perf, tools: Add support for recording and printing XMM registers
PATCH 1/3 perf, tools: Add support for recording and printing XMM registers
From: Andi Kleen <[email protected]>
Icelake and later platforms support collecting XMM registers with PEBS event.
Add support for perf script to dump them, and support
for the register parser in perf record -I ... to configure them. For now they are just printed in hex, could potentially add other formats too.
--- tools/arch/x86/include/uapi/asm/perf_regs.h | 23 ++++++++++++++++++- tools/perf/arch/x86/include/perf_regs.h | 25 +++++++++++++++++++-- tools/perf/arch/x86/util/perf_regs.c | 16 +++++++++++++ tools/perf/util/perf_regs.h | 1 + 4 files changed, 62 insertions(+), 3 deletions(-)
tools/arch/x86/include/uapi/asm/perf_regs.h +22 -1
@@ -27,8 +27,29 @@ enum perf_event_x86_regs {PERF_REG_X86_R13 ,PERF_REG_X86_R14 ,PERF_REG_X86_R15 , - +/* These are the limits for the GPRs. */ PERF_REG_X86_32_MAX =PERF_REG_X86_GS +1 ,PERF_REG_X86_64_MAX =PERF_REG_X86_R15 +1 , + +/* These all need two bits set because they are 128bit */ +PERF_REG_X86_XMM0 =32 , +PERF_REG_X86_XMM1 =34 , +PERF_REG_X86_XMM2 =36 , +PERF_REG_X86_XMM3 =38 , +PERF_REG_X86_XMM4 =40 , +PERF_REG_X86_XMM5 =42 , +PERF_REG_X86_XMM6 =44 , +PERF_REG_X86_XMM7 =46 , +PERF_REG_X86_XMM8 =48 , +PERF_REG_X86_XMM9 =50 , +PERF_REG_X86_XMM10 =52 , +PERF_REG_X86_XMM11 =54 , +PERF_REG_X86_XMM12 =56 , +PERF_REG_X86_XMM13 =58 , +PERF_REG_X86_XMM14 =60 , +PERF_REG_X86_XMM15 =62 , + +/* These include both GPRs and XMMX registers */ + PERF_REG_X86_XMM_MAX = PERF_REG_X86_XMM15 + 2, };#endif /* _ASM_X86_PERF_REGS_H */
tools/perf/arch/x86/include/perf_regs.h +23 -2
@@ -8,9 +8,9 @@void perf_regs_load (u64 *regs); +#define PERF_REGS_MAX PERF_REG_X86_XMM_MAX#ifndef HAVE_ARCH_X86_64_SUPPORT #define PERF_REGS_MASK ((1ULL << PERF_REG_X86_32_MAX) - 1) -#define PERF_REGS_MAX PERF_REG_X86_32_MAX#define PERF_SAMPLE_REGS_ABI PERF_SAMPLE_REGS_ABI_32#else #define REG_NOSUPPORT ((1ULL << PERF_REG_X86_DS) | \
@@ -18,7 +18,6 @@ void perf_regs_load(u64 *regs); (1ULL << PERF_REG_X86_FS) | \ (1ULL << PERF_REG_X86_GS))#define PERF_REGS_MASK (((1ULL << PERF_REG_X86_64_MAX) - 1) & ~REG_NOSUPPORT) -#define PERF_REGS_MAX PERF_REG_X86_64_MAX#define PERF_SAMPLE_REGS_ABI PERF_SAMPLE_REGS_ABI_64#endif #define PERF_REG_IP PERF_REG_X86_IP
@@ -77,6 +76,28 @@ static inline const char *perf_reg_name(int id)case PERF_REG_X86_R15 :return "R15" ;#endif /* HAVE_ARCH_X86_64_SUPPORT */ + +#define XMM (x) \ + case PERF_REG_X86_XMM ## x: \ + case PERF_REG_X86_XMM ## x + 1: \ + return "XMM" #x; + XMM(0) + XMM(1) + XMM(2) + XMM(3) + XMM(4) + XMM(5) + XMM(6) + XMM(7) + XMM(8) + XMM(9) + XMM(10) + XMM(11) + XMM(12) + XMM(13) + XMM(14) + XMM(15) +#undef XMMdefault :return NULL ; }
tools/perf/arch/x86/util/perf_regs.c +16 -0
@@ -31,6 +31,22 @@ const struct sample_reg sample_reg_masks[] = {SMPL_REG (R14 ,PERF_REG_X86_R14 ),SMPL_REG (R15 ,PERF_REG_X86_R15 ), #endif +SMPL_REG2 (XMM0 ,PERF_REG_X86_XMM0 ), +SMPL_REG2 (XMM1 ,PERF_REG_X86_XMM1 ), +SMPL_REG2 (XMM2 ,PERF_REG_X86_XMM2 ), +SMPL_REG2 (XMM3 ,PERF_REG_X86_XMM3 ), +SMPL_REG2 (XMM4 ,PERF_REG_X86_XMM4 ), +SMPL_REG2 (XMM5 ,PERF_REG_X86_XMM5 ), +SMPL_REG2 (XMM6 ,PERF_REG_X86_XMM6 ), +SMPL_REG2 (XMM7 ,PERF_REG_X86_XMM7 ), +SMPL_REG2 (XMM8 ,PERF_REG_X86_XMM8 ), +SMPL_REG2 (XMM9 ,PERF_REG_X86_XMM9 ), +SMPL_REG2 (XMM10 ,PERF_REG_X86_XMM10 ), +SMPL_REG2 (XMM11 ,PERF_REG_X86_XMM11 ), +SMPL_REG2 (XMM12 ,PERF_REG_X86_XMM12 ), +SMPL_REG2 (XMM13 ,PERF_REG_X86_XMM13 ), +SMPL_REG2 (XMM14 ,PERF_REG_X86_XMM14 ), +SMPL_REG2 (XMM15 ,PERF_REG_X86_XMM15 ),SMPL_REG_END };
tools/perf/util/perf_regs.h +1 -0
@@ -12,6 +12,7 @@ struct sample_reg {uint64_t mask; };#define SMPL_REG (n, b) { .name = #n, .mask = 1ULL << (b) } +#define SMPL_REG2 (n, b) { .name = #n, .mask = 3ULL << (b) }#define SMPL_REG_END { .name = NULL }extern const struct sample_reg sample_reg_masks[];
Signature · 1 line
2.17.1
PATCH 2/3 perf vendor events intel: Add JSON files for Icelake
From: Kan Liang <[email protected]>
Add V1 event list for Icelake.
--- .../pmu-events/arch/x86/icelake/cache.json | 552 +++++++++++ .../arch/x86/icelake/floating-point.json | 90 ++ .../pmu-events/arch/x86/icelake/frontend.json | 424 +++++++++ .../pmu-events/arch/x86/icelake/memory.json | 410 ++++++++ .../pmu-events/arch/x86/icelake/other.json | 133 +++ .../pmu-events/arch/x86/icelake/pipeline.json | 892 ++++++++++++++++++ .../arch/x86/icelake/virtual-memory.json | 236 +++++ tools/perf/pmu-events/arch/x86/mapfile.csv | 1 + 8 files changed, 2738 insertions(+) create mode 100644 tools/perf/pmu-events/arch/x86/icelake/cache.json create mode 100644 tools/perf/pmu-events/arch/x86/icelake/floating-point.json create mode 100644 tools/perf/pmu-events/arch/x86/icelake/frontend.json create mode 100644 tools/perf/pmu-events/arch/x86/icelake/memory.json create mode 100644 tools/perf/pmu-events/arch/x86/icelake/other.json create mode 100644 tools/perf/pmu-events/arch/x86/icelake/pipeline.json create mode 100644 tools/perf/pmu-events/arch/x86/icelake/virtual-memory.json
tools/perf/pmu-events/arch/x86/icelake/cache.json new file +552 -0
@@ -0,0 +1,552 @@ +[ + { + "CollectPEBSRecord": "2", + "PublicDescription": "Counts the number of demand Data Read requests that miss L2 cache. Only not rejected loads are counted.", + "EventCode": "0x24", + "Counter": "0,1,2,3", + "UMask": "0x21", + "PEBScounters": "0,1,2,3", + "EventName": "L2_RQSTS.DEMAND_DATA_RD_MISS", + "SampleAfterValue": "200003", + "BriefDescription": "Demand Data Read miss L2, no rejects" + }, + { + "CollectPEBSRecord": "2", + "PublicDescription": "Counts the RFO (Read-for-Ownership) requests that miss L2 cache.", + "EventCode": "0x24", + "Counter": "0,1,2,3", + "UMask": "0x22", + "PEBScounters": "0,1,2,3", + "EventName": "L2_RQSTS.RFO_MISS", + "SampleAfterValue": "200003", + "BriefDescription": "RFO requests that miss L2 cache" + }, + { + "CollectPEBSRecord": "2", + "PublicDescription": "Counts L2 cache misses when fetching instructions.", + "EventCode": "0x24", + "Counter": "0,1,2,3", + "UMask": "0x24", + "PEBScounters": "0,1,2,3", + "EventName": "L2_RQSTS.CODE_RD_MISS", + "SampleAfterValue": "200003", + "BriefDescription": "L2 cache misses when fetching instructions" + }, + { + "CollectPEBSRecord": "2", + "PublicDescription": "Counts demand requests that miss L2 cache.", + "EventCode": "0x24", + "Counter": "0,1,2,3", + "UMask": "0x27", + "PEBScounters": "0,1,2,3", + "EventName": "L2_RQSTS.ALL_DEMAND_MISS", + "SampleAfterValue": "200003", + "BriefDescription": "Demand requests that miss L2 cache" + }, + { + "CollectPEBSRecord": "2", + "PublicDescription": "Counts Software prefetch requests that miss the L2 cache. This event accounts for PREFETCHNTA and PREFETCHT0/1/2 instructions.", + "EventCode": "0x24", + "Counter": "0,1,2,3", + "UMask": "0x28", + "PEBScounters": "0,1,2,3", + "EventName": "L2_RQSTS.SWPF_MISS", + "SampleAfterValue": "200003", + "BriefDescription": "SW prefetch requests that miss L2 cache." + }, + { + "CollectPEBSRecord": "2", + "PublicDescription": "Counts the number of demand Data Read requests initiated by load instructions that hit L2 cache.", + "EventCode": "0x24", + "Counter": "0,1,2,3", + "UMask": "0xc1", + "PEBScounters": "0,1,2,3", + "EventName": "L2_RQSTS.DEMAND_DATA_RD_HIT", + "SampleAfterValue": "200003", + "BriefDescription": "Demand Data Read requests that hit L2 cache" + }, + { + "CollectPEBSRecord": "2", + "PublicDescription": "Counts the RFO (Read-for-Ownership) requests that hit L2 cache.", + "EventCode": "0x24", + "Counter": "0,1,2,3", + "UMask": "0xc2", + "PEBScounters": "0,1,2,3", + "EventName": "L2_RQSTS.RFO_HIT", + "SampleAfterValue": "200003", + "BriefDescription": "RFO requests that hit L2 cache" + }, + { + "CollectPEBSRecord": "2", + "PublicDescription": "Counts L2 cache hits when fetching instructions, code reads.", + "EventCode": "0x24", + "Counter": "0,1,2,3", + "UMask": "0xc4", + "PEBScounters": "0,1,2,3", + "EventName": "L2_RQSTS.CODE_RD_HIT", + "SampleAfterValue": "200003", + "BriefDescription": "L2 cache hits when fetching instructions, code reads." + }, + { + "CollectPEBSRecord": "2", + "PublicDescription": "Counts Software prefetch requests that hit the L2 cache. This event accounts for PREFETCHNTA and PREFETCHT0/1/2 instructions.", + "EventCode": "0x24", + "Counter": "0,1,2,3", + "UMask": "0xc8", + "PEBScounters": "0,1,2,3", + "EventName": "L2_RQSTS.SWPF_HIT", + "SampleAfterValue": "200003", + "BriefDescription": "SW prefetch requests that hit L2 cache." + }, + { + "CollectPEBSRecord": "2", + "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.", + "EventCode": "0x24", + "Counter": "0,1,2,3", + "UMask": "0xe1", + "PEBScounters": "0,1,2,3", + "EventName": "L2_RQSTS.ALL_DEMAND_DATA_RD", + "SampleAfterValue": "200003", + "BriefDescription": "Demand Data Read requests" + }, + { + "CollectPEBSRecord": "2", + "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.", + "EventCode": "0x24", + "Counter": "0,1,2,3", + "UMask": "0xe2", + "PEBScounters": "0,1,2,3", + "EventName": "L2_RQSTS.ALL_RFO", + "SampleAfterValue": "200003", + "BriefDescription": "RFO requests to L2 