github-mirror/linux
1
0
Fork 0
mirror of https://github.com/torvalds/linux.git synced 2026-05-30 18:13:41 +02:00
Code Issues Actions Packages Projects Releases Wiki Activity Graph

perf vendor events intel: Update pantherlake events to v1.00

Browse Source 
Update pantherlake events to v1.00 released in:

  b149786b6f

Event JSON automatically generated by:

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

Signed-off-by: Ian Rogers <irogers@google.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andreas Färber <afaerber@suse.de>
Cc: Caleb Biggers <caleb.biggers@intel.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Manivannan Sadhasivam <mani@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Perry Taylor <perry.taylor@intel.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Falcon <thomas.falcon@intel.com>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
This commit is contained in:
Ian Rogers 2025-09-25 10:27:34 -07:00 committed by Arnaldo Carvalho de Melo
parent 53366556aa
commit dd171167f2
9 changed files with 3932 additions and 47 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1125
tools/perf/pmu-events/arch/x86/pantherlake/cache.json
View File

File diff suppressed because it is too large Load Diff

9
tools/perf/pmu-events/arch/x86/pantherlake/counter.json
View File

@ -1,12 +1,17 @@
[
{
"Unit": "cpu_atom",
"CountersNumFixed": "3",
"CountersNumGeneric": "39"
"CountersNumFixed": "7",
"CountersNumGeneric": "8"
},
{
"Unit": "cpu_core",
"CountersNumFixed": "4",
"CountersNumGeneric": "10"
},
{
"Unit": "iMC",
"CountersNumFixed": "0",
"CountersNumGeneric": "5"
}
]

286
tools/perf/pmu-events/arch/x86/pantherlake/floating-point.json Normal file
View File

