Update Intel perf vendor events
Subsystems (2)
Ian Rogers
reviewerPATCH v2 16/37 perf vendor events: Add/update icelake events/metrics
In reply to Ian RogersUpdate events from v1.21 to v1.22.
Add TMA metrics v4.8.
Bring in the event updates v1.22:
https://github.com/intel/perfmon/commit/e5640646e96d59e3c1c1e0d0100a475220ff1dfe
The TMA 4.8 information was added in:
https://github.com/intel/perfmon/commit/59194d4d90ca50a3fcb2de0d82b9f6fc0c9a5736
Adds the event SW_PREFETCH_ACCESS.ANY.
--- .../pmu-events/arch/x86/icelake/cache.json | 109 +++++++ .../pmu-events/arch/x86/icelake/counter.json | 17 + .../arch/x86/icelake/floating-point.json | 13 + .../pmu-events/arch/x86/icelake/frontend.json | 41 ++- .../arch/x86/icelake/icl-metrics.json | 308 +++++++++++++----- .../pmu-events/arch/x86/icelake/memory.json | 44 +++ .../arch/x86/icelake/metricgroups.json | 13 + .../pmu-events/arch/x86/icelake/other.json | 27 ++ .../pmu-events/arch/x86/icelake/pipeline.json | 94 ++++++ .../arch/x86/icelake/uncore-interconnect.json | 34 +- .../arch/x86/icelake/uncore-other.json | 1 + .../arch/x86/icelake/virtual-memory.json | 20 ++ tools/perf/pmu-events/arch/x86/mapfile.csv | 2 +- 13 files changed, 635 insertions(+), 88 deletions(-) create mode 100644 tools/perf/pmu-events/arch/x86/icelake/counter.json
tools/perf/pmu-events/arch/x86/icelake/cache.json +109 -0
@@ -1,6 +1,7 @@ [ { "BriefDescription": "Counts the number of cache lines replaced in L1 data cache.", + "Counter": "0,1,2,3", "EventCode": "0x51", "EventName": "L1D.REPLACEMENT", "PublicDescription": "Counts L1D data line replacements including opportunistic replacements, and replacements that require stall-for-replace or block-for-replace.",
@@ -9,6 +10,7 @@ }, { "BriefDescription": "Number of cycles a demand request has waited due to L1D Fill Buffer (FB) unavailability.", + "Counter": "0,1,2,3", "EventCode": "0x48", "EventName": "L1D_PEND_MISS.FB_FULL", "PublicDescription": "Counts number of cycles a demand request has waited due to L1D Fill Buffer (FB) unavailability. Demand requests include cacheable/uncacheable demand load, store, lock or SW prefetch accesses.",
@@ -17,6 +19,7 @@ }, { "BriefDescription": "Number of phases a demand request has waited due to L1D Fill Buffer (FB) unavailability.", + "Counter": "0,1,2,3", "CounterMask": "1", "EdgeDetect": "1", "EventCode": "0x48",
@@ -27,6 +30,7 @@ }, { "BriefDescription": "Number of cycles a demand request has waited due to L1D due to lack of L2 resources.", + "Counter": "0,1,2,3", "EventCode": "0x48", "EventName": "L1D_PEND_MISS.L2_STALL", "PublicDescription": "Counts number of cycles a demand request has waited due to L1D due to lack of L2 resources. Demand requests include cacheable/uncacheable demand load, store, lock or SW prefetch accesses.",
@@ -35,6 +39,7 @@ }, { "BriefDescription": "Number of L1D misses that are outstanding", + "Counter": "0,1,2,3", "EventCode": "0x48", "EventName": "L1D_PEND_MISS.PENDING", "PublicDescription": "Counts number of L1D misses that are outstanding in each cycle, that is each cycle the number of Fill Buffers (FB) outstanding required by Demand Reads. FB either is held by demand loads, or it is held by non-demand loads and gets hit at least once by demand. The valid outstanding interval is defined until the FB deallocation by one of the following ways: from FB allocation, if FB is allocated by demand from the demand Hit FB, if it is allocated by hardware or software prefetch. Note: In the L1D, a Demand Read contains cacheable or noncacheable demand loads, including ones causing cache-line splits and reads due to page walks resulted from any request type.",
@@ -43,6 +48,7 @@ }, { "BriefDescription": "Cycles with L1D load Misses outstanding.", + "Counter": "0,1,2,3", "CounterMask": "1", "EventCode": "0x48", "EventName": "L1D_PEND_MISS.PENDING_CYCLES",
@@ -52,6 +58,7 @@ }, { "BriefDescription": "L2 cache lines filling L2", + "Counter": "0,1,2,3", "EventCode": "0xF1", "EventName": "L2_LINES_IN.ALL", "PublicDescription": "Counts the number of L2 cache lines filling the L2. Counting does not cover rejects.",
@@ -60,6 +67,7 @@ }, { "BriefDescription": "Modified cache lines that are evicted by L2 cache when triggered by an L2 cache fill.", + "Counter": "0,1,2,3", "EventCode": "0xF2", "EventName": "L2_LINES_OUT.NON_SILENT", "PublicDescription": "Counts the number of lines that are evicted by L2 cache when triggered by an L2 cache fill. Those lines are in Modified state. Modified lines are written back to L3",
@@ -68,6 +76,7 @@ }, { "BriefDescription": "Non-modified cache lines that are silently dropped by L2 cache when triggered by an L2 cache fill.", + "Counter": "0,1,2,3", "EventCode": "0xF2", "EventName": "L2_LINES_OUT.SILENT", "PublicDescription": "Counts the number of lines that are silently dropped by L2 cache when triggered by an L2 cache fill. These lines are typically in Shared or Exclusive state. A non-threaded event.",
@@ -76,6 +85,7 @@ }, { "BriefDescription": "Cache lines that have been L2 hardware prefetched but not used by demand accesses", + "Counter": "0,1,2,3", "EventCode": "0xf2", "EventName": "L2_LINES_OUT.USELESS_HWPF", "PublicDescription": "Counts the number of cache lines that have been prefetched by the L2 hardware prefetcher but not used by demand access when evicted from the L2 cache",
@@ -84,6 +94,7 @@ }, { "BriefDescription": "L2 code requests", + "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_RQSTS.ALL_CODE_RD", "PublicDescription": "Counts the total number of L2 code requests.",
@@ -92,6 +103,7 @@ }, { "BriefDescription": "Demand Data Read requests", + "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_RQSTS.ALL_DEMAND_DATA_RD", "PublicDescription": "Counts the number of demand Data Read requests (including requests from L1D hardware prefetchers). These loads may hit or miss L2 cache. Only non rejected loads are counted.",
@@ -100,6 +112,7 @@ }, { "BriefDescription": "Demand requests that miss L2 cache", + "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_RQSTS.ALL_DEMAND_MISS", "PublicDescription": "Counts demand requests that miss L2 cache.",
@@ -108,6 +121,7 @@ }, { "BriefDescription": "Demand requests to L2 cache", + "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_RQSTS.ALL_DEMAND_REFERENCES", "PublicDescription": "Counts demand requests to L2 cache.",
@@ -116,6 +130,7 @@ }, { "BriefDescription": "RFO requests to L2 cache", + "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_RQSTS.ALL_RFO", "PublicDescription": "Counts the total number of RFO (read for ownership) requests to L2 cache. L2 RFO requests include both L1D demand RFO misses as well as L1D RFO prefetches.",
@@ -124,6 +139,7 @@ }, { "BriefDescription": "L2 cache hits when fetching instructions, code reads.", + "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_RQSTS.CODE_RD_HIT", "PublicDescription": "Counts L2 cache hits when fetching instructions, code reads.",
@@ -132,6 +148,7 @@ }, { "BriefDescription": "L2 cache misses when fetching instructions", + "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_RQSTS.CODE_RD_MISS", "PublicDescription": "Counts L2 cache misses when fetching instructions.",
@@ -140,6 +157,7 @@ }, { "BriefDescription": "Demand Data Read requests that hit L2 cache", + "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_RQSTS.DEMAND_DATA_RD_HIT", "PublicDescription": "Counts the number of demand Data Read requests initiated by load instructions that hit L2 cache.",
@@ -148,6 +166,7 @@ }, { "BriefDescription": "Demand Data Read miss L2, no rejects", + "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_RQSTS.DEMAND_DATA_RD_MISS", "PublicDescription": "Counts the number of demand Data Read requests that miss L2 cache. Only not rejected loads are counted.",
@@ -156,6 +175,7 @@ }, { "BriefDescription": "This event is deprecated.", + "Counter": "0,1,2,3", "Deprecated": "1", "EventCode": "0x24", "EventName": "L2_RQSTS.MISS",
@@ -164,6 +184,7 @@ }, { "BriefDescription": "This event is deprecated.", + "Counter": "0,1,2,3", "Deprecated": "1", "EventCode": "0x24", "EventName": "L2_RQSTS.REFERENCES",
@@ -172,6 +193,7 @@ }, { "BriefDescription": "RFO requests that hit L2 cache", + "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_RQSTS.RFO_HIT", "PublicDescription": "Counts the RFO (Read-for-Ownership) requests that hit L2 cache.",
@@ -180,6 +202,7 @@ }, { "BriefDescription": "RFO requests that miss L2 cache", + "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_RQSTS.RFO_MISS", "PublicDescription": "Counts the RFO (Read-for-Ownership) requests that miss L2 cache.",
@@ -188,6 +211,7 @@ }, { "BriefDescription": "SW prefetch requests that hit L2 cache.", + "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_RQSTS.SWPF_HIT", "PublicDescription": "Counts Software prefetch requests that hit the L2 cache. Accounts for PREFETCHNTA and PREFETCHT0/1/2 instructions when FB is not full.",
@@ -196,6 +220,7 @@ }, { "BriefDescription": "SW prefetch requests that miss L2 cache.", + "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_RQSTS.SWPF_MISS", "PublicDescription": "Counts Software prefetch requests that miss the L2 cache. Accounts for PREFETCHNTA and PREFETCHT0/1/2 instructions when FB is not full.",
@@ -204,6 +229,7 @@ }, { "BriefDescription": "L2 writebacks that access L2 cache", + "Counter": "0,1,2,3", "EventCode": "0xF0", "EventName": "L2_TRANS.L2_WB", "PublicDescription": "Counts L2 writebacks that access L2 cache.",
@@ -212,6 +238,7 @@ }, { "BriefDescription": "Core-originated cacheable requests that missed L3 (Except hardware prefetches to the L3)", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0x2e", "EventName": "LONGEST_LAT_CACHE.MISS", "PublicDescription": "Counts core-originated cacheable requests that miss the L3 cache (Longest Latency cache). Requests include data and code reads, Reads-for-Ownership (RFOs), speculative accesses and hardware prefetches to the L1 and L2. It does not include hardware prefetches to the L3, and may not count other types of requests to the L3.",
@@ -220,6 +247,7 @@ }, { "BriefDescription": "Retired load instructions.", + "Counter": "0,1,2,3", "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_INST_RETIRED.ALL_LOADS",
@@ -230,6 +258,7 @@ }, { "BriefDescription": "Retired store instructions.", + "Counter": "0,1,2,3", "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_INST_RETIRED.ALL_STORES",
@@ -240,6 +269,7 @@ }, { "BriefDescription": "All retired memory instructions.", + "Counter": "0,1,2,3", "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_INST_RETIRED.ANY",
@@ -250,6 +280,7 @@ }, { "BriefDescription": "Retired load instructions with locked access.", + "Counter": "0,1,2,3", "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_INST_RETIRED.LOCK_LOADS",
@@ -260,6 +291,7 @@ }, { "BriefDescription": "Retired load instructions that split across a cacheline boundary.", + "Counter": "0,1,2,3", "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_INST_RETIRED.SPLIT_LOADS",
@@ -270,6 +302,7 @@ }, { "BriefDescription": "Retired store instructions that split across a cacheline boundary.", + "Counter": "0,1,2,3", "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_INST_RETIRED.SPLIT_STORES",
@@ -280,6 +313,7 @@ }, { "BriefDescription": "Retired load instructions that miss the STLB.", + "Counter": "0,1,2,3", "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_INST_RETIRED.STLB_MISS_LOADS",
@@ -290,6 +324,7 @@ }, { "BriefDescription": "Retired store instructions that miss the STLB.", + "Counter": "0,1,2,3", "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_INST_RETIRED.STLB_MISS_STORES",
@@ -300,6 +335,7 @@ }, { "BriefDescription": "Retired load instructions whose data sources were L3 and cross-core snoop hits in on-pkg core cache", + "Counter": "0,1,2,3", "Data_LA": "1", "EventCode": "0xd2", "EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_HIT",
@@ -310,6 +346,7 @@ }, { "BriefDescription": "Retired load instructions whose data sources were HitM responses from shared L3", + "Counter": "0,1,2,3", "Data_LA": "1", "EventCode": "0xd2", "EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM",
@@ -320,6 +357,7 @@ }, { "BriefDescription": "Retired load instructions whose data sources were L3 hit and cross-core snoop missed in on-pkg core cache.", + "Counter": "0,1,2,3", "Data_LA": "1", "EventCode": "0xd2", "EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS",
@@ -330,6 +368,7 @@ }, { "BriefDescription": "Retired load instructions whose data sources were hits in L3 without snoops required", + "Counter": "0,1,2,3", "Data_LA": "1", "EventCode": "0xd2", "EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_NONE",
@@ -340,6 +379,7 @@ }, { "BriefDescription": "Retired instructions with at least 1 uncacheable load or Bus Lock.", + "Counter": "0,1,2,3", "Data_LA": "1", "EventCode": "0xd4", "EventName": "MEM_LOAD_MISC_RETIRED.UC",
@@ -350,6 +390,7 @@ }, { "BriefDescription": "Number of completed demand load requests that missed the L1, but hit the FB(fill buffer), because a preceding miss to the same cacheline initiated the line to be brought into L1, but data is not yet ready in L1.", + "Counter": "0,1,2,3", "Data_LA": "1", "EventCode": "0xd1", "EventName": "MEM_LOAD_RETIRED.FB_HIT",
@@ -360,6 +401,7 @@ }, { "BriefDescription": "Retired load instructions with L1 cache hits as data sources", + "Counter": "0,1,2,3", "Data_LA": "1", "EventCode": "0xd1", "EventName": "MEM_LOAD_RETIRED.L1_HIT",
@@ -370,6 +412,7 @@ }, { "BriefDescription": "Retired load instructions missed L1 cache as data sources", + "Counter": "0,1,2,3", "Data_LA": "1", "EventCode": "0xd1", "EventName": "MEM_LOAD_RETIRED.L1_MISS",
@@ -380,6 +423,7 @@ }, { "BriefDescription": "Retired load instructions with L2 cache hits as data sources", + "Counter": "0,1,2,3", "Data_LA": "1", "EventCode": "0xd1", "EventName": "MEM_LOAD_RETIRED.L2_HIT",
@@ -390,6 +434,7 @@ }, { "BriefDescription": "Retired load instructions missed L2 cache as data sources", + "Counter": "0,1,2,3", "Data_LA": "1", "EventCode": "0xd1", "EventName": "MEM_LOAD_RETIRED.L2_MISS",
@@ -400,6 +445,7 @@ }, { "BriefDescription": "Retired load instructions with L3 cache hits as data sources", + "Counter": "0,1,2,3", "Data_LA": "1", "EventCode": "0xd1", "EventName": "MEM_LOAD_RETIRED.L3_HIT",
@@ -410,6 +456,7 @@ }, { "BriefDescription": "Retired load instructions missed L3 cache as data sources", + "Counter": "0,1,2,3", "Data_LA": "1", "EventCode": "0xd1", "EventName": "MEM_LOAD_RETIRED.L3_MISS",
@@ -420,6 +467,7 @@ }, { "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that hit a cacheline in the L3 where a snoop was sent or not.", + "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", "EventName": "OCR.DEMAND_CODE_RD.L3_HIT.ANY", "MSRIndex": "0x1a6,0x1a7",
@@ -429,6 +477,7 @@ }, { "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that hit a cacheline in the L3 where a snoop hit in another cores caches, data forwarding is required as the data is modified.", + "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", "EventName": "OCR.DEMAND_CODE_RD.L3_HIT.SNOOP_HITM", "MSRIndex": "0x1a6,0x1a7",
@@ -438,6 +487,7 @@ }, { "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that hit a cacheline in the L3 where a snoop hit in another core, data forwarding is not required.", + "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", "EventName": "OCR.DEMAND_CODE_RD.L3_HIT.SNOOP_HIT_NO_FWD", "MSRIndex": "0x1a6,0x1a7",
@@ -447,6 +497,7 @@ }, { "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that hit a cacheline in the L3 where a snoop was sent but no other cores had the data.", + "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", "EventName": "OCR.DEMAND_CODE_RD.L3_HIT.SNOOP_MISS", "MSRIndex": "0x1a6,0x1a7",
@@ -456,6 +507,7 @@ }, { "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that hit a cacheline in the L3 where a snoop was not needed to satisfy the request.", + "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", "EventName": "OCR.DEMAND_CODE_RD.L3_HIT.SNOOP_NOT_NEEDED", "MSRIndex": "0x1a6,0x1a7",
@@ -465,6 +517,7 @@ }, { "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that hit a cacheline in the L3 where a snoop was sent.", + "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", "EventName": "OCR.DEMAND_CODE_RD.L3_HIT.SNOOP_SENT", "MSRIndex": "0x1a6,0x1a7",
@@ -474,6 +527,7 @@ }, { "BriefDescription": "Counts demand data reads that hit a cacheline in the L3 where a snoop was sent or not.", + "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", "EventName": "OCR.DEMAND_DATA_RD.L3_HIT.ANY", "MSRIndex": "0x1a6,0x1a7",
@@ -483,6 +537,7 @@ }, { "BriefDescription": "Counts demand data reads that hit a cacheline in the L3 where a snoop hit in another cores caches, data forwarding is required as the data is modified.", + "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", "EventName": "OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM", "MSRIndex": "0x1a6,0x1a7",
@@ -492,6 +547,7 @@ }, { "BriefDescription": "Counts demand data reads that hit a cacheline in the L3 where a snoop hit in another core, data forwarding is not required.", + "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", "EventName": "OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_NO_FWD", "MSRIndex": "0x1a6,0x1a7",
@@ -501,6 +557,7 @@ }, { "BriefDescription": "Counts demand data reads that hit a cacheline in the L3 where a snoop was sent but no other cores had the data.", + "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", "EventName": "OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_MISS", "MSRIndex": "0x1a6,0x1a7",
@@ -510,6 +567,7 @@ }, { "BriefDescription": "Counts demand data reads that hit a cacheline in the L3 where a snoop was not needed to satisfy the request.", + "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", "EventName": "OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_NOT_NEEDED", "MSRIndex": "0x1a6,0x1a7",
@@ -519,6 +577,7 @@ }, { "BriefDescription": "Counts demand data reads that hit a cacheline in the L3 where a snoop was sent.", + "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", "EventName": "OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_SENT", "MSRIndex": "0x1a6,0x1a7",
@@ -528,6 +587,7 @@ }, { "BriefDescription": "Counts demand reads for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that hit a cacheline in the L3 where a snoop was sent or not.", + "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", "EventName": "OCR.DEMAND_RFO.L3_HIT.ANY", "MSRIndex": "0x1a6,0x1a7",
@@ -537,6 +597,7 @@ }, { "BriefDescription": "Counts demand reads for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that hit a cacheline in the L3 where a snoop hit in another cores caches, data forwarding is required as the data is modified.", + "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", "EventName": "OCR.DEMAND_RFO.L3_HIT.SNOOP_HITM", "MSRIndex": "0x1a6,0x1a7",
@@ -546,6 +607,7 @@ }, { "BriefDescription": "Counts demand reads for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that hit a cacheline in the L3 where a snoop hit in another core, data forwarding is not required.", + "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", "EventName": "OCR.DEMAND_RFO.L3_HIT.SNOOP_HIT_NO_FWD", "MSRIndex": "0x1a6,0x1a7",
@@ -555,6 +617,7 @@ }, { "BriefDescription": "Counts demand reads for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that hit a cacheline in the L3 where a snoop was sent but no other cores had the data.", + "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", "EventName": "OCR.DEMAND_RFO.L3_HIT.SNOOP_MISS", "MSRIndex": "0x1a6,0x1a7",
@@ -564,6 +627,7 @@ }, { "BriefDescription": "Counts demand reads for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that hit a cacheline in the L3 where a snoop was not needed to satisfy the request.", + "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", "EventName": "OCR.DEMAND_RFO.L3_HIT.SNOOP_NOT_NEEDED", "MSRIndex": "0x1a6,0x1a7",
@@ -573,6 +637,7 @@ }, { "BriefDescription": "Counts demand reads for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that hit a cacheline in the L3 where a snoop was sent.", + "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", "EventName": "OCR.DEMAND_RFO.L3_HIT.SNOOP_SENT", "MSRIndex": "0x1a6,0x1a7",
@@ -582,6 +647,7 @@ }, { "BriefDescription": "Counts L1 data cache prefetch requests and software prefetches (except PREFETCHW) that hit a cacheline in the L3 where a snoop was sent or not.", + "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", "EventName": "OCR.HWPF_L1D_AND_SWPF.L3_HIT.ANY", "MSRIndex": "0x1a6,0x1a7",
@@ -591,6 +657,7 @@ }, { "BriefDescription": "Counts L1 data cache prefetch requests and software prefetches (except PREFETCHW) that hit a cacheline in the L3 where a snoop was sent but no other cores had the data.", + "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", "EventName": "OCR.HWPF_L1D_AND_SWPF.L3_HIT.SNOOP_MISS", "MSRIndex": "0x1a6,0x1a7",
@@ -600,6 +667,7 @@ }, { "BriefDescription": "Counts L1 data cache prefetch requests and software prefetches (except PREFETCHW) that hit a cacheline in the L3 where a snoop was not needed to satisfy the request.", + "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", "EventName": "OCR.HWPF_L1D_AND_SWPF.L3_HIT.SNOOP_NOT_NEEDED", "MSRIndex": "0x1a6,0x1a7",
@@ -609,6 +677,7 @@ }, { "BriefDescription": "Counts hardware prefetch data reads (which bring data to L2) that hit a cacheline in the L3 where a snoop was sent or not.", + "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", "EventName": "OCR.HWPF_L2_DATA_RD.L3_HIT.ANY", "MSRIndex": "0x1a6,0x1a7",
@@ -618,6 +687,7 @@ }, { "BriefDescription": "Counts hardware prefetch data reads (which bring data to L2) that hit a cacheline in the L3 where a snoop hit in another cores caches, data forwarding is required as the data is modified.", + "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", "EventName": "OCR.HWPF_L2_DATA_RD.L3_HIT.SNOOP_HITM", "MSRIndex": "0x1a6,0x1a7",
@@ -627,6 +697,7 @@ }, { "BriefDescription": "Counts hardware prefetch data reads (which bring data to L2) that hit a cacheline in the L3 where a snoop hit in another core, data forwarding is not required.", + "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", "EventName": "OCR.HWPF_L2_DATA_RD.L3_HIT.SNOOP_HIT_NO_FWD", "MSRIndex": "0x1a6,0x1a7",
@@ -636,6 +707,7 @@ }, { "BriefDescription": "Counts hardware prefetch data reads (which bring data to L2) that hit a cacheline in the L3 where a snoop was sent but no other cores had the data.", + "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", "EventName": "OCR.HWPF_L2_DATA_RD.L3_HIT.SNOOP_MISS", "MSRIndex": "0x1a6,0x1a7",
@@ -645,6 +717,7 @@ }, { "BriefDescription": "Counts hardware prefetch data reads (which bring data to L2) that hit a cacheline in the L3 where a snoop was not needed to satisfy the request.", + "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", "EventName": "OCR.HWPF_L2_DATA_RD.L3_HIT.SNOOP_NOT_NEEDED", "MSRIndex": "0x1a6,0x1a7",
@@ -654,6 +727,7 @@ }, { "BriefDescription": "Counts hardware prefetch data reads (which bring data to L2) that hit a cacheline in the L3 where a snoop was sent.", + "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", "EventName": "OCR.HWPF_L2_DATA_RD.L3_HIT.SNOOP_SENT", "MSRIndex": "0x1a6,0x1a7",
@@ -663,6 +737,7 @@ }, { "BriefDescription": "Counts hardware prefetch RFOs (which bring data to L2) that hit a cacheline in the L3 where a snoop was sent or not.", + "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", "EventName": "OCR.HWPF_L2_RFO.L3_HIT.ANY", "MSRIndex": "0x1a6,0x1a7",
@@ -672,6 +747,7 @@ }, { "BriefDescription": "Counts hardware prefetch RFOs (which bring data to L2) that hit a cacheline in the L3 where a snoop hit in another cores caches, data forwarding is required as the data is modified.", + "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", "EventName": "OCR.HWPF_L2_RFO.L3_HIT.SNOOP_HITM", "MSRIndex": "0x1a6,0x1a7",
@@ -681,6 +757,7 @@ }, { "BriefDescription": "Counts hardware prefetch RFOs (which bring data to L2) that hit a cacheline in the L3 where a snoop hit in another core, data forwarding is not required.", + "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", "EventName": "OCR.HWPF_L2_RFO.L3_HIT.SNOOP_HIT_NO_FWD", "MSRIndex": "0x1a6,0x1a7",
@@ -690,6 +767,7 @@ }, { "BriefDescription": "Counts hardware prefetch RFOs (which bring data to L2) that hit a cacheline in the L3 where a snoop was sent but no other cores had the data.", + "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", "EventName": "OCR.HWPF_L2_RFO.L3_HIT.SNOOP_MISS", "MSRIndex": "0x1a6,0x1a7",
@@ -699,6 +777,7 @@ }, { "BriefDescription": "Counts hardware prefetch RFOs (which bring data to L2) that hit a cacheline in the L3 where a snoop was not needed to satisfy the request.", + "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", "EventName": "OCR.HWPF_L2_RFO.L3_HIT.SNOOP_NOT_NEEDED", "MSRIndex": "0x1a6,0x1a7",
@@ -708,6 +787,7 @@ }, { "BriefDescription": "Counts hardware prefetch RFOs (which bring data to L2) that hit a cacheline in the L3 where a snoop was sent.", + "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", "EventName": "OCR.HWPF_L2_RFO.L3_HIT.SNOOP_SENT", "MSRIndex": "0x1a6,0x1a7",
@@ -717,6 +797,7 @@ }, { "BriefDescription": "Counts hardware prefetches to the L3 only that hit a cacheline in the L3 where a snoop was sent or not.", + "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", "EventName": "OCR.HWPF_L3.L3_HIT.ANY", "MSRIndex": "0x1a6,0x1a7",
@@ -726,6 +807,7 @@ }, { "BriefDescription": "Counts miscellaneous requests, such as I/O and un-cacheable accesses that hit a cacheline in the L3 where a snoop hit in another core, data forwarding is not required.", + "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", "EventName": "OCR.OTHER.L3_HIT.SNOOP_HIT_NO_FWD", "MSRIndex": "0x1a6,0x1a7",
@@ -735,6 +817,7 @@ }, { "BriefDescription": "Counts miscellaneous requests, such as I/O and un-cacheable accesses that hit a cacheline in the L3 where a snoop was sent but no other cores had the data.", + "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", "EventName": "OCR.OTHER.L3_HIT.SNOOP_MISS", "MSRIndex": "0x1a6,0x1a7",
@@ -744,6 +827,7 @@ }, { "BriefDescription": "Counts miscellaneous requests, such as I/O and un-cacheable accesses that hit a cacheline in the L3 where a snoop was not needed to satisfy the request.", + "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", "EventName": "OCR.OTHER.L3_HIT.SNOOP_NOT_NEEDED", "MSRIndex": "0x1a6,0x1a7",
@@ -753,6 +837,7 @@ }, { "BriefDescription": "Counts miscellaneous requests, such as I/O and un-cacheable accesses that hit a cacheline in the L3 where a snoop was sent.", + "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", "EventName": "OCR.OTHER.L3_HIT.SNOOP_SENT", "MSRIndex": "0x1a6,0x1a7",
@@ -762,6 +847,7 @@ }, { "BriefDescription": "Counts streaming stores that hit a cacheline in the L3 where a snoop was sent or not.", + "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", "EventName": "OCR.STREAMING_WR.L3_HIT.ANY", "MSRIndex": "0x1a6,0x1a7",
@@ -771,6 +857,7 @@ }, { "BriefDescription": "Demand and prefetch data reads", + "Counter": "0,1,2,3", "EventCode": "0xB0", "EventName": "OFFCORE_REQUESTS.ALL_DATA_RD", "PublicDescription": "Counts the demand and prefetch data reads. All Core Data Reads include cacheable 'Demands' and L2 prefetchers (not L3 prefetchers). Counting also covers reads due to page walks resulted from any request type.",
@@ -779,6 +866,7 @@ }, { "BriefDescription": "Counts memory transactions sent to the uncore.", + "Counter": "0,1,2,3", "EventCode": "0xB0", "EventName": "OFFCORE_REQUESTS.ALL_REQUESTS", "PublicDescription": "Counts memory transactions sent to the uncore including requests initiated by the core, all L3 prefetches, reads resulting from page walks, and snoop responses.",
@@ -787,6 +875,7 @@ }, { "BriefDescription": "Demand Data Read requests sent to uncore", + "Counter": "0,1,2,3", "EventCode": "0xb0", "EventName": "OFFCORE_REQUESTS.DEMAND_DATA_RD", "PublicDescription": "Counts the Demand Data Read requests sent to uncore. Use it in conjunction with OFFCORE_REQUESTS_OUTSTANDING to determine average latency in the uncore.",
@@ -795,6 +884,7 @@ }, { "BriefDescription": "Demand RFO requests including regular RFOs, locks, ItoM", + "Counter": "0,1,2,3", "EventCode": "0xb0", "EventName": "OFFCORE_REQUESTS.DEMAND_RFO", "PublicDescription": "Counts the demand RFO (read for ownership) requests including regular RFOs, locks, ItoM.",
@@ -803,6 +893,7 @@ }, { "BriefDescription": "For every cycle, increments by the number of outstanding data read requests pending.", + "Counter": "0,1,2,3", "EventCode": "0x60", "EventName": "OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD", "PublicDescription": "For every cycle, increments by the number of outstanding data read requests pending. Data read requests include cacheable demand reads and L2 prefetches, but do not include RFOs, code reads or prefetches to the L3. Reads due to page walks resulting from any request type will also be counted. Requests are considered outstanding from the time they miss the core's L2 cache until the transaction completion message is sent to the requestor.",
@@ -811,6 +902,7 @@ }, { "BriefDescription": "Cycles where at least 1 outstanding data read request is pending.", + "Counter": "0,1,2,3", "CounterMask": "1", "EventCode": "0x60", "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD",
@@ -820,6 +912,7 @@ }, { "BriefDescription": "Cycles where at least 1 outstanding Demand RFO request is pending.", + "Counter": "0,1,2,3", "CounterMask": "1", "EventCode": "0x60", "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO",
@@ -829,6 +922,7 @@ }, { "BriefDescription": "For every cycle, increments by the number of outstanding demand data read requests pending.", + "Counter": "0,1,2,3", "EventCode": "0x60", "EventName": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD", "PublicDescription": "For every cycle, increments by the number of outstanding demand data read requests pending. Requests are considered outstanding from the time they miss the core's L2 cache until the transaction completion message is sent to the requestor.",
@@ -837,6 +931,7 @@ }, { "BriefDescription": "Store Read transactions pending for off-core. Highly correlated.", + "Counter": "0,1,2,3", "EventCode": "0x60", "EventName": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_RFO", "PublicDescription": "Counts the number of off-core outstanding read-for-ownership (RFO) store transactions every cycle. An RFO transaction is considered to be in the Off-core outstanding state between L2 cache miss and transaction completion.",
@@ -845,6 +940,7 @@ }, { "BriefDescription": "Counts bus locks, accounts for cache line split locks and UC locks.", + "Counter": "0,1,2,3", "EventCode": "0xF4", "EventName": "SQ_MISC.BUS_LOCK", "PublicDescription": "Counts the more expensive bus lock needed to enforce cache coherency for certain memory accesses that need to be done atomically. Can be created by issuing an atomic instruction (via the LOCK prefix) which causes a cache line split or accesses uncacheable memory.",
@@ -853,14 +949,24 @@ }, { "BriefDescription": "Cycles the queue waiting for offcore responses is full.", + "Counter": "0,1,2,3", "EventCode": "0xf4", "EventName": "SQ_MISC.SQ_FULL", "PublicDescription": "Counts the cycles for which the thread is active and the queue waiting for responses from the uncore cannot take any more entries.", "SampleAfterValue": "100003", "UMask": "0x4" }, + { + "BriefDescription": "Counts the number of PREFETCHNTA, PREFETCHW, PREFETCHT0, PREFETCHT1 or PREFETCHT2 instructions executed.", + "Counter": "0,1,2,3", + "EventCode": "0x32", + "EventName": "SW_PREFETCH_ACCESS.ANY", + "SampleAfterValue": "100003", + "UMask": "0xf" + }, { "BriefDescription": "Number of PREFETCHNTA instructions executed.", + "Counter": "0,1,2,3", "EventCode": "0x32", "EventName": "SW_PREFETCH_ACCESS.NTA", "PublicDescription": "Counts the number of PREFETCHNTA instructions executed.",
@@ -869,6 +975,7 @@ }, { "BriefDescription": "Number of PREFETCHW instructions executed.", + "Counter": "0,1,2,3", "EventCode": "0x32", "EventName": "SW_PREFETCH_ACCESS.PREFETCHW", "PublicDescription": "Counts the number of PREFETCHW instructions executed.",
@@ -877,6 +984,7 @@ }, { "BriefDescription": "Number of PREFETCHT0 instructions executed.", + "Counter": "0,1,2,3", "EventCode": "0x32", "EventName": "SW_PREFETCH_ACCESS.T0", "PublicDescription": "Counts the number of PREFETCHT0 instructions executed.",
@@ -885,6 +993,7 @@ }, { "BriefDescription": "Number of PREFETCHT1 or PREFETCHT2 instructions executed.", + "Counter": "0,1,2,3", "EventCode": "0x32", "EventName": "SW_PREFETCH_ACCESS.T1_T2", "PublicDescription": "Counts the number of PREFETCHT1 or PREFETCHT2 instructions executed.",
tools/perf/pmu-events/arch/x86/icelake/counter.json new file +17 -0
@@ -0,0 +1,17 @@ +[ + { + "Unit": "core", + "CountersNumFixed": "4", + "CountersNumGeneric": "8" + }, + { + "Unit": "ARB", + "CountersNumFixed": "0", + "CountersNumGeneric": "2" + }, + { + "Unit": "CLOCK", + "CountersNumFixed": 1, + "CountersNumGeneric": "0" + } +]
tools/perf/pmu-events/arch/x86/icelake/floating-point.json +13 -0
@@ -1,6 +1,7 @@ [ { "BriefDescription": "Counts all microcode FP assists.", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc1", "EventName": "ASSISTS.FP", "PublicDescription": "Counts all microcode Floating Point assists.",
@@ -9,6 +10,7 @@ }, { "BriefDescription": "Counts number of SSE/AVX computational 128-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 2 computation operations, one for each element. Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element.", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc7", "EventName": "FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE", "PublicDescription": "Number of SSE/AVX computational 128-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 2 computation operations, one for each element. Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.",
@@ -17,6 +19,7 @@ }, { "BriefDescription": "Number of SSE/AVX computational 128-bit packed single precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 4 computation operations, one for each element. Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB MUL DIV MIN MAX RCP14 RSQRT14 SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element.", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc7", "EventName": "FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE", "PublicDescription": "Number of SSE/AVX computational 128-bit packed single precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 4 computation operations, one for each element. Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT RSQRT RCP DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.",
@@ -25,6 +28,7 @@ }, { "BriefDescription": "Counts number of SSE/AVX computational 256-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 4 computation operations, one for each element. Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element.", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc7", "EventName": "FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE", "PublicDescription": "Number of SSE/AVX computational 256-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 4 computation operations, one for each element. Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.",
@@ -33,6 +37,7 @@ }, { "BriefDescription": "Counts number of SSE/AVX computational 256-bit packed single precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 8 computation operations, one for each element. Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT RSQRT RCP DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element.", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc7", "EventName": "FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE", "PublicDescription": "Number of SSE/AVX computational 256-bit packed single precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 8 computation operations, one for each element. Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT RSQRT RCP DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.",
@@ -41,6 +46,7 @@ }, { "BriefDescription": "Number of SSE/AVX computational 128-bit packed single and 256-bit packed double precision FP instructions retired; some instructions will count twice as noted below. Each count represents 2 or/and 4 computation operations, 1 for each element. Applies to SSE* and AVX* packed single precision and packed double precision FP instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX RCP14 RSQRT14 SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB count twice as they perform 2 calculations per element.", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc7", "EventName": "FP_ARITH_INST_RETIRED.4_FLOPS", "PublicDescription": "Number of SSE/AVX computational 128-bit packed single precision and 256-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 2 or/and 4 computation operations, one for each element. Applies to SSE* and AVX* packed single precision floating-point and packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX RCP14 RSQRT14 SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.",
@@ -49,6 +55,7 @@ }, { "BriefDescription": "Counts number of SSE/AVX computational 512-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 8 computation operations, one for each element. Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT RSQRT14 RCP14 FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element.", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc7", "EventName": "FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE", "PublicDescription": "Number of SSE/AVX computational 512-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 8 computation operations, one for each element. Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT RSQRT14 RCP14 FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.",
@@ -57,6 +64,7 @@ }, { "BriefDescription": "Counts number of SSE/AVX computational 512-bit packed single precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 16 computation operations, one for each element. Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT RSQRT14 RCP14 FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element.", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc7", "EventName": "FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE", "PublicDescription": "Number of SSE/AVX computational 512-bit packed single precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 16 computation operations, one for each element. Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT RSQRT14 RCP14 FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.",
@@ -65,6 +73,7 @@ }, { "BriefDescription": "Number of SSE/AVX computational 256-bit packed single precision and 512-bit packed double precision FP instructions retired; some instructions will count twice as noted below. Each count represents 8 computation operations, 1 for each element. Applies to SSE* and AVX* packed single precision and double precision FP instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT RSQRT RSQRT14 RCP RCP14 DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB count twice as they perform 2 calculations per element.", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc7", "EventName": "FP_ARITH_INST_RETIRED.8_FLOPS", "PublicDescription": "Number of SSE/AVX computational 256-bit packed single precision and 512-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 8 computation operations, one for each element. Applies to SSE* and AVX* packed single precision and double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT RSQRT RSQRT14 RCP RCP14 DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.",
@@ -73,6 +82,7 @@ }, { "BriefDescription": "Number of SSE/AVX computational scalar floating-point instructions retired; some instructions will count twice as noted below. Applies to SSE* and AVX* scalar, double and single precision floating-point: ADD SUB MUL DIV MIN MAX RCP14 RSQRT14 SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc7", "EventName": "FP_ARITH_INST_RETIRED.SCALAR", "PublicDescription": "Number of SSE/AVX computational scalar single precision and double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 1 computational operation. Applies to SSE* and AVX* scalar single precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT RSQRT RCP FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.",
@@ -81,6 +91,7 @@ }, { "BriefDescription": "Counts number of SSE/AVX computational scalar double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 1 computational operation. Applies to SSE* and AVX* scalar double precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element.", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc7", "EventName": "FP_ARITH_INST_RETIRED.SCALAR_DOUBLE", "PublicDescription": "Number of SSE/AVX computational scalar double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 1 computational operation. Applies to SSE* and AVX* scalar double precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.",
@@ -89,6 +100,7 @@ }, { "BriefDescription": "Counts number of SSE/AVX computational scalar single precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 1 computational operation. Applies to SSE* and AVX* scalar single precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT RSQRT RCP FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element.", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc7", "EventName": "FP_ARITH_INST_RETIRED.SCALAR_SINGLE", "PublicDescription": "Number of SSE/AVX computational scalar single precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 1 computational operation. Applies to SSE* and AVX* scalar single precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT RSQRT RCP FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.",
@@ -97,6 +109,7 @@ }, { "BriefDescription": "Number of any Vector retired FP arithmetic instructions", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc7", "EventName": "FP_ARITH_INST_RETIRED.VECTOR", "SampleAfterValue": "1000003",
tools/perf/pmu-events/arch/x86/icelake/frontend.json +40 -1
277 lines not on this page · raw message
tools/perf/pmu-events/arch/x86/icelake/icl-metrics.json +228 -80
739 lines not on this page · raw message
tools/perf/pmu-events/arch/x86/icelake/memory.json +44 -0
308 lines not on this page · raw message
tools/perf/pmu-events/arch/x86/icelake/metricgroups.json +13 -0
@@ -5,7 +5,20 @@ "BigFootprint": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", "BrMispredicts": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", "Branches": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "BvBC": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "BvBO": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "BvCB": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "BvFB": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "BvIO": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "BvMB": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "BvML": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "BvMP": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "BvMS": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "BvMT": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "BvOB": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "BvUW": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", "CacheHits": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "CacheMisses": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", "CodeGen": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", "Compute": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", "Cor": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
tools/perf/pmu-events/arch/x86/icelake/other.json +27 -0
@@ -1,6 +1,7 @@ [ { "BriefDescription": "Core cycles where the core was running in a manner where Turbo may be clipped to the Non-AVX turbo schedule.", + "Counter": "0,1,2,3", "EventCode": "0x28", "EventName": "CORE_POWER.LVL0_TURBO_LICENSE", "PublicDescription": "Counts Core cycles where the core was running with power-delivery for baseline license level 0. This includes non-AVX codes, SSE, AVX 128-bit, and low-current AVX 256-bit codes.",
@@ -9,6 +10,7 @@ }, { "BriefDescription": "Core cycles where the core was running in a manner where Turbo may be clipped to the AVX2 turbo schedule.", + "Counter": "0,1,2,3", "EventCode": "0x28", "EventName": "CORE_POWER.LVL1_TURBO_LICENSE", "PublicDescription": "Counts Core cycles where the core was running with power-delivery for license level 1. This includes high current AVX 256-bit instructions as well as low current AVX 512-bit instructions.",
@@ -17,6 +19,7 @@ }, { "BriefDescription": "Core cycles where the core was running in a manner where Turbo may be clipped to the AVX512 turbo schedule.", + "Counter": "0,1,2,3", "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 microarchitecture). This includes high current AVX 512-bit instructions.",
@@ -25,6 +28,7 @@ }, { "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that have any type of response.", + "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", "EventName": "OCR.DEMAND_CODE_RD.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7",
@@ -34,6 +38,7 @@ }, { "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that DRAM supplied the request.", + "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", "EventName": "OCR.DEMAND_CODE_RD.DRAM", "MSRIndex": "0x1a6,0x1a7",
@@ -43,6 +48,7 @@ }, { "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that DRAM supplied the request.", + "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", "EventName": "OCR.DEMAND_CODE_RD.LOCAL_DRAM", "MSRIndex": "0x1a6,0x1a7",
@@ -52,6 +58,7 @@ }, { "BriefDescription": "Counts demand data reads that have any type of response.", + "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", "EventName": "OCR.DEMAND_DATA_RD.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7",
@@ -61,6 +68,7 @@ }, { "BriefDescription": "Counts demand data reads that DRAM supplied the request.", + "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", "EventName": "OCR.DEMAND_DATA_RD.DRAM", "MSRIndex": "0x1a6,0x1a7",
@@ -70,6 +78,7 @@ }, { "BriefDescription": "Counts demand data reads that DRAM supplied the request.", + "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", "EventName": "OCR.DEMAND_DATA_RD.LOCAL_DRAM", "MSRIndex": "0x1a6,0x1a7",
@@ -79,6 +88,7 @@ }, { "BriefDescription": "Counts demand reads for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that have any type of response.", + "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", "EventName": "OCR.DEMAND_RFO.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7",
@@ -88,6 +98,7 @@ }, { "BriefDescription": "Counts demand reads for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that DRAM supplied the request.", + "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", "EventName": "OCR.DEMAND_RFO.DRAM", "MSRIndex": "0x1a6,0x1a7",
@@ -97,6 +108,7 @@ }, { "BriefDescription": "Counts demand reads for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that DRAM supplied the request.", + "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", "EventName": "OCR.DEMAND_RFO.LOCAL_DRAM", "MSRIndex": "0x1a6,0x1a7",
@@ -106,6 +118,7 @@ }, { "BriefDescription": "Counts L1 data cache prefetch requests and software prefetches (except PREFETCHW) that have any type of response.", + "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", "EventName": "OCR.HWPF_L1D_AND_SWPF.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7",
@@ -115,6 +128,7 @@ }, { "BriefDescription": "Counts L1 data cache prefetch requests and software prefetches (except PREFETCHW) that DRAM supplied the request.", + "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", "EventName": "OCR.HWPF_L1D_AND_SWPF.DRAM", "MSRIndex": "0x1a6,0x1a7",
@@ -124,6 +138,7 @@ }, { "BriefDescription": "Counts L1 data cache prefetch requests and software prefetches (except PREFETCHW) that DRAM supplied the request.", + "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", "EventName": "OCR.HWPF_L1D_AND_SWPF.LOCAL_DRAM", "MSRIndex": "0x1a6,0x1a7",
@@ -133,6 +148,7 @@ }, { "BriefDescription": "Counts hardware prefetch data reads (which bring data to L2) that have any type of response.", + "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", "EventName": "OCR.HWPF_L2_DATA_RD.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7",
@@ -142,6 +158,7 @@ }, { "BriefDescription": "Counts hardware prefetch data reads (which bring data to L2) that DRAM supplied the request.", + "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", "EventName": "OCR.HWPF_L2_DATA_RD.DRAM", "MSRIndex": "0x1a6,0x1a7",
@@ -151,6 +168,7 @@ }, { "BriefDescription": "Counts hardware prefetch data reads (which bring data to L2) that DRAM supplied the request.", + "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", "EventName": "OCR.HWPF_L2_DATA_RD.LOCAL_DRAM", "MSRIndex": "0x1a6,0x1a7",
@@ -160,6 +178,7 @@ }, { "BriefDescription": "Counts hardware prefetch RFOs (which bring data to L2) that have any type of response.", + "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", "EventName": "OCR.HWPF_L2_RFO.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7",
@@ -169,6 +188,7 @@ }, { "BriefDescription": "Counts hardware prefetch RFOs (which bring data to L2) that DRAM supplied the request.", + "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", "EventName": "OCR.HWPF_L2_RFO.DRAM", "MSRIndex": "0x1a6,0x1a7",
@@ -178,6 +198,7 @@ }, { "BriefDescription": "Counts hardware prefetch RFOs (which bring data to L2) that DRAM supplied the request.", + "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", "EventName": "OCR.HWPF_L2_RFO.LOCAL_DRAM", "MSRIndex": "0x1a6,0x1a7",
@@ -187,6 +208,7 @@ }, { "BriefDescription": "Counts miscellaneous requests, such as I/O and un-cacheable accesses that have any type of response.", + "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", "EventName": "OCR.OTHER.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7",
@@ -196,6 +218,7 @@ }, { "BriefDescription": "Counts miscellaneous requests, such as I/O and un-cacheable accesses that DRAM supplied the request.", + "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", "EventName": "OCR.OTHER.DRAM", "MSRIndex": "0x1a6,0x1a7",
@@ -205,6 +228,7 @@ }, { "BriefDescription": "Counts miscellaneous requests, such as I/O and un-cacheable accesses that DRAM supplied the request.", + "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", "EventName": "OCR.OTHER.LOCAL_DRAM", "MSRIndex": "0x1a6,0x1a7",
@@ -214,6 +238,7 @@ }, { "BriefDescription": "Counts streaming stores that have any type of response.", + "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", "EventName": "OCR.STREAMING_WR.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7",
@@ -223,6 +248,7 @@ }, { "BriefDescription": "Counts streaming stores that DRAM supplied the request.", + "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", "EventName": "OCR.STREAMING_WR.DRAM", "MSRIndex": "0x1a6,0x1a7",
@@ -232,6 +258,7 @@ }, { "BriefDescription": "Counts streaming stores that DRAM supplied the request.", + "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", "EventName": "OCR.STREAMING_WR.LOCAL_DRAM", "MSRIndex": "0x1a6,0x1a7",
tools/perf/pmu-events/arch/x86/icelake/pipeline.json +94 -0
641 lines not on this page · raw message
tools/perf/pmu-events/arch/x86/icelake/uncore-interconnect.json +28 -6
Lines of this file are not shown. View the raw message.
tools/perf/pmu-events/arch/x86/icelake/uncore-other.json +1 -0
Lines of this file are not shown. View the raw message.
tools/perf/pmu-events/arch/x86/icelake/virtual-memory.json +20 -0
Lines of this file are not shown. View the raw message.
tools/perf/pmu-events/arch/x86/mapfile.csv +1 -1
Lines of this file are not shown. View the raw message.
The rest of this diff is not shown. View the raw message.
Signature · 1 line
2.45.2.627.g7a2c4fd464-goog
Part of the diff is not shown here. View the raw message.
Ian Rogers
reviewerPATCH v2 17/37 perf vendor events: Add/update icelakex events/metrics
In reply to Ian RogersUpdate events from v1.24 to v1.26.
Add TMA metrics v4.8.
Bring in the event updates v1.26:
https://github.com/intel/perfmon/commit/c607c739e05f2569f95998cc98e1283f042b4fd1
v1.25:
https://github.com/intel/perfmon/commit/42d996769069921ec06f6fbb600b0c663b9ec5a9
The TMA 4.8 information was added in:
https://github.com/intel/perfmon/commit/59194d4d90ca50a3fcb2de0d82b9f6fc0c9a5736
Adds the event SW_PREFETCH_ACCESS.ANY.