cache" + }, + { + "CollectPEBSRecord": "2", + "PublicDescription": "Counts the total number of L2 code requests.", + "EventCode": "0x24", + "Counter": "0,1,2,3", + "UMask": "0xe4", + "PEBScounters": "0,1,2,3", + "EventName": "L2_RQSTS.ALL_CODE_RD", + "SampleAfterValue": "200003", + "BriefDescription": "L2 code requests" + }, + { + "CollectPEBSRecord": "2", + "PublicDescription": "Counts demand requests to L2 cache.", + "EventCode": "0x24", + "Counter": "0,1,2,3", + "UMask": "0xe7", + "PEBScounters": "0,1,2,3", + "EventName": "L2_RQSTS.ALL_DEMAND_REFERENCES", + "SampleAfterValue": "200003", + "BriefDescription": "Demand requests to L2 cache" + }, + { + "CollectPEBSRecord": "2", + "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.", + "EventCode": "0x48", + "Counter": "0,1,2,3", + "UMask": "0x1", + "PEBScounters": "0,1,2,3", + "EventName": "L1D_PEND_MISS.PENDING", + "SampleAfterValue": "2000003", + "BriefDescription": "Number of L1D misses that are outstanding" + }, + { + "CollectPEBSRecord": "2", + "PublicDescription": "Counts duration of L1D miss outstanding in cycles.", + "EventCode": "0x48", + "Counter": "0,1,2,3", + "UMask": "0x1", + "PEBScounters": "0,1,2,3", + "EventName": "L1D_PEND_MISS.PENDING_CYCLES", + "SampleAfterValue": "2000003", + "BriefDescription": "Cycles with L1D load Misses outstanding.", + "CounterMask": "1" + }, + { + "CollectPEBSRecord": "2", + "PublicDescription": "Counts number of cycles a demand request has waited due to L1D Fill Buffer (FB) unavailablability. Demand requests include cacheable/uncacheable demand load, store, lock or SW prefetch accesses.", + "EventCode": "0x48", + "Counter": "0,1,2,3", + "UMask": "0x2", + "PEBScounters": "0,1,2,3", + "EventName": "L1D_PEND_MISS.FB_FULL", + "SampleAfterValue": "2000003", + "BriefDescription": "Number of cycles a demand request has waited due to L1D Fill Buffer (FB) unavailablability." + }, + { + "CollectPEBSRecord": "2", + "PublicDescription": "Counts number of phases a demand request has waited due to L1D Fill Buffer (FB) unavailablability. Demand requests include cacheable/uncacheable demand load, store, lock or SW prefetch accesses.", + "EventCode": "0x48", + "Counter": "0,1,2,3", + "UMask": "0x2", + "PEBScounters": "0,1,2,3", + "EventName": "L1D_PEND_MISS.FB_FULL_PERIODS", + "SampleAfterValue": "2000003", + "BriefDescription": "Number of phases a demand request has waited due to L1D Fill Buffer (FB) unavailablability.", + "CounterMask": "1", + "EdgeDetect": "1" + }, + { + "CollectPEBSRecord": "2", + "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.", + "EventCode": "0x48", + "Counter": "0,1,2,3", + "UMask": "0x4", + "PEBScounters": "0,1,2,3", + "EventName": "L1D_PEND_MISS.L2_STALL", + "SampleAfterValue": "2000003", + "BriefDescription": "Number of cycles a demand request has waited due to L1D due to lack of L2 resources." + }, + { + "CollectPEBSRecord": "2", + "PublicDescription": "Counts L1D data line replacements including opportunistic replacements, and replacements that require stall-for-replace or block-for-replace.", + "EventCode": "0x51", + "Counter": "0,1,2,3", + "UMask": "0x1", + "PEBScounters": "0,1,2,3", + "EventName": "L1D.REPLACEMENT", + "SampleAfterValue": "2000003", + "BriefDescription": "Counts the number of cache lines replaced in L1 data cache." + }, + { + "CollectPEBSRecord": "2", + "PublicDescription": "Counts the number of offcore outstanding demand rfo Reads transactions in the super queue every cycle. The 'Offcore outstanding' state of the transaction lasts from the L2 miss until the sending transaction completion to requestor (SQ deallocation). See the corresponding Umask under OFFCORE_REQUESTS.", + "EventCode": "0x60", + "Counter": "0,1,2,3", + "UMask": "0x4", + "PEBScounters": "0,1,2,3", + "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO", + "SampleAfterValue": "2000003", + "BriefDescription": "Cycles with offcore outstanding demand rfo reads transactions in SuperQueue (SQ), queue to uncore.", + "CounterMask": "1" + }, + { + "CollectPEBSRecord": "2", + "PublicDescription": "Counts the number of offcore outstanding cacheable Core Data Read transactions in the super queue every cycle. A transaction is considered to be in the Offcore outstanding state between L2 miss and transaction completion sent to requestor (SQ de-allocation). See corresponding Umask under OFFCORE_REQUESTS.", + "EventCode": "0x60", + "Counter": "0,1,2,3", + "UMask": "0x8", + "PEBScounters": "0,1,2,3", + "EventName": "OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD", + "SampleAfterValue": "2000003", + "BriefDescription": "Offcore outstanding cacheable Core Data Read transactions in SuperQueue (SQ), queue to uncore" + }, + { + "CollectPEBSRecord": "2", + "PublicDescription": "Counts cycles when offcore outstanding cacheable Core Data Read transactions are present in the super queue. A transaction is considered to be in the Offcore outstanding state between L2 miss and transaction completion sent to requestor (SQ de-allocation). See corresponding Umask under OFFCORE_REQUESTS.", + "EventCode": "0x60", + "Counter": "0,1,2,3", + "UMask": "0x8", + "PEBScounters": "0,1,2,3", + "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD", + "SampleAfterValue": "2000003", + "BriefDescription": "Cycles when offcore outstanding cacheable Core Data Read transactions are present in SuperQueue (SQ), queue to uncore.", + "CounterMask": "1" + }, + { + "CollectPEBSRecord": "2", + "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.", + "EventCode": "0xB0", + "Counter": "0,1,2,3", + "UMask": "0x1", + "PEBScounters": "0,1,2,3", + "EventName": "OFFCORE_REQUESTS.DEMAND_DATA_RD", + "SampleAfterValue": "100003", + "BriefDescription": "Demand Data Read requests sent to uncore" + }, + { + "CollectPEBSRecord": "2", + "PublicDescription": "Counts the demand RFO (read for ownership) requests including regular RFOs, locks, ItoM.", + "EventCode": "0xB0", + "Counter": "0,1,2,3", + "UMask": "0x4", + "PEBScounters": "0,1,2,3", + "EventName": "OFFCORE_REQUESTS.DEMAND_RFO", + "SampleAfterValue": "100003", + "BriefDescription": "Demand RFO requests including regular RFOs, locks, ItoM" + }, + { + "CollectPEBSRecord": "2", + "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.", + "EventCode": "0xB0", + "Counter": "0,1,2,3", + "UMask": "0x8", + "PEBScounters": "0,1,2,3", + "EventName": "OFFCORE_REQUESTS.ALL_DATA_RD", + "SampleAfterValue": "100003", + "BriefDescription": "Demand and prefetch data reads" + }, + { + "CollectPEBSRecord": "2", + "PublicDescription": "Counts memory transactions reached the super queue including requests initiated by the core, all L3 prefetches, page walks, etc..", + "EventCode": "0xB0", + "Counter": "0,1,2,3", + "UMask": "0x80", + "PEBScounters": "0,1,2,3", + "EventName": "OFFCORE_REQUESTS.ALL_REQUESTS", + "SampleAfterValue": "100003", + "BriefDescription": "Any memory transaction that reached the SQ." + }, + { + "PEBS": "1", + "CollectPEBSRecord": "2", + "PublicDescription": "Counts retired load instructions that true miss the STLB.", + "EventCode": "0xD0", + "Counter": "0,1,2,3", + "UMask": "0x11", + "PEBScounters": "0,1,2,3", + "EventName": "MEM_INST_RETIRED.STLB_MISS_LOADS", + "SampleAfterValue": "100003", + "BriefDescription": "Retired load instructions that miss the STLB.", + "Data_LA": "1" + }, + { + "PEBS": "1", + "CollectPEBSRecord": "2", + "PublicDescription": "Counts retired store instructions that true miss the STLB.", + "EventCode": "0xD0", + "Counter": "0,1,2,3", + "UMask": "0x12", + "PEBScounters": "0,1,2,3", + "EventName": "MEM_INST_RETIRED.STLB_MISS_STORES", + "SampleAfterValue": "100003", + "BriefDescription": "Retired store instructions that miss the STLB.", + "Data_LA": "1", + "L1_Hit_Indication": "1" + }, + { + "PEBS": "1", + "CollectPEBSRecord": "2", + "PublicDescription": "Counts retired load instructions with locked access.", + "EventCode": "0xD0", + "Counter": "0,1,2,3", + "UMask": "0x21", + "PEBScounters": "0,1,2,3", + "EventName": "MEM_INST_RETIRED.LOCK_LOADS", + "SampleAfterValue": "100007", + "BriefDescription": "Retired load instructions with locked access.", + "Data_LA": "1" + }, + { + "PEBS": "1", + "CollectPEBSRecord": "2", + "PublicDescription": "Counts retired load instructions that split across a cacheline boundary.", + "EventCode": "0xD0", + "Counter": "0,1,2,3", + "UMask": "0x41", + "PEBScounters": "0,1,2,3", + "EventName": "MEM_INST_RETIRED.SPLIT_LOADS", + "SampleAfterValue": "100003", + "BriefDescription": "Retired load instructions that split across a cacheline boundary.", + "Data_LA": "1" + }, + { + "PEBS": "1", + "CollectPEBSRecord": "2", + "PublicDescription": "Counts retired store instructions that split across a cacheline boundary.", + "EventCode": "0xD0", + "Counter": "0,1,2,3", + "UMask": "0x42", + "PEBScounters": "0,1,2,3", + "EventName": "MEM_INST_RETIRED.SPLIT_STORES", + "SampleAfterValue": "100003", + "BriefDescription": "Retired store instructions that split across a cacheline boundary.", + "Data_LA": "1", + "L1_Hit_Indication": "1" + }, + { + "PEBS": "1", + "CollectPEBSRecord": "2", + "PublicDescription": "Counts all retired load instructions. This event accounts for SW prefetch instructions