@ -0,0 +1,286 @@
[
{
"BriefDescription": "Cycles when floating-point divide unit is busy executing divide or square root operations.",
"Counter": "0,1,2,3,4,5,6,7,8,9",
"CounterMask": "1",
"EventCode": "0xb0",
"EventName": "ARITH.FPDIV_ACTIVE",
"PublicDescription": "Counts cycles when divide unit is busy executing divide or square root operations. Accounts for floating-point operations only.",
"SampleAfterValue": "1000003",
"UMask": "0x1",
"Unit": "cpu_core"
},
{
"BriefDescription": "Counts all microcode FP assists.",
"Counter": "0,1,2,3,4,5,6,7,8,9",
"EventCode": "0xc1",
"EventName": "ASSISTS.FP",
"PublicDescription": "Counts all microcode Floating Point assists.",
"SampleAfterValue": "100003",
"UMask": "0x2",
"Unit": "cpu_core"
},
{
"BriefDescription": "ASSISTS.SSE_AVX_MIX",
"Counter": "0,1,2,3,4,5,6,7,8,9",
"EventCode": "0xc1",
"EventName": "ASSISTS.SSE_AVX_MIX",
"SampleAfterValue": "1000003",
"UMask": "0x10",
"Unit": "cpu_core"
},
{
"BriefDescription": "Number of FP-arith-uops dispatched on 1st VEC port (port 0). FP-arith-uops are of type ADD* / SUB* / MUL / FMA* / DPP.",
"Counter": "0,1,2,3,4,5,6,7,8,9",
"EventCode": "0xb3",
"EventName": "FP_ARITH_DISPATCHED.V0",
"SampleAfterValue": "2000003",
"UMask": "0x1",
"Unit": "cpu_core"
},
{
"BriefDescription": "Number of FP-arith-uops dispatched on 2nd VEC port (port 1)",
"Counter": "0,1,2,3,4,5,6,7,8,9",
"EventCode": "0xb3",
"EventName": "FP_ARITH_DISPATCHED.V1",
"SampleAfterValue": "2000003",
"UMask": "0x2",
"Unit": "cpu_core"
},
{
"BriefDescription": "Number of FP-arith-uops dispatched on 3rd VEC port (port 5)",
"Counter": "0,1,2,3,4,5,6,7,8,9",
"EventCode": "0xb3",
"EventName": "FP_ARITH_DISPATCHED.V2",
"SampleAfterValue": "2000003",
"UMask": "0x4",
"Unit": "cpu_core"
},
{
"BriefDescription": "Number of FP-arith-uops dispatched on 4th VEC port",
"Counter": "0,1,2,3,4,5,6,7,8,9",
"EventCode": "0xb3",
"EventName": "FP_ARITH_DISPATCHED.V3",
"SampleAfterValue": "2000003",
"UMask": "0x8",
"Unit": "cpu_core"
},
{
"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": "0,1,2,3,4,5,6,7,8,9",
"EventCode": "0xc7",
"EventName": "FP_ARITH_OPS_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.",
"SampleAfterValue": "100003",
"UMask": "0x4",
"Unit": "cpu_core"
},
{
"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": "0,1,2,3,4,5,6,7,8,9",
"EventCode": "0xc7",
"EventName": "FP_ARITH_OPS_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.",
"SampleAfterValue": "100003",
"UMask": "0x8",
"Unit": "cpu_core"
},
{
"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": "0,1,2,3,4,5,6,7,8,9",
"EventCode": "0xc7",
"EventName": "FP_ARITH_OPS_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.",
"SampleAfterValue": "100003",
"UMask": "0x10",
"Unit": "cpu_core"
},
{
"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": "0,1,2,3,4,5,6,7,8,9",
"EventCode": "0xc7",
"EventName": "FP_ARITH_OPS_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.",
"SampleAfterValue": "100003",
"UMask": "0x20",
"Unit": "cpu_core"
},
{
"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": "0,1,2,3,4,5,6,7,8,9",
"EventCode": "0xc7",
"EventName": "FP_ARITH_OPS_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.",
"SampleAfterValue": "100003",
"UMask": "0x18",
"Unit": "cpu_core"
},
{
"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 RANGE SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.",
"Counter": "0,1,2,3,4,5,6,7,8,9",
"EventCode": "0xc7",
"EventName": "FP_ARITH_OPS_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.",
"SampleAfterValue": "1000003",
"UMask": "0x3",
"Unit": "cpu_core"
},
{
"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": "0,1,2,3,4,5,6,7,8,9",
"EventCode": "0xc7",
"EventName": "FP_ARITH_OPS_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.",
"SampleAfterValue": "100003",
"UMask": "0x1",
"Unit": "cpu_core"
},
{
"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": "0,1,2,3,4,5,6,7,8,9",
"EventCode": "0xc7",
"EventName": "FP_ARITH_OPS_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.",
"SampleAfterValue": "100003",
"UMask": "0x2",
"Unit": "cpu_core"
},
{
"BriefDescription": "Number of any Vector retired FP arithmetic instructions",
"Counter": "0,1,2,3,4,5,6,7,8,9",
"EventCode": "0xc7",
"EventName": "FP_ARITH_OPS_RETIRED.VECTOR",
"PublicDescription": "Number of any Vector retired FP arithmetic instructions. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.",
"SampleAfterValue": "1000003",
"UMask": "0x3c",
"Unit": "cpu_core"
},
{
"BriefDescription": "FP_ARITH_OPS_RETIRED.VECTOR_128B",
"Counter": "0,1,2,3,4,5,6,7,8,9",
"EventCode": "0xc7",
"EventName": "FP_ARITH_OPS_RETIRED.VECTOR_128B",
"SampleAfterValue": "100003",
"UMask": "0xc",
"Unit": "cpu_core"
},
{
"BriefDescription": "FP_ARITH_OPS_RETIRED.VECTOR_256B",
"Counter": "0,1,2,3,4,5,6,7,8,9",
"EventCode": "0xc7",
"EventName": "FP_ARITH_OPS_RETIRED.VECTOR_256B",
"SampleAfterValue": "100003",
"UMask": "0x30",
"Unit": "cpu_core"
},
{