--- .../pmu-events/arch/x86/icelakex/cache.json | 106 + .../pmu-events/arch/x86/icelakex/counter.json | 57 + .../arch/x86/icelakex/floating-point.json | 13 + .../arch/x86/icelakex/frontend.json | 38 + .../arch/x86/icelakex/icx-metrics.json | 340 +- .../pmu-events/arch/x86/icelakex/memory.json | 45 + .../arch/x86/icelakex/metricgroups.json | 13 + .../pmu-events/arch/x86/icelakex/other.json | 52 + .../arch/x86/icelakex/pipeline.json | 92 + .../arch/x86/icelakex/uncore-cache.json | 2149 ++++++++++- .../x86/icelakex/uncore-interconnect.json | 3344 +++++++++++++++++ .../arch/x86/icelakex/uncore-io.json | 1829 +++++++++ .../arch/x86/icelakex/uncore-memory.json | 338 ++ .../arch/x86/icelakex/uncore-power.json | 51 + .../arch/x86/icelakex/virtual-memory.json | 22 + tools/perf/pmu-events/arch/x86/mapfile.csv | 2 +- 16 files changed, 8269 insertions(+), 222 deletions(-) create mode 100644 tools/perf/pmu-events/arch/x86/icelakex/counter.json
tools/perf/pmu-events/arch/x86/icelakex/cache.json +106 -0
@@ -1,6 +1,7 @@ [ { "BriefDescription": "Counts the number of cache lines replaced in L1 data cache.", + "Counter": "0,1,2,3", "EventCode": "0x51", "EventName": "L1D.REPLACEMENT", "PublicDescription": "Counts L1D data line replacements including opportunistic replacements, and replacements that require stall-for-replace or block-for-replace.",
@@ -9,6 +10,7 @@ }, { "BriefDescription": "Number of cycles a demand request has waited due to L1D Fill Buffer (FB) unavailability.", + "Counter": "0,1,2,3", "EventCode": "0x48", "EventName": "L1D_PEND_MISS.FB_FULL", "PublicDescription": "Counts number of cycles a demand request has waited due to L1D Fill Buffer (FB) unavailability. Demand requests include cacheable/uncacheable demand load, store, lock or SW prefetch accesses.",
@@ -17,6 +19,7 @@ }, { "BriefDescription": "Number of phases a demand request has waited due to L1D Fill Buffer (FB) unavailability.", + "Counter": "0,1,2,3", "CounterMask": "1", "EdgeDetect": "1", "EventCode": "0x48",
@@ -27,6 +30,7 @@ }, { "BriefDescription": "Number of cycles a demand request has waited due to L1D due to lack of L2 resources.", + "Counter": "0,1,2,3", "EventCode": "0x48", "EventName": "L1D_PEND_MISS.L2_STALL", "PublicDescription": "Counts number of cycles a demand request has waited due to L1D due to lack of L2 resources. Demand requests include cacheable/uncacheable demand load, store, lock or SW prefetch accesses.",
@@ -35,6 +39,7 @@ }, { "BriefDescription": "Number of L1D misses that are outstanding", + "Counter": "0,1,2,3", "EventCode": "0x48", "EventName": "L1D_PEND_MISS.PENDING", "PublicDescription": "Counts number of L1D misses that are outstanding in each cycle, that is each cycle the number of Fill Buffers (FB) outstanding required by Demand Reads. FB either is held by demand loads, or it is held by non-demand loads and gets hit at least once by demand. The valid outstanding interval is defined until the FB deallocation by one of the following ways: from FB allocation, if FB is allocated by demand from the demand Hit FB, if it is allocated by hardware or software prefetch. Note: In the L1D, a Demand Read contains cacheable or noncacheable demand loads, including ones causing cache-line splits and reads due to page walks resulted from any request type.",
@@ -43,6 +48,7 @@ }, { "BriefDescription": "Cycles with L1D load Misses outstanding.", + "Counter": "0,1,2,3", "CounterMask": "1", "EventCode": "0x48", "EventName": "L1D_PEND_MISS.PENDING_CYCLES",
@@ -52,6 +58,7 @@ }, { "BriefDescription": "L2 cache lines filling L2", + "Counter": "0,1,2,3", "EventCode": "0xF1", "EventName": "L2_LINES_IN.ALL", "PublicDescription": "Counts the number of L2 cache lines filling the L2. Counting does not cover rejects.",
@@ -60,6 +67,7 @@ }, { "BriefDescription": "Cache lines that are evicted by L2 cache when triggered by an L2 cache fill.", + "Counter": "0,1,2,3", "EventCode": "0xF2", "EventName": "L2_LINES_OUT.NON_SILENT", "PublicDescription": "Counts the number of lines that are evicted by the L2 cache due to L2 cache fills. Evicted lines are delivered to the L3, which may or may not cache them, according to system load and priorities.",
@@ -68,6 +76,7 @@ }, { "BriefDescription": "Non-modified cache lines that are silently dropped by L2 cache when triggered by an L2 cache fill.", + "Counter": "0,1,2,3", "EventCode": "0xF2", "EventName": "L2_LINES_OUT.SILENT", "PublicDescription": "Counts the number of lines that are silently dropped by L2 cache when triggered by an L2 cache fill. These lines are typically in Shared or Exclusive state. A non-threaded event.",
@@ -76,6 +85,7 @@ }, { "BriefDescription": "L2 code requests", + "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_RQSTS.ALL_CODE_RD", "PublicDescription": "Counts the total number of L2 code requests.",
@@ -84,6 +94,7 @@ }, { "BriefDescription": "Demand Data Read requests", + "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_RQSTS.ALL_DEMAND_DATA_RD", "PublicDescription": "Counts the number of demand Data Read requests (including requests from L1D hardware prefetchers). These loads may hit or miss L2 cache. Only non rejected loads are counted.",
@@ -92,6 +103,7 @@ }, { "BriefDescription": "Demand requests that miss L2 cache", + "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_RQSTS.ALL_DEMAND_MISS", "PublicDescription": "Counts demand requests that miss L2 cache.",
@@ -100,6 +112,7 @@ }, { "BriefDescription": "RFO requests to L2 cache", + "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_RQSTS.ALL_RFO", "PublicDescription": "Counts the total number of RFO (read for ownership) requests to L2 cache. L2 RFO requests include both L1D demand RFO misses as well as L1D RFO prefetches.",
@@ -108,6 +121,7 @@ }, { "BriefDescription": "L2 cache hits when fetching instructions, code reads.", + "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_RQSTS.CODE_RD_HIT", "PublicDescription": "Counts L2 cache hits when fetching instructions, code reads.",
@@ -116,6 +130,7 @@ }, { "BriefDescription": "L2 cache misses when fetching instructions", + "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_RQSTS.CODE_RD_MISS", "PublicDescription": "Counts L2 cache misses when fetching instructions.",
@@ -124,6 +139,7 @@ }, { "BriefDescription": "Demand Data Read requests that hit L2 cache", + "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_RQSTS.DEMAND_DATA_RD_HIT", "PublicDescription": "Counts the number of demand Data Read requests initiated by load instructions that hit L2 cache.",
@@ -132,6 +148,7 @@ }, { "BriefDescription": "Demand Data Read miss L2, no rejects", + "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_RQSTS.DEMAND_DATA_RD_MISS", "PublicDescription": "Counts the number of demand Data Read requests that miss L2 cache. Only not rejected loads are counted.",
@@ -140,6 +157,7 @@ }, { "BriefDescription": "RFO requests that hit L2 cache", + "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_RQSTS.RFO_HIT", "PublicDescription": "Counts the RFO (Read-for-Ownership) requests that hit L2 cache.",
@@ -148,6 +166,7 @@ }, { "BriefDescription": "RFO requests that miss L2 cache", + "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_RQSTS.RFO_MISS", "PublicDescription": "Counts the RFO (Read-for-Ownership) requests that miss L2 cache.",
@@ -156,6 +175,7 @@ }, { "BriefDescription": "SW prefetch requests that hit L2 cache.", + "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_RQSTS.SWPF_HIT", "PublicDescription": "Counts Software prefetch requests that hit the L2 cache. Accounts for PREFETCHNTA and PREFETCHT0/1/2 instructions when FB is not full.",
@@ -164,6 +184,7 @@ }, { "BriefDescription": "SW prefetch requests that miss L2 cache.", + "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_RQSTS.SWPF_MISS", "PublicDescription": "Counts Software prefetch requests that miss the L2 cache. Accounts for PREFETCHNTA and PREFETCHT0/1/2 instructions when FB is not full.",
@@ -172,6 +193,7 @@ }, { "BriefDescription": "L2 writebacks that access L2 cache", + "Counter": "0,1,2,3", "EventCode": "0xF0", "EventName": "L2_TRANS.L2_WB", "PublicDescription": "Counts L2 writebacks that access L2 cache.",
@@ -180,6 +202,7 @@ }, { "BriefDescription": "Core-originated cacheable requests that missed L3 (Except hardware prefetches to the L3)", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0x2e", "EventName": "LONGEST_LAT_CACHE.MISS", "PublicDescription": "Counts core-originated cacheable requests that miss the L3 cache (Longest Latency cache). Requests include data and code reads, Reads-for-Ownership (RFOs), speculative accesses and hardware prefetches to the L1 and L2. It does not include hardware prefetches to the L3, and may not count other types of requests to the L3.",
@@ -188,6 +211,7 @@ }, { "BriefDescription": "Core-originated cacheable requests that refer to L3 (Except hardware prefetches to the L3)", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0x2e", "EventName": "LONGEST_LAT_CACHE.REFERENCE", "PublicDescription": "Counts core-originated cacheable requests to the L3 cache (Longest Latency cache). Requests include data and code reads, Reads-for-Ownership (RFOs), speculative accesses and hardware prefetches to the L1 and L2. It does not include hardware prefetches to the L3, and may not count other types of requests to the L3.",
@@ -196,6 +220,7 @@ }, { "BriefDescription": "Retired load instructions.", + "Counter": "0,1,2,3", "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_INST_RETIRED.ALL_LOADS",
@@ -206,6 +231,7 @@ }, { "BriefDescription": "Retired store instructions.", + "Counter": "0,1,2,3", "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_INST_RETIRED.ALL_STORES",
@@ -216,6 +242,7 @@ }, { "BriefDescription": "All retired memory instructions.", + "Counter": "0,1,2,3", "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_INST_RETIRED.ANY",
@@ -226,6 +253,7 @@ }, { "BriefDescription": "Retired load instructions with locked access.", + "Counter": "0,1,2,3", "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_INST_RETIRED.LOCK_LOADS",
@@ -236,6 +264,7 @@ }, { "BriefDescription": "Retired load instructions that split across a cacheline boundary.", + "Counter": "0,1,2,3", "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_INST_RETIRED.SPLIT_LOADS",
@@ -246,6 +275,7 @@ }, { "BriefDescription": "Retired store instructions that split across a cacheline boundary.", + "Counter": "0,1,2,3", "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_INST_RETIRED.SPLIT_STORES",
@@ -256,6 +286,7 @@ }, { "BriefDescription": "Retired load instructions that miss the STLB.", + "Counter": "0,1,2,3", "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_INST_RETIRED.STLB_MISS_LOADS",
@@ -266,6 +297,7 @@ }, { "BriefDescription": "Retired store instructions that miss the STLB.", + "Counter": "0,1,2,3", "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_INST_RETIRED.STLB_MISS_STORES",
@@ -276,6 +308,7 @@ }, { "BriefDescription": "Retired load instructions whose data sources were HitM responses from shared L3", + "Counter": "0,1,2,3", "Data_LA": "1", "EventCode": "0xd2", "EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD",
@@ -286,6 +319,7 @@ }, { "BriefDescription": "This event is deprecated. Refer to new event MEM_LOAD_L3_HIT_RETIRED.XSNP_NO_FWD", + "Counter": "0,1,2,3", "Data_LA": "1", "Deprecated": "1", "EventCode": "0xd2",
@@ -296,6 +330,7 @@ }, { "BriefDescription": "This event is deprecated. Refer to new event MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD", + "Counter": "0,1,2,3", "Data_LA": "1", "Deprecated": "1", "EventCode": "0xd2",
@@ -306,6 +341,7 @@ }, { "BriefDescription": "Retired load instructions whose data sources were L3 hit and cross-core snoop missed in on-pkg core cache.", + "Counter": "0,1,2,3", "Data_LA": "1", "EventCode": "0xd2", "EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS",
@@ -316,6 +352,7 @@ }, { "BriefDescription": "Retired load instructions whose data sources were hits in L3 without snoops required", + "Counter": "0,1,2,3", "Data_LA": "1", "EventCode": "0xd2", "EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_NONE",
@@ -326,6 +363,7 @@ }, { "BriefDescription": "Retired load instructions whose data sources were L3 and cross-core snoop hits in on-pkg core cache", + "Counter": "0,1,2,3", "Data_LA": "1", "EventCode": "0xd2", "EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_NO_FWD",
@@ -336,6 +374,7 @@ }, { "BriefDescription": "Retired load instructions which data sources missed L3 but serviced from local dram", + "Counter": "0,1,2,3", "Data_LA": "1", "EventCode": "0xd3", "EventName": "MEM_LOAD_L3_MISS_RETIRED.LOCAL_DRAM",
@@ -346,6 +385,7 @@ }, { "BriefDescription": "Retired load instructions which data sources missed L3 but serviced from remote dram", + "Counter": "0,1,2,3", "Data_LA": "1", "EventCode": "0xd3", "EventName": "MEM_LOAD_L3_MISS_RETIRED.REMOTE_DRAM",
@@ -355,6 +395,7 @@ }, { "BriefDescription": "Retired load instructions whose data sources was forwarded from a remote cache", + "Counter": "0,1,2,3", "Data_LA": "1", "EventCode": "0xd3", "EventName": "MEM_LOAD_L3_MISS_RETIRED.REMOTE_FWD",
@@ -365,6 +406,7 @@ }, { "BriefDescription": "Retired load instructions whose data sources was remote HITM", + "Counter": "0,1,2,3", "Data_LA": "1", "EventCode": "0xd3", "EventName": "MEM_LOAD_L3_MISS_RETIRED.REMOTE_HITM",
@@ -375,6 +417,7 @@ }, { "BriefDescription": "Retired load instructions with remote Intel(R) Optane(TM) DC persistent memory as the data source where the data request missed all caches.", + "Counter": "0,1,2,3", "Data_LA": "1", "EventCode": "0xd3", "EventName": "MEM_LOAD_L3_MISS_RETIRED.REMOTE_PMM",
@@ -385,6 +428,7 @@ }, { "BriefDescription": "Retired instructions with at least 1 uncacheable load or Bus Lock.", + "Counter": "0,1,2,3", "Data_LA": "1", "EventCode": "0xd4", "EventName": "MEM_LOAD_MISC_RETIRED.UC",
@@ -395,6 +439,7 @@ }, { "BriefDescription": "Number of completed demand load requests that missed the L1, but hit the FB(fill buffer), because a preceding miss to the same cacheline initiated the line to be brought into L1, but data is not yet ready in L1.", + "Counter": "0,1,2,3", "Data_LA": "1", "EventCode": "0xd1", "EventName": "MEM_LOAD_RETIRED.FB_HIT",
@@ -405,6 +450,7 @@ }, { "BriefDescription": "Retired load instructions with L1 cache hits as data sources", + "Counter": "0,1,2,3", "Data_LA": "1", "EventCode": "0xd1", "EventName": "MEM_LOAD_RETIRED.L1_HIT",
@@ -415,6 +461,7 @@ }, { "BriefDescription": "Retired load instructions missed L1 cache as data sources", + "Counter": "0,1,2,3", "Data_LA": "1", "EventCode": "0xd1", "EventName": "MEM_LOAD_RETIRED.L1_MISS",
@@ -425,6 +472,7 @@ }, { "BriefDescription": "Retired load instructions with L2 cache hits as data sources", + "Counter": "0,1,2,3", "Data_LA": "1", "EventCode": "0xd1", "EventName": "MEM_LOAD_RETIRED.L2_HIT",
@@ -435,6 +483,7 @@ }, { "BriefDescription": "Retired load instructions missed L2 cache as data sources", + "Counter": "0,1,2,3", "Data_LA": "1", "EventCode": "0xd1", "EventName": "MEM_LOAD_RETIRED.L2_MISS",
@@ -445,6 +494,7 @@ }, { "BriefDescription": "Retired load instructions with L3 cache hits as data sources", + "Counter": "0,1,2,3", "Data_LA": "1", "EventCode": "0xd1", "EventName": "MEM_LOAD_RETIRED.L3_HIT",
@@ -455,6 +505,7 @@ }, { "BriefDescription": "Retired load instructions missed L3 cache as data sources", + "Counter": "0,1,2,3", "Data_LA": "1", "EventCode": "0xd1", "EventName": "MEM_LOAD_RETIRED.L3_MISS",
@@ -465,6 +516,7 @@ }, { "BriefDescription": "Retired load instructions with local Intel(R) Optane(TM) DC persistent memory as the data source where the data request missed all caches.", + "Counter": "0,1,2,3", "Data_LA": "1", "EventCode": "0xd1", "EventName": "MEM_LOAD_RETIRED.LOCAL_PMM",
@@ -475,6 +527,7 @@ }, { "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that hit in the L3 or were snooped from another core's caches on the same socket.", + "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", "EventName": "OCR.DEMAND_CODE_RD.L3_HIT", "MSRIndex": "0x1a6,0x1a7",
@@ -484,6 +537,7 @@ }, { "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that resulted in a snoop hit a modified line in another core's caches which forwarded the data.", + "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", "EventName": "OCR.DEMAND_CODE_RD.L3_HIT.SNOOP_HITM", "MSRIndex": "0x1a6,0x1a7",
@@ -493,6 +547,7 @@ }, { "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that hit a modified line in a distant L3 Cache or were snooped from a distant core's L1/L2 caches on this socket when the system is in SNC (sub-NUMA cluster) mode.", + "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", "EventName": "OCR.DEMAND_CODE_RD.SNC_CACHE.HITM", "MSRIndex": "0x1a6,0x1a7",
@@ -502,6 +557,7 @@ }, { "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that either hit a non-modified line in a distant L3 Cache or were snooped from a distant core's L1/L2 caches on this socket when the system is in SNC (sub-NUMA cluster) mode.", + "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", "EventName": "OCR.DEMAND_CODE_RD.SNC_CACHE.HIT_WITH_FWD", "MSRIndex": "0x1a6,0x1a7",
@@ -511,6 +567,7 @@ }, { "BriefDescription": "Counts demand data reads that hit in the L3 or were snooped from another core's caches on the same socket.", + "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", "EventName": "OCR.DEMAND_DATA_RD.L3_HIT", "MSRIndex": "0x1a6,0x1a7",
@@ -520,6 +577,7 @@ }, { "BriefDescription": "Counts demand data reads that resulted in a snoop hit a modified line in another core's caches which forwarded the data.", + "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", "EventName": "OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM", "MSRIndex": "0x1a6,0x1a7",
@@ -529,6 +587,7 @@ }, { "BriefDescription": "Counts demand data reads that resulted in a snoop that hit in another core, which did not forward the data.", + "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", "EventName": "OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_NO_FWD", "MSRIndex": "0x1a6,0x1a7",
@@ -538,6 +597,7 @@ }, { "BriefDescription": "Counts demand data reads that resulted in a snoop hit in another core's caches which forwarded the unmodified data to the requesting core.", + "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", "EventName": "OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD", "MSRIndex": "0x1a6,0x1a7",
@@ -547,6 +607,7 @@ }, { "BriefDescription": "Counts demand data reads that were supplied by a cache on a remote socket where a snoop hit a modified line in another core's caches which forwarded the data.", + "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", "EventName": "OCR.DEMAND_DATA_RD.REMOTE_CACHE.SNOOP_HITM", "MSRIndex": "0x1a6,0x1a7",
@@ -556,6 +617,7 @@ }, { "BriefDescription": "Counts demand data reads that were supplied by a cache on a remote socket where a snoop hit in another core's caches which forwarded the unmodified data to the requesting core.", + "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", "EventName": "OCR.DEMAND_DATA_RD.REMOTE_CACHE.SNOOP_HIT_WITH_FWD", "MSRIndex": "0x1a6,0x1a7",
@@ -565,6 +627,7 @@ }, { "BriefDescription": "Counts demand data reads that hit a modified line in a distant L3 Cache or were snooped from a distant core's L1/L2 caches on this socket when the system is in SNC (sub-NUMA cluster) mode.", + "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", "EventName": "OCR.DEMAND_DATA_RD.SNC_CACHE.HITM", "MSRIndex": "0x1a6,0x1a7",
@@ -574,6 +637,7 @@ }, { "BriefDescription": "Counts demand data reads that either hit a non-modified line in a distant L3 Cache or were snooped from a distant core's L1/L2 caches on this socket when the system is in SNC (sub-NUMA cluster) mode.", + "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", "EventName": "OCR.DEMAND_DATA_RD.SNC_CACHE.HIT_WITH_FWD", "MSRIndex": "0x1a6,0x1a7",
@@ -583,6 +647,7 @@ }, { "BriefDescription": "Counts demand reads for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that hit in the L3 or were snooped from another core's caches on the same socket.", + "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", "EventName": "OCR.DEMAND_RFO.L3_HIT", "MSRIndex": "0x1a6,0x1a7",
@@ -592,6 +657,7 @@ }, { "BriefDescription": "Counts demand reads for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that resulted in a snoop hit a modified line in another core's caches which forwarded the data.", + "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", "EventName": "OCR.DEMAND_RFO.L3_HIT.SNOOP_HITM", "MSRIndex": "0x1a6,0x1a7",
@@ -601,6 +667,7 @@ }, { "BriefDescription": "Counts demand reads for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that hit a modified line in a distant L3 Cache or were snooped from a distant core's L1/L2 caches on this socket when the system is in SNC (sub-NUMA cluster) mode.", + "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", "EventName": "OCR.DEMAND_RFO.SNC_CACHE.HITM", "MSRIndex": "0x1a6,0x1a7",
@@ -610,6 +677,7 @@ }, { "BriefDescription": "Counts demand reads for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that either hit a non-modified line in a distant L3 Cache or were snooped from a distant core's L1/L2 caches on this socket when the system is in SNC (sub-NUMA cluster) mode.", + "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", "EventName": "OCR.DEMAND_RFO.SNC_CACHE.HIT_WITH_FWD", "MSRIndex": "0x1a6,0x1a7",
@@ -619,6 +687,7 @@ }, { "BriefDescription": "Counts L1 data cache prefetch requests and software prefetches (except PREFETCHW) that hit in the L3 or were snooped from another core's caches on the same socket.", + "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", "EventName": "OCR.HWPF_L1D_AND_SWPF.L3_HIT", "MSRIndex": "0x1a6,0x1a7",
@@ -628,6 +697,7 @@ }, { "BriefDescription": "Counts hardware prefetches to the L3 only that hit in the L3 or were snooped from another core's caches on the same socket.", + "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", "EventName": "OCR.HWPF_L3.L3_HIT", "MSRIndex": "0x1a6,0x1a7",
@@ -637,6 +707,7 @@ }, { "BriefDescription": "Counts hardware and software prefetches to all cache levels that hit in the L3 or were snooped from another core's caches on the same socket.", + "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", "EventName": "OCR.PREFETCHES.L3_HIT", "MSRIndex": "0x1a6,0x1a7",
@@ -646,6 +717,7 @@ }, { "BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that hit in the L3 or were snooped from another core's caches on the same socket.", + "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", "EventName": "OCR.READS_TO_CORE.L3_HIT", "MSRIndex": "0x1a6,0x1a7",
@@ -655,6 +727,7 @@ }, { "BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that resulted in a snoop hit a modified line in another core's caches which forwarded the data.", + "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", "EventName": "OCR.READS_TO_CORE.L3_HIT.SNOOP_HITM", "MSRIndex": "0x1a6,0x1a7",
@@ -664,6 +737,7 @@ }, { "BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that resulted in a snoop that hit in another core, which did not forward the data.", + "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", "EventName": "OCR.READS_TO_CORE.L3_HIT.SNOOP_HIT_NO_FWD", "MSRIndex": "0x1a6,0x1a7",
@@ -673,6 +747,7 @@ }, { "BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that resulted in a snoop hit in another core's caches which forwarded the unmodified data to the requesting core.", + "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", "EventName": "OCR.READS_TO_CORE.L3_HIT.SNOOP_HIT_WITH_FWD", "MSRIndex": "0x1a6,0x1a7",
@@ -682,6 +757,7 @@ }, { "BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by a cache on a remote socket where a snoop was sent and data was returned (Modified or Not Modified).", + "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", "EventName": "OCR.READS_TO_CORE.REMOTE_CACHE.SNOOP_FWD", "MSRIndex": "0x1a6,0x1a7",
@@ -691,6 +767,7 @@ }, { "BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by a cache on a remote socket where a snoop hit a modified line in another core's caches which forwarded the data.", + "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", "EventName": "OCR.READS_TO_CORE.REMOTE_CACHE.SNOOP_HITM", "MSRIndex": "0x1a6,0x1a7",
@@ -700,6 +777,7 @@ }, { "BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by a cache on a remote socket where a snoop hit in another core's caches which forwarded the unmodified data to the requesting core.", + "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", "EventName": "OCR.READS_TO_CORE.REMOTE_CACHE.SNOOP_HIT_WITH_FWD", "MSRIndex": "0x1a6,0x1a7",
@@ -709,6 +787,7 @@ }, { "BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that hit a modified line in a distant L3 Cache or were snooped from a distant core's L1/L2 caches on this socket when the system is in SNC (sub-NUMA cluster) mode.", + "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", "EventName": "OCR.READS_TO_CORE.SNC_CACHE.HITM", "MSRIndex": "0x1a6,0x1a7",
@@ -718,6 +797,7 @@ }, { "BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that either hit a non-modified line in a distant L3 Cache or were snooped from a distant core's L1/L2 caches on this socket when the system is in SNC (sub-NUMA cluster) mode.", + "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", "EventName": "OCR.READS_TO_CORE.SNC_CACHE.HIT_WITH_FWD", "MSRIndex": "0x1a6,0x1a7",
@@ -727,6 +807,7 @@ }, { "BriefDescription": "Counts streaming stores that hit in the L3 or were snooped from another core's caches on the same socket.", + "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", "EventName": "OCR.STREAMING_WR.L3_HIT", "MSRIndex": "0x1a6,0x1a7",
@@ -736,6 +817,7 @@ }, { "BriefDescription": "Demand and prefetch data reads", + "Counter": "0,1,2,3", "EventCode": "0xB0", "EventName": "OFFCORE_REQUESTS.ALL_DATA_RD", "PublicDescription": "Counts the demand and prefetch data reads. All Core Data Reads include cacheable 'Demands' and L2 prefetchers (not L3 prefetchers). Counting also covers reads due to page walks resulted from any request type.",
@@ -744,6 +826,7 @@ }, { "BriefDescription": "Counts memory transactions sent to the uncore.", + "Counter": "0,1,2,3", "EventCode": "0xB0", "EventName": "OFFCORE_REQUESTS.ALL_REQUESTS", "PublicDescription": "Counts memory transactions sent to the uncore including requests initiated by the core, all L3 prefetches, reads resulting from page walks, and snoop responses.",
@@ -752,6 +835,7 @@ }, { "BriefDescription": "Counts cacheable and non-cacheable code reads to the core.", + "Counter": "0,1,2,3", "EventCode": "0xb0", "EventName": "OFFCORE_REQUESTS.DEMAND_CODE_RD", "PublicDescription": "Counts both cacheable and non-cacheable code reads to the core.",
@@ -760,6 +844,7 @@ }, { "BriefDescription": "Demand Data Read requests sent to uncore", + "Counter": "0,1,2,3", "EventCode": "0xb0", "EventName": "OFFCORE_REQUESTS.DEMAND_DATA_RD", "PublicDescription": "Counts the Demand Data Read requests sent to uncore. Use it in conjunction with OFFCORE_REQUESTS_OUTSTANDING to determine average latency in the uncore.",
@@ -768,6 +853,7 @@ }, { "BriefDescription": "Demand RFO requests including regular RFOs, locks, ItoM", + "Counter": "0,1,2,3", "EventCode": "0xb0", "EventName": "OFFCORE_REQUESTS.DEMAND_RFO", "PublicDescription": "Counts the demand RFO (read for ownership) requests including regular RFOs, locks, ItoM.",
@@ -776,6 +862,7 @@ }, { "BriefDescription": "For every cycle, increments by the number of outstanding data read requests pending.", + "Counter": "0,1,2,3", "EventCode": "0x60", "EventName": "OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD", "PublicDescription": "For every cycle, increments by the number of outstanding data read requests pending. Data read requests include cacheable demand reads and L2 prefetches, but do not include RFOs, code reads or prefetches to the L3. Reads due to page walks resulting from any request type will also be counted. Requests are considered outstanding from the time they miss the core's L2 cache until the transaction completion message is sent to the requestor.",
@@ -784,6 +871,7 @@ }, { "BriefDescription": "Cycles where at least 1 outstanding data read request is pending.", + "Counter": "0,1,2,3", "CounterMask": "1", "EventCode": "0x60", "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD",
@@ -793,6 +881,7 @@ }, { "BriefDescription": "Cycles with outstanding code read requests pending.", + "Counter": "0,1,2,3", "CounterMask": "1", "EventCode": "0x60", "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_CODE_RD",
@@ -802,6 +891,7 @@ }, { "BriefDescription": "Cycles where at least 1 outstanding Demand RFO request is pending.", + "Counter": "0,1,2,3", "CounterMask": "1", "EventCode": "0x60", "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO",
@@ -811,6 +901,7 @@ }, { "BriefDescription": "For every cycle, increments by the number of outstanding code read requests pending.", + "Counter": "0,1,2,3", "EventCode": "0x60", "EventName": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_CODE_RD", "PublicDescription": "For every cycle, increments by the number of outstanding code read requests pending. Code Read requests include both cacheable and non-cacheable Code Reads. Requests are considered outstanding from the time they miss the core's L2 cache until the transaction completion message is sent to the requestor.",
@@ -819,6 +910,7 @@ }, { "BriefDescription": "For every cycle, increments by the number of outstanding demand data read requests pending.", + "Counter": "0,1,2,3", "EventCode": "0x60", "EventName": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD", "PublicDescription": "For every cycle, increments by the number of outstanding demand data read requests pending. Requests are considered outstanding from the time they miss the core's L2 cache until the transaction completion message is sent to the requestor.",
@@ -827,6 +919,7 @@ }, { "BriefDescription": "Counts bus locks, accounts for cache line split locks and UC locks.", + "Counter": "0,1,2,3", "EventCode": "0xF4", "EventName": "SQ_MISC.BUS_LOCK", "PublicDescription": "Counts the more expensive bus lock needed to enforce cache coherency for certain memory accesses that need to be done atomically. Can be created by issuing an atomic instruction (via the LOCK prefix) which causes a cache line split or accesses uncacheable memory.",
@@ -835,14 +928,24 @@ }, { "BriefDescription": "Cycles the queue waiting for offcore responses is full.", + "Counter": "0,1,2,3", "EventCode": "0xf4", "EventName": "SQ_MISC.SQ_FULL", "PublicDescription": "Counts the cycles for which the thread is active and the queue waiting for responses from the uncore cannot take any more entries.", "SampleAfterValue": "100003", "UMask": "0x4" }, + { + "BriefDescription": "Counts the number of PREFETCHNTA, PREFETCHW, PREFETCHT0, PREFETCHT1 or PREFETCHT2 instructions executed.", + "Counter": "0,1,2,3", + "EventCode": "0x32", + "EventName": "SW_PREFETCH_ACCESS.ANY", + "SampleAfterValue": "100003", + "UMask": "0xf" + }, { "BriefDescription": "Number of PREFETCHNTA instructions executed.", + "Counter": "0,1,2,3", "EventCode": "0x32", "EventName": "SW_PREFETCH_ACCESS.NTA", "PublicDescription": "Counts the number of PREFETCHNTA instructions executed.",
@@ -851,6 +954,7 @@ }, { "BriefDescription": "Number of PREFETCHW instructions executed.", + "Counter": "0,1,2,3", "EventCode": "0x32", "EventName": "SW_PREFETCH_ACCESS.PREFETCHW", "PublicDescription": "Counts the number of PREFETCHW instructions executed.",
@@ -859,6 +963,7 @@ }, { "BriefDescription": "Number of PREFETCHT0 instructions executed.", + "Counter": "0,1,2,3", "EventCode": "0x32", "EventName": "SW_PREFETCH_ACCESS.T0", "PublicDescription": "Counts the number of PREFETCHT0 instructions executed.",
@@ -867,6 +972,7 @@ }, { "BriefDescription": "Number of PREFETCHT1 or PREFETCHT2 instructions executed.", + "Counter": "0,1,2,3", "EventCode": "0x32", "EventName": "SW_PREFETCH_ACCESS.T1_T2", "PublicDescription": "Counts the number of PREFETCHT1 or PREFETCHT2 instructions executed.",
tools/perf/pmu-events/arch/x86/icelakex/counter.json new file +57 -0
58 lines not on this page · raw message
tools/perf/pmu-events/arch/x86/icelakex/floating-point.json +13 -0
@@ -1,6 +1,7 @@ [ { "BriefDescription": "Counts all microcode FP assists.", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc1", "EventName": "ASSISTS.FP", "PublicDescription": "Counts all microcode Floating Point assists.",
@@ -9,6 +10,7 @@ }, { "BriefDescription": "Counts number of SSE/AVX computational 128-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 2 computation operations, one for each element. Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element.", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc7", "EventName": "FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE", "PublicDescription": "Number of SSE/AVX computational 128-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 2 computation operations, one for each element. Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.",
@@ -17,6 +19,7 @@ }, { "BriefDescription": "Number of SSE/AVX computational 128-bit packed single precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 4 computation operations, one for each element. Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB MUL DIV MIN MAX RCP14 RSQRT14 SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element.", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc7", "EventName": "FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE", "PublicDescription": "Number of SSE/AVX computational 128-bit packed single precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 4 computation operations, one for each element. Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT RSQRT RCP DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.",
@@ -25,6 +28,7 @@ }, { "BriefDescription": "Counts number of SSE/AVX computational 256-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 4 computation operations, one for each element. Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element.", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc7", "EventName": "FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE", "PublicDescription": "Number of SSE/AVX computational 256-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 4 computation operations, one for each element. Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.",
@@ -33,6 +37,7 @@ }, { "BriefDescription": "Counts number of SSE/AVX computational 256-bit packed single precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 8 computation operations, one for each element. Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT RSQRT RCP DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element.", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc7", "EventName": "FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE", "PublicDescription": "Number of SSE/AVX computational 256-bit packed single precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 8 computation operations, one for each element. Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT RSQRT RCP DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.",
@@ -41,6 +46,7 @@ }, { "BriefDescription": "Number of SSE/AVX computational 128-bit packed single and 256-bit packed double precision FP instructions retired; some instructions will count twice as noted below. Each count represents 2 or/and 4 computation operations, 1 for each element. Applies to SSE* and AVX* packed single precision and packed double precision FP instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX RCP14 RSQRT14 SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB count twice as they perform 2 calculations per element.", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc7", "EventName": "FP_ARITH_INST_RETIRED.4_FLOPS", "PublicDescription": "Number of SSE/AVX computational 128-bit packed single precision and 256-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 2 or/and 4 computation operations, one for each element. Applies to SSE* and AVX* packed single precision floating-point and packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX RCP14 RSQRT14 SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.",
@@ -49,6 +55,7 @@ }, { "BriefDescription": "Counts number of SSE/AVX computational 512-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 8 computation operations, one for each element. Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT RSQRT14 RCP14 FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element.", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc7", "EventName": "FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE", "PublicDescription": "Number of SSE/AVX computational 512-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 8 computation operations, one for each element. Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT RSQRT14 RCP14 FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.",
@@ -57,6 +64,7 @@ }, { "BriefDescription": "Counts number of SSE/AVX computational 512-bit packed single precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 16 computation operations, one for each element. Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT RSQRT14 RCP14 FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element.", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc7", "EventName": "FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE", "PublicDescription": "Number of SSE/AVX computational 512-bit packed single precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 16 computation operations, one for each element. Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT RSQRT14 RCP14 FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.",
@@ -65,6 +73,7 @@ }, { "BriefDescription": "Number of SSE/AVX computational 256-bit packed single precision and 512-bit packed double precision FP instructions retired; some instructions will count twice as noted below. Each count represents 8 computation operations, 1 for each element. Applies to SSE* and AVX* packed single precision and double precision FP instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT RSQRT RSQRT14 RCP RCP14 DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB count twice as they perform 2 calculations per element.", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc7", "EventName": "FP_ARITH_INST_RETIRED.8_FLOPS", "PublicDescription": "Number of SSE/AVX computational 256-bit packed single precision and 512-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 8 computation operations, one for each element. Applies to SSE* and AVX* packed single precision and double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT RSQRT RSQRT14 RCP RCP14 DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.",
@@ -73,6 +82,7 @@ }, { "BriefDescription": "Number of SSE/AVX computational scalar floating-point instructions retired; some instructions will count twice as noted below. Applies to SSE* and AVX* scalar, double and single precision floating-point: ADD SUB MUL DIV MIN MAX RCP14 RSQRT14 SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc7", "EventName": "FP_ARITH_INST_RETIRED.SCALAR", "PublicDescription": "Number of SSE/AVX computational scalar single precision and double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 1 computational operation. Applies to SSE* and AVX* scalar single precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT RSQRT RCP FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.",
@@ -81,6 +91,7 @@ }, { "BriefDescription": "Counts number of SSE/AVX computational scalar double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 1 computational operation. Applies to SSE* and AVX* scalar double precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element.", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc7", "EventName": "FP_ARITH_INST_RETIRED.SCALAR_DOUBLE", "PublicDescription": "Number of SSE/AVX computational scalar double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 1 computational operation. Applies to SSE* and AVX* scalar double precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.",
@@ -89,6 +100,7 @@ }, { "BriefDescription": "Counts number of SSE/AVX computational scalar single precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 1 computational operation. Applies to SSE* and AVX* scalar single precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT RSQRT RCP FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element.", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc7", "EventName": "FP_ARITH_INST_RETIRED.SCALAR_SINGLE", "PublicDescription": "Number of SSE/AVX computational scalar single precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 1 computational operation. Applies to SSE* and AVX* scalar single precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT RSQRT RCP FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.",
@@ -97,6 +109,7 @@ }, { "BriefDescription": "Number of any Vector retired FP arithmetic instructions", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc7", "EventName": "FP_ARITH_INST_RETIRED.VECTOR", "SampleAfterValue": "1000003",
tools/perf/pmu-events/arch/x86/icelakex/frontend.json +38 -0
@@ -1,6 +1,7 @@ [ { "BriefDescription": "Counts the total number when the front end is resteered, mainly when the BPU cannot provide a correct prediction and this is corrected by other branch handling mechanisms at the front end.", + "Counter": "0,1,2,3", "EventCode": "0xe6", "EventName": "BACLEARS.ANY", "PublicDescription": "Counts the number of times the front-end is resteered when it finds a branch instruction in a fetch line. This occurs for the first time a branch instruction is fetched or when the branch is not tracked by the BPU (Branch Prediction Unit) anymore.",
@@ -9,6 +10,7 @@ }, { "BriefDescription": "Stalls caused by changing prefix length of the instruction. [This event is alias to ILD_STALL.LCP]", + "Counter": "0,1,2,3", "EventCode": "0x87", "EventName": "DECODE.LCP", "PublicDescription": "Counts cycles that the Instruction Length decoder (ILD) stalls occurred due to dynamically changing prefix length of the decoded instruction (by operand size prefix instruction 0x66, address size prefix instruction 0x67 or REX.W for Intel64). Count is proportional to the number of prefixes in a 16B-line. This may result in a three-cycle penalty for each LCP (Length changing prefix) in a 16-byte chunk. [This event is alias to ILD_STALL.LCP]",
@@ -17,6 +19,7 @@ }, { "BriefDescription": "Decode Stream Buffer (DSB)-to-MITE transitions count.", + "Counter": "0,1,2,3", "CounterMask": "1", "EdgeDetect": "1", "EventCode": "0xab",
@@ -27,6 +30,7 @@ }, { "BriefDescription": "DSB-to-MITE switch true penalty cycles.", + "Counter": "0,1,2,3", "EventCode": "0xab", "EventName": "DSB2MITE_SWITCHES.PENALTY_CYCLES", "PublicDescription": "Decode Stream Buffer (DSB) is a Uop-cache that holds translations of previously fetched instructions that were decoded by the legacy x86 decode pipeline (MITE). This event counts fetch penalty cycles when a transition occurs from DSB to MITE.",
@@ -35,6 +39,7 @@ }, { "BriefDescription": "Retired Instructions who experienced DSB miss.", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc6", "EventName": "FRONTEND_RETIRED.ANY_DSB_MISS", "MSRIndex": "0x3F7",
@@ -46,6 +51,7 @@ }, { "BriefDescription": "Retired Instructions who experienced a critical DSB miss.", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc6", "EventName": "FRONTEND_RETIRED.DSB_MISS", "MSRIndex": "0x3F7",
@@ -57,6 +63,7 @@ }, { "BriefDescription": "Retired Instructions who experienced iTLB true miss.", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc6", "EventName": "FRONTEND_RETIRED.ITLB_MISS", "MSRIndex": "0x3F7",
@@ -68,6 +75,7 @@ }, { "BriefDescription": "Retired Instructions who experienced Instruction L1 Cache true miss.", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc6", "EventName": "FRONTEND_RETIRED.L1I_MISS", "MSRIndex": "0x3F7",
@@ -79,6 +87,7 @@ }, { "BriefDescription": "Retired Instructions who experienced Instruction L2 Cache true miss.", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc6", "EventName": "FRONTEND_RETIRED.L2_MISS", "MSRIndex": "0x3F7",
@@ -90,6 +99,7 @@ }, { "BriefDescription": "Retired instructions after front-end starvation of at least 1 cycle", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc6", "EventName": "FRONTEND_RETIRED.LATENCY_GE_1", "MSRIndex": "0x3F7",
@@ -101,6 +111,7 @@ }, { "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 128 cycles which was not interrupted by a back-end stall.", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc6", "EventName": "FRONTEND_RETIRED.LATENCY_GE_128", "MSRIndex": "0x3F7",
@@ -112,6 +123,7 @@ }, { "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 16 cycles which was not interrupted by a back-end stall.", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc6", "EventName": "FRONTEND_RETIRED.LATENCY_GE_16", "MSRIndex": "0x3F7",
@@ -123,6 +135,7 @@ }, { "BriefDescription": "Retired instructions after front-end starvation of at least 2 cycles", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc6", "EventName": "FRONTEND_RETIRED.LATENCY_GE_2", "MSRIndex": "0x3F7",
@@ -134,6 +147,7 @@ }, { "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 256 cycles which was not interrupted by a back-end stall.", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc6", "EventName": "FRONTEND_RETIRED.LATENCY_GE_256", "MSRIndex": "0x3F7",
@@ -145,6 +159,7 @@ }, { "BriefDescription": "Retired instructions that are fetched after an interval where the front-end had at least 1 bubble-slot for a period of 2 cycles which was not interrupted by a back-end stall.", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc6", "EventName": "FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1", "MSRIndex": "0x3F7",
@@ -156,6 +171,7 @@ }, { "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 32 cycles which was not interrupted by a back-end stall.", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc6", "EventName": "FRONTEND_RETIRED.LATENCY_GE_32", "MSRIndex": "0x3F7",
@@ -167,6 +183,7 @@ }, { "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 4 cycles which was not interrupted by a back-end stall.", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc6", "EventName": "FRONTEND_RETIRED.LATENCY_GE_4", "MSRIndex": "0x3F7",
@@ -178,6 +195,7 @@ }, { "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 512 cycles which was not interrupted by a back-end stall.", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc6", "EventName": "FRONTEND_RETIRED.LATENCY_GE_512", "MSRIndex": "0x3F7",
@@ -189,6 +207,7 @@ }, { "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 64 cycles which was not interrupted by a back-end stall.", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc6", "EventName": "FRONTEND_RETIRED.LATENCY_GE_64", "MSRIndex": "0x3F7",
@@ -200,6 +219,7 @@ }, { "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 8 cycles which was not interrupted by a back-end stall.", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc6", "EventName": "FRONTEND_RETIRED.LATENCY_GE_8", "MSRIndex": "0x3F7",
@@ -211,6 +231,7 @@ }, { "BriefDescription": "Retired Instructions who experienced STLB (2nd level TLB) true miss.", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc6", "EventName": "FRONTEND_RETIRED.STLB_MISS", "MSRIndex": "0x3F7",
@@ -222,6 +243,7 @@ }, { "BriefDescription": "Cycles where a code fetch is stalled due to L1 instruction cache miss. [This event is alias to ICACHE_DATA.STALLS]", + "Counter": "0,1,2,3", "EventCode": "0x80", "EventName": "ICACHE_16B.IFDATA_STALL", "PublicDescription": "Counts cycles where a code line fetch is stalled due to an L1 instruction cache miss. The legacy decode pipeline works at a 16 Byte granularity. [This event is alias to ICACHE_DATA.STALLS]",
@@ -230,6 +252,7 @@ }, { "BriefDescription": "Instruction fetch tag lookups that hit in the instruction cache (L1I). Counts at 64-byte cache-line granularity.", + "Counter": "0,1,2,3", "EventCode": "0x83", "EventName": "ICACHE_64B.IFTAG_HIT", "PublicDescription": "Counts instruction fetch tag lookups that hit in the instruction cache (L1I). Counts at 64-byte cache-line granularity. Accounts for both cacheable and uncacheable accesses.",
@@ -238,6 +261,7 @@ }, { "BriefDescription": "Instruction fetch tag lookups that miss in the instruction cache (L1I). Counts at 64-byte cache-line granularity.", + "Counter": "0,1,2,3", "EventCode": "0x83", "EventName": "ICACHE_64B.IFTAG_MISS", "PublicDescription": "Counts instruction fetch tag lookups that miss in the instruction cache (L1I). Counts at 64-byte cache-line granularity. Accounts for both cacheable and uncacheable accesses.",
@@ -246,6 +270,7 @@ }, { "BriefDescription": "Cycles where a code fetch is stalled due to L1 instruction cache tag miss. [This event is alias to ICACHE_TAG.STALLS]", + "Counter": "0,1,2,3", "EventCode": "0x83", "EventName": "ICACHE_64B.IFTAG_STALL", "PublicDescription": "Counts cycles where a code fetch is stalled due to L1 instruction cache tag miss. [This event is alias to ICACHE_TAG.STALLS]",
@@ -254,6 +279,7 @@ }, { "BriefDescription": "Cycles where a code fetch is stalled due to L1 instruction cache miss. [This event is alias to ICACHE_16B.IFDATA_STALL]", + "Counter": "0,1,2,3", "EventCode": "0x80", "EventName": "ICACHE_DATA.STALLS", "PublicDescription": "Counts cycles where a code line fetch is stalled due to an L1 instruction cache miss. The legacy decode pipeline works at a 16 Byte granularity. [This event is alias to ICACHE_16B.IFDATA_STALL]",
@@ -262,6 +288,7 @@ }, { "BriefDescription": "Cycles where a code fetch is stalled due to L1 instruction cache tag miss. [This event is alias to ICACHE_64B.IFTAG_STALL]", + "Counter": "0,1,2,3", "EventCode": "0x83", "EventName": "ICACHE_TAG.STALLS", "PublicDescription": "Counts cycles where a code fetch is stalled due to L1 instruction cache tag miss. [This event is alias to ICACHE_64B.IFTAG_STALL]",
@@ -270,6 +297,7 @@ }, { "BriefDescription": "Cycles Decode Stream Buffer (DSB) is delivering any Uop", + "Counter": "0,1,2,3", "CounterMask": "1", "EventCode": "0x79", "EventName": "IDQ.DSB_CYCLES_ANY",
@@ -279,6 +307,7 @@ }, { "BriefDescription": "Cycles DSB is delivering optimal number of Uops", + "Counter": "0,1,2,3", "CounterMask": "5", "EventCode": "0x79", "EventName": "IDQ.DSB_CYCLES_OK",
@@ -288,6 +317,7 @@ }, { "BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path", + "Counter": "0,1,2,3", "EventCode": "0x79", "EventName": "IDQ.DSB_UOPS", "PublicDescription": "Counts the number of uops delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path.",
@@ -296,6 +326,7 @@ }, { "BriefDescription": "Cycles MITE is delivering any Uop", + "Counter": "0,1,2,3", "CounterMask": "1", "EventCode": "0x79", "EventName": "IDQ.MITE_CYCLES_ANY",
@@ -305,6 +336,7 @@ }, { "BriefDescription": "Cycles MITE is delivering optimal number of Uops", + "Counter": "0,1,2,3", "CounterMask": "5", "EventCode": "0x79", "EventName": "IDQ.MITE_CYCLES_OK",
@@ -314,6 +346,7 @@ }, { "BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) from MITE path", + "Counter": "0,1,2,3", "EventCode": "0x79", "EventName": "IDQ.MITE_UOPS", "PublicDescription": "Counts the number of uops delivered to Instruction Decode Queue (IDQ) from the MITE path. This also means that uops are not being delivered from the Decode Stream Buffer (DSB).",
@@ -322,6 +355,7 @@ }, { "BriefDescription": "Number of switches from DSB or MITE to the MS", + "Counter": "0,1,2,3", "CounterMask": "1", "EdgeDetect": "1", "EventCode": "0x79",
@@ -332,6 +366,7 @@ }, { "BriefDescription": "Uops delivered to IDQ while MS is busy", + "Counter": "0,1,2,3", "EventCode": "0x79", "EventName": "IDQ.MS_UOPS", "PublicDescription": "Counts the total number of uops delivered by the Microcode Sequencer (MS). Any instruction over 4 uops will be delivered by the MS. Some instructions such as transcendentals may additionally generate uops from the MS.",
@@ -340,6 +375,7 @@ }, { "BriefDescription": "Uops not delivered by IDQ when backend of the machine is not stalled", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0x9c", "EventName": "IDQ_UOPS_NOT_DELIVERED.CORE", "PublicDescription": "Counts the number of uops not delivered to by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle.",
@@ -348,6 +384,7 @@ }, { "BriefDescription": "Cycles when no uops are not delivered by the IDQ when backend of the machine is not stalled", + "Counter": "0,1,2,3,4,5,6,7", "CounterMask": "5", "EventCode": "0x9c", "EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE",
@@ -357,6 +394,7 @@ }, { "BriefDescription": "Cycles when optimal number of uops was delivered to the back-end when the back-end is not stalled", + "Counter": "0,1,2,3,4,5,6,7", "CounterMask": "1", "EventCode": "0x9C", "EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_FE_WAS_OK",
tools/perf/pmu-events/arch/x86/icelakex/icx-metrics.json +143 -197
798 lines not on this page · raw message
tools/perf/pmu-events/arch/x86/icelakex/memory.json +45 -0
315 lines not on this page · raw message
tools/perf/pmu-events/arch/x86/icelakex/metricgroups.json +13 -0
@@ -5,7 +5,20 @@ "BigFootprint": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", "BrMispredicts": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", "Branches": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "BvBC": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "BvBO": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "BvCB": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "BvFB": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "BvIO": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "BvMB": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "BvML": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "BvMP": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "BvMS": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "BvMT": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "BvOB": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "BvUW": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", "CacheHits": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "CacheMisses": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", "CodeGen": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", "Compute": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", "Cor": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
tools/perf/pmu-events/arch/x86/icelakex/other.json +52 -0
364 lines not on this page · raw message
tools/perf/pmu-events/arch/x86/icelakex/pipeline.json +92 -0
392 lines not on this page · raw message
tools/perf/pmu-events/arch/x86/icelakex/uncore-cache.json +2125 -24
2,149 lines not on this page · raw message
tools/perf/pmu-events/arch/x86/icelakex/uncore-interconnect.json +3344 -0
3,344 lines not on this page · raw message
tools/perf/pmu-events/arch/x86/icelakex/uncore-io.json +1829 -0
1,829 lines not on this page · raw message
tools/perf/pmu-events/arch/x86/icelakex/uncore-memory.json +338 -0
338 lines not on this page · raw message
tools/perf/pmu-events/arch/x86/icelakex/uncore-power.json +51 -0
51 lines not on this page · raw message
tools/perf/pmu-events/arch/x86/icelakex/virtual-memory.json +22 -0
Lines of this file are not shown. View the raw message.
tools/perf/pmu-events/arch/x86/mapfile.csv +1 -1
Lines of this file are not shown. View the raw message.
The rest of this diff is not shown. View the raw message.
Signature · 1 line
2.45.2.627.g7a2c4fd464-goog
Part of the diff is not shown here. View the raw message.
Ian Rogers
reviewerPATCH v2 18/37 perf vendor events: Update ivybridge metrics add event counter information
In reply to Ian RogersAdd counter information necessary for optimizing event grouping the perf tool.
The most recent RFC patch set using this information:
https://lore.kernel.org/lkml/[email protected]/
The information was added in:
https://github.com/intel/perfmon/commit/475892a9690cb048949e593fe39cee65cd4765e1
and later patches.
