": "cpu_atom" },
@@ -130,7 +130,7 @@ "MSRIndex": "0x3F6", "MSRValue": "0x800", "PEBS": "2", - "SampleAfterValue": "1000003", + "SampleAfterValue": "200003", "UMask": "0x5", "Unit": "cpu_atom" },
@@ -142,7 +142,7 @@ "MSRIndex": "0x3F6", "MSRValue": "0x100", "PEBS": "2", - "SampleAfterValue": "1000003", + "SampleAfterValue": "200003", "UMask": "0x5", "Unit": "cpu_atom" },
@@ -154,7 +154,7 @@ "MSRIndex": "0x3F6", "MSRValue": "0x20", "PEBS": "2", - "SampleAfterValue": "1000003", + "SampleAfterValue": "200003", "UMask": "0x5", "Unit": "cpu_atom" },
@@ -166,7 +166,7 @@ "MSRIndex": "0x3F6", "MSRValue": "0x4", "PEBS": "2", - "SampleAfterValue": "1000003", + "SampleAfterValue": "200003", "UMask": "0x5", "Unit": "cpu_atom" },
@@ -178,7 +178,7 @@ "MSRIndex": "0x3F6", "MSRValue": "0x200", "PEBS": "2", - "SampleAfterValue": "1000003", + "SampleAfterValue": "200003", "UMask": "0x5", "Unit": "cpu_atom" },
@@ -190,7 +190,7 @@ "MSRIndex": "0x3F6", "MSRValue": "0x40", "PEBS": "2", - "SampleAfterValue": "1000003", + "SampleAfterValue": "200003", "UMask": "0x5", "Unit": "cpu_atom" },
@@ -202,7 +202,7 @@ "MSRIndex": "0x3F6", "MSRValue": "0x8", "PEBS": "2", - "SampleAfterValue": "1000003", + "SampleAfterValue": "200003", "UMask": "0x5", "Unit": "cpu_atom" },
@@ -212,7 +212,7 @@ "EventCode": "0xd0", "EventName": "MEM_UOPS_RETIRED.STORE_LATENCY", "PEBS": "2", - "SampleAfterValue": "1000003", + "SampleAfterValue": "200003", "UMask": "0x6", "Unit": "cpu_atom" }
tools/perf/pmu-events/arch/x86/lunarlake/frontend.json +1 -1
@@ -19,7 +19,7 @@ "BriefDescription": "This event counts a subset of the Topdown Slots event that were no operation was delivered to the back-end pipeline due to instruction fetch limitations when the back-end could have accepted more operations. Common examples include instruction cache misses or x86 instruction decode limitations.", "EventCode": "0x9c", "EventName": "IDQ_BUBBLES.CORE", - "PublicDescription": "This event counts a subset of the Topdown Slots event that were no operation was delivered to the back-end pipeline due to instruction fetch limitations when the back-end could have accepted more operations. Common examples include instruction cache misses or x86 instruction decode limitations.\nSoftware can use this event as the numerator for the Frontend Bound metric (or top-level category) of the Top-down Microarchitecture Analysis method.", + "PublicDescription": "This event counts a subset of the Topdown Slots event that were no operation was delivered to the back-end pipeline due to instruction fetch limitations when the back-end could have accepted more operations. Common examples include instruction cache misses or x86 instruction decode limitations. Software can use this event as the numerator for the Frontend Bound metric (or top-level category) of the Top-down Microarchitecture Analysis method.", "SampleAfterValue": "1000003", "UMask": "0x1", "Unit": "cpu_core"
tools/perf/pmu-events/arch/x86/lunarlake/memory.json +2 -2
@@ -155,7 +155,7 @@ "EventCode": "0x2A,0x2B", "EventName": "OCR.DEMAND_DATA_RD.L3_MISS", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x3FBFC00001", + "MSRValue": "0xFE7F8000001", "SampleAfterValue": "100003", "UMask": "0x1", "Unit": "cpu_core"
@@ -175,7 +175,7 @@ "EventCode": "0x2A,0x2B", "EventName": "OCR.DEMAND_RFO.L3_MISS", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x3FBFC00002", + "MSRValue": "0xFE7F8000002", "SampleAfterValue": "100003", "UMask": "0x1", "Unit": "cpu_core"
tools/perf/pmu-events/arch/x86/lunarlake/other.json +2 -2
@@ -24,7 +24,7 @@ "EventCode": "0xB7", "EventName": "OCR.DEMAND_DATA_RD.DRAM", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x184000001", + "MSRValue": "0x1FBC000001", "SampleAfterValue": "100003", "UMask": "0x1", "Unit": "cpu_atom"
@@ -34,7 +34,7 @@ "EventCode": "0x2A,0x2B", "EventName": "OCR.DEMAND_DATA_RD.DRAM", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x184000001", + "MSRValue": "0x1E780000001", "SampleAfterValue": "100003", "UMask": "0x1", "Unit": "cpu_core"
tools/perf/pmu-events/arch/x86/lunarlake/pipeline.json +95 -14
197 lines not on this page · raw message
tools/perf/pmu-events/arch/x86/mapfile.csv +1 -1
@@ -20,7 +20,7 @@ GenuineIntel-6-3A,v24,ivybridge,core 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-BD,v1.01,lunarlake,core GenuineIntel-6-A[AC],v1.07,meteorlake,core GenuineIntel-6-1[AEF],v4,nehalemep,core GenuineIntel-6-2E,v4,nehalemex,core
Signature · 1 line
2.44.0.396.g6e790dbe36-goog
Ian Rogers
reviewerPATCH 6/12 perf vendor events intel: Update meteorlake to 1.08
In reply to Ian RogersUpdate events from 1.07 to 1.08 as released in:
https://github.com/intel/perfmon/commit/f0f8f3e163d9eb84e6ce8e2108a22cb43b2527e5
Various description updates. Adds topdown, offcore and uncore events OCR.DEMAND_DATA_RD.L3_HIT, OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_NO_FWD, OCR.DEMAND_RFO.L3_HIT, OCR.DEMAND_DATA_RD.L3_MISS, OCR.DEMAND_RFO.L3_MISS, OCR.DEMAND_DATA_RD.ANY_RESPONSE, OCR.DEMAND_DATA_RD.DRAM, OCR.DEMAND_RFO.ANY_RESPONSE, OCR.DEMAND_RFO.DRAM, TOPDOWN_BAD_SPECULATION.ALL_P, TOPDOWN_BE_BOUND.ALL_P, TOPDOWN_FE_BOUND.ALL_P, TOPDOWN_RETIRING.ALL_P, UNC_ARB_DAT_OCCUPANCY.RD and UNC_HAC_ARB_COH_TRK_REQUESTS.ALL.
--- tools/perf/pmu-events/arch/x86/mapfile.csv | 2 +- .../pmu-events/arch/x86/meteorlake/cache.json | 30 +++++++++++++ .../arch/x86/meteorlake/frontend.json | 4 +- .../arch/x86/meteorlake/memory.json | 20 +++++++++ .../pmu-events/arch/x86/meteorlake/other.json | 42 +++++++++++++++++- .../arch/x86/meteorlake/pipeline.json | 44 ++++++++++++++++--- .../x86/meteorlake/uncore-interconnect.json | 22 ++++++++-- 7 files changed, 150 insertions(+), 14 deletions(-)
tools/perf/pmu-events/arch/x86/mapfile.csv +1 -1
@@ -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,v1.01,lunarlake,core -GenuineIntel-6-A[AC],v1.07,meteorlake,core +GenuineIntel-6-A[AC],v1.08,meteorlake,core GenuineIntel-6-1[AEF],v4,nehalemep,core GenuineIntel-6-2E,v4,nehalemex,core GenuineIntel-6-A7,v1.02,rocketlake,core
tools/perf/pmu-events/arch/x86/meteorlake/cache.json +30 -0
@@ -966,6 +966,16 @@ "UMask": "0x3", "Unit": "cpu_core" }, + { + "BriefDescription": "Counts demand data reads that were supplied by the L3 cache.", + "EventCode": "0xB7", + "EventName": "OCR.DEMAND_DATA_RD.L3_HIT", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x3F803C0001", + "SampleAfterValue": "100003", + "UMask": "0x1", + "Unit": "cpu_atom" + }, { "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",
@@ -986,6 +996,16 @@ "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, but no data was forwarded.", + "EventCode": "0xB7", + "EventName": "OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_NO_FWD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x4003C0001", + "SampleAfterValue": "100003", + "UMask": "0x1", + "Unit": "cpu_atom" + }, { "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",
@@ -1006,6 +1026,16 @@ "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.", + "EventCode": "0xB7", + "EventName": "OCR.DEMAND_RFO.L3_HIT", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x3F803C0002", + "SampleAfterValue": "100003", + "UMask": "0x1", + "Unit": "cpu_atom" + }, { "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",
tools/perf/pmu-events/arch/x86/meteorlake/frontend.json +2 -2
@@ -378,7 +378,7 @@ "CounterMask": "6", "EventCode": "0x79", "EventName": "IDQ.DSB_CYCLES_OK", - "PublicDescription": "Counts the number of cycles where optimal number of uops was delivered to the Instruction Decode Queue (IDQ) from the MITE (legacy decode pipeline) path. During these cycles uops are not being delivered from the Decode Stream Buffer (DSB).", + "PublicDescription": "Counts the number of cycles where optimal number of uops was delivered to the Instruction Decode Queue (IDQ) from the DSB (Decode Stream Buffer) path. Count includes uops that may 'bypass' the IDQ.", "SampleAfterValue": "2000003", "UMask": "0x8", "Unit": "cpu_core"
@@ -455,7 +455,7 @@ "BriefDescription": "This event counts a subset of the Topdown Slots event that were no operation was delivered to the back-end pipeline due to instruction fetch limitations when the back-end could have accepted more operations. Common examples include instruction cache misses or x86 instruction decode limitations.", "EventCode": "0x9c", "EventName": "IDQ_BUBBLES.CORE", - "PublicDescription": "This event counts a subset of the Topdown Slots event that were no operation was delivered to the back-end pipeline due to instruction fetch limitations when the back-end could have accepted more operations. Common examples include instruction cache misses or x86 instruction decode limitations.\nThe count may be distributed among unhalted logical processors (hyper-threads) who share the same physical core, in processors that support Intel Hyper-Threading Technology. Software can use this event as the numerator for the Frontend Bound metric (or top-level category) of the Top-down Microarchitecture Analysis method.", + "PublicDescription": "This event counts a subset of the Topdown Slots event that were no operation was delivered to the back-end pipeline due to instruction fetch limitations when the back-end could have accepted more operations. Common examples include instruction cache misses or x86 instruction decode limitations. The count may be distributed among unhalted logical processors (hyper-threads) who share the same physical core, in processors that support Intel Hyper-Threading Technology. Software can use this event as the numerator for the Frontend Bound metric (or top-level category) of the Top-down Microarchitecture Analysis method.", "SampleAfterValue": "1000003", "UMask": "0x1", "Unit": "cpu_core"