"BriefDescription": "Counts the number of all types of floating point operations per uop with all default weighting",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc8",
"EventName": "FP_FLOPS_RETIRED.ALL",
"PublicDescription": "Counts the number of all types of floating point operations per uop with all default weighting Available PDIST counters: 0,1",
"SampleAfterValue": "1000003",
"UMask": "0x3",
"Unit": "cpu_atom"
},
{
"BriefDescription": "Counts the number of floating point operations that produce 32 bit single precision results",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc8",
"EventName": "FP_FLOPS_RETIRED.FP32",
"PublicDescription": "Counts the number of floating point operations that produce 32 bit single precision results Available PDIST counters: 0,1",
"SampleAfterValue": "1000003",
"UMask": "0x2",
"Unit": "cpu_atom"
},
{
"BriefDescription": "Counts the number of floating point operations that produce 64 bit double precision results",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc8",
"EventName": "FP_FLOPS_RETIRED.FP64",
"PublicDescription": "Counts the number of floating point operations that produce 64 bit double precision results Available PDIST counters: 0,1",
"SampleAfterValue": "1000003",
"UMask": "0x1",
"Unit": "cpu_atom"
},
{
"BriefDescription": "Counts the number of retired instructions whose sources are a packed 128 bit double precision floating point. This may be SSE or AVX.128 operations.",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc7",
"EventName": "FP_INST_RETIRED.128B_DP",
"PublicDescription": "Counts the number of retired instructions whose sources are a packed 128 bit double precision floating point. This may be SSE or AVX.128 operations. Available PDIST counters: 0,1",
"SampleAfterValue": "1000003",
"UMask": "0x8",
"Unit": "cpu_atom"
},
{
"BriefDescription": "Counts the number of retired instructions whose sources are a packed 128 bit single precision floating point. This may be SSE or AVX.128 operations.",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc7",
"EventName": "FP_INST_RETIRED.128B_SP",
"PublicDescription": "Counts the number of retired instructions whose sources are a packed 128 bit single precision floating point. This may be SSE or AVX.128 operations. Available PDIST counters: 0,1",
"SampleAfterValue": "1000003",
"UMask": "0x4",
"Unit": "cpu_atom"
},
{
"BriefDescription": "Counts the number of retired instructions whose sources are a packed 256 bit double precision floating point.",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc7",
"EventName": "FP_INST_RETIRED.256B_DP",
"PublicDescription": "Counts the number of retired instructions whose sources are a packed 256 bit double precision floating point. Available PDIST counters: 0,1",
"SampleAfterValue": "1000003",
"UMask": "0x20",
"Unit": "cpu_atom"
},
{
"BriefDescription": "Counts the number of retired instructions whose sources are a packed 256 bit single precision floating point.",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc7",
"EventName": "FP_INST_RETIRED.256B_SP",
"PublicDescription": "Counts the number of retired instructions whose sources are a packed 256 bit single precision floating point. Available PDIST counters: 0,1",
"SampleAfterValue": "1000003",
"UMask": "0x10",
"Unit": "cpu_atom"
},
{
"BriefDescription": "Counts the number of retired instructions whose sources are a scalar 32bit single precision floating point.",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc7",
"EventName": "FP_INST_RETIRED.32B_SP",
"PublicDescription": "Counts the number of retired instructions whose sources are a scalar 32bit single precision floating point. Available PDIST counters: 0,1",
"SampleAfterValue": "1000003",
"UMask": "0x1",
"Unit": "cpu_atom"
},
{
"BriefDescription": "Counts the number of retired instructions whose sources are a scalar 64 bit double precision floating point.",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc7",
"EventName": "FP_INST_RETIRED.64B_DP",
"PublicDescription": "Counts the number of retired instructions whose sources are a scalar 64 bit double precision floating point. Available PDIST counters: 0,1",
"SampleAfterValue": "1000003",
"UMask": "0x2",
"Unit": "cpu_atom"
},
{
"BriefDescription": "Counts the total number of floating point retired instructions.",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc7",
"EventName": "FP_INST_RETIRED.ALL",
"PublicDescription": "Counts the total number of floating point retired instructions. Available PDIST counters: 0,1",
"SampleAfterValue": "1000003",
"UMask": "0x3f",
"Unit": "cpu_atom"
},
{
"BriefDescription": "Counts the number of floating point operations retired that required microcode assist.",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc3",
"EventName": "MACHINE_CLEARS.FP_ASSIST",
"PublicDescription": "Counts the number of floating point operations retired that required microcode assist, which is not a reflection of the number of FP operations, instructions or uops.",
"SampleAfterValue": "1000003",
"UMask": "0x4",
"Unit": "cpu_atom"
}
]