The TMA 4.8 information was updated in:
https://github.com/intel/perfmon/commit/59194d4d90ca50a3fcb2de0d82b9f6fc0c9a5736
--- .../pmu-events/arch/x86/ivybridge/cache.json | 104 +++++++++++++++ .../arch/x86/ivybridge/counter.json | 17 +++ .../arch/x86/ivybridge/floating-point.json | 17 +++ .../arch/x86/ivybridge/frontend.json | 30 +++++ .../arch/x86/ivybridge/ivb-metrics.json | 68 +++++----- .../pmu-events/arch/x86/ivybridge/memory.json | 19 +++ .../arch/x86/ivybridge/metricgroups.json | 11 ++ .../pmu-events/arch/x86/ivybridge/other.json | 4 + .../arch/x86/ivybridge/pipeline.json | 126 ++++++++++++++++++ .../arch/x86/ivybridge/uncore-cache.json | 25 ++++ .../x86/ivybridge/uncore-interconnect.json | 9 ++ .../arch/x86/ivybridge/virtual-memory.json | 18 +++ 12 files changed, 417 insertions(+), 31 deletions(-) create mode 100644 tools/perf/pmu-events/arch/x86/ivybridge/counter.json
tools/perf/pmu-events/arch/x86/ivybridge/cache.json +104 -0
@@ -1,6 +1,7 @@ [ { "BriefDescription": "L1D data line replacements", + "Counter": "0,1,2,3", "EventCode": "0x51", "EventName": "L1D.REPLACEMENT", "PublicDescription": "Counts the number of lines brought into the L1 data cache.",
@@ -9,6 +10,7 @@ }, { "BriefDescription": "Cycles a demand request was blocked due to Fill Buffers unavailability", + "Counter": "0,1,2,3", "CounterMask": "1", "EventCode": "0x48", "EventName": "L1D_PEND_MISS.FB_FULL",
@@ -18,6 +20,7 @@ }, { "BriefDescription": "L1D miss outstanding duration in cycles", + "Counter": "2", "EventCode": "0x48", "EventName": "L1D_PEND_MISS.PENDING", "PublicDescription": "Increments the number of outstanding L1D misses every cycle. Set Cmask = 1 and Edge =1 to count occurrences.",
@@ -26,6 +29,7 @@ }, { "BriefDescription": "Cycles with L1D load Misses outstanding.", + "Counter": "2", "CounterMask": "1", "EventCode": "0x48", "EventName": "L1D_PEND_MISS.PENDING_CYCLES",
@@ -35,6 +39,7 @@ { "AnyThread": "1", "BriefDescription": "Cycles with L1D load Misses outstanding from any thread on physical core", + "Counter": "2", "CounterMask": "1", "EventCode": "0x48", "EventName": "L1D_PEND_MISS.PENDING_CYCLES_ANY",
@@ -44,6 +49,7 @@ }, { "BriefDescription": "Not rejected writebacks from L1D to L2 cache lines in any state.", + "Counter": "0,1,2,3", "EventCode": "0x28", "EventName": "L2_L1D_WB_RQSTS.ALL", "SampleAfterValue": "200003",
@@ -51,6 +57,7 @@ }, { "BriefDescription": "Not rejected writebacks from L1D to L2 cache lines in E state", + "Counter": "0,1,2,3", "EventCode": "0x28", "EventName": "L2_L1D_WB_RQSTS.HIT_E", "PublicDescription": "Not rejected writebacks from L1D to L2 cache lines in E state.",
@@ -59,6 +66,7 @@ }, { "BriefDescription": "Not rejected writebacks from L1D to L2 cache lines in M state", + "Counter": "0,1,2,3", "EventCode": "0x28", "EventName": "L2_L1D_WB_RQSTS.HIT_M", "PublicDescription": "Not rejected writebacks from L1D to L2 cache lines in M state.",
@@ -67,6 +75,7 @@ }, { "BriefDescription": "Count the number of modified Lines evicted from L1 and missed L2. (Non-rejected WBs from the DCU.)", + "Counter": "0,1,2,3", "EventCode": "0x28", "EventName": "L2_L1D_WB_RQSTS.MISS", "PublicDescription": "Not rejected writebacks that missed LLC.",
@@ -75,6 +84,7 @@ }, { "BriefDescription": "L2 cache lines filling L2", + "Counter": "0,1,2,3", "EventCode": "0xF1", "EventName": "L2_LINES_IN.ALL", "PublicDescription": "L2 cache lines filling L2.",
@@ -83,6 +93,7 @@ }, { "BriefDescription": "L2 cache lines in E state filling L2", + "Counter": "0,1,2,3", "EventCode": "0xF1", "EventName": "L2_LINES_IN.E", "PublicDescription": "L2 cache lines in E state filling L2.",
@@ -91,6 +102,7 @@ }, { "BriefDescription": "L2 cache lines in I state filling L2", + "Counter": "0,1,2,3", "EventCode": "0xF1", "EventName": "L2_LINES_IN.I", "PublicDescription": "L2 cache lines in I state filling L2.",
@@ -99,6 +111,7 @@ }, { "BriefDescription": "L2 cache lines in S state filling L2", + "Counter": "0,1,2,3", "EventCode": "0xF1", "EventName": "L2_LINES_IN.S", "PublicDescription": "L2 cache lines in S state filling L2.",
@@ -107,6 +120,7 @@ }, { "BriefDescription": "Clean L2 cache lines evicted by demand", + "Counter": "0,1,2,3", "EventCode": "0xF2", "EventName": "L2_LINES_OUT.DEMAND_CLEAN", "PublicDescription": "Clean L2 cache lines evicted by demand.",
@@ -115,6 +129,7 @@ }, { "BriefDescription": "Dirty L2 cache lines evicted by demand", + "Counter": "0,1,2,3", "EventCode": "0xF2", "EventName": "L2_LINES_OUT.DEMAND_DIRTY", "PublicDescription": "Dirty L2 cache lines evicted by demand.",
@@ -123,6 +138,7 @@ }, { "BriefDescription": "Dirty L2 cache lines filling the L2", + "Counter": "0,1,2,3", "EventCode": "0xF2", "EventName": "L2_LINES_OUT.DIRTY_ALL", "PublicDescription": "Dirty L2 cache lines filling the L2.",
@@ -131,6 +147,7 @@ }, { "BriefDescription": "Clean L2 cache lines evicted by L2 prefetch", + "Counter": "0,1,2,3", "EventCode": "0xF2", "EventName": "L2_LINES_OUT.PF_CLEAN", "PublicDescription": "Clean L2 cache lines evicted by the MLC prefetcher.",
@@ -139,6 +156,7 @@ }, { "BriefDescription": "Dirty L2 cache lines evicted by L2 prefetch", + "Counter": "0,1,2,3", "EventCode": "0xF2", "EventName": "L2_LINES_OUT.PF_DIRTY", "PublicDescription": "Dirty L2 cache lines evicted by the MLC prefetcher.",
@@ -147,6 +165,7 @@ }, { "BriefDescription": "L2 code requests", + "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_RQSTS.ALL_CODE_RD", "PublicDescription": "Counts all L2 code requests.",
@@ -155,6 +174,7 @@ }, { "BriefDescription": "Demand Data Read requests", + "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_RQSTS.ALL_DEMAND_DATA_RD", "PublicDescription": "Counts any demand and L1 HW prefetch data load requests to L2.",
@@ -163,6 +183,7 @@ }, { "BriefDescription": "Requests from L2 hardware prefetchers", + "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_RQSTS.ALL_PF", "PublicDescription": "Counts all L2 HW prefetcher requests.",
@@ -171,6 +192,7 @@ }, { "BriefDescription": "RFO requests to L2 cache", + "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_RQSTS.ALL_RFO", "PublicDescription": "Counts all L2 store RFO requests.",
@@ -179,6 +201,7 @@ }, { "BriefDescription": "L2 cache hits when fetching instructions, code reads.", + "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_RQSTS.CODE_RD_HIT", "PublicDescription": "Number of instruction fetches that hit the L2 cache.",
@@ -187,6 +210,7 @@ }, { "BriefDescription": "L2 cache misses when fetching instructions", + "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_RQSTS.CODE_RD_MISS", "PublicDescription": "Number of instruction fetches that missed the L2 cache.",
@@ -195,6 +219,7 @@ }, { "BriefDescription": "Demand Data Read requests that hit L2 cache", + "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_RQSTS.DEMAND_DATA_RD_HIT", "PublicDescription": "Demand Data Read requests that hit L2 cache.",
@@ -203,6 +228,7 @@ }, { "BriefDescription": "Requests from the L2 hardware prefetchers that hit L2 cache", + "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_RQSTS.PF_HIT", "PublicDescription": "Counts all L2 HW prefetcher requests that hit L2.",
@@ -211,6 +237,7 @@ }, { "BriefDescription": "Requests from the L2 hardware prefetchers that miss L2 cache", + "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_RQSTS.PF_MISS", "PublicDescription": "Counts all L2 HW prefetcher requests that missed L2.",
@@ -219,6 +246,7 @@ }, { "BriefDescription": "RFO requests that hit L2 cache", + "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_RQSTS.RFO_HIT", "PublicDescription": "RFO requests that hit L2 cache.",
@@ -227,6 +255,7 @@ }, { "BriefDescription": "RFO requests that miss L2 cache", + "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_RQSTS.RFO_MISS", "PublicDescription": "Counts the number of store RFO requests that miss the L2 cache.",
@@ -235,6 +264,7 @@ }, { "BriefDescription": "RFOs that access cache lines in any state", + "Counter": "0,1,2,3", "EventCode": "0x27", "EventName": "L2_STORE_LOCK_RQSTS.ALL", "PublicDescription": "RFOs that access cache lines in any state.",
@@ -243,6 +273,7 @@ }, { "BriefDescription": "RFOs that hit cache lines in M state", + "Counter": "0,1,2,3", "EventCode": "0x27", "EventName": "L2_STORE_LOCK_RQSTS.HIT_M", "PublicDescription": "RFOs that hit cache lines in M state.",
@@ -251,6 +282,7 @@ }, { "BriefDescription": "RFOs that miss cache lines", + "Counter": "0,1,2,3", "EventCode": "0x27", "EventName": "L2_STORE_LOCK_RQSTS.MISS", "PublicDescription": "RFOs that miss cache lines.",
@@ -259,6 +291,7 @@ }, { "BriefDescription": "L2 or LLC HW prefetches that access L2 cache", + "Counter": "0,1,2,3", "EventCode": "0xF0", "EventName": "L2_TRANS.ALL_PF", "PublicDescription": "Any MLC or LLC HW prefetch accessing L2, including rejects.",
@@ -267,6 +300,7 @@ }, { "BriefDescription": "Transactions accessing L2 pipe", + "Counter": "0,1,2,3", "EventCode": "0xF0", "EventName": "L2_TRANS.ALL_REQUESTS", "PublicDescription": "Transactions accessing L2 pipe.",
@@ -275,6 +309,7 @@ }, { "BriefDescription": "L2 cache accesses when fetching instructions", + "Counter": "0,1,2,3", "EventCode": "0xF0", "EventName": "L2_TRANS.CODE_RD", "PublicDescription": "L2 cache accesses when fetching instructions.",
@@ -283,6 +318,7 @@ }, { "BriefDescription": "Demand Data Read requests that access L2 cache", + "Counter": "0,1,2,3", "EventCode": "0xF0", "EventName": "L2_TRANS.DEMAND_DATA_RD", "PublicDescription": "Demand Data Read requests that access L2 cache.",
@@ -291,6 +327,7 @@ }, { "BriefDescription": "L1D writebacks that access L2 cache", + "Counter": "0,1,2,3", "EventCode": "0xF0", "EventName": "L2_TRANS.L1D_WB", "PublicDescription": "L1D writebacks that access L2 cache.",
@@ -299,6 +336,7 @@ }, { "BriefDescription": "L2 fill requests that access L2 cache", + "Counter": "0,1,2,3", "EventCode": "0xF0", "EventName": "L2_TRANS.L2_FILL", "PublicDescription": "L2 fill requests that access L2 cache.",
@@ -307,6 +345,7 @@ }, { "BriefDescription": "L2 writebacks that access L2 cache", + "Counter": "0,1,2,3", "EventCode": "0xF0", "EventName": "L2_TRANS.L2_WB", "PublicDescription": "L2 writebacks that access L2 cache.",
@@ -315,6 +354,7 @@ }, { "BriefDescription": "RFO requests that access L2 cache", + "Counter": "0,1,2,3", "EventCode": "0xF0", "EventName": "L2_TRANS.RFO", "PublicDescription": "RFO requests that access L2 cache.",
@@ -323,6 +363,7 @@ }, { "BriefDescription": "Cycles when L1D is locked", + "Counter": "0,1,2,3", "EventCode": "0x63", "EventName": "LOCK_CYCLES.CACHE_LOCK_DURATION", "PublicDescription": "Cycles in which the L1D is locked.",
@@ -331,6 +372,7 @@ }, { "BriefDescription": "Core-originated cacheable demand requests missed LLC", + "Counter": "0,1,2,3", "EventCode": "0x2E", "EventName": "LONGEST_LAT_CACHE.MISS", "PublicDescription": "This event counts each cache miss condition for references to the last level cache.",
@@ -339,6 +381,7 @@ }, { "BriefDescription": "Core-originated cacheable demand requests that refer to LLC", + "Counter": "0,1,2,3", "EventCode": "0x2E", "EventName": "LONGEST_LAT_CACHE.REFERENCE", "PublicDescription": "This event counts requests originating from the core that reference a cache line in the last level cache.",
@@ -347,6 +390,7 @@ }, { "BriefDescription": "Retired load uops which data sources were LLC and cross-core snoop hits in on-pkg core cache.", + "Counter": "0,1,2,3", "EventCode": "0xD2", "EventName": "MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_HIT", "PEBS": "1",
@@ -355,6 +399,7 @@ }, { "BriefDescription": "Retired load uops which data sources were HitM responses from shared LLC.", + "Counter": "0,1,2,3", "EventCode": "0xD2", "EventName": "MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_HITM", "PEBS": "1",
@@ -363,6 +408,7 @@ }, { "BriefDescription": "Retired load uops which data sources were LLC hit and cross-core snoop missed in on-pkg core cache.", + "Counter": "0,1,2,3", "EventCode": "0xD2", "EventName": "MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_MISS", "PEBS": "1",
@@ -371,6 +417,7 @@ }, { "BriefDescription": "Retired load uops which data sources were hits in LLC without snoops required.", + "Counter": "0,1,2,3", "EventCode": "0xD2", "EventName": "MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_NONE", "PEBS": "1",
@@ -379,6 +426,7 @@ }, { "BriefDescription": "Retired load uops which data sources missed LLC but serviced from local dram.", + "Counter": "0,1,2,3", "EventCode": "0xD3", "EventName": "MEM_LOAD_UOPS_LLC_MISS_RETIRED.LOCAL_DRAM", "PublicDescription": "Retired load uops whose data source was local memory (cross-socket snoop not needed or missed).",
@@ -387,6 +435,7 @@ }, { "BriefDescription": "Retired load uops which data sources were load uops missed L1 but hit FB due to preceding miss to the same cache line with data not ready.", + "Counter": "0,1,2,3", "EventCode": "0xD1", "EventName": "MEM_LOAD_UOPS_RETIRED.HIT_LFB", "PEBS": "1",
@@ -395,6 +444,7 @@ }, { "BriefDescription": "Retired load uops with L1 cache hits as data sources.", + "Counter": "0,1,2,3", "EventCode": "0xD1", "EventName": "MEM_LOAD_UOPS_RETIRED.L1_HIT", "PEBS": "1",
@@ -403,6 +453,7 @@ }, { "BriefDescription": "Retired load uops which data sources following L1 data-cache miss.", + "Counter": "0,1,2,3", "EventCode": "0xD1", "EventName": "MEM_LOAD_UOPS_RETIRED.L1_MISS", "PEBS": "1",
@@ -411,6 +462,7 @@ }, { "BriefDescription": "Retired load uops with L2 cache hits as data sources.", + "Counter": "0,1,2,3", "EventCode": "0xD1", "EventName": "MEM_LOAD_UOPS_RETIRED.L2_HIT", "PEBS": "1",
@@ -419,6 +471,7 @@ }, { "BriefDescription": "Retired load uops with L2 cache misses as data sources.", + "Counter": "0,1,2,3", "EventCode": "0xD1", "EventName": "MEM_LOAD_UOPS_RETIRED.L2_MISS", "PEBS": "1",
@@ -427,6 +480,7 @@ }, { "BriefDescription": "Retired load uops which data sources were data hits in LLC without snoops required.", + "Counter": "0,1,2,3", "EventCode": "0xD1", "EventName": "MEM_LOAD_UOPS_RETIRED.LLC_HIT", "PEBS": "1",
@@ -435,6 +489,7 @@ }, { "BriefDescription": "Miss in last-level (L3) cache. Excludes Unknown data-source.", + "Counter": "0,1,2,3", "EventCode": "0xD1", "EventName": "MEM_LOAD_UOPS_RETIRED.LLC_MISS", "PEBS": "1",
@@ -443,6 +498,7 @@ }, { "BriefDescription": "All retired load uops. (Precise Event)", + "Counter": "0,1,2,3", "EventCode": "0xD0", "EventName": "MEM_UOPS_RETIRED.ALL_LOADS", "PEBS": "1",
@@ -451,6 +507,7 @@ }, { "BriefDescription": "All retired store uops. (Precise Event)", + "Counter": "0,1,2,3", "EventCode": "0xD0", "EventName": "MEM_UOPS_RETIRED.ALL_STORES", "PEBS": "1",
@@ -459,6 +516,7 @@ }, { "BriefDescription": "Retired load uops with locked access. (Precise Event)", + "Counter": "0,1,2,3", "EventCode": "0xD0", "EventName": "MEM_UOPS_RETIRED.LOCK_LOADS", "PEBS": "1",
@@ -467,6 +525,7 @@ }, { "BriefDescription": "Retired load uops that split across a cacheline boundary. (Precise Event)", + "Counter": "0,1,2,3", "EventCode": "0xD0", "EventName": "MEM_UOPS_RETIRED.SPLIT_LOADS", "PEBS": "1",
@@ -475,6 +534,7 @@ }, { "BriefDescription": "Retired store uops that split across a cacheline boundary. (Precise Event)", + "Counter": "0,1,2,3", "EventCode": "0xD0", "EventName": "MEM_UOPS_RETIRED.SPLIT_STORES", "PEBS": "1",
@@ -483,6 +543,7 @@ }, { "BriefDescription": "Retired load uops that miss the STLB. (Precise Event)", + "Counter": "0,1,2,3", "EventCode": "0xD0", "EventName": "MEM_UOPS_RETIRED.STLB_MISS_LOADS", "PEBS": "1",
@@ -491,6 +552,7 @@ }, { "BriefDescription": "Retired store uops that miss the STLB. (Precise Event)", + "Counter": "0,1,2,3", "EventCode": "0xD0", "EventName": "MEM_UOPS_RETIRED.STLB_MISS_STORES", "PEBS": "1",
@@ -499,6 +561,7 @@ }, { "BriefDescription": "Demand and prefetch data reads", + "Counter": "0,1,2,3", "EventCode": "0xB0", "EventName": "OFFCORE_REQUESTS.ALL_DATA_RD", "PublicDescription": "Data read requests sent to uncore (demand and prefetch).",
@@ -507,6 +570,7 @@ }, { "BriefDescription": "Cacheable and noncacheable code read requests", + "Counter": "0,1,2,3", "EventCode": "0xB0", "EventName": "OFFCORE_REQUESTS.DEMAND_CODE_RD", "PublicDescription": "Demand code read requests sent to uncore.",
@@ -515,6 +579,7 @@ }, { "BriefDescription": "Demand Data Read requests sent to uncore", + "Counter": "0,1,2,3", "EventCode": "0xB0", "EventName": "OFFCORE_REQUESTS.DEMAND_DATA_RD", "PublicDescription": "Demand data read requests sent to uncore.",
@@ -523,6 +588,7 @@ }, { "BriefDescription": "Demand RFO requests including regular RFOs, locks, ItoM", + "Counter": "0,1,2,3", "EventCode": "0xB0", "EventName": "OFFCORE_REQUESTS.DEMAND_RFO", "PublicDescription": "Demand RFO read requests sent to uncore, including regular RFOs, locks, ItoM.",
@@ -531,6 +597,7 @@ }, { "BriefDescription": "Cases when offcore requests buffer cannot take more entries for core", + "Counter": "0,1,2,3", "EventCode": "0xB2", "EventName": "OFFCORE_REQUESTS_BUFFER.SQ_FULL", "PublicDescription": "Cases when offcore requests buffer cannot take more entries for core.",
@@ -539,6 +606,7 @@ }, { "BriefDescription": "Offcore outstanding cacheable Core Data Read transactions in SuperQueue (SQ), queue to uncore", + "Counter": "0,1,2,3", "EventCode": "0x60", "EventName": "OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD", "PublicDescription": "Offcore outstanding cacheable data read transactions in SQ to uncore. Set Cmask=1 to count cycles.",
@@ -547,6 +615,7 @@ }, { "BriefDescription": "Cycles when offcore outstanding cacheable Core Data Read transactions are present in SuperQueue (SQ), queue to uncore", + "Counter": "0,1,2,3", "CounterMask": "1", "EventCode": "0x60", "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD",
@@ -556,6 +625,7 @@ }, { "BriefDescription": "Offcore outstanding code reads transactions in SuperQueue (SQ), queue to uncore, every cycle", + "Counter": "0,1,2,3", "CounterMask": "1", "EventCode": "0x60", "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_CODE_RD",
@@ -565,6 +635,7 @@ }, { "BriefDescription": "Cycles when offcore outstanding Demand Data Read transactions are present in SuperQueue (SQ), queue to uncore", + "Counter": "0,1,2,3", "CounterMask": "1", "EventCode": "0x60", "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_DATA_RD",
@@ -574,6 +645,7 @@ }, { "BriefDescription": "Offcore outstanding demand rfo reads transactions in SuperQueue (SQ), queue to uncore, every cycle", + "Counter": "0,1,2,3", "CounterMask": "1", "EventCode": "0x60", "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO",
@@ -583,6 +655,7 @@ }, { "BriefDescription": "Offcore outstanding code reads transactions in SuperQueue (SQ), queue to uncore, every cycle", + "Counter": "0,1,2,3", "EventCode": "0x60", "EventName": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_CODE_RD", "PublicDescription": "Offcore outstanding Demand Code Read transactions in SQ to uncore. Set Cmask=1 to count cycles.",
@@ -591,6 +664,7 @@ }, { "BriefDescription": "Offcore outstanding Demand Data Read transactions in uncore queue.", + "Counter": "0,1,2,3", "EventCode": "0x60", "EventName": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD", "PublicDescription": "Offcore outstanding Demand Data Read transactions in SQ to uncore. Set Cmask=1 to count cycles.",
@@ -599,6 +673,7 @@ }, { "BriefDescription": "Cycles with at least 6 offcore outstanding Demand Data Read transactions in uncore queue", + "Counter": "0,1,2,3", "CounterMask": "6", "EventCode": "0x60", "EventName": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD_GE_6",
@@ -608,6 +683,7 @@ }, { "BriefDescription": "Offcore outstanding RFO store transactions in SuperQueue (SQ), queue to uncore", + "Counter": "0,1,2,3", "EventCode": "0x60", "EventName": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_RFO", "PublicDescription": "Offcore outstanding RFO store transactions in SQ to uncore. Set Cmask=1 to count cycles.",
@@ -616,6 +692,7 @@ }, { "BriefDescription": "Counts all demand & prefetch code reads that hit in the LLC", + "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.ALL_CODE_RD.LLC_HIT.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7",
@@ -625,6 +702,7 @@ }, { "BriefDescription": "Counts demand & prefetch code reads that hit in the LLC and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores", + "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.ALL_CODE_RD.LLC_HIT.NO_SNOOP_NEEDED", "MSRIndex": "0x1a6,0x1a7",
@@ -634,6 +712,7 @@ }, { "BriefDescription": "Counts all demand & prefetch data reads", + "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7",
@@ -643,6 +722,7 @@ }, { "BriefDescription": "Counts all demand & prefetch data reads that hit in the LLC", + "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.LLC_HIT.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7",
@@ -652,6 +732,7 @@ }, { "BriefDescription": "Counts demand & prefetch data reads that hit in the LLC and the snoop to one of the sibling cores hits the line in M state and the line is forwarded", + "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.LLC_HIT.HITM_OTHER_CORE", "MSRIndex": "0x1a6,0x1a7",
@@ -661,6 +742,7 @@ }, { "BriefDescription": "Counts demand & prefetch data reads that hit in the LLC and the snoops to sibling cores hit in either E/S state and the line is not forwarded", + "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.LLC_HIT.HIT_OTHER_CORE_NO_FWD", "MSRIndex": "0x1a6,0x1a7",
@@ -670,6 +752,7 @@ }, { "BriefDescription": "Counts demand & prefetch data reads that hit in the LLC and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores", + "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.LLC_HIT.NO_SNOOP_NEEDED", "MSRIndex": "0x1a6,0x1a7",
@@ -679,6 +762,7 @@ }, { "BriefDescription": "Counts all data/code/rfo references (demand & prefetch)", + "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.ALL_READS.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7",
@@ -688,6 +772,7 @@ }, { "BriefDescription": "Counts all demand & prefetch prefetch RFOs", + "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.ALL_RFO.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7",
@@ -697,6 +782,7 @@ }, { "BriefDescription": "Counts all demand & prefetch RFOs that hit in the LLC", + "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.ALL_RFO.LLC_HIT.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7",
@@ -706,6 +792,7 @@ }, { "BriefDescription": "Counts demand & prefetch RFOs that hit in the LLC and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores", + "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.ALL_RFO.LLC_HIT.NO_SNOOP_NEEDED", "MSRIndex": "0x1a6,0x1a7",
@@ -715,6 +802,7 @@ }, { "BriefDescription": "Counts all writebacks from the core to the LLC", + "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.COREWB.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7",
@@ -724,6 +812,7 @@ }, { "BriefDescription": "Counts all demand code reads", + "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7",
@@ -733,6 +822,7 @@ }, { "BriefDescription": "Counts all demand code reads that hit in the LLC", + "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.LLC_HIT.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7",
@@ -742,6 +832,7 @@ }, { "BriefDescription": "Counts demand code reads that hit in the LLC and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores", + "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.LLC_HIT.NO_SNOOP_NEEDED", "MSRIndex": "0x1a6,0x1a7",
@@ -751,6 +842,7 @@ }, { "BriefDescription": "Counts all demand data reads", + "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7",
@@ -760,6 +852,7 @@ }, { "BriefDescription": "Counts all demand data reads that hit in the LLC", + "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.LLC_HIT.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7",
@@ -769,6 +862,7 @@ }, { "BriefDescription": "Counts demand data reads that hit in the LLC and the snoop to one of the sibling cores hits the line in M state and the line is forwarded", + "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.LLC_HIT.HITM_OTHER_CORE", "MSRIndex": "0x1a6,0x1a7",
@@ -778,6 +872,7 @@ }, { "BriefDescription": "Counts demand data reads that hit in the LLC and the snoops to sibling cores hit in either E/S state and the line is not forwarded", + "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.LLC_HIT.HIT_OTHER_CORE_NO_FWD", "MSRIndex": "0x1a6,0x1a7",
@@ -787,6 +882,7 @@ }, { "BriefDescription": "Counts demand data reads that hit in the LLC and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores", + "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.LLC_HIT.NO_SNOOP_NEEDED", "MSRIndex": "0x1a6,0x1a7",
@@ -796,6 +892,7 @@ }, { "BriefDescription": "Counts all demand rfo's", + "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7",
@@ -805,6 +902,7 @@ }, { "BriefDescription": "Counts all demand data writes (RFOs) that hit in the LLC", + "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.LLC_HIT.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7",
@@ -814,6 +912,7 @@ }, { "BriefDescription": "Counts demand data writes (RFOs) that hit in the LLC and the snoop to one of the sibling cores hits the line in M state and the line is forwarded", + "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.LLC_HIT.HITM_OTHER_CORE", "MSRIndex": "0x1a6,0x1a7",
@@ -823,6 +922,7 @@ }, { "BriefDescription": "Counts demand data writes (RFOs) that hit in the LLC and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores", + "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.LLC_HIT.NO_SNOOP_NEEDED", "MSRIndex": "0x1a6,0x1a7",
@@ -832,6 +932,7 @@ }, { "BriefDescription": "Counts miscellaneous accesses that include port i/o, MMIO and uncacheable memory accesses. It also includes L2 hints sent to LLC to keep a line from being evicted out of the core caches", + "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.OTHER.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7",
@@ -841,6 +942,7 @@ }, { "BriefDescription": "Counts requests where the address of an atomic lock instruction spans a cache line boundary or the lock instruction is executed on uncacheable address", + "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.SPLIT_LOCK_UC_LOCK.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7",
@@ -850,6 +952,7 @@ }, { "BriefDescription": "Counts non-temporal stores", + "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.STREAMING_STORES.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7",
@@ -859,6 +962,7 @@ }, { "BriefDescription": "Split locks in SQ", + "Counter": "0,1,2,3", "EventCode": "0xF4", "EventName": "SQ_MISC.SPLIT_LOCK", "SampleAfterValue": "100003",
tools/perf/pmu-events/arch/x86/ivybridge/counter.json new file +17 -0
@@ -0,0 +1,17 @@ +[ + { + "Unit": "core", + "CountersNumFixed": "3", + "CountersNumGeneric": "4" + }, + { + "Unit": "ARB", + "CountersNumFixed": "1", + "CountersNumGeneric": "2" + }, + { + "Unit": "CBOX", + "CountersNumFixed": "0", + "CountersNumGeneric": "2" + } +]
tools/perf/pmu-events/arch/x86/ivybridge/floating-point.json +17 -0
@@ -1,6 +1,7 @@ [ { "BriefDescription": "Cycles with any input/output SSE or FP assist", + "Counter": "0,1,2,3", "CounterMask": "1", "EventCode": "0xCA", "EventName": "FP_ASSIST.ANY",
@@ -10,6 +11,7 @@ }, { "BriefDescription": "Number of SIMD FP assists due to input values", + "Counter": "0,1,2,3", "EventCode": "0xCA", "EventName": "FP_ASSIST.SIMD_INPUT", "PublicDescription": "Number of SIMD FP assists due to input values.",
@@ -18,6 +20,7 @@ }, { "BriefDescription": "Number of SIMD FP assists due to Output values", + "Counter": "0,1,2,3", "EventCode": "0xCA", "EventName": "FP_ASSIST.SIMD_OUTPUT", "PublicDescription": "Number of SIMD FP assists due to output values.",
@@ -26,6 +29,7 @@ }, { "BriefDescription": "Number of X87 assists due to input value.", + "Counter": "0,1,2,3", "EventCode": "0xCA", "EventName": "FP_ASSIST.X87_INPUT", "PublicDescription": "Number of X87 FP assists due to input values.",
@@ -34,6 +38,7 @@ }, { "BriefDescription": "Number of X87 assists due to output value.", + "Counter": "0,1,2,3", "EventCode": "0xCA", "EventName": "FP_ASSIST.X87_OUTPUT", "PublicDescription": "Number of X87 FP assists due to output values.",
@@ -42,6 +47,7 @@ }, { "BriefDescription": "Number of SSE* or AVX-128 FP Computational packed double-precision uops issued this cycle", + "Counter": "0,1,2,3", "EventCode": "0x10", "EventName": "FP_COMP_OPS_EXE.SSE_PACKED_DOUBLE", "PublicDescription": "Number of SSE* or AVX-128 FP Computational packed double-precision uops issued this cycle.",
@@ -50,6 +56,7 @@ }, { "BriefDescription": "Number of SSE* or AVX-128 FP Computational packed single-precision uops issued this cycle", + "Counter": "0,1,2,3", "EventCode": "0x10", "EventName": "FP_COMP_OPS_EXE.SSE_PACKED_SINGLE", "PublicDescription": "Number of SSE* or AVX-128 FP Computational packed single-precision uops issued this cycle.",
@@ -58,6 +65,7 @@ }, { "BriefDescription": "Number of SSE* or AVX-128 FP Computational scalar double-precision uops issued this cycle", + "Counter": "0,1,2,3", "EventCode": "0x10", "EventName": "FP_COMP_OPS_EXE.SSE_SCALAR_DOUBLE", "PublicDescription": "Counts number of SSE* or AVX-128 double precision FP scalar uops executed.",
@@ -66,6 +74,7 @@ }, { "BriefDescription": "Number of SSE* or AVX-128 FP Computational scalar single-precision uops issued this cycle", + "Counter": "0,1,2,3", "EventCode": "0x10", "EventName": "FP_COMP_OPS_EXE.SSE_SCALAR_SINGLE", "PublicDescription": "Number of SSE* or AVX-128 FP Computational scalar single-precision uops issued this cycle.",
@@ -74,6 +83,7 @@ }, { "BriefDescription": "Number of FP Computational Uops Executed this cycle. The number of FADD, FSUB, FCOM, FMULs, integer MULs and IMULs, FDIVs, FPREMs, FSQRTS, integer DIVs, and IDIVs. This event does not distinguish an FADD used in the middle of a transcendental flow from a s", + "Counter": "0,1,2,3", "EventCode": "0x10", "EventName": "FP_COMP_OPS_EXE.X87", "PublicDescription": "Counts number of X87 uops executed.",
@@ -82,6 +92,7 @@ }, { "BriefDescription": "Number of SIMD Move Elimination candidate uops that were eliminated.", + "Counter": "0,1,2,3", "EventCode": "0x58", "EventName": "MOVE_ELIMINATION.SIMD_ELIMINATED", "SampleAfterValue": "1000003",
@@ -89,6 +100,7 @@ }, { "BriefDescription": "Number of SIMD Move Elimination candidate uops that were not eliminated.", + "Counter": "0,1,2,3", "EventCode": "0x58", "EventName": "MOVE_ELIMINATION.SIMD_NOT_ELIMINATED", "SampleAfterValue": "1000003",
@@ -96,6 +108,7 @@ }, { "BriefDescription": "Number of GSSE memory assist for stores. GSSE microcode assist is being invoked whenever the hardware is unable to properly handle GSSE-256b operations.", + "Counter": "0,1,2,3", "EventCode": "0xC1", "EventName": "OTHER_ASSISTS.AVX_STORE", "PublicDescription": "Number of assists associated with 256-bit AVX store operations.",
@@ -104,6 +117,7 @@ }, { "BriefDescription": "Number of transitions from AVX-256 to legacy SSE when penalty applicable.", + "Counter": "0,1,2,3", "EventCode": "0xC1", "EventName": "OTHER_ASSISTS.AVX_TO_SSE", "SampleAfterValue": "100003",
@@ -111,6 +125,7 @@ }, { "BriefDescription": "Number of transitions from SSE to AVX-256 when penalty applicable.", + "Counter": "0,1,2,3", "EventCode": "0xC1", "EventName": "OTHER_ASSISTS.SSE_TO_AVX", "SampleAfterValue": "100003",
@@ -118,6 +133,7 @@ }, { "BriefDescription": "number of AVX-256 Computational FP double precision uops issued this cycle", + "Counter": "0,1,2,3", "EventCode": "0x11", "EventName": "SIMD_FP_256.PACKED_DOUBLE", "PublicDescription": "Counts 256-bit packed double-precision floating-point instructions.",
@@ -126,6 +142,7 @@ }, { "BriefDescription": "number of GSSE-256 Computational FP single precision uops issued this cycle", + "Counter": "0,1,2,3", "EventCode": "0x11", "EventName": "SIMD_FP_256.PACKED_SINGLE", "PublicDescription": "Counts 256-bit packed single-precision floating-point instructions.",
tools/perf/pmu-events/arch/x86/ivybridge/frontend.json +30 -0
@@ -1,6 +1,7 @@ [ { "BriefDescription": "Counts the total number when the front end is resteered, mainly when the BPU cannot provide a correct prediction and this is corrected by other branch handling mechanisms at the front end.", + "Counter": "0,1,2,3", "EventCode": "0xE6", "EventName": "BACLEARS.ANY", "PublicDescription": "Number of front end re-steers due to BPU misprediction.",
@@ -9,6 +10,7 @@ }, { "BriefDescription": "Decode Stream Buffer (DSB)-to-MITE switches", + "Counter": "0,1,2,3", "EventCode": "0xAB", "EventName": "DSB2MITE_SWITCHES.COUNT", "PublicDescription": "Number of DSB to MITE switches.",
@@ -17,6 +19,7 @@ }, { "BriefDescription": "Decode Stream Buffer (DSB)-to-MITE switch true penalty cycles", + "Counter": "0,1,2,3", "EventCode": "0xAB", "EventName": "DSB2MITE_SWITCHES.PENALTY_CYCLES", "PublicDescription": "Cycles DSB to MITE switches caused delay.",
@@ -25,6 +28,7 @@ }, { "BriefDescription": "Cycles when Decode Stream Buffer (DSB) fill encounter more than 3 Decode Stream Buffer (DSB) lines", + "Counter": "0,1,2,3", "EventCode": "0xAC", "EventName": "DSB_FILL.EXCEED_DSB_LINES", "PublicDescription": "DSB Fill encountered > 3 DSB lines.",
@@ -33,6 +37,7 @@ }, { "BriefDescription": "Number of Instruction Cache, Streaming Buffer and Victim Cache Reads. both cacheable and noncacheable, including UC fetches", + "Counter": "0,1,2,3", "EventCode": "0x80", "EventName": "ICACHE.HIT", "PublicDescription": "Number of Instruction Cache, Streaming Buffer and Victim Cache Reads. both cacheable and noncacheable, including UC fetches.",
@@ -41,6 +46,7 @@ }, { "BriefDescription": "Cycles where a code-fetch stalled due to L1 instruction-cache miss or an iTLB miss", + "Counter": "0,1,2,3", "EventCode": "0x80", "EventName": "ICACHE.IFETCH_STALL", "PublicDescription": "Cycles where a code-fetch stalled due to L1 instruction-cache miss or an iTLB miss.",
@@ -49,6 +55,7 @@ }, { "BriefDescription": "Instruction cache, streaming buffer and victim cache misses", + "Counter": "0,1,2,3", "EventCode": "0x80", "EventName": "ICACHE.MISSES", "PublicDescription": "Number of Instruction Cache, Streaming Buffer and Victim Cache Misses. Includes UC accesses.",
@@ -57,6 +64,7 @@ }, { "BriefDescription": "Cycles Decode Stream Buffer (DSB) is delivering 4 Uops", + "Counter": "0,1,2,3", "CounterMask": "4", "EventCode": "0x79", "EventName": "IDQ.ALL_DSB_CYCLES_4_UOPS",
@@ -66,6 +74,7 @@ }, { "BriefDescription": "Cycles Decode Stream Buffer (DSB) is delivering any Uop", + "Counter": "0,1,2,3", "CounterMask": "1", "EventCode": "0x79", "EventName": "IDQ.ALL_DSB_CYCLES_ANY_UOPS",
@@ -75,6 +84,7 @@ }, { "BriefDescription": "Cycles MITE is delivering 4 Uops", + "Counter": "0,1,2,3", "CounterMask": "4", "EventCode": "0x79", "EventName": "IDQ.ALL_MITE_CYCLES_4_UOPS",
@@ -84,6 +94,7 @@ }, { "BriefDescription": "Cycles MITE is delivering any Uop", + "Counter": "0,1,2,3", "CounterMask": "1", "EventCode": "0x79", "EventName": "IDQ.ALL_MITE_CYCLES_ANY_UOPS",
@@ -93,6 +104,7 @@ }, { "BriefDescription": "Cycles when uops are being delivered to Instruction Decode Queue (IDQ) from Decode Stream Buffer (DSB) path", + "Counter": "0,1,2,3", "CounterMask": "1", "EventCode": "0x79", "EventName": "IDQ.DSB_CYCLES",
@@ -102,6 +114,7 @@ }, { "BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path", + "Counter": "0,1,2,3", "EventCode": "0x79", "EventName": "IDQ.DSB_UOPS", "PublicDescription": "Increment each cycle. # of uops delivered to IDQ from DSB path. Set Cmask = 1 to count cycles.",
@@ -110,6 +123,7 @@ }, { "BriefDescription": "Instruction Decode Queue (IDQ) empty cycles", + "Counter": "0,1,2,3", "EventCode": "0x79", "EventName": "IDQ.EMPTY", "PublicDescription": "Counts cycles the IDQ is empty.",
@@ -118,6 +132,7 @@ }, { "BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) from MITE path", + "Counter": "0,1,2,3", "EventCode": "0x79", "EventName": "IDQ.MITE_ALL_UOPS", "PublicDescription": "Number of uops delivered to IDQ from any path.",
@@ -126,6 +141,7 @@ }, { "BriefDescription": "Cycles when uops are being delivered to Instruction Decode Queue (IDQ) from MITE path", + "Counter": "0,1,2,3", "CounterMask": "1", "EventCode": "0x79", "EventName": "IDQ.MITE_CYCLES",
@@ -135,6 +151,7 @@ }, { "BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) from MITE path", + "Counter": "0,1,2,3", "EventCode": "0x79", "EventName": "IDQ.MITE_UOPS", "PublicDescription": "Increment each cycle # of uops delivered to IDQ from MITE path. Set Cmask = 1 to count cycles.",
@@ -143,6 +160,7 @@ }, { "BriefDescription": "Cycles when uops are being delivered to Instruction Decode Queue (IDQ) while Microcode Sequencer (MS) is busy", + "Counter": "0,1,2,3", "CounterMask": "1", "EventCode": "0x79", "EventName": "IDQ.MS_CYCLES",
@@ -152,6 +170,7 @@ }, { "BriefDescription": "Cycles when uops initiated by Decode Stream Buffer (DSB) are being delivered to Instruction Decode Queue (IDQ) while Microcode Sequencer (MS) is busy", + "Counter": "0,1,2,3", "CounterMask": "1", "EventCode": "0x79", "EventName": "IDQ.MS_DSB_CYCLES",
@@ -161,6 +180,7 @@ }, { "BriefDescription": "Deliveries to Instruction Decode Queue (IDQ) initiated by Decode Stream Buffer (DSB) while Microcode Sequencer (MS) is busy", + "Counter": "0,1,2,3", "CounterMask": "1", "EdgeDetect": "1", "EventCode": "0x79",
@@ -171,6 +191,7 @@ }, { "BriefDescription": "Uops initiated by Decode Stream Buffer (DSB) that are being delivered to Instruction Decode Queue (IDQ) while Microcode Sequencer (MS) is busy", + "Counter": "0,1,2,3", "EventCode": "0x79", "EventName": "IDQ.MS_DSB_UOPS", "PublicDescription": "Increment each cycle # of uops delivered to IDQ when MS_busy by DSB. Set Cmask = 1 to count cycles. Add Edge=1 to count # of delivery.",
@@ -179,6 +200,7 @@ }, { "BriefDescription": "Uops initiated by MITE and delivered to Instruction Decode Queue (IDQ) while Microcode Sequencer (MS) is busy", + "Counter": "0,1,2,3", "EventCode": "0x79", "EventName": "IDQ.MS_MITE_UOPS", "PublicDescription": "Increment each cycle # of uops delivered to IDQ when MS_busy by MITE. Set Cmask = 1 to count cycles.",
@@ -187,6 +209,7 @@ }, { "BriefDescription": "Number of switches from DSB (Decode Stream Buffer) or MITE (legacy decode pipeline) to the Microcode Sequencer", + "Counter": "0,1,2,3", "CounterMask": "1", "EdgeDetect": "1", "EventCode": "0x79",
@@ -197,6 +220,7 @@ }, { "BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) while Microcode Sequencer (MS) is busy", + "Counter": "0,1,2,3", "EventCode": "0x79", "EventName": "IDQ.MS_UOPS", "PublicDescription": "Increment each cycle # of uops delivered to IDQ from MS by either DSB or MITE. Set Cmask = 1 to count cycles.",
@@ -205,6 +229,7 @@ }, { "BriefDescription": "Uops not delivered to Resource Allocation Table (RAT) per thread when backend of the machine is not stalled", + "Counter": "0,1,2,3", "EventCode": "0x9C", "EventName": "IDQ_UOPS_NOT_DELIVERED.CORE", "PublicDescription": "Count issue pipeline slots where no uop was delivered from the front end to the back end when there is no back-end stall.",
@@ -213,6 +238,7 @@ }, { "BriefDescription": "Cycles per thread when 4 or more uops are not delivered to Resource Allocation Table (RAT) when backend of the machine is not stalled.", + "Counter": "0,1,2,3", "CounterMask": "4", "EventCode": "0x9C", "EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE",
@@ -221,6 +247,7 @@ }, { "BriefDescription": "Counts cycles FE delivered 4 uops or Resource Allocation Table (RAT) was stalling FE.", + "Counter": "0,1,2,3", "CounterMask": "1", "EventCode": "0x9C", "EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_FE_WAS_OK",
@@ -230,6 +257,7 @@ }, { "BriefDescription": "Cycles per thread when 3 or more uops are not delivered to Resource Allocation Table (RAT) when backend of the machine is not stalled.", + "Counter": "0,1,2,3", "CounterMask": "3", "EventCode": "0x9C", "EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_LE_1_UOP_DELIV.CORE",
@@ -238,6 +266,7 @@ }, { "BriefDescription": "Cycles with less than 2 uops delivered by the front end.", + "Counter": "0,1,2,3", "CounterMask": "2", "EventCode": "0x9C", "EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_LE_2_UOP_DELIV.CORE",
@@ -246,6 +275,7 @@ }, { "BriefDescription": "Cycles with less than 3 uops delivered by the front end.", + "Counter": "0,1,2,3", "CounterMask": "1", "EventCode": "0x9C", "EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_LE_3_UOP_DELIV.CORE",
tools/perf/pmu-events/arch/x86/ivybridge/ivb-metrics.json +37 -31
251 lines not on this page · raw message
tools/perf/pmu-events/arch/x86/ivybridge/memory.json +19 -0
@@ -1,6 +1,7 @@ [ { "BriefDescription": "Counts the number of machine clears due to memory order conflicts.", + "Counter": "0,1,2,3", "EventCode": "0xC3", "EventName": "MACHINE_CLEARS.MEMORY_ORDERING", "SampleAfterValue": "100003",
@@ -8,6 +9,7 @@ }, { "BriefDescription": "Loads with latency value being above 128", + "Counter": "3", "EventCode": "0xCD", "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_128", "MSRIndex": "0x3F6",
@@ -19,6 +21,7 @@ }, { "BriefDescription": "Loads with latency value being above 16", + "Counter": "3", "EventCode": "0xCD", "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_16", "MSRIndex": "0x3F6",
@@ -30,6 +33,7 @@ }, { "BriefDescription": "Loads with latency value being above 256", + "Counter": "3", "EventCode": "0xCD", "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_256", "MSRIndex": "0x3F6",
@@ -41,6 +45,7 @@ }, { "BriefDescription": "Loads with latency value being above 32", + "Counter": "3", "EventCode": "0xCD", "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_32", "MSRIndex": "0x3F6",
@@ -52,6 +57,7 @@ }, { "BriefDescription": "Loads with latency value being above 4", + "Counter": "3", "EventCode": "0xCD", "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_4", "MSRIndex": "0x3F6",
@@ -63,6 +69,7 @@ }, { "BriefDescription": "Loads with latency value being above 512", + "Counter": "3", "EventCode": "0xCD", "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_512", "MSRIndex": "0x3F6",
@@ -74,6 +81,7 @@ }, { "BriefDescription": "Loads with latency value being above 64", + "Counter": "3", "EventCode": "0xCD", "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_64", "MSRIndex": "0x3F6",
@@ -85,6 +93,7 @@ }, { "BriefDescription": "Loads with latency value being above 8", + "Counter": "3", "EventCode": "0xCD", "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_8", "MSRIndex": "0x3F6",
@@ -96,6 +105,7 @@ }, { "BriefDescription": "Sample stores and collect precise store operation via PEBS record. PMC3 only.", + "Counter": "3", "EventCode": "0xCD", "EventName": "MEM_TRANS_RETIRED.PRECISE_STORE", "PEBS": "2",
@@ -104,6 +114,7 @@ }, { "BriefDescription": "Speculative cache line split load uops dispatched to L1 cache", + "Counter": "0,1,2,3", "EventCode": "0x05", "EventName": "MISALIGN_MEM_REF.LOADS", "PublicDescription": "Speculative cache-line split load uops dispatched to L1D.",
@@ -112,6 +123,7 @@ }, { "BriefDescription": "Speculative cache line split STA uops dispatched to L1 cache", + "Counter": "0,1,2,3", "EventCode": "0x05", "EventName": "MISALIGN_MEM_REF.STORES", "PublicDescription": "Speculative cache-line split Store-address uops dispatched to L1D.",
@@ -120,6 +132,7 @@ }, { "BriefDescription": "Counts all demand & prefetch code reads that miss the LLC and the data returned from dram", + "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.ALL_CODE_RD.LLC_MISS.DRAM", "MSRIndex": "0x1a6,0x1a7",
@@ -129,6 +142,7 @@ }, { "BriefDescription": "Counts all demand & prefetch data reads that miss the LLC and the data returned from dram", + "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.LLC_MISS.DRAM", "MSRIndex": "0x1a6,0x1a7",
@@ -138,6 +152,7 @@ }, { "BriefDescription": "Counts all data/code/rfo reads (demand & prefetch) that miss the LLC and the data returned from dram", + "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.ALL_READS.LLC_MISS.DRAM", "MSRIndex": "0x1a6,0x1a7",
@@ -147,6 +162,7 @@ }, { "BriefDescription": "Counts LLC replacements", + "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.DATA_IN_SOCKET.LLC_MISS.LOCAL_DRAM", "MSRIndex": "0x1a6,0x1a7",
@@ -156,6 +172,7 @@ }, { "BriefDescription": "Counts demand code reads that miss the LLC and the data returned from dram", + "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.LLC_MISS.DRAM", "MSRIndex": "0x1a6,0x1a7",
@@ -165,6 +182,7 @@ }, { "BriefDescription": "Counts demand data reads that miss the LLC and the data returned from dram", + "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.LLC_MISS.DRAM", "MSRIndex": "0x1a6,0x1a7",
@@ -174,6 +192,7 @@ }, { "BriefDescription": "Number of any page walk that had a miss in LLC.", + "Counter": "0,1,2,3", "EventCode": "0xBE", "EventName": "PAGE_WALKS.LLC_MISS", "SampleAfterValue": "100003",
tools/perf/pmu-events/arch/x86/ivybridge/metricgroups.json +11 -0
@@ -5,7 +5,18 @@ "BigFootprint": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", "BrMispredicts": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", "Branches": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "BvBC": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "BvCB": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "BvFB": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "BvIO": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "BvML": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "BvMP": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "BvMS": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "BvMT": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "BvOB": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "BvUW": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", "CacheHits": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "CacheMisses": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", "Compute": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", "Cor": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", "DSB": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
tools/perf/pmu-events/arch/x86/ivybridge/other.json +4 -0
@@ -1,6 +1,7 @@ [ { "BriefDescription": "Unhalted core cycles when the thread is in ring 0", + "Counter": "0,1,2,3", "EventCode": "0x5C", "EventName": "CPL_CYCLES.RING0", "PublicDescription": "Unhalted core cycles when the thread is in ring 0.",
@@ -9,6 +10,7 @@ }, { "BriefDescription": "Number of intervals between processor halts while thread is in ring 0", + "Counter": "0,1,2,3", "CounterMask": "1", "EdgeDetect": "1", "EventCode": "0x5C",
@@ -19,6 +21,7 @@ }, { "BriefDescription": "Unhalted core cycles when thread is in rings 1, 2, or 3", + "Counter": "0,1,2,3", "EventCode": "0x5C", "EventName": "CPL_CYCLES.RING123", "PublicDescription": "Unhalted core cycles when the thread is not in ring 0.",
@@ -27,6 +30,7 @@ }, { "BriefDescription": "Cycles when L1 and L2 are locked due to UC or split lock", + "Counter": "0,1,2,3", "EventCode": "0x63", "EventName": "LOCK_CYCLES.SPLIT_LOCK_UC_LOCK_DURATION", "PublicDescription": "Cycles in which the L1D and L2 are locked, due to a UC lock or split lock.",
tools/perf/pmu-events/arch/x86/ivybridge/pipeline.json +126 -0
882 lines not on this page · raw message
tools/perf/pmu-events/arch/x86/ivybridge/uncore-cache.json +25 -0
@@ -1,6 +1,7 @@ [ { "BriefDescription": "L3 Lookup any request that access cache and found line in E or S-state.", + "Counter": "0,1", "EventCode": "0x34", "EventName": "UNC_CBO_CACHE_LOOKUP.ANY_ES", "PerPkg": "1",
@@ -9,6 +10,7 @@ }, { "BriefDescription": "L3 Lookup any request that access cache and found line in I-state.", + "Counter": "0,1", "EventCode": "0x34", "EventName": "UNC_CBO_CACHE_LOOKUP.ANY_I", "PerPkg": "1",
@@ -17,6 +19,7 @@ }, { "BriefDescription": "L3 Lookup any request that access cache and found line in M-state.", + "Counter": "0,1", "EventCode": "0x34", "EventName": "UNC_CBO_CACHE_LOOKUP.ANY_M", "PerPkg": "1",
@@ -25,6 +28,7 @@ }, { "BriefDescription": "L3 Lookup any request that access cache and found line in MESI-state.", + "Counter": "0,1", "EventCode": "0x34", "EventName": "UNC_CBO_CACHE_LOOKUP.ANY_MESI", "PerPkg": "1",
@@ -33,6 +37,7 @@ }, { "BriefDescription": "L3 Lookup external snoop request that access cache and found line in E or S-state.", + "Counter": "0,1", "EventCode": "0x34", "EventName": "UNC_CBO_CACHE_LOOKUP.EXTSNP_ES", "PerPkg": "1",
@@ -41,6 +46,7 @@ }, { "BriefDescription": "L3 Lookup external snoop request that access cache and found line in I-state.", + "Counter": "0,1", "EventCode": "0x34", "EventName": "UNC_CBO_CACHE_LOOKUP.EXTSNP_I", "PerPkg": "1",
@@ -49,6 +55,7 @@ }, { "BriefDescription": "L3 Lookup external snoop request that access cache and found line in M-state.", + "Counter": "0,1", "EventCode": "0x34", "EventName": "UNC_CBO_CACHE_LOOKUP.EXTSNP_M", "PerPkg": "1",
@@ -57,6 +64,7 @@ }, { "BriefDescription": "L3 Lookup external snoop request that access cache and found line in MESI-state.", + "Counter": "0,1", "EventCode": "0x34", "EventName": "UNC_CBO_CACHE_LOOKUP.EXTSNP_MESI", "PerPkg": "1",
@@ -65,6 +73,7 @@ }, { "BriefDescription": "L3 Lookup read request that access cache and found line in E or S-state.", + "Counter": "0,1", "EventCode": "0x34", "EventName": "UNC_CBO_CACHE_LOOKUP.READ_ES", "PerPkg": "1",
@@ -73,6 +82,7 @@ }, { "BriefDescription": "L3 Lookup read request that access cache and found line in I-state.", + "Counter": "0,1", "EventCode": "0x34", "EventName": "UNC_CBO_CACHE_LOOKUP.READ_I", "PerPkg": "1",
@@ -81,6 +91,7 @@ }, { "BriefDescription": "L3 Lookup read request that access cache and found line in M-state.", + "Counter": "0,1", "EventCode": "0x34", "EventName": "UNC_CBO_CACHE_LOOKUP.READ_M", "PerPkg": "1",
@@ -89,6 +100,7 @@ }, { "BriefDescription": "L3 Lookup read request that access cache and found line in any MESI-state.", + "Counter": "0,1", "EventCode": "0x34", "EventName": "UNC_CBO_CACHE_LOOKUP.READ_MESI", "PerPkg": "1",
@@ -97,6 +109,7 @@ }, { "BriefDescription": "L3 Lookup write request that access cache and found line in E or S-state.", + "Counter": "0,1", "EventCode": "0x34", "EventName": "UNC_CBO_CACHE_LOOKUP.WRITE_ES", "PerPkg": "1",
@@ -105,6 +118,7 @@ }, { "BriefDescription": "L3 Lookup write request that access cache and found line in I-state.", + "Counter": "0,1", "EventCode": "0x34", "EventName": "UNC_CBO_CACHE_LOOKUP.WRITE_I", "PerPkg": "1",
@@ -113,6 +127,7 @@ }, { "BriefDescription": "L3 Lookup write request that access cache and found line in M-state.", + "Counter": "0,1", "EventCode": "0x34", "EventName": "UNC_CBO_CACHE_LOOKUP.WRITE_M", "PerPkg": "1",
@@ -121,6 +136,7 @@ }, { "BriefDescription": "L3 Lookup write request that access cache and found line in MESI-state.", + "Counter": "0,1", "EventCode": "0x34", "EventName": "UNC_CBO_CACHE_LOOKUP.WRITE_MESI", "PerPkg": "1",
@@ -129,6 +145,7 @@ }, { "BriefDescription": "A cross-core snoop resulted from L3 Eviction which hits a modified line in some processor core.", + "Counter": "0,1", "EventCode": "0x22", "EventName": "UNC_CBO_XSNP_RESPONSE.HITM_EVICTION", "PerPkg": "1",
@@ -137,6 +154,7 @@ }, { "BriefDescription": "An external snoop hits a modified line in some processor core.", + "Counter": "0,1", "EventCode": "0x22", "EventName": "UNC_CBO_XSNP_RESPONSE.HITM_EXTERNAL", "PerPkg": "1",
@@ -145,6 +163,7 @@ }, { "BriefDescription": "A cross-core snoop initiated by this Cbox due to processor core memory request which hits a modified line in some processor core.", + "Counter": "0,1", "EventCode": "0x22", "EventName": "UNC_CBO_XSNP_RESPONSE.HITM_XCORE", "PerPkg": "1",
@@ -153,6 +172,7 @@ }, { "BriefDescription": "A cross-core snoop resulted from L3 Eviction which hits a non-modified line in some processor core.", + "Counter": "0,1", "EventCode": "0x22", "EventName": "UNC_CBO_XSNP_RESPONSE.HIT_EVICTION", "PerPkg": "1",
@@ -161,6 +181,7 @@ }, { "BriefDescription": "An external snoop hits a non-modified line in some processor core.", + "Counter": "0,1", "EventCode": "0x22", "EventName": "UNC_CBO_XSNP_RESPONSE.HIT_EXTERNAL", "PerPkg": "1",
@@ -169,6 +190,7 @@ }, { "BriefDescription": "A cross-core snoop initiated by this Cbox due to processor core memory request which hits a non-modified line in some processor core.", + "Counter": "0,1", "EventCode": "0x22", "EventName": "UNC_CBO_XSNP_RESPONSE.HIT_XCORE", "PerPkg": "1",
@@ -177,6 +199,7 @@ }, { "BriefDescription": "A cross-core snoop resulted from L3 Eviction which misses in some processor core.", + "Counter": "0,1", "EventCode": "0x22", "EventName": "UNC_CBO_XSNP_RESPONSE.MISS_EVICTION", "PerPkg": "1",
@@ -185,6 +208,7 @@ }, { "BriefDescription": "An external snoop misses in some processor core.", + "Counter": "0,1", "EventCode": "0x22", "EventName": "UNC_CBO_XSNP_RESPONSE.MISS_EXTERNAL", "PerPkg": "1",
@@ -193,6 +217,7 @@ }, { "BriefDescription": "A cross-core snoop initiated by this Cbox due to processor core memory request which misses in some processor core.", + "Counter": "0,1", "EventCode": "0x22", "EventName": "UNC_CBO_XSNP_RESPONSE.MISS_XCORE", "PerPkg": "1",
tools/perf/pmu-events/arch/x86/ivybridge/uncore-interconnect.json +9 -0
@@ -1,6 +1,7 @@ [ { "BriefDescription": "Cycles weighted by number of requests pending in Coherency Tracker.", + "Counter": "0", "EventCode": "0x83", "EventName": "UNC_ARB_COH_TRK_OCCUPANCY.ALL", "PerPkg": "1",
@@ -9,6 +10,7 @@ }, { "BriefDescription": "Number of requests allocated in Coherency Tracker.", + "Counter": "0,1", "EventCode": "0x84", "EventName": "UNC_ARB_COH_TRK_REQUESTS.ALL", "PerPkg": "1",
@@ -17,6 +19,7 @@ }, { "BriefDescription": "Counts cycles weighted by the number of requests waiting for data returning from the memory controller. Accounts for coherent and non-coherent requests initiated by IA cores, processor graphic units, or LLC.", + "Counter": "0", "EventCode": "0x80", "EventName": "UNC_ARB_TRK_OCCUPANCY.ALL", "PerPkg": "1",
@@ -25,6 +28,7 @@ }, { "BriefDescription": "Cycles with at least half of the requests outstanding are waiting for data return from memory controller. Account for coherent and non-coherent requests initiated by IA Cores, Processor Graphics Unit, or LLC.", + "Counter": "0,1", "CounterMask": "10", "EventCode": "0x80", "EventName": "UNC_ARB_TRK_OCCUPANCY.CYCLES_OVER_HALF_FULL",
@@ -34,6 +38,7 @@ }, { "BriefDescription": "Cycles with at least one request outstanding is waiting for data return from memory controller. Account for coherent and non-coherent requests initiated by IA Cores, Processor Graphics Unit, or LLC.", + "Counter": "0,1", "CounterMask": "1", "EventCode": "0x80", "EventName": "UNC_ARB_TRK_OCCUPANCY.CYCLES_WITH_ANY_REQUEST",
@@ -43,6 +48,7 @@ }, { "BriefDescription": "Counts the number of coherent and in-coherent requests initiated by IA cores, processor graphic units, or LLC.", + "Counter": "0,1", "EventCode": "0x81", "EventName": "UNC_ARB_TRK_REQUESTS.ALL", "PerPkg": "1",
@@ -51,6 +57,7 @@ }, { "BriefDescription": "Counts the number of LLC evictions allocated.", + "Counter": "0,1", "EventCode": "0x81", "EventName": "UNC_ARB_TRK_REQUESTS.EVICTIONS", "PerPkg": "1",
@@ -59,6 +66,7 @@ }, { "BriefDescription": "Counts the number of allocated write entries, include full, partial, and LLC evictions.", + "Counter": "0,1", "EventCode": "0x81", "EventName": "UNC_ARB_TRK_REQUESTS.WRITES", "PerPkg": "1",
@@ -67,6 +75,7 @@ }, { "BriefDescription": "This 48-bit fixed counter counts the UCLK cycles.", + "Counter": "Fixed", "EventCode": "0xff", "EventName": "UNC_CLOCK.SOCKET", "PerPkg": "1",
tools/perf/pmu-events/arch/x86/ivybridge/virtual-memory.json +18 -0
@@ -1,6 +1,7 @@ [ { "BriefDescription": "Page walk for a large page completed for Demand load.", + "Counter": "0,1,2,3", "EventCode": "0x08", "EventName": "DTLB_LOAD_MISSES.LARGE_PAGE_WALK_COMPLETED", "SampleAfterValue": "100003",
@@ -8,6 +9,7 @@ }, { "BriefDescription": "Demand load Miss in all translation lookaside buffer (TLB) levels causes an page walk of any page size.", + "Counter": "0,1,2,3", "EventCode": "0x08", "EventName": "DTLB_LOAD_MISSES.MISS_CAUSES_A_WALK", "PublicDescription": "Misses in all TLB levels that cause a page walk of any page size from demand loads.",
@@ -16,6 +18,7 @@ }, { "BriefDescription": "Load operations that miss the first DTLB level but hit the second and do not cause page walks", + "Counter": "0,1,2,3", "EventCode": "0x5F", "EventName": "DTLB_LOAD_MISSES.STLB_HIT", "PublicDescription": "Counts load operations that missed 1st level DTLB but hit the 2nd level.",
@@ -24,6 +27,7 @@ }, { "BriefDescription": "Demand load Miss in all translation lookaside buffer (TLB) levels causes a page walk that completes of any page size.", + "Counter": "0,1,2,3", "EventCode": "0x08", "EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED", "PublicDescription": "Misses in all TLB levels that caused page walk completed of any size by demand loads.",
@@ -32,6 +36,7 @@ }, { "BriefDescription": "Demand load cycles page miss handler (PMH) is busy with this walk.", + "Counter": "0,1,2,3", "EventCode": "0x08", "EventName": "DTLB_LOAD_MISSES.WALK_DURATION", "PublicDescription": "Cycle PMH is busy with a walk due to demand loads.",
@@ -40,6 +45,7 @@ }, { "BriefDescription": "Store misses in all DTLB levels that cause page walks", + "Counter": "0,1,2,3", "EventCode": "0x49", "EventName": "DTLB_STORE_MISSES.MISS_CAUSES_A_WALK", "PublicDescription": "Miss in all TLB levels causes a page walk of any page size (4K/2M/4M/1G).",
@@ -48,6 +54,7 @@ }, { "BriefDescription": "Store operations that miss the first TLB level but hit the second and do not cause page walks", + "Counter": "0,1,2,3", "EventCode": "0x49", "EventName": "DTLB_STORE_MISSES.STLB_HIT", "PublicDescription": "Store operations that miss the first TLB level but hit the second and do not cause page walks.",
@@ -56,6 +63,7 @@ }, { "BriefDescription": "Store misses in all DTLB levels that cause completed page walks", + "Counter": "0,1,2,3", "EventCode": "0x49", "EventName": "DTLB_STORE_MISSES.WALK_COMPLETED", "PublicDescription": "Miss in all TLB levels causes a page walk that completes of any page size (4K/2M/4M/1G).",
@@ -64,6 +72,7 @@ }, { "BriefDescription": "Cycles when PMH is busy with page walks", + "Counter": "0,1,2,3", "EventCode": "0x49", "EventName": "DTLB_STORE_MISSES.WALK_DURATION", "PublicDescription": "Cycles PMH is busy with this walk.",
@@ -72,6 +81,7 @@ }, { "BriefDescription": "Cycle count for an Extended Page table walk. The Extended Page Directory cache is used by Virtual Machine operating systems while the guest operating systems use the standard TLB caches.", + "Counter": "0,1,2,3", "EventCode": "0x4F", "EventName": "EPT.WALK_CYCLES", "SampleAfterValue": "2000003",
@@ -79,6 +89,7 @@ }, { "BriefDescription": "Flushing of the Instruction TLB (ITLB) pages, includes 4k/2M/4M pages.", + "Counter": "0,1,2,3", "EventCode": "0xAE", "EventName": "ITLB.ITLB_FLUSH", "PublicDescription": "Counts the number of ITLB flushes, includes 4k/2M/4M pages.",
@@ -87,6 +98,7 @@ }, { "BriefDescription": "Completed page walks in ITLB due to STLB load misses for large pages", + "Counter": "0,1,2,3", "EventCode": "0x85", "EventName": "ITLB_MISSES.LARGE_PAGE_WALK_COMPLETED", "PublicDescription": "Completed page walks in ITLB due to STLB load misses for large pages.",
@@ -95,6 +107,7 @@ }, { "BriefDescription": "Misses at all ITLB levels that cause page walks", + "Counter": "0,1,2,3", "EventCode": "0x85", "EventName": "ITLB_MISSES.MISS_CAUSES_A_WALK", "PublicDescription": "Misses in all ITLB levels that cause page walks.",
@@ -103,6 +116,7 @@ }, { "BriefDescription": "Operations that miss the first ITLB level but hit the second and do not cause any page walks", + "Counter": "0,1,2,3", "EventCode": "0x85", "EventName": "ITLB_MISSES.STLB_HIT", "PublicDescription": "Number of cache load STLB hits. No page walk.",
@@ -111,6 +125,7 @@ }, { "BriefDescription": "Misses in all ITLB levels that cause completed page walks", + "Counter": "0,1,2,3", "EventCode": "0x85", "EventName": "ITLB_MISSES.WALK_COMPLETED", "PublicDescription": "Misses in all ITLB levels that cause completed page walks.",
@@ -119,6 +134,7 @@ }, { "BriefDescription": "Cycles when PMH is busy with page walks", + "Counter": "0,1,2,3", "EventCode": "0x85", "EventName": "ITLB_MISSES.WALK_DURATION", "PublicDescription": "Cycle PMH is busy with a walk.",
@@ -127,6 +143,7 @@ }, { "BriefDescription": "DTLB flush attempts of the thread-specific entries", + "Counter": "0,1,2,3", "EventCode": "0xBD", "EventName": "TLB_FLUSH.DTLB_THREAD", "PublicDescription": "DTLB flush attempts of the thread-specific entries.",
@@ -135,6 +152,7 @@ }, { "BriefDescription": "STLB flush attempts", + "Counter": "0,1,2,3", "EventCode": "0xBD", "EventName": "TLB_FLUSH.STLB_ANY", "PublicDescription": "Count number of STLB flush attempts.",
Signature · 1 line
2.45.2.627.g7a2c4fd464-goog
Ian Rogers
reviewerPATCH v2 19/37 perf vendor events: Update ivytown metrics add event counter information
In reply to Ian RogersAdd counter information necessary for optimizing event grouping the perf tool.