for loads.", + "EventCode": "0xD0", + "Counter": "0,1,2,3", + "UMask": "0x81", + "PEBScounters": "0,1,2,3", + "EventName": "MEM_INST_RETIRED.ALL_LOADS", + "SampleAfterValue": "2000003", + "BriefDescription": "All retired load instructions.", + "Data_LA": "1" + }, + { + "PEBS": "1", + "CollectPEBSRecord": "2", + "PublicDescription": "Counts all retired store instructions. This event account for SW prefetch instructions and PREFETCHW instruction for stores.", + "EventCode": "0xD0", + "Counter": "0,1,2,3", + "UMask": "0x82", + "PEBScounters": "0,1,2,3", + "EventName": "MEM_INST_RETIRED.ALL_STORES", + "SampleAfterValue": "2000003", + "BriefDescription": "All retired store instructions.", + "Data_LA": "1", + "L1_Hit_Indication": "1" + }, + { + "PEBS": "1", + "CollectPEBSRecord": "2", + "PublicDescription": "Counts retired load instructions with at least one uop that hit in the L1 data cache. This event includes all SW prefetches and lock instructions regardless of the data source.", + "EventCode": "0xD1", + "Counter": "0,1,2,3", + "UMask": "0x1", + "PEBScounters": "0,1,2,3", + "EventName": "MEM_LOAD_RETIRED.L1_HIT", + "SampleAfterValue": "2000003", + "BriefDescription": "Retired load instructions with L1 cache hits as data sources", + "Data_LA": "1" + }, + { + "PEBS": "1", + "CollectPEBSRecord": "2", + "PublicDescription": "Counts retired load instructions with L2 cache hits as data sources.", + "EventCode": "0xD1", + "Counter": "0,1,2,3", + "UMask": "0x2", + "PEBScounters": "0,1,2,3", + "EventName": "MEM_LOAD_RETIRED.L2_HIT", + "SampleAfterValue": "100003", + "BriefDescription": "Retired load instructions with L2 cache hits as data sources", + "Data_LA": "1" + }, + { + "PEBS": "1", + "CollectPEBSRecord": "2", + "PublicDescription": "Counts retired load instructions with at least one uop that hit in the L3 cache.", + "EventCode": "0xD1", + "Counter": "0,1,2,3", + "UMask": "0x4", + "PEBScounters": "0,1,2,3", + "EventName": "MEM_LOAD_RETIRED.L3_HIT", + "SampleAfterValue": "50021", + "BriefDescription": "Retired load instructions with L3 cache hits as data sources", + "Data_LA": "1" + }, + { + "PEBS": "1", + "CollectPEBSRecord": "2", + "PublicDescription": "Counts retired load instructions with at least one uop that missed in the L1 cache.", + "EventCode": "0xD1", + "Counter": "0,1,2,3", + "UMask": "0x8", + "PEBScounters": "0,1,2,3", + "EventName": "MEM_LOAD_RETIRED.L1_MISS", + "SampleAfterValue": "100003", + "BriefDescription": "Retired load instructions missed L1 cache as data sources", + "Data_LA": "1" + }, + { + "PEBS": "1", + "CollectPEBSRecord": "2", + "PublicDescription": "Counts retired load instructions missed L2 cache as data sources.", + "EventCode": "0xD1", + "Counter": "0,1,2,3", + "UMask": "0x10", + "PEBScounters": "0,1,2,3", + "EventName": "MEM_LOAD_RETIRED.L2_MISS", + "SampleAfterValue": "50021", + "BriefDescription": "Retired load instructions missed L2 cache as data sources", + "Data_LA": "1" + }, + { + "PEBS": "1", + "CollectPEBSRecord": "2", + "PublicDescription": "Counts retired load instructions with at least one uop that missed in the L3 cache.", + "EventCode": "0xD1", + "Counter": "0,1,2,3", + "UMask": "0x20", + "PEBScounters": "0,1,2,3", + "EventName": "MEM_LOAD_RETIRED.L3_MISS", + "SampleAfterValue": "100007", + "BriefDescription": "Retired load instructions missed L3 cache as data sources", + "Data_LA": "1" + }, + { + "PEBS": "1", + "CollectPEBSRecord": "2", + "PublicDescription": "Counts retired load instructions with at least one uop was load missed in L1 but hit FB (Fill Buffers) due to preceding miss to the same cache line with data not ready.", + "EventCode": "0xd1", + "Counter": "0,1,2,3", + "UMask": "0x40", + "PEBScounters": "0,1,2,3", + "EventName": "MEM_LOAD_RETIRED.FB_HIT", + "SampleAfterValue": "100007", + "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.", + "Data_LA": "1" + }, + { + "PEBS": "1", + "CollectPEBSRecord": "2", + "PublicDescription": "Counts the retired load instructions whose data sources were L3 hit and cross-core snoop missed in on-pkg core cache.", + "EventCode": "0xd2", + "Counter": "0,1,2,3", + "UMask": "0x1", + "PEBScounters": "0,1,2,3", + "EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS", + "SampleAfterValue": "20011", + "BriefDescription": "Retired load instructions whose data sources were L3 hit and cross-core snoop missed in on-pkg core cache.", + "Data_LA": "1" + }, + { + "PEBS": "1", + "CollectPEBSRecord": "2", + "PublicDescription": "Counts retired load instructions whose data sources were L3 and cross-core snoop hits in on-pkg core cache.", + "EventCode": "0xd2", + "Counter": "0,1,2,3", + "UMask": "0x2", + "PEBScounters": "0,1,2,3", + "EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_HIT", + "SampleAfterValue": "20011", + "BriefDescription": "Retired load instructions whose data sources were L3 and cross-core snoop hits in on-pkg core cache", + "Data_LA": "1" + }, + { + "PEBS": "1", + "CollectPEBSRecord": "2", + "PublicDescription": "Counts retired load instructions whose data sources were HitM responses from shared L3.", + "EventCode": "0xd2", + "Counter": "0,1,2,3", + "UMask": "0x4", + "PEBScounters": "0,1,2,3", + "EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM", + "SampleAfterValue": "20011", + "BriefDescription": "Retired load instructions whose data sources were HitM responses from shared L3", + "Data_LA": "1" + }, + { + "PEBS": "1", + "CollectPEBSRecord": "2", + "PublicDescription": "Counts retired load instructions whose data sources were hits in L3 without snoops required.", + "EventCode": "0xd2", + "Counter": "0,1,2,3", + "UMask": "0x8", + "PEBScounters": "0,1,2,3", + "EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_NONE", + "SampleAfterValue": "100003", + "BriefDescription": "Retired load instructions whose data sources were hits in L3 without snoops required", + "Data_LA": "1" + }, + { + "CollectPEBSRecord": "2", + "PublicDescription": "Counts the number of L2 cache lines filling the L2. Counting does not cover rejects.", + "EventCode": "0xF1", + "Counter": "0,1,2,3", + "UMask": "0x1f", + "PEBScounters": "0,1,2,3", + "EventName": "L2_LINES_IN.ALL", + "SampleAfterValue": "100003", + "BriefDescription": "L2 cache lines filling L2" + }, + { + "CollectPEBSRecord": "2", + "PublicDescription": "Counts the cycles for which the thread is active and the superQ cannot take any more entries.", + "EventCode": "0xF4", + "Counter": "0,1,2,3", + "UMask": "0x4", + "PEBScounters": "0,1,2,3", + "EventName": "SQ_MISC.SQ_FULL", + "SampleAfterValue": "100003", + "BriefDescription": "Cycles the thread is active and superQ cannot take any more entries." + } +]
tools/perf/pmu-events/arch/x86/icelake/floating-point.json new file +90 -0
91 lines not on this page · raw message
tools/perf/pmu-events/arch/x86/icelake/frontend.json new file +424 -0
425 lines not on this page · raw message
tools/perf/pmu-events/arch/x86/icelake/memory.json new file +410 -0
411 lines not on this page · raw message
tools/perf/pmu-events/arch/x86/icelake/other.json new file +133 -0
134 lines not on this page · raw message
tools/perf/pmu-events/arch/x86/icelake/pipeline.json new file +35 -0
@@ -0,0 +1,892 @@ +[ + { + "CollectPEBSRecord": "2", + "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.", + "Counter": "32", + "UMask": "0x1", + "PEBScounters": "32", + "EventName": "INST_RETIRED.ANY", + "SampleAfterValue": "2000003", + "BriefDescription": "Number of instructions retired. Fixed Counter - architectural event" + }, + { + "PEBS": "2", + "CollectPEBSRecord": "3", + "PublicDescription": "A version of INST_RETIRED that allows for a more unbiased distribution of samples across instructions retired. It utilizes the Precise Distribution of Instructions Retired (PDIR) feature to mitigate some bias in how retired instructions get sampled. Use on Fixed Counter 0.", + "Counter": "32", + "UMask": "0x1", + "PEBScounters": "32", + "EventName": "INST_RETIRED.PREC_DIST", + "SampleAfterValue": "2000003", + "BriefDescription": "Precise instruction retired event with a reduced effect of PEBS shadow in IP distribution" + }, + { + "CollectPEBSRecord": "2", + "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 four (eight when Hyperthreading is disabled) programmable counters available for other events.", + "Counter": "33", + "UMask": "0x2", + "PEBScounters": "33", + "EventName": "CPU_CLK_UNHALTED.THREAD", + "SampleAfterValue": "2000003", + "BriefDescription": "Core cycles when the thread is not in halt state" + }, + { + "CollectPEBSRecord": "2", + "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. This event has a constant ratio with the CPU_CLK_UNHALTED.REF_XCLK event. It is counted on a dedicated fixed counter, leaving the four (eight when Hyperthreading is disabled) programmable counters available for other events. 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 overfl
ow 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.",
+ "Counter": "34",
+ "UMask": "0x3",
+ "PEBScounters": "34",
+ "EventName": "CPU_CLK_UNHALTED.REF_TSC",
+ "SampleAfterValue": "2000003",
+ "BriefDescription": "Reference cycles when the core is not in halt state."