tools/perf/pmu-events/arch/x86/meteorlake/memory.json +20 -0
@@ -296,6 +296,16 @@ "UMask": "0x4", "Unit": "cpu_atom" }, + { + "BriefDescription": "Counts demand data reads that were not supplied by the L3 cache.", + "EventCode": "0xB7", + "EventName": "OCR.DEMAND_DATA_RD.L3_MISS", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x3FBFC00001", + "SampleAfterValue": "100003", + "UMask": "0x1", + "Unit": "cpu_atom" + }, { "BriefDescription": "Counts demand data reads that were not supplied by the L3 cache.", "EventCode": "0x2A,0x2B",
@@ -306,6 +316,16 @@ "UMask": "0x1", "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.", + "EventCode": "0xB7", + "EventName": "OCR.DEMAND_RFO.L3_MISS", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x3FBFC00002", + "SampleAfterValue": "100003", + "UMask": "0x1", + "Unit": "cpu_atom" + }, { "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",
tools/perf/pmu-events/arch/x86/meteorlake/other.json +41 -1
72 lines not on this page · raw message
tools/perf/pmu-events/arch/x86/meteorlake/pipeline.json +37 -7
99 lines not on this page · raw message
tools/perf/pmu-events/arch/x86/meteorlake/uncore-interconnect.json +19 -3
@@ -1,4 +1,20 @@ [ + { + "BriefDescription": "Each cycle counts number of coherent reads pending on data return from memory controller that were issued by any core.", + "EventCode": "0x85", + "EventName": "UNC_ARB_DAT_OCCUPANCY.RD", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "ARB" + }, + { + "BriefDescription": "Number of entries allocated. Account for Any type: e.g. Snoop, etc.", + "EventCode": "0x84", + "EventName": "UNC_HAC_ARB_COH_TRK_REQUESTS.ALL", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "HAC_ARB" + }, { "BriefDescription": "Number of all coherent Data Read entries. Doesn't include prefetches", "EventCode": "0x81",
@@ -9,7 +25,7 @@ }, { "BriefDescription": "Number of all CMI transactions", - "EventCode": "0x8a", + "EventCode": "0x8A", "EventName": "UNC_HAC_ARB_TRANSACTIONS.ALL", "PerPkg": "1", "UMask": "0x1",
@@ -17,7 +33,7 @@ }, { "BriefDescription": "Number of all CMI reads", - "EventCode": "0x8a", + "EventCode": "0x8A", "EventName": "UNC_HAC_ARB_TRANSACTIONS.READS", "PerPkg": "1", "UMask": "0x2",
@@ -25,7 +41,7 @@ }, { "BriefDescription": "Number of all CMI writes not including Mflush", - "EventCode": "0x8a", + "EventCode": "0x8A", "EventName": "UNC_HAC_ARB_TRANSACTIONS.WRITES", "PerPkg": "1", "UMask": "0x4",
Signature · 1 line
2.44.0.396.g6e790dbe36-goog
Ian Rogers
reviewerPATCH 7/12 perf vendor events intel: Update sapphirerapids to 1.20
In reply to Ian RogersUpdate events from 1.17 to 1.20 as released in:
https://github.com/intel/perfmon/commit/6f674057745acf0125395638ca6be36458a59bda
Various description updates. Adds uncore events UNC_CHA_TOR_INSERTS.IO_ITOMCACHENEAR_LOCAL, UNC_CHA_TOR_INSERTS.IO_ITOMCACHENEAR_REMOTE, UNC_CHA_TOR_INSERTS.IO_ITOM_LOCAL, UNC_CHA_TOR_INSERTS.IO_ITOM_REMOTE, UNC_CHA_TOR_INSERTS.IO_PCIRDCUR_LOCAL, UNC_CHA_TOR_INSERTS.IO_PCIRDCUR_REMOTE, UNC_CHA_TOR_OCCUPANCY.IO_MISS_ITOMCACHENEAR_LOCAL, UNC_CHA_TOR_OCCUPANCY.IO_MISS_ITOMCACHENEAR_REMOTE, UNC_CHA_TOR_OCCUPANCY.IO_MISS_ITOM_LOCAL, UNC_CHA_TOR_OCCUPANCY.IO_MISS_ITOM_REMOTE, UNC_CHA_TOR_OCCUPANCY.IO_MISS_PCIRDCUR_LOCAL, UNC_CHA_TOR_OCCUPANCY.IO_MISS_PCIRDCUR_REMOTE and removes core events AMX_OPS_RETIRED.BF16 and AMX_OPS_RETIRED.INT8.
--- tools/perf/pmu-events/arch/x86/mapfile.csv | 2 +- .../arch/x86/sapphirerapids/cache.json | 1 + .../arch/x86/sapphirerapids/frontend.json | 2 +- .../arch/x86/sapphirerapids/memory.json | 1 + .../arch/x86/sapphirerapids/pipeline.json | 19 +-- .../arch/x86/sapphirerapids/uncore-cache.json | 112 +++++++++++++++++- .../sapphirerapids/uncore-interconnect.json | 26 ++-- 7 files changed, 130 insertions(+), 33 deletions(-)
tools/perf/pmu-events/arch/x86/mapfile.csv +1 -1
@@ -26,7 +26,7 @@ GenuineIntel-6-1[AEF],v4,nehalemep,core GenuineIntel-6-2E,v4,nehalemex,core GenuineIntel-6-A7,v1.02,rocketlake,core GenuineIntel-6-2A,v19,sandybridge,core -GenuineIntel-6-8F,v1.17,sapphirerapids,core +GenuineIntel-6-8F,v1.20,sapphirerapids,core GenuineIntel-6-AF,v1.01,sierraforest,core GenuineIntel-6-(37|4A|4C|4D|5A),v15,silvermont,core GenuineIntel-6-(4E|5E|8E|9E|A5|A6),v58,skylake,core
tools/perf/pmu-events/arch/x86/sapphirerapids/cache.json +1 -0
@@ -432,6 +432,7 @@ "BriefDescription": "Retired load instructions with remote Intel(R) Optane(TM) DC persistent memory as the data source where the data request missed all caches.", "EventCode": "0xd3", "EventName": "MEM_LOAD_L3_MISS_RETIRED.REMOTE_PMM", + "PEBS": "1", "PublicDescription": "Counts retired load instructions with remote Intel(R) Optane(TM) DC persistent memory as the data source and the data request missed L3.", "SampleAfterValue": "100007", "UMask": "0x10"
tools/perf/pmu-events/arch/x86/sapphirerapids/frontend.json +1 -1
@@ -267,7 +267,7 @@ "CounterMask": "6", "EventCode": "0x79", "EventName": "IDQ.DSB_CYCLES_OK", - "PublicDescription": "Counts the number of cycles where optimal number of uops was delivered to the Instruction Decode Queue (IDQ) from the MITE (legacy decode pipeline) path. During these cycles uops are not being delivered from the Decode Stream Buffer (DSB).", + "PublicDescription": "Counts the number of cycles where optimal number of uops was delivered to the Instruction Decode Queue (IDQ) from the DSB (Decode Stream Buffer) path. Count includes uops that may 'bypass' the IDQ.", "SampleAfterValue": "2000003", "UMask": "0x8" },
tools/perf/pmu-events/arch/x86/sapphirerapids/memory.json +1 -0
@@ -264,6 +264,7 @@ "BriefDescription": "Number of times an RTM execution aborted.", "EventCode": "0xc9", "EventName": "RTM_RETIRED.ABORTED", + "PEBS": "1", "PublicDescription": "Counts the number of times RTM abort was triggered.", "SampleAfterValue": "100003", "UMask": "0x4"
tools/perf/pmu-events/arch/x86/sapphirerapids/pipeline.json +3 -16
@@ -1,20 +1,4 @@ [ - { - "BriefDescription": "AMX retired arithmetic BF16 operations.", - "EventCode": "0xce", - "EventName": "AMX_OPS_RETIRED.BF16", - "PublicDescription": "Number of AMX-based retired arithmetic bfloat16 (BF16) floating-point operations. Counts TDPBF16PS FP instructions. SW to use operation multiplier of 4", - "SampleAfterValue": "1000003", - "UMask": "0x2" - }, - { - "BriefDescription": "AMX retired arithmetic integer 8-bit operations.", - "EventCode": "0xce", - "EventName": "AMX_OPS_RETIRED.INT8", - "PublicDescription": "Number of AMX-based retired arithmetic integer operations of 8-bit width source operands. Counts TDPB[SS,UU,US,SU]D instructions. SW should use operation multiplier of 8.", - "SampleAfterValue": "1000003", - "UMask": "0x1" - }, { "BriefDescription": "This event is deprecated. Refer to new event ARITH.DIV_ACTIVE", "CounterMask": "1",
@@ -444,6 +428,7 @@ "BriefDescription": "INST_RETIRED.MACRO_FUSED", "EventCode": "0xc0", "EventName": "INST_RETIRED.MACRO_FUSED", + "PEBS": "1", "SampleAfterValue": "2000003", "UMask": "0x10" },
@@ -451,6 +436,7 @@ "BriefDescription": "Retired NOP instructions.", "EventCode": "0xc0", "EventName": "INST_RETIRED.NOP", + "PEBS": "1", "PublicDescription": "Counts all retired NOP or ENDBR32/64 instructions", "SampleAfterValue": "2000003", "UMask": "0x2"
@@ -467,6 +453,7 @@ "BriefDescription": "Iterations of Repeat string retired instructions.", "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"
tools/perf/pmu-events/arch/x86/sapphirerapids/uncore-cache.json +110 -2
148 lines not on this page · raw message
tools/perf/pmu-events/arch/x86/sapphirerapids/uncore-interconnect.json +13 -13
@@ -4888,7 +4888,7 @@ "Unit": "MDF" }, { - "BriefDescription": "Number of cycles incoming messages from the vertical ring that are bounced at the SBO\r\nIngress (V-EMIB) (AD)", + "BriefDescription": "Number of cycles incoming messages from the vertical ring that are bounced at the SBO Ingress (V-EMIB) (AD)", "EventCode": "0x4B", "EventName": "UNC_MDF_CRS_TxR_V_BOUNCES.AD", "PerPkg": "1",
@@ -4897,7 +4897,7 @@ "Unit": "MDF" }, { - "BriefDescription": "Number of cycles incoming messages from the vertical ring that are bounced at the SBO\r\nIngress (V-EMIB) (AK)", + "BriefDescription": "Number of cycles incoming messages from the vertical ring that are bounced at the SBO Ingress (V-EMIB) (AK)", "EventCode": "0x4B", "EventName": "UNC_MDF_CRS_TxR_V_BOUNCES.AK", "PerPkg": "1",
@@ -4906,7 +4906,7 @@ "Unit": "MDF" }, { - "BriefDescription": "Number of cycles incoming messages from the vertical ring that are bounced at the SBO\r\nIngress (V-EMIB) (AKC)", + "BriefDescription": "Number of cycles incoming messages from the vertical ring that are bounced at the SBO Ingress (V-EMIB) (AKC)", "EventCode": "0x4B", "EventName": "UNC_MDF_CRS_TxR_V_BOUNCES.AKC", "PerPkg": "1",