The most recent RFC patch set using this information:
https://lore.kernel.org/lkml/[email protected]/
The information was added in:
https://github.com/intel/perfmon/commit/475892a9690cb048949e593fe39cee65cd4765e1
and later patches.
The TMA 4.8 information was updated in:
https://github.com/intel/perfmon/commit/59194d4d90ca50a3fcb2de0d82b9f6fc0c9a5736
--- .../pmu-events/arch/x86/ivytown/cache.json | 118 ++++++ .../pmu-events/arch/x86/ivytown/counter.json | 52 +++ .../arch/x86/ivytown/floating-point.json | 17 + .../pmu-events/arch/x86/ivytown/frontend.json | 30 ++ .../arch/x86/ivytown/ivt-metrics.json | 68 ++-- .../pmu-events/arch/x86/ivytown/memory.json | 41 ++ .../arch/x86/ivytown/metricgroups.json | 11 + .../pmu-events/arch/x86/ivytown/other.json | 4 + .../pmu-events/arch/x86/ivytown/pipeline.json | 126 ++++++ .../arch/x86/ivytown/uncore-cache.json | 349 ++++++++++++++++ .../arch/x86/ivytown/uncore-interconnect.json | 385 ++++++++++++++++++ .../arch/x86/ivytown/uncore-io.json | 61 +++ .../arch/x86/ivytown/uncore-memory.json | 198 +++++++++ .../arch/x86/ivytown/uncore-power.json | 74 ++++ .../arch/x86/ivytown/virtual-memory.json | 20 + 15 files changed, 1523 insertions(+), 31 deletions(-) create mode 100644 tools/perf/pmu-events/arch/x86/ivytown/counter.json
tools/perf/pmu-events/arch/x86/ivytown/cache.json +118 -0
@@ -1,6 +1,7 @@ [ { "BriefDescription": "L1D data line replacements", + "Counter": "0,1,2,3", "EventCode": "0x51", "EventName": "L1D.REPLACEMENT", "PublicDescription": "Counts the number of lines brought into the L1 data cache.",
@@ -9,6 +10,7 @@ }, { "BriefDescription": "Cycles a demand request was blocked due to Fill Buffers unavailability", + "Counter": "0,1,2,3", "CounterMask": "1", "EventCode": "0x48", "EventName": "L1D_PEND_MISS.FB_FULL",
@@ -18,6 +20,7 @@ }, { "BriefDescription": "L1D miss outstanding duration in cycles", + "Counter": "2", "EventCode": "0x48", "EventName": "L1D_PEND_MISS.PENDING", "PublicDescription": "Increments the number of outstanding L1D misses every cycle. Set Cmask = 1 and Edge =1 to count occurrences.",
@@ -26,6 +29,7 @@ }, { "BriefDescription": "Cycles with L1D load Misses outstanding.", + "Counter": "2", "CounterMask": "1", "EventCode": "0x48", "EventName": "L1D_PEND_MISS.PENDING_CYCLES",
@@ -35,6 +39,7 @@ { "AnyThread": "1", "BriefDescription": "Cycles with L1D load Misses outstanding from any thread on physical core", + "Counter": "2", "CounterMask": "1", "EventCode": "0x48", "EventName": "L1D_PEND_MISS.PENDING_CYCLES_ANY",
@@ -44,6 +49,7 @@ }, { "BriefDescription": "Not rejected writebacks from L1D to L2 cache lines in any state.", + "Counter": "0,1,2,3", "EventCode": "0x28", "EventName": "L2_L1D_WB_RQSTS.ALL", "SampleAfterValue": "200003",
@@ -51,6 +57,7 @@ }, { "BriefDescription": "Not rejected writebacks from L1D to L2 cache lines in E state", + "Counter": "0,1,2,3", "EventCode": "0x28", "EventName": "L2_L1D_WB_RQSTS.HIT_E", "PublicDescription": "Not rejected writebacks from L1D to L2 cache lines in E state.",
@@ -59,6 +66,7 @@ }, { "BriefDescription": "Not rejected writebacks from L1D to L2 cache lines in M state", + "Counter": "0,1,2,3", "EventCode": "0x28", "EventName": "L2_L1D_WB_RQSTS.HIT_M", "PublicDescription": "Not rejected writebacks from L1D to L2 cache lines in M state.",
@@ -67,6 +75,7 @@ }, { "BriefDescription": "Count the number of modified Lines evicted from L1 and missed L2. (Non-rejected WBs from the DCU.)", + "Counter": "0,1,2,3", "EventCode": "0x28", "EventName": "L2_L1D_WB_RQSTS.MISS", "PublicDescription": "Not rejected writebacks that missed LLC.",
@@ -75,6 +84,7 @@ }, { "BriefDescription": "L2 cache lines filling L2", + "Counter": "0,1,2,3", "EventCode": "0xF1", "EventName": "L2_LINES_IN.ALL", "PublicDescription": "L2 cache lines filling L2.",
@@ -83,6 +93,7 @@ }, { "BriefDescription": "L2 cache lines in E state filling L2", + "Counter": "0,1,2,3", "EventCode": "0xF1", "EventName": "L2_LINES_IN.E", "PublicDescription": "L2 cache lines in E state filling L2.",
@@ -91,6 +102,7 @@ }, { "BriefDescription": "L2 cache lines in I state filling L2", + "Counter": "0,1,2,3", "EventCode": "0xF1", "EventName": "L2_LINES_IN.I", "PublicDescription": "L2 cache lines in I state filling L2.",
@@ -99,6 +111,7 @@ }, { "BriefDescription": "L2 cache lines in S state filling L2", + "Counter": "0,1,2,3", "EventCode": "0xF1", "EventName": "L2_LINES_IN.S", "PublicDescription": "L2 cache lines in S state filling L2.",
@@ -107,6 +120,7 @@ }, { "BriefDescription": "Clean L2 cache lines evicted by demand", + "Counter": "0,1,2,3", "EventCode": "0xF2", "EventName": "L2_LINES_OUT.DEMAND_CLEAN", "PublicDescription": "Clean L2 cache lines evicted by demand.",
@@ -115,6 +129,7 @@ }, { "BriefDescription": "Dirty L2 cache lines evicted by demand", + "Counter": "0,1,2,3", "EventCode": "0xF2", "EventName": "L2_LINES_OUT.DEMAND_DIRTY", "PublicDescription": "Dirty L2 cache lines evicted by demand.",
@@ -123,6 +138,7 @@ }, { "BriefDescription": "Dirty L2 cache lines filling the L2", + "Counter": "0,1,2,3", "EventCode": "0xF2", "EventName": "L2_LINES_OUT.DIRTY_ALL", "PublicDescription": "Dirty L2 cache lines filling the L2.",
@@ -131,6 +147,7 @@ }, { "BriefDescription": "Clean L2 cache lines evicted by L2 prefetch", + "Counter": "0,1,2,3", "EventCode": "0xF2", "EventName": "L2_LINES_OUT.PF_CLEAN", "PublicDescription": "Clean L2 cache lines evicted by the MLC prefetcher.",
@@ -139,6 +156,7 @@ }, { "BriefDescription": "Dirty L2 cache lines evicted by L2 prefetch", + "Counter": "0,1,2,3", "EventCode": "0xF2", "EventName": "L2_LINES_OUT.PF_DIRTY", "PublicDescription": "Dirty L2 cache lines evicted by the MLC prefetcher.",
@@ -147,6 +165,7 @@ }, { "BriefDescription": "L2 code requests", + "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_RQSTS.ALL_CODE_RD", "PublicDescription": "Counts all L2 code requests.",
@@ -155,6 +174,7 @@ }, { "BriefDescription": "Demand Data Read requests", + "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_RQSTS.ALL_DEMAND_DATA_RD", "PublicDescription": "Counts any demand and L1 HW prefetch data load requests to L2.",
@@ -163,6 +183,7 @@ }, { "BriefDescription": "Requests from L2 hardware prefetchers", + "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_RQSTS.ALL_PF", "PublicDescription": "Counts all L2 HW prefetcher requests.",
@@ -171,6 +192,7 @@ }, { "BriefDescription": "RFO requests to L2 cache", + "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_RQSTS.ALL_RFO", "PublicDescription": "Counts all L2 store RFO requests.",
@@ -179,6 +201,7 @@ }, { "BriefDescription": "L2 cache hits when fetching instructions, code reads.", + "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_RQSTS.CODE_RD_HIT", "PublicDescription": "Number of instruction fetches that hit the L2 cache.",
@@ -187,6 +210,7 @@ }, { "BriefDescription": "L2 cache misses when fetching instructions", + "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_RQSTS.CODE_RD_MISS", "PublicDescription": "Number of instruction fetches that missed the L2 cache.",
@@ -195,6 +219,7 @@ }, { "BriefDescription": "Demand Data Read requests that hit L2 cache", + "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_RQSTS.DEMAND_DATA_RD_HIT", "PublicDescription": "Demand Data Read requests that hit L2 cache.",
@@ -203,6 +228,7 @@ }, { "BriefDescription": "Requests from the L2 hardware prefetchers that hit L2 cache", + "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_RQSTS.PF_HIT", "PublicDescription": "Counts all L2 HW prefetcher requests that hit L2.",
@@ -211,6 +237,7 @@ }, { "BriefDescription": "Requests from the L2 hardware prefetchers that miss L2 cache", + "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_RQSTS.PF_MISS", "PublicDescription": "Counts all L2 HW prefetcher requests that missed L2.",
@@ -219,6 +246,7 @@ }, { "BriefDescription": "RFO requests that hit L2 cache", + "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_RQSTS.RFO_HIT", "PublicDescription": "RFO requests that hit L2 cache.",
@@ -227,6 +255,7 @@ }, { "BriefDescription": "RFO requests that miss L2 cache", + "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_RQSTS.RFO_MISS", "PublicDescription": "Counts the number of store RFO requests that miss the L2 cache.",
@@ -235,6 +264,7 @@ }, { "BriefDescription": "RFOs that access cache lines in any state", + "Counter": "0,1,2,3", "EventCode": "0x27", "EventName": "L2_STORE_LOCK_RQSTS.ALL", "PublicDescription": "RFOs that access cache lines in any state.",
@@ -243,6 +273,7 @@ }, { "BriefDescription": "RFOs that hit cache lines in M state", + "Counter": "0,1,2,3", "EventCode": "0x27", "EventName": "L2_STORE_LOCK_RQSTS.HIT_M", "PublicDescription": "RFOs that hit cache lines in M state.",
@@ -251,6 +282,7 @@ }, { "BriefDescription": "RFOs that miss cache lines", + "Counter": "0,1,2,3", "EventCode": "0x27", "EventName": "L2_STORE_LOCK_RQSTS.MISS", "PublicDescription": "RFOs that miss cache lines.",
@@ -259,6 +291,7 @@ }, { "BriefDescription": "L2 or LLC HW prefetches that access L2 cache", + "Counter": "0,1,2,3", "EventCode": "0xF0", "EventName": "L2_TRANS.ALL_PF", "PublicDescription": "Any MLC or LLC HW prefetch accessing L2, including rejects.",
@@ -267,6 +300,7 @@ }, { "BriefDescription": "Transactions accessing L2 pipe", + "Counter": "0,1,2,3", "EventCode": "0xF0", "EventName": "L2_TRANS.ALL_REQUESTS", "PublicDescription": "Transactions accessing L2 pipe.",
@@ -275,6 +309,7 @@ }, { "BriefDescription": "L2 cache accesses when fetching instructions", + "Counter": "0,1,2,3", "EventCode": "0xF0", "EventName": "L2_TRANS.CODE_RD", "PublicDescription": "L2 cache accesses when fetching instructions.",
@@ -283,6 +318,7 @@ }, { "BriefDescription": "Demand Data Read requests that access L2 cache", + "Counter": "0,1,2,3", "EventCode": "0xF0", "EventName": "L2_TRANS.DEMAND_DATA_RD", "PublicDescription": "Demand Data Read requests that access L2 cache.",
@@ -291,6 +327,7 @@ }, { "BriefDescription": "L1D writebacks that access L2 cache", + "Counter": "0,1,2,3", "EventCode": "0xF0", "EventName": "L2_TRANS.L1D_WB", "PublicDescription": "L1D writebacks that access L2 cache.",
@@ -299,6 +336,7 @@ }, { "BriefDescription": "L2 fill requests that access L2 cache", + "Counter": "0,1,2,3", "EventCode": "0xF0", "EventName": "L2_TRANS.L2_FILL", "PublicDescription": "L2 fill requests that access L2 cache.",
@@ -307,6 +345,7 @@ }, { "BriefDescription": "L2 writebacks that access L2 cache", + "Counter": "0,1,2,3", "EventCode": "0xF0", "EventName": "L2_TRANS.L2_WB", "PublicDescription": "L2 writebacks that access L2 cache.",
@@ -315,6 +354,7 @@ }, { "BriefDescription": "RFO requests that access L2 cache", + "Counter": "0,1,2,3", "EventCode": "0xF0", "EventName": "L2_TRANS.RFO", "PublicDescription": "RFO requests that access L2 cache.",
@@ -323,6 +363,7 @@ }, { "BriefDescription": "Cycles when L1D is locked", + "Counter": "0,1,2,3", "EventCode": "0x63", "EventName": "LOCK_CYCLES.CACHE_LOCK_DURATION", "PublicDescription": "Cycles in which the L1D is locked.",
@@ -331,6 +372,7 @@ }, { "BriefDescription": "Core-originated cacheable demand requests missed LLC", + "Counter": "0,1,2,3", "EventCode": "0x2E", "EventName": "LONGEST_LAT_CACHE.MISS", "PublicDescription": "This event counts each cache miss condition for references to the last level cache.",
@@ -339,6 +381,7 @@ }, { "BriefDescription": "Core-originated cacheable demand requests that refer to LLC", + "Counter": "0,1,2,3", "EventCode": "0x2E", "EventName": "LONGEST_LAT_CACHE.REFERENCE", "PublicDescription": "This event counts requests originating from the core that reference a cache line in the last level cache.",
@@ -347,6 +390,7 @@ }, { "BriefDescription": "Retired load uops which data sources were LLC and cross-core snoop hits in on-pkg core cache.", + "Counter": "0,1,2,3", "EventCode": "0xD2", "EventName": "MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_HIT", "PEBS": "1",
@@ -355,6 +399,7 @@ }, { "BriefDescription": "Retired load uops which data sources were HitM responses from shared LLC.", + "Counter": "0,1,2,3", "EventCode": "0xD2", "EventName": "MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_HITM", "PEBS": "1",
@@ -363,6 +408,7 @@ }, { "BriefDescription": "Retired load uops which data sources were LLC hit and cross-core snoop missed in on-pkg core cache.", + "Counter": "0,1,2,3", "EventCode": "0xD2", "EventName": "MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_MISS", "PEBS": "1",
@@ -371,6 +417,7 @@ }, { "BriefDescription": "Retired load uops which data sources were hits in LLC without snoops required.", + "Counter": "0,1,2,3", "EventCode": "0xD2", "EventName": "MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_NONE", "PEBS": "1",
@@ -379,6 +426,7 @@ }, { "BriefDescription": "Retired load uops whose data source was local DRAM (Snoop not needed, Snoop Miss, or Snoop Hit data not forwarded).", + "Counter": "0,1,2,3", "EventCode": "0xD3", "EventName": "MEM_LOAD_UOPS_LLC_MISS_RETIRED.LOCAL_DRAM", "SampleAfterValue": "100007",
@@ -386,6 +434,7 @@ }, { "BriefDescription": "Retired load uops whose data source was remote DRAM (Snoop not needed, Snoop Miss, or Snoop Hit data not forwarded).", + "Counter": "0,1,2,3", "EventCode": "0xD3", "EventName": "MEM_LOAD_UOPS_LLC_MISS_RETIRED.REMOTE_DRAM", "SampleAfterValue": "100007",
@@ -393,6 +442,7 @@ }, { "BriefDescription": "Data forwarded from remote cache.", + "Counter": "0,1,2,3", "EventCode": "0xD3", "EventName": "MEM_LOAD_UOPS_LLC_MISS_RETIRED.REMOTE_FWD", "SampleAfterValue": "100007",
@@ -400,6 +450,7 @@ }, { "BriefDescription": "Remote cache HITM.", + "Counter": "0,1,2,3", "EventCode": "0xD3", "EventName": "MEM_LOAD_UOPS_LLC_MISS_RETIRED.REMOTE_HITM", "SampleAfterValue": "100007",
@@ -407,6 +458,7 @@ }, { "BriefDescription": "Retired load uops which data sources were load uops missed L1 but hit FB due to preceding miss to the same cache line with data not ready.", + "Counter": "0,1,2,3", "EventCode": "0xD1", "EventName": "MEM_LOAD_UOPS_RETIRED.HIT_LFB", "PEBS": "1",
@@ -415,6 +467,7 @@ }, { "BriefDescription": "Retired load uops with L1 cache hits as data sources.", + "Counter": "0,1,2,3", "EventCode": "0xD1", "EventName": "MEM_LOAD_UOPS_RETIRED.L1_HIT", "PEBS": "1",
@@ -423,6 +476,7 @@ }, { "BriefDescription": "Retired load uops which data sources following L1 data-cache miss.", + "Counter": "0,1,2,3", "EventCode": "0xD1", "EventName": "MEM_LOAD_UOPS_RETIRED.L1_MISS", "PEBS": "1",
@@ -431,6 +485,7 @@ }, { "BriefDescription": "Retired load uops with L2 cache hits as data sources.", + "Counter": "0,1,2,3", "EventCode": "0xD1", "EventName": "MEM_LOAD_UOPS_RETIRED.L2_HIT", "PEBS": "1",
@@ -439,6 +494,7 @@ }, { "BriefDescription": "Retired load uops with L2 cache misses as data sources.", + "Counter": "0,1,2,3", "EventCode": "0xD1", "EventName": "MEM_LOAD_UOPS_RETIRED.L2_MISS", "PEBS": "1",
@@ -447,6 +503,7 @@ }, { "BriefDescription": "Retired load uops which data sources were data hits in LLC without snoops required.", + "Counter": "0,1,2,3", "EventCode": "0xD1", "EventName": "MEM_LOAD_UOPS_RETIRED.LLC_HIT", "PEBS": "1",
@@ -455,6 +512,7 @@ }, { "BriefDescription": "Miss in last-level (L3) cache. Excludes Unknown data-source.", + "Counter": "0,1,2,3", "EventCode": "0xD1", "EventName": "MEM_LOAD_UOPS_RETIRED.LLC_MISS", "PEBS": "1",
@@ -463,6 +521,7 @@ }, { "BriefDescription": "All retired load uops. (Precise Event)", + "Counter": "0,1,2,3", "EventCode": "0xD0", "EventName": "MEM_UOPS_RETIRED.ALL_LOADS", "PEBS": "1",
@@ -471,6 +530,7 @@ }, { "BriefDescription": "All retired store uops. (Precise Event)", + "Counter": "0,1,2,3", "EventCode": "0xD0", "EventName": "MEM_UOPS_RETIRED.ALL_STORES", "PEBS": "1",
@@ -479,6 +539,7 @@ }, { "BriefDescription": "Retired load uops with locked access. (Precise Event)", + "Counter": "0,1,2,3", "EventCode": "0xD0", "EventName": "MEM_UOPS_RETIRED.LOCK_LOADS", "PEBS": "1",
@@ -487,6 +548,7 @@ }, { "BriefDescription": "Retired load uops that split across a cacheline boundary. (Precise Event)", + "Counter": "0,1,2,3", "EventCode": "0xD0", "EventName": "MEM_UOPS_RETIRED.SPLIT_LOADS", "PEBS": "1",
@@ -495,6 +557,7 @@ }, { "BriefDescription": "Retired store uops that split across a cacheline boundary. (Precise Event)", + "Counter": "0,1,2,3", "EventCode": "0xD0", "EventName": "MEM_UOPS_RETIRED.SPLIT_STORES", "PEBS": "1",
@@ -503,6 +566,7 @@ }, { "BriefDescription": "Retired load uops that miss the STLB. (Precise Event)", + "Counter": "0,1,2,3", "EventCode": "0xD0", "EventName": "MEM_UOPS_RETIRED.STLB_MISS_LOADS", "PEBS": "1",
@@ -511,6 +575,7 @@ }, { "BriefDescription": "Retired store uops that miss the STLB. (Precise Event)", + "Counter": "0,1,2,3", "EventCode": "0xD0", "EventName": "MEM_UOPS_RETIRED.STLB_MISS_STORES", "PEBS": "1",
@@ -519,6 +584,7 @@ }, { "BriefDescription": "Demand and prefetch data reads", + "Counter": "0,1,2,3", "EventCode": "0xB0", "EventName": "OFFCORE_REQUESTS.ALL_DATA_RD", "PublicDescription": "Data read requests sent to uncore (demand and prefetch).",
@@ -527,6 +593,7 @@ }, { "BriefDescription": "Cacheable and noncacheable code read requests", + "Counter": "0,1,2,3", "EventCode": "0xB0", "EventName": "OFFCORE_REQUESTS.DEMAND_CODE_RD", "PublicDescription": "Demand code read requests sent to uncore.",
@@ -535,6 +602,7 @@ }, { "BriefDescription": "Demand Data Read requests sent to uncore", + "Counter": "0,1,2,3", "EventCode": "0xB0", "EventName": "OFFCORE_REQUESTS.DEMAND_DATA_RD", "PublicDescription": "Demand data read requests sent to uncore.",
@@ -543,6 +611,7 @@ }, { "BriefDescription": "Demand RFO requests including regular RFOs, locks, ItoM", + "Counter": "0,1,2,3", "EventCode": "0xB0", "EventName": "OFFCORE_REQUESTS.DEMAND_RFO", "PublicDescription": "Demand RFO read requests sent to uncore, including regular RFOs, locks, ItoM.",
@@ -551,6 +620,7 @@ }, { "BriefDescription": "Cases when offcore requests buffer cannot take more entries for core", + "Counter": "0,1,2,3", "EventCode": "0xB2", "EventName": "OFFCORE_REQUESTS_BUFFER.SQ_FULL", "PublicDescription": "Cases when offcore requests buffer cannot take more entries for core.",
@@ -559,6 +629,7 @@ }, { "BriefDescription": "Offcore outstanding cacheable Core Data Read transactions in SuperQueue (SQ), queue to uncore", + "Counter": "0,1,2,3", "EventCode": "0x60", "EventName": "OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD", "PublicDescription": "Offcore outstanding cacheable data read transactions in SQ to uncore. Set Cmask=1 to count cycles.",
@@ -567,6 +638,7 @@ }, { "BriefDescription": "Cycles when offcore outstanding cacheable Core Data Read transactions are present in SuperQueue (SQ), queue to uncore", + "Counter": "0,1,2,3", "CounterMask": "1", "EventCode": "0x60", "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD",
@@ -576,6 +648,7 @@ }, { "BriefDescription": "Offcore outstanding code reads transactions in SuperQueue (SQ), queue to uncore, every cycle", + "Counter": "0,1,2,3", "CounterMask": "1", "EventCode": "0x60", "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_CODE_RD",
@@ -585,6 +658,7 @@ }, { "BriefDescription": "Cycles when offcore outstanding Demand Data Read transactions are present in SuperQueue (SQ), queue to uncore", + "Counter": "0,1,2,3", "CounterMask": "1", "EventCode": "0x60", "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_DATA_RD",
@@ -594,6 +668,7 @@ }, { "BriefDescription": "Offcore outstanding demand rfo reads transactions in SuperQueue (SQ), queue to uncore, every cycle", + "Counter": "0,1,2,3", "CounterMask": "1", "EventCode": "0x60", "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO",
@@ -603,6 +678,7 @@ }, { "BriefDescription": "Offcore outstanding code reads transactions in SuperQueue (SQ), queue to uncore, every cycle", + "Counter": "0,1,2,3", "EventCode": "0x60", "EventName": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_CODE_RD", "PublicDescription": "Offcore outstanding Demand Code Read transactions in SQ to uncore. Set Cmask=1 to count cycles.",
@@ -611,6 +687,7 @@ }, { "BriefDescription": "Offcore outstanding Demand Data Read transactions in uncore queue.", + "Counter": "0,1,2,3", "EventCode": "0x60", "EventName": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD", "PublicDescription": "Offcore outstanding Demand Data Read transactions in SQ to uncore. Set Cmask=1 to count cycles.",
@@ -619,6 +696,7 @@ }, { "BriefDescription": "Cycles with at least 6 offcore outstanding Demand Data Read transactions in uncore queue", + "Counter": "0,1,2,3", "CounterMask": "6", "EventCode": "0x60", "EventName": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD_GE_6",
@@ -628,6 +706,7 @@ }, { "BriefDescription": "Offcore outstanding RFO store transactions in SuperQueue (SQ), queue to uncore", + "Counter": "0,1,2,3", "EventCode": "0x60", "EventName": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_RFO", "PublicDescription": "Offcore outstanding RFO store transactions in SQ to uncore. Set Cmask=1 to count cycles.",
@@ -636,6 +715,7 @@ }, { "BriefDescription": "Counts demand & prefetch data reads that hit in the LLC and the snoop to one of the sibling cores hits the line in M state and the line is forwarded", + "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.LLC_HIT.HITM_OTHER_CORE", "MSRIndex": "0x1a6,0x1a7",
@@ -645,6 +725,7 @@ }, { "BriefDescription": "Counts demand & prefetch data reads that hit in the LLC and the snoops to sibling cores hit in either E/S state and the line is not forwarded", + "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.LLC_HIT.HIT_OTHER_CORE_NO_FWD", "MSRIndex": "0x1a6,0x1a7",
@@ -654,6 +735,7 @@ }, { "BriefDescription": "Counts demand & prefetch data reads that hit in the LLC and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores", + "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.LLC_HIT.NO_SNOOP_NEEDED", "MSRIndex": "0x1a6,0x1a7",
@@ -663,6 +745,7 @@ }, { "BriefDescription": "Counts demand & prefetch data reads that hit in the LLC and sibling core snoop returned a clean response", + "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.LLC_HIT.SNOOP_MISS", "MSRIndex": "0x1a6,0x1a7",
@@ -672,6 +755,7 @@ }, { "BriefDescription": "Counts all prefetch data reads that hit the LLC", + "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.LLC_HIT.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7",
@@ -681,6 +765,7 @@ }, { "BriefDescription": "Counts prefetch data reads that hit in the LLC and the snoop to one of the sibling cores hits the line in M state and the line is forwarded", + "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.LLC_HIT.HITM_OTHER_CORE", "MSRIndex": "0x1a6,0x1a7",
@@ -690,6 +775,7 @@ }, { "BriefDescription": "Counts prefetch data reads that hit in the LLC and the snoops to sibling cores hit in either E/S state and the line is not forwarded", + "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.LLC_HIT.HIT_OTHER_CORE_NO_FWD", "MSRIndex": "0x1a6,0x1a7",
@@ -699,6 +785,7 @@ }, { "BriefDescription": "Counts prefetch data reads that hit in the LLC and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores", + "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.LLC_HIT.NO_SNOOP_NEEDED", "MSRIndex": "0x1a6,0x1a7",
@@ -708,6 +795,7 @@ }, { "BriefDescription": "Counts prefetch data reads that hit in the LLC and sibling core snoop returned a clean response", + "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.LLC_HIT.SNOOP_MISS", "MSRIndex": "0x1a6,0x1a7",
@@ -717,6 +805,7 @@ }, { "BriefDescription": "Counts all data/code/rfo reads (demand & prefetch) that hit in the LLC", + "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.ALL_READS.LLC_HIT.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7",
@@ -726,6 +815,7 @@ }, { "BriefDescription": "Counts all data/code/rfo reads (demand & prefetch) that hit in the LLC and the snoop to one of the sibling cores hits the line in M state and the line is forwarded", + "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.ALL_READS.LLC_HIT.HITM_OTHER_CORE", "MSRIndex": "0x1a6,0x1a7",
@@ -735,6 +825,7 @@ }, { "BriefDescription": "Counts all data/code/rfo reads (demand & prefetch) that hit in the LLC and the snoops to sibling cores hit in either E/S state and the line is not forwarded", + "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.ALL_READS.LLC_HIT.HIT_OTHER_CORE_NO_FWD", "MSRIndex": "0x1a6,0x1a7",
@@ -744,6 +835,7 @@ }, { "BriefDescription": "Counts all data/code/rfo reads (demand & prefetch) that hit in the LLC and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores", + "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.ALL_READS.LLC_HIT.NO_SNOOP_NEEDED", "MSRIndex": "0x1a6,0x1a7",
@@ -753,6 +845,7 @@ }, { "BriefDescription": "Counts all data/code/rfo reads (demand & prefetch) that hit in the LLC and sibling core snoop returned a clean response", + "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.ALL_READS.LLC_HIT.SNOOP_MISS", "MSRIndex": "0x1a6,0x1a7",
@@ -762,6 +855,7 @@ }, { "BriefDescription": "Counts all writebacks from the core to the LLC", + "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.COREWB.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7",
@@ -771,6 +865,7 @@ }, { "BriefDescription": "Counts all demand code reads that hit in the LLC", + "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.LLC_HIT.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7",
@@ -780,6 +875,7 @@ }, { "BriefDescription": "Counts all demand data reads that hit in the LLC", + "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.LLC_HIT.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7",
@@ -789,6 +885,7 @@ }, { "BriefDescription": "Counts demand data reads that hit in the LLC and the snoop to one of the sibling cores hits the line in M state and the line is forwarded", + "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.LLC_HIT.HITM_OTHER_CORE", "MSRIndex": "0x1a6,0x1a7",
@@ -798,6 +895,7 @@ }, { "BriefDescription": "Counts demand data reads that hit in the LLC and the snoops to sibling cores hit in either E/S state and the line is not forwarded", + "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.LLC_HIT.HIT_OTHER_CORE_NO_FWD", "MSRIndex": "0x1a6,0x1a7",
@@ -807,6 +905,7 @@ }, { "BriefDescription": "Counts demand data reads that hit in the LLC and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores", + "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.LLC_HIT.NO_SNOOP_NEEDED", "MSRIndex": "0x1a6,0x1a7",
@@ -816,6 +915,7 @@ }, { "BriefDescription": "Counts demand data reads that hit in the LLC and sibling core snoop returned a clean response", + "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.LLC_HIT.SNOOP_MISS", "MSRIndex": "0x1a6,0x1a7",
@@ -825,6 +925,7 @@ }, { "BriefDescription": "Counts demand data writes (RFOs) that hit in the LLC and the snoop to one of the sibling cores hits the line in M state and the line is forwarded", + "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.LLC_HIT.HITM_OTHER_CORE", "MSRIndex": "0x1a6,0x1a7",
@@ -834,6 +935,7 @@ }, { "BriefDescription": "Counts L2 hints sent to LLC to keep a line from being evicted out of the core caches", + "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.OTHER.LRU_HINTS", "MSRIndex": "0x1a6,0x1a7",
@@ -843,6 +945,7 @@ }, { "BriefDescription": "Counts miscellaneous accesses that include port i/o, MMIO and uncacheable memory accesses", + "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.OTHER.PORTIO_MMIO_UC", "MSRIndex": "0x1a6,0x1a7",
@@ -852,6 +955,7 @@ }, { "BriefDescription": "Counts all prefetch (that bring data to L2) code reads that hit in the LLC", + "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.LLC_HIT.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7",
@@ -861,6 +965,7 @@ }, { "BriefDescription": "Counts prefetch (that bring data to L2) data reads that hit in the LLC", + "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.LLC_HIT.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7",
@@ -870,6 +975,7 @@ }, { "BriefDescription": "Counts prefetch (that bring data to L2) data reads that hit in the LLC and the snoop to one of the sibling cores hits the line in M state and the line is forwarded", + "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.LLC_HIT.HITM_OTHER_CORE", "MSRIndex": "0x1a6,0x1a7",
@@ -879,6 +985,7 @@ }, { "BriefDescription": "Counts prefetch (that bring data to L2) data reads that hit in the LLC and the snoops to sibling cores hit in either E/S state and the line is not forwarded", + "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.LLC_HIT.HIT_OTHER_CORE_NO_FWD", "MSRIndex": "0x1a6,0x1a7",
@@ -888,6 +995,7 @@ }, { "BriefDescription": "Counts prefetch (that bring data to L2) data reads that hit in the LLC and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores", + "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.LLC_HIT.NO_SNOOP_NEEDED", "MSRIndex": "0x1a6,0x1a7",
@@ -897,6 +1005,7 @@ }, { "BriefDescription": "Counts prefetch (that bring data to L2) data reads that hit in the LLC and the snoops sent to sibling cores return clean response", + "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.LLC_HIT.SNOOP_MISS", "MSRIndex": "0x1a6,0x1a7",
@@ -906,6 +1015,7 @@ }, { "BriefDescription": "Counts all prefetch (that bring data to LLC only) code reads that hit in the LLC", + "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.PF_LLC_CODE_RD.LLC_HIT.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7",
@@ -915,6 +1025,7 @@ }, { "BriefDescription": "Counts prefetch (that bring data to LLC only) data reads that hit in the LLC", + "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.PF_LLC_DATA_RD.LLC_HIT.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7",
@@ -924,6 +1035,7 @@ }, { "BriefDescription": "Counts prefetch (that bring data to LLC only) data reads that hit in the LLC and the snoop to one of the sibling cores hits the line in M state and the line is forwarded", + "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.PF_LLC_DATA_RD.LLC_HIT.HITM_OTHER_CORE", "MSRIndex": "0x1a6,0x1a7",
@@ -933,6 +1045,7 @@ }, { "BriefDescription": "Counts prefetch (that bring data to LLC only) data reads that hit in the LLC and the snoops to sibling cores hit in either E/S state and the line is not forwarded", + "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.PF_LLC_DATA_RD.LLC_HIT.HIT_OTHER_CORE_NO_FWD", "MSRIndex": "0x1a6,0x1a7",
@@ -942,6 +1055,7 @@ }, { "BriefDescription": "Counts prefetch (that bring data to LLC only) data reads that hit in the LLC and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores", + "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.PF_LLC_DATA_RD.LLC_HIT.NO_SNOOP_NEEDED", "MSRIndex": "0x1a6,0x1a7",
@@ -951,6 +1065,7 @@ }, { "BriefDescription": "Counts prefetch (that bring data to LLC only) data reads that hit in the LLC and the snoops sent to sibling cores return clean response", + "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.PF_LLC_DATA_RD.LLC_HIT.SNOOP_MISS", "MSRIndex": "0x1a6,0x1a7",
@@ -960,6 +1075,7 @@ }, { "BriefDescription": "Counts requests where the address of an atomic lock instruction spans a cache line boundary or the lock instruction is executed on uncacheable address", + "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.SPLIT_LOCK_UC_LOCK.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7",
@@ -969,6 +1085,7 @@ }, { "BriefDescription": "Counts non-temporal stores", + "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.STREAMING_STORES.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7",
@@ -978,6 +1095,7 @@ }, { "BriefDescription": "Split locks in SQ", + "Counter": "0,1,2,3", "EventCode": "0xF4", "EventName": "SQ_MISC.SPLIT_LOCK", "SampleAfterValue": "100003",
tools/perf/pmu-events/arch/x86/ivytown/counter.json new file +52 -0
53 lines not on this page · raw message
tools/perf/pmu-events/arch/x86/ivytown/floating-point.json +17 -0
@@ -1,6 +1,7 @@ [ { "BriefDescription": "Cycles with any input/output SSE or FP assist", + "Counter": "0,1,2,3", "CounterMask": "1", "EventCode": "0xCA", "EventName": "FP_ASSIST.ANY",
@@ -10,6 +11,7 @@ }, { "BriefDescription": "Number of SIMD FP assists due to input values", + "Counter": "0,1,2,3", "EventCode": "0xCA", "EventName": "FP_ASSIST.SIMD_INPUT", "PublicDescription": "Number of SIMD FP assists due to input values.",
@@ -18,6 +20,7 @@ }, { "BriefDescription": "Number of SIMD FP assists due to Output values", + "Counter": "0,1,2,3", "EventCode": "0xCA", "EventName": "FP_ASSIST.SIMD_OUTPUT", "PublicDescription": "Number of SIMD FP assists due to output values.",
@@ -26,6 +29,7 @@ }, { "BriefDescription": "Number of X87 assists due to input value.", + "Counter": "0,1,2,3", "EventCode": "0xCA", "EventName": "FP_ASSIST.X87_INPUT", "PublicDescription": "Number of X87 FP assists due to input values.",
@@ -34,6 +38,7 @@ }, { "BriefDescription": "Number of X87 assists due to output value.", + "Counter": "0,1,2,3", "EventCode": "0xCA", "EventName": "FP_ASSIST.X87_OUTPUT", "PublicDescription": "Number of X87 FP assists due to output values.",
@@ -42,6 +47,7 @@ }, { "BriefDescription": "Number of SSE* or AVX-128 FP Computational packed double-precision uops issued this cycle", + "Counter": "0,1,2,3", "EventCode": "0x10", "EventName": "FP_COMP_OPS_EXE.SSE_PACKED_DOUBLE", "PublicDescription": "Number of SSE* or AVX-128 FP Computational packed double-precision uops issued this cycle.",
@@ -50,6 +56,7 @@ }, { "BriefDescription": "Number of SSE* or AVX-128 FP Computational packed single-precision uops issued this cycle", + "Counter": "0,1,2,3", "EventCode": "0x10", "EventName": "FP_COMP_OPS_EXE.SSE_PACKED_SINGLE", "PublicDescription": "Number of SSE* or AVX-128 FP Computational packed single-precision uops issued this cycle.",
@@ -58,6 +65,7 @@ }, { "BriefDescription": "Number of SSE* or AVX-128 FP Computational scalar double-precision uops issued this cycle", + "Counter": "0,1,2,3", "EventCode": "0x10", "EventName": "FP_COMP_OPS_EXE.SSE_SCALAR_DOUBLE", "PublicDescription": "Counts number of SSE* or AVX-128 double precision FP scalar uops executed.",
@@ -66,6 +74,7 @@ }, { "BriefDescription": "Number of SSE* or AVX-128 FP Computational scalar single-precision uops issued this cycle", + "Counter": "0,1,2,3", "EventCode": "0x10", "EventName": "FP_COMP_OPS_EXE.SSE_SCALAR_SINGLE", "PublicDescription": "Number of SSE* or AVX-128 FP Computational scalar single-precision uops issued this cycle.",
@@ -74,6 +83,7 @@ }, { "BriefDescription": "Number of FP Computational Uops Executed this cycle. The number of FADD, FSUB, FCOM, FMULs, integer MULs and IMULs, FDIVs, FPREMs, FSQRTS, integer DIVs, and IDIVs. This event does not distinguish an FADD used in the middle of a transcendental flow from a s", + "Counter": "0,1,2,3", "EventCode": "0x10", "EventName": "FP_COMP_OPS_EXE.X87", "PublicDescription": "Counts number of X87 uops executed.",
@@ -82,6 +92,7 @@ }, { "BriefDescription": "Number of SIMD Move Elimination candidate uops that were eliminated.", + "Counter": "0,1,2,3", "EventCode": "0x58", "EventName": "MOVE_ELIMINATION.SIMD_ELIMINATED", "SampleAfterValue": "1000003",
@@ -89,6 +100,7 @@ }, { "BriefDescription": "Number of SIMD Move Elimination candidate uops that were not eliminated.", + "Counter": "0,1,2,3", "EventCode": "0x58", "EventName": "MOVE_ELIMINATION.SIMD_NOT_ELIMINATED", "SampleAfterValue": "1000003",
@@ -96,6 +108,7 @@ }, { "BriefDescription": "Number of GSSE memory assist for stores. GSSE microcode assist is being invoked whenever the hardware is unable to properly handle GSSE-256b operations.", + "Counter": "0,1,2,3", "EventCode": "0xC1", "EventName": "OTHER_ASSISTS.AVX_STORE", "PublicDescription": "Number of assists associated with 256-bit AVX store operations.",
@@ -104,6 +117,7 @@ }, { "BriefDescription": "Number of transitions from AVX-256 to legacy SSE when penalty applicable.", + "Counter": "0,1,2,3", "EventCode": "0xC1", "EventName": "OTHER_ASSISTS.AVX_TO_SSE", "SampleAfterValue": "100003",
@@ -111,6 +125,7 @@ }, { "BriefDescription": "Number of transitions from SSE to AVX-256 when penalty applicable.", + "Counter": "0,1,2,3", "EventCode": "0xC1", "EventName": "OTHER_ASSISTS.SSE_TO_AVX", "SampleAfterValue": "100003",
@@ -118,6 +133,7 @@ }, { "BriefDescription": "number of AVX-256 Computational FP double precision uops issued this cycle", + "Counter": "0,1,2,3", "EventCode": "0x11", "EventName": "SIMD_FP_256.PACKED_DOUBLE", "PublicDescription": "Counts 256-bit packed double-precision floating-point instructions.",
@@ -126,6 +142,7 @@ }, { "BriefDescription": "number of GSSE-256 Computational FP single precision uops issued this cycle", + "Counter": "0,1,2,3", "EventCode": "0x11", "EventName": "SIMD_FP_256.PACKED_SINGLE", "PublicDescription": "Counts 256-bit packed single-precision floating-point instructions.",
tools/perf/pmu-events/arch/x86/ivytown/frontend.json +30 -0
@@ -1,6 +1,7 @@ [ { "BriefDescription": "Counts the total number when the front end is resteered, mainly when the BPU cannot provide a correct prediction and this is corrected by other branch handling mechanisms at the front end.", + "Counter": "0,1,2,3", "EventCode": "0xE6", "EventName": "BACLEARS.ANY", "PublicDescription": "Number of front end re-steers due to BPU misprediction.",
@@ -9,6 +10,7 @@ }, { "BriefDescription": "Decode Stream Buffer (DSB)-to-MITE switches", + "Counter": "0,1,2,3", "EventCode": "0xAB", "EventName": "DSB2MITE_SWITCHES.COUNT", "PublicDescription": "Number of DSB to MITE switches.",
@@ -17,6 +19,7 @@ }, { "BriefDescription": "Decode Stream Buffer (DSB)-to-MITE switch true penalty cycles", + "Counter": "0,1,2,3", "EventCode": "0xAB", "EventName": "DSB2MITE_SWITCHES.PENALTY_CYCLES", "PublicDescription": "Cycles DSB to MITE switches caused delay.",
@@ -25,6 +28,7 @@ }, { "BriefDescription": "Cycles when Decode Stream Buffer (DSB) fill encounter more than 3 Decode Stream Buffer (DSB) lines", + "Counter": "0,1,2,3", "EventCode": "0xAC", "EventName": "DSB_FILL.EXCEED_DSB_LINES", "PublicDescription": "DSB Fill encountered > 3 DSB lines.",
@@ -33,6 +37,7 @@ }, { "BriefDescription": "Number of Instruction Cache, Streaming Buffer and Victim Cache Reads. both cacheable and noncacheable, including UC fetches", + "Counter": "0,1,2,3", "EventCode": "0x80", "EventName": "ICACHE.HIT", "PublicDescription": "Number of Instruction Cache, Streaming Buffer and Victim Cache Reads. both cacheable and noncacheable, including UC fetches.",
@@ -41,6 +46,7 @@ }, { "BriefDescription": "Cycles where a code-fetch stalled due to L1 instruction-cache miss or an iTLB miss", + "Counter": "0,1,2,3", "EventCode": "0x80", "EventName": "ICACHE.IFETCH_STALL", "PublicDescription": "Cycles where a code-fetch stalled due to L1 instruction-cache miss or an iTLB miss.",
@@ -49,6 +55,7 @@ }, { "BriefDescription": "Instruction cache, streaming buffer and victim cache misses", + "Counter": "0,1,2,3", "EventCode": "0x80", "EventName": "ICACHE.MISSES", "PublicDescription": "Number of Instruction Cache, Streaming Buffer and Victim Cache Misses. Includes UC accesses.",
@@ -57,6 +64,7 @@ }, { "BriefDescription": "Cycles Decode Stream Buffer (DSB) is delivering 4 Uops", + "Counter": "0,1,2,3", "CounterMask": "4", "EventCode": "0x79", "EventName": "IDQ.ALL_DSB_CYCLES_4_UOPS",
@@ -66,6 +74,7 @@ }, { "BriefDescription": "Cycles Decode Stream Buffer (DSB) is delivering any Uop", + "Counter": "0,1,2,3", "CounterMask": "1", "EventCode": "0x79", "EventName": "IDQ.ALL_DSB_CYCLES_ANY_UOPS",
@@ -75,6 +84,7 @@ }, { "BriefDescription": "Cycles MITE is delivering 4 Uops", + "Counter": "0,1,2,3", "CounterMask": "4", "EventCode": "0x79", "EventName": "IDQ.ALL_MITE_CYCLES_4_UOPS",
@@ -84,6 +94,7 @@ }, { "BriefDescription": "Cycles MITE is delivering any Uop", + "Counter": "0,1,2,3", "CounterMask": "1", "EventCode": "0x79", "EventName": "IDQ.ALL_MITE_CYCLES_ANY_UOPS",
@@ -93,6 +104,7 @@ }, { "BriefDescription": "Cycles when uops are being delivered to Instruction Decode Queue (IDQ) from Decode Stream Buffer (DSB) path", + "Counter": "0,1,2,3", "CounterMask": "1", "EventCode": "0x79", "EventName": "IDQ.DSB_CYCLES",
@@ -102,6 +114,7 @@ }, { "BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path", + "Counter": "0,1,2,3", "EventCode": "0x79", "EventName": "IDQ.DSB_UOPS", "PublicDescription": "Increment each cycle. # of uops delivered to IDQ from DSB path. Set Cmask = 1 to count cycles.",
@@ -110,6 +123,7 @@ }, { "BriefDescription": "Instruction Decode Queue (IDQ) empty cycles", + "Counter": "0,1,2,3", "EventCode": "0x79", "EventName": "IDQ.EMPTY", "PublicDescription": "Counts cycles the IDQ is empty.",
@@ -118,6 +132,7 @@ }, { "BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) from MITE path", + "Counter": "0,1,2,3", "EventCode": "0x79", "EventName": "IDQ.MITE_ALL_UOPS", "PublicDescription": "Number of uops delivered to IDQ from any path.",
@@ -126,6 +141,7 @@ }, { "BriefDescription": "Cycles when uops are being delivered to Instruction Decode Queue (IDQ) from MITE path", + "Counter": "0,1,2,3", "CounterMask": "1", "EventCode": "0x79", "EventName": "IDQ.MITE_CYCLES",
@@ -135,6 +151,7 @@ }, { "BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) from MITE path", + "Counter": "0,1,2,3", "EventCode": "0x79", "EventName": "IDQ.MITE_UOPS", "PublicDescription": "Increment each cycle # of uops delivered to IDQ from MITE path. Set Cmask = 1 to count cycles.",
@@ -143,6 +160,7 @@ }, { "BriefDescription": "Cycles when uops are being delivered to Instruction Decode Queue (IDQ) while Microcode Sequencer (MS) is busy", + "Counter": "0,1,2,3", "CounterMask": "1", "EventCode": "0x79", "EventName": "IDQ.MS_CYCLES",
@@ -152,6 +170,7 @@ }, { "BriefDescription": "Cycles when uops initiated by Decode Stream Buffer (DSB) are being delivered to Instruction Decode Queue (IDQ) while Microcode Sequencer (MS) is busy", + "Counter": "0,1,2,3", "CounterMask": "1", "EventCode": "0x79", "EventName": "IDQ.MS_DSB_CYCLES",
@@ -161,6 +180,7 @@ }, { "BriefDescription": "Deliveries to Instruction Decode Queue (IDQ) initiated by Decode Stream Buffer (DSB) while Microcode Sequencer (MS) is busy", + "Counter": "0,1,2,3", "CounterMask": "1", "EdgeDetect": "1", "EventCode": "0x79",
@@ -171,6 +191,7 @@ }, { "BriefDescription": "Uops initiated by Decode Stream Buffer (DSB) that are being delivered to Instruction Decode Queue (IDQ) while Microcode Sequencer (MS) is busy", + "Counter": "0,1,2,3", "EventCode": "0x79", "EventName": "IDQ.MS_DSB_UOPS", "PublicDescription": "Increment each cycle # of uops delivered to IDQ when MS_busy by DSB. Set Cmask = 1 to count cycles. Add Edge=1 to count # of delivery.",
@@ -179,6 +200,7 @@ }, { "BriefDescription": "Uops initiated by MITE and delivered to Instruction Decode Queue (IDQ) while Microcode Sequencer (MS) is busy", + "Counter": "0,1,2,3", "EventCode": "0x79", "EventName": "IDQ.MS_MITE_UOPS", "PublicDescription": "Increment each cycle # of uops delivered to IDQ when MS_busy by MITE. Set Cmask = 1 to count cycles.",
@@ -187,6 +209,7 @@ }, { "BriefDescription": "Number of switches from DSB (Decode Stream Buffer) or MITE (legacy decode pipeline) to the Microcode Sequencer", + "Counter": "0,1,2,3", "CounterMask": "1", "EdgeDetect": "1", "EventCode": "0x79",
@@ -197,6 +220,7 @@ }, { "BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) while Microcode Sequencer (MS) is busy", + "Counter": "0,1,2,3", "EventCode": "0x79", "EventName": "IDQ.MS_UOPS", "PublicDescription": "Increment each cycle # of uops delivered to IDQ from MS by either DSB or MITE. Set Cmask = 1 to count cycles.",
@@ -205,6 +229,7 @@ }, { "BriefDescription": "Uops not delivered to Resource Allocation Table (RAT) per thread when backend of the machine is not stalled", + "Counter": "0,1,2,3", "EventCode": "0x9C", "EventName": "IDQ_UOPS_NOT_DELIVERED.CORE", "PublicDescription": "Count issue pipeline slots where no uop was delivered from the front end to the back end when there is no back-end stall.",
@@ -213,6 +238,7 @@ }, { "BriefDescription": "Cycles per thread when 4 or more uops are not delivered to Resource Allocation Table (RAT) when backend of the machine is not stalled.", + "Counter": "0,1,2,3", "CounterMask": "4", "EventCode": "0x9C", "EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE",
@@ -221,6 +247,7 @@ }, { "BriefDescription": "Counts cycles FE delivered 4 uops or Resource Allocation Table (RAT) was stalling FE.", + "Counter": "0,1,2,3", "CounterMask": "1", "EventCode": "0x9C", "EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_FE_WAS_OK",
@@ -230,6 +257,7 @@ }, { "BriefDescription": "Cycles per thread when 3 or more uops are not delivered to Resource Allocation Table (RAT) when backend of the machine is not stalled.", + "Counter": "0,1,2,3", "CounterMask": "3", "EventCode": "0x9C", "EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_LE_1_UOP_DELIV.CORE",
@@ -238,6 +266,7 @@ }, { "BriefDescription": "Cycles with less than 2 uops delivered by the front end.", + "Counter": "0,1,2,3", "CounterMask": "2", "EventCode": "0x9C", "EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_LE_2_UOP_DELIV.CORE",
@@ -246,6 +275,7 @@ }, { "BriefDescription": "Cycles with less than 3 uops delivered by the front end.", + "Counter": "0,1,2,3", "CounterMask": "1", "EventCode": "0x9C", "EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_LE_3_UOP_DELIV.CORE",
tools/perf/pmu-events/arch/x86/ivytown/ivt-metrics.json +37 -31
251 lines not on this page · raw message
tools/perf/pmu-events/arch/x86/ivytown/memory.json +41 -0
287 lines not on this page · raw message
tools/perf/pmu-events/arch/x86/ivytown/metricgroups.json +11 -0
@@ -5,7 +5,18 @@ "BigFootprint": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", "BrMispredicts": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", "Branches": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "BvBC": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "BvCB": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "BvFB": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "BvIO": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "BvML": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "BvMP": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "BvMS": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "BvMT": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "BvOB": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "BvUW": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", "CacheHits": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "CacheMisses": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", "Compute": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", "Cor": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", "DSB": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
tools/perf/pmu-events/arch/x86/ivytown/other.json +4 -0
@@ -1,6 +1,7 @@ [ { "BriefDescription": "Unhalted core cycles when the thread is in ring 0", + "Counter": "0,1,2,3", "EventCode": "0x5C", "EventName": "CPL_CYCLES.RING0", "PublicDescription": "Unhalted core cycles when the thread is in ring 0.",
@@ -9,6 +10,7 @@ }, { "BriefDescription": "Number of intervals between processor halts while thread is in ring 0", + "Counter": "0,1,2,3", "CounterMask": "1", "EdgeDetect": "1", "EventCode": "0x5C",
@@ -19,6 +21,7 @@ }, { "BriefDescription": "Unhalted core cycles when thread is in rings 1, 2, or 3", + "Counter": "0,1,2,3", "EventCode": "0x5C", "EventName": "CPL_CYCLES.RING123", "PublicDescription": "Unhalted core cycles when the thread is not in ring 0.",
@@ -27,6 +30,7 @@ }, { "BriefDescription": "Cycles when L1 and L2 are locked due to UC or split lock", + "Counter": "0,1,2,3", "EventCode": "0x63", "EventName": "LOCK_CYCLES.SPLIT_LOCK_UC_LOCK_DURATION", "PublicDescription": "Cycles in which the L1D and L2 are locked, due to a UC lock or split lock.",
tools/perf/pmu-events/arch/x86/ivytown/pipeline.json +126 -0
882 lines not on this page · raw message
tools/perf/pmu-events/arch/x86/ivytown/uncore-cache.json +349 -0
326 lines not on this page · raw message
tools/perf/pmu-events/arch/x86/ivytown/uncore-interconnect.json +385 -0
385 lines not on this page · raw message
tools/perf/pmu-events/arch/x86/ivytown/uncore-io.json +61 -0
61 lines not on this page · raw message
tools/perf/pmu-events/arch/x86/ivytown/uncore-memory.json +198 -0
198 lines not on this page · raw message
tools/perf/pmu-events/arch/x86/ivytown/uncore-power.json +74 -0
74 lines not on this page · raw message
tools/perf/pmu-events/arch/x86/ivytown/virtual-memory.json +20 -0
Lines of this file are not shown. View the raw message.