+ },
+ {
+ "CollectPEBSRecord": "2",
+ "PublicDescription": "Counts the number of times the load operation got the true Block-on-Store blocking code preventing store forwarding. This includes cases when: a. preceding store conflicts with the load (incomplete overlap),b. store forwarding is impossible due to u-arch limitations, c. preceding lock RMW operations are not forwarded, d. store has the no-forward bit set (uncacheable/page-split/masked stores), e. all-blocking stores are used (mostly, fences and port I/O), and others. The most common case is a load blocked due to its address range overlapping with a preceding smaller uncompleted store. Note: This event does not take into account cases of out-of-SW-control (for example, SbTailHit), unknown physical STA, and cases of blocking loads on store due to being non-WB memory type or a lock. These cases are covered by other events. See the table of not supported store forwards in the Optimization Guide.",
+ "EventCode": "0x03",
+ "Counter": "0,1,2,3",
+ "UMask": "0x2",
+ "PEBScounters": "0,1,2,3",
+ "EventName": "LD_BLOCKS.STORE_FORWARD",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "Loads blocked by overlapping with store buffer that cannot be forwarded."
+ },
+ {
+ "CollectPEBSRecord": "2",
+ "PublicDescription": "Counts the number of times that split load operations are temporarily blocked because all resources for handling the split accesses are in use.",
+ "EventCode": "0x03",
+ "Counter": "0,1,2,3",
+ "UMask": "0x8",
+ "PEBScounters": "0,1,2,3",
+ "EventName": "LD_BLOCKS.NO_SR",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "The number of times that split load operations are temporarily blocked because all resources for handling the split accesses are in use."
+ },
+ {
+ "CollectPEBSRecord": "2",
+ "PublicDescription": "Counts the number of times a load got blocked due to false dependencies in MOB due to partial compare on address.",
+ "EventCode": "0x07",
+ "Counter": "0,1,2,3",
+ "UMask": "0x1",
+ "PEBScounters": "0,1,2,3",
+ "EventName": "LD_BLOCKS_PARTIAL.ADDRESS_ALIAS",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "False dependencies in MOB due to partial compare on address."
+ },
+ {
+ "CollectPEBSRecord": "2",
+ "PublicDescription": "Counts core cycles when the Resource allocator was stalled due to recovery from an earlier branch misprediction or machine clear event.",
+ "EventCode": "0x0D",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "UMask": "0x1",
+ "PEBScounters": "0,1,2,3,4,5,6,7",
+ "EventName": "INT_MISC.RECOVERY_CYCLES",
+ "SampleAfterValue": "2000003",
+ "BriefDescription": "Core cycles the allocator was stalled due to recovery from earlier clear event for this thread"
+ },
+ {
+ "CollectPEBSRecord": "2",
+ "PublicDescription": "Counts cycles the Backend cluster is recovering after a miss-speculation or a Store Buffer or Load Buffer drain stall.",
+ "EventCode": "0x0D",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "UMask": "0x3",
+ "PEBScounters": "0,1,2,3,4,5,6,7",
+ "EventName": "INT_MISC.ALL_RECOVERY_CYCLES",
+ "SampleAfterValue": "2000003",
+ "BriefDescription": "Cycles the Backend cluster is recovering after a miss-speculation or a Store Buffer or Load Buffer drain stall.",
+ "CounterMask": "1"
+ },
+ {
+ "CollectPEBSRecord": "2",
+ "PublicDescription": "Cycles after recovery from a branch misprediction or machine clear till the first uop is issued from the resteered path.",
+ "EventCode": "0x0d",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "UMask": "0x80",
+ "PEBScounters": "0,1,2,3,4,5,6,7",
+ "EventName": "INT_MISC.CLEAR_RESTEER_CYCLES",
+ "SampleAfterValue": "2000003",
+ "BriefDescription": "Counts cycles after recovery from a branch misprediction or machine clear till the first uop is issued from the resteered path."
+ },
+ {
+ "CollectPEBSRecord": "2",
+ "PublicDescription": "Counts the number of uops that the Resource Allocation Table (RAT) issues to the Reservation Station (RS).",
+ "EventCode": "0x0E",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "UMask": "0x1",
+ "PEBScounters": "0,1,2,3,4,5,6,7",
+ "EventName": "UOPS_ISSUED.ANY",
+ "SampleAfterValue": "2000003",
+ "BriefDescription": "Uops that RAT issues to RS"
+ },
+ {
+ "CollectPEBSRecord": "2",
+ "PublicDescription": "Counts cycles during which the Resource Allocation Table (RAT) does not issue any Uops to the reservation station (RS) for the current thread.",
+ "EventCode": "0x0E",
+ "Invert": "1",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "UMask": "0x1",
+ "PEBScounters": "0,1,2,3,4,5,6,7",
+ "EventName": "UOPS_ISSUED.STALL_CYCLES",
+ "SampleAfterValue": "2000003",
+ "BriefDescription": "Cycles when RAT does not issue Uops to RS for the thread",
+ "CounterMask": "1"
+ },
+ {
+ "CollectPEBSRecord": "2",
+ "PublicDescription": "Counts cycles when divide unit is busy executing divide or square root operations. Accounts for integer and floating-point operations.",
+ "EventCode": "0x14",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "UMask": "0x9",
+ "PEBScounters": "0,1,2,3,4,5,6,7",
+ "EventName": "ARITH.DIVIDER_ACTIVE",
+ "SampleAfterValue": "2000003",
+ "BriefDescription": "Cycles when divide unit is busy executing divide or square root operations.",
+ "CounterMask": "1"
+ },
+ {
+ "CollectPEBSRecord": "2",
+ "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.",
+ "EventCode": "0x3C",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "PEBScounters": "0,1,2,3,4,5,6,7",
+ "EventName": "CPU_CLK_UNHALTED.THREAD_P",
+ "SampleAfterValue": "2000003",
+ "BriefDescription": "Thread cycles when thread is not in halt state"
+ },
+ {
+ "CollectPEBSRecord": "2",
+ "PublicDescription": "Counts core crystal clock cycles when the thread is unhalted.",
+ "EventCode": "0x3C",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "UMask": "0x1",
+ "PEBScounters": "0,1,2,3,4,5,6,7",
+ "EventName": "CPU_CLK_UNHALTED.REF_XCLK",
+ "SampleAfterValue": "25003",
+ "BriefDescription": "Core crystal clock cycles when the thread is unhalted."
+ },
+ {
+ "CollectPEBSRecord": "2",
+ "PublicDescription": "Counts Core crystal clock cycles when current thread is unhalted and the other thread is halted.",
+ "EventCode": "0x3C",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "UMask": "0x2",
+ "PEBScounters": "0,1,2,3,4,5,6,7",
+ "EventName": "CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE",
+ "SampleAfterValue": "25003",
+ "BriefDescription": "Core crystal clock cycles when this thread is unhalted and the other thread is halted."
+ },
+ {
+ "CollectPEBSRecord": "2",
+ "PublicDescription": "Counts all not software-prefetch load dispatches that hit the fill buffer (FB) allocated for the software prefetch. It can also be incremented by some lock instructions. So it should only be used with profiling so that the locks can be excluded by ASM (Assembly File) inspection of the nearby instructions.",
+ "EventCode": "0x4c",
+ "Counter": "0,1,2,3",
+ "UMask": "0x1",
+ "PEBScounters": "0,1,2,3",
+ "EventName": "LOAD_HIT_PREFETCH.SWPF",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "Counts the number of demand load dispatches that hit L1D fill buffer (FB) allocated for software prefetch."
+ },
+ {
+ "CollectPEBSRecord": "2",
+ "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 stravation periods (e.g. branch mispredictions or i-cache misses)",
+ "EventCode": "0x5E",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "UMask": "0x1",
+ "PEBScounters": "0,1,2,3,4,5,6,7",
+ "EventName": "RS_EVENTS.EMPTY_CYCLES",
+ "SampleAfterValue": "2000003",
+ "BriefDescription": "Cycles when Reservation Station (RS) is empty for the thread"
+ },
+ {
+ "CollectPEBSRecord": "2",
+ "PublicDescription": "Counts end of periods where the Reservation Station (RS) was empty. Could be useful to closely sample on front-end latency issues (see the FRONTEND_RETIRED event of designated precise events)",
+ "EventCode": "0x5E",
+ "Invert": "1",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "UMask": "0x1",
+ "PEBScounters": "0,1,2,3,4,5,6,7",
+ "EventName": "RS_EVENTS.EMPTY_END",
+ "SampleAfterValue": "2000003",
+ "BriefDescription": "Counts end of periods where the Reservation Station (RS) was empty.",
+ "CounterMask": "1",
+ "EdgeDetect": "1"
+ },
+ {
+ "CollectPEBSRecord": "2",
+ "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.",
+ "EventCode": "0x87",
+ "Counter": "0,1,2,3",
+ "UMask": "0x1",
+ "PEBScounters": "0,1,2,3",
+ "EventName": "ILD_STALL.LCP",
+ "SampleAfterValue": "2000003",
+ "BriefDescription": "Stalls caused by changing prefix length of the instruction."