535
tools/perf/pmu-events/arch/x86/pantherlake/frontend.json
View File

@ -1,4 +1,369 @@
[
{
"BriefDescription": "Counts the total number of BACLEARS due to all branch types including conditional and unconditional jumps, returns, and indirect branches.",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xe6",
"EventName": "BACLEARS.ANY",
"PublicDescription": "Counts the total number of BACLEARS, which occur when the Branch Target Buffer (BTB) prediction or lack thereof, was corrected by a later branch predictor in the frontend. Includes BACLEARS due to all branch types including conditional and unconditional jumps, returns, and indirect branches.",
"SampleAfterValue": "1000003",
"UMask": "0x1",
"Unit": "cpu_atom"
},
{
"BriefDescription": "Clears due to Unknown Branches.",
"Counter": "0,1,2,3,4,5,6,7,8,9",
"EventCode": "0x60",
"EventName": "BACLEARS.ANY",
"PublicDescription": "Number of times the front-end is resteered when it finds a branch instruction in a fetch line. This is called Unknown Branch which occurs for the first time a branch instruction is fetched or when the branch is not tracked by the BPU (Branch Prediction Unit) anymore.",
"SampleAfterValue": "100003",
"UMask": "0x1",
"Unit": "cpu_core"
},
{
"BriefDescription": "Counts the number of BACLEARS due to a conditional jump.",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xe6",
"EventName": "BACLEARS.COND",
"SampleAfterValue": "1000003",
"UMask": "0x10",
"Unit": "cpu_atom"
},
{
"BriefDescription": "Counts the number of BACLEARS due to an indirect branch.",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xe6",
"EventName": "BACLEARS.INDIRECT",
"SampleAfterValue": "1000003",
"UMask": "0x2",
"Unit": "cpu_atom"
},
{
"BriefDescription": "Counts the number of BACLEARS due to a return branch.",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xe6",
"EventName": "BACLEARS.RETURN",
"SampleAfterValue": "1000003",
"UMask": "0x8",
"Unit": "cpu_atom"
},
{
"BriefDescription": "Counts the number of BACLEARS due to a direct, unconditional jump.",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xe6",
"EventName": "BACLEARS.UNCOND",
"SampleAfterValue": "1000003",
"UMask": "0x4",
"Unit": "cpu_atom"
},
{
"BriefDescription": "Stalls caused by changing prefix length of the instruction.",
"Counter": "0,1,2,3,4,5,6,7,8,9",
"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.",
"SampleAfterValue": "500009",
"UMask": "0x1",
"Unit": "cpu_core"
},
{
"BriefDescription": "Cycles the Microcode Sequencer is busy.",
"Counter": "0,1,2,3,4,5,6,7,8,9",
"EventCode": "0x87",
"EventName": "DECODE.MS_BUSY",
"SampleAfterValue": "500009",
"UMask": "0x2",
"Unit": "cpu_core"
},
{
"BriefDescription": "DSB-to-MITE switch true penalty cycles.",
"Counter": "0,1,2,3,4,5,6,7,8,9",
"EventCode": "0x61",
"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.",
"SampleAfterValue": "100003",
"UMask": "0x2",
"Unit": "cpu_core"
},
{
"BriefDescription": "Retired ANT branches",
"Counter": "0,1,2,3,4,5,6,7,8,9",
"EventCode": "0xc6",
"EventName": "FRONTEND_RETIRED.ANY_ANT",
"MSRIndex": "0x3F7",
"MSRValue": "0x9",
"PublicDescription": "Always Not Taken (ANT) conditional retired branches (no BTB entry and not mispredicted) Available PDIST counters: 0,1",
"SampleAfterValue": "100007",
"UMask": "0x3",
"Unit": "cpu_core"
},
{
"BriefDescription": "Retired Instructions who experienced DSB miss.",
"Counter": "0,1,2,3,4,5,6,7,8,9",
"EventCode": "0xc6",
"EventName": "FRONTEND_RETIRED.ANY_DSB_MISS",
"MSRIndex": "0x3F7",
"MSRValue": "0x1",
"PublicDescription": "Counts retired Instructions that experienced DSB (Decode stream buffer i.e. the decoded instruction-cache) miss. Available PDIST counters: 0,1",
"SampleAfterValue": "100007",
"UMask": "0x3",
"Unit": "cpu_core"
},
{
"BriefDescription": "Retired Instructions who experienced a critical DSB miss.",
"Counter": "0,1,2,3,4,5,6,7,8,9",
"EventCode": "0xc6",
"EventName": "FRONTEND_RETIRED.DSB_MISS",
"MSRIndex": "0x3F7",
"MSRValue": "0x11",
"PublicDescription": "Number of retired Instructions that experienced a critical DSB (Decode stream buffer i.e. the decoded instruction-cache) miss. Critical means stalls were exposed to the back-end as a result of the DSB miss. Available PDIST counters: 0,1",
"SampleAfterValue": "100007",
"UMask": "0x3",
"Unit": "cpu_core"
},
{
"BriefDescription": "Counts the number of instructions retired that were tagged because empty issue slots were seen before the uop due to ITLB miss",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc6",
"EventName": "FRONTEND_RETIRED.ITLB_MISS",
"PublicDescription": "Counts the number of instructions retired that were tagged because empty issue slots were seen before the uop due to ITLB miss Available PDIST counters: 0,1",
"SampleAfterValue": "1000003",
"UMask": "0x10",
"Unit": "cpu_atom"
},
{
"BriefDescription": "Retired Instructions who experienced iTLB true miss.",
"Counter": "0,1,2,3,4,5,6,7,8,9",
"EventCode": "0xc6",
"EventName": "FRONTEND_RETIRED.ITLB_MISS",
"MSRIndex": "0x3F7",
"MSRValue": "0x14",
"PublicDescription": "Counts retired Instructions that experienced iTLB (Instruction TLB) true miss. Available PDIST counters: 0,1",
"SampleAfterValue": "100007",
"UMask": "0x3",
"Unit": "cpu_core"
},
{