The rest of this diff is not shown. View the raw message.
Signature · 1 line
2.45.2.627.g7a2c4fd464-goog
Part of the diff is not shown here. View the raw message.
Ian Rogers
reviewerPATCH v2 20/37 perf vendor events: Update jaketown metrics add event counter information
In reply to Ian RogersAdd counter information necessary for optimizing event grouping the perf tool.
The most recent RFC patch set using this information:
https://lore.kernel.org/lkml/[email protected]/
The information was added in:
https://github.com/intel/perfmon/commit/475892a9690cb048949e593fe39cee65cd4765e1
and later patches.
The TMA 4.8 information was updated in:
https://github.com/intel/perfmon/commit/59194d4d90ca50a3fcb2de0d82b9f6fc0c9a5736
--- .../pmu-events/arch/x86/jaketown/cache.json | 123 +++++++++++ .../pmu-events/arch/x86/jaketown/counter.json | 52 +++++ .../arch/x86/jaketown/floating-point.json | 15 ++ .../arch/x86/jaketown/frontend.json | 32 +++ .../arch/x86/jaketown/jkt-metrics.json | 24 +- .../pmu-events/arch/x86/jaketown/memory.json | 35 +++ .../arch/x86/jaketown/metricgroups.json | 11 + .../pmu-events/arch/x86/jaketown/other.json | 6 + .../arch/x86/jaketown/pipeline.json | 127 +++++++++++ .../arch/x86/jaketown/uncore-cache.json | 205 +++++++++++++++++ .../x86/jaketown/uncore-interconnect.json | 207 ++++++++++++++++++ .../arch/x86/jaketown/uncore-io.json | 36 +++ .../arch/x86/jaketown/uncore-memory.json | 51 +++++ .../arch/x86/jaketown/uncore-power.json | 39 ++++ .../arch/x86/jaketown/virtual-memory.json | 16 ++ 15 files changed, 967 insertions(+), 12 deletions(-) create mode 100644 tools/perf/pmu-events/arch/x86/jaketown/counter.json
tools/perf/pmu-events/arch/x86/jaketown/cache.json +123 -0
@@ -1,6 +1,7 @@ [ { "BriefDescription": "Allocated L1D data cache lines in M state.", + "Counter": "0,1,2,3", "EventCode": "0x51", "EventName": "L1D.ALLOCATED_IN_M", "SampleAfterValue": "2000003",
@@ -8,6 +9,7 @@ }, { "BriefDescription": "Cache lines in M state evicted out of L1D due to Snoop HitM or dirty line replacement.", + "Counter": "0,1,2,3", "EventCode": "0x51", "EventName": "L1D.ALL_M_REPLACEMENT", "SampleAfterValue": "2000003",
@@ -15,6 +17,7 @@ }, { "BriefDescription": "L1D data cache lines in M state evicted due to replacement.", + "Counter": "0,1,2,3", "EventCode": "0x51", "EventName": "L1D.EVICTION", "SampleAfterValue": "2000003",
@@ -22,6 +25,7 @@ }, { "BriefDescription": "L1D data line replacements.", + "Counter": "0,1,2,3", "EventCode": "0x51", "EventName": "L1D.REPLACEMENT", "PublicDescription": "This event counts L1D data line replacements. Replacements occur when a new line is brought into the cache, causing eviction of a line loaded earlier.",
@@ -30,6 +34,7 @@ }, { "BriefDescription": "Cycles when dispatched loads are cancelled due to L1D bank conflicts with other load ports.", + "Counter": "0,1,2,3", "CounterMask": "1", "EventCode": "0xBF", "EventName": "L1D_BLOCKS.BANK_CONFLICT_CYCLES",
@@ -38,6 +43,7 @@ }, { "BriefDescription": "Cycles a demand request was blocked due to Fill Buffers unavailability.", + "Counter": "0,1,2,3", "CounterMask": "1", "EventCode": "0x48", "EventName": "L1D_PEND_MISS.FB_FULL",
@@ -46,6 +52,7 @@ }, { "BriefDescription": "L1D miss outstanding duration in cycles.", + "Counter": "2", "EventCode": "0x48", "EventName": "L1D_PEND_MISS.PENDING", "SampleAfterValue": "2000003",
@@ -53,6 +60,7 @@ }, { "BriefDescription": "Cycles with L1D load Misses outstanding.", + "Counter": "2", "CounterMask": "1", "EventCode": "0x48", "EventName": "L1D_PEND_MISS.PENDING_CYCLES",
@@ -62,6 +70,7 @@ { "AnyThread": "1", "BriefDescription": "Cycles with L1D load Misses outstanding from any thread on physical core.", + "Counter": "2", "CounterMask": "1", "EventCode": "0x48", "EventName": "L1D_PEND_MISS.PENDING_CYCLES_ANY",
@@ -70,6 +79,7 @@ }, { "BriefDescription": "Not rejected writebacks from L1D to L2 cache lines in any state.", + "Counter": "0,1,2,3", "EventCode": "0x28", "EventName": "L2_L1D_WB_RQSTS.ALL", "SampleAfterValue": "200003",
@@ -77,6 +87,7 @@ }, { "BriefDescription": "Not rejected writebacks from L1D to L2 cache lines in E state.", + "Counter": "0,1,2,3", "EventCode": "0x28", "EventName": "L2_L1D_WB_RQSTS.HIT_E", "SampleAfterValue": "200003",
@@ -84,6 +95,7 @@ }, { "BriefDescription": "Not rejected writebacks from L1D to L2 cache lines in M state.", + "Counter": "0,1,2,3", "EventCode": "0x28", "EventName": "L2_L1D_WB_RQSTS.HIT_M", "SampleAfterValue": "200003",
@@ -91,6 +103,7 @@ }, { "BriefDescription": "Not rejected writebacks from L1D to L2 cache lines in S state.", + "Counter": "0,1,2,3", "EventCode": "0x28", "EventName": "L2_L1D_WB_RQSTS.HIT_S", "SampleAfterValue": "200003",
@@ -98,6 +111,7 @@ }, { "BriefDescription": "Count the number of modified Lines evicted from L1 and missed L2. (Non-rejected WBs from the DCU.).", + "Counter": "0,1,2,3", "EventCode": "0x28", "EventName": "L2_L1D_WB_RQSTS.MISS", "SampleAfterValue": "200003",
@@ -105,6 +119,7 @@ }, { "BriefDescription": "L2 cache lines filling L2.", + "Counter": "0,1,2,3", "EventCode": "0xF1", "EventName": "L2_LINES_IN.ALL", "PublicDescription": "This event counts the number of L2 cache lines brought into the L2 cache. Lines are filled into the L2 cache when there was an L2 miss.",
@@ -113,6 +128,7 @@ }, { "BriefDescription": "L2 cache lines in E state filling L2.", + "Counter": "0,1,2,3", "EventCode": "0xF1", "EventName": "L2_LINES_IN.E", "SampleAfterValue": "100003",
@@ -120,6 +136,7 @@ }, { "BriefDescription": "L2 cache lines in I state filling L2.", + "Counter": "0,1,2,3", "EventCode": "0xF1", "EventName": "L2_LINES_IN.I", "SampleAfterValue": "100003",
@@ -127,6 +144,7 @@ }, { "BriefDescription": "L2 cache lines in S state filling L2.", + "Counter": "0,1,2,3", "EventCode": "0xF1", "EventName": "L2_LINES_IN.S", "SampleAfterValue": "100003",
@@ -134,6 +152,7 @@ }, { "BriefDescription": "Clean L2 cache lines evicted by demand.", + "Counter": "0,1,2,3", "EventCode": "0xF2", "EventName": "L2_LINES_OUT.DEMAND_CLEAN", "SampleAfterValue": "100003",
@@ -141,6 +160,7 @@ }, { "BriefDescription": "Dirty L2 cache lines evicted by demand.", + "Counter": "0,1,2,3", "EventCode": "0xF2", "EventName": "L2_LINES_OUT.DEMAND_DIRTY", "SampleAfterValue": "100003",
@@ -148,6 +168,7 @@ }, { "BriefDescription": "Dirty L2 cache lines filling the L2.", + "Counter": "0,1,2,3", "EventCode": "0xF2", "EventName": "L2_LINES_OUT.DIRTY_ALL", "SampleAfterValue": "100003",
@@ -155,6 +176,7 @@ }, { "BriefDescription": "Clean L2 cache lines evicted by L2 prefetch.", + "Counter": "0,1,2,3", "EventCode": "0xF2", "EventName": "L2_LINES_OUT.PF_CLEAN", "SampleAfterValue": "100003",
@@ -162,6 +184,7 @@ }, { "BriefDescription": "Dirty L2 cache lines evicted by L2 prefetch.", + "Counter": "0,1,2,3", "EventCode": "0xF2", "EventName": "L2_LINES_OUT.PF_DIRTY", "SampleAfterValue": "100003",
@@ -169,6 +192,7 @@ }, { "BriefDescription": "L2 code requests.", + "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_RQSTS.ALL_CODE_RD", "SampleAfterValue": "200003",
@@ -176,6 +200,7 @@ }, { "BriefDescription": "Demand Data Read requests.", + "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_RQSTS.ALL_DEMAND_DATA_RD", "SampleAfterValue": "200003",
@@ -183,6 +208,7 @@ }, { "BriefDescription": "Requests from L2 hardware prefetchers.", + "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_RQSTS.ALL_PF", "SampleAfterValue": "200003",
@@ -190,6 +216,7 @@ }, { "BriefDescription": "RFO requests to L2 cache.", + "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_RQSTS.ALL_RFO", "SampleAfterValue": "200003",
@@ -197,6 +224,7 @@ }, { "BriefDescription": "L2 cache hits when fetching instructions, code reads.", + "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_RQSTS.CODE_RD_HIT", "SampleAfterValue": "200003",
@@ -204,6 +232,7 @@ }, { "BriefDescription": "L2 cache misses when fetching instructions.", + "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_RQSTS.CODE_RD_MISS", "SampleAfterValue": "200003",
@@ -211,6 +240,7 @@ }, { "BriefDescription": "Demand Data Read requests that hit L2 cache.", + "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_RQSTS.DEMAND_DATA_RD_HIT", "SampleAfterValue": "200003",
@@ -218,6 +248,7 @@ }, { "BriefDescription": "Requests from the L2 hardware prefetchers that hit L2 cache.", + "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_RQSTS.PF_HIT", "SampleAfterValue": "200003",
@@ -225,6 +256,7 @@ }, { "BriefDescription": "Requests from the L2 hardware prefetchers that miss L2 cache.", + "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_RQSTS.PF_MISS", "SampleAfterValue": "200003",
@@ -232,6 +264,7 @@ }, { "BriefDescription": "RFO requests that hit L2 cache.", + "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_RQSTS.RFO_HIT", "SampleAfterValue": "200003",
@@ -239,6 +272,7 @@ }, { "BriefDescription": "RFO requests that miss L2 cache.", + "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_RQSTS.RFO_MISS", "SampleAfterValue": "200003",
@@ -246,6 +280,7 @@ }, { "BriefDescription": "RFOs that access cache lines in any state.", + "Counter": "0,1,2,3", "EventCode": "0x27", "EventName": "L2_STORE_LOCK_RQSTS.ALL", "SampleAfterValue": "200003",
@@ -253,6 +288,7 @@ }, { "BriefDescription": "RFOs that hit cache lines in E state.", + "Counter": "0,1,2,3", "EventCode": "0x27", "EventName": "L2_STORE_LOCK_RQSTS.HIT_E", "SampleAfterValue": "200003",
@@ -260,6 +296,7 @@ }, { "BriefDescription": "RFOs that hit cache lines in M state.", + "Counter": "0,1,2,3", "EventCode": "0x27", "EventName": "L2_STORE_LOCK_RQSTS.HIT_M", "SampleAfterValue": "200003",
@@ -267,6 +304,7 @@ }, { "BriefDescription": "RFOs that miss cache lines.", + "Counter": "0,1,2,3", "EventCode": "0x27", "EventName": "L2_STORE_LOCK_RQSTS.MISS", "SampleAfterValue": "200003",
@@ -274,6 +312,7 @@ }, { "BriefDescription": "L2 or LLC HW prefetches that access L2 cache.", + "Counter": "0,1,2,3", "EventCode": "0xF0", "EventName": "L2_TRANS.ALL_PF", "SampleAfterValue": "200003",
@@ -281,6 +320,7 @@ }, { "BriefDescription": "Transactions accessing L2 pipe.", + "Counter": "0,1,2,3", "EventCode": "0xF0", "EventName": "L2_TRANS.ALL_REQUESTS", "SampleAfterValue": "200003",
@@ -288,6 +328,7 @@ }, { "BriefDescription": "L2 cache accesses when fetching instructions.", + "Counter": "0,1,2,3", "EventCode": "0xF0", "EventName": "L2_TRANS.CODE_RD", "SampleAfterValue": "200003",
@@ -295,6 +336,7 @@ }, { "BriefDescription": "Demand Data Read requests that access L2 cache.", + "Counter": "0,1,2,3", "EventCode": "0xF0", "EventName": "L2_TRANS.DEMAND_DATA_RD", "SampleAfterValue": "200003",
@@ -302,6 +344,7 @@ }, { "BriefDescription": "L1D writebacks that access L2 cache.", + "Counter": "0,1,2,3", "EventCode": "0xF0", "EventName": "L2_TRANS.L1D_WB", "SampleAfterValue": "200003",
@@ -309,6 +352,7 @@ }, { "BriefDescription": "L2 fill requests that access L2 cache.", + "Counter": "0,1,2,3", "EventCode": "0xF0", "EventName": "L2_TRANS.L2_FILL", "SampleAfterValue": "200003",
@@ -316,6 +360,7 @@ }, { "BriefDescription": "L2 writebacks that access L2 cache.", + "Counter": "0,1,2,3", "EventCode": "0xF0", "EventName": "L2_TRANS.L2_WB", "SampleAfterValue": "200003",
@@ -323,6 +368,7 @@ }, { "BriefDescription": "RFO requests that access L2 cache.", + "Counter": "0,1,2,3", "EventCode": "0xF0", "EventName": "L2_TRANS.RFO", "SampleAfterValue": "200003",
@@ -330,6 +376,7 @@ }, { "BriefDescription": "Cycles when L1D is locked.", + "Counter": "0,1,2,3", "EventCode": "0x63", "EventName": "LOCK_CYCLES.CACHE_LOCK_DURATION", "SampleAfterValue": "2000003",
@@ -337,6 +384,7 @@ }, { "BriefDescription": "Core-originated cacheable demand requests missed LLC.", + "Counter": "0,1,2,3", "EventCode": "0x2E", "EventName": "LONGEST_LAT_CACHE.MISS", "SampleAfterValue": "100003",
@@ -344,6 +392,7 @@ }, { "BriefDescription": "Core-originated cacheable demand requests that refer to LLC.", + "Counter": "0,1,2,3", "EventCode": "0x2E", "EventName": "LONGEST_LAT_CACHE.REFERENCE", "SampleAfterValue": "100003",
@@ -351,6 +400,7 @@ }, { "BriefDescription": "Retired load uops which data sources were LLC and cross-core snoop hits in on-pkg core cache.", + "Counter": "0,1,2,3", "EventCode": "0xD2", "EventName": "MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_HIT", "PublicDescription": "This event counts retired load uops that hit in the last-level cache (L3) and were found in a non-modified state in a neighboring core's private cache (same package). Since the last level cache is inclusive, hits to the L3 may require snooping the private L2 caches of any cores on the same socket that have the line. In this case, a snoop was required, and another L2 had the line in a non-modified state.",
@@ -359,6 +409,7 @@ }, { "BriefDescription": "Retired load uops which data sources were HitM responses from shared LLC.", + "Counter": "0,1,2,3", "EventCode": "0xD2", "EventName": "MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_HITM", "PublicDescription": "This event counts retired load uops that hit in the last-level cache (L3) and were found in a non-modified state in a neighboring core's private cache (same package). Since the last level cache is inclusive, hits to the L3 may require snooping the private L2 caches of any cores on the same socket that have the line. In this case, a snoop was required, and another L2 had the line in a modified state, so the line had to be invalidated in that L2 cache and transferred to the requesting L2.",
@@ -367,6 +418,7 @@ }, { "BriefDescription": "Retired load uops which data sources were LLC hit and cross-core snoop missed in on-pkg core cache.", + "Counter": "0,1,2,3", "EventCode": "0xD2", "EventName": "MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_MISS", "SampleAfterValue": "20011",
@@ -374,6 +426,7 @@ }, { "BriefDescription": "Retired load uops which data sources were hits in LLC without snoops required.", + "Counter": "0,1,2,3", "EventCode": "0xD2", "EventName": "MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_NONE", "SampleAfterValue": "100003",
@@ -381,6 +434,7 @@ }, { "BriefDescription": "Data from local DRAM either Snoop not needed or Snoop Miss (RspI)", + "Counter": "0,1,2,3", "EventCode": "0xD3", "EventName": "MEM_LOAD_UOPS_LLC_MISS_RETIRED.LOCAL_DRAM", "SampleAfterValue": "100007",
@@ -388,6 +442,7 @@ }, { "BriefDescription": "Data from remote DRAM either Snoop not needed or Snoop Miss (RspI)", + "Counter": "0,1,2,3", "EventCode": "0xD3", "EventName": "MEM_LOAD_UOPS_LLC_MISS_RETIRED.REMOTE_DRAM", "SampleAfterValue": "100007",
@@ -395,6 +450,7 @@ }, { "BriefDescription": "Retired load uops which data sources were load uops missed L1 but hit FB due to preceding miss to the same cache line with data not ready.", + "Counter": "0,1,2,3", "EventCode": "0xD1", "EventName": "MEM_LOAD_UOPS_RETIRED.HIT_LFB", "PEBS": "1",
@@ -403,6 +459,7 @@ }, { "BriefDescription": "Retired load uops with L1 cache hits as data sources.", + "Counter": "0,1,2,3", "EventCode": "0xD1", "EventName": "MEM_LOAD_UOPS_RETIRED.L1_HIT", "PEBS": "1",
@@ -411,6 +468,7 @@ }, { "BriefDescription": "Retired load uops with L2 cache hits as data sources.", + "Counter": "0,1,2,3", "EventCode": "0xD1", "EventName": "MEM_LOAD_UOPS_RETIRED.L2_HIT", "PEBS": "1",
@@ -419,6 +477,7 @@ }, { "BriefDescription": "Retired load uops which data sources were data hits in LLC without snoops required.", + "Counter": "0,1,2,3", "EventCode": "0xD1", "EventName": "MEM_LOAD_UOPS_RETIRED.LLC_HIT", "PublicDescription": "This event counts retired load uops that hit in the last-level (L3) cache without snoops required.",
@@ -427,6 +486,7 @@ }, { "BriefDescription": "Miss in last-level (L3) cache. Excludes Unknown data-source.", + "Counter": "0,1,2,3", "EventCode": "0xD1", "EventName": "MEM_LOAD_UOPS_RETIRED.LLC_MISS", "SampleAfterValue": "100007",
@@ -434,6 +494,7 @@ }, { "BriefDescription": "All retired load uops.", + "Counter": "0,1,2,3", "EventCode": "0xD0", "EventName": "MEM_UOPS_RETIRED.ALL_LOADS", "PEBS": "1",
@@ -443,6 +504,7 @@ }, { "BriefDescription": "All retired store uops.", + "Counter": "0,1,2,3", "EventCode": "0xD0", "EventName": "MEM_UOPS_RETIRED.ALL_STORES", "PEBS": "1",
@@ -452,6 +514,7 @@ }, { "BriefDescription": "Retired load uops with locked access.", + "Counter": "0,1,2,3", "EventCode": "0xD0", "EventName": "MEM_UOPS_RETIRED.LOCK_LOADS", "PEBS": "1",
@@ -460,6 +523,7 @@ }, { "BriefDescription": "Retired load uops that split across a cacheline boundary.", + "Counter": "0,1,2,3", "EventCode": "0xD0", "EventName": "MEM_UOPS_RETIRED.SPLIT_LOADS", "PEBS": "1",
@@ -469,6 +533,7 @@ }, { "BriefDescription": "Retired store uops that split across a cacheline boundary.", + "Counter": "0,1,2,3", "EventCode": "0xD0", "EventName": "MEM_UOPS_RETIRED.SPLIT_STORES", "PEBS": "1",
@@ -478,6 +543,7 @@ }, { "BriefDescription": "Retired load uops that miss the STLB.", + "Counter": "0,1,2,3", "EventCode": "0xD0", "EventName": "MEM_UOPS_RETIRED.STLB_MISS_LOADS", "PEBS": "1",
@@ -486,6 +552,7 @@ }, { "BriefDescription": "Retired store uops that miss the STLB.", + "Counter": "0,1,2,3", "EventCode": "0xD0", "EventName": "MEM_UOPS_RETIRED.STLB_MISS_STORES", "PEBS": "1",
@@ -494,6 +561,7 @@ }, { "BriefDescription": "Demand and prefetch data reads.", + "Counter": "0,1,2,3", "EventCode": "0xB0", "EventName": "OFFCORE_REQUESTS.ALL_DATA_RD", "SampleAfterValue": "100003",
@@ -501,6 +569,7 @@ }, { "BriefDescription": "Cacheable and non-cacheable code read requests.", + "Counter": "0,1,2,3", "EventCode": "0xB0", "EventName": "OFFCORE_REQUESTS.DEMAND_CODE_RD", "SampleAfterValue": "100003",
@@ -508,6 +577,7 @@ }, { "BriefDescription": "Demand Data Read requests sent to uncore.", + "Counter": "0,1,2,3", "EventCode": "0xB0", "EventName": "OFFCORE_REQUESTS.DEMAND_DATA_RD", "SampleAfterValue": "100003",
@@ -515,6 +585,7 @@ }, { "BriefDescription": "Demand RFO requests including regular RFOs, locks, ItoM.", + "Counter": "0,1,2,3", "EventCode": "0xB0", "EventName": "OFFCORE_REQUESTS.DEMAND_RFO", "SampleAfterValue": "100003",
@@ -522,6 +593,7 @@ }, { "BriefDescription": "Cases when offcore requests buffer cannot take more entries for core.", + "Counter": "0,1,2,3", "EventCode": "0xB2", "EventName": "OFFCORE_REQUESTS_BUFFER.SQ_FULL", "SampleAfterValue": "2000003",
@@ -529,6 +601,7 @@ }, { "BriefDescription": "Offcore outstanding cacheable Core Data Read transactions in SuperQueue (SQ), queue to uncore.", + "Counter": "0,1,2,3", "EventCode": "0x60", "EventName": "OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD", "SampleAfterValue": "2000003",
@@ -536,6 +609,7 @@ }, { "BriefDescription": "Cycles when offcore outstanding cacheable Core Data Read transactions are present in SuperQueue (SQ), queue to uncore.", + "Counter": "0,1,2,3", "CounterMask": "1", "EventCode": "0x60", "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD",
@@ -544,6 +618,7 @@ }, { "BriefDescription": "Cycles when offcore outstanding Demand Data Read transactions are present in SuperQueue (SQ), queue to uncore.", + "Counter": "0,1,2,3", "CounterMask": "1", "EventCode": "0x60", "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_DATA_RD",
@@ -552,6 +627,7 @@ }, { "BriefDescription": "Offcore outstanding demand rfo reads transactions in SuperQueue (SQ), queue to uncore, every cycle.", + "Counter": "0,1,2,3", "CounterMask": "1", "EventCode": "0x60", "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO",
@@ -560,6 +636,7 @@ }, { "BriefDescription": "Offcore outstanding Demand Data Read transactions in uncore queue.", + "Counter": "0,1,2,3", "EventCode": "0x60", "EventName": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD", "SampleAfterValue": "2000003",
@@ -567,6 +644,7 @@ }, { "BriefDescription": "Cycles with at least 6 offcore outstanding Demand Data Read transactions in uncore queue.", + "Counter": "0,1,2,3", "CounterMask": "6", "EventCode": "0x60", "EventName": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD_C6",
@@ -575,6 +653,7 @@ }, { "BriefDescription": "Offcore outstanding RFO store transactions in SuperQueue (SQ), queue to uncore.", + "Counter": "0,1,2,3", "EventCode": "0x60", "EventName": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_RFO", "SampleAfterValue": "2000003",
@@ -582,6 +661,7 @@ }, { "BriefDescription": "Counts all demand & prefetch data reads", + "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7",
@@ -591,6 +671,7 @@ }, { "BriefDescription": "Counts demand & prefetch data reads that hit in the LLC and the snoop to one of the sibling cores hits the line in M state and the line is forwarded", + "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.LLC_HIT.HITM_OTHER_CORE", "MSRIndex": "0x1a6,0x1a7",
@@ -600,6 +681,7 @@ }, { "BriefDescription": "Counts demand & prefetch data reads that hit in the LLC and the snoops to sibling cores hit in either E/S state and the line is not forwarded", + "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.LLC_HIT.HIT_OTHER_CORE_NO_FWD", "MSRIndex": "0x1a6,0x1a7",
@@ -609,6 +691,7 @@ }, { "BriefDescription": "Counts demand & prefetch data reads that hit in the LLC and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores", + "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.LLC_HIT.NO_SNOOP_NEEDED", "MSRIndex": "0x1a6,0x1a7",
@@ -618,6 +701,7 @@ }, { "BriefDescription": "Counts demand & prefetch data reads that hit in the LLC and sibling core snoop returned a clean response", + "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.LLC_HIT.SNOOP_MISS", "MSRIndex": "0x1a6,0x1a7",
@@ -627,6 +711,7 @@ }, { "BriefDescription": "Counts all prefetch data reads that hit the LLC", + "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.LLC_HIT.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7",
@@ -636,6 +721,7 @@ }, { "BriefDescription": "Counts prefetch data reads that hit in the LLC and the snoop to one of the sibling cores hits the line in M state and the line is forwarded", + "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.LLC_HIT.HITM_OTHER_CORE", "MSRIndex": "0x1a6,0x1a7",
@@ -645,6 +731,7 @@ }, { "BriefDescription": "Counts prefetch data reads that hit in the LLC and the snoops to sibling cores hit in either E/S state and the line is not forwarded", + "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.LLC_HIT.HIT_OTHER_CORE_NO_FWD", "MSRIndex": "0x1a6,0x1a7",
@@ -654,6 +741,7 @@ }, { "BriefDescription": "Counts prefetch data reads that hit in the LLC and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores", + "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.LLC_HIT.NO_SNOOP_NEEDED", "MSRIndex": "0x1a6,0x1a7",
@@ -663,6 +751,7 @@ }, { "BriefDescription": "Counts prefetch data reads that hit in the LLC and sibling core snoop returned a clean response", + "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.LLC_HIT.SNOOP_MISS", "MSRIndex": "0x1a6,0x1a7",
@@ -672,6 +761,7 @@ }, { "BriefDescription": "Counts all data/code/rfo references (demand & prefetch)", + "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.ALL_READS.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7",
@@ -681,6 +771,7 @@ }, { "BriefDescription": "Counts all data/code/rfo reads (demand & prefetch) that hit in the LLC", + "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.ALL_READS.LLC_HIT.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7",
@@ -690,6 +781,7 @@ }, { "BriefDescription": "Counts all data/code/rfo reads (demand & prefetch) that hit in the LLC and the snoop to one of the sibling cores hits the line in M state and the line is forwarded", + "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.ALL_READS.LLC_HIT.HITM_OTHER_CORE", "MSRIndex": "0x1a6,0x1a7",
@@ -699,6 +791,7 @@ }, { "BriefDescription": "Counts all data/code/rfo reads (demand & prefetch) that hit in the LLC and the snoops to sibling cores hit in either E/S state and the line is not forwarded", + "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.ALL_READS.LLC_HIT.HIT_OTHER_CORE_NO_FWD", "MSRIndex": "0x1a6,0x1a7",
@@ -708,6 +801,7 @@ }, { "BriefDescription": "Counts all data/code/rfo reads (demand & prefetch) that hit in the LLC and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores", + "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.ALL_READS.LLC_HIT.NO_SNOOP_NEEDED", "MSRIndex": "0x1a6,0x1a7",
@@ -717,6 +811,7 @@ }, { "BriefDescription": "Counts all data/code/rfo reads (demand & prefetch) that hit in the LLC and sibling core snoop returned a clean response", + "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.ALL_READS.LLC_HIT.SNOOP_MISS", "MSRIndex": "0x1a6,0x1a7",
@@ -726,6 +821,7 @@ }, { "BriefDescription": "Counts all demand & prefetch prefetch RFOs", + "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.ALL_RFO.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7",
@@ -735,6 +831,7 @@ }, { "BriefDescription": "Counts all writebacks from the core to the LLC", + "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.COREWB.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7",
@@ -744,6 +841,7 @@ }, { "BriefDescription": "Counts all demand code reads", + "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7",
@@ -753,6 +851,7 @@ }, { "BriefDescription": "Counts all demand code reads that hit in the LLC", + "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.LLC_HIT.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7",
@@ -762,6 +861,7 @@ }, { "BriefDescription": "Counts all demand data reads", + "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7",
@@ -771,6 +871,7 @@ }, { "BriefDescription": "Counts all demand data reads that hit in the LLC", + "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.LLC_HIT.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7",
@@ -780,6 +881,7 @@ }, { "BriefDescription": "Counts demand data reads that hit in the LLC and the snoop to one of the sibling cores hits the line in M state and the line is forwarded", + "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.LLC_HIT.HITM_OTHER_CORE", "MSRIndex": "0x1a6,0x1a7",
@@ -789,6 +891,7 @@ }, { "BriefDescription": "Counts demand data reads that hit in the LLC and the snoops to sibling cores hit in either E/S state and the line is not forwarded", + "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.LLC_HIT.HIT_OTHER_CORE_NO_FWD", "MSRIndex": "0x1a6,0x1a7",
@@ -798,6 +901,7 @@ }, { "BriefDescription": "Counts demand data reads that hit in the LLC and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores", + "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.LLC_HIT.NO_SNOOP_NEEDED", "MSRIndex": "0x1a6,0x1a7",
@@ -807,6 +911,7 @@ }, { "BriefDescription": "Counts demand data reads that hit in the LLC and sibling core snoop returned a clean response", + "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.LLC_HIT.SNOOP_MISS", "MSRIndex": "0x1a6,0x1a7",
@@ -816,6 +921,7 @@ }, { "BriefDescription": "Counts all demand rfo's", + "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7",
@@ -825,6 +931,7 @@ }, { "BriefDescription": "Counts L2 hints sent to LLC to keep a line from being evicted out of the core caches", + "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.OTHER.LRU_HINTS", "MSRIndex": "0x1a6,0x1a7",
@@ -834,6 +941,7 @@ }, { "BriefDescription": "Counts miscellaneous accesses that include port i/o, MMIO and uncacheable memory accesses", + "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.OTHER.PORTIO_MMIO_UC", "MSRIndex": "0x1a6,0x1a7",
@@ -843,6 +951,7 @@ }, { "BriefDescription": "Counts all prefetch (that bring data to L2) code reads that hit in the LLC", + "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.LLC_HIT.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7",
@@ -852,6 +961,7 @@ }, { "BriefDescription": "Counts prefetch (that bring data to L2) data reads that hit in the LLC", + "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.LLC_HIT.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7",
@@ -861,6 +971,7 @@ }, { "BriefDescription": "Counts prefetch (that bring data to L2) data reads that hit in the LLC and the snoop to one of the sibling cores hits the line in M state and the line is forwarded", + "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.LLC_HIT.HITM_OTHER_CORE", "MSRIndex": "0x1a6,0x1a7",
@@ -870,6 +981,7 @@ }, { "BriefDescription": "Counts prefetch (that bring data to L2) data reads that hit in the LLC and the snoops to sibling cores hit in either E/S state and the line is not forwarded", + "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.LLC_HIT.HIT_OTHER_CORE_NO_FWD", "MSRIndex": "0x1a6,0x1a7",
@@ -879,6 +991,7 @@ }, { "BriefDescription": "Counts prefetch (that bring data to L2) data reads that hit in the LLC and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores", + "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.LLC_HIT.NO_SNOOP_NEEDED", "MSRIndex": "0x1a6,0x1a7",
@@ -888,6 +1001,7 @@ }, { "BriefDescription": "Counts prefetch (that bring data to L2) data reads that hit in the LLC and the snoops sent to sibling cores return clean response", + "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.LLC_HIT.SNOOP_MISS", "MSRIndex": "0x1a6,0x1a7",
@@ -897,6 +1011,7 @@ }, { "BriefDescription": "Counts all prefetch (that bring data to LLC only) code reads that hit in the LLC", + "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.PF_LLC_CODE_RD.LLC_HIT.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7",
@@ -906,6 +1021,7 @@ }, { "BriefDescription": "Counts prefetch (that bring data to LLC only) data reads that hit in the LLC", + "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.PF_LLC_DATA_RD.LLC_HIT.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7",
@@ -915,6 +1031,7 @@ }, { "BriefDescription": "Counts prefetch (that bring data to LLC only) data reads that hit in the LLC and the snoop to one of the sibling cores hits the line in M state and the line is forwarded", + "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.PF_LLC_DATA_RD.LLC_HIT.HITM_OTHER_CORE", "MSRIndex": "0x1a6,0x1a7",
@@ -924,6 +1041,7 @@ }, { "BriefDescription": "Counts prefetch (that bring data to LLC only) data reads that hit in the LLC and the snoops to sibling cores hit in either E/S state and the line is not forwarded", + "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.PF_LLC_DATA_RD.LLC_HIT.HIT_OTHER_CORE_NO_FWD", "MSRIndex": "0x1a6,0x1a7",
@@ -933,6 +1051,7 @@ }, { "BriefDescription": "Counts prefetch (that bring data to LLC only) data reads that hit in the LLC and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores", + "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.PF_LLC_DATA_RD.LLC_HIT.NO_SNOOP_NEEDED", "MSRIndex": "0x1a6,0x1a7",
@@ -942,6 +1061,7 @@ }, { "BriefDescription": "Counts prefetch (that bring data to LLC only) data reads that hit in the LLC and the snoops sent to sibling cores return clean response", + "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.PF_LLC_DATA_RD.LLC_HIT.SNOOP_MISS", "MSRIndex": "0x1a6,0x1a7",
@@ -951,6 +1071,7 @@ }, { "BriefDescription": "Counts requests where the address of an atomic lock instruction spans a cache line boundary or the lock instruction is executed on uncacheable address", + "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.SPLIT_LOCK_UC_LOCK.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7",
@@ -960,6 +1081,7 @@ }, { "BriefDescription": "Counts non-temporal stores", + "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.STREAMING_STORES.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7",
@@ -969,6 +1091,7 @@ }, { "BriefDescription": "Split locks in SQ.", + "Counter": "0,1,2,3", "EventCode": "0xF4", "EventName": "SQ_MISC.SPLIT_LOCK", "SampleAfterValue": "100003",
tools/perf/pmu-events/arch/x86/jaketown/counter.json new file +52 -0
53 lines not on this page · raw message
tools/perf/pmu-events/arch/x86/jaketown/floating-point.json +15 -0
@@ -1,6 +1,7 @@ [ { "BriefDescription": "Cycles with any input/output SSE or FP assist.", + "Counter": "0,1,2,3", "CounterMask": "1", "EventCode": "0xCA", "EventName": "FP_ASSIST.ANY",
@@ -9,6 +10,7 @@ }, { "BriefDescription": "Number of SIMD FP assists due to input values.", + "Counter": "0,1,2,3", "EventCode": "0xCA", "EventName": "FP_ASSIST.SIMD_INPUT", "SampleAfterValue": "100003",
@@ -16,6 +18,7 @@ }, { "BriefDescription": "Number of SIMD FP assists due to Output values.", + "Counter": "0,1,2,3", "EventCode": "0xCA", "EventName": "FP_ASSIST.SIMD_OUTPUT", "SampleAfterValue": "100003",
@@ -23,6 +26,7 @@ }, { "BriefDescription": "Number of X87 assists due to input value.", + "Counter": "0,1,2,3", "EventCode": "0xCA", "EventName": "FP_ASSIST.X87_INPUT", "SampleAfterValue": "100003",
@@ -30,6 +34,7 @@ }, { "BriefDescription": "Number of X87 assists due to output value.", + "Counter": "0,1,2,3", "EventCode": "0xCA", "EventName": "FP_ASSIST.X87_OUTPUT", "SampleAfterValue": "100003",
@@ -37,6 +42,7 @@ }, { "BriefDescription": "Number of SSE* or AVX-128 FP Computational packed double-precision uops issued this cycle.", + "Counter": "0,1,2,3", "EventCode": "0x10", "EventName": "FP_COMP_OPS_EXE.SSE_PACKED_DOUBLE", "SampleAfterValue": "2000003",
@@ -44,6 +50,7 @@ }, { "BriefDescription": "Number of SSE* or AVX-128 FP Computational packed single-precision uops issued this cycle.", + "Counter": "0,1,2,3", "EventCode": "0x10", "EventName": "FP_COMP_OPS_EXE.SSE_PACKED_SINGLE", "SampleAfterValue": "2000003",
@@ -51,6 +58,7 @@ }, { "BriefDescription": "Number of SSE* or AVX-128 FP Computational scalar double-precision uops issued this cycle.", + "Counter": "0,1,2,3", "EventCode": "0x10", "EventName": "FP_COMP_OPS_EXE.SSE_SCALAR_DOUBLE", "SampleAfterValue": "2000003",
@@ -58,6 +66,7 @@ }, { "BriefDescription": "Number of SSE* or AVX-128 FP Computational scalar single-precision uops issued this cycle.", + "Counter": "0,1,2,3", "EventCode": "0x10", "EventName": "FP_COMP_OPS_EXE.SSE_SCALAR_SINGLE", "SampleAfterValue": "2000003",
@@ -65,6 +74,7 @@ }, { "BriefDescription": "Number of FP Computational Uops Executed this cycle. The number of FADD, FSUB, FCOM, FMULs, integer MULs and IMULs, FDIVs, FPREMs, FSQRTS, integer DIVs, and IDIVs. This event does not distinguish an FADD used in the middle of a transcendental flow from a s.", + "Counter": "0,1,2,3", "EventCode": "0x10", "EventName": "FP_COMP_OPS_EXE.X87", "SampleAfterValue": "2000003",
@@ -72,6 +82,7 @@ }, { "BriefDescription": "Number of GSSE memory assist for stores. GSSE microcode assist is being invoked whenever the hardware is unable to properly handle GSSE-256b operations.", + "Counter": "0,1,2,3", "EventCode": "0xC1", "EventName": "OTHER_ASSISTS.AVX_STORE", "SampleAfterValue": "100003",
@@ -79,6 +90,7 @@ }, { "BriefDescription": "Number of transitions from AVX-256 to legacy SSE when penalty applicable.", + "Counter": "0,1,2,3", "EventCode": "0xC1", "EventName": "OTHER_ASSISTS.AVX_TO_SSE", "SampleAfterValue": "100003",
@@ -86,6 +98,7 @@ }, { "BriefDescription": "Number of transitions from SSE to AVX-256 when penalty applicable.", + "Counter": "0,1,2,3", "EventCode": "0xC1", "EventName": "OTHER_ASSISTS.SSE_TO_AVX", "SampleAfterValue": "100003",
@@ -93,6 +106,7 @@ }, { "BriefDescription": "Number of AVX-256 Computational FP double precision uops issued this cycle.", + "Counter": "0,1,2,3", "EventCode": "0x11", "EventName": "SIMD_FP_256.PACKED_DOUBLE", "SampleAfterValue": "2000003",
@@ -100,6 +114,7 @@ }, { "BriefDescription": "Number of GSSE-256 Computational FP single precision uops issued this cycle.", + "Counter": "0,1,2,3", "EventCode": "0x11", "EventName": "SIMD_FP_256.PACKED_SINGLE", "SampleAfterValue": "2000003",
tools/perf/pmu-events/arch/x86/jaketown/frontend.json +32 -0
@@ -1,6 +1,7 @@ [ { "BriefDescription": "Counts the total number when the front end is resteered, mainly when the BPU cannot provide a correct prediction and this is corrected by other branch handling mechanisms at the front end.", + "Counter": "0,1,2,3", "EventCode": "0xE6", "EventName": "BACLEARS.ANY", "SampleAfterValue": "100003",
@@ -8,6 +9,7 @@ }, { "BriefDescription": "Decode Stream Buffer (DSB)-to-MITE switches.", + "Counter": "0,1,2,3", "EventCode": "0xAB", "EventName": "DSB2MITE_SWITCHES.COUNT", "SampleAfterValue": "2000003",
@@ -15,6 +17,7 @@ }, { "BriefDescription": "Decode Stream Buffer (DSB)-to-MITE switch true penalty cycles.", + "Counter": "0,1,2,3", "EventCode": "0xAB", "EventName": "DSB2MITE_SWITCHES.PENALTY_CYCLES", "PublicDescription": "This event counts the cycles attributed to a switch from the Decoded Stream Buffer (DSB), which holds decoded instructions, to the legacy decode pipeline. It excludes cycles when the back-end cannot accept new micro-ops. The penalty for these switches is potentially several cycles of instruction starvation, where no micro-ops are delivered to the back-end.",
@@ -23,6 +26,7 @@ }, { "BriefDescription": "Cases of cancelling valid Decode Stream Buffer (DSB) fill not because of exceeding way limit.", + "Counter": "0,1,2,3", "EventCode": "0xAC", "EventName": "DSB_FILL.ALL_CANCEL", "SampleAfterValue": "2000003",
@@ -30,6 +34,7 @@ }, { "BriefDescription": "Cycles when Decode Stream Buffer (DSB) fill encounter more than 3 Decode Stream Buffer (DSB) lines.", + "Counter": "0,1,2,3", "EventCode": "0xAC", "EventName": "DSB_FILL.EXCEED_DSB_LINES", "SampleAfterValue": "2000003",
@@ -37,6 +42,7 @@ }, { "BriefDescription": "Cases of cancelling valid DSB fill not because of exceeding way limit.", + "Counter": "0,1,2,3", "EventCode": "0xAC", "EventName": "DSB_FILL.OTHER_CANCEL", "SampleAfterValue": "2000003",
@@ -44,6 +50,7 @@ }, { "BriefDescription": "Number of Instruction Cache, Streaming Buffer and Victim Cache Reads. both cacheable and noncacheable, including UC fetches.", + "Counter": "0,1,2,3", "EventCode": "0x80", "EventName": "ICACHE.HIT", "SampleAfterValue": "2000003",
@@ -51,6 +58,7 @@ }, { "BriefDescription": "Instruction cache, streaming buffer and victim cache misses.", + "Counter": "0,1,2,3", "EventCode": "0x80", "EventName": "ICACHE.MISSES", "PublicDescription": "This event counts the number of instruction cache, streaming buffer and victim cache misses. Counting includes unchacheable accesses.",
@@ -59,6 +67,7 @@ }, { "BriefDescription": "Cycles Decode Stream Buffer (DSB) is delivering 4 Uops.", + "Counter": "0,1,2,3", "CounterMask": "4", "EventCode": "0x79", "EventName": "IDQ.ALL_DSB_CYCLES_4_UOPS",
@@ -67,6 +76,7 @@ }, { "BriefDescription": "Cycles Decode Stream Buffer (DSB) is delivering any Uop.", + "Counter": "0,1,2,3", "CounterMask": "1", "EventCode": "0x79", "EventName": "IDQ.ALL_DSB_CYCLES_ANY_UOPS",
@@ -75,6 +85,7 @@ }, { "BriefDescription": "Cycles MITE is delivering 4 Uops.", + "Counter": "0,1,2,3", "CounterMask": "4", "EventCode": "0x79", "EventName": "IDQ.ALL_MITE_CYCLES_4_UOPS",
@@ -83,6 +94,7 @@ }, { "BriefDescription": "Cycles MITE is delivering any Uop.", + "Counter": "0,1,2,3", "CounterMask": "1", "EventCode": "0x79", "EventName": "IDQ.ALL_MITE_CYCLES_ANY_UOPS",
@@ -91,6 +103,7 @@ }, { "BriefDescription": "Cycles when uops are being delivered to Instruction Decode Queue (IDQ) from Decode Stream Buffer (DSB) path.", + "Counter": "0,1,2,3", "CounterMask": "1", "EventCode": "0x79", "EventName": "IDQ.DSB_CYCLES",
@@ -99,6 +112,7 @@ }, { "BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path.", + "Counter": "0,1,2,3", "EventCode": "0x79", "EventName": "IDQ.DSB_UOPS", "SampleAfterValue": "2000003",
@@ -106,6 +120,7 @@ }, { "BriefDescription": "Instruction Decode Queue (IDQ) empty cycles.", + "Counter": "0,1,2,3", "EventCode": "0x79", "EventName": "IDQ.EMPTY", "SampleAfterValue": "2000003",
@@ -113,6 +128,7 @@ }, { "BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) from MITE path.", + "Counter": "0,1,2,3", "EventCode": "0x79", "EventName": "IDQ.MITE_ALL_UOPS", "SampleAfterValue": "2000003",
@@ -120,6 +136,7 @@ }, { "BriefDescription": "Cycles when uops are being delivered to Instruction Decode Queue (IDQ) from MITE path.", + "Counter": "0,1,2,3", "CounterMask": "1", "EventCode": "0x79", "EventName": "IDQ.MITE_CYCLES",
@@ -128,6 +145,7 @@ }, { "BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) from MITE path.", + "Counter": "0,1,2,3", "EventCode": "0x79", "EventName": "IDQ.MITE_UOPS", "SampleAfterValue": "2000003",
@@ -135,6 +153,7 @@ }, { "BriefDescription": "Cycles when uops are being delivered to Instruction Decode Queue (IDQ) while Microcode Sequencer (MS) is busy.", + "Counter": "0,1,2,3", "CounterMask": "1", "EventCode": "0x79", "EventName": "IDQ.MS_CYCLES",
@@ -144,6 +163,7 @@ }, { "BriefDescription": "Cycles when uops initiated by Decode Stream Buffer (DSB) are being delivered to Instruction Decode Queue (IDQ) while Microcode Sequencer (MS) is busy.", + "Counter": "0,1,2,3", "CounterMask": "1", "EventCode": "0x79", "EventName": "IDQ.MS_DSB_CYCLES",
@@ -152,6 +172,7 @@ }, { "BriefDescription": "Deliveries to Instruction Decode Queue (IDQ) initiated by Decode Stream Buffer (DSB) while Microcode Sequencer (MS) is busy.", + "Counter": "0,1,2,3", "CounterMask": "1", "EdgeDetect": "1", "EventCode": "0x79",
@@ -161,6 +182,7 @@ }, { "BriefDescription": "Uops initiated by Decode Stream Buffer (DSB) that are being delivered to Instruction Decode Queue (IDQ) while Microcode Sequencer (MS) is busy.", + "Counter": "0,1,2,3", "EventCode": "0x79", "EventName": "IDQ.MS_DSB_UOPS", "SampleAfterValue": "2000003",
@@ -168,6 +190,7 @@ }, { "BriefDescription": "Uops initiated by MITE and delivered to Instruction Decode Queue (IDQ) while Microcode Sequencer (MS) is busy.", + "Counter": "0,1,2,3", "EventCode": "0x79", "EventName": "IDQ.MS_MITE_UOPS", "SampleAfterValue": "2000003",
@@ -175,6 +198,7 @@ }, { "BriefDescription": "Number of switches from DSB (Decode Stream Buffer) or MITE (legacy decode pipeline) to the Microcode Sequencer.", + "Counter": "0,1,2,3", "CounterMask": "1", "EdgeDetect": "1", "EventCode": "0x79",
@@ -184,6 +208,7 @@ }, { "BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) while Microcode Sequencer (MS) is busy.", + "Counter": "0,1,2,3", "EventCode": "0x79", "EventName": "IDQ.MS_UOPS", "SampleAfterValue": "2000003",
@@ -191,6 +216,7 @@ }, { "BriefDescription": "Uops not delivered to Resource Allocation Table (RAT) per thread when backend of the machine is not stalled .", + "Counter": "0,1,2,3", "EventCode": "0x9C", "EventName": "IDQ_UOPS_NOT_DELIVERED.CORE", "PublicDescription": "This event counts the number of uops not delivered to the back-end per cycle, per thread, when the back-end was not stalled. In the ideal case 4 uops can be delivered each cycle. The event counts the undelivered uops - so if 3 were delivered in one cycle, the counter would be incremented by 1 for that cycle (4 - 3). If the back-end is stalled, the count for this event is not incremented even when uops were not delivered, because the back-end would not have been able to accept them. This event is used in determining the front-end bound category of the top-down pipeline slots characterization.",
@@ -199,6 +225,7 @@ }, { "BriefDescription": "Cycles per thread when 4 or more uops are not delivered to Resource Allocation Table (RAT) when backend of the machine is not stalled.", + "Counter": "0,1,2,3", "CounterMask": "4", "EventCode": "0x9C", "EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE",
@@ -207,6 +234,7 @@ }, { "BriefDescription": "Counts cycles FE delivered 4 uops or Resource Allocation Table (RAT) was stalling FE.", + "Counter": "0,1,2,3", "CounterMask": "1", "EventCode": "0x9C", "EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_FE_WAS_OK",
@@ -216,6 +244,7 @@ }, { "BriefDescription": "Cycles when 1 or more uops were delivered to the by the front end.", + "Counter": "0,1,2,3", "CounterMask": "4", "EventCode": "0x9C", "EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_GE_1_UOP_DELIV.CORE",
@@ -225,6 +254,7 @@ }, { "BriefDescription": "Cycles per thread when 3 or more uops are not delivered to Resource Allocation Table (RAT) when backend of the machine is not stalled.", + "Counter": "0,1,2,3", "CounterMask": "3", "EventCode": "0x9C", "EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_LE_1_UOP_DELIV.CORE",
@@ -233,6 +263,7 @@ }, { "BriefDescription": "Cycles with less than 2 uops delivered by the front end.", + "Counter": "0,1,2,3", "CounterMask": "2", "EventCode": "0x9C", "EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_LE_2_UOP_DELIV.CORE",
@@ -241,6 +272,7 @@ }, { "BriefDescription": "Cycles with less than 3 uops delivered by the front end.", + "Counter": "0,1,2,3", "CounterMask": "1", "EventCode": "0x9C", "EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_LE_3_UOP_DELIV.CORE",
tools/perf/pmu-events/arch/x86/jaketown/jkt-metrics.json +12 -12
@@ -73,7 +73,7 @@ "BriefDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend", "MetricConstraint": "NO_GROUP_EVENTS_NMI", "MetricExpr": "1 - (tma_frontend_bound + tma_bad_speculation + tma_retiring)", - "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", + "MetricGroup": "BvOB;TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_backend_bound", "MetricThreshold": "tma_backend_bound > 0.2", "MetricgroupNoGroup": "TopdownL1",
@@ -94,7 +94,7 @@ "BriefDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction", "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "BR_MISP_RETIRED.ALL_BRANCHES / (BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT) * tma_bad_speculation", - "MetricGroup": "BadSpec;BrMispredicts;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueBM", + "MetricGroup": "BadSpec;BrMispredicts;BvMP;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueBM", "MetricName": "tma_branch_mispredicts", "MetricThreshold": "tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", "MetricgroupNoGroup": "TopdownL2",
@@ -124,7 +124,7 @@ { "BriefDescription": "This metric represents fraction of cycles where the Divider unit was active", "MetricExpr": "ARITH.FPU_DIV_ACTIVE / tma_info_core_core_clks", - "MetricGroup": "TopdownL3;tma_L3_group;tma_core_bound_group", + "MetricGroup": "BvCB;TopdownL3;tma_L3_group;tma_core_bound_group", "MetricName": "tma_divider", "MetricThreshold": "tma_divider > 0.2 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)", "PublicDescription": "This metric represents fraction of cycles where the Divider unit was active. Divide and square root instructions are performed by the Divider unit and can take considerably longer latency than integer or Floating Point addition; subtraction; or multiplication. Sample with: ARITH.DIVIDER_UOPS",