+ },
+ {
+ "CollectPEBSRecord": "2",
+ "PublicDescription": "Counts, on the per-thread basis, cycles during which at least one uop is dispatched from the Reservation Station (RS) to port 0.",
+ "EventCode": "0xa1",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "UMask": "0x1",
+ "PEBScounters": "0,1,2,3,4,5,6,7",
+ "EventName": "UOPS_DISPATCHED.PORT_0",
+ "SampleAfterValue": "2000003",
+ "BriefDescription": "Number of uops executed on port 0"
+ },
+ {
+ "CollectPEBSRecord": "2",
+ "PublicDescription": "Counts, on the per-thread basis, cycles during which at least one uop is dispatched from the Reservation Station (RS) to port 1.",
+ "EventCode": "0xa1",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "UMask": "0x2",
+ "PEBScounters": "0,1,2,3,4,5,6,7",
+ "EventName": "UOPS_DISPATCHED.PORT_1",
+ "SampleAfterValue": "2000003",
+ "BriefDescription": "Number of uops executed on port 1"
+ },
+ {
+ "CollectPEBSRecord": "2",
+ "PublicDescription": "Counts, on the per-thread basis, cycles during which at least one uop is dispatched from the Reservation Station (RS) to ports 2 and 3.",
+ "EventCode": "0xa1",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "UMask": "0x4",
+ "PEBScounters": "0,1,2,3,4,5,6,7",
+ "EventName": "UOPS_DISPATCHED.PORT_2_3",
+ "SampleAfterValue": "2000003",
+ "BriefDescription": "Number of uops executed on port 2 and 3"
+ },
+ {
+ "CollectPEBSRecord": "2",
+ "PublicDescription": "Counts, on the per-thread basis, cycles during which at least one uop is dispatched from the Reservation Station (RS) to ports 5 and 9.",
+ "EventCode": "0xa1",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "UMask": "0x10",
+ "PEBScounters": "0,1,2,3,4,5,6,7",
+ "EventName": "UOPS_DISPATCHED.PORT_4_9",
+ "SampleAfterValue": "2000003",
+ "BriefDescription": "Number of uops executed on port 4 and 9"
+ },
+ {
+ "CollectPEBSRecord": "2",
+ "PublicDescription": "Counts, on the per-thread basis, cycles during which at least one uop is dispatched from the Reservation Station (RS) to port 5.",
+ "EventCode": "0xa1",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "UMask": "0x20",
+ "PEBScounters": "0,1,2,3,4,5,6,7",
+ "EventName": "UOPS_DISPATCHED.PORT_5",
+ "SampleAfterValue": "2000003",
+ "BriefDescription": "Number of uops executed on port 5"
+ },
+ {
+ "CollectPEBSRecord": "2",
+ "PublicDescription": "Counts, on the per-thread basis, cycles during which at least one uop is dispatched from the Reservation Station (RS) to port 6.",
+ "EventCode": "0xa1",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "UMask": "0x40",
+ "PEBScounters": "0,1,2,3,4,5,6,7",
+ "EventName": "UOPS_DISPATCHED.PORT_6",
+ "SampleAfterValue": "2000003",
+ "BriefDescription": "Number of uops executed on port 6"
+ },
+ {
+ "CollectPEBSRecord": "2",
+ "PublicDescription": "Counts, on the per-thread basis, cycles during which at least one uop is dispatched from the Reservation Station (RS) to ports 7 and 8.",
+ "EventCode": "0xa1",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "UMask": "0x80",
+ "PEBScounters": "0,1,2,3,4,5,6,7",
+ "EventName": "UOPS_DISPATCHED.PORT_7_8",
+ "SampleAfterValue": "2000003",
+ "BriefDescription": "Number of uops executed on port 7 and 8"
+ },
+ {
+ "CollectPEBSRecord": "2",
+ "EventCode": "0xa2",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "UMask": "0x2",
+ "PEBScounters": "0,1,2,3,4,5,6,7",
+ "EventName": "RESOURCE_STALLS.SCOREBOARD",
+ "SampleAfterValue": "2000003",
+ "BriefDescription": "Counts cycles where the pipeline is stalled due to serializing operations."
+ },
+ {
+ "CollectPEBSRecord": "2",
+ "PublicDescription": "Counts allocation stall cycles caused by the store buffer (SB) being full. This counts cycles that the pipeline back-end blocked uop delivery from the front-end.",
+ "EventCode": "0xA2",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "UMask": "0x8",
+ "PEBScounters": "0,1,2,3,4,5,6,7",
+ "EventName": "RESOURCE_STALLS.SB",
+ "SampleAfterValue": "2000003",
+ "BriefDescription": "Cycles stalled due to no store buffers available. (not including draining form sync)."
+ },
+ {
+ "CollectPEBSRecord": "2",
+ "EventCode": "0xA3",
+ "Counter": "0,1,2,3",
+ "UMask": "0x1",
+ "PEBScounters": "0,1,2,3",
+ "EventName": "CYCLE_ACTIVITY.CYCLES_L2_MISS",
+ "SampleAfterValue": "2000003",
+ "BriefDescription": "Cycles while L2 cache miss demand load is outstanding.",
+ "CounterMask": "1"
+ },
+ {
+ "CollectPEBSRecord": "2",
+ "EventCode": "0xA3",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "UMask": "0x4",
+ "PEBScounters": "0,1,2,3,4,5,6,7",
+ "EventName": "CYCLE_ACTIVITY.STALLS_TOTAL",
+ "SampleAfterValue": "2000003",
+ "BriefDescription": "Total execution stalls.",
+ "CounterMask": "4"
+ },
+ {
+ "CollectPEBSRecord": "2",
+ "EventCode": "0xA3",
+ "Counter": "0,1,2,3",
+ "UMask": "0x5",
+ "PEBScounters": "0,1,2,3",
+ "EventName": "CYCLE_ACTIVITY.STALLS_L2_MISS",
+ "SampleAfterValue": "2000003",
+ "BriefDescription": "Execution stalls while L2 cache miss demand load is outstanding.",
+ "CounterMask": "5"
+ },
+ {
+ "CollectPEBSRecord": "2",
+ "EventCode": "0xA3",
+ "Counter": "0,1,2,3",
+ "UMask": "0x8",
+ "PEBScounters": "0,1,2,3",
+ "EventName": "CYCLE_ACTIVITY.CYCLES_L1D_MISS",
+ "SampleAfterValue": "2000003",
+ "BriefDescription": "Cycles while L1 cache miss demand load is outstanding.",
+ "CounterMask": "8"
+ },
+ {
+ "CollectPEBSRecord": "2",
+ "EventCode": "0xA3",
+ "Counter": "0,1,2,3",
+ "UMask": "0xc",
+ "PEBScounters": "0,1,2,3",
+ "EventName": "CYCLE_ACTIVITY.STALLS_L1D_MISS",
+ "SampleAfterValue": "2000003",
+ "BriefDescription": "Execution stalls while L1 cache miss demand load is outstanding.",
+ "CounterMask": "12"
+ },
+ {
+ "CollectPEBSRecord": "2",
+ "EventCode": "0xA3",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "UMask": "0x10",
+ "PEBScounters": "0,1,2,3,4,5,6,7",
+ "EventName": "CYCLE_ACTIVITY.CYCLES_MEM_ANY",
+ "SampleAfterValue": "2000003",
+ "BriefDescription": "Cycles while memory subsystem has an outstanding load.",
+ "CounterMask": "16"
+ },
+ {
+ "CollectPEBSRecord": "2",
+ "EventCode": "0xA3",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "UMask": "0x14",
+ "PEBScounters": "0,1,2,3,4,5,6,7",
+ "EventName": "CYCLE_ACTIVITY.STALLS_MEM_ANY",
+ "SampleAfterValue": "2000003",
+ "BriefDescription": "Execution stalls while memory subsystem has an outstanding load.",
+ "CounterMask": "20"
+ },
+ {
+ "CollectPEBSRecord": "2",
+ "PublicDescription": "Counts cycles during which a total of 1 uop was executed on all ports and Reservation Station (RS) was not empty.",
+ "EventCode": "0xa6",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "UMask": "0x2",
+ "PEBScounters": "0,1,2,3,4,5,6,7",
+ "EventName": "EXE_ACTIVITY.1_PORTS_UTIL",
+ "SampleAfterValue": "2000003",
+ "BriefDescription": "Cycles total of 1 uop is executed on all ports and Reservation Station was not empty."
+ },
+ {
+ "CollectPEBSRecord": "2",
+ "PublicDescription": "Counts cycles during which a total of 2 uops were executed on all ports and Reservation Station (RS) was not empty.",
+ "EventCode": "0xa6",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "UMask": "0x4",
+ "PEBScounters": "0,1,2,3,4,5,6,7",
+ "EventName": "EXE_ACTIVITY.2_PORTS_UTIL",
+ "SampleAfterValue": "2000003",
+ "BriefDescription": "Cycles total of 2 uops are executed on all ports and Reservation Station was not empty."
+ },
+ {
+ "CollectPEBSRecord": "2",
+ "PublicDescription": "Counts cycles where the Store Buffer was full and no loads caused an execution stall.",
+ "EventCode": "0xA6",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "UMask": "0x40",
+ "PEBScounters": "0,1,2,3,4,5,6,7",
+ "EventName": "EXE_ACTIVITY.BOUND_ON_STORES",
+ "SampleAfterValue": "2000003",
+ "BriefDescription": "Cycles where the Store Buffer was full and no loads caused an execution stall.",
+ "CounterMask": "2"
+ },
+ {
+ "CollectPEBSRecord": "2",
+ "PublicDescription": "Counts cycles during which no uops were executed on all ports and Reservation Station (RS) was not empty.",
+ "EventCode": "0xa6",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "UMask": "0x80",
+ "PEBScounters": "0,1,2,3,4,5,6,7",
+ "EventName": "EXE_ACTIVITY.EXE_BOUND_0_PORTS",
+ "SampleAfterValue": "2000003",
+ "BriefDescription": "Cycles where no uops were executed, the Reservation Station was not empty, the Store Buffer was full and there was no outstanding load."
+ },
+ {
+ "CollectPEBSRecord": "2",
+ "PublicDescription": "Counts the number of uops delivered to the back-end by the LSD(Loop Stream Detector).",
+ "EventCode": "0xA8",
+ "Counter": "0,1,2,3",
+ "UMask": "0x1",
+ "PEBScounters": "0,1,2,3",
+ "EventName": "LSD.UOPS",
+ "SampleAfterValue": "2000003",
+ "BriefDescription": "Number of Uops delivered by the LSD."