@@ -4915,7 +4915,7 @@ "Unit": "MDF" }, { - "BriefDescription": "Number of cycles incoming messages from the vertical ring that are bounced at the SBO\r\nIngress (V-EMIB) (BL)", + "BriefDescription": "Number of cycles incoming messages from the vertical ring that are bounced at the SBO Ingress (V-EMIB) (BL)", "EventCode": "0x4B", "EventName": "UNC_MDF_CRS_TxR_V_BOUNCES.BL", "PerPkg": "1",
@@ -4924,7 +4924,7 @@ "Unit": "MDF" }, { - "BriefDescription": "Number of cycles incoming messages from the vertical ring that are bounced at the SBO\r\nIngress (V-EMIB) (IV)", + "BriefDescription": "Number of cycles incoming messages from the vertical ring that are bounced at the SBO Ingress (V-EMIB) (IV)", "EventCode": "0x4B", "EventName": "UNC_MDF_CRS_TxR_V_BOUNCES.IV", "PerPkg": "1",
@@ -5291,7 +5291,7 @@ "EventCode": "0x05", "EventName": "UNC_UPI_RxL_BASIC_HDR_MATCH.NCB", "PerPkg": "1", - "PublicDescription": "Matches on Receive path of a UPI Port : Non-Coherent Bypass : Matches on Receive path of a UPI port.\r\nMatch based on UMask specific bits:\r\nZ: Message Class (3-bit)\r\nY: Message Class Enable\r\nW: Opcode (4-bit)\r\nV: Opcode Enable\r\nU: Local Enable\r\nT: Remote Enable\r\nS: Data Hdr Enable\r\nR: Non-Data Hdr Enable\r\nQ: Dual Slot Hdr Enable\r\nP: Single Slot Hdr Enable\r\nLink Layer control types are excluded (LL CTRL, slot NULL, LLCRD) even under specific opcode match_en cases.\r\nNote: If Message Class is disabled, we expect opcode to also be disabled.", + "PublicDescription": "Matches on Receive path of a UPI Port : Non-Coherent Bypass : Matches on Receive path of a UPI port. Match based on UMask specific bits: Z: Message Class (3-bit) Y: Message Class Enable W: Opcode (4-bit) V: Opcode Enable U: Local Enable T: Remote Enable S: Data Hdr Enable R: Non-Data Hdr Enable Q: Dual Slot Hdr Enable P: Single Slot Hdr Enable Link Layer control types are excluded (LL CTRL, slot NULL, LLCRD) even under specific opcode match_en cases. Note: If Message Class is disabled, we expect opcode to also be disabled.", "UMask": "0xe", "Unit": "UPI" },
@@ -5300,7 +5300,7 @@ "EventCode": "0x05", "EventName": "UNC_UPI_RxL_BASIC_HDR_MATCH.NCB_OPC", "PerPkg": "1", - "PublicDescription": "Matches on Receive path of a UPI Port : Non-Coherent Bypass, Match Opcode : Matches on Receive path of a UPI port.\r\nMatch based on UMask specific bits:\r\nZ: Message Class (3-bit)\r\nY: Message Class Enable\r\nW: Opcode (4-bit)\r\nV: Opcode Enable\r\nU: Local Enable\r\nT: Remote Enable\r\nS: Data Hdr Enable\r\nR: Non-Data Hdr Enable\r\nQ: Dual Slot Hdr Enable\r\nP: Single Slot Hdr Enable\r\nLink Layer control types are excluded (LL CTRL, slot NULL, LLCRD) even under specific opcode match_en cases.\r\nNote: If Message Class is disabled, we expect opcode to also be disabled.", + "PublicDescription": "Matches on Receive path of a UPI Port : Non-Coherent Bypass, Match Opcode : Matches on Receive path of a UPI port. Match based on UMask specific bits: Z: Message Class (3-bit) Y: Message Class Enable W: Opcode (4-bit) V: Opcode Enable U: Local Enable T: Remote Enable S: Data Hdr Enable R: Non-Data Hdr Enable Q: Dual Slot Hdr Enable P: Single Slot Hdr Enable Link Layer control types are excluded (LL CTRL, slot NULL, LLCRD) even under specific opcode match_en cases. Note: If Message Class is disabled, we expect opcode to also be disabled.", "UMask": "0x10e", "Unit": "UPI" },
@@ -5309,7 +5309,7 @@ "EventCode": "0x05", "EventName": "UNC_UPI_RxL_BASIC_HDR_MATCH.NCS", "PerPkg": "1", - "PublicDescription": "Matches on Receive path of a UPI Port : Non-Coherent Standard : Matches on Receive path of a UPI port.\r\nMatch based on UMask specific bits:\r\nZ: Message Class (3-bit)\r\nY: Message Class Enable\r\nW: Opcode (4-bit)\r\nV: Opcode Enable\r\nU: Local Enable\r\nT: Remote Enable\r\nS: Data Hdr Enable\r\nR: Non-Data Hdr Enable\r\nQ: Dual Slot Hdr Enable\r\nP: Single Slot Hdr Enable\r\nLink Layer control types are excluded (LL CTRL, slot NULL, LLCRD) even under specific opcode match_en cases.\r\nNote: If Message Class is disabled, we expect opcode to also be disabled.", + "PublicDescription": "Matches on Receive path of a UPI Port : Non-Coherent Standard : Matches on Receive path of a UPI port. Match based on UMask specific bits: Z: Message Class (3-bit) Y: Message Class Enable W: Opcode (4-bit) V: Opcode Enable U: Local Enable T: Remote Enable S: Data Hdr Enable R: Non-Data Hdr Enable Q: Dual Slot Hdr Enable P: Single Slot Hdr Enable Link Layer control types are excluded (LL CTRL, slot NULL, LLCRD) even under specific opcode match_en cases. Note: If Message Class is disabled, we expect opcode to also be disabled.", "UMask": "0xf", "Unit": "UPI" },
@@ -5318,7 +5318,7 @@ "EventCode": "0x05", "EventName": "UNC_UPI_RxL_BASIC_HDR_MATCH.NCS_OPC", "PerPkg": "1", - "PublicDescription": "Matches on Receive path of a UPI Port : Non-Coherent Standard, Match Opcode : Matches on Receive path of a UPI port.\r\nMatch based on UMask specific bits:\r\nZ: Message Class (3-bit)\r\nY: Message Class Enable\r\nW: Opcode (4-bit)\r\nV: Opcode Enable\r\nU: Local Enable\r\nT: Remote Enable\r\nS: Data Hdr Enable\r\nR: Non-Data Hdr Enable\r\nQ: Dual Slot Hdr Enable\r\nP: Single Slot Hdr Enable\r\nLink Layer control types are excluded (LL CTRL, slot NULL, LLCRD) even under specific opcode match_en cases.\r\nNote: If Message Class is disabled, we expect opcode to also be disabled.", + "PublicDescription": "Matches on Receive path of a UPI Port : Non-Coherent Standard, Match Opcode : Matches on Receive path of a UPI port. Match based on UMask specific bits: Z: Message Class (3-bit) Y: Message Class Enable W: Opcode (4-bit) V: Opcode Enable U: Local Enable T: Remote Enable S: Data Hdr Enable R: Non-Data Hdr Enable Q: Dual Slot Hdr Enable P: Single Slot Hdr Enable Link Layer control types are excluded (LL CTRL, slot NULL, LLCRD) even under specific opcode match_en cases. Note: If Message Class is disabled, we expect opcode to also be disabled.", "UMask": "0x10f", "Unit": "UPI" },
@@ -5763,7 +5763,7 @@ "EventCode": "0x04", "EventName": "UNC_UPI_TxL_BASIC_HDR_MATCH.NCB", "PerPkg": "1", - "PublicDescription": "Matches on Transmit path of a UPI Port : Non-Coherent Bypass : Matches on Transmit path of a UPI port.\r\nMatch based on UMask specific bits:\r\nZ: Message Class (3-bit)\r\nY: Message Class Enable\r\nW: Opcode (4-bit)\r\nV: Opcode Enable\r\nU: Local Enable\r\nT: Remote Enable\r\nS: Data Hdr Enable\r\nR: Non-Data Hdr Enable\r\nQ: Dual Slot Hdr Enable\r\nP: Single Slot Hdr Enable\r\nLink Layer control types are excluded (LL CTRL, slot NULL, LLCRD) even under specific opcode match_en cases.\r\nNote: If Message Class is disabled, we expect opcode to also be disabled.", + "PublicDescription": "Matches on Transmit path of a UPI Port : Non-Coherent Bypass : Matches on Transmit path of a UPI port. Match based on UMask specific bits: Z: Message Class (3-bit) Y: Message Class Enable W: Opcode (4-bit) V: Opcode Enable U: Local Enable T: Remote Enable S: Data Hdr Enable R: Non-Data Hdr Enable Q: Dual Slot Hdr Enable P: Single Slot Hdr Enable Link Layer control types are excluded (LL CTRL, slot NULL, LLCRD) even under specific opcode match_en cases. Note: If Message Class is disabled, we expect opcode to also be disabled.", "UMask": "0xe", "Unit": "UPI" },
@@ -5772,7 +5772,7 @@ "EventCode": "0x04", "EventName": "UNC_UPI_TxL_BASIC_HDR_MATCH.NCB_OPC", "PerPkg": "1", - "PublicDescription": "Matches on Transmit path of a UPI Port : Non-Coherent Bypass, Match Opcode : Matches on Transmit path of a UPI port.\r\nMatch based on UMask specific bits:\r\nZ: Message Class (3-bit)\r\nY: Message Class Enable\r\nW: Opcode (4-bit)\r\nV: Opcode Enable\r\nU: Local Enable\r\nT: Remote Enable\r\nS: Data Hdr Enable\r\nR: Non-Data Hdr Enable\r\nQ: Dual Slot Hdr Enable\r\nP: Single Slot Hdr Enable\r\nLink Layer control types are excluded (LL CTRL, slot NULL, LLCRD) even under specific opcode match_en cases.\r\nNote: If Message Class is disabled, we expect opcode to also be disabled.", + "PublicDescription": "Matches on Transmit path of a UPI Port : Non-Coherent Bypass, Match Opcode : Matches on Transmit path of a UPI port. Match based on UMask specific bits: Z: Message Class (3-bit) Y: Message Class Enable W: Opcode (4-bit) V: Opcode Enable U: Local Enable T: Remote Enable S: Data Hdr Enable R: Non-Data Hdr Enable Q: Dual Slot Hdr Enable P: Single Slot Hdr Enable Link Layer control types are excluded (LL CTRL, slot NULL, LLCRD) even under specific opcode match_en cases. Note: If Message Class is disabled, we expect opcode to also be disabled.", "UMask": "0x10e", "Unit": "UPI" },