"BriefDescription": "Retired Instructions who experienced Instruction L1 Cache true miss.",
"Counter": "0,1,2,3,4,5,6,7,8,9",
"EventCode": "0xc6",
"EventName": "FRONTEND_RETIRED.L1I_MISS",
"MSRIndex": "0x3F7",
"MSRValue": "0x12",
"PublicDescription": "Counts retired Instructions who experienced Instruction L1 Cache true miss. Available PDIST counters: 0,1",
"SampleAfterValue": "100007",
"UMask": "0x3",
"Unit": "cpu_core"
},
{
"BriefDescription": "Retired Instructions who experienced Instruction L2 Cache true miss.",
"Counter": "0,1,2,3,4,5,6,7,8,9",
"EventCode": "0xc6",
"EventName": "FRONTEND_RETIRED.L2_MISS",
"MSRIndex": "0x3F7",
"MSRValue": "0x13",
"PublicDescription": "Counts retired Instructions who experienced Instruction L2 Cache true miss. Available PDIST counters: 0,1",
"SampleAfterValue": "100007",
"UMask": "0x3",
"Unit": "cpu_core"
},
{
"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": "0,1,2,3,4,5,6,7,8,9",
"EventCode": "0xc6",
"EventName": "FRONTEND_RETIRED.LATENCY_GE_128",
"MSRIndex": "0x3F7",
"MSRValue": "0x608006",
"PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 128 cycles which was not interrupted by a back-end stall. Available PDIST counters: 0,1",
"SampleAfterValue": "100007",
"UMask": "0x3",
"Unit": "cpu_core"
},
{
"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": "0,1,2,3,4,5,6,7,8,9",
"EventCode": "0xc6",
"EventName": "FRONTEND_RETIRED.LATENCY_GE_16",
"MSRIndex": "0x3F7",
"MSRValue": "0x601006",
"PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 16 cycles. During this period the front-end delivered no uops. Available PDIST counters: 0,1",
"SampleAfterValue": "100007",
"UMask": "0x3",
"Unit": "cpu_core"
},
{
"BriefDescription": "Retired instructions after front-end starvation of at least 2 cycles",
"Counter": "0,1,2,3,4,5,6,7,8,9",
"EventCode": "0xc6",
"EventName": "FRONTEND_RETIRED.LATENCY_GE_2",
"MSRIndex": "0x3F7",
"MSRValue": "0x600206",
"PublicDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of at least 2 cycles which was not interrupted by a back-end stall. Available PDIST counters: 0,1",
"SampleAfterValue": "100007",
"UMask": "0x3",
"Unit": "cpu_core"
},
{
"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": "0,1,2,3,4,5,6,7,8,9",
"EventCode": "0xc6",
"EventName": "FRONTEND_RETIRED.LATENCY_GE_256",
"MSRIndex": "0x3F7",
"MSRValue": "0x610006",
"PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 256 cycles which was not interrupted by a back-end stall. Available PDIST counters: 0,1",
"SampleAfterValue": "100007",
"UMask": "0x3",
"Unit": "cpu_core"
},
{
"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": "0,1,2,3,4,5,6,7,8,9",
"EventCode": "0xc6",
"EventName": "FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1",
"MSRIndex": "0x3F7",
"MSRValue": "0x100206",
"PublicDescription": "Counts retired instructions that are delivered to the back-end after the front-end had at least 1 bubble-slot for a period of 2 cycles. A bubble-slot is an empty issue-pipeline slot while there was no RAT stall. Available PDIST counters: 0,1",
"SampleAfterValue": "100007",
"UMask": "0x3",
"Unit": "cpu_core"
},
{
"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": "0,1,2,3,4,5,6,7,8,9",
"EventCode": "0xc6",
"EventName": "FRONTEND_RETIRED.LATENCY_GE_32",
"MSRIndex": "0x3F7",
"MSRValue": "0x602006",
"PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 32 cycles. During this period the front-end delivered no uops. Available PDIST counters: 0,1",
"SampleAfterValue": "100007",
"UMask": "0x3",
"Unit": "cpu_core"
},
{
"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": "0,1,2,3,4,5,6,7,8,9",
"EventCode": "0xc6",
"EventName": "FRONTEND_RETIRED.LATENCY_GE_4",
"MSRIndex": "0x3F7",
"MSRValue": "0x600406",
"PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 4 cycles which was not interrupted by a back-end stall. Available PDIST counters: 0,1",
"SampleAfterValue": "100007",
"UMask": "0x3",
"Unit": "cpu_core"
},
{
"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": "0,1,2,3,4,5,6,7,8,9",
"EventCode": "0xc6",
"EventName": "FRONTEND_RETIRED.LATENCY_GE_512",
"MSRIndex": "0x3F7",
"MSRValue": "0x620006",
"PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 512 cycles which was not interrupted by a back-end stall. Available PDIST counters: 0,1",
"SampleAfterValue": "100007",
"UMask": "0x3",
"Unit": "cpu_core"
},
{
"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": "0,1,2,3,4,5,6,7,8,9",
"EventCode": "0xc6",
"EventName": "FRONTEND_RETIRED.LATENCY_GE_64",
"MSRIndex": "0x3F7",
"MSRValue": "0x604006",
"PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 64 cycles which was not interrupted by a back-end stall. Available PDIST counters: 0,1",
"SampleAfterValue": "100007",
"UMask": "0x3",
"Unit": "cpu_core"
},
{
"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": "0,1,2,3,4,5,6,7,8,9",
"EventCode": "0xc6",
"EventName": "FRONTEND_RETIRED.LATENCY_GE_8",
"MSRIndex": "0x3F7",
"MSRValue": "0x600806",
"PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 8 cycles. During this period the front-end delivered no uops. Available PDIST counters: 0,1",
"SampleAfterValue": "100007",
"UMask": "0x3",
"Unit": "cpu_core"
},
{
"BriefDescription": "Mispredicted Retired ANT branches",
"Counter": "0,1,2,3,4,5,6,7,8,9",