+ },
+ {
+ "CollectPEBSRecord": "2",
+ "PublicDescription": "Counts the cycles when at least one uop is delivered by the LSD (Loop-stream detector).",
+ "EventCode": "0xA8",
+ "Counter": "0,1,2,3",
+ "UMask": "0x1",
+ "PEBScounters": "0,1,2,3",
+ "EventName": "LSD.CYCLES_ACTIVE",
+ "SampleAfterValue": "2000003",
+ "BriefDescription": "Cycles Uops delivered by the LSD, but didn't come from the decoder.",
+ "CounterMask": "1"
+ },
+ {
+ "CollectPEBSRecord": "2",
+ "PublicDescription": "Counts the cycles when optimal number of uops is delivered by the LSD (Loop-stream detector).",
+ "EventCode": "0xa8",
+ "Counter": "0,1,2,3",
+ "UMask": "0x1",
+ "PEBScounters": "0,1,2,3",
+ "EventName": "LSD.CYCLES_OK",
+ "SampleAfterValue": "2000003",
+ "BriefDescription": "Cycles optimal number of Uops delivered by the LSD, but did not come from the decoder.",
+ "CounterMask": "5"
+ },
+ {
+ "CollectPEBSRecord": "2",
+ "EventCode": "0xB1",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "UMask": "0x1",
+ "PEBScounters": "0,1,2,3,4,5,6,7",
+ "EventName": "UOPS_EXECUTED.THREAD",
+ "SampleAfterValue": "2000003",
+ "BriefDescription": "Counts the number of uops to be executed per-thread each cycle."
+ },
+ {
+ "CollectPEBSRecord": "2",
+ "PublicDescription": "Counts cycles during which no uops were dispatched from the Reservation Station (RS) per thread.",
+ "EventCode": "0xB1",
+ "Invert": "1",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "UMask": "0x1",
+ "PEBScounters": "0,1,2,3,4,5,6,7",
+ "EventName": "UOPS_EXECUTED.STALL_CYCLES",
+ "SampleAfterValue": "2000003",
+ "BriefDescription": "Counts number of cycles no uops were dispatched to be executed on this thread.",
+ "CounterMask": "1"
+ },
+ {
+ "CollectPEBSRecord": "2",
+ "PublicDescription": "Cycles where at least 1 uop was executed per-thread.",
+ "EventCode": "0xb1",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "UMask": "0x1",
+ "PEBScounters": "0,1,2,3,4,5,6,7",
+ "EventName": "UOPS_EXECUTED.CYCLES_GE_1",
+ "SampleAfterValue": "2000003",
+ "BriefDescription": "Cycles where at least 1 uop was executed per-thread",
+ "CounterMask": "1"
+ },
+ {
+ "CollectPEBSRecord": "2",
+ "PublicDescription": "Cycles where at least 2 uops were executed per-thread.",
+ "EventCode": "0xb1",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "UMask": "0x1",
+ "PEBScounters": "0,1,2,3,4,5,6,7",
+ "EventName": "UOPS_EXECUTED.CYCLES_GE_2",
+ "SampleAfterValue": "2000003",
+ "BriefDescription": "Cycles where at least 2 uops were executed per-thread",
+ "CounterMask": "2"
+ },
+ {
+ "CollectPEBSRecord": "2",
+ "PublicDescription": "Cycles where at least 3 uops were executed per-thread.",
+ "EventCode": "0xb1",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "UMask": "0x1",
+ "PEBScounters": "0,1,2,3,4,5,6,7",
+ "EventName": "UOPS_EXECUTED.CYCLES_GE_3",
+ "SampleAfterValue": "2000003",
+ "BriefDescription": "Cycles where at least 3 uops were executed per-thread",
+ "CounterMask": "3"
+ },
+ {
+ "CollectPEBSRecord": "2",
+ "PublicDescription": "Cycles where at least 4 uops were executed per-thread.",
+ "EventCode": "0xb1",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "UMask": "0x1",
+ "PEBScounters": "0,1,2,3,4,5,6,7",
+ "EventName": "UOPS_EXECUTED.CYCLES_GE_4",
+ "SampleAfterValue": "2000003",
+ "BriefDescription": "Cycles where at least 4 uops were executed per-thread",
+ "CounterMask": "4"
+ },
+ {
+ "CollectPEBSRecord": "2",
+ "PublicDescription": "Counts the number of uops executed from any thread.",
+ "EventCode": "0xB1",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "UMask": "0x2",
+ "PEBScounters": "0,1,2,3,4,5,6,7",
+ "EventName": "UOPS_EXECUTED.CORE",
+ "SampleAfterValue": "2000003",
+ "BriefDescription": "Number of uops executed on the core."
+ },
+ {
+ "CollectPEBSRecord": "2",
+ "PublicDescription": "Counts cycles when at least 1 micro-op is executed from any thread on physical core.",
+ "EventCode": "0xB1",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "UMask": "0x2",
+ "PEBScounters": "0,1,2,3,4,5,6,7",
+ "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_1",
+ "SampleAfterValue": "2000003",
+ "BriefDescription": "Cycles at least 1 micro-op is executed from any thread on physical core.",
+ "CounterMask": "1"
+ },
+ {
+ "CollectPEBSRecord": "2",
+ "PublicDescription": "Counts cycles when at least 2 micro-ops are executed from any thread on physical core.",
+ "EventCode": "0xB1",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "UMask": "0x2",
+ "PEBScounters": "0,1,2,3,4,5,6,7",
+ "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_2",
+ "SampleAfterValue": "2000003",
+ "BriefDescription": "Cycles at least 2 micro-op is executed from any thread on physical core.",
+ "CounterMask": "2"
+ },
+ {
+ "CollectPEBSRecord": "2",
+ "PublicDescription": "Counts cycles when at least 3 micro-ops are executed from any thread on physical core.",
+ "EventCode": "0xB1",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "UMask": "0x2",
+ "PEBScounters": "0,1,2,3,4,5,6,7",
+ "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_3",
+ "SampleAfterValue": "2000003",
+ "BriefDescription": "Cycles at least 3 micro-op is executed from any thread on physical core.",
+ "CounterMask": "3"
+ },
+ {
+ "CollectPEBSRecord": "2",
+ "PublicDescription": "Counts cycles when at least 4 micro-ops are executed from any thread on physical core.",
+ "EventCode": "0xB1",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "UMask": "0x2",
+ "PEBScounters": "0,1,2,3,4,5,6,7",
+ "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_4",
+ "SampleAfterValue": "2000003",
+ "BriefDescription": "Cycles at least 4 micro-op is executed from any thread on physical core.",
+ "CounterMask": "4"
+ },
+ {
+ "CollectPEBSRecord": "2",
+ "PublicDescription": "Counts the number of x87 uops executed.",
+ "EventCode": "0xB1",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "UMask": "0x10",
+ "PEBScounters": "0,1,2,3,4,5,6,7",
+ "EventName": "UOPS_EXECUTED.X87",
+ "SampleAfterValue": "2000003",
+ "BriefDescription": "Counts the number of x87 uops dispatched."
+ },
+ {
+ "CollectPEBSRecord": "2",
+ "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.",
+ "EventCode": "0xC0",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "PEBScounters": "0,1,2,3,4,5,6,7",
+ "EventName": "INST_RETIRED.ANY_P",
+ "SampleAfterValue": "2000003",
+ "BriefDescription": "Number of instructions retired. General Counter - architectural event"
+ },
+ {
+ "CollectPEBSRecord": "2",
+ "PublicDescription": "Counts the number of cycles using always true condition (uops_ret &lt; 16) applied to non PEBS uops retired event.",
+ "EventCode": "0xC2",
+ "Invert": "1",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "UMask": "0x2",
+ "PEBScounters": "0,1,2,3,4,5,6,7",
+ "EventName": "UOPS_RETIRED.TOTAL_CYCLES",
+ "SampleAfterValue": "2000003",
+ "BriefDescription": "Cycles with less than 10 actually retired uops.",
+ "CounterMask": "10"
+ },
+ {
+ "CollectPEBSRecord": "2",
+ "PublicDescription": "Counts the retirement slots used each cycle.",
+ "EventCode": "0xc2",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "UMask": "0x2",
+ "PEBScounters": "0,1,2,3,4,5,6,7",
+ "EventName": "UOPS_RETIRED.SLOTS",
+ "SampleAfterValue": "2000003",
+ "BriefDescription": "Retirement slots used."
+ },
+ {
+ "CollectPEBSRecord": "2",
+ "PublicDescription": "Counts the number of machine clears (nukes) of any type.",
+ "EventCode": "0xC3",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "UMask": "0x1",
+ "PEBScounters": "0,1,2,3,4,5,6,7",
+ "EventName": "MACHINE_CLEARS.COUNT",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "Number of machine clears (nukes) of any type.",
+ "CounterMask": "1",
+ "EdgeDetect": "1"
+ },
+ {
+ "CollectPEBSRecord": "2",
+ "PublicDescription": "Counts self-modifying code (SMC) detected, which causes a machine clear.",
+ "EventCode": "0xC3",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "UMask": "0x4",
+ "PEBScounters": "0,1,2,3,4,5,6,7",
+ "EventName": "MACHINE_CLEARS.SMC",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "Self-modifying code (SMC) detected."
+ },
+ {
+ "PEBS": "1",
+ "CollectPEBSRecord": "2",
+ "PublicDescription": "Counts all branch instructions retired.",
+ "EventCode": "0xC4",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "PEBScounters": "0,1,2,3,4,5,6,7",
+ "EventName": "BR_INST_RETIRED.ALL_BRANCHES",
+ "SampleAfterValue": "400009",
+ "BriefDescription": "All branch instructions retired."
+ },
+ {
+ "PEBS": "1",
+ "CollectPEBSRecord": "2",
+ "PublicDescription": "Counts taken conditional branch instructions retired.",
+ "EventCode": "0xc4",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "UMask": "0x1",
+ "PEBScounters": "0,1,2,3,4,5,6,7",
+ "EventName": "BR_INST_RETIRED.COND_TAKEN",
+ "SampleAfterValue": "400009",
+ "BriefDescription": "Taken conditional branch instructions retired."
+ },
+ {
+ "PEBS": "1",
+ "CollectPEBSRecord": "2",
+ "PublicDescription": "Counts both direct and indirect near call instructions retired.",
+ "EventCode": "0xC4",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "UMask": "0x2",
+ "PEBScounters": "0,1,2,3,4,5,6,7",
+ "EventName": "BR_INST_RETIRED.NEAR_CALL",
+ "SampleAfterValue": "100007",
+ "BriefDescription": "Direct and indirect near call instructions retired."
+ },
+ {
+ "PEBS": "1",
+ "CollectPEBSRecord": "2",
+ "PublicDescription": "Counts return instructions retired.",
+ "EventCode": "0xC4",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "UMask": "0x8",
+ "PEBScounters": "0,1,2,3,4,5,6,7",
+ "EventName": "BR_INST_RETIRED.NEAR_RETURN",
+ "SampleAfterValue": "100007",
+ "BriefDescription": "Return instructions retired."