@@ -5781,7 +5781,7 @@ "EventCode": "0x04", "EventName": "UNC_UPI_TxL_BASIC_HDR_MATCH.NCS", "PerPkg": "1", - "PublicDescription": "Matches on Transmit path of a UPI Port : Non-Coherent Standard : Matches on Transmit path of a UPI port.\r\nMatch based on UMask specific bits:\r\nZ: Message Class (3-bit)\r\nY: Message Class Enable\r\nW: Opcode (4-bit)\r\nV: Opcode Enable\r\nU: Local Enable\r\nT: Remote Enable\r\nS: Data Hdr Enable\r\nR: Non-Data Hdr Enable\r\nQ: Dual Slot Hdr Enable\r\nP: Single Slot Hdr Enable\r\nLink Layer control types are excluded (LL CTRL, slot NULL, LLCRD) even under specific opcode match_en cases.\r\nNote: If Message Class is disabled, we expect opcode to also be disabled.", + "PublicDescription": "Matches on Transmit path of a UPI Port : Non-Coherent Standard : Matches on Transmit path of a UPI port. Match based on UMask specific bits: Z: Message Class (3-bit) Y: Message Class Enable W: Opcode (4-bit) V: Opcode Enable U: Local Enable T: Remote Enable S: Data Hdr Enable R: Non-Data Hdr Enable Q: Dual Slot Hdr Enable P: Single Slot Hdr Enable Link Layer control types are excluded (LL CTRL, slot NULL, LLCRD) even under specific opcode match_en cases. Note: If Message Class is disabled, we expect opcode to also be disabled.", "UMask": "0xf", "Unit": "UPI" },
@@ -5790,7 +5790,7 @@ "EventCode": "0x04", "EventName": "UNC_UPI_TxL_BASIC_HDR_MATCH.NCS_OPC", "PerPkg": "1", - "PublicDescription": "Matches on Transmit path of a UPI Port : Non-Coherent Standard, Match Opcode : Matches on Transmit path of a UPI port.\r\nMatch based on UMask specific bits:\r\nZ: Message Class (3-bit)\r\nY: Message Class Enable\r\nW: Opcode (4-bit)\r\nV: Opcode Enable\r\nU: Local Enable\r\nT: Remote Enable\r\nS: Data Hdr Enable\r\nR: Non-Data Hdr Enable\r\nQ: Dual Slot Hdr Enable\r\nP: Single Slot Hdr Enable\r\nLink Layer control types are excluded (LL CTRL, slot NULL, LLCRD) even under specific opcode match_en cases.\r\nNote: If Message Class is disabled, we expect opcode to also be disabled.", + "PublicDescription": "Matches on Transmit path of a UPI Port : Non-Coherent Standard, Match Opcode : Matches on Transmit path of a UPI port. Match based on UMask specific bits: Z: Message Class (3-bit) Y: Message Class Enable W: Opcode (4-bit) V: Opcode Enable U: Local Enable T: Remote Enable S: Data Hdr Enable R: Non-Data Hdr Enable Q: Dual Slot Hdr Enable P: Single Slot Hdr Enable Link Layer control types are excluded (LL CTRL, slot NULL, LLCRD) even under specific opcode match_en cases. Note: If Message Class is disabled, we expect opcode to also be disabled.", "UMask": "0x10f", "Unit": "UPI" },
Signature · 1 line
2.44.0.396.g6e790dbe36-goog
Ian Rogers
reviewerPATCH 8/12 perf vendor events intel: Update sierraforest to 1.02
In reply to Ian RogersUpdate events from 1.01 to 1.02 as released in:
https://github.com/intel/perfmon/commit/451dd41ae627b56433ad4065bf3632789eb70834
Various description updates. Adds topdown events TOPDOWN_BAD_SPECULATION.ALL_P, TOPDOWN_BE_BOUND.ALL_P, TOPDOWN_FE_BOUND.ALL_P and TOPDOWN_RETIRING.ALL_P.
--- tools/perf/pmu-events/arch/x86/mapfile.csv | 2 +- .../arch/x86/sierraforest/pipeline.json | 36 ++++++++++++++++--- 2 files changed, 32 insertions(+), 6 deletions(-)
tools/perf/pmu-events/arch/x86/mapfile.csv +1 -1
@@ -27,7 +27,7 @@ GenuineIntel-6-2E,v4,nehalemex,core GenuineIntel-6-A7,v1.02,rocketlake,core GenuineIntel-6-2A,v19,sandybridge,core GenuineIntel-6-8F,v1.20,sapphirerapids,core -GenuineIntel-6-AF,v1.01,sierraforest,core +GenuineIntel-6-AF,v1.02,sierraforest,core GenuineIntel-6-(37|4A|4C|4D|5A),v15,silvermont,core GenuineIntel-6-(4E|5E|8E|9E|A5|A6),v58,skylake,core GenuineIntel-6-55-[01234],v1.32,skylakex,core
tools/perf/pmu-events/arch/x86/sierraforest/pipeline.json +31 -5
@@ -249,10 +249,17 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts the number of issue slots that were not consumed by the backend because allocation is stalled due to a mispredicted jump or a machine clear.", + "BriefDescription": "Counts the number of issue slots that were not consumed by the backend because allocation is stalled due to a mispredicted jump or a machine clear. [This event is alias to TOPDOWN_BAD_SPECULATION.ALL_P]", "EventCode": "0x73", "EventName": "TOPDOWN_BAD_SPECULATION.ALL", - "PublicDescription": "Counts the total number of issue slots that were not consumed by the backend because allocation is stalled due to a mispredicted jump or a machine clear. Only issue slots wasted due to fast nukes such as memory ordering nukes are counted. Other nukes are not accounted for. Counts all issue slots blocked during this recovery window, including relevant microcode flows, and while uops are not yet available in the instruction queue (IQ) or until an FE_BOUND event occurs besides OTHER and CISC. Also includes the issue slots that were consumed by the backend but were thrown away because they were younger than the mispredict or machine clear.", + "PublicDescription": "Counts the total number of issue slots that were not consumed by the backend because allocation is stalled due to a mispredicted jump or a machine clear. Only issue slots wasted due to fast nukes such as memory ordering nukes are counted. Other nukes are not accounted for. Counts all issue slots blocked during this recovery window, including relevant microcode flows, and while uops are not yet available in the instruction queue (IQ) or until an FE_BOUND event occurs besides OTHER and CISC. Also includes the issue slots that were consumed by the backend but were thrown away because they were younger than the mispredict or machine clear. [This event is alias to TOPDOWN_BAD_SPECULATION.ALL_P]", + "SampleAfterValue": "1000003" + }, + { + "BriefDescription": "Counts the number of issue slots that were not consumed by the backend because allocation is stalled due to a mispredicted jump or a machine clear. [This event is alias to TOPDOWN_BAD_SPECULATION.ALL]", + "EventCode": "0x73", + "EventName": "TOPDOWN_BAD_SPECULATION.ALL_P", + "PublicDescription": "Counts the total number of issue slots that were not consumed by the backend because allocation is stalled due to a mispredicted jump or a machine clear. Only issue slots wasted due to fast nukes such as memory ordering nukes are counted. Other nukes are not accounted for. Counts all issue slots blocked during this recovery window, including relevant microcode flows, and while uops are not yet available in the instruction queue (IQ) or until an FE_BOUND event occurs besides OTHER and CISC. Also includes the issue slots that were consumed by the backend but were thrown away because they were younger than the mispredict or machine clear. [This event is alias to TOPDOWN_BAD_SPECULATION.ALL]", "SampleAfterValue": "1000003" }, {
@@ -284,7 +291,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts the number of retirement slots not consumed due to backend stalls", + "BriefDescription": "Counts the number of retirement slots not consumed due to backend stalls [This event is alias to TOPDOWN_BE_BOUND.ALL_P]", "EventCode": "0x74", "EventName": "TOPDOWN_BE_BOUND.ALL", "SampleAfterValue": "1000003"
@@ -296,6 +303,12 @@ "SampleAfterValue": "1000003", "UMask": "0x1" }, + { + "BriefDescription": "Counts the number of retirement slots not consumed due to backend stalls [This event is alias to TOPDOWN_BE_BOUND.ALL]", + "EventCode": "0x74", + "EventName": "TOPDOWN_BE_BOUND.ALL_P", + "SampleAfterValue": "1000003" + }, { "BriefDescription": "Counts the number of issue slots every cycle that were not consumed by the backend due to memory reservation stall (scheduler not being able to accept another uop). This could be caused by RSV full or load/store buffer block.", "EventCode": "0x74",
@@ -332,11 +345,17 @@ "UMask": "0x10" }, { - "BriefDescription": "Counts the number of retirement slots not consumed due to front end stalls", + "BriefDescription": "Counts the number of retirement slots not consumed due to front end stalls [This event is alias to TOPDOWN_FE_BOUND.ALL_P]", "EventCode": "0x71", "EventName": "TOPDOWN_FE_BOUND.ALL", "SampleAfterValue": "1000003" }, + { + "BriefDescription": "Counts the number of retirement slots not consumed due to front end stalls [This event is alias to TOPDOWN_FE_BOUND.ALL]", + "EventCode": "0x71", + "EventName": "TOPDOWN_FE_BOUND.ALL_P", + "SampleAfterValue": "1000003" + }, { "BriefDescription": "Counts the number of issue slots every cycle that were not delivered by the frontend due to BAClear", "EventCode": "0x71",
@@ -409,12 +428,19 @@ "UMask": "0x4" }, { - "BriefDescription": "Counts the number of consumed retirement slots. Similar to UOPS_RETIRED.ALL", + "BriefDescription": "Counts the number of consumed retirement slots. Similar to UOPS_RETIRED.ALL [This event is alias to TOPDOWN_RETIRING.ALL_P]", "EventCode": "0x72", "EventName": "TOPDOWN_RETIRING.ALL", "PEBS": "1", "SampleAfterValue": "1000003" }, + { + "BriefDescription": "Counts the number of consumed retirement slots. Similar to UOPS_RETIRED.ALL [This event is alias to TOPDOWN_RETIRING.ALL]", + "EventCode": "0x72", + "EventName": "TOPDOWN_RETIRING.ALL_P", + "PEBS": "1", + "SampleAfterValue": "1000003" + }, { "BriefDescription": "Counts the number of uops issued by the front end every cycle.", "EventCode": "0x0e",
Signature · 1 line
2.44.0.396.g6e790dbe36-goog
Ian Rogers
reviewerPATCH 9/12 perf vendor events intel: Update skylakex to 1.33
In reply to Ian RogersUpdate events from 1.32 to 1.33 as released in:
https://github.com/intel/perfmon/commit/3fe7390dd18496c35ec3a9cf17de0473fd5485cb
Various description updates. Adds the event OFFCORE_RESPONSE.ALL_READS.L3_HIT.HIT_OTHER_CORE_FWD.