@@ -152,7 +152,7 @@ { "BriefDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses", "MetricExpr": "(7 * DTLB_LOAD_MISSES.STLB_HIT + DTLB_LOAD_MISSES.WALK_DURATION) / tma_info_thread_clks", - "MetricGroup": "MemoryTLB;TopdownL4;tma_L4_group;tma_issueTLB;tma_l1_bound_group", + "MetricGroup": "BvMT;MemoryTLB;TopdownL4;tma_L4_group;tma_issueTLB;tma_l1_bound_group", "MetricName": "tma_dtlb_load", "MetricThreshold": "tma_dtlb_load > 0.1", "PublicDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses. TLBs (Translation Look-aside Buffers) are processor caches for recently used entries out of the Page Tables that are used to map virtual- to physical-addresses by the operating system. This metric approximates the potential delay of demand loads missing the first-level data TLB (assuming worst case scenario with back to back misses to different pages). This includes hitting in the second-level TLB (STLB) as well as performing a hardware page walk on an STLB miss. Sample with: MEM_UOPS_RETIRED.STLB_MISS_LOADS_PS. Related metrics: tma_dtlb_store",
@@ -226,7 +226,7 @@ { "BriefDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend", "MetricExpr": "IDQ_UOPS_NOT_DELIVERED.CORE / tma_info_thread_slots", - "MetricGroup": "PGO;TmaL1;TopdownL1;tma_L1_group", + "MetricGroup": "BvFB;BvIO;PGO;TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_frontend_bound", "MetricThreshold": "tma_frontend_bound > 0.15", "MetricgroupNoGroup": "TopdownL1",
@@ -296,13 +296,13 @@ }, { "BriefDescription": "Average CPU Utilization (percentage)", - "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / TSC", + "MetricExpr": "tma_info_system_cpus_utilized / #num_cpus_online", "MetricGroup": "HPC;Summary", "MetricName": "tma_info_system_cpu_utilization" }, { "BriefDescription": "Average number of utilized CPUs", - "MetricExpr": "#num_cpus_online * tma_info_system_cpu_utilization", + "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / TSC", "MetricGroup": "Summary", "MetricName": "tma_info_system_cpus_utilized" },
@@ -419,7 +419,7 @@ { "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to Instruction TLB (ITLB) misses", "MetricExpr": "(12 * ITLB_MISSES.STLB_HIT + ITLB_MISSES.WALK_DURATION) / tma_info_thread_clks", - "MetricGroup": "BigFootprint;FetchLat;MemoryTLB;TopdownL3;tma_L3_group;tma_fetch_latency_group", + "MetricGroup": "BigFootprint;BvBC;FetchLat;MemoryTLB;TopdownL3;tma_L3_group;tma_fetch_latency_group", "MetricName": "tma_itlb_misses", "MetricThreshold": "tma_itlb_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Instruction TLB (ITLB) misses. Sample with: ITLB_MISSES.WALK_COMPLETED",
@@ -458,7 +458,7 @@ "BriefDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears", "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "tma_bad_speculation - tma_branch_mispredicts", - "MetricGroup": "BadSpec;MachineClears;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueMC;tma_issueSyncxn", + "MetricGroup": "BadSpec;BvMS;MachineClears;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueMC;tma_issueSyncxn", "MetricName": "tma_machine_clears", "MetricThreshold": "tma_machine_clears > 0.1 & tma_bad_speculation > 0.15", "MetricgroupNoGroup": "TopdownL2",
@@ -468,7 +468,7 @@ { "BriefDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory - DRAM ([SPR-HBM] and/or HBM)", "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, cpu@OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD\\,cmask\\=6@) / tma_info_thread_clks", - "MetricGroup": "MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueBW", + "MetricGroup": "BvMS;MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueBW", "MetricName": "tma_mem_bandwidth", "MetricThreshold": "tma_mem_bandwidth > 0.2 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", "PublicDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory - DRAM ([SPR-HBM] and/or HBM). The underlying heuristic assumes that a similar off-core traffic is generated by all IA cores. This metric does not aggregate non-data-read requests by this logical processor; requests from other IA Logical Processors/Physical Cores/sockets; or other non-IA devices like GPU; hence the maximum external memory bandwidth limits may or may not be approached when this metric is flagged (see Uncore counters for that). Related metrics: tma_info_system_dram_bw_use",
@@ -477,7 +477,7 @@ { "BriefDescription": "This metric estimates fraction of cycles where the performance was likely hurt due to latency from external memory - DRAM ([SPR-HBM] and/or HBM)", "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD) / tma_info_thread_clks - tma_mem_bandwidth", - "MetricGroup": "MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueLat", + "MetricGroup": "BvML;MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueLat", "MetricName": "tma_mem_latency", "MetricThreshold": "tma_mem_latency > 0.1 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", "PublicDescription": "This metric estimates fraction of cycles where the performance was likely hurt due to latency from external memory - DRAM ([SPR-HBM] and/or HBM). This metric does not aggregate requests from other Logical Processors/Physical Cores/sockets (see Uncore counters for that). Related metrics: ",
@@ -525,7 +525,7 @@ { "BriefDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired", "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / tma_info_thread_slots", - "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", + "MetricGroup": "BvUW;TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_retiring", "MetricThreshold": "tma_retiring > 0.7 | tma_heavy_operations > 0.1", "MetricgroupNoGroup": "TopdownL1",
tools/perf/pmu-events/arch/x86/jaketown/memory.json +35 -0
@@ -1,6 +1,7 @@ [ { "BriefDescription": "Counts the number of machine clears due to memory order conflicts.", + "Counter": "0,1,2,3", "EventCode": "0xC3", "EventName": "MACHINE_CLEARS.MEMORY_ORDERING", "PublicDescription": "This event counts the number of memory ordering Machine Clears detected. Memory Ordering Machine Clears can result from memory disambiguation, external snoops, or cross SMT-HW-thread snoop (stores) hitting load buffers. Machine clears can have a significant performance impact if they are happening frequently.",
@@ -9,6 +10,7 @@ }, { "BriefDescription": "Loads with latency value being above 128.", + "Counter": "3", "EventCode": "0xCD", "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_128", "MSRIndex": "0x3F6",
@@ -19,6 +21,7 @@ }, { "BriefDescription": "Loads with latency value being above 16.", + "Counter": "3", "EventCode": "0xCD", "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_16", "MSRIndex": "0x3F6",
@@ -29,6 +32,7 @@ }, { "BriefDescription": "Loads with latency value being above 256.", + "Counter": "3", "EventCode": "0xCD", "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_256", "MSRIndex": "0x3F6",
@@ -39,6 +43,7 @@ }, { "BriefDescription": "Loads with latency value being above 32.", + "Counter": "3", "EventCode": "0xCD", "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_32", "MSRIndex": "0x3F6",
@@ -49,6 +54,7 @@ }, { "BriefDescription": "Loads with latency value being above 4 .", + "Counter": "3", "EventCode": "0xCD", "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_4", "MSRIndex": "0x3F6",
@@ -59,6 +65,7 @@ }, { "BriefDescription": "Loads with latency value being above 512.", + "Counter": "3", "EventCode": "0xCD", "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_512", "MSRIndex": "0x3F6",
@@ -69,6 +76,7 @@ }, { "BriefDescription": "Loads with latency value being above 64.", + "Counter": "3", "EventCode": "0xCD", "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_64", "MSRIndex": "0x3F6",
@@ -79,6 +87,7 @@ }, { "BriefDescription": "Loads with latency value being above 8.", + "Counter": "3", "EventCode": "0xCD", "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_8", "MSRIndex": "0x3F6",
@@ -89,6 +98,7 @@ }, { "BriefDescription": "Sample stores and collect precise store operation via PEBS record. PMC3 only. (Precise Event - PEBS).", + "Counter": "3", "EventCode": "0xCD", "EventName": "MEM_TRANS_RETIRED.PRECISE_STORE", "PEBS": "2",
@@ -97,6 +107,7 @@ }, { "BriefDescription": "Speculative cache line split load uops dispatched to L1 cache.", + "Counter": "0,1,2,3", "EventCode": "0x05", "EventName": "MISALIGN_MEM_REF.LOADS", "SampleAfterValue": "2000003",
@@ -104,6 +115,7 @@ }, { "BriefDescription": "Speculative cache line split STA uops dispatched to L1 cache.", + "Counter": "0,1,2,3", "EventCode": "0x05", "EventName": "MISALIGN_MEM_REF.STORES", "SampleAfterValue": "2000003",
@@ -111,6 +123,7 @@ }, { "BriefDescription": "This event counts all LLC misses for all demand and L2 prefetches. LLC prefetches are excluded.", + "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.ALL_DEMAND_MLC_PREF_READS.LLC_MISS.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7",
@@ -120,6 +133,7 @@ }, { "BriefDescription": "Counts all local dram accesses for all demand and L2 prefetches. LLC prefetches are excluded.", + "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.ALL_DEMAND_MLC_PREF_READS.LLC_MISS.LOCAL_DRAM", "MSRIndex": "0x1a6,0x1a7",
@@ -129,6 +143,7 @@ }, { "BriefDescription": "This event counts all remote cache-to-cache transfers (includes HITM and HIT-Forward) for all demand and L2 prefetches. LLC prefetches are excluded.", + "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.ALL_DEMAND_MLC_PREF_READS.LLC_MISS.REMOTE_HITM_HIT_FORWARD", "MSRIndex": "0x1a6,0x1a7",
@@ -138,6 +153,7 @@ }, { "BriefDescription": "Counts all demand code reads that miss the LLC", + "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.LLC_MISS.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7",
@@ -147,6 +163,7 @@ }, { "BriefDescription": "Counts all demand code reads that miss the LLC and the data returned from local dram", + "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.LLC_MISS.LOCAL_DRAM", "MSRIndex": "0x1a6,0x1a7",
@@ -156,6 +173,7 @@ }, { "BriefDescription": "Counts all demand code reads that miss the LLC and the data returned from remote dram", + "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.LLC_MISS.REMOTE_DRAM", "MSRIndex": "0x1a6,0x1a7",
@@ -165,6 +183,7 @@ }, { "BriefDescription": "Counts all demand code reads that miss the LLC the data is found in M state in remote cache and forwarded from there", + "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.LLC_MISS.REMOTE_HITM", "MSRIndex": "0x1a6,0x1a7",
@@ -174,6 +193,7 @@ }, { "BriefDescription": "Counts all demand code reads that miss the LLC and the data forwarded from remote cache", + "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.LLC_MISS.REMOTE_HIT_FORWARD", "MSRIndex": "0x1a6,0x1a7",
@@ -183,6 +203,7 @@ }, { "BriefDescription": "Counts demand data reads that miss the LLC and the data returned from remote & local dram", + "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.LLC_MISS.ANY_DRAM", "MSRIndex": "0x1a6,0x1a7",
@@ -192,6 +213,7 @@ }, { "BriefDescription": "Counts demand data reads that miss in the LLC", + "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.LLC_MISS.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7",
@@ -201,6 +223,7 @@ }, { "BriefDescription": "Counts demand data reads that miss the LLC and the data returned from local dram", + "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.LLC_MISS.LOCAL_DRAM", "MSRIndex": "0x1a6,0x1a7",
@@ -210,6 +233,7 @@ }, { "BriefDescription": "Counts demand data reads that miss the LLC and the data returned from remote dram", + "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.LLC_MISS.REMOTE_DRAM", "MSRIndex": "0x1a6,0x1a7",
@@ -219,6 +243,7 @@ }, { "BriefDescription": "Counts demand data reads that miss the LLC the data is found in M state in remote cache and forwarded from there", + "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.LLC_MISS.REMOTE_HITM", "MSRIndex": "0x1a6,0x1a7",
@@ -228,6 +253,7 @@ }, { "BriefDescription": "Counts demand data reads that miss the LLC and the data forwarded from remote cache", + "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.LLC_MISS.REMOTE_HIT_FORWARD", "MSRIndex": "0x1a6,0x1a7",
@@ -237,6 +263,7 @@ }, { "BriefDescription": "Counts all prefetch (that bring data to L2) code reads that miss the LLC and the data returned from remote & local dram", + "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.LLC_MISS.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7",
@@ -246,6 +273,7 @@ }, { "BriefDescription": "Counts prefetch (that bring data to L2) data reads that miss the LLC and the data returned from remote & local dram", + "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.LLC_MISS.ANY_DRAM", "MSRIndex": "0x1a6,0x1a7",
@@ -255,6 +283,7 @@ }, { "BriefDescription": "Counts prefetch (that bring data to L2) data reads that miss in the LLC", + "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.LLC_MISS.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7",
@@ -264,6 +293,7 @@ }, { "BriefDescription": "Counts prefetch (that bring data to L2) data reads that miss the LLC and the data returned from local dram", + "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.LLC_MISS.LOCAL_DRAM", "MSRIndex": "0x1a6,0x1a7",
@@ -273,6 +303,7 @@ }, { "BriefDescription": "Counts prefetch (that bring data to L2) data reads that miss the LLC and the data returned from remote dram", + "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.LLC_MISS.REMOTE_DRAM", "MSRIndex": "0x1a6,0x1a7",
@@ -282,6 +313,7 @@ }, { "BriefDescription": "Counts prefetch (that bring data to L2) data reads that miss the LLC the data is found in M state in remote cache and forwarded from there", + "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.LLC_MISS.REMOTE_HITM", "MSRIndex": "0x1a6,0x1a7",
@@ -291,6 +323,7 @@ }, { "BriefDescription": "Counts prefetch (that bring data to L2) data reads that miss the LLC and the data forwarded from remote cache", + "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.LLC_MISS.REMOTE_HIT_FORWARD", "MSRIndex": "0x1a6,0x1a7",
@@ -300,6 +333,7 @@ }, { "BriefDescription": "Counts all prefetch (that bring data to LLC only) code reads that miss in the LLC", + "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.PF_LLC_CODE_RD.LLC_MISS.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7",
@@ -309,6 +343,7 @@ }, { "BriefDescription": "Counts prefetch (that bring data to LLC only) data reads that hit in the LLC and the snoops sent to sibling cores return clean response", + "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.PF_LLC_DATA_RD.LLC_MISS.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7",
tools/perf/pmu-events/arch/x86/jaketown/metricgroups.json +11 -0
@@ -5,7 +5,18 @@ "BigFootprint": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", "BrMispredicts": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", "Branches": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "BvBC": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "BvCB": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "BvFB": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "BvIO": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "BvML": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "BvMP": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "BvMS": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "BvMT": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "BvOB": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "BvUW": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", "CacheHits": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "CacheMisses": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", "Compute": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", "Cor": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", "DSB": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
tools/perf/pmu-events/arch/x86/jaketown/other.json +6 -0
@@ -1,6 +1,7 @@ [ { "BriefDescription": "Unhalted core cycles when the thread is in ring 0.", + "Counter": "0,1,2,3", "EventCode": "0x5C", "EventName": "CPL_CYCLES.RING0", "SampleAfterValue": "2000003",
@@ -8,6 +9,7 @@ }, { "BriefDescription": "Number of intervals between processor halts while thread is in ring 0.", + "Counter": "0,1,2,3", "CounterMask": "1", "EdgeDetect": "1", "EventCode": "0x5C",
@@ -17,6 +19,7 @@ }, { "BriefDescription": "Unhalted core cycles when thread is in rings 1, 2, or 3.", + "Counter": "0,1,2,3", "EventCode": "0x5C", "EventName": "CPL_CYCLES.RING123", "SampleAfterValue": "2000003",
@@ -24,6 +27,7 @@ }, { "BriefDescription": "Hardware Prefetch requests that miss the L1D cache. This accounts for both L1 streamer and IP-based (IPP) HW prefetchers. A request is being counted each time it access the cache & miss it, including if a block is applicable or if hit the Fill Buffer for .", + "Counter": "0,1,2,3", "EventCode": "0x4E", "EventName": "HW_PRE_REQ.DL1_MISS", "SampleAfterValue": "2000003",
@@ -31,6 +35,7 @@ }, { "BriefDescription": "Valid instructions written to IQ per cycle.", + "Counter": "0,1,2,3", "EventCode": "0x17", "EventName": "INSTS_WRITTEN_TO_IQ.INSTS", "SampleAfterValue": "2000003",
@@ -38,6 +43,7 @@ }, { "BriefDescription": "Cycles when L1 and L2 are locked due to UC or split lock.", + "Counter": "0,1,2,3", "EventCode": "0x63", "EventName": "LOCK_CYCLES.SPLIT_LOCK_UC_LOCK_DURATION", "SampleAfterValue": "2000003",
tools/perf/pmu-events/arch/x86/jaketown/pipeline.json +127 -0
889 lines not on this page · raw message
tools/perf/pmu-events/arch/x86/jaketown/uncore-cache.json +205 -0
468 lines not on this page · raw message
tools/perf/pmu-events/arch/x86/jaketown/uncore-interconnect.json +207 -0
207 lines not on this page · raw message
tools/perf/pmu-events/arch/x86/jaketown/uncore-io.json +36 -0
Lines of this file are not shown. View the raw message.
tools/perf/pmu-events/arch/x86/jaketown/uncore-memory.json +51 -0
51 lines not on this page · raw message
tools/perf/pmu-events/arch/x86/jaketown/uncore-power.json +39 -0
Lines of this file are not shown. View the raw message.
tools/perf/pmu-events/arch/x86/jaketown/virtual-memory.json +16 -0
Lines of this file are not shown. View the raw message.
The rest of this diff is not shown. View the raw message.
Signature · 1 line
2.45.2.627.g7a2c4fd464-goog
Part of the diff is not shown here. View the raw message.
Ian Rogers
reviewerPATCH v2 21/37 perf vendor events: Add knightslanding counter information
In reply to Ian RogersAdd counter information necessary for optimizing event grouping the perf tool.
The most recent RFC patch set using this information:
https://lore.kernel.org/lkml/[email protected]/
The information was added in:
https://github.com/intel/perfmon/commit/475892a9690cb048949e593fe39cee65cd4765e1
and later patches.
--- .../arch/x86/knightslanding/cache.json | 213 +++++++++ .../arch/x86/knightslanding/counter.json | 37 ++ .../x86/knightslanding/floating-point.json | 3 + .../arch/x86/knightslanding/frontend.json | 7 + .../arch/x86/knightslanding/memory.json | 101 +++++ .../arch/x86/knightslanding/pipeline.json | 45 ++ .../arch/x86/knightslanding/uncore-cache.json | 421 ++++++++++++++++++ .../arch/x86/knightslanding/uncore-io.json | 24 + .../x86/knightslanding/uncore-memory.json | 14 + .../x86/knightslanding/virtual-memory.json | 7 + 10 files changed, 872 insertions(+) create mode 100644 tools/perf/pmu-events/arch/x86/knightslanding/counter.json
tools/perf/pmu-events/arch/x86/knightslanding/cache.json +213 -0
@@ -1,12 +1,14 @@ [ { "BriefDescription": "Counts the number of MEC requests that were not accepted into the L2Q because of any L2 queue reject condition. There is no concept of at-ret here. It might include requests due to instructions in the speculative path.", + "Counter": "0,1", "EventCode": "0x31", "EventName": "CORE_REJECT_L2Q.ALL", "SampleAfterValue": "200003" }, { "BriefDescription": "This event counts the number of core cycles the fetch stalls because of an icache miss. This is a cumulative count of cycles the NIP stalled for all icache misses.", + "Counter": "0,1", "EventCode": "0x86", "EventName": "FETCH_STALL.ICACHE_FILL_PENDING_CYCLES", "SampleAfterValue": "200003",
@@ -14,6 +16,7 @@ }, { "BriefDescription": "Counts the number of L2HWP allocated into XQ GP", + "Counter": "0,1", "EventCode": "0x3E", "EventName": "L2_PREFETCHER.ALLOC_XQ", "SampleAfterValue": "100007",
@@ -21,6 +24,7 @@ }, { "BriefDescription": "Counts the number of L2 cache misses", + "Counter": "0,1", "EventCode": "0x2E", "EventName": "L2_REQUESTS.MISS", "SampleAfterValue": "200003",
@@ -28,6 +32,7 @@ }, { "BriefDescription": "Counts the total number of L2 cache references.", + "Counter": "0,1", "EventCode": "0x2E", "EventName": "L2_REQUESTS.REFERENCE", "SampleAfterValue": "200003",
@@ -35,12 +40,14 @@ }, { "BriefDescription": "Counts the number of MEC requests from the L2Q that reference a cache line (cacheable requests) excluding SW prefetches filling only to L2 cache and L1 evictions (automatically excludes L2HWP, UC, WC) that were rejected - Multiple repeated rejects should be counted multiple times", + "Counter": "0,1", "EventCode": "0x30", "EventName": "L2_REQUESTS_REJECT.ALL", "SampleAfterValue": "200003" }, { "BriefDescription": "Counts all the load micro-ops retired", + "Counter": "0,1", "EventCode": "0x04", "EventName": "MEM_UOPS_RETIRED.ALL_LOADS", "PublicDescription": "This event counts the number of load micro-ops retired.",
@@ -49,6 +56,7 @@ }, { "BriefDescription": "Counts all the store micro-ops retired", + "Counter": "0,1", "EventCode": "0x04", "EventName": "MEM_UOPS_RETIRED.ALL_STORES", "PublicDescription": "This event counts the number of store micro-ops retired.",
@@ -57,6 +65,7 @@ }, { "BriefDescription": "Counts the loads retired that get the data from the other core in the same tile in M state (Precise Event)", + "Counter": "0,1", "Data_LA": "1", "EventCode": "0x04", "EventName": "MEM_UOPS_RETIRED.HITM",
@@ -67,6 +76,7 @@ }, { "BriefDescription": "Counts the number of load micro-ops retired that miss in L1 D cache", + "Counter": "0,1", "EventCode": "0x04", "EventName": "MEM_UOPS_RETIRED.L1_MISS_LOADS", "PublicDescription": "This event counts the number of load micro-ops retired that miss in L1 Data cache. Note that prefetch misses will not be counted.",
@@ -75,6 +85,7 @@ }, { "BriefDescription": "Counts the number of load micro-ops retired that hit in the L2 (Precise Event)", + "Counter": "0,1", "Data_LA": "1", "EventCode": "0x04", "EventName": "MEM_UOPS_RETIRED.L2_HIT_LOADS",
@@ -85,6 +96,7 @@ }, { "BriefDescription": "Counts the number of load micro-ops retired that miss in the L2 (Precise Event)", + "Counter": "0,1", "Data_LA": "1", "EventCode": "0x04", "EventName": "MEM_UOPS_RETIRED.L2_MISS_LOADS",
@@ -95,6 +107,7 @@ }, { "BriefDescription": "Counts the number of load micro-ops retired that caused micro TLB miss", + "Counter": "0,1", "EventCode": "0x04", "EventName": "MEM_UOPS_RETIRED.UTLB_MISS_LOADS", "SampleAfterValue": "200003",
@@ -102,6 +115,7 @@ }, { "BriefDescription": "Counts the matrix events specified by MSR_OFFCORE_RESPx", + "Counter": "0,1", "EventCode": "0xB7", "EventName": "OFFCORE_RESPONSE", "SampleAfterValue": "100007",
@@ -109,6 +123,7 @@ }, { "BriefDescription": "Counts Demand code reads and prefetch code read requests that accounts for any response", + "Counter": "0,1", "EventCode": "0xB7", "EventName": "OFFCORE_RESPONSE.ANY_CODE_RD.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7",
@@ -118,6 +133,7 @@ }, { "BriefDescription": "Counts Demand code reads and prefetch code read requests that accounts for responses from snoop request hit with data forwarded from it Far(not in the same quadrant as the request)-other tile L2 in E/F/M state. Valid only in SNC4 Cluster mode.", + "Counter": "0,1", "EventCode": "0xB7", "EventName": "OFFCORE_RESPONSE.ANY_CODE_RD.L2_HIT_FAR_TILE", "MSRIndex": "0x1a6,0x1a7",
@@ -127,6 +143,7 @@ }, { "BriefDescription": "Counts Demand code reads and prefetch code read requests that accounts for responses from a snoop request hit with data forwarded from its Far(not in the same quadrant as the request)-other tile's L2 in E/F state. Valid only for SNC4 cluster mode.", + "Counter": "0,1", "EventCode": "0xB7", "EventName": "OFFCORE_RESPONSE.ANY_CODE_RD.L2_HIT_FAR_TILE_E_F", "MSRIndex": "0x1a6,0x1a7",
@@ -136,6 +153,7 @@ }, { "BriefDescription": "Counts Demand code reads and prefetch code read requests that accounts for responses from a snoop request hit with data forwarded from its Far(not in the same quadrant as the request)-other tile's L2 in M state.", + "Counter": "0,1", "EventCode": "0xB7", "EventName": "OFFCORE_RESPONSE.ANY_CODE_RD.L2_HIT_FAR_TILE_M", "MSRIndex": "0x1a6,0x1a7",
@@ -145,6 +163,7 @@ }, { "BriefDescription": "Counts Demand code reads and prefetch code read requests that accounts for responses from snoop request hit with data forwarded from its Near-other tile L2 in E/F/M state", + "Counter": "0,1", "EventCode": "0xB7", "EventName": "OFFCORE_RESPONSE.ANY_CODE_RD.L2_HIT_NEAR_TILE", "MSRIndex": "0x1a6,0x1a7",
@@ -154,6 +173,7 @@ }, { "BriefDescription": "Counts Demand code reads and prefetch code read requests that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in E/F state.", + "Counter": "0,1", "EventCode": "0xB7", "EventName": "OFFCORE_RESPONSE.ANY_CODE_RD.L2_HIT_NEAR_TILE_E_F", "MSRIndex": "0x1a6,0x1a7",
@@ -163,6 +183,7 @@ }, { "BriefDescription": "Counts Demand code reads and prefetch code read requests that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in M state.", + "Counter": "0,1", "EventCode": "0xB7", "EventName": "OFFCORE_RESPONSE.ANY_CODE_RD.L2_HIT_NEAR_TILE_M", "MSRIndex": "0x1a6,0x1a7",
@@ -172,6 +193,7 @@ }, { "BriefDescription": "Counts Demand code reads and prefetch code read requests that accounts for responses which hit its own tile's L2 with data in E state", + "Counter": "0,1", "EventCode": "0xB7", "EventName": "OFFCORE_RESPONSE.ANY_CODE_RD.L2_HIT_THIS_TILE_E", "MSRIndex": "0x1a6,0x1a7",
@@ -181,6 +203,7 @@ }, { "BriefDescription": "Counts Demand code reads and prefetch code read requests that accounts for responses which hit its own tile's L2 with data in F state", + "Counter": "0,1", "EventCode": "0xB7", "EventName": "OFFCORE_RESPONSE.ANY_CODE_RD.L2_HIT_THIS_TILE_F", "MSRIndex": "0x1a6,0x1a7",
@@ -190,6 +213,7 @@ }, { "BriefDescription": "Counts Demand code reads and prefetch code read requests that accounts for responses which hit its own tile's L2 with data in M state", + "Counter": "0,1", "EventCode": "0xB7", "EventName": "OFFCORE_RESPONSE.ANY_CODE_RD.L2_HIT_THIS_TILE_M", "MSRIndex": "0x1a6,0x1a7",
@@ -199,6 +223,7 @@ }, { "BriefDescription": "Counts Demand code reads and prefetch code read requests that accounts for responses which hit its own tile's L2 with data in S state", + "Counter": "0,1", "EventCode": "0xB7", "EventName": "OFFCORE_RESPONSE.ANY_CODE_RD.L2_HIT_THIS_TILE_S", "MSRIndex": "0x1a6,0x1a7",
@@ -208,6 +233,7 @@ }, { "BriefDescription": "Counts Demand code reads and prefetch code read requests that are outstanding, per weighted cycle, from the time of the request to when any response is received. The outstanding response should be programmed only on PMC0.", + "Counter": "0,1", "EventCode": "0xB7", "EventName": "OFFCORE_RESPONSE.ANY_CODE_RD.OUTSTANDING", "MSRIndex": "0x1a6",
@@ -217,6 +243,7 @@ }, { "BriefDescription": "Counts Demand cacheable data and L1 prefetch data read requests that accounts for any response", + "Counter": "0,1", "EventCode": "0xB7", "EventName": "OFFCORE_RESPONSE.ANY_DATA_RD.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7",
@@ -226,6 +253,7 @@ }, { "BriefDescription": "Counts Demand cacheable data and L1 prefetch data read requests that accounts for responses from snoop request hit with data forwarded from it Far(not in the same quadrant as the request)-other tile L2 in E/F/M state. Valid only in SNC4 Cluster mode.", + "Counter": "0,1", "EventCode": "0xB7", "EventName": "OFFCORE_RESPONSE.ANY_DATA_RD.L2_HIT_FAR_TILE", "MSRIndex": "0x1a6,0x1a7",
@@ -235,6 +263,7 @@ }, { "BriefDescription": "Counts Demand cacheable data and L1 prefetch data read requests that accounts for responses from a snoop request hit with data forwarded from its Far(not in the same quadrant as the request)-other tile's L2 in E/F state. Valid only for SNC4 cluster mode.", + "Counter": "0,1", "EventCode": "0xB7", "EventName": "OFFCORE_RESPONSE.ANY_DATA_RD.L2_HIT_FAR_TILE_E_F", "MSRIndex": "0x1a6,0x1a7",
@@ -244,6 +273,7 @@ }, { "BriefDescription": "Counts Demand cacheable data and L1 prefetch data read requests that accounts for responses from a snoop request hit with data forwarded from its Far(not in the same quadrant as the request)-other tile's L2 in M state.", + "Counter": "0,1", "EventCode": "0xB7", "EventName": "OFFCORE_RESPONSE.ANY_DATA_RD.L2_HIT_FAR_TILE_M", "MSRIndex": "0x1a6,0x1a7",
@@ -253,6 +283,7 @@ }, { "BriefDescription": "Counts Demand cacheable data and L1 prefetch data read requests that accounts for responses from snoop request hit with data forwarded from its Near-other tile L2 in E/F/M state", + "Counter": "0,1", "EventCode": "0xB7", "EventName": "OFFCORE_RESPONSE.ANY_DATA_RD.L2_HIT_NEAR_TILE", "MSRIndex": "0x1a6,0x1a7",
@@ -262,6 +293,7 @@ }, { "BriefDescription": "Counts Demand cacheable data and L1 prefetch data read requests that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in E/F state.", + "Counter": "0,1", "EventCode": "0xB7", "EventName": "OFFCORE_RESPONSE.ANY_DATA_RD.L2_HIT_NEAR_TILE_E_F", "MSRIndex": "0x1a6,0x1a7",
@@ -271,6 +303,7 @@ }, { "BriefDescription": "Counts Demand cacheable data and L1 prefetch data read requests that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in M state.", + "Counter": "0,1", "EventCode": "0xB7", "EventName": "OFFCORE_RESPONSE.ANY_DATA_RD.L2_HIT_NEAR_TILE_M", "MSRIndex": "0x1a6,0x1a7",
@@ -280,6 +313,7 @@ }, { "BriefDescription": "Counts Demand cacheable data and L1 prefetch data read requests that accounts for responses which hit its own tile's L2 with data in E state", + "Counter": "0,1", "EventCode": "0xB7", "EventName": "OFFCORE_RESPONSE.ANY_DATA_RD.L2_HIT_THIS_TILE_E", "MSRIndex": "0x1a6,0x1a7",
@@ -289,6 +323,7 @@ }, { "BriefDescription": "Counts Demand cacheable data and L1 prefetch data read requests that accounts for responses which hit its own tile's L2 with data in F state", + "Counter": "0,1", "EventCode": "0xB7", "EventName": "OFFCORE_RESPONSE.ANY_DATA_RD.L2_HIT_THIS_TILE_F", "MSRIndex": "0x1a6,0x1a7",
@@ -298,6 +333,7 @@ }, { "BriefDescription": "Counts Demand cacheable data and L1 prefetch data read requests that accounts for responses which hit its own tile's L2 with data in M state", + "Counter": "0,1", "EventCode": "0xB7", "EventName": "OFFCORE_RESPONSE.ANY_DATA_RD.L2_HIT_THIS_TILE_M", "MSRIndex": "0x1a6,0x1a7",
@@ -307,6 +343,7 @@ }, { "BriefDescription": "Counts Demand cacheable data and L1 prefetch data read requests that accounts for responses which hit its own tile's L2 with data in S state", + "Counter": "0,1", "EventCode": "0xB7", "EventName": "OFFCORE_RESPONSE.ANY_DATA_RD.L2_HIT_THIS_TILE_S", "MSRIndex": "0x1a6,0x1a7",
@@ -316,6 +353,7 @@ }, { "BriefDescription": "Counts Demand cacheable data and L1 prefetch data read requests that are outstanding, per weighted cycle, from the time of the request to when any response is received. The outstanding response should be programmed only on PMC0.", + "Counter": "0,1", "EventCode": "0xB7", "EventName": "OFFCORE_RESPONSE.ANY_DATA_RD.OUTSTANDING", "MSRIndex": "0x1a6",
@@ -325,6 +363,7 @@ }, { "BriefDescription": "Counts any Prefetch requests that accounts for any response", + "Counter": "0,1", "EventCode": "0xB7", "EventName": "OFFCORE_RESPONSE.ANY_PF_L2.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7",
@@ -334,6 +373,7 @@ }, { "BriefDescription": "Counts any Prefetch requests that accounts for responses from snoop request hit with data forwarded from it Far(not in the same quadrant as the request)-other tile L2 in E/F/M state. Valid only in SNC4 Cluster mode.", + "Counter": "0,1", "EventCode": "0xB7", "EventName": "OFFCORE_RESPONSE.ANY_PF_L2.L2_HIT_FAR_TILE", "MSRIndex": "0x1a6,0x1a7",
@@ -343,6 +383,7 @@ }, { "BriefDescription": "Counts any Prefetch requests that accounts for responses from a snoop request hit with data forwarded from its Far(not in the same quadrant as the request)-other tile's L2 in E/F state. Valid only for SNC4 cluster mode.", + "Counter": "0,1", "EventCode": "0xB7", "EventName": "OFFCORE_RESPONSE.ANY_PF_L2.L2_HIT_FAR_TILE_E_F", "MSRIndex": "0x1a6,0x1a7",
@@ -352,6 +393,7 @@ }, { "BriefDescription": "Counts any Prefetch requests that accounts for responses from a snoop request hit with data forwarded from its Far(not in the same quadrant as the request)-other tile's L2 in M state.", + "Counter": "0,1", "EventCode": "0xB7", "EventName": "OFFCORE_RESPONSE.ANY_PF_L2.L2_HIT_FAR_TILE_M", "MSRIndex": "0x1a6,0x1a7",
@@ -361,6 +403,7 @@ }, { "BriefDescription": "Counts any Prefetch requests that accounts for responses from snoop request hit with data forwarded from its Near-other tile L2 in E/F/M state", + "Counter": "0,1", "EventCode": "0xB7", "EventName": "OFFCORE_RESPONSE.ANY_PF_L2.L2_HIT_NEAR_TILE", "MSRIndex": "0x1a6,0x1a7",
@@ -370,6 +413,7 @@ }, { "BriefDescription": "Counts any Prefetch requests that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in E/F state.", + "Counter": "0,1", "EventCode": "0xB7", "EventName": "OFFCORE_RESPONSE.ANY_PF_L2.L2_HIT_NEAR_TILE_E_F", "MSRIndex": "0x1a6,0x1a7",
@@ -379,6 +423,7 @@ }, { "BriefDescription": "Counts any Prefetch requests that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in M state.", + "Counter": "0,1", "EventCode": "0xB7", "EventName": "OFFCORE_RESPONSE.ANY_PF_L2.L2_HIT_NEAR_TILE_M", "MSRIndex": "0x1a6,0x1a7",
@@ -388,6 +433,7 @@ }, { "BriefDescription": "Counts any Prefetch requests that accounts for responses which hit its own tile's L2 with data in E state", + "Counter": "0,1", "EventCode": "0xB7", "EventName": "OFFCORE_RESPONSE.ANY_PF_L2.L2_HIT_THIS_TILE_E", "MSRIndex": "0x1a6,0x1a7",
@@ -397,6 +443,7 @@ }, { "BriefDescription": "Counts any Prefetch requests that accounts for responses which hit its own tile's L2 with data in F state", + "Counter": "0,1", "EventCode": "0xB7", "EventName": "OFFCORE_RESPONSE.ANY_PF_L2.L2_HIT_THIS_TILE_F", "MSRIndex": "0x1a6,0x1a7",
@@ -406,6 +453,7 @@ }, { "BriefDescription": "Counts any Prefetch requests that accounts for responses which hit its own tile's L2 with data in M state", + "Counter": "0,1", "EventCode": "0xB7", "EventName": "OFFCORE_RESPONSE.ANY_PF_L2.L2_HIT_THIS_TILE_M", "MSRIndex": "0x1a6,0x1a7",
@@ -415,6 +463,7 @@ }, { "BriefDescription": "Counts any Prefetch requests that are outstanding, per weighted cycle, from the time of the request to when any response is received. The outstanding response should be programmed only on PMC0.", + "Counter": "0,1", "EventCode": "0xB7", "EventName": "OFFCORE_RESPONSE.ANY_PF_L2.OUTSTANDING", "MSRIndex": "0x1a6",
@@ -424,6 +473,7 @@ }, { "BriefDescription": "Counts any Read request that accounts for any response", + "Counter": "0,1", "EventCode": "0xB7", "EventName": "OFFCORE_RESPONSE.ANY_READ.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7",
@@ -433,6 +483,7 @@ }, { "BriefDescription": "Counts any Read request that accounts for responses from snoop request hit with data forwarded from it Far(not in the same quadrant as the request)-other tile L2 in E/F/M state. Valid only in SNC4 Cluster mode.", + "Counter": "0,1", "EventCode": "0xB7", "EventName": "OFFCORE_RESPONSE.ANY_READ.L2_HIT_FAR_TILE", "MSRIndex": "0x1a6,0x1a7",
@@ -442,6 +493,7 @@ }, { "BriefDescription": "Counts any Read request that accounts for responses from a snoop request hit with data forwarded from its Far(not in the same quadrant as the request)-other tile's L2 in E/F state. Valid only for SNC4 cluster mode.", + "Counter": "0,1", "EventCode": "0xB7", "EventName": "OFFCORE_RESPONSE.ANY_READ.L2_HIT_FAR_TILE_E_F", "MSRIndex": "0x1a6,0x1a7",
@@ -451,6 +503,7 @@ }, { "BriefDescription": "Counts any Read request that accounts for responses from a snoop request hit with data forwarded from its Far(not in the same quadrant as the request)-other tile's L2 in M state.", + "Counter": "0,1", "EventCode": "0xB7", "EventName": "OFFCORE_RESPONSE.ANY_READ.L2_HIT_FAR_TILE_M", "MSRIndex": "0x1a6,0x1a7",
@@ -460,6 +513,7 @@ }, { "BriefDescription": "Counts any Read request that accounts for responses from snoop request hit with data forwarded from its Near-other tile L2 in E/F/M state", + "Counter": "0,1", "EventCode": "0xB7", "EventName": "OFFCORE_RESPONSE.ANY_READ.L2_HIT_NEAR_TILE", "MSRIndex": "0x1a6,0x1a7",
@@ -469,6 +523,7 @@ }, { "BriefDescription": "Counts any Read request that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in E/F state.", + "Counter": "0,1", "EventCode": "0xB7", "EventName": "OFFCORE_RESPONSE.ANY_READ.L2_HIT_NEAR_TILE_E_F", "MSRIndex": "0x1a6,0x1a7",
@@ -478,6 +533,7 @@ }, { "BriefDescription": "Counts any Read request that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in M state.", + "Counter": "0,1", "EventCode": "0xB7", "EventName": "OFFCORE_RESPONSE.ANY_READ.L2_HIT_NEAR_TILE_M", "MSRIndex": "0x1a6,0x1a7",
@@ -487,6 +543,7 @@ }, { "BriefDescription": "Counts any Read request that accounts for responses which hit its own tile's L2 with data in E state", + "Counter": "0,1", "EventCode": "0xB7", "EventName": "OFFCORE_RESPONSE.ANY_READ.L2_HIT_THIS_TILE_E", "MSRIndex": "0x1a6,0x1a7",
@@ -496,6 +553,7 @@ }, { "BriefDescription": "Counts any Read request that accounts for responses which hit its own tile's L2 with data in F state", + "Counter": "0,1", "EventCode": "0xB7", "EventName": "OFFCORE_RESPONSE.ANY_READ.L2_HIT_THIS_TILE_F", "MSRIndex": "0x1a6,0x1a7",
@@ -505,6 +563,7 @@ }, { "BriefDescription": "Counts any Read request that accounts for responses which hit its own tile's L2 with data in M state", + "Counter": "0,1", "EventCode": "0xB7", "EventName": "OFFCORE_RESPONSE.ANY_READ.L2_HIT_THIS_TILE_M", "MSRIndex": "0x1a6,0x1a7",
@@ -514,6 +573,7 @@ }, { "BriefDescription": "Counts any Read request that accounts for responses which hit its own tile's L2 with data in S state", + "Counter": "0,1", "EventCode": "0xB7", "EventName": "OFFCORE_RESPONSE.ANY_READ.L2_HIT_THIS_TILE_S", "MSRIndex": "0x1a6,0x1a7",
@@ -523,6 +583,7 @@ }, { "BriefDescription": "Counts any Read request that are outstanding, per weighted cycle, from the time of the request to when any response is received. The outstanding response should be programmed only on PMC0.", + "Counter": "0,1", "EventCode": "0xB7", "EventName": "OFFCORE_RESPONSE.ANY_READ.OUTSTANDING", "MSRIndex": "0x1a6",
@@ -532,6 +593,7 @@ }, { "BriefDescription": "Counts any request that accounts for any response", + "Counter": "0,1", "EventCode": "0xB7", "EventName": "OFFCORE_RESPONSE.ANY_REQUEST.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7",
@@ -541,6 +603,7 @@ }, { "BriefDescription": "Counts any request that accounts for responses from snoop request hit with data forwarded from it Far(not in the same quadrant as the request)-other tile L2 in E/F/M state. Valid only in SNC4 Cluster mode.", + "Counter": "0,1", "EventCode": "0xB7", "EventName": "OFFCORE_RESPONSE.ANY_REQUEST.L2_HIT_FAR_TILE", "MSRIndex": "0x1a6,0x1a7",
@@ -550,6 +613,7 @@ }, { "BriefDescription": "Counts any request that accounts for responses from a snoop request hit with data forwarded from its Far(not in the same quadrant as the request)-other tile's L2 in E/F state. Valid only for SNC4 cluster mode.", + "Counter": "0,1", "EventCode": "0xB7", "EventName": "OFFCORE_RESPONSE.ANY_REQUEST.L2_HIT_FAR_TILE_E_F", "MSRIndex": "0x1a6,0x1a7",
@@ -559,6 +623,7 @@ }, { "BriefDescription": "Counts any request that accounts for responses from a snoop request hit with data forwarded from its Far(not in the same quadrant as the request)-other tile's L2 in M state.", + "Counter": "0,1", "EventCode": "0xB7", "EventName": "OFFCORE_RESPONSE.ANY_REQUEST.L2_HIT_FAR_TILE_M", "MSRIndex": "0x1a6,0x1a7",
@@ -568,6 +633,7 @@ }, { "BriefDescription": "Counts any request that accounts for responses from snoop request hit with data forwarded from its Near-other tile L2 in E/F/M state", + "Counter": "0,1", "EventCode": "0xB7", "EventName": "OFFCORE_RESPONSE.ANY_REQUEST.L2_HIT_NEAR_TILE", "MSRIndex": "0x1a6,0x1a7",
@@ -577,6 +643,7 @@ }, { "BriefDescription": "Counts any request that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in E/F state.", + "Counter": "0,1", "EventCode": "0xB7", "EventName": "OFFCORE_RESPONSE.ANY_REQUEST.L2_HIT_NEAR_TILE_E_F", "MSRIndex": "0x1a6,0x1a7",
@@ -586,6 +653,7 @@ }, { "BriefDescription": "Counts any request that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in M state.", + "Counter": "0,1", "EventCode": "0xB7", "EventName": "OFFCORE_RESPONSE.ANY_REQUEST.L2_HIT_NEAR_TILE_M", "MSRIndex": "0x1a6,0x1a7",
@@ -595,6 +663,7 @@ }, { "BriefDescription": "Counts any request that accounts for responses which hit its own tile's L2 with data in E state", + "Counter": "0,1", "EventCode": "0xB7", "EventName": "OFFCORE_RESPONSE.ANY_REQUEST.L2_HIT_THIS_TILE_E", "MSRIndex": "0x1a6,0x1a7",
@@ -604,6 +673,7 @@ }, { "BriefDescription": "Counts any request that accounts for responses which hit its own tile's L2 with data in F state", + "Counter": "0,1", "EventCode": "0xB7", "EventName": "OFFCORE_RESPONSE.ANY_REQUEST.L2_HIT_THIS_TILE_F", "MSRIndex": "0x1a6,0x1a7",
@@ -613,6 +683,7 @@ }, { "BriefDescription": "Counts any request that accounts for responses which hit its own tile's L2 with data in M state", + "Counter": "0,1", "EventCode": "0xB7", "EventName": "OFFCORE_RESPONSE.ANY_REQUEST.L2_HIT_THIS_TILE_M", "MSRIndex": "0x1a6,0x1a7",
@@ -622,6 +693,7 @@ }, { "BriefDescription": "Counts any request that accounts for responses which hit its own tile's L2 with data in S state", + "Counter": "0,1", "EventCode": "0xB7", "EventName": "OFFCORE_RESPONSE.ANY_REQUEST.L2_HIT_THIS_TILE_S", "MSRIndex": "0x1a6,0x1a7",
@@ -631,6 +703,7 @@ }, { "BriefDescription": "Accounts for responses which miss its own tile's L2.", + "Counter": "0,1", "EventCode": "0xB7", "EventName": "OFFCORE_RESPONSE.ANY_REQUEST.L2_MISS", "MSRIndex": "0x1a6,0x1a7",
@@ -640,6 +713,7 @@ }, { "BriefDescription": "Counts any request that are outstanding, per weighted cycle, from the time of the request to when any response is received. The outstanding response should be programmed only on PMC0.", + "Counter": "0,1", "EventCode": "0xB7", "EventName": "OFFCORE_RESPONSE.ANY_REQUEST.OUTSTANDING", "MSRIndex": "0x1a6",
@@ -649,6 +723,7 @@ }, { "BriefDescription": "Counts Demand cacheable data write requests that accounts for any response", + "Counter": "0,1", "EventCode": "0xB7", "EventName": "OFFCORE_RESPONSE.ANY_RFO.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7",
@@ -658,6 +733,7 @@ }, { "BriefDescription": "Counts Demand cacheable data write requests that accounts for responses from snoop request hit with data forwarded from it Far(not in the same quadrant as the request)-other tile L2 in E/F/M state. Valid only in SNC4 Cluster mode.", + "Counter": "0,1", "EventCode": "0xB7", "EventName": "OFFCORE_RESPONSE.ANY_RFO.L2_HIT_FAR_TILE", "MSRIndex": "0x1a6,0x1a7",
@@ -667,6 +743,7 @@ }, { "BriefDescription": "Counts Demand cacheable data write requests that accounts for responses from a snoop request hit with data forwarded from its Far(not in the same quadrant as the request)-other tile's L2 in E/F state. Valid only for SNC4 cluster mode.", + "Counter": "0,1", "EventCode": "0xB7", "EventName": "OFFCORE_RESPONSE.ANY_RFO.L2_HIT_FAR_TILE_E_F", "MSRIndex": "0x1a6,0x1a7",
@@ -676,6 +753,7 @@ }, { "BriefDescription": "Counts Demand cacheable data write requests that accounts for responses from a snoop request hit with data forwarded from its Far(not in the same quadrant as the request)-other tile's L2 in M state.", + "Counter": "0,1", "EventCode": "0xB7", "EventName": "OFFCORE_RESPONSE.ANY_RFO.L2_HIT_FAR_TILE_M", "MSRIndex": "0x1a6,0x1a7",
@@ -685,6 +763,7 @@ }, { "BriefDescription": "Counts Demand cacheable data write requests that accounts for responses from snoop request hit with data forwarded from its Near-other tile L2 in E/F/M state", + "Counter": "0,1", "EventCode": "0xB7", "EventName": "OFFCORE_RESPONSE.ANY_RFO.L2_HIT_NEAR_TILE", "MSRIndex": "0x1a6,0x1a7",
@@ -694,6 +773,7 @@ }, { "BriefDescription": "Counts Demand cacheable data write requests that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in E/F state.", + "Counter": "0,1", "EventCode": "0xB7", "EventName": "OFFCORE_RESPONSE.ANY_RFO.L2_HIT_NEAR_TILE_E_F", "MSRIndex": "0x1a6,0x1a7",
@@ -703,6 +783,7 @@ }, { "BriefDescription": "Counts Demand cacheable data write requests that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in M state.", + "Counter": "0,1", "EventCode": "0xB7", "EventName": "OFFCORE_RESPONSE.ANY_RFO.L2_HIT_NEAR_TILE_M", "MSRIndex": "0x1a6,0x1a7",
@@ -712,6 +793,7 @@ }, { "BriefDescription": "Counts Demand cacheable data write requests that accounts for responses which hit its own tile's L2 with data in E state", + "Counter": "0,1", "EventCode": "0xB7", "EventName": "OFFCORE_RESPONSE.ANY_RFO.L2_HIT_THIS_TILE_E", "MSRIndex": "0x1a6,0x1a7",
@@ -721,6 +803,7 @@ }, { "BriefDescription": "Counts Demand cacheable data write requests that accounts for responses which hit its own tile's L2 with data in F state", + "Counter": "0,1", "EventCode": "0xB7", "EventName": "OFFCORE_RESPONSE.ANY_RFO.L2_HIT_THIS_TILE_F", "MSRIndex": "0x1a6,0x1a7",
@@ -730,6 +813,7 @@ }, { "BriefDescription": "Counts Demand cacheable data write requests that accounts for responses which hit its own tile's L2 with data in M state", + "Counter": "0,1", "EventCode": "0xB7", "EventName": "OFFCORE_RESPONSE.ANY_RFO.L2_HIT_THIS_TILE_M", "MSRIndex": "0x1a6,0x1a7",
@@ -739,6 +823,7 @@ }, { "BriefDescription": "Counts Demand cacheable data write requests that accounts for responses which hit its own tile's L2 with data in S state", + "Counter": "0,1", "EventCode": "0xB7", "EventName": "OFFCORE_RESPONSE.ANY_RFO.L2_HIT_THIS_TILE_S", "MSRIndex": "0x1a6,0x1a7",
@@ -748,6 +833,7 @@ }, { "BriefDescription": "Counts Demand cacheable data write requests that are outstanding, per weighted cycle, from the time of the request to when any response is received. The outstanding response should be programmed only on PMC0.", + "Counter": "0,1", "EventCode": "0xB7", "EventName": "OFFCORE_RESPONSE.ANY_RFO.OUTSTANDING", "MSRIndex": "0x1a6",
@@ -757,6 +843,7 @@ }, { "BriefDescription": "Counts Bus locks and split lock requests that accounts for any response", + "Counter": "0,1", "EventCode": "0xB7", "EventName": "OFFCORE_RESPONSE.BUS_LOCKS.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7",
@@ -766,6 +853,7 @@ }, { "BriefDescription": "Counts Bus locks and split lock requests that accounts for responses from snoop request hit with data forwarded from it Far(not in the same quadrant as the request)-other tile L2 in E/F/M state. Valid only in SNC4 Cluster mode.", + "Counter": "0,1", "EventCode": "0xB7", "EventName": "OFFCORE_RESPONSE.BUS_LOCKS.L2_HIT_FAR_TILE", "MSRIndex": "0x1a6,0x1a7",