+ },
+ {
+ "PEBS": "1",
+ "CollectPEBSRecord": "2",
+ "PublicDescription": "Counts not taken branch instructions retired.",
+ "EventCode": "0xC4",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "UMask": "0x10",
+ "PEBScounters": "0,1,2,3,4,5,6,7",
+ "EventName": "BR_INST_RETIRED.COND_NTAKEN",
+ "SampleAfterValue": "400009",
+ "BriefDescription": "Not taken branch instructions retired."
+ },
+ {
+ "PEBS": "1",
+ "CollectPEBSRecord": "2",
+ "PublicDescription": "Counts conditional branch instructions retired.",
+ "EventCode": "0xc4",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "UMask": "0x11",
+ "PEBScounters": "0,1,2,3,4,5,6,7",
+ "EventName": "BR_INST_RETIRED.COND",
+ "SampleAfterValue": "400009",
+ "BriefDescription": "Conditional branch instructions retired."
+ },
+ {
+ "PEBS": "1",
+ "CollectPEBSRecord": "2",
+ "PublicDescription": "Counts taken branch instructions retired.",
+ "EventCode": "0xC4",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "UMask": "0x20",
+ "PEBScounters": "0,1,2,3,4,5,6,7",
+ "EventName": "BR_INST_RETIRED.NEAR_TAKEN",
+ "SampleAfterValue": "400009",
+ "BriefDescription": "Taken branch instructions retired."
+ },
+ {
+ "PEBS": "1",
+ "CollectPEBSRecord": "2",
+ "PublicDescription": "Counts far branch instructions retired.",
+ "EventCode": "0xC4",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "UMask": "0x40",
+ "PEBScounters": "0,1,2,3,4,5,6,7",
+ "EventName": "BR_INST_RETIRED.FAR_BRANCH",
+ "SampleAfterValue": "100007",
+ "BriefDescription": "Far branch instructions retired."
+ },
+ {
+ "PEBS": "1",
+ "CollectPEBSRecord": "2",
+ "PublicDescription": "Counts all indirect branch instructions retired (excluding RETs. TSX aborts is considered indirect branch).",
+ "EventCode": "0xc4",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "UMask": "0x80",
+ "PEBScounters": "0,1,2,3,4,5,6,7",
+ "EventName": "BR_INST_RETIRED.INDIRECT",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "All indirect branch instructions retired (excluding RETs. TSX aborts are considered indirect branch)."
+ },
+ {
+ "PEBS": "1",
+ "CollectPEBSRecord": "2",
+ "PublicDescription": "Counts all the retired branch instructions that were mispredicted by the processor. A branch misprediction occurs when the processor incorrectly predicts the destination of the branch. When the misprediction is discovered at execution, all the instructions executed in the wrong (speculative) path must be discarded, and the processor must start fetching from the correct path.",
+ "EventCode": "0xC5",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "PEBScounters": "0,1,2,3,4,5,6,7",
+ "EventName": "BR_MISP_RETIRED.ALL_BRANCHES",
+ "SampleAfterValue": "400009",
+ "BriefDescription": "All mispredicted branch instructions retired.",
+ "Data_LA": "1"
+ },
+ {
+ "PEBS": "1",
+ "CollectPEBSRecord": "2",
+ "PublicDescription": "Counts taken conditional mispredicted branch instructions retired.",
+ "EventCode": "0xc5",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "UMask": "0x1",
+ "PEBScounters": "0,1,2,3,4,5,6,7",
+ "EventName": "BR_MISP_RETIRED.COND_TAKEN",
+ "SampleAfterValue": "400009",
+ "BriefDescription": "number of branch instructions retired that were mispredicted and taken. Non PEBS",
+ "Data_LA": "1"
+ },
+ {
+ "PEBS": "1",
+ "CollectPEBSRecord": "2",
+ "PublicDescription": "Counts mispredicted conditional branch instructions retired.",
+ "EventCode": "0xc5",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "UMask": "0x11",
+ "PEBScounters": "0,1,2,3,4,5,6,7",
+ "EventName": "BR_MISP_RETIRED.COND",
+ "SampleAfterValue": "400009",
+ "BriefDescription": "Mispredicted conditional branch instructions retired.",
+ "Data_LA": "1"
+ },
+ {
+ "PEBS": "1",
+ "CollectPEBSRecord": "2",
+ "PublicDescription": "Counts number of near branch instructions retired that were mispredicted and taken.",
+ "EventCode": "0xC5",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "UMask": "0x20",
+ "PEBScounters": "0,1,2,3,4,5,6,7",
+ "EventName": "BR_MISP_RETIRED.NEAR_TAKEN",
+ "SampleAfterValue": "400009",
+ "BriefDescription": "Number of near branch instructions retired that were mispredicted and taken.",
+ "Data_LA": "1"
+ },
+ {
+ "PEBS": "1",
+ "CollectPEBSRecord": "2",
+ "PublicDescription": "Counts all miss-predicted indirect branch instructions retired (excluding RETs. TSX aborts is considered indirect branch).",
+ "EventCode": "0xC5",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "UMask": "0x80",
+ "PEBScounters": "0,1,2,3,4,5,6,7",
+ "EventName": "BR_MISP_RETIRED.INDIRECT",
+ "SampleAfterValue": "100003",
+ "BriefDescription": "All miss-predicted indirect branch instructions retired (excluding RETs. TSX aborts is considered indirect branch).",
+ "Data_LA": "1"
+ },
+ {
+ "CollectPEBSRecord": "2",
+ "PublicDescription": "Increments when an entry is added to the Last Branch Record (LBR) array (or removed from the array in case of RETURNs in call stack mode). The event requires LBR enable via IA32_DEBUGCTL MSR and branch type selection via MSR_LBR_SELECT.",
+ "EventCode": "0xcc",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "UMask": "0x20",
+ "PEBScounters": "0,1,2,3,4,5,6,7",
+ "EventName": "MISC_RETIRED.LBR_INSERTS",
+ "SampleAfterValue": "2000003",
+ "BriefDescription": "Increments whenever there is an update to the LBR array."
+ },
+ {
+ "PublicDescription": "Counts number of retired PAUSE instructions (that do not end up with a VMExit to the VMM; TSX aborted Instructions may be counted).",
+ "EventCode": "0xcc",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "UMask": "0x40",
+ "EventName": "MISC_RETIRED.PAUSE_INST",
+ "SampleAfterValue": "2000003",
+ "BriefDescription": "Number of retired PAUSE instructions."
+ },
+ {
+ "CollectPEBSRecord": "2",
+ "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.",
+ "EventCode": "0xE6",
+ "Counter": "0,1,2,3",
+ "UMask": "0x1",
+ "PEBScounters": "0,1,2,3",
+ "EventName": "BACLEARS.ANY",
+ "SampleAfterValue": "100003",
+ "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."
+ },
+ {
+ "CollectPEBSRecord": "2",
+ "PublicDescription": "This event distributes cycle counts between active hyperthreads, i.e., those in C0. A hyperthread becomes inactive when it executes the HLT or MWAIT instructions. If all other hyperthreads are inactive (or disabled or do not exist), all counts are attributed to this hyperthread. To obtain the full count when the Core is active, sum the counts from each hyperthread.",
+ "EventCode": "0xec",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "UMask": "0x2",
+ "PEBScounters": "0,1,2,3,4,5,6,7",
+ "EventName": "CPU_CLK_UNHALTED.DISTRIBUTED",
+ "SampleAfterValue": "2000003",
+ "BriefDescription": "Cycle counts are evenly distributed between active threads in the Core."+ }
+]
\ No newline at end of file
tools/perf/pmu-events/arch/x86/icelake/virtual-memory.json new file +236 -0
237 lines not on this page · raw message
tools/perf/pmu-events/arch/x86/mapfile.csv +1 -0
@@ -33,4 +33,5 @@ GenuineIntel-6-25,v2,westmereep-sp,core GenuineIntel-6-2F,v2,westmereex,core GenuineIntel-6-55-[01234],v1,skylakex,core GenuineIntel-6-55-[56789ABCDEF],v1,cascadelakex,core +GenuineIntel-6-7E,v1,icelake,core AuthenticAMD-23-[[:xdigit:]]+,v1,amdfam17h,core
Signature · 1 line
2.17.1
PATCH 3/3 perf vendor events intel: Add JSON files for Tremontx
In reply to [email protected]From: Kan Liang <[email protected]>
Add V1 event list. This is not a full event list yet, but a short list for now.