--- tools/perf/pmu-events/arch/x86/mapfile.csv | 2 +- tools/perf/pmu-events/arch/x86/skylakex/cache.json | 9 +++++++++ .../pmu-events/arch/x86/skylakex/frontend.json | 10 +++++----- .../perf/pmu-events/arch/x86/skylakex/memory.json | 2 +- tools/perf/pmu-events/arch/x86/skylakex/other.json | 2 +- .../pmu-events/arch/x86/skylakex/pipeline.json | 2 +- .../arch/x86/skylakex/uncore-interconnect.json | 14 +++++++------- .../pmu-events/arch/x86/skylakex/uncore-io.json | 2 +- .../arch/x86/skylakex/virtual-memory.json | 2 +- 9 files changed, 27 insertions(+), 18 deletions(-)
tools/perf/pmu-events/arch/x86/mapfile.csv +1 -1
@@ -30,7 +30,7 @@ GenuineIntel-6-8F,v1.20,sapphirerapids,core GenuineIntel-6-AF,v1.02,sierraforest,core GenuineIntel-6-(37|4A|4C|4D|5A),v15,silvermont,core GenuineIntel-6-(4E|5E|8E|9E|A5|A6),v58,skylake,core -GenuineIntel-6-55-[01234],v1.32,skylakex,core +GenuineIntel-6-55-[01234],v1.33,skylakex,core GenuineIntel-6-86,v1.21,snowridgex,core GenuineIntel-6-8[CD],v1.15,tigerlake,core GenuineIntel-6-2C,v5,westmereep-dp,core
tools/perf/pmu-events/arch/x86/skylakex/cache.json +9 -0
@@ -763,6 +763,15 @@ "SampleAfterValue": "100003", "UMask": "0x1" }, + { + "BriefDescription": "OFFCORE_RESPONSE.ALL_READS.L3_HIT.HIT_OTHER_CORE_FWD hit in the L3 and the snoop to one of the sibling cores hits the line in E/S/F state and the line is forwarded.", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.ALL_READS.L3_HIT.HIT_OTHER_CORE_FWD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x8003C07F7", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, { "BriefDescription": "Counts all demand & prefetch RFOs that have any response type.", "EventCode": "0xB7, 0xBB",
tools/perf/pmu-events/arch/x86/skylakex/frontend.json +5 -5
@@ -19,7 +19,7 @@ "BriefDescription": "Decode Stream Buffer (DSB)-to-MITE switches", "EventCode": "0xAB", "EventName": "DSB2MITE_SWITCHES.COUNT", - "PublicDescription": "This event counts the number of the Decode Stream Buffer (DSB)-to-MITE switches including all misses because of missing Decode Stream Buffer (DSB) cache and u-arch forced misses.\nNote: Invoking MITE requires two or three cycles delay.", + "PublicDescription": "This event counts the number of the Decode Stream Buffer (DSB)-to-MITE switches including all misses because of missing Decode Stream Buffer (DSB) cache and u-arch forced misses. Note: Invoking MITE requires two or three cycles delay.", "SampleAfterValue": "2000003", "UMask": "0x1" },
@@ -267,11 +267,11 @@ "UMask": "0x4" }, { - "BriefDescription": "Cycles Decode Stream Buffer (DSB) is delivering 4 Uops [This event is alias to IDQ.DSB_CYCLES_OK]", + "BriefDescription": "Cycles Decode Stream Buffer (DSB) is delivering 4 or more Uops [This event is alias to IDQ.DSB_CYCLES_OK]", "CounterMask": "4", "EventCode": "0x79", "EventName": "IDQ.ALL_DSB_CYCLES_4_UOPS", - "PublicDescription": "Counts the number of cycles 4 uops were delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path. Count includes uops that may 'bypass' the IDQ. [This event is alias to IDQ.DSB_CYCLES_OK]", + "PublicDescription": "Counts the number of cycles 4 or more uops were delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path. Count includes uops that may 'bypass' the IDQ. [This event is alias to IDQ.DSB_CYCLES_OK]", "SampleAfterValue": "2000003", "UMask": "0x18" },
@@ -321,11 +321,11 @@ "UMask": "0x18" }, { - "BriefDescription": "Cycles Decode Stream Buffer (DSB) is delivering 4 Uops [This event is alias to IDQ.ALL_DSB_CYCLES_4_UOPS]", + "BriefDescription": "Cycles Decode Stream Buffer (DSB) is delivering 4 or more Uops [This event is alias to IDQ.ALL_DSB_CYCLES_4_UOPS]", "CounterMask": "4", "EventCode": "0x79", "EventName": "IDQ.DSB_CYCLES_OK", - "PublicDescription": "Counts the number of cycles 4 uops were delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path. Count includes uops that may 'bypass' the IDQ. [This event is alias to IDQ.ALL_DSB_CYCLES_4_UOPS]", + "PublicDescription": "Counts the number of cycles 4 or more uops were delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path. Count includes uops that may 'bypass' the IDQ. [This event is alias to IDQ.ALL_DSB_CYCLES_4_UOPS]", "SampleAfterValue": "2000003", "UMask": "0x18" },
tools/perf/pmu-events/arch/x86/skylakex/memory.json +1 -1
@@ -864,7 +864,7 @@ "BriefDescription": "Number of times an RTM execution aborted due to any reasons (multiple categories may count as one).", "EventCode": "0xC9", "EventName": "RTM_RETIRED.ABORTED", - "PEBS": "1", + "PEBS": "2", "PublicDescription": "Number of times RTM abort was triggered.", "SampleAfterValue": "2000003", "UMask": "0x4"
tools/perf/pmu-events/arch/x86/skylakex/other.json +1 -1
@@ -19,7 +19,7 @@ "BriefDescription": "Core cycles where the core was running in a manner where Turbo may be clipped to the AVX512 turbo schedule.", "EventCode": "0x28", "EventName": "CORE_POWER.LVL2_TURBO_LICENSE", - "PublicDescription": "Core cycles where the core was running with power-delivery for license level 2 (introduced in Skylake Server michroarchtecture). This includes high current AVX 512-bit instructions.", + "PublicDescription": "Core cycles where the core was running with power-delivery for license level 2 (introduced in Skylake Server microarchitecture). This includes high current AVX 512-bit instructions.", "SampleAfterValue": "200003", "UMask": "0x20" },
tools/perf/pmu-events/arch/x86/skylakex/pipeline.json +1 -1
@@ -396,7 +396,7 @@ "Errata": "SKL091, SKL044", "EventCode": "0xC0", "EventName": "INST_RETIRED.NOP", - "PEBS": "1", + "PEBS": "2", "SampleAfterValue": "2000003", "UMask": "0x2" },
tools/perf/pmu-events/arch/x86/skylakex/uncore-interconnect.json +7 -7
@@ -38,7 +38,7 @@ "EventCode": "0x10", "EventName": "UNC_I_COHERENT_OPS.CLFLUSH", "PerPkg": "1", - "PublicDescription": "Counts the number of coherency related operations servied by the IRP", + "PublicDescription": "Counts the number of coherency related operations serviced by the IRP", "UMask": "0x80", "Unit": "IRP" },
@@ -47,7 +47,7 @@ "EventCode": "0x10", "EventName": "UNC_I_COHERENT_OPS.CRD", "PerPkg": "1", - "PublicDescription": "Counts the number of coherency related operations servied by the IRP", + "PublicDescription": "Counts the number of coherency related operations serviced by the IRP", "UMask": "0x2", "Unit": "IRP" },
@@ -56,7 +56,7 @@ "EventCode": "0x10", "EventName": "UNC_I_COHERENT_OPS.DRD", "PerPkg": "1", - "PublicDescription": "Counts the number of coherency related operations servied by the IRP", + "PublicDescription": "Counts the number of coherency related operations serviced by the IRP", "UMask": "0x4", "Unit": "IRP" },
@@ -65,7 +65,7 @@ "EventCode": "0x10", "EventName": "UNC_I_COHERENT_OPS.PCIDCAHINT", "PerPkg": "1", - "PublicDescription": "Counts the number of coherency related operations servied by the IRP", + "PublicDescription": "Counts the number of coherency related operations serviced by the IRP", "UMask": "0x20", "Unit": "IRP" },
@@ -74,7 +74,7 @@ "EventCode": "0x10", "EventName": "UNC_I_COHERENT_OPS.PCIRDCUR", "PerPkg": "1", - "PublicDescription": "Counts the number of coherency related operations servied by the IRP", + "PublicDescription": "Counts the number of coherency related operations serviced by the IRP", "UMask": "0x1", "Unit": "IRP" },
@@ -101,7 +101,7 @@ "EventCode": "0x10", "EventName": "UNC_I_COHERENT_OPS.WBMTOI", "PerPkg": "1", - "PublicDescription": "Counts the number of coherency related operations servied by the IRP", + "PublicDescription": "Counts the number of coherency related operations serviced by the IRP", "UMask": "0x40", "Unit": "IRP" },
@@ -500,7 +500,7 @@ "EventCode": "0x11", "EventName": "UNC_I_TRANSACTIONS.WRITES", "PerPkg": "1", - "PublicDescription": "Counts the number of Inbound transactions from the IRP to the Uncore. This can be filtered based on request type in addition to the source queue. Note the special filtering equation. We do OR-reduction on the request type. If the SOURCE bit is set, then we also do AND qualification based on the source portID.; Trackes only write requests. Each write request should have a prefetch, so there is no need to explicitly track these requests. For writes that are tickled and have to retry, the counter will be incremented for each retry.", + "PublicDescription": "Counts the number of Inbound transactions from the IRP to the Uncore. This can be filtered based on request type in addition to the source queue. Note the special filtering equation. We do OR-reduction on the request type. If the SOURCE bit is set, then we also do AND qualification based on the source portID.; Tracks only write requests. Each write request should have a prefetch, so there is no need to explicitly track these requests. For writes that are tickled and have to retry, the counter will be incremented for each retry.", "UMask": "0x2", "Unit": "IRP" },
tools/perf/pmu-events/arch/x86/skylakex/uncore-io.json +1 -1
@@ -34,7 +34,7 @@ "EventCode": "0x1", "EventName": "UNC_IIO_CLOCKTICKS", "PerPkg": "1", - "PublicDescription": "Counts clockticks of the 1GHz trafiic controller clock in the IIO unit.", + "PublicDescription": "Counts clockticks of the 1GHz traffic controller clock in the IIO unit.", "Unit": "IIO" }, {
tools/perf/pmu-events/arch/x86/skylakex/virtual-memory.json +1 -1
@@ -205,7 +205,7 @@ "BriefDescription": "Counts 1 per cycle for each PMH that is busy with a page walk for an instruction fetch request. EPT page walk duration are excluded in Skylake.", "EventCode": "0x85", "EventName": "ITLB_MISSES.WALK_PENDING", - "PublicDescription": "Counts 1 per cycle for each PMH (Page Miss Handler) that is busy with a page walk for an instruction fetch request. EPT page walk duration are excluded in Skylake michroarchitecture.", + "PublicDescription": "Counts 1 per cycle for each PMH (Page Miss Handler) that is busy with a page walk for an instruction fetch request. EPT page walk duration are excluded in Skylake microarchitecture.", "SampleAfterValue": "100003", "UMask": "0x10" },
Signature · 1 line
2.44.0.396.g6e790dbe36-goog
Ian Rogers
reviewerPATCH 10/12 perf vendor events intel: Update skylake to v58
In reply to Ian RogersUpdate events from:
https://github.com/intel/perfmon/commit/f2e5136e062a91ae554dc40530132e66f9271848
This change didn't increase the version number from v58.