"EventCode": "0xc6",
"EventName": "FRONTEND_RETIRED.MISP_ANT",
"MSRIndex": "0x3F7",
"MSRValue": "0x9",
"PublicDescription": "ANT retired branches that got just mispredicted Available PDIST counters: 0,1",
"SampleAfterValue": "100007",
"UMask": "0x2",
"Unit": "cpu_core"
},
{
"BriefDescription": "Counts flows delivered by the Microcode Sequencer",
"Counter": "0,1,2,3,4,5,6,7,8,9",
"EventCode": "0xc6",
"EventName": "FRONTEND_RETIRED.MS_FLOWS",
"MSRIndex": "0x3F7",
"MSRValue": "0x8",
"PublicDescription": "Counts flows delivered by the Microcode Sequencer Available PDIST counters: 0,1",
"SampleAfterValue": "100007",
"UMask": "0x3",
"Unit": "cpu_core"
},
{
"BriefDescription": "Retired Instructions who experienced STLB (2nd level TLB) true miss.",
"Counter": "0,1,2,3,4,5,6,7,8,9",
"EventCode": "0xc6",
"EventName": "FRONTEND_RETIRED.STLB_MISS",
"MSRIndex": "0x3F7",
"MSRValue": "0x15",
"PublicDescription": "Counts retired Instructions that experienced STLB (2nd level TLB) true miss. Available PDIST counters: 0,1",
"SampleAfterValue": "100007",
"UMask": "0x3",
"Unit": "cpu_core"
},
{
"BriefDescription": "Retired instructions that caused clears due to being Unknown Branches.",
"Counter": "0,1,2,3,4,5,6,7,8,9",
"EventCode": "0xc6",
"EventName": "FRONTEND_RETIRED.UNKNOWN_BRANCH",
"MSRIndex": "0x3F7",
"MSRValue": "0x17",
"PublicDescription": "Number retired branch instructions that caused the front-end to be resteered when it finds the instruction in a fetch line. This is called Unknown Branch which occurs for the first time a branch instruction is fetched or when the branch is not tracked by the BPU (Branch Prediction Unit) anymore. Available PDIST counters: 0,1",
"SampleAfterValue": "100007",
"UMask": "0x3",
"Unit": "cpu_core"
},
{
"BriefDescription": "Counts the number of instructions retired that were tagged because empty issue slots were seen before the uop due to Instruction L1 cache miss, that hit in the L2 cache.",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc9",
"EventName": "FRONTEND_RETIRED_SOURCE.ICACHE_L2_HIT",
"PublicDescription": "Counts the number of instructions retired that were tagged because empty issue slots were seen before the uop due to Instruction L1 cache miss, that hit in the L2 cache. Available PDIST counters: 0,1",
"SampleAfterValue": "1000003",
"UMask": "0x1",
"Unit": "cpu_atom"
},
{
"BriefDescription": "Counts the number of instructions retired that were tagged because empty issue slots were seen before the uop due to ITLB miss that hit in the second level TLB.",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc9",
"EventName": "FRONTEND_RETIRED_SOURCE.ITLB_STLB_HIT",
"PublicDescription": "Counts the number of instructions retired that were tagged because empty issue slots were seen before the uop due to ITLB miss that hit in the second level TLB. Available PDIST counters: 0,1",
"SampleAfterValue": "1000003",
"UMask": "0x10",
"Unit": "cpu_atom"
},
{
"BriefDescription": "Counts the number of instructions retired that were tagged because empty issue slots were seen before the uop due to ITLB miss that also missed the second level TLB.",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc9",
"EventName": "FRONTEND_RETIRED_SOURCE.ITLB_STLB_MISS",
"PublicDescription": "Counts the number of instructions retired that were tagged because empty issue slots were seen before the uop due to ITLB miss that also missed the second level TLB. Available PDIST counters: 0,1",
"SampleAfterValue": "1000003",
"UMask": "0x20",
"Unit": "cpu_atom"
},
{
"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",
@ -8,6 +373,15 @@
"UMask": "0x3",
"Unit": "cpu_atom"
},
{
"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 present.",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0x80",
"EventName": "ICACHE.HIT",
"SampleAfterValue": "1000003",
"UMask": "0x1",
"Unit": "cpu_atom"
},
{
"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",
@ -17,6 +391,134 @@
"UMask": "0x2",
"Unit": "cpu_atom"
},
{
"BriefDescription": "Cycles where a code fetch is stalled due to L1 instruction cache miss.",
"Counter": "0,1,2,3,4,5,6,7,8,9",
"EventCode": "0x80",
"EventName": "ICACHE_DATA.STALLS",
"PublicDescription": "Counts cycles where a code line fetch is stalled due to an L1 instruction cache miss. The decode pipeline works at a 32 Byte granularity.",
"SampleAfterValue": "500009",
"UMask": "0x4",
"Unit": "cpu_core"
},
{
"BriefDescription": "ICACHE_DATA.STALL_PERIODS",
"Counter": "0,1,2,3,4,5,6,7,8,9",
"CounterMask": "1",
"EdgeDetect": "1",
"EventCode": "0x80",
"EventName": "ICACHE_DATA.STALL_PERIODS",
"SampleAfterValue": "500009",
"UMask": "0x4",
"Unit": "cpu_core"
},
{
"BriefDescription": "Cycles where a code fetch is stalled due to L1 instruction cache tag miss.",
"Counter": "0,1,2,3,4,5,6,7,8,9",
"EventCode": "0x83",
"EventName": "ICACHE_TAG.STALLS",
"PublicDescription": "Counts cycles where a code fetch is stalled due to L1 instruction cache tag miss.",
"SampleAfterValue": "200003",
"UMask": "0x4",
"Unit": "cpu_core"
},
{
"BriefDescription": "Cycles Decode Stream Buffer (DSB) is delivering any Uop",
"Counter": "0,1,2,3,4,5,6,7,8,9",
"CounterMask": "1",
"EventCode": "0x79",
"EventName": "IDQ.DSB_CYCLES_ANY",