--- tools/perf/pmu-events/arch/x86/mapfile.csv | 1 + .../pmu-events/arch/x86/tremontx/cache.json | 52 +++++++++++ .../pmu-events/arch/x86/tremontx/memory.json | 26 ++++++ .../pmu-events/arch/x86/tremontx/other.json | 26 ++++++ .../arch/x86/tremontx/pipeline.json | 91 +++++++++++++++++++ .../arch/x86/tremontx/uncore-memory.json | 29 ++++++ .../arch/x86/tremontx/uncore-other.json | 40 ++++++++ .../arch/x86/tremontx/uncore-power.json | 9 ++ .../arch/x86/tremontx/virtual-memory.json | 86 ++++++++++++++++++ 9 files changed, 360 insertions(+) create mode 100644 tools/perf/pmu-events/arch/x86/tremontx/cache.json create mode 100644 tools/perf/pmu-events/arch/x86/tremontx/memory.json create mode 100644 tools/perf/pmu-events/arch/x86/tremontx/other.json create mode 100644 tools/perf/pmu-events/arch/x86/tremontx/pipeline.json create mode 100644 tools/perf/pmu-events/arch/x86/tremontx/uncore-memory.json create mode 100644 tools/perf/pmu-events/arch/x86/tremontx/uncore-other.json create mode 100644 tools/perf/pmu-events/arch/x86/tremontx/uncore-power.json create mode 100644 tools/perf/pmu-events/arch/x86/tremontx/virtual-memory.json
tools/perf/pmu-events/arch/x86/mapfile.csv +1 -0
@@ -34,4 +34,5 @@ GenuineIntel-6-2F,v2,westmereex,core GenuineIntel-6-55-[01234],v1,skylakex,core GenuineIntel-6-55-[56789ABCDEF],v1,cascadelakex,core GenuineIntel-6-7E,v1,icelake,core +GenuineIntel-6-86,v1,tremontx,core AuthenticAMD-23-[[:xdigit:]]+,v1,amdfam17h,core
tools/perf/pmu-events/arch/x86/tremontx/cache.json new file +52 -0
53 lines not on this page · raw message
tools/perf/pmu-events/arch/x86/tremontx/memory.json new file +26 -0
@@ -0,0 +1,26 @@ +[ + { + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "EventCode": "0XB7", + "MSRValue": "0x000000003F04000001", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OCR.DEMAND_DATA_RD.L3_MISS", + "MSRIndex": "0x1a6,0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts demand data reads that was not supplied by the L3 cache.", + "Offcore": "1" + }, + { + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "EventCode": "0XB7", + "MSRValue": "0x000000003F04000002", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OCR.DEMAND_RFO.L3_MISS", + "MSRIndex": "0x1a6,0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts all demand reads for ownership (RFO) requests and software based prefetches for exclusive ownership (PREFETCHW) that was not supplied by the L3 cache.", + "Offcore": "1" + } +]
tools/perf/pmu-events/arch/x86/tremontx/other.json new file +26 -0
@@ -0,0 +1,26 @@ +[ + { + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "EventCode": "0XB7", + "MSRValue": "0x000000000000010001", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OCR.DEMAND_DATA_RD.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts demand data reads that have any response type.", + "Offcore": "1" + }, + { + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "EventCode": "0XB7", + "MSRValue": "0x000000000000010002", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OCR.DEMAND_RFO.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts all demand reads for ownership (RFO) requests and software based prefetches for exclusive ownership (PREFETCHW) that have any response type.", + "Offcore": "1" + } +]
tools/perf/pmu-events/arch/x86/tremontx/pipeline.json new file +91 -0
92 lines not on this page · raw message
tools/perf/pmu-events/arch/x86/tremontx/uncore-memory.json new file +29 -0
@@ -0,0 +1,29 @@ +[ + { + "BriefDescription": "read requests to memory controller. Derived from unc_m_cas_count.rd", + "Counter": "0,1,2,3", + "EventCode": "0x04", + "EventName": "LLC_MISSES.MEM_READ", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x0f", + "Unit": "iMC" + }, + { + "BriefDescription": "write requests to memory controller. Derived from unc_m_cas_count.wr", + "Counter": "0,1,2,3", + "EventCode": "0x04", + "EventName": "LLC_MISSES.MEM_WRITE", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x30", + "Unit": "iMC" + }, + { + "BriefDescription": "Memory controller clock ticks", + "Counter": "0,1,2,3", + "EventName": "UNC_M_CLOCKTICKS", + "PerPkg": "1", + "Unit": "iMC" + } +]
tools/perf/pmu-events/arch/x86/tremontx/uncore-other.json new file +40 -0
@@ -0,0 +1,40 @@ +[ + { + "BriefDescription": "Clockticks of the uncore caching and home agent", + "Counter": "0,1,2,3", + "EventName": "UNC_CHA_CLOCKTICKS", + "PerPkg": "1", + "Unit": "CHA" + }, + { + "BriefDescription": "Clockticks of the integrated IO (IIO) traffic controller", + "Counter": "0,1,2,3", + "EventCode": "0x01", + "EventName": "UNC_IIO_CLOCKTICKS", + "PerPkg": "1", + "Unit": "IIO" + }, + { + "BriefDescription": "Clockticks of the IO coherency tracker (IRP)", + "Counter": "0,1", + "EventCode": "0x01", + "EventName": "UNC_I_CLOCKTICKS", + "PerPkg": "1", + "Unit": "IRP" + }, + { + "BriefDescription": "Clockticks of the mesh to memory (M2M)", + "Counter": "0,1,2,3", + "EventName": "UNC_M2M_CLOCKTICKS", + "PerPkg": "1", + "Unit": "M2M" + }, + { + "BriefDescription": "Clockticks of the mesh to PCI (M2P)", + "Counter": "0,1,2,3", + "EventCode": "0x01", + "EventName": "UNC_M2P_CLOCKTICKS", + "PerPkg": "1", + "Unit": "M2PCIe" + } +]
tools/perf/pmu-events/arch/x86/tremontx/uncore-power.json new file +9 -0
@@ -0,0 +1,9 @@ +[ + { + "BriefDescription": "Clockticks of the power control unit (PCU)", + "Counter": "0,1,2,3", + "EventName": "UNC_P_CLOCKTICKS", + "PerPkg": "1", + "Unit": "PCU" + } +]
tools/perf/pmu-events/arch/x86/tremontx/virtual-memory.json new file +86 -0
87 lines not on this page · raw message
Signature · 1 line
2.17.1
Hi Arnaldo and Jirka,
Have you got a chance to review this patch series?
This series is user space tool support for Icelake and Tremont.
Thanks,
Kan
Quoted 145 lines · On 4/16/2019 11:24 AM, [email protected] wrote:
From: Andi Kleen <[email protected]>
Icelake and later platforms support collecting XMM registers with PEBS event.
Add support for perf script to dump them, and support
for the register parser in perf record -I ... to configure them. For now they are just printed in hex, could potentially add other formats too.Signed-off-by Andi Kleen <[email protected]>Signed-off-by Kan Liang <[email protected]>--- tools/arch/x86/include/uapi/asm/perf_regs.h | 23 ++++++++++++++++++- tools/perf/arch/x86/include/perf_regs.h | 25 +++++++++++++++++++-- tools/perf/arch/x86/util/perf_regs.c | 16 +++++++++++++ tools/perf/util/perf_regs.h | 1 + 4 files changed, 62 insertions(+), 3 deletions(-)tools/arch/x86/include/uapi/asm/perf_regs.h +22
-1@@ -27,8 +27,29 @@ enum perf_event_x86_regs {PERF_REG_X86_R13 ,PERF_REG_X86_R14 ,PERF_REG_X86_R15 , - +/* These are the limits for the GPRs. */ PERF_REG_X86_32_MAX =PERF_REG_X86_GS +1 ,PERF_REG_X86_64_MAX =PERF_REG_X86_R15 +1 , + +/* These all need two bits set because they are 128bit */ +PERF_REG_X86_XMM0 =32 , +PERF_REG_X86_XMM1 =34 , +PERF_REG_X86_XMM2 =36 , +PERF_REG_X86_XMM3 =38 , +PERF_REG_X86_XMM4 =40 , +PERF_REG_X86_XMM5 =42 , +PERF_REG_X86_XMM6 =44 , +PERF_REG_X86_XMM7 =46 , +PERF_REG_X86_XMM8 =48 , +PERF_REG_X86_XMM9 =50 , +PERF_REG_X86_XMM10 =52 , +PERF_REG_X86_XMM11 =54 , +PERF_REG_X86_XMM12 =56 , +PERF_REG_X86_XMM13 =58 , +PERF_REG_X86_XMM14 =60 , +PERF_REG_X86_XMM15 =62 , + +/* These include both GPRs and XMMX registers */ + PERF_REG_X86_XMM_MAX = PERF_REG_X86_XMM15 + 2, };#endif /* _ASM_X86_PERF_REGS_H */ tools/perf/arch/x86/include/perf_regs.h +23
-2@@ -8,9 +8,9 @@void perf_regs_load (u64 *regs); +#define PERF_REGS_MAX PERF_REG_X86_XMM_MAX#ifndef HAVE_ARCH_X86_64_SUPPORT #define PERF_REGS_MASK ((1ULL << PERF_REG_X86_32_MAX) - 1) -#define PERF_REGS_MAX PERF_REG_X86_32_MAX#define PERF_SAMPLE_REGS_ABI PERF_SAMPLE_REGS_ABI_32#else #define REG_NOSUPPORT ((1ULL << PERF_REG_X86_DS) | \@@ -18,7 +18,6 @@ void perf_regs_load(u64 *regs); (1ULL << PERF_REG_X86_FS) | \ (1ULL << PERF_REG_X86_GS))#define PERF_REGS_MASK (((1ULL << PERF_REG_X86_64_MAX) - 1) & ~REG_NOSUPPORT) -#define PERF_REGS_MAX PERF_REG_X86_64_MAX#define PERF_SAMPLE_REGS_ABI PERF_SAMPLE_REGS_ABI_64#endif #define PERF_REG_IP PERF_REG_X86_IP@@ -77,6 +76,28 @@ static inline const char *perf_reg_name(int id)case PERF_REG_X86_R15 :return "R15" ;#endif /* HAVE_ARCH_X86_64_SUPPORT */ + +#define XMM (x) \ + case PERF_REG_X86_XMM ## x: \ + case PERF_REG_X86_XMM ## x + 1: \ + return "XMM" #x; + XMM(0) + XMM(1) + XMM(2) + XMM(3) + XMM(4) + XMM(5) + XMM(6) + XMM(7) + XMM(8) + XMM(9) + XMM(10) + XMM(11) + XMM(12) + XMM(13) + XMM(14) + XMM(15) +#undef XMMdefault :return NULL ; }tools/perf/arch/x86/util/perf_regs.c +16
-0@@ -31,6 +31,22 @@ const struct sample_reg sample_reg_masks[] = {SMPL_REG (R14 ,PERF_REG_X86_R14 ),SMPL_REG (R15 ,PERF_REG_X86_R15 ), #endif +SMPL_REG2 (XMM0 ,PERF_REG_X86_XMM0 ), +SMPL_REG2 (XMM1 ,PERF_REG_X86_XMM1 ), +SMPL_REG2 (XMM2 ,PERF_REG_X86_XMM2 ), +SMPL_REG2 (XMM3 ,PERF_REG_X86_XMM3 ), +SMPL_REG2 (XMM4 ,PERF_REG_X86_XMM4 ), +SMPL_REG2 (XMM5 ,PERF_REG_X86_XMM5 ), +SMPL_REG2 (XMM6 ,PERF_REG_X86_XMM6 ), +SMPL_REG2 (XMM7 ,PERF_REG_X86_XMM7 ), +SMPL_REG2 (XMM8 ,PERF_REG_X86_XMM8 ), +SMPL_REG2 (XMM9 ,PERF_REG_X86_XMM9 ), +SMPL_REG2 (XMM10 ,PERF_REG_X86_XMM10 ), +SMPL_REG2 (XMM11 ,PERF_REG_X86_XMM11 ), +SMPL_REG2 (XMM12 ,PERF_REG_X86_XMM12 ), +SMPL_REG2 (XMM13 ,PERF_REG_X86_XMM13 ), +SMPL_REG2 (XMM14 ,PERF_REG_X86_XMM14 ), +SMPL_REG2 (XMM15 ,PERF_REG_X86_XMM15 ),SMPL_REG_END };tools/perf/util/perf_regs.h +1
-0@@ -12,6 +12,7 @@ struct sample_reg {uint64_t mask; };#define SMPL_REG (n, b) { .name = #n, .mask = 1ULL << (b) } +#define SMPL_REG2 (n, b) { .name = #n, .mask = 3ULL << (b) }#define SMPL_REG_END { .name = NULL }extern const struct sample_reg sample_reg_masks[];