Updates various descriptions.
--- tools/perf/pmu-events/arch/x86/skylake/frontend.json | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-)
tools/perf/pmu-events/arch/x86/skylake/frontend.json +5 -5
@@ -19,7 +19,7 @@ "BriefDescription": "Decode Stream Buffer (DSB)-to-MITE switches", "EventCode": "0xAB", "EventName": "DSB2MITE_SWITCHES.COUNT", - "PublicDescription": "This event counts the number of the Decode Stream Buffer (DSB)-to-MITE switches including all misses because of missing Decode Stream Buffer (DSB) cache and u-arch forced misses.\nNote: Invoking MITE requires two or three cycles delay.", + "PublicDescription": "This event counts the number of the Decode Stream Buffer (DSB)-to-MITE switches including all misses because of missing Decode Stream Buffer (DSB) cache and u-arch forced misses. Note: Invoking MITE requires two or three cycles delay.", "SampleAfterValue": "2000003", "UMask": "0x1" },
@@ -267,11 +267,11 @@ "UMask": "0x4" }, { - "BriefDescription": "Cycles Decode Stream Buffer (DSB) is delivering 4 Uops [This event is alias to IDQ.DSB_CYCLES_OK]", + "BriefDescription": "Cycles Decode Stream Buffer (DSB) is delivering 4 or more Uops [This event is alias to IDQ.DSB_CYCLES_OK]", "CounterMask": "4", "EventCode": "0x79", "EventName": "IDQ.ALL_DSB_CYCLES_4_UOPS", - "PublicDescription": "Counts the number of cycles 4 uops were delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path. Count includes uops that may 'bypass' the IDQ. [This event is alias to IDQ.DSB_CYCLES_OK]", + "PublicDescription": "Counts the number of cycles 4 or more uops were delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path. Count includes uops that may 'bypass' the IDQ. [This event is alias to IDQ.DSB_CYCLES_OK]", "SampleAfterValue": "2000003", "UMask": "0x18" },
@@ -321,11 +321,11 @@ "UMask": "0x18" }, { - "BriefDescription": "Cycles Decode Stream Buffer (DSB) is delivering 4 Uops [This event is alias to IDQ.ALL_DSB_CYCLES_4_UOPS]", + "BriefDescription": "Cycles Decode Stream Buffer (DSB) is delivering 4 or more Uops [This event is alias to IDQ.ALL_DSB_CYCLES_4_UOPS]", "CounterMask": "4", "EventCode": "0x79", "EventName": "IDQ.DSB_CYCLES_OK", - "PublicDescription": "Counts the number of cycles 4 uops were delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path. Count includes uops that may 'bypass' the IDQ. [This event is alias to IDQ.ALL_DSB_CYCLES_4_UOPS]", + "PublicDescription": "Counts the number of cycles 4 or more uops were delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path. Count includes uops that may 'bypass' the IDQ. [This event is alias to IDQ.ALL_DSB_CYCLES_4_UOPS]", "SampleAfterValue": "2000003", "UMask": "0x18" },
Signature · 1 line
2.44.0.396.g6e790dbe36-goog
Ian Rogers
reviewerPATCH 11/12 perf vendor events intel: Update snowridgex to 1.22
In reply to Ian RogersUpdate events from 1.21 to 1.22 as released in:
https://github.com/intel/perfmon/commit/ba4f96039f96231b51e3eb69d5a21e2b00f6de5b
Updates various descriptions and removes the event UNC_IIO_NUM_REQ_FROM_CPU.IRP.
--- tools/perf/pmu-events/arch/x86/mapfile.csv | 2 +- .../pmu-events/arch/x86/snowridgex/uncore-cache.json | 4 ++-- .../arch/x86/snowridgex/uncore-interconnect.json | 6 +++--- .../pmu-events/arch/x86/snowridgex/uncore-io.json | 11 ----------- 4 files changed, 6 insertions(+), 17 deletions(-)
tools/perf/pmu-events/arch/x86/mapfile.csv +1 -1
@@ -31,7 +31,7 @@ GenuineIntel-6-AF,v1.02,sierraforest,core GenuineIntel-6-(37|4A|4C|4D|5A),v15,silvermont,core GenuineIntel-6-(4E|5E|8E|9E|A5|A6),v58,skylake,core GenuineIntel-6-55-[01234],v1.33,skylakex,core -GenuineIntel-6-86,v1.21,snowridgex,core +GenuineIntel-6-86,v1.22,snowridgex,core GenuineIntel-6-8[CD],v1.15,tigerlake,core GenuineIntel-6-2C,v5,westmereep-dp,core GenuineIntel-6-25,v4,westmereep-sp,core
tools/perf/pmu-events/arch/x86/snowridgex/uncore-cache.json +2 -2
@@ -1444,7 +1444,7 @@ "Unit": "CHA" }, { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_LLC_LOOKUP.DATA_READ_LOCAL", + "BriefDescription": "This event is deprecated.", "Deprecated": "1", "EventCode": "0x34", "EventName": "UNC_CHA_LLC_LOOKUP.DMND_READ_LOCAL",
@@ -1638,7 +1638,7 @@ "Unit": "CHA" }, { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_LLC_LOOKUP.RFO_LOCAL", + "BriefDescription": "This event is deprecated.", "Deprecated": "1", "EventCode": "0x34", "EventName": "UNC_CHA_LLC_LOOKUP.RFO_PREF_LOCAL",
tools/perf/pmu-events/arch/x86/snowridgex/uncore-interconnect.json +3 -3
@@ -38,7 +38,7 @@ "EventCode": "0x10", "EventName": "UNC_I_COHERENT_OPS.CLFLUSH", "PerPkg": "1", - "PublicDescription": "Coherent Ops : CLFlush : Counts the number of coherency related operations servied by the IRP", + "PublicDescription": "Coherent Ops : CLFlush : Counts the number of coherency related operations serviced by the IRP", "UMask": "0x80", "Unit": "IRP" },
@@ -65,7 +65,7 @@ "EventCode": "0x10", "EventName": "UNC_I_COHERENT_OPS.WBMTOI", "PerPkg": "1", - "PublicDescription": "Coherent Ops : WbMtoI : Counts the number of coherency related operations servied by the IRP", + "PublicDescription": "Coherent Ops : WbMtoI : Counts the number of coherency related operations serviced by the IRP", "UMask": "0x40", "Unit": "IRP" },
@@ -454,7 +454,7 @@ "EventCode": "0x11", "EventName": "UNC_I_TRANSACTIONS.WRITES", "PerPkg": "1", - "PublicDescription": "Inbound Transaction Count : Writes : Counts the number of Inbound transactions from the IRP to the Uncore. This can be filtered based on request type in addition to the source queue. Note the special filtering equation. We do OR-reduction on the request type. If the SOURCE bit is set, then we also do AND qualification based on the source portID. : Trackes only write requests. Each write request should have a prefetch, so there is no need to explicitly track these requests. For writes that are tickled and have to retry, the counter will be incremented for each retry.", + "PublicDescription": "Inbound Transaction Count : Writes : Counts the number of Inbound transactions from the IRP to the Uncore. This can be filtered based on request type in addition to the source queue. Note the special filtering equation. We do OR-reduction on the request type. If the SOURCE bit is set, then we also do AND qualification based on the source portID. : Tracks only write requests. Each write request should have a prefetch, so there is no need to explicitly track these requests. For writes that are tickled and have to retry, the counter will be incremented for each retry.", "UMask": "0x2", "Unit": "IRP" },
tools/perf/pmu-events/arch/x86/snowridgex/uncore-io.json +0 -11
@@ -2505,17 +2505,6 @@ "UMask": "0x10", "Unit": "IIO" }, - { - "BriefDescription": "Number requests sent to PCIe from main die : From IRP", - "EventCode": "0xC2", - "EventName": "UNC_IIO_NUM_REQ_FROM_CPU.IRP", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0xFF", - "PublicDescription": "Number requests sent to PCIe from main die : From IRP : Captures Posted/Non-posted allocations from IRP. i.e. either non-confined P2P traffic or from the CPU", - "UMask": "0x1", - "Unit": "IIO" - }, { "BriefDescription": "Number requests sent to PCIe from main die : From ITC", "EventCode": "0xC2",
Signature · 1 line
2.44.0.396.g6e790dbe36-goog
Ian Rogers
reviewerPATCH 12/12 perf vendor events intel: Remove info metrics erroneously in TopdownL1
In reply to Ian RogersBug affected server metrics only. This doesn't impact default metrics but if the TopdownL1 metric group is specified. Passes on the fix in:
https://github.com/intel/perfmon/commit/b09f0a3953234ec592b4a872b87764c78da05d8b
--- .../arch/x86/broadwellx/bdx-metrics.json | 35 +++--- .../arch/x86/cascadelakex/clx-metrics.json | 85 +++++-------- .../arch/x86/haswellx/hsx-metrics.json | 35 +++--- .../arch/x86/icelakex/icx-metrics.json | 95 ++++++-------- .../arch/x86/sapphirerapids/spr-metrics.json | 119 +++++++----------- .../arch/x86/skylakex/skx-metrics.json | 85 +++++-------- 6 files changed, 181 insertions(+), 273 deletions(-)