"PublicDescription": "Counts the number of cycles uops were delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path.",
"SampleAfterValue": "2000003",
"UMask": "0x8",
"Unit": "cpu_core"
},
{
"BriefDescription": "Cycles DSB is delivering optimal number of Uops",
"Counter": "0,1,2,3,4,5,6,7,8,9",
"CounterMask": "8",
"EventCode": "0x79",
"EventName": "IDQ.DSB_CYCLES_OK",
"PublicDescription": "Counts the number of cycles where optimal number of uops was delivered to the Instruction Decode Queue (IDQ) from the DSB (Decode Stream Buffer) path. Count includes uops that may 'bypass' the IDQ.",
"SampleAfterValue": "2000003",
"UMask": "0x8",
"Unit": "cpu_core"
},
{
"BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path",
"Counter": "0,1,2,3,4,5,6,7,8,9",
"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.",
"SampleAfterValue": "2000003",
"UMask": "0x8",
"Unit": "cpu_core"
},
{
"BriefDescription": "Cycles MITE is delivering any Uop",
"Counter": "0,1,2,3,4,5,6,7,8,9",
"CounterMask": "1",
"EventCode": "0x79",
"EventName": "IDQ.MITE_CYCLES_ANY",
"PublicDescription": "Counts the number of cycles uops were delivered to the Instruction Decode Queue (IDQ) from the MITE (legacy decode pipeline) path. During these cycles uops are not being delivered from the Decode Stream Buffer (DSB).",
"SampleAfterValue": "2000003",
"UMask": "0x4",
"Unit": "cpu_core"
},
{
"BriefDescription": "Cycles MITE is delivering optimal number of Uops",
"Counter": "0,1,2,3,4,5,6,7,8,9",
"CounterMask": "8",
"EventCode": "0x79",
"EventName": "IDQ.MITE_CYCLES_OK",
"PublicDescription": "Counts the number of cycles where optimal number of uops was delivered to the Instruction Decode Queue (IDQ) from the MITE (legacy decode pipeline) path. During these cycles uops are not being delivered from the Decode Stream Buffer (DSB).",
"SampleAfterValue": "2000003",
"UMask": "0x4",
"Unit": "cpu_core"
},
{
"BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) from MITE path",
"Counter": "0,1,2,3,4,5,6,7,8,9",
"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).",
"SampleAfterValue": "2000003",
"UMask": "0x4",
"Unit": "cpu_core"
},
{
"BriefDescription": "Cycles when uops are being delivered to IDQ while MS is busy",
"Counter": "0,1,2,3,4,5,6,7,8,9",
"CounterMask": "1",
"EventCode": "0x79",
"EventName": "IDQ.MS_CYCLES_ANY",
"PublicDescription": "Counts cycles during which uops are being delivered to Instruction Decode Queue (IDQ) while the Microcode Sequencer (MS) is busy. Uops maybe initiated by Decode Stream Buffer (DSB) or MITE.",
"SampleAfterValue": "2000003",
"UMask": "0x20",
"Unit": "cpu_core"
},
{
"BriefDescription": "Number of switches from DSB or MITE to the MS",
"Counter": "0,1,2,3,4,5,6,7,8,9",
"CounterMask": "1",
"EdgeDetect": "1",
"EventCode": "0x79",
"EventName": "IDQ.MS_SWITCHES",
"PublicDescription": "Number of switches from DSB (Decode Stream Buffer) or MITE (legacy decode pipeline) to the Microcode Sequencer.",
"SampleAfterValue": "100003",
"UMask": "0x20",
"Unit": "cpu_core"
},
{
"BriefDescription": "Uops initiated by MITE or Decode Stream Buffer (DSB) and delivered to Instruction Decode Queue (IDQ) while Microcode Sequencer (MS) is busy",
"Counter": "0,1,2,3,4,5,6,7,8,9",
"EventCode": "0x79",
"EventName": "IDQ.MS_UOPS",
"PublicDescription": "Counts the number of uops initiated by MITE or Decode Stream Buffer (DSB) and delivered to Instruction Decode Queue (IDQ) while the Microcode Sequencer (MS) is busy. Counting includes uops that may 'bypass' the IDQ.",
"SampleAfterValue": "1000003",
"UMask": "0x20",
"Unit": "cpu_core"
},
{
"BriefDescription": "This event counts a subset of the Topdown Slots event that when 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",
@ -26,5 +528,38 @@
"SampleAfterValue": "1000003",
"UMask": "0x1",
"Unit": "cpu_core"
},
{
"BriefDescription": "Cycles when optimal number of uops was delivered to the back-end when the back-end is not stalled",
"Counter": "0,1,2,3,4,5,6,7,8,9",
"CounterMask": "1",
"EventCode": "0x9c",
"EventName": "IDQ_BUBBLES.CYCLES_FE_WAS_OK",
"Invert": "1",
"PublicDescription": "Counts the number of cycles when the optimal number of uops were delivered by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls.",
"SampleAfterValue": "1000003",
"UMask": "0x1",
"Unit": "cpu_core"
},
{
"BriefDescription": "Cycles when no uops are delivered by the IDQ for 2 or more cycles when backend of the machine is not stalled - normally indicating a Fetch Latency issue",
"Counter": "0,1,2,3,4,5,6,7,8,9",
"EventCode": "0x9c",
"EventName": "IDQ_BUBBLES.FETCH_LATENCY",
"PublicDescription": "Counts the number of cycles when no uops were delivered by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls for 2 or more cycles - normally indicating a Fetch Latency issue.",
"SampleAfterValue": "1000003",
"UMask": "0x4",
"Unit": "cpu_core"
},
{
"BriefDescription": "Cycles when no uops are not delivered by the IDQ when backend of the machine is not stalled",
"Counter": "0,1,2,3,4,5,6,7,8,9",
"CounterMask": "8",
"EventCode": "0x9c",
"EventName": "IDQ_BUBBLES.STARVATION_CYCLES",
"PublicDescription": "Counts the number of cycles when no uops were delivered by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls.",
"SampleAfterValue": "1000003",
"UMask": "0x1",
"Unit": "cpu_core"
}
]