@@ -775,6 +863,7 @@ }, { "BriefDescription": "Counts Bus locks and split lock requests that accounts for responses from a snoop request hit with data forwarded from its Far(not in the same quadrant as the request)-other tile's L2 in E/F state. Valid only for SNC4 cluster mode.", + "Counter": "0,1", "EventCode": "0xB7", "EventName": "OFFCORE_RESPONSE.BUS_LOCKS.L2_HIT_FAR_TILE_E_F", "MSRIndex": "0x1a6,0x1a7",
@@ -784,6 +873,7 @@ }, { "BriefDescription": "Counts Bus locks and split lock requests that accounts for responses from a snoop request hit with data forwarded from its Far(not in the same quadrant as the request)-other tile's L2 in M state.", + "Counter": "0,1", "EventCode": "0xB7", "EventName": "OFFCORE_RESPONSE.BUS_LOCKS.L2_HIT_FAR_TILE_M", "MSRIndex": "0x1a6,0x1a7",
@@ -793,6 +883,7 @@ }, { "BriefDescription": "Counts Bus locks and split lock requests that accounts for responses from snoop request hit with data forwarded from its Near-other tile L2 in E/F/M state", + "Counter": "0,1", "EventCode": "0xB7", "EventName": "OFFCORE_RESPONSE.BUS_LOCKS.L2_HIT_NEAR_TILE", "MSRIndex": "0x1a6,0x1a7",
@@ -802,6 +893,7 @@ }, { "BriefDescription": "Counts Bus locks and split lock requests that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in E/F state.", + "Counter": "0,1", "EventCode": "0xB7", "EventName": "OFFCORE_RESPONSE.BUS_LOCKS.L2_HIT_NEAR_TILE_E_F", "MSRIndex": "0x1a6,0x1a7",
@@ -811,6 +903,7 @@ }, { "BriefDescription": "Counts Bus locks and split lock requests that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in M state.", + "Counter": "0,1", "EventCode": "0xB7", "EventName": "OFFCORE_RESPONSE.BUS_LOCKS.L2_HIT_NEAR_TILE_M", "MSRIndex": "0x1a6,0x1a7",
@@ -820,6 +913,7 @@ }, { "BriefDescription": "Counts Bus locks and split lock requests that accounts for responses which hit its own tile's L2 with data in E state", + "Counter": "0,1", "EventCode": "0xB7", "EventName": "OFFCORE_RESPONSE.BUS_LOCKS.L2_HIT_THIS_TILE_E", "MSRIndex": "0x1a6,0x1a7",
@@ -829,6 +923,7 @@ }, { "BriefDescription": "Counts Bus locks and split lock requests that accounts for responses which hit its own tile's L2 with data in F state", + "Counter": "0,1", "EventCode": "0xB7", "EventName": "OFFCORE_RESPONSE.BUS_LOCKS.L2_HIT_THIS_TILE_F", "MSRIndex": "0x1a6,0x1a7",
@@ -838,6 +933,7 @@ }, { "BriefDescription": "Counts Bus locks and split lock requests that accounts for responses which hit its own tile's L2 with data in M state", + "Counter": "0,1", "EventCode": "0xB7", "EventName": "OFFCORE_RESPONSE.BUS_LOCKS.L2_HIT_THIS_TILE_M", "MSRIndex": "0x1a6,0x1a7",
@@ -847,6 +943,7 @@ }, { "BriefDescription": "Counts Bus locks and split lock requests that accounts for responses which hit its own tile's L2 with data in S state", + "Counter": "0,1", "EventCode": "0xB7", "EventName": "OFFCORE_RESPONSE.BUS_LOCKS.L2_HIT_THIS_TILE_S", "MSRIndex": "0x1a6,0x1a7",
@@ -856,6 +953,7 @@ }, { "BriefDescription": "Counts Bus locks and split lock requests that are outstanding, per weighted cycle, from the time of the request to when any response is received. The outstanding response should be programmed only on PMC0.", + "Counter": "0,1", "EventCode": "0xB7", "EventName": "OFFCORE_RESPONSE.BUS_LOCKS.OUTSTANDING", "MSRIndex": "0x1a6",
@@ -865,6 +963,7 @@ }, { "BriefDescription": "Counts demand code reads and prefetch code reads that accounts for any response", + "Counter": "0,1", "EventCode": "0xB7", "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7",
@@ -874,6 +973,7 @@ }, { "BriefDescription": "Counts demand code reads and prefetch code reads that accounts for responses from snoop request hit with data forwarded from it Far(not in the same quadrant as the request)-other tile L2 in E/F/M state. Valid only in SNC4 Cluster mode.", + "Counter": "0,1", "EventCode": "0xB7", "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L2_HIT_FAR_TILE", "MSRIndex": "0x1a6,0x1a7",
@@ -883,6 +983,7 @@ }, { "BriefDescription": "Counts demand code reads and prefetch code reads that accounts for responses from a snoop request hit with data forwarded from its Far(not in the same quadrant as the request)-other tile's L2 in E/F state. Valid only for SNC4 cluster mode.", + "Counter": "0,1", "EventCode": "0xB7", "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L2_HIT_FAR_TILE_E_F", "MSRIndex": "0x1a6,0x1a7",
@@ -892,6 +993,7 @@ }, { "BriefDescription": "Counts demand code reads and prefetch code reads that accounts for responses from a snoop request hit with data forwarded from its Far(not in the same quadrant as the request)-other tile's L2 in M state.", + "Counter": "0,1", "EventCode": "0xB7", "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L2_HIT_FAR_TILE_M", "MSRIndex": "0x1a6,0x1a7",
@@ -901,6 +1003,7 @@ }, { "BriefDescription": "Counts demand code reads and prefetch code reads that accounts for responses from snoop request hit with data forwarded from its Near-other tile L2 in E/F/M state", + "Counter": "0,1", "EventCode": "0xB7", "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L2_HIT_NEAR_TILE", "MSRIndex": "0x1a6,0x1a7",
@@ -910,6 +1013,7 @@ }, { "BriefDescription": "Counts demand code reads and prefetch code reads that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in E/F state.", + "Counter": "0,1", "EventCode": "0xB7", "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L2_HIT_NEAR_TILE_E_F", "MSRIndex": "0x1a6,0x1a7",
@@ -919,6 +1023,7 @@ }, { "BriefDescription": "Counts demand code reads and prefetch code reads that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in M state.", + "Counter": "0,1", "EventCode": "0xB7", "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L2_HIT_NEAR_TILE_M", "MSRIndex": "0x1a6,0x1a7",
@@ -928,6 +1033,7 @@ }, { "BriefDescription": "Counts demand code reads and prefetch code reads that accounts for responses which hit its own tile's L2 with data in E state", + "Counter": "0,1", "EventCode": "0xB7", "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L2_HIT_THIS_TILE_E", "MSRIndex": "0x1a6,0x1a7",
@@ -937,6 +1043,7 @@ }, { "BriefDescription": "Counts demand code reads and prefetch code reads that accounts for responses which hit its own tile's L2 with data in F state", + "Counter": "0,1", "EventCode": "0xB7", "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L2_HIT_THIS_TILE_F", "MSRIndex": "0x1a6,0x1a7",
@@ -946,6 +1053,7 @@ }, { "BriefDescription": "Counts demand code reads and prefetch code reads that accounts for responses which hit its own tile's L2 with data in M state", + "Counter": "0,1", "EventCode": "0xB7", "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L2_HIT_THIS_TILE_M", "MSRIndex": "0x1a6,0x1a7",
@@ -955,6 +1063,7 @@ }, { "BriefDescription": "Counts demand code reads and prefetch code reads that accounts for responses which hit its own tile's L2 with data in S state", + "Counter": "0,1", "EventCode": "0xB7", "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L2_HIT_THIS_TILE_S", "MSRIndex": "0x1a6,0x1a7",
@@ -964,6 +1073,7 @@ }, { "BriefDescription": "Counts demand code reads and prefetch code reads that are outstanding, per weighted cycle, from the time of the request to when any response is received. The outstanding response should be programmed only on PMC0.", + "Counter": "0,1", "EventCode": "0xB7", "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.OUTSTANDING", "MSRIndex": "0x1a6",
@@ -973,6 +1083,7 @@ }, { "BriefDescription": "Counts demand cacheable data and L1 prefetch data reads that accounts for any response", + "Counter": "0,1", "EventCode": "0xB7", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7",
@@ -982,6 +1093,7 @@ }, { "BriefDescription": "Counts demand cacheable data and L1 prefetch data reads that accounts for responses from a snoop request hit with data forwarded from its Far(not in the same quadrant as the request)-other tile's L2 in E/F state. Valid only for SNC4 cluster mode.", + "Counter": "0,1", "EventCode": "0xB7", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L2_HIT_FAR_TILE_E_F", "MSRIndex": "0x1a6,0x1a7",
@@ -991,6 +1103,7 @@ }, { "BriefDescription": "Counts demand cacheable data and L1 prefetch data reads that accounts for responses from a snoop request hit with data forwarded from its Far(not in the same quadrant as the request)-other tile's L2 in M state.", + "Counter": "0,1", "EventCode": "0xB7", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L2_HIT_FAR_TILE_M", "MSRIndex": "0x1a6,0x1a7",
@@ -1000,6 +1113,7 @@ }, { "BriefDescription": "Counts demand cacheable data and L1 prefetch data reads that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in E/F state.", + "Counter": "0,1", "EventCode": "0xB7", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L2_HIT_NEAR_TILE_E_F", "MSRIndex": "0x1a6,0x1a7",
@@ -1009,6 +1123,7 @@ }, { "BriefDescription": "Counts demand cacheable data and L1 prefetch data reads that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in M state.", + "Counter": "0,1", "EventCode": "0xB7", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L2_HIT_NEAR_TILE_M", "MSRIndex": "0x1a6,0x1a7",
@@ -1018,6 +1133,7 @@ }, { "BriefDescription": "Counts demand cacheable data and L1 prefetch data reads that accounts for responses which hit its own tile's L2 with data in E state", + "Counter": "0,1", "EventCode": "0xB7", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L2_HIT_THIS_TILE_E", "MSRIndex": "0x1a6,0x1a7",
@@ -1027,6 +1143,7 @@ }, { "BriefDescription": "Counts demand cacheable data and L1 prefetch data reads that accounts for responses which hit its own tile's L2 with data in F state", + "Counter": "0,1", "EventCode": "0xB7", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L2_HIT_THIS_TILE_F", "MSRIndex": "0x1a6,0x1a7",
@@ -1036,6 +1153,7 @@ }, { "BriefDescription": "Counts demand cacheable data and L1 prefetch data reads that accounts for responses which hit its own tile's L2 with data in M state", + "Counter": "0,1", "EventCode": "0xB7", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L2_HIT_THIS_TILE_M", "MSRIndex": "0x1a6,0x1a7",
@@ -1045,6 +1163,7 @@ }, { "BriefDescription": "Counts demand cacheable data and L1 prefetch data reads that accounts for responses which hit its own tile's L2 with data in S state", + "Counter": "0,1", "EventCode": "0xB7", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L2_HIT_THIS_TILE_S", "MSRIndex": "0x1a6,0x1a7",
@@ -1054,6 +1173,7 @@ }, { "BriefDescription": "Counts demand cacheable data and L1 prefetch data reads that are outstanding, per weighted cycle, from the time of the request to when any response is received. The outstanding response should be programmed only on PMC0.", + "Counter": "0,1", "EventCode": "0xB7", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.OUTSTANDING", "MSRIndex": "0x1a6",
@@ -1063,6 +1183,7 @@ }, { "BriefDescription": "Counts Demand cacheable data writes that accounts for any response", + "Counter": "0,1", "EventCode": "0xB7", "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7",
@@ -1072,6 +1193,7 @@ }, { "BriefDescription": "Counts Demand cacheable data writes that accounts for responses from snoop request hit with data forwarded from it Far(not in the same quadrant as the request)-other tile L2 in E/F/M state. Valid only in SNC4 Cluster mode.", + "Counter": "0,1", "EventCode": "0xB7", "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L2_HIT_FAR_TILE", "MSRIndex": "0x1a6,0x1a7",
@@ -1081,6 +1203,7 @@ }, { "BriefDescription": "Counts Demand cacheable data writes that accounts for responses from a snoop request hit with data forwarded from its Far(not in the same quadrant as the request)-other tile's L2 in E/F state. Valid only for SNC4 cluster mode.", + "Counter": "0,1", "EventCode": "0xB7", "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L2_HIT_FAR_TILE_E_F", "MSRIndex": "0x1a6,0x1a7",
@@ -1090,6 +1213,7 @@ }, { "BriefDescription": "Counts Demand cacheable data writes that accounts for responses from a snoop request hit with data forwarded from its Far(not in the same quadrant as the request)-other tile's L2 in M state.", + "Counter": "0,1", "EventCode": "0xB7", "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L2_HIT_FAR_TILE_M", "MSRIndex": "0x1a6,0x1a7",
@@ -1099,6 +1223,7 @@ }, { "BriefDescription": "Counts Demand cacheable data writes that accounts for responses from snoop request hit with data forwarded from its Near-other tile L2 in E/F/M state", + "Counter": "0,1", "EventCode": "0xB7", "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L2_HIT_NEAR_TILE", "MSRIndex": "0x1a6,0x1a7",
@@ -1108,6 +1233,7 @@ }, { "BriefDescription": "Counts Demand cacheable data writes that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in E/F state.", + "Counter": "0,1", "EventCode": "0xB7", "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L2_HIT_NEAR_TILE_E_F", "MSRIndex": "0x1a6,0x1a7",
@@ -1117,6 +1243,7 @@ }, { "BriefDescription": "Counts Demand cacheable data writes that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in M state.", + "Counter": "0,1", "EventCode": "0xB7", "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L2_HIT_NEAR_TILE_M", "MSRIndex": "0x1a6,0x1a7",
@@ -1126,6 +1253,7 @@ }, { "BriefDescription": "Counts Demand cacheable data writes that accounts for responses which hit its own tile's L2 with data in E state", + "Counter": "0,1", "EventCode": "0xB7", "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L2_HIT_THIS_TILE_E", "MSRIndex": "0x1a6,0x1a7",
@@ -1135,6 +1263,7 @@ }, { "BriefDescription": "Counts Demand cacheable data writes that accounts for responses which hit its own tile's L2 with data in F state", + "Counter": "0,1", "EventCode": "0xB7", "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L2_HIT_THIS_TILE_F", "MSRIndex": "0x1a6,0x1a7",
@@ -1144,6 +1273,7 @@ }, { "BriefDescription": "Counts Demand cacheable data writes that accounts for responses which hit its own tile's L2 with data in M state", + "Counter": "0,1", "EventCode": "0xB7", "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L2_HIT_THIS_TILE_M", "MSRIndex": "0x1a6,0x1a7",
@@ -1153,6 +1283,7 @@ }, { "BriefDescription": "Counts Demand cacheable data writes that accounts for responses which hit its own tile's L2 with data in S state", + "Counter": "0,1", "EventCode": "0xB7", "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L2_HIT_THIS_TILE_S", "MSRIndex": "0x1a6,0x1a7",
@@ -1162,6 +1293,7 @@ }, { "BriefDescription": "Counts Demand cacheable data writes that are outstanding, per weighted cycle, from the time of the request to when any response is received. The outstanding response should be programmed only on PMC0.", + "Counter": "0,1", "EventCode": "0xB7", "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.OUTSTANDING", "MSRIndex": "0x1a6",
@@ -1171,6 +1303,7 @@ }, { "BriefDescription": "Counts Full streaming stores (WC and should be programmed on PMC1) that accounts for any response", + "Counter": "0,1", "EventCode": "0xB7", "EventName": "OFFCORE_RESPONSE.FULL_STREAMING_STORES.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7",
@@ -1180,6 +1313,7 @@ }, { "BriefDescription": "Counts Partial reads (UC or WC and is valid only for Outstanding response type). that accounts for any response", + "Counter": "0,1", "EventCode": "0xB7", "EventName": "OFFCORE_RESPONSE.PARTIAL_READS.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7",
@@ -1189,6 +1323,7 @@ }, { "BriefDescription": "Counts Partial reads (UC or WC and is valid only for Outstanding response type). that accounts for responses from snoop request hit with data forwarded from it Far(not in the same quadrant as the request)-other tile L2 in E/F/M state. Valid only in SNC4 Cluster mode.", + "Counter": "0,1", "EventCode": "0xB7", "EventName": "OFFCORE_RESPONSE.PARTIAL_READS.L2_HIT_FAR_TILE", "MSRIndex": "0x1a6,0x1a7",
@@ -1198,6 +1333,7 @@ }, { "BriefDescription": "Counts Partial reads (UC or WC and is valid only for Outstanding response type). that accounts for responses from a snoop request hit with data forwarded from its Far(not in the same quadrant as the request)-other tile's L2 in E/F state. Valid only for SNC4 cluster mode.", + "Counter": "0,1", "EventCode": "0xB7", "EventName": "OFFCORE_RESPONSE.PARTIAL_READS.L2_HIT_FAR_TILE_E_F", "MSRIndex": "0x1a6,0x1a7",
@@ -1207,6 +1343,7 @@ }, { "BriefDescription": "Counts Partial reads (UC or WC and is valid only for Outstanding response type). that accounts for responses from a snoop request hit with data forwarded from its Far(not in the same quadrant as the request)-other tile's L2 in M state.", + "Counter": "0,1", "EventCode": "0xB7", "EventName": "OFFCORE_RESPONSE.PARTIAL_READS.L2_HIT_FAR_TILE_M", "MSRIndex": "0x1a6,0x1a7",
@@ -1216,6 +1353,7 @@ }, { "BriefDescription": "Counts Partial reads (UC or WC and is valid only for Outstanding response type). that accounts for responses from snoop request hit with data forwarded from its Near-other tile L2 in E/F/M state", + "Counter": "0,1", "EventCode": "0xB7", "EventName": "OFFCORE_RESPONSE.PARTIAL_READS.L2_HIT_NEAR_TILE", "MSRIndex": "0x1a6,0x1a7",
@@ -1225,6 +1363,7 @@ }, { "BriefDescription": "Counts Partial reads (UC or WC and is valid only for Outstanding response type). that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in E/F state.", + "Counter": "0,1", "EventCode": "0xB7", "EventName": "OFFCORE_RESPONSE.PARTIAL_READS.L2_HIT_NEAR_TILE_E_F", "MSRIndex": "0x1a6,0x1a7",
@@ -1234,6 +1373,7 @@ }, { "BriefDescription": "Counts Partial reads (UC or WC and is valid only for Outstanding response type). that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in M state.", + "Counter": "0,1", "EventCode": "0xB7", "EventName": "OFFCORE_RESPONSE.PARTIAL_READS.L2_HIT_NEAR_TILE_M", "MSRIndex": "0x1a6,0x1a7",
@@ -1243,6 +1383,7 @@ }, { "BriefDescription": "Counts Partial reads (UC or WC and is valid only for Outstanding response type). that accounts for responses which hit its own tile's L2 with data in E state", + "Counter": "0,1", "EventCode": "0xB7", "EventName": "OFFCORE_RESPONSE.PARTIAL_READS.L2_HIT_THIS_TILE_E", "MSRIndex": "0x1a6,0x1a7",
@@ -1252,6 +1393,7 @@ }, { "BriefDescription": "Counts Partial reads (UC or WC and is valid only for Outstanding response type). that accounts for responses which hit its own tile's L2 with data in F state", + "Counter": "0,1", "EventCode": "0xB7", "EventName": "OFFCORE_RESPONSE.PARTIAL_READS.L2_HIT_THIS_TILE_F", "MSRIndex": "0x1a6,0x1a7",
@@ -1261,6 +1403,7 @@ }, { "BriefDescription": "Counts Partial reads (UC or WC and is valid only for Outstanding response type). that accounts for responses which hit its own tile's L2 with data in M state", + "Counter": "0,1", "EventCode": "0xB7", "EventName": "OFFCORE_RESPONSE.PARTIAL_READS.L2_HIT_THIS_TILE_M", "MSRIndex": "0x1a6,0x1a7",
@@ -1270,6 +1413,7 @@ }, { "BriefDescription": "Counts Partial reads (UC or WC and is valid only for Outstanding response type). that accounts for responses which hit its own tile's L2 with data in S state", + "Counter": "0,1", "EventCode": "0xB7", "EventName": "OFFCORE_RESPONSE.PARTIAL_READS.L2_HIT_THIS_TILE_S", "MSRIndex": "0x1a6,0x1a7",
@@ -1279,6 +1423,7 @@ }, { "BriefDescription": "Counts Partial reads (UC or WC and is valid only for Outstanding response type). that are outstanding, per weighted cycle, from the time of the request to when any response is received. The outstanding response should be programmed only on PMC0.", + "Counter": "0,1", "EventCode": "0xB7", "EventName": "OFFCORE_RESPONSE.PARTIAL_READS.OUTSTANDING", "MSRIndex": "0x1a6",
@@ -1288,6 +1433,7 @@ }, { "BriefDescription": "Counts Partial streaming stores (WC and should be programmed on PMC1) that accounts for any response", + "Counter": "0,1", "EventCode": "0xB7", "EventName": "OFFCORE_RESPONSE.PARTIAL_STREAMING_STORES.ANY_RESPONSE", "MSRIndex": "0x1a7",
@@ -1297,6 +1443,7 @@ }, { "BriefDescription": "Counts Partial writes (UC or WT or WP and should be programmed on PMC1) that accounts for any response", + "Counter": "0,1", "EventCode": "0xB7", "EventName": "OFFCORE_RESPONSE.PARTIAL_WRITES.ANY_RESPONSE", "MSRIndex": "0x1a7",
@@ -1306,6 +1453,7 @@ }, { "BriefDescription": "Counts Partial writes (UC or WT or WP and should be programmed on PMC1) that accounts for responses from snoop request hit with data forwarded from it Far(not in the same quadrant as the request)-other tile L2 in E/F/M state. Valid only in SNC4 Cluster mode.", + "Counter": "0,1", "EventCode": "0xB7", "EventName": "OFFCORE_RESPONSE.PARTIAL_WRITES.L2_HIT_FAR_TILE", "MSRIndex": "0x1a7",
@@ -1315,6 +1463,7 @@ }, { "BriefDescription": "Counts Partial writes (UC or WT or WP and should be programmed on PMC1) that accounts for responses from a snoop request hit with data forwarded from its Far(not in the same quadrant as the request)-other tile's L2 in E/F state. Valid only for SNC4 cluster mode.", + "Counter": "0,1", "EventCode": "0xB7", "EventName": "OFFCORE_RESPONSE.PARTIAL_WRITES.L2_HIT_FAR_TILE_E_F", "MSRIndex": "0x1a7",
@@ -1324,6 +1473,7 @@ }, { "BriefDescription": "Counts Partial writes (UC or WT or WP and should be programmed on PMC1) that accounts for responses from a snoop request hit with data forwarded from its Far(not in the same quadrant as the request)-other tile's L2 in M state.", + "Counter": "0,1", "EventCode": "0xB7", "EventName": "OFFCORE_RESPONSE.PARTIAL_WRITES.L2_HIT_FAR_TILE_M", "MSRIndex": "0x1a7",
@@ -1333,6 +1483,7 @@ }, { "BriefDescription": "Counts Partial writes (UC or WT or WP and should be programmed on PMC1) that accounts for responses from snoop request hit with data forwarded from its Near-other tile L2 in E/F/M state", + "Counter": "0,1", "EventCode": "0xB7", "EventName": "OFFCORE_RESPONSE.PARTIAL_WRITES.L2_HIT_NEAR_TILE", "MSRIndex": "0x1a7",
@@ -1342,6 +1493,7 @@ }, { "BriefDescription": "Counts Partial writes (UC or WT or WP and should be programmed on PMC1) that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in E/F state.", + "Counter": "0,1", "EventCode": "0xB7", "EventName": "OFFCORE_RESPONSE.PARTIAL_WRITES.L2_HIT_NEAR_TILE_E_F", "MSRIndex": "0x1a7",
@@ -1351,6 +1503,7 @@ }, { "BriefDescription": "Counts Partial writes (UC or WT or WP and should be programmed on PMC1) that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in M state.", + "Counter": "0,1", "EventCode": "0xB7", "EventName": "OFFCORE_RESPONSE.PARTIAL_WRITES.L2_HIT_NEAR_TILE_M", "MSRIndex": "0x1a7",
@@ -1360,6 +1513,7 @@ }, { "BriefDescription": "Counts Partial writes (UC or WT or WP and should be programmed on PMC1) that accounts for responses which hit its own tile's L2 with data in E state", + "Counter": "0,1", "EventCode": "0xB7", "EventName": "OFFCORE_RESPONSE.PARTIAL_WRITES.L2_HIT_THIS_TILE_E", "MSRIndex": "0x1a7",
@@ -1369,6 +1523,7 @@ }, { "BriefDescription": "Counts Partial writes (UC or WT or WP and should be programmed on PMC1) that accounts for responses which hit its own tile's L2 with data in F state", + "Counter": "0,1", "EventCode": "0xB7", "EventName": "OFFCORE_RESPONSE.PARTIAL_WRITES.L2_HIT_THIS_TILE_F", "MSRIndex": "0x1a7",
@@ -1378,6 +1533,7 @@ }, { "BriefDescription": "Counts Partial writes (UC or WT or WP and should be programmed on PMC1) that accounts for responses which hit its own tile's L2 with data in M state", + "Counter": "0,1", "EventCode": "0xB7", "EventName": "OFFCORE_RESPONSE.PARTIAL_WRITES.L2_HIT_THIS_TILE_M", "MSRIndex": "0x1a7",
@@ -1387,6 +1543,7 @@ }, { "BriefDescription": "Counts Partial writes (UC or WT or WP and should be programmed on PMC1) that accounts for responses which hit its own tile's L2 with data in S state", + "Counter": "0,1", "EventCode": "0xB7", "EventName": "OFFCORE_RESPONSE.PARTIAL_WRITES.L2_HIT_THIS_TILE_S", "MSRIndex": "0x1a7",
@@ -1396,6 +1553,7 @@ }, { "BriefDescription": "Counts L1 data HW prefetches that accounts for any response", + "Counter": "0,1", "EventCode": "0xB7", "EventName": "OFFCORE_RESPONSE.PF_L1_DATA_RD.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7",
@@ -1405,6 +1563,7 @@ }, { "BriefDescription": "Counts L1 data HW prefetches that accounts for responses from snoop request hit with data forwarded from it Far(not in the same quadrant as the request)-other tile L2 in E/F/M state. Valid only in SNC4 Cluster mode.", + "Counter": "0,1", "EventCode": "0xB7", "EventName": "OFFCORE_RESPONSE.PF_L1_DATA_RD.L2_HIT_FAR_TILE", "MSRIndex": "0x1a6,0x1a7",
@@ -1414,6 +1573,7 @@ }, { "BriefDescription": "Counts L1 data HW prefetches that accounts for responses from a snoop request hit with data forwarded from its Far(not in the same quadrant as the request)-other tile's L2 in E/F state. Valid only for SNC4 cluster mode.", + "Counter": "0,1", "EventCode": "0xB7", "EventName": "OFFCORE_RESPONSE.PF_L1_DATA_RD.L2_HIT_FAR_TILE_E_F", "MSRIndex": "0x1a6,0x1a7",
@@ -1423,6 +1583,7 @@ }, { "BriefDescription": "Counts L1 data HW prefetches that accounts for responses from a snoop request hit with data forwarded from its Far(not in the same quadrant as the request)-other tile's L2 in M state.", + "Counter": "0,1", "EventCode": "0xB7", "EventName": "OFFCORE_RESPONSE.PF_L1_DATA_RD.L2_HIT_FAR_TILE_M", "MSRIndex": "0x1a6,0x1a7",
@@ -1432,6 +1593,7 @@ }, { "BriefDescription": "Counts L1 data HW prefetches that accounts for responses from snoop request hit with data forwarded from its Near-other tile L2 in E/F/M state", + "Counter": "0,1", "EventCode": "0xB7", "EventName": "OFFCORE_RESPONSE.PF_L1_DATA_RD.L2_HIT_NEAR_TILE", "MSRIndex": "0x1a6,0x1a7",
@@ -1441,6 +1603,7 @@ }, { "BriefDescription": "Counts L1 data HW prefetches that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in E/F state.", + "Counter": "0,1", "EventCode": "0xB7", "EventName": "OFFCORE_RESPONSE.PF_L1_DATA_RD.L2_HIT_NEAR_TILE_E_F", "MSRIndex": "0x1a6,0x1a7",
@@ -1450,6 +1613,7 @@ }, { "BriefDescription": "Counts L1 data HW prefetches that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in M state.", + "Counter": "0,1", "EventCode": "0xB7", "EventName": "OFFCORE_RESPONSE.PF_L1_DATA_RD.L2_HIT_NEAR_TILE_M", "MSRIndex": "0x1a6,0x1a7",
@@ -1459,6 +1623,7 @@ }, { "BriefDescription": "Counts L1 data HW prefetches that accounts for responses which hit its own tile's L2 with data in E state", + "Counter": "0,1", "EventCode": "0xB7", "EventName": "OFFCORE_RESPONSE.PF_L1_DATA_RD.L2_HIT_THIS_TILE_E", "MSRIndex": "0x1a6,0x1a7",
@@ -1468,6 +1633,7 @@ }, { "BriefDescription": "Counts L1 data HW prefetches that accounts for responses which hit its own tile's L2 with data in F state", + "Counter": "0,1", "EventCode": "0xB7", "EventName": "OFFCORE_RESPONSE.PF_L1_DATA_RD.L2_HIT_THIS_TILE_F", "MSRIndex": "0x1a6,0x1a7",
@@ -1477,6 +1643,7 @@ }, { "BriefDescription": "Counts L1 data HW prefetches that accounts for responses which hit its own tile's L2 with data in M state", + "Counter": "0,1", "EventCode": "0xB7", "EventName": "OFFCORE_RESPONSE.PF_L1_DATA_RD.L2_HIT_THIS_TILE_M", "MSRIndex": "0x1a6,0x1a7",
@@ -1486,6 +1653,7 @@ }, { "BriefDescription": "Counts L1 data HW prefetches that accounts for responses which hit its own tile's L2 with data in S state", + "Counter": "0,1", "EventCode": "0xB7", "EventName": "OFFCORE_RESPONSE.PF_L1_DATA_RD.L2_HIT_THIS_TILE_S", "MSRIndex": "0x1a6,0x1a7",
@@ -1495,6 +1663,7 @@ }, { "BriefDescription": "Counts L1 data HW prefetches that are outstanding, per weighted cycle, from the time of the request to when any response is received. The outstanding response should be programmed only on PMC0.", + "Counter": "0,1", "EventCode": "0xB7", "EventName": "OFFCORE_RESPONSE.PF_L1_DATA_RD.OUTSTANDING", "MSRIndex": "0x1a6",
@@ -1504,6 +1673,7 @@ }, { "BriefDescription": "Counts L2 code HW prefetches that accounts for any response", + "Counter": "0,1", "EventCode": "0xB7", "EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7",
@@ -1513,6 +1683,7 @@ }, { "BriefDescription": "Counts L2 code HW prefetches that accounts for responses from snoop request hit with data forwarded from it Far(not in the same quadrant as the request)-other tile L2 in E/F/M state. Valid only in SNC4 Cluster mode.", + "Counter": "0,1", "EventCode": "0xB7", "EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.L2_HIT_FAR_TILE", "MSRIndex": "0x1a6,0x1a7",
@@ -1522,6 +1693,7 @@ }, { "BriefDescription": "Counts L2 code HW prefetches that accounts for responses from a snoop request hit with data forwarded from its Far(not in the same quadrant as the request)-other tile's L2 in E/F state. Valid only for SNC4 cluster mode.", + "Counter": "0,1", "EventCode": "0xB7", "EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.L2_HIT_FAR_TILE_E_F", "MSRIndex": "0x1a6,0x1a7",
@@ -1531,6 +1703,7 @@ }, { "BriefDescription": "Counts L2 code HW prefetches that accounts for responses from a snoop request hit with data forwarded from its Far(not in the same quadrant as the request)-other tile's L2 in M state.", + "Counter": "0,1", "EventCode": "0xB7", "EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.L2_HIT_FAR_TILE_M", "MSRIndex": "0x1a6,0x1a7",
@@ -1540,6 +1713,7 @@ }, { "BriefDescription": "Counts L2 code HW prefetches that accounts for responses from snoop request hit with data forwarded from its Near-other tile L2 in E/F/M state", + "Counter": "0,1", "EventCode": "0xB7", "EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.L2_HIT_NEAR_TILE", "MSRIndex": "0x1a6,0x1a7",
@@ -1549,6 +1723,7 @@ }, { "BriefDescription": "Counts L2 code HW prefetches that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in E/F state.", + "Counter": "0,1", "EventCode": "0xB7", "EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.L2_HIT_NEAR_TILE_E_F", "MSRIndex": "0x1a6,0x1a7",
@@ -1558,6 +1733,7 @@ }, { "BriefDescription": "Counts L2 code HW prefetches that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in M state.", + "Counter": "0,1", "EventCode": "0xB7", "EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.L2_HIT_NEAR_TILE_M", "MSRIndex": "0x1a6,0x1a7",
@@ -1567,6 +1743,7 @@ }, { "BriefDescription": "Counts L2 code HW prefetches that accounts for responses which hit its own tile's L2 with data in E state", + "Counter": "0,1", "EventCode": "0xB7", "EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.L2_HIT_THIS_TILE_E", "MSRIndex": "0x1a6,0x1a7",
@@ -1576,6 +1753,7 @@ }, { "BriefDescription": "Counts L2 code HW prefetches that accounts for responses which hit its own tile's L2 with data in F state", + "Counter": "0,1", "EventCode": "0xB7", "EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.L2_HIT_THIS_TILE_F", "MSRIndex": "0x1a6,0x1a7",
@@ -1585,6 +1763,7 @@ }, { "BriefDescription": "Counts L2 code HW prefetches that are outstanding, per weighted cycle, from the time of the request to when any response is received. The outstanding response should be programmed only on PMC0.", + "Counter": "0,1", "EventCode": "0xB7", "EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.OUTSTANDING", "MSRIndex": "0x1a6",
@@ -1594,6 +1773,7 @@ }, { "BriefDescription": "Counts L2 data RFO prefetches (includes PREFETCHW instruction) that accounts for any response", + "Counter": "0,1", "EventCode": "0xB7", "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7",
@@ -1603,6 +1783,7 @@ }, { "BriefDescription": "Counts L2 data RFO prefetches (includes PREFETCHW instruction) that accounts for responses from a snoop request hit with data forwarded from its Far(not in the same quadrant as the request)-other tile's L2 in E/F state. Valid only for SNC4 cluster mode.", + "Counter": "0,1", "EventCode": "0xB7", "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L2_HIT_FAR_TILE_E_F", "MSRIndex": "0x1a6,0x1a7",
@@ -1612,6 +1793,7 @@ }, { "BriefDescription": "Counts L2 data RFO prefetches (includes PREFETCHW instruction) that accounts for responses from a snoop request hit with data forwarded from its Far(not in the same quadrant as the request)-other tile's L2 in M state.", + "Counter": "0,1", "EventCode": "0xB7", "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L2_HIT_FAR_TILE_M", "MSRIndex": "0x1a6,0x1a7",
@@ -1621,6 +1803,7 @@ }, { "BriefDescription": "Counts L2 data RFO prefetches (includes PREFETCHW instruction) that accounts for responses from snoop request hit with data forwarded from its Near-other tile L2 in E/F/M state", + "Counter": "0,1", "EventCode": "0xB7", "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L2_HIT_NEAR_TILE", "MSRIndex": "0x1a6,0x1a7",
@@ -1630,6 +1813,7 @@ }, { "BriefDescription": "Counts L2 data RFO prefetches (includes PREFETCHW instruction) that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in E/F state.", + "Counter": "0,1", "EventCode": "0xB7", "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L2_HIT_NEAR_TILE_E_F", "MSRIndex": "0x1a6,0x1a7",
@@ -1639,6 +1823,7 @@ }, { "BriefDescription": "Counts L2 data RFO prefetches (includes PREFETCHW instruction) that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in M state.", + "Counter": "0,1", "EventCode": "0xB7", "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L2_HIT_NEAR_TILE_M", "MSRIndex": "0x1a6,0x1a7",
@@ -1648,6 +1833,7 @@ }, { "BriefDescription": "Counts L2 data RFO prefetches (includes PREFETCHW instruction) that accounts for responses which hit its own tile's L2 with data in E state", + "Counter": "0,1", "EventCode": "0xB7", "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L2_HIT_THIS_TILE_E", "MSRIndex": "0x1a6,0x1a7",
@@ -1657,6 +1843,7 @@ }, { "BriefDescription": "Counts L2 data RFO prefetches (includes PREFETCHW instruction) that accounts for responses which hit its own tile's L2 with data in F state", + "Counter": "0,1", "EventCode": "0xB7", "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L2_HIT_THIS_TILE_F", "MSRIndex": "0x1a6,0x1a7",
@@ -1666,6 +1853,7 @@ }, { "BriefDescription": "Counts L2 data RFO prefetches (includes PREFETCHW instruction) that accounts for responses which hit its own tile's L2 with data in M state", + "Counter": "0,1", "EventCode": "0xB7", "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L2_HIT_THIS_TILE_M", "MSRIndex": "0x1a6,0x1a7",
@@ -1675,6 +1863,7 @@ }, { "BriefDescription": "Counts L2 data RFO prefetches (includes PREFETCHW instruction) that accounts for responses which hit its own tile's L2 with data in S state", + "Counter": "0,1", "EventCode": "0xB7", "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L2_HIT_THIS_TILE_S", "MSRIndex": "0x1a6,0x1a7",
@@ -1684,6 +1873,7 @@ }, { "BriefDescription": "Counts Software Prefetches that accounts for any response", + "Counter": "0,1", "EventCode": "0xB7", "EventName": "OFFCORE_RESPONSE.PF_SOFTWARE.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7",
@@ -1693,6 +1883,7 @@ }, { "BriefDescription": "Counts Software Prefetches that accounts for responses from snoop request hit with data forwarded from it Far(not in the same quadrant as the request)-other tile L2 in E/F/M state. Valid only in SNC4 Cluster mode.", + "Counter": "0,1", "EventCode": "0xB7", "EventName": "OFFCORE_RESPONSE.PF_SOFTWARE.L2_HIT_FAR_TILE", "MSRIndex": "0x1a6,0x1a7",
@@ -1702,6 +1893,7 @@ }, { "BriefDescription": "Counts Software Prefetches that accounts for responses from a snoop request hit with data forwarded from its Far(not in the same quadrant as the request)-other tile's L2 in E/F state. Valid only for SNC4 cluster mode.", + "Counter": "0,1", "EventCode": "0xB7", "EventName": "OFFCORE_RESPONSE.PF_SOFTWARE.L2_HIT_FAR_TILE_E_F", "MSRIndex": "0x1a6,0x1a7",
@@ -1711,6 +1903,7 @@ }, { "BriefDescription": "Counts Software Prefetches that accounts for responses from a snoop request hit with data forwarded from its Far(not in the same quadrant as the request)-other tile's L2 in M state.", + "Counter": "0,1", "EventCode": "0xB7", "EventName": "OFFCORE_RESPONSE.PF_SOFTWARE.L2_HIT_FAR_TILE_M", "MSRIndex": "0x1a6,0x1a7",
@@ -1720,6 +1913,7 @@ }, { "BriefDescription": "Counts Software Prefetches that accounts for responses from snoop request hit with data forwarded from its Near-other tile L2 in E/F/M state", + "Counter": "0,1", "EventCode": "0xB7", "EventName": "OFFCORE_RESPONSE.PF_SOFTWARE.L2_HIT_NEAR_TILE", "MSRIndex": "0x1a6,0x1a7",
@@ -1729,6 +1923,7 @@ }, { "BriefDescription": "Counts Software Prefetches that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in E/F state.", + "Counter": "0,1", "EventCode": "0xB7", "EventName": "OFFCORE_RESPONSE.PF_SOFTWARE.L2_HIT_NEAR_TILE_E_F", "MSRIndex": "0x1a6,0x1a7",
@@ -1738,6 +1933,7 @@ }, { "BriefDescription": "Counts Software Prefetches that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in M state.", + "Counter": "0,1", "EventCode": "0xB7", "EventName": "OFFCORE_RESPONSE.PF_SOFTWARE.L2_HIT_NEAR_TILE_M", "MSRIndex": "0x1a6,0x1a7",
@@ -1747,6 +1943,7 @@ }, { "BriefDescription": "Counts Software Prefetches that accounts for responses which hit its own tile's L2 with data in E state", + "Counter": "0,1", "EventCode": "0xB7", "EventName": "OFFCORE_RESPONSE.PF_SOFTWARE.L2_HIT_THIS_TILE_E", "MSRIndex": "0x1a6,0x1a7",
@@ -1756,6 +1953,7 @@ }, { "BriefDescription": "Counts Software Prefetches that accounts for responses which hit its own tile's L2 with data in F state", + "Counter": "0,1", "EventCode": "0xB7", "EventName": "OFFCORE_RESPONSE.PF_SOFTWARE.L2_HIT_THIS_TILE_F", "MSRIndex": "0x1a6,0x1a7",
@@ -1765,6 +1963,7 @@ }, { "BriefDescription": "Counts Software Prefetches that accounts for responses which hit its own tile's L2 with data in M state", + "Counter": "0,1", "EventCode": "0xB7", "EventName": "OFFCORE_RESPONSE.PF_SOFTWARE.L2_HIT_THIS_TILE_M", "MSRIndex": "0x1a6,0x1a7",
@@ -1774,6 +1973,7 @@ }, { "BriefDescription": "Counts Software Prefetches that accounts for responses which hit its own tile's L2 with data in S state", + "Counter": "0,1", "EventCode": "0xB7", "EventName": "OFFCORE_RESPONSE.PF_SOFTWARE.L2_HIT_THIS_TILE_S", "MSRIndex": "0x1a6,0x1a7",
@@ -1783,6 +1983,7 @@ }, { "BriefDescription": "Counts Software Prefetches that are outstanding, per weighted cycle, from the time of the request to when any response is received. The outstanding response should be programmed only on PMC0.", + "Counter": "0,1", "EventCode": "0xB7", "EventName": "OFFCORE_RESPONSE.PF_SOFTWARE.OUTSTANDING", "MSRIndex": "0x1a6",
@@ -1792,6 +1993,7 @@ }, { "BriefDescription": "Counts all streaming stores (WC and should be programmed on PMC1) that accounts for any response", + "Counter": "0,1", "EventCode": "0xB7", "EventName": "OFFCORE_RESPONSE.STREAMING_STORES.ANY_RESPONSE", "MSRIndex": "0x1a7",
@@ -1801,6 +2003,7 @@ }, { "BriefDescription": "Counts UC code reads (valid only for Outstanding response type) that accounts for any response", + "Counter": "0,1", "EventCode": "0xB7", "EventName": "OFFCORE_RESPONSE.UC_CODE_READS.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7",
@@ -1810,6 +2013,7 @@ }, { "BriefDescription": "Counts UC code reads (valid only for Outstanding response type) that accounts for responses from a snoop request hit with data forwarded from its Far(not in the same quadrant as the request)-other tile's L2 in E/F state. Valid only for SNC4 cluster mode.", + "Counter": "0,1", "EventCode": "0xB7", "EventName": "OFFCORE_RESPONSE.UC_CODE_READS.L2_HIT_FAR_TILE_E_F", "MSRIndex": "0x1a6,0x1a7",
@@ -1819,6 +2023,7 @@ }, { "BriefDescription": "Counts UC code reads (valid only for Outstanding response type) that accounts for responses from a snoop request hit with data forwarded from its Far(not in the same quadrant as the request)-other tile's L2 in M state.", + "Counter": "0,1", "EventCode": "0xB7", "EventName": "OFFCORE_RESPONSE.UC_CODE_READS.L2_HIT_FAR_TILE_M", "MSRIndex": "0x1a6,0x1a7",
@@ -1828,6 +2033,7 @@ }, { "BriefDescription": "Counts UC code reads (valid only for Outstanding response type) that accounts for responses from snoop request hit with data forwarded from its Near-other tile L2 in E/F/M state", + "Counter": "0,1", "EventCode": "0xB7", "EventName": "OFFCORE_RESPONSE.UC_CODE_READS.L2_HIT_NEAR_TILE", "MSRIndex": "0x1a6,0x1a7",
@@ -1837,6 +2043,7 @@ }, { "BriefDescription": "Counts UC code reads (valid only for Outstanding response type) that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in E/F state.", + "Counter": "0,1", "EventCode": "0xB7", "EventName": "OFFCORE_RESPONSE.UC_CODE_READS.L2_HIT_NEAR_TILE_E_F", "MSRIndex": "0x1a6,0x1a7",
@@ -1846,6 +2053,7 @@ }, { "BriefDescription": "Counts UC code reads (valid only for Outstanding response type) that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in M state.", + "Counter": "0,1", "EventCode": "0xB7", "EventName": "OFFCORE_RESPONSE.UC_CODE_READS.L2_HIT_NEAR_TILE_M", "MSRIndex": "0x1a6,0x1a7",
@@ -1855,6 +2063,7 @@ }, { "BriefDescription": "Counts UC code reads (valid only for Outstanding response type) that accounts for responses which hit its own tile's L2 with data in E state", + "Counter": "0,1", "EventCode": "0xB7", "EventName": "OFFCORE_RESPONSE.UC_CODE_READS.L2_HIT_THIS_TILE_E", "MSRIndex": "0x1a6,0x1a7",
@@ -1864,6 +2073,7 @@ }, { "BriefDescription": "Counts UC code reads (valid only for Outstanding response type) that accounts for responses which hit its own tile's L2 with data in F state", + "Counter": "0,1", "EventCode": "0xB7", "EventName": "OFFCORE_RESPONSE.UC_CODE_READS.L2_HIT_THIS_TILE_F", "MSRIndex": "0x1a6,0x1a7",
@@ -1873,6 +2083,7 @@ }, { "BriefDescription": "Counts UC code reads (valid only for Outstanding response type) that accounts for responses which hit its own tile's L2 with data in M state", + "Counter": "0,1", "EventCode": "0xB7", "EventName": "OFFCORE_RESPONSE.UC_CODE_READS.L2_HIT_THIS_TILE_M", "MSRIndex": "0x1a6,0x1a7",
@@ -1882,6 +2093,7 @@ }, { "BriefDescription": "Counts UC code reads (valid only for Outstanding response type) that accounts for responses which hit its own tile's L2 with data in S state", + "Counter": "0,1", "EventCode": "0xB7", "EventName": "OFFCORE_RESPONSE.UC_CODE_READS.L2_HIT_THIS_TILE_S", "MSRIndex": "0x1a6,0x1a7",
@@ -1891,6 +2103,7 @@ }, { "BriefDescription": "Counts UC code reads (valid only for Outstanding response type) that are outstanding, per weighted cycle, from the time of the request to when any response is received. The outstanding response should be programmed only on PMC0.", + "Counter": "0,1", "EventCode": "0xB7", "EventName": "OFFCORE_RESPONSE.UC_CODE_READS.OUTSTANDING", "MSRIndex": "0x1a6",
tools/perf/pmu-events/arch/x86/knightslanding/counter.json new file +37 -0
@@ -0,0 +1,37 @@ +[ + { + "Unit": "core", + "CountersNumFixed": "3", + "CountersNumGeneric": "2" + }, + { + "Unit": "CHA", + "CountersNumFixed": "0", + "CountersNumGeneric": "4" + }, + { + "Unit": "EDC_ECLK", + "CountersNumFixed": "0", + "CountersNumGeneric": "4" + }, + { + "Unit": "EDC_UCLK", + "CountersNumFixed": "0", + "CountersNumGeneric": "4" + }, + { + "Unit": "iMC_DCLK", + "CountersNumFixed": "0", + "CountersNumGeneric": "4" + }, + { + "Unit": "iMC_UCLK", + "CountersNumFixed": "0", + "CountersNumGeneric": 4 + }, + { + "Unit": "M2PCIe", + "CountersNumFixed": "0", + "CountersNumGeneric": "4" + } +]
tools/perf/pmu-events/arch/x86/knightslanding/floating-point.json +3 -0
@@ -1,6 +1,7 @@ [ { "BriefDescription": "Counts the number of floating operations retired that required microcode assists", + "Counter": "0,1", "EventCode": "0xC3", "EventName": "MACHINE_CLEARS.FP_ASSIST", "PublicDescription": "This event counts the number of times that the pipeline stalled due to FP operations needing assists.",
@@ -9,6 +10,7 @@ }, { "BriefDescription": "Counts the number of packed SSE, AVX, AVX2, AVX-512 micro-ops (both floating point and integer) except for loads (memory-to-register mov-type micro-ops), packed byte and word multiplies.", + "Counter": "0,1", "EventCode": "0xC2", "EventName": "UOPS_RETIRED.PACKED_SIMD", "PublicDescription": "The length of the packed operation (128bits, 256bits or 512bits) is not taken into account when updating the counter; all count the same (+1). \r\nMask (k) registers are ignored. For example: a micro-op operating with a mask that only enables one element or even zero elements will still trigger this counter (+1)\r\nThis event is defined at the micro-op level and not instruction level. Most instructions are implemented with one micro-op but not all.",
@@ -17,6 +19,7 @@ }, { "BriefDescription": "Counts the number of scalar SSE, AVX, AVX2, AVX-512 micro-ops except for loads (memory-to-register mov-type micro ops), division, sqrt.", + "Counter": "0,1", "EventCode": "0xC2", "EventName": "UOPS_RETIRED.SCALAR_SIMD", "PublicDescription": "This event is defined at the micro-op level and not instruction level. Most instructions are implemented with one micro-op but not all.",
tools/perf/pmu-events/arch/x86/knightslanding/frontend.json +7 -0
@@ -1,6 +1,7 @@ [ { "BriefDescription": "Counts the number of times the front end resteers for any branch as a result of another branch handling mechanism in the front end.", + "Counter": "0,1", "EventCode": "0xE6", "EventName": "BACLEARS.ALL", "SampleAfterValue": "200003",
@@ -8,6 +9,7 @@ }, { "BriefDescription": "Counts the number of times the front end resteers for conditional branches as a result of another branch handling mechanism in the front end.", + "Counter": "0,1", "EventCode": "0xE6", "EventName": "BACLEARS.COND", "SampleAfterValue": "200003",
@@ -15,6 +17,7 @@ }, { "BriefDescription": "Counts the number of times the front end resteers for RET branches as a result of another branch handling mechanism in the front end.", + "Counter": "0,1", "EventCode": "0xE6", "EventName": "BACLEARS.RETURN", "SampleAfterValue": "200003",
@@ -22,6 +25,7 @@ }, { "BriefDescription": "Counts all instruction fetches, including uncacheable fetches.", + "Counter": "0,1", "EventCode": "0x80", "EventName": "ICACHE.ACCESSES", "SampleAfterValue": "200003",
@@ -29,6 +33,7 @@ }, { "BriefDescription": "Counts all instruction fetches that hit the instruction cache.", + "Counter": "0,1", "EventCode": "0x80", "EventName": "ICACHE.HIT", "SampleAfterValue": "200003",
@@ -36,6 +41,7 @@ }, { "BriefDescription": "Counts all instruction fetches that miss the instruction cache or produce memory requests. An instruction fetch miss is counted only once and not once for every cycle it is outstanding.", + "Counter": "0,1", "EventCode": "0x80", "EventName": "ICACHE.MISSES", "SampleAfterValue": "200003",
@@ -43,6 +49,7 @@ }, { "BriefDescription": "Counts the number of times the MSROM starts a flow of uops.", + "Counter": "0,1", "EventCode": "0xE7", "EventName": "MS_DECODED.MS_ENTRY", "SampleAfterValue": "200003",
tools/perf/pmu-events/arch/x86/knightslanding/memory.json +101 -0
707 lines not on this page · raw message
tools/perf/pmu-events/arch/x86/knightslanding/pipeline.json +45 -0
315 lines not on this page · raw message
tools/perf/pmu-events/arch/x86/knightslanding/uncore-cache.json +421 -0
379 lines not on this page · raw message
tools/perf/pmu-events/arch/x86/knightslanding/uncore-io.json +24 -0
Lines of this file are not shown. View the raw message.