tools/perf/pmu-events/arch/x86/broadwellx/bdx-metrics.json +14 -21
@@ -732,9 +732,8 @@ { "BriefDescription": "Average Parallel L2 cache miss data reads", "MetricExpr": "tma_info_memory_latency_data_l2_mlp", - "MetricGroup": "Memory_BW;Offcore;TopdownL1;tma_L1_group", - "MetricName": "tma_info_memory_data_l2_mlp", - "MetricgroupNoGroup": "TopdownL1" + "MetricGroup": "Memory_BW;Offcore", + "MetricName": "tma_info_memory_data_l2_mlp" }, { "BriefDescription": "",
@@ -745,9 +744,8 @@ { "BriefDescription": "Average per-core data fill bandwidth to the L1 data cache [GB / sec]", "MetricExpr": "64 * L1D.REPLACEMENT / 1e9 / (duration_time * 1e3 / 1e3)", - "MetricGroup": "Mem;MemoryBW;TopdownL1;tma_L1_group", - "MetricName": "tma_info_memory_l1d_cache_fill_bw_2t", - "MetricgroupNoGroup": "TopdownL1" + "MetricGroup": "Mem;MemoryBW", + "MetricName": "tma_info_memory_l1d_cache_fill_bw_2t" }, { "BriefDescription": "L1 cache true misses per kilo instruction for retired demand loads",
@@ -764,9 +762,8 @@ { "BriefDescription": "Average per-core data fill bandwidth to the L2 cache [GB / sec]", "MetricExpr": "64 * L2_LINES_IN.ALL / 1e9 / (duration_time * 1e3 / 1e3)", - "MetricGroup": "Mem;MemoryBW;TopdownL1;tma_L1_group", - "MetricName": "tma_info_memory_l2_cache_fill_bw_2t", - "MetricgroupNoGroup": "TopdownL1" + "MetricGroup": "Mem;MemoryBW", + "MetricName": "tma_info_memory_l2_cache_fill_bw_2t" }, { "BriefDescription": "L2 cache hits per kilo instruction for all request types (including speculative)",
@@ -807,9 +804,8 @@ { "BriefDescription": "Average per-core data fill bandwidth to the L3 cache [GB / sec]", "MetricExpr": "64 * LONGEST_LAT_CACHE.MISS / 1e9 / (duration_time * 1e3 / 1e3)", - "MetricGroup": "Mem;MemoryBW;TopdownL1;tma_L1_group", - "MetricName": "tma_info_memory_l3_cache_fill_bw_2t", - "MetricgroupNoGroup": "TopdownL1" + "MetricGroup": "Mem;MemoryBW", + "MetricName": "tma_info_memory_l3_cache_fill_bw_2t" }, { "BriefDescription": "L3 cache true misses per kilo instruction for retired demand loads",
@@ -838,16 +834,14 @@ { "BriefDescription": "Average Latency for L2 cache miss demand Loads", "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD / OFFCORE_REQUESTS.DEMAND_DATA_RD", - "MetricGroup": "Memory_Lat;Offcore;TopdownL1;tma_L1_group", - "MetricName": "tma_info_memory_load_l2_miss_latency", - "MetricgroupNoGroup": "TopdownL1" + "MetricGroup": "Memory_Lat;Offcore", + "MetricName": "tma_info_memory_load_l2_miss_latency" }, { "BriefDescription": "Average Parallel L2 cache miss demand Loads", "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD / OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_DATA_RD", - "MetricGroup": "Memory_BW;Offcore;TopdownL1;tma_L1_group", - "MetricName": "tma_info_memory_load_l2_mlp", - "MetricgroupNoGroup": "TopdownL1" + "MetricGroup": "Memory_BW;Offcore", + "MetricName": "tma_info_memory_load_l2_mlp" }, { "BriefDescription": "Actual Average Latency for L1 data-cache miss demand load operations (in core cycles)",
@@ -867,9 +861,8 @@ { "BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses", "MetricExpr": "tma_info_memory_tlb_page_walks_utilization", - "MetricGroup": "Mem;MemoryTLB;TopdownL1;tma_L1_group", - "MetricName": "tma_info_memory_page_walks_utilization", - "MetricgroupNoGroup": "TopdownL1" + "MetricGroup": "Mem;MemoryTLB", + "MetricName": "tma_info_memory_page_walks_utilization" }, { "BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses",
tools/perf/pmu-events/arch/x86/cascadelakex/clx-metrics.json +34 -51
175 lines not on this page · raw message
tools/perf/pmu-events/arch/x86/haswellx/hsx-metrics.json +14 -21
@@ -618,9 +618,8 @@ { "BriefDescription": "Average Parallel L2 cache miss data reads", "MetricExpr": "tma_info_memory_latency_data_l2_mlp", - "MetricGroup": "Memory_BW;Offcore;TopdownL1;tma_L1_group", - "MetricName": "tma_info_memory_data_l2_mlp", - "MetricgroupNoGroup": "TopdownL1" + "MetricGroup": "Memory_BW;Offcore", + "MetricName": "tma_info_memory_data_l2_mlp" }, { "BriefDescription": "",
@@ -631,9 +630,8 @@ { "BriefDescription": "Average per-core data fill bandwidth to the L1 data cache [GB / sec]", "MetricExpr": "64 * L1D.REPLACEMENT / 1e9 / (duration_time * 1e3 / 1e3)", - "MetricGroup": "Mem;MemoryBW;TopdownL1;tma_L1_group", - "MetricName": "tma_info_memory_l1d_cache_fill_bw_2t", - "MetricgroupNoGroup": "TopdownL1" + "MetricGroup": "Mem;MemoryBW", + "MetricName": "tma_info_memory_l1d_cache_fill_bw_2t" }, { "BriefDescription": "L1 cache true misses per kilo instruction for retired demand loads",
@@ -650,9 +648,8 @@ { "BriefDescription": "Average per-core data fill bandwidth to the L2 cache [GB / sec]", "MetricExpr": "64 * L2_LINES_IN.ALL / 1e9 / (duration_time * 1e3 / 1e3)", - "MetricGroup": "Mem;MemoryBW;TopdownL1;tma_L1_group", - "MetricName": "tma_info_memory_l2_cache_fill_bw_2t", - "MetricgroupNoGroup": "TopdownL1" + "MetricGroup": "Mem;MemoryBW", + "MetricName": "tma_info_memory_l2_cache_fill_bw_2t" }, { "BriefDescription": "L2 cache true misses per kilo instruction for retired demand loads",
@@ -669,9 +666,8 @@ { "BriefDescription": "Average per-core data fill bandwidth to the L3 cache [GB / sec]", "MetricExpr": "64 * LONGEST_LAT_CACHE.MISS / 1e9 / (duration_time * 1e3 / 1e3)", - "MetricGroup": "Mem;MemoryBW;TopdownL1;tma_L1_group", - "MetricName": "tma_info_memory_l3_cache_fill_bw_2t", - "MetricgroupNoGroup": "TopdownL1" + "MetricGroup": "Mem;MemoryBW", + "MetricName": "tma_info_memory_l3_cache_fill_bw_2t" }, { "BriefDescription": "L3 cache true misses per kilo instruction for retired demand loads",
@@ -700,16 +696,14 @@ { "BriefDescription": "Average Latency for L2 cache miss demand Loads", "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD / OFFCORE_REQUESTS.DEMAND_DATA_RD", - "MetricGroup": "Memory_Lat;Offcore;TopdownL1;tma_L1_group", - "MetricName": "tma_info_memory_load_l2_miss_latency", - "MetricgroupNoGroup": "TopdownL1" + "MetricGroup": "Memory_Lat;Offcore", + "MetricName": "tma_info_memory_load_l2_miss_latency" }, { "BriefDescription": "Average Parallel L2 cache miss demand Loads", "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD / OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_DATA_RD", - "MetricGroup": "Memory_BW;Offcore;TopdownL1;tma_L1_group", - "MetricName": "tma_info_memory_load_l2_mlp", - "MetricgroupNoGroup": "TopdownL1" + "MetricGroup": "Memory_BW;Offcore", + "MetricName": "tma_info_memory_load_l2_mlp" }, { "BriefDescription": "Actual Average Latency for L1 data-cache miss demand load operations (in core cycles)",
@@ -729,9 +723,8 @@ { "BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses", "MetricExpr": "tma_info_memory_tlb_page_walks_utilization", - "MetricGroup": "Mem;MemoryTLB;TopdownL1;tma_L1_group", - "MetricName": "tma_info_memory_page_walks_utilization", - "MetricgroupNoGroup": "TopdownL1" + "MetricGroup": "Mem;MemoryTLB", + "MetricName": "tma_info_memory_page_walks_utilization" }, { "BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses",
tools/perf/pmu-events/arch/x86/icelakex/icx-metrics.json +38 -57
193 lines not on this page · raw message
tools/perf/pmu-events/arch/x86/sapphirerapids/spr-metrics.json +47 -72
248 lines not on this page · raw message
tools/perf/pmu-events/arch/x86/skylakex/skx-metrics.json +34 -51
175 lines not on this page · raw message
Signature · 1 line
2.44.0.396.g6e790dbe36-goog
Arnaldo Carvalho de Melo
maintainerQuoted 5 lines · Ian Rogers
Update events to the latest on:
https://github.com/intel/perfmonUsing the converter script:
https://github.com/intel/perfmon/blob/main/scripts/create_perf_json.py
Kan,
Can you please take a look and provide an Acked or Reviewed-by?
Thanks!
- Arnaldo
Quoted 74 lines
Ian Rogers (12):
perf vendor events intel: Update cascadelakex to 1.21
perf vendor events intel: Update emeraldrapids to 1.06 perf vendor events intel: Update grandridge to 1.02
perf vendor events intel: Update icelakex to 1.24
perf vendor events intel: Update lunarlake to 1.01
perf vendor events intel: Update meteorlake to 1.08
perf vendor events intel: Update sapphirerapids to 1.20 perf vendor events intel: Update sierraforest to 1.02
perf vendor events intel: Update skylakex to 1.33
perf vendor events intel: Update skylake to v58
perf vendor events intel: Update snowridgex to 1.22
perf vendor events intel: Remove info metrics erroneously in TopdownL1.../arch/x86/broadwellx/bdx-metrics.json | 35 +++--- .../arch/x86/cascadelakex/clx-metrics.json | 85 +++++-------- .../arch/x86/cascadelakex/frontend.json | 10 +- .../arch/x86/cascadelakex/memory.json | 2 +- .../arch/x86/cascadelakex/other.json | 2 +- .../arch/x86/cascadelakex/pipeline.json | 2 +- .../x86/cascadelakex/uncore-interconnect.json | 14 +-- .../arch/x86/cascadelakex/virtual-memory.json | 2 +- .../arch/x86/emeraldrapids/frontend.json | 2 +- .../arch/x86/emeraldrapids/memory.json | 1 + .../arch/x86/emeraldrapids/pipeline.json | 3 + .../arch/x86/emeraldrapids/uncore-cache.json | 112 ++++++++++++++++- .../emeraldrapids/uncore-interconnect.json | 26 ++-- .../arch/x86/grandridge/pipeline.json | 43 ++++++- .../arch/x86/grandridge/uncore-cache.json | 28 ++++- .../arch/x86/haswellx/hsx-metrics.json | 35 +++--- .../arch/x86/icelakex/frontend.json | 2 +- .../arch/x86/icelakex/icx-metrics.json | 95 ++++++-------- .../pmu-events/arch/x86/icelakex/memory.json | 1 + .../arch/x86/icelakex/uncore-cache.json | 22 +++- .../x86/icelakex/uncore-interconnect.json | 64 +++++----- .../arch/x86/icelakex/uncore-io.json | 11 -- .../pmu-events/arch/x86/lunarlake/cache.json | 24 ++-- .../arch/x86/lunarlake/frontend.json | 2 +- .../pmu-events/arch/x86/lunarlake/memory.json | 4 +- .../pmu-events/arch/x86/lunarlake/other.json | 4 +- .../arch/x86/lunarlake/pipeline.json | 109 +++++++++++++--- tools/perf/pmu-events/arch/x86/mapfile.csv | 20 +-- .../pmu-events/arch/x86/meteorlake/cache.json | 30 +++++ .../arch/x86/meteorlake/frontend.json | 4 +- .../arch/x86/meteorlake/memory.json | 20 +++ .../pmu-events/arch/x86/meteorlake/other.json | 42 ++++++- .../arch/x86/meteorlake/pipeline.json | 44 +++++-- .../x86/meteorlake/uncore-interconnect.json | 22 +++- .../arch/x86/sapphirerapids/cache.json | 1 + .../arch/x86/sapphirerapids/frontend.json | 2 +- .../arch/x86/sapphirerapids/memory.json | 1 + .../arch/x86/sapphirerapids/pipeline.json | 19 +-- .../arch/x86/sapphirerapids/spr-metrics.json | 119 +++++++----------- .../arch/x86/sapphirerapids/uncore-cache.json | 112 ++++++++++++++++- .../sapphirerapids/uncore-interconnect.json | 26 ++-- .../arch/x86/sierraforest/pipeline.json | 36 +++++- .../pmu-events/arch/x86/skylake/frontend.json | 10 +- .../pmu-events/arch/x86/skylakex/cache.json | 9 ++ .../arch/x86/skylakex/frontend.json | 10 +- .../pmu-events/arch/x86/skylakex/memory.json | 2 +- .../pmu-events/arch/x86/skylakex/other.json | 2 +- .../arch/x86/skylakex/pipeline.json | 2 +- .../arch/x86/skylakex/skx-metrics.json | 85 +++++-------- .../x86/skylakex/uncore-interconnect.json | 14 +-- .../arch/x86/skylakex/uncore-io.json | 2 +- .../arch/x86/skylakex/virtual-memory.json | 2 +- .../arch/x86/snowridgex/uncore-cache.json | 4 +- .../x86/snowridgex/uncore-interconnect.json | 6 +- .../arch/x86/snowridgex/uncore-io.json | 11 -- 55 files changed, 911 insertions(+), 486 deletions(-)Signature · 1 line
2.44.0.396.g6e790dbe36-goog
Liang, Kan
Reviewed-byQuoted 11 lines · Arnaldo Carvalho de Melo
Quoted 5 lines · Ian Rogers
Update events to the latest on:
https://github.com/intel/perfmonUsing the converter script:
https://github.com/intel/perfmon/blob/main/scripts/create_perf_json.pyKan,
Can you please take a look and provide an Acked or Reviewed-by?
Sure. The patch series look good to me. Thanks Ian!
Thanks,
Kan
Quoted 79 lines
Thanks!
- Arnaldo
Quoted 74 lines
Ian Rogers (12):
perf vendor events intel: Update cascadelakex to 1.21
perf vendor events intel: Update emeraldrapids to 1.06 perf vendor events intel: Update grandridge to 1.02
perf vendor events intel: Update icelakex to 1.24
perf vendor events intel: Update lunarlake to 1.01
perf vendor events intel: Update meteorlake to 1.08
perf vendor events intel: Update sapphirerapids to 1.20 perf vendor events intel: Update sierraforest to 1.02
perf vendor events intel: Update skylakex to 1.33
perf vendor events intel: Update skylake to v58
perf vendor events intel: Update snowridgex to 1.22
perf vendor events intel: Remove info metrics erroneously in TopdownL1.../arch/x86/broadwellx/bdx-metrics.json | 35 +++--- .../arch/x86/cascadelakex/clx-metrics.json | 85 +++++-------- .../arch/x86/cascadelakex/frontend.json | 10 +- .../arch/x86/cascadelakex/memory.json | 2 +- .../arch/x86/cascadelakex/other.json | 2 +- .../arch/x86/cascadelakex/pipeline.json | 2 +- .../x86/cascadelakex/uncore-interconnect.json | 14 +-- .../arch/x86/cascadelakex/virtual-memory.json | 2 +- .../arch/x86/emeraldrapids/frontend.json | 2 +- .../arch/x86/emeraldrapids/memory.json | 1 + .../arch/x86/emeraldrapids/pipeline.json | 3 + .../arch/x86/emeraldrapids/uncore-cache.json | 112 ++++++++++++++++- .../emeraldrapids/uncore-interconnect.json | 26 ++-- .../arch/x86/grandridge/pipeline.json | 43 ++++++- .../arch/x86/grandridge/uncore-cache.json | 28 ++++- .../arch/x86/haswellx/hsx-metrics.json | 35 +++--- .../arch/x86/icelakex/frontend.json | 2 +- .../arch/x86/icelakex/icx-metrics.json | 95 ++++++-------- .../pmu-events/arch/x86/icelakex/memory.json | 1 + .../arch/x86/icelakex/uncore-cache.json | 22 +++- .../x86/icelakex/uncore-interconnect.json | 64 +++++----- .../arch/x86/icelakex/uncore-io.json | 11 -- .../pmu-events/arch/x86/lunarlake/cache.json | 24 ++-- .../arch/x86/lunarlake/frontend.json | 2 +- .../pmu-events/arch/x86/lunarlake/memory.json | 4 +- .../pmu-events/arch/x86/lunarlake/other.json | 4 +- .../arch/x86/lunarlake/pipeline.json | 109 +++++++++++++--- tools/perf/pmu-events/arch/x86/mapfile.csv | 20 +-- .../pmu-events/arch/x86/meteorlake/cache.json | 30 +++++ .../arch/x86/meteorlake/frontend.json | 4 +- .../arch/x86/meteorlake/memory.json | 20 +++ .../pmu-events/arch/x86/meteorlake/other.json | 42 ++++++- .../arch/x86/meteorlake/pipeline.json | 44 +++++-- .../x86/meteorlake/uncore-interconnect.json | 22 +++- .../arch/x86/sapphirerapids/cache.json | 1 + .../arch/x86/sapphirerapids/frontend.json | 2 +- .../arch/x86/sapphirerapids/memory.json | 1 + .../arch/x86/sapphirerapids/pipeline.json | 19 +-- .../arch/x86/sapphirerapids/spr-metrics.json | 119 +++++++----------- .../arch/x86/sapphirerapids/uncore-cache.json | 112 ++++++++++++++++- .../sapphirerapids/uncore-interconnect.json | 26 ++-- .../arch/x86/sierraforest/pipeline.json | 36 +++++- .../pmu-events/arch/x86/skylake/frontend.json | 10 +- .../pmu-events/arch/x86/skylakex/cache.json | 9 ++ .../arch/x86/skylakex/frontend.json | 10 +- .../pmu-events/arch/x86/skylakex/memory.json | 2 +- .../pmu-events/arch/x86/skylakex/other.json | 2 +- .../arch/x86/skylakex/pipeline.json | 2 +- .../arch/x86/skylakex/skx-metrics.json | 85 +++++-------- .../x86/skylakex/uncore-interconnect.json | 14 +-- .../arch/x86/skylakex/uncore-io.json | 2 +- .../arch/x86/skylakex/virtual-memory.json | 2 +- .../arch/x86/snowridgex/uncore-cache.json | 4 +- .../x86/snowridgex/uncore-interconnect.json | 6 +- .../arch/x86/snowridgex/uncore-io.json | 11 -- 55 files changed, 911 insertions(+), 486 deletions(-)Signature · 1 line
2.44.0.396.g6e790dbe36-goog
Arnaldo Carvalho de Melo
maintainerQuoted 12 lines · Kan
Quoted 9 lines · Arnaldo Carvalho de Melo
Quoted 5 lines · Ian Rogers
Update events to the latest on:
https://github.com/intel/perfmonUsing the converter script:
https://github.com/intel/perfmon/blob/main/scripts/create_perf_json.pyKan,
Quoted 7 lines
Quoted 2 lines
Can you please take a look and provide an Acked or Reviewed-by?
Sure. The patch series look good to me. Thanks Ian!
Reviewed-by Kan Liang <[email protected]>
Thanks!
- Arnaldo