tools/perf/pmu-events/arch/x86/knightslanding/uncore-memory.json +14 -0
Lines of this file are not shown. View the raw message.
tools/perf/pmu-events/arch/x86/knightslanding/virtual-memory.json +7 -0
Lines of this file are not shown. View the raw message.
The rest of this diff is not shown. View the raw message.
Signature · 1 line
2.45.2.627.g7a2c4fd464-goog
Part of the diff is not shown here. View the raw message.
Ian Rogers
reviewerPATCH v2 22/37 perf vendor events: Add lunarlake counter information
In reply to Ian RogersAdd counter information necessary for optimizing event grouping the perf tool.
The most recent RFC patch set using this information:
https://lore.kernel.org/lkml/[email protected]/
The information was added in:
https://github.com/intel/perfmon/commit/475892a9690cb048949e593fe39cee65cd4765e1
and later patches.
--- .../pmu-events/arch/x86/lunarlake/cache.json | 20 +++++++++++ .../arch/x86/lunarlake/frontend.json | 3 ++ .../pmu-events/arch/x86/lunarlake/memory.json | 15 ++++++++ .../pmu-events/arch/x86/lunarlake/other.json | 6 ++++ .../arch/x86/lunarlake/pipeline.json | 36 +++++++++++++++++++ .../arch/x86/lunarlake/virtual-memory.json | 6 ++++ 6 files changed, 86 insertions(+)
tools/perf/pmu-events/arch/x86/lunarlake/cache.json +20 -0
@@ -1,6 +1,7 @@ [ { "BriefDescription": "Counts the number of L2 Cache Accesses Counts the total number of L2 Cache Accesses - sum of hits, misses, rejects front door requests for CRd/DRd/RFO/ItoM/L2 Prefetches only, per core event", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0x24", "EventName": "L2_REQUEST.ALL", "PublicDescription": "Counts the number of L2 Cache Accesses Counts the total number of L2 Cache Accesses - sum of hits, misses, rejects front door requests for CRd/DRd/RFO/ItoM/L2 Prefetches only.",
@@ -10,6 +11,7 @@ }, { "BriefDescription": "Counts the number of cacheable memory requests that miss in the LLC. Counts on a per core basis.", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0x2e", "EventName": "LONGEST_LAT_CACHE.MISS", "PublicDescription": "Counts the number of cacheable memory requests that miss in 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.",
@@ -19,6 +21,7 @@ }, { "BriefDescription": "Core-originated cacheable requests that missed L3 (Except hardware prefetches to the L3)", + "Counter": "0,1,2,3,4,5,6,7,8,9", "EventCode": "0x2e", "EventName": "LONGEST_LAT_CACHE.MISS", "PublicDescription": "Counts core-originated cacheable requests that miss the L3 cache (Longest Latency cache). Requests include data and code reads, Reads-for-Ownership (RFOs), speculative accesses and hardware prefetches to the L1 and L2. It does not include hardware prefetches to the L3, and may not count other types of requests to the L3.",
@@ -28,6 +31,7 @@ }, { "BriefDescription": "Counts the number of cacheable memory requests that access the LLC. Counts on a per core basis.", + "Counter": "0,1,2,3,4,5,6,7", "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.",
@@ -37,6 +41,7 @@ }, { "BriefDescription": "Core-originated cacheable requests that refer to L3 (Except hardware prefetches to the L3)", + "Counter": "0,1,2,3,4,5,6,7,8,9", "EventCode": "0x2e", "EventName": "LONGEST_LAT_CACHE.REFERENCE", "PublicDescription": "Counts core-originated cacheable requests to the L3 cache (Longest Latency cache). Requests include data and code reads, Reads-for-Ownership (RFOs), speculative accesses and hardware prefetches to the L1 and L2. It does not include hardware prefetches to the L3, and may not count other types of requests to the L3.",
@@ -46,6 +51,7 @@ }, { "BriefDescription": "Retired load instructions.", + "Counter": "0,1,2,3", "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_INST_RETIRED.ALL_LOADS",
@@ -57,6 +63,7 @@ }, { "BriefDescription": "Retired store instructions.", + "Counter": "0,1,2,3", "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_INST_RETIRED.ALL_STORES",
@@ -68,6 +75,7 @@ }, { "BriefDescription": "Counts the number of load uops retired.", + "Counter": "0,1,2,3,4,5,6,7", "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_UOPS_RETIRED.ALL_LOADS",
@@ -78,6 +86,7 @@ }, { "BriefDescription": "Counts the number of store uops retired.", + "Counter": "0,1,2,3,4,5,6,7", "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_UOPS_RETIRED.ALL_STORES",
@@ -88,6 +97,7 @@ }, { "BriefDescription": "Counts the number of tagged load uops retired that exceed the latency threshold defined in MEC_CR_PEBS_LD_LAT_THRESHOLD - Only counts with PEBS enabled", + "Counter": "0,1,2,3,4,5,6,7", "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_1024",
@@ -100,6 +110,7 @@ }, { "BriefDescription": "Counts the number of tagged load uops retired that exceed the latency threshold defined in MEC_CR_PEBS_LD_LAT_THRESHOLD - Only counts with PEBS enabled", + "Counter": "0,1,2,3,4,5,6,7", "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_128",
@@ -112,6 +123,7 @@ }, { "BriefDescription": "Counts the number of tagged load uops retired that exceed the latency threshold defined in MEC_CR_PEBS_LD_LAT_THRESHOLD - Only counts with PEBS enabled", + "Counter": "0,1,2,3,4,5,6,7", "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_16",
@@ -124,6 +136,7 @@ }, { "BriefDescription": "Counts the number of tagged load uops retired that exceed the latency threshold defined in MEC_CR_PEBS_LD_LAT_THRESHOLD - Only counts with PEBS enabled", + "Counter": "0,1,2,3,4,5,6,7", "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_2048",
@@ -136,6 +149,7 @@ }, { "BriefDescription": "Counts the number of tagged load uops retired that exceed the latency threshold defined in MEC_CR_PEBS_LD_LAT_THRESHOLD - Only counts with PEBS enabled", + "Counter": "0,1,2,3,4,5,6,7", "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_256",
@@ -148,6 +162,7 @@ }, { "BriefDescription": "Counts the number of tagged load uops retired that exceed the latency threshold defined in MEC_CR_PEBS_LD_LAT_THRESHOLD - Only counts with PEBS enabled", + "Counter": "0,1,2,3,4,5,6,7", "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_32",
@@ -160,6 +175,7 @@ }, { "BriefDescription": "Counts the number of tagged load uops retired that exceed the latency threshold defined in MEC_CR_PEBS_LD_LAT_THRESHOLD - Only counts with PEBS enabled", + "Counter": "0,1,2,3,4,5,6,7", "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_4",
@@ -172,6 +188,7 @@ }, { "BriefDescription": "Counts the number of tagged load uops retired that exceed the latency threshold defined in MEC_CR_PEBS_LD_LAT_THRESHOLD - Only counts with PEBS enabled", + "Counter": "0,1,2,3,4,5,6,7", "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_512",
@@ -184,6 +201,7 @@ }, { "BriefDescription": "Counts the number of tagged load uops retired that exceed the latency threshold defined in MEC_CR_PEBS_LD_LAT_THRESHOLD - Only counts with PEBS enabled", + "Counter": "0,1,2,3,4,5,6,7", "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_64",
@@ -196,6 +214,7 @@ }, { "BriefDescription": "Counts the number of tagged load uops retired that exceed the latency threshold defined in MEC_CR_PEBS_LD_LAT_THRESHOLD - Only counts with PEBS enabled", + "Counter": "0,1,2,3,4,5,6,7", "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_8",
@@ -208,6 +227,7 @@ }, { "BriefDescription": "Counts the number of stores uops retired same as MEM_UOPS_RETIRED.ALL_STORES", + "Counter": "0,1,2,3,4,5,6,7", "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_UOPS_RETIRED.STORE_LATENCY",
tools/perf/pmu-events/arch/x86/lunarlake/frontend.json +3 -0
@@ -1,6 +1,7 @@ [ { "BriefDescription": "Counts every time the code stream enters into a new cache line by walking sequential from the previous line or being redirected by a jump.", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0x80", "EventName": "ICACHE.ACCESSES", "SampleAfterValue": "200003",
@@ -9,6 +10,7 @@ }, { "BriefDescription": "Counts every time the code stream enters into a new cache line by walking sequential from the previous line or being redirected by a jump and the instruction cache registers bytes are not present. -", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0x80", "EventName": "ICACHE.MISSES", "SampleAfterValue": "200003",
@@ -17,6 +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.", + "Counter": "0,1,2,3,4,5,6,7,8,9", "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. Software can use this event as the numerator for the Frontend Bound metric (or top-level category) of the Top-down Microarchitecture Analysis method.",
tools/perf/pmu-events/arch/x86/lunarlake/memory.json +15 -0
@@ -1,6 +1,7 @@ [ { "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 1024 cycles.", + "Counter": "0,1,2,3,4,5,6,7,8,9", "Data_LA": "1", "EventCode": "0xcd", "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_1024",
@@ -14,6 +15,7 @@ }, { "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 128 cycles.", + "Counter": "0,1,2,3,4,5,6,7,8,9", "Data_LA": "1", "EventCode": "0xcd", "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_128",
@@ -27,6 +29,7 @@ }, { "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 16 cycles.", + "Counter": "0,1,2,3,4,5,6,7,8,9", "Data_LA": "1", "EventCode": "0xcd", "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_16",
@@ -40,6 +43,7 @@ }, { "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 2048 cycles.", + "Counter": "0,1,2,3,4,5,6,7,8,9", "Data_LA": "1", "EventCode": "0xcd", "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_2048",
@@ -53,6 +57,7 @@ }, { "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 256 cycles.", + "Counter": "0,1,2,3,4,5,6,7,8,9", "Data_LA": "1", "EventCode": "0xcd", "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_256",
@@ -66,6 +71,7 @@ }, { "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 32 cycles.", + "Counter": "0,1,2,3,4,5,6,7,8,9", "Data_LA": "1", "EventCode": "0xcd", "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_32",
@@ -79,6 +85,7 @@ }, { "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 4 cycles.", + "Counter": "0,1,2,3,4,5,6,7,8,9", "Data_LA": "1", "EventCode": "0xcd", "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_4",
@@ -92,6 +99,7 @@ }, { "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 512 cycles.", + "Counter": "0,1,2,3,4,5,6,7,8,9", "Data_LA": "1", "EventCode": "0xcd", "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_512",
@@ -105,6 +113,7 @@ }, { "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 64 cycles.", + "Counter": "0,1,2,3,4,5,6,7,8,9", "Data_LA": "1", "EventCode": "0xcd", "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_64",
@@ -118,6 +127,7 @@ }, { "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 8 cycles.", + "Counter": "0,1,2,3,4,5,6,7,8,9", "Data_LA": "1", "EventCode": "0xcd", "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_8",
@@ -131,6 +141,7 @@ }, { "BriefDescription": "Retired memory store access operations. A PDist event for PEBS Store Latency Facility.", + "Counter": "0,1", "Data_LA": "1", "EventCode": "0xcd", "EventName": "MEM_TRANS_RETIRED.STORE_SAMPLE",
@@ -142,6 +153,7 @@ }, { "BriefDescription": "Counts cacheable demand data reads were not supplied by the L3 cache.", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xB7", "EventName": "OCR.DEMAND_DATA_RD.L3_MISS", "MSRIndex": "0x1a6,0x1a7",
@@ -152,6 +164,7 @@ }, { "BriefDescription": "Counts demand data reads that were not supplied by the L3 cache.", + "Counter": "0,1,2,3", "EventCode": "0x2A,0x2B", "EventName": "OCR.DEMAND_DATA_RD.L3_MISS", "MSRIndex": "0x1a6,0x1a7",
@@ -162,6 +175,7 @@ }, { "BriefDescription": "Counts demand reads for ownership, including SWPREFETCHW which is an RFO were not supplied by the L3 cache.", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xB7", "EventName": "OCR.DEMAND_RFO.L3_MISS", "MSRIndex": "0x1a6,0x1a7",
@@ -172,6 +186,7 @@ }, { "BriefDescription": "Counts demand read for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that were not supplied by the L3 cache.", + "Counter": "0,1,2,3", "EventCode": "0x2A,0x2B", "EventName": "OCR.DEMAND_RFO.L3_MISS", "MSRIndex": "0x1a6,0x1a7",
tools/perf/pmu-events/arch/x86/lunarlake/other.json +6 -0
@@ -1,6 +1,7 @@ [ { "BriefDescription": "Counts cacheable demand data reads Catch all value for any response types - this includes response types not define in the OCR. If this is set all other response types will be ignored", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xB7", "EventName": "OCR.DEMAND_DATA_RD.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7",
@@ -11,6 +12,7 @@ }, { "BriefDescription": "Counts demand data reads that have any type of response.", + "Counter": "0,1,2,3", "EventCode": "0x2A,0x2B", "EventName": "OCR.DEMAND_DATA_RD.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7",
@@ -21,6 +23,7 @@ }, { "BriefDescription": "Counts cacheable demand data reads were supplied by DRAM.", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xB7", "EventName": "OCR.DEMAND_DATA_RD.DRAM", "MSRIndex": "0x1a6,0x1a7",
@@ -31,6 +34,7 @@ }, { "BriefDescription": "Counts demand data reads that were supplied by DRAM.", + "Counter": "0,1,2,3", "EventCode": "0x2A,0x2B", "EventName": "OCR.DEMAND_DATA_RD.DRAM", "MSRIndex": "0x1a6,0x1a7",
@@ -41,6 +45,7 @@ }, { "BriefDescription": "Counts demand reads for ownership, including SWPREFETCHW which is an RFO Catch all value for any response types - this includes response types not define in the OCR. If this is set all other response types will be ignored", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xB7", "EventName": "OCR.DEMAND_RFO.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7",
@@ -51,6 +56,7 @@ }, { "BriefDescription": "Counts demand read for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that have any type of response.", + "Counter": "0,1,2,3", "EventCode": "0x2A,0x2B", "EventName": "OCR.DEMAND_RFO.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7",
tools/perf/pmu-events/arch/x86/lunarlake/pipeline.json +36 -0
@@ -1,6 +1,7 @@ [ { "BriefDescription": "Counts the total number of branch instructions retired for all branch types.", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.ALL_BRANCHES", "PEBS": "1",
@@ -10,6 +11,7 @@ }, { "BriefDescription": "All branch instructions retired.", + "Counter": "0,1,2,3,4,5,6,7,8,9", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.ALL_BRANCHES", "PEBS": "1",
@@ -19,6 +21,7 @@ }, { "BriefDescription": "Counts the total number of mispredicted branch instructions retired for all branch types.", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.ALL_BRANCHES", "PEBS": "1",
@@ -28,6 +31,7 @@ }, { "BriefDescription": "All mispredicted branch instructions retired.", + "Counter": "0,1,2,3,4,5,6,7,8,9", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.ALL_BRANCHES", "PEBS": "1",
@@ -37,6 +41,7 @@ }, { "BriefDescription": "Fixed Counter: Counts the number of unhalted core clock cycles", + "Counter": "Fixed counter 1", "EventName": "CPU_CLK_UNHALTED.CORE", "SampleAfterValue": "2000003", "UMask": "0x2",
@@ -44,6 +49,7 @@ }, { "BriefDescription": "Core cycles when the core is not in a halt state.", + "Counter": "Fixed counter 1", "EventName": "CPU_CLK_UNHALTED.CORE", "PublicDescription": "Counts the number of core cycles while the core is not in a halt state. The core enters the halt state when it is running the HLT instruction. This event is a component in many key event ratios. The core frequency may change from time to time due to transitions associated with Enhanced Intel SpeedStep Technology or TM2. For this reason this event may have a changing ratio with regards to time. When the core frequency is constant, this event can approximate elapsed time while the core was not in the halt state. It is counted on a dedicated fixed counter, leaving the programmable counters available for other events.", "SampleAfterValue": "2000003",
@@ -52,6 +58,7 @@ }, { "BriefDescription": "Counts the number of unhalted core clock cycles [This event is alias to CPU_CLK_UNHALTED.THREAD_P]", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0x3c", "EventName": "CPU_CLK_UNHALTED.CORE_P", "SampleAfterValue": "2000003",
@@ -59,6 +66,7 @@ }, { "BriefDescription": "Thread cycles when thread is not in halt state [This event is alias to CPU_CLK_UNHALTED.THREAD_P]", + "Counter": "0,1,2,3,4,5,6,7,8,9", "EventCode": "0x3c", "EventName": "CPU_CLK_UNHALTED.CORE_P", "PublicDescription": "This is an architectural event that counts the number of thread cycles while the thread is not in a halt state. The thread enters the halt state when it is running the HLT instruction. The core frequency may change from time to time due to power or thermal throttling. For this reason, this event may have a changing ratio with regards to wall clock time. [This event is alias to CPU_CLK_UNHALTED.THREAD_P]",
@@ -67,6 +75,7 @@ }, { "BriefDescription": "Fixed Counter: Counts the number of unhalted reference clock cycles", + "Counter": "Fixed counter 2", "EventName": "CPU_CLK_UNHALTED.REF_TSC", "SampleAfterValue": "2000003", "UMask": "0x3",
@@ -74,6 +83,7 @@ }, { "BriefDescription": "Reference cycles when the core is not in halt state.", + "Counter": "Fixed counter 2", "EventName": "CPU_CLK_UNHALTED.REF_TSC", "PublicDescription": "Counts the number of reference cycles when the core is not in a halt state. The core enters the halt state when it is running the HLT instruction or the MWAIT instruction. This event is not affected by core frequency changes (for example, P states, TM2 transitions) but has the same incrementing frequency as the time stamp counter. This event can approximate elapsed time while the core was not in a halt state. Note: On all current platforms this event stops counting during 'throttling (TM)' states duty off periods the processor is 'halted'. The counter update is done at a lower clock rate then the core clock the overflow status bit for this counter may appear 'sticky'. After the counter has overflowed and software clears the overflow status bit and resets the counter to less than MAX. The reset value to the counter is not clocked immediately so the overflow status bit will flip 'high (1)' and generate another PMI (if enabled) after which the reset value gets clocked into the counter. Therefore, software will get the interrupt, read the overflow status bit '1 for bit 34 while the counter value is less than MAX. Software should ignore this case.", "SampleAfterValue": "2000003",
@@ -82,6 +92,7 @@ }, { "BriefDescription": "Counts the number of unhalted reference clock cycles", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0x3c", "EventName": "CPU_CLK_UNHALTED.REF_TSC_P", "PublicDescription": "Counts the number of reference cycles that the core is not in a halt state. The core enters the halt state when it is running the HLT instruction. This event is not affected by core frequency changes and increments at a fixed frequency that is also used for the Time Stamp Counter (TSC). This event uses a programmable general purpose performance counter.",
@@ -91,6 +102,7 @@ }, { "BriefDescription": "Reference cycles when the core is not in halt state.", + "Counter": "0,1,2,3,4,5,6,7,8,9", "EventCode": "0x3c", "EventName": "CPU_CLK_UNHALTED.REF_TSC_P", "PublicDescription": "Counts the number of reference cycles when the core is not in a halt state. The core enters the halt state when it is running the HLT instruction or the MWAIT instruction. This event is not affected by core frequency changes (for example, P states, TM2 transitions) but has the same incrementing frequency as the time stamp counter. This event can approximate elapsed time while the core was not in a halt state. Note: On all current platforms this event stops counting during 'throttling (TM)' states duty off periods the processor is 'halted'. The counter update is done at a lower clock rate then the core clock the overflow status bit for this counter may appear 'sticky'. After the counter has overflowed and software clears the overflow status bit and resets the counter to less than MAX. The reset value to the counter is not clocked immediately so the overflow status bit will flip 'high (1)' and generate another PMI (if enabled) after which the reset value gets clocked into the counter. Therefore, software will get the interrupt, read the overflow status bit '1 for bit 34 while the counter value is less than MAX. Software should ignore this case.",
@@ -100,6 +112,7 @@ }, { "BriefDescription": "Fixed Counter: Counts the number of unhalted core clock cycles", + "Counter": "Fixed counter 1", "EventName": "CPU_CLK_UNHALTED.THREAD", "SampleAfterValue": "2000003", "UMask": "0x2",
@@ -107,6 +120,7 @@ }, { "BriefDescription": "Core cycles when the thread is not in a halt state.", + "Counter": "Fixed counter 1", "EventName": "CPU_CLK_UNHALTED.THREAD", "PublicDescription": "Counts the number of core cycles while the thread is not in a halt state. The thread enters the halt state when it is running the HLT instruction. This event is a component in many key event ratios. The core frequency may change from time to time due to transitions associated with Enhanced Intel SpeedStep Technology or TM2. For this reason this event may have a changing ratio with regards to time. When the core frequency is constant, this event can approximate elapsed time while the core was not in the halt state. It is counted on a dedicated fixed counter, leaving the programmable counters available for other events.", "SampleAfterValue": "2000003",
@@ -115,6 +129,7 @@ }, { "BriefDescription": "Counts the number of unhalted core clock cycles [This event is alias to CPU_CLK_UNHALTED.CORE_P]", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0x3c", "EventName": "CPU_CLK_UNHALTED.THREAD_P", "SampleAfterValue": "2000003",
@@ -122,6 +137,7 @@ }, { "BriefDescription": "Thread cycles when thread is not in halt state [This event is alias to CPU_CLK_UNHALTED.CORE_P]", + "Counter": "0,1,2,3,4,5,6,7,8,9", "EventCode": "0x3c", "EventName": "CPU_CLK_UNHALTED.THREAD_P", "PublicDescription": "This is an architectural event that counts the number of thread cycles while the thread is not in a halt state. The thread enters the halt state when it is running the HLT instruction. The core frequency may change from time to time due to power or thermal throttling. For this reason, this event may have a changing ratio with regards to wall clock time. [This event is alias to CPU_CLK_UNHALTED.CORE_P]",
@@ -130,6 +146,7 @@ }, { "BriefDescription": "Fixed Counter: Counts the number of instructions retired", + "Counter": "Fixed counter 0", "EventName": "INST_RETIRED.ANY", "PEBS": "1", "SampleAfterValue": "2000003",
@@ -138,6 +155,7 @@ }, { "BriefDescription": "Number of instructions retired. Fixed Counter - architectural event", + "Counter": "Fixed counter 0", "EventName": "INST_RETIRED.ANY", "PEBS": "1", "PublicDescription": "Counts the number of X86 instructions retired - an Architectural PerfMon event. Counting continues during hardware interrupts, traps, and inside interrupt handlers. Notes: INST_RETIRED.ANY is counted by a designated fixed counter freeing up programmable counters to count other events. INST_RETIRED.ANY_P is counted by a programmable counter.",
@@ -147,6 +165,7 @@ }, { "BriefDescription": "Counts the number of instructions retired", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc0", "EventName": "INST_RETIRED.ANY_P", "PEBS": "1",
@@ -155,6 +174,7 @@ }, { "BriefDescription": "Number of instructions retired. General Counter - architectural event", + "Counter": "0,1,2,3,4,5,6,7,8,9", "EventCode": "0xc0", "EventName": "INST_RETIRED.ANY_P", "PEBS": "1",
@@ -164,6 +184,7 @@ }, { "BriefDescription": "Counts the number of occurrences a retired load gets blocked because its address partially overlaps with an older store (size mismatch) - unknown_sta/bad_forward", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0x03", "EventName": "LD_BLOCKS.STORE_FORWARD", "PEBS": "1",
@@ -173,6 +194,7 @@ }, { "BriefDescription": "Loads blocked due to overlapping with a preceding store that cannot be forwarded.", + "Counter": "0,1,2,3,4,5,6,7,8,9", "EventCode": "0x03", "EventName": "LD_BLOCKS.STORE_FORWARD", "PublicDescription": "Counts the number of times where store forwarding was prevented for a load operation. The most common case is a load blocked due to the address of memory access (partially) overlapping with a preceding uncompleted store. Note: See the table of not supported store forwards in the Optimization Guide.",
@@ -182,6 +204,7 @@ }, { "BriefDescription": "Counts the number of LBR entries recorded. Requires LBRs to be enabled in IA32_LBR_CTL.", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xe4", "EventName": "MISC_RETIRED.LBR_INSERTS", "PEBS": "1",
@@ -191,6 +214,7 @@ }, { "BriefDescription": "LBR record is inserted", + "Counter": "0,1,2,3,4,5,6,7,8,9", "EventCode": "0xe4", "EventName": "MISC_RETIRED.LBR_INSERTS", "PEBS": "1",
@@ -200,6 +224,7 @@ }, { "BriefDescription": "This event counts a subset of the Topdown Slots event that were not consumed by the back-end pipeline due to lack of back-end resources, as a result of memory subsystem delays, execution units limitations, or other conditions.", + "Counter": "0,1,2,3,4,5,6,7,8,9", "EventCode": "0xa4", "EventName": "TOPDOWN.BACKEND_BOUND_SLOTS", "PublicDescription": "This event counts a subset of the Topdown Slots event that were not consumed by the back-end pipeline due to lack of back-end resources, as a result of memory subsystem delays, execution units limitations, or other conditions. Software can use this event as the numerator for the Backend Bound metric (or top-level category) of the Top-down Microarchitecture Analysis method.",
@@ -209,6 +234,7 @@ }, { "BriefDescription": "TMA slots available for an unhalted logical processor. Fixed counter - architectural event", + "Counter": "Fixed counter 3", "EventName": "TOPDOWN.SLOTS", "PublicDescription": "Number of available slots for an unhalted logical processor. The event increments by machine-width of the narrowest pipeline as employed by the Top-down Microarchitecture Analysis method (TMA). Software can use this event as the denominator for the top-level metrics of the TMA method. This architectural event is counted on a designated fixed counter (Fixed Counter 3).", "SampleAfterValue": "10000003",
@@ -217,6 +243,7 @@ }, { "BriefDescription": "TMA slots available for an unhalted logical processor. General counter - architectural event", + "Counter": "0,1,2,3,4,5,6,7,8,9", "EventCode": "0xa4", "EventName": "TOPDOWN.SLOTS_P", "PublicDescription": "Counts the number of available slots for an unhalted logical processor. The event increments by machine-width of the narrowest pipeline as employed by the Top-down Microarchitecture Analysis method.",
@@ -226,6 +253,7 @@ }, { "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]", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0x73", "EventName": "TOPDOWN_BAD_SPECULATION.ALL", "SampleAfterValue": "1000003",
@@ -233,6 +261,7 @@ }, { "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]", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0x73", "EventName": "TOPDOWN_BAD_SPECULATION.ALL_P", "SampleAfterValue": "1000003",
@@ -240,6 +269,7 @@ }, { "BriefDescription": "Counts the number of retirement slots not consumed due to backend stalls [This event is alias to TOPDOWN_BE_BOUND.ALL_P]", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xa4", "EventName": "TOPDOWN_BE_BOUND.ALL", "SampleAfterValue": "1000003",
@@ -248,6 +278,7 @@ }, { "BriefDescription": "Counts the number of retirement slots not consumed due to backend stalls [This event is alias to TOPDOWN_BE_BOUND.ALL]", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xa4", "EventName": "TOPDOWN_BE_BOUND.ALL_P", "SampleAfterValue": "1000003",
@@ -256,6 +287,7 @@ }, { "BriefDescription": "Fixed Counter: Counts the number of retirement slots not consumed due to front end stalls", + "Counter": "37", "EventName": "TOPDOWN_FE_BOUND.ALL", "SampleAfterValue": "1000003", "UMask": "0x6",
@@ -263,6 +295,7 @@ }, { "BriefDescription": "Counts the number of retirement slots not consumed due to front end stalls", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0x9c", "EventName": "TOPDOWN_FE_BOUND.ALL_P", "SampleAfterValue": "1000003",
@@ -271,6 +304,7 @@ }, { "BriefDescription": "Fixed Counter: Counts the number of consumed retirement slots.", + "Counter": "38", "EventName": "TOPDOWN_RETIRING.ALL", "PEBS": "1", "SampleAfterValue": "1000003",
@@ -279,6 +313,7 @@ }, { "BriefDescription": "Counts the number of consumed retirement slots.", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc2", "EventName": "TOPDOWN_RETIRING.ALL_P", "PEBS": "1",
@@ -288,6 +323,7 @@ }, { "BriefDescription": "This event counts a subset of the Topdown Slots event that are utilized by operations that eventually get retired (committed) by the processor pipeline. Usually, this event positively correlates with higher performance for example, as measured by the instructions-per-cycle metric.", + "Counter": "0,1,2,3,4,5,6,7,8,9", "EventCode": "0xc2", "EventName": "UOPS_RETIRED.SLOTS", "PublicDescription": "This event counts a subset of the Topdown Slots event that are utilized by operations that eventually get retired (committed) by the processor pipeline. Usually, this event positively correlates with higher performance for example, as measured by the instructions-per-cycle metric. Software can use this event as the numerator for the Retiring metric (or top-level category) of the Top-down Microarchitecture Analysis method.",
tools/perf/pmu-events/arch/x86/lunarlake/virtual-memory.json +6 -0
@@ -1,6 +1,7 @@ [ { "BriefDescription": "Counts the number of page walks completed due to load DTLB misses to any page size.", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0x08", "EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED", "PublicDescription": "Counts the number of page walks completed due to loads (including SW prefetches) whose address translations missed in all Translation Lookaside Buffer (TLB) levels and were mapped to any page size. Includes page walks that page fault.",
@@ -10,6 +11,7 @@ }, { "BriefDescription": "Load miss in all TLB levels causes a page walk that completes. (All page sizes)", + "Counter": "0,1,2,3,4,5,6,7,8,9", "EventCode": "0x12", "EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED", "PublicDescription": "Counts completed page walks (all page sizes) caused by demand data loads. This implies it missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.",
@@ -19,6 +21,7 @@ }, { "BriefDescription": "Counts the number of page walks completed due to store DTLB misses to any page size.", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0x49", "EventName": "DTLB_STORE_MISSES.WALK_COMPLETED", "PublicDescription": "Counts the number of page walks completed due to stores whose address translations missed in all Translation Lookaside Buffer (TLB) levels and were mapped to any page size. Includes page walks that page fault.",
@@ -28,6 +31,7 @@ }, { "BriefDescription": "Store misses in all TLB levels causes a page walk that completes. (All page sizes)", + "Counter": "0,1,2,3,4,5,6,7,8,9", "EventCode": "0x13", "EventName": "DTLB_STORE_MISSES.WALK_COMPLETED", "PublicDescription": "Counts completed page walks (all page sizes) caused by demand data stores. This implies it missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.",
@@ -37,6 +41,7 @@ }, { "BriefDescription": "Counts the number of page walks completed due to instruction fetch misses to any page size.", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0x85", "EventName": "ITLB_MISSES.WALK_COMPLETED", "PublicDescription": "Counts the number of page walks completed due to instruction fetches whose address translations missed in all Translation Lookaside Buffer (TLB) levels and were mapped to any page size. Includes page walks that page fault.",
@@ -46,6 +51,7 @@ }, { "BriefDescription": "Code miss in all TLB levels causes a page walk that completes. (All page sizes)", + "Counter": "0,1,2,3,4,5,6,7,8,9", "EventCode": "0x11", "EventName": "ITLB_MISSES.WALK_COMPLETED", "PublicDescription": "Counts completed page walks (all page sizes) caused by a code fetch. This implies it missed in the ITLB (Instruction TLB) and further levels of TLB. The page walk can end with or without a fault.",
Signature · 1 line
2.45.2.627.g7a2c4fd464-goog
Ian Rogers
reviewerPATCH v2 23/37 perf vendor events: Update meteorlake events and add counter information
In reply to Ian RogersUpdate events from v1.08 to v1.10.
Bring in the event updates v1.10:
https://github.com/intel/perfmon/commit/3bee3dc150164df0bec5980ca5586930730e5778
v1.09:
https://github.com/intel/perfmon/commit/01c8c99f17a72460b2eaf7efe3495913f36c9d42
Add counter information. The most recent RFC patch set using this information:
https://lore.kernel.org/lkml/[email protected]/
New events are:
EXE_ACTIVITY.2_3_PORTS_UTIL,
FP_INST_RETIRED.128B_DP,
FP_INST_RETIRED.128B_SP,
FP_INST_RETIRED.256B_DP,
FP_INST_RETIRED.32B_SP,
FP_INST_RETIRED.64B_DP,
FP_VINT_UOPS_EXECUTED.STD,
L2_LINES_OUT.USELESS_HWPF,
L2_RQSTS.SWPF_HIT,
L2_RQSTS.SWPF_MISS,
LOAD_HIT_PREFETCH.SWPF,
MACHINE_CLEARS.ANY,
MACHINE_CLEARS.MRN_NUKE,
MISC_RETIRED.LBR_INSERTS,
SW_PREFETCH_ACCESS.ANY.
The metrics aren't updated as they require retirement latency support that is added in this series:
https://lore.kernel.org/lkml/[email protected]/
--- tools/perf/pmu-events/arch/x86/mapfile.csv | 2 +- .../pmu-events/arch/x86/meteorlake/cache.json | 223 +++++++++---- .../arch/x86/meteorlake/floating-point.json | 86 ++++- .../arch/x86/meteorlake/frontend.json | 69 ++-- .../arch/x86/meteorlake/memory.json | 62 ++-- .../pmu-events/arch/x86/meteorlake/other.json | 19 +- .../arch/x86/meteorlake/pipeline.json | 300 ++++++++++++++---- .../arch/x86/meteorlake/uncore-cache.json | 2 + .../x86/meteorlake/uncore-interconnect.json | 8 + .../arch/x86/meteorlake/uncore-memory.json | 16 + .../arch/x86/meteorlake/uncore-other.json | 1 + .../arch/x86/meteorlake/virtual-memory.json | 37 +++ 12 files changed, 641 insertions(+), 184 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],v1.08,meteorlake,core +GenuineIntel-6-A[AC],v1.10,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 +166 -57
1,072 lines not on this page · raw message
tools/perf/pmu-events/arch/x86/meteorlake/floating-point.json +80 -6
256 lines not on this page · raw message
tools/perf/pmu-events/arch/x86/meteorlake/frontend.json +49 -20
359 lines not on this page · raw message
tools/perf/pmu-events/arch/x86/meteorlake/memory.json +34 -28
277 lines not on this page · raw message
tools/perf/pmu-events/arch/x86/meteorlake/other.json +17 -2
@@ -1,6 +1,7 @@ [ { "BriefDescription": "ASSISTS.PAGE_FAULT", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc1", "EventName": "ASSISTS.PAGE_FAULT", "SampleAfterValue": "1000003",
@@ -9,16 +10,17 @@ }, { "BriefDescription": "This event is deprecated. [This event is alias to MISC_RETIRED.LBR_INSERTS]", + "Counter": "0,1,2,3,4,5,6,7", "Deprecated": "1", "EventCode": "0xe4", "EventName": "LBR_INSERTS.ANY", - "PEBS": "1", "SampleAfterValue": "1000003", "UMask": "0x1", "Unit": "cpu_atom" }, { "BriefDescription": "Counts demand data reads that have any type of response.", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xB7", "EventName": "OCR.DEMAND_DATA_RD.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7",
@@ -29,6 +31,7 @@ }, { "BriefDescription": "Counts demand data reads that have any type of response.", + "Counter": "0,1,2,3", "EventCode": "0x2A,0x2B", "EventName": "OCR.DEMAND_DATA_RD.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7",
@@ -39,6 +42,7 @@ }, { "BriefDescription": "Counts demand data reads that were supplied by DRAM.", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xB7", "EventName": "OCR.DEMAND_DATA_RD.DRAM", "MSRIndex": "0x1a6,0x1a7",
@@ -49,6 +53,7 @@ }, { "BriefDescription": "Counts demand data reads that were supplied by DRAM.", + "Counter": "0,1,2,3", "EventCode": "0x2A,0x2B", "EventName": "OCR.DEMAND_DATA_RD.DRAM", "MSRIndex": "0x1a6,0x1a7",
@@ -59,6 +64,7 @@ }, { "BriefDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that have any type of response.", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xB7", "EventName": "OCR.DEMAND_RFO.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7",
@@ -69,6 +75,7 @@ }, { "BriefDescription": "Counts demand read for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that have any type of response.", + "Counter": "0,1,2,3", "EventCode": "0x2A,0x2B", "EventName": "OCR.DEMAND_RFO.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7",
@@ -79,6 +86,7 @@ }, { "BriefDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that were supplied by DRAM.", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xB7", "EventName": "OCR.DEMAND_RFO.DRAM", "MSRIndex": "0x1a6,0x1a7",
@@ -89,6 +97,7 @@ }, { "BriefDescription": "Counts streaming stores that have any type of response.", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xB7", "EventName": "OCR.STREAMING_WR.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7",
@@ -99,6 +108,7 @@ }, { "BriefDescription": "Counts streaming stores that have any type of response.", + "Counter": "0,1,2,3", "EventCode": "0x2A,0x2B", "EventName": "OCR.STREAMING_WR.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7",
@@ -109,6 +119,7 @@ }, { "BriefDescription": "Cycles when Reservation Station (RS) is empty for the thread.", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xa5", "EventName": "RS.EMPTY", "PublicDescription": "Counts cycles during which the reservation station (RS) is empty for this logical processor. This is usually caused when the front-end pipeline runs into starvation periods (e.g. branch mispredictions or i-cache misses)",
@@ -118,6 +129,7 @@ }, { "BriefDescription": "Counts end of periods where the Reservation Station (RS) was empty.", + "Counter": "0,1,2,3,4,5,6,7", "CounterMask": "1", "EdgeDetect": "1", "EventCode": "0xa5",
@@ -129,7 +141,8 @@ "Unit": "cpu_core" }, { - "BriefDescription": "RS.EMPTY_RESOURCE", + "BriefDescription": "Cycles when RS was empty and a resource allocation stall is asserted", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xa5", "EventName": "RS.EMPTY_RESOURCE", "SampleAfterValue": "1000003",
@@ -138,6 +151,7 @@ }, { "BriefDescription": "Counts the number of issue slots in a UMWAIT or TPAUSE instruction where no uop issues due to the instruction putting the CPU into the C0.1 activity state.", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0x75", "EventName": "SERIALIZATION.C01_MS_SCB", "SampleAfterValue": "200003",
@@ -146,6 +160,7 @@ }, { "BriefDescription": "Cycles the uncore cannot take further requests", + "Counter": "0,1,2,3", "CounterMask": "1", "EventCode": "0x2d", "EventName": "XQ.FULL_CYCLES",
tools/perf/pmu-events/arch/x86/meteorlake/pipeline.json +230 -70
910 lines not on this page · raw message
tools/perf/pmu-events/arch/x86/meteorlake/uncore-cache.json +2 -0
Lines of this file are not shown. View the raw message.
tools/perf/pmu-events/arch/x86/meteorlake/uncore-interconnect.json +8 -0
Lines of this file are not shown. View the raw message.
tools/perf/pmu-events/arch/x86/meteorlake/uncore-memory.json +16 -0
Lines of this file are not shown. View the raw message.
tools/perf/pmu-events/arch/x86/meteorlake/uncore-other.json +1 -0
Lines of this file are not shown. View the raw message.
tools/perf/pmu-events/arch/x86/meteorlake/virtual-memory.json +37 -0
Lines of this file are not shown. View the raw message.
The rest of this diff is not shown. View the raw message.
Signature · 1 line
2.45.2.627.g7a2c4fd464-goog
Part of the diff is not shown here. View the raw message.