106
tools/perf/pmu-events/arch/x86/pantherlake/memory.json
View File

@ -1,4 +1,32 @@
[
{
"BriefDescription": "Counts the number of cycles that the head (oldest load) of the load buffer is stalled due to a core bound stall including a store address match, a DTLB miss or a page walk that detains the load from retiring.",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0x05",
"EventName": "LD_HEAD.L1_BOUND_AT_RET",
"SampleAfterValue": "1000003",
"UMask": "0xf4",
"Unit": "cpu_atom"
},
{
"BriefDescription": "Counts the number of machine clears due to memory ordering caused by a snoop from an external agent. Does not count internally generated machine clears such as those due to memory disambiguation.",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc3",
"EventName": "MACHINE_CLEARS.MEMORY_ORDERING",
"SampleAfterValue": "1000003",
"UMask": "0x2",
"Unit": "cpu_atom"
},
{
"BriefDescription": "Number of machine clears due to memory ordering conflicts.",
"Counter": "0,1,2,3,4,5,6,7,8,9",
"EventCode": "0xc3",
"EventName": "MACHINE_CLEARS.MEMORY_ORDERING",
"PublicDescription": "Counts the number of Machine Clears detected dye to memory ordering. Memory Ordering Machine Clears may apply when a memory read may not conform to the memory ordering rules of the x86 architecture",
"SampleAfterValue": "100003",
"UMask": "0x2",
"Unit": "cpu_core"
},
{
"BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 1024 cycles.",
"Counter": "2,3,4,5,6,7,8,9",
@ -7,7 +35,7 @@
"EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_1024",
"MSRIndex": "0x3F6",
"MSRValue": "0x400",
"PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 1024 cycles. Reported latency may be longer than just the memory latency. Available PDIST counters: 0",
"PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 1024 cycles. Reported latency may be longer than just the memory latency. Available PDIST counters: 0,1",
"SampleAfterValue": "53",
"UMask": "0x1",
"Unit": "cpu_core"
@ -20,7 +48,7 @@
"EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_128",
"MSRIndex": "0x3F6",
"MSRValue": "0x80",
"PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 128 cycles. Reported latency may be longer than just the memory latency. Available PDIST counters: 0",
"PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 128 cycles. Reported latency may be longer than just the memory latency. Available PDIST counters: 0,1",
"SampleAfterValue": "1009",
"UMask": "0x1",
"Unit": "cpu_core"
@ -33,7 +61,7 @@
"EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_16",
"MSRIndex": "0x3F6",
"MSRValue": "0x10",
"PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 16 cycles. Reported latency may be longer than just the memory latency. Available PDIST counters: 0",
"PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 16 cycles. Reported latency may be longer than just the memory latency. Available PDIST counters: 0,1",
"SampleAfterValue": "20011",
"UMask": "0x1",
"Unit": "cpu_core"
@ -46,7 +74,7 @@
"EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_2048",
"MSRIndex": "0x3F6",
"MSRValue": "0x800",
"PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 2048 cycles. Reported latency may be longer than just the memory latency. Available PDIST counters: 0",
"PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 2048 cycles. Reported latency may be longer than just the memory latency. Available PDIST counters: 0,1",
"SampleAfterValue": "23",
"UMask": "0x1",
"Unit": "cpu_core"
@ -59,7 +87,7 @@
"EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_256",
"MSRIndex": "0x3F6",
"MSRValue": "0x100",
"PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 256 cycles. Reported latency may be longer than just the memory latency. Available PDIST counters: 0",
"PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 256 cycles. Reported latency may be longer than just the memory latency. Available PDIST counters: 0,1",
"SampleAfterValue": "503",
"UMask": "0x1",
"Unit": "cpu_core"
@ -72,7 +100,7 @@
"EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_32",
"MSRIndex": "0x3F6",
"MSRValue": "0x20",
"PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 32 cycles. Reported latency may be longer than just the memory latency. Available PDIST counters: 0",
"PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 32 cycles. Reported latency may be longer than just the memory latency. Available PDIST counters: 0,1",
"SampleAfterValue": "100007",
"UMask": "0x1",
"Unit": "cpu_core"
@ -85,7 +113,7 @@
"EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_4",
"MSRIndex": "0x3F6",
"MSRValue": "0x4",
"PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 4 cycles. Reported latency may be longer than just the memory latency. Available PDIST counters: 0",
"PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 4 cycles. Reported latency may be longer than just the memory latency. Available PDIST counters: 0,1",
"SampleAfterValue": "100003",
"UMask": "0x1",
"Unit": "cpu_core"
@ -98,7 +126,7 @@
"EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_512",
"MSRIndex": "0x3F6",
"MSRValue": "0x200",
"PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 512 cycles. Reported latency may be longer than just the memory latency. Available PDIST counters: 0",
"PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 512 cycles. Reported latency may be longer than just the memory latency. Available PDIST counters: 0,1",
"SampleAfterValue": "101",
"UMask": "0x1",
"Unit": "cpu_core"
@ -111,7 +139,7 @@
"EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_64",
"MSRIndex": "0x3F6",
"MSRValue": "0x40",
"PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 64 cycles. Reported latency may be longer than just the memory latency. Available PDIST counters: 0",
"PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 64 cycles. Reported latency may be longer than just the memory latency. Available PDIST counters: 0,1",
"SampleAfterValue": "2003",
"UMask": "0x1",
"Unit": "cpu_core"
@ -124,7 +152,7 @@
"EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_8",
"MSRIndex": "0x3F6",
"MSRValue": "0x8",
"PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 8 cycles. Reported latency may be longer than just the memory latency. Available PDIST counters: 0",
"PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 8 cycles. Reported latency may be longer than just the memory latency. Available PDIST counters: 0,1",
"SampleAfterValue": "50021",
"UMask": "0x1",
"Unit": "cpu_core"
@ -135,11 +163,31 @@
"Data_LA": "1",
"EventCode": "0xcd",
"EventName": "MEM_TRANS_RETIRED.STORE_SAMPLE",
"PublicDescription": "Counts Retired memory accesses with at least 1 store operation. This PEBS event is the precisely-distributed (PDist) trigger covering all stores uops for sampling by the PEBS Store Latency Facility. The facility is described in Intel SDM Volume 3 section 19.9.8 Available PDIST counters: 0",
"PublicDescription": "Counts Retired memory accesses with at least 1 store operation. This PEBS event is the precisely-distributed (PDist) trigger covering all stores uops for sampling by the PEBS Store Latency Facility. The facility is described in Intel SDM Volume 3 section 19.9.8 Available PDIST counters: 0,1",
"SampleAfterValue": "1000003",
"UMask": "0x2",
"Unit": "cpu_core"
},
{
"BriefDescription": "Counts misaligned loads that are 4K page splits.",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0x13",
"EventName": "MISALIGN_MEM_REF.LOAD_PAGE_SPLIT",
"PublicDescription": "Counts misaligned loads that are 4K page splits. Available PDIST counters: 0,1",
"SampleAfterValue": "1000003",
"UMask": "0x2",
"Unit": "cpu_atom"
},
{
"BriefDescription": "Counts misaligned stores that are 4K page splits.",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0x13",
"EventName": "MISALIGN_MEM_REF.STORE_PAGE_SPLIT",
"PublicDescription": "Counts misaligned stores that are 4K page splits. Available PDIST counters: 0,1",
"SampleAfterValue": "1000003",
"UMask": "0x4",
"Unit": "cpu_atom"
},
{
"BriefDescription": "Counts demand data reads that were supplied by DRAM.",
"Counter": "0,1,2,3,4,5,6,7",
@ -154,7 +202,7 @@
},
{
"BriefDescription": "Counts demand data reads that were supplied by DRAM.",
"Counter": "0,1,2,3",
"Counter": "0,1,2,3,4,5,6,7,8,9",
"EventCode": "0x2A,0x2B",
"EventName": "OCR.DEMAND_DATA_RD.DRAM",
"MSRIndex": "0x1a6,0x1a7",
@ -178,7 +226,7 @@
},
{
"BriefDescription": "Counts demand data reads that were not supplied by the L3 cache.",
"Counter": "0,1,2,3",
"Counter": "0,1,2,3,4,5,6,7,8,9",
"EventCode": "0x2A,0x2B",
"EventName": "OCR.DEMAND_DATA_RD.L3_MISS",
"MSRIndex": "0x1a6,0x1a7",
@ -202,7 +250,7 @@
},
{
"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",
"Counter": "0,1,2,3,4,5,6,7,8,9",
"EventCode": "0x2A,0x2B",
"EventName": "OCR.DEMAND_RFO.L3_MISS",
"MSRIndex": "0x1a6,0x1a7",
@ -211,5 +259,35 @@
"SampleAfterValue": "100003",
"UMask": "0x1",
"Unit": "cpu_core"
},
{
"BriefDescription": "Counts demand data read requests that miss the L3 cache.",
"Counter": "0,1,2,3,4,5,6,7,8,9",
"EventCode": "0x21",
"EventName": "OFFCORE_REQUESTS.L3_MISS_DEMAND_DATA_RD",
"SampleAfterValue": "100003",
"UMask": "0x10",
"Unit": "cpu_core"
},
{
"BriefDescription": "Cycles where data return is pending for a Demand Data Read request who miss L3 cache.",
"Counter": "0,1,2,3",
"CounterMask": "1",
"EventCode": "0x20",
"EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_L3_MISS_DEMAND_DATA_RD",
"PublicDescription": "Cycles with at least 1 Demand Data Read requests who miss L3 cache in the superQ.",
"SampleAfterValue": "1000003",
"UMask": "0x10",
"Unit": "cpu_core"
},
{
"BriefDescription": "For every cycle, increments by the number of demand data read requests pending that are known to have missed the L3 cache.",
"Counter": "0,1,2,3",
"EventCode": "0x20",
"EventName": "OFFCORE_REQUESTS_OUTSTANDING.L3_MISS_DEMAND_DATA_RD",
"PublicDescription": "For every cycle, increments by the number of demand data read requests pending that are known to have missed the L3 cache. Note that this does not capture all elapsed cycles while requests are outstanding - only cycles from when the requests were known by the requesting core to have missed the L3 cache.",
"SampleAfterValue": "2000003",
"UMask": "0x10",
"Unit": "cpu_core"
}
]

44
tools/perf/pmu-events/arch/x86/pantherlake/other.json Normal file
View File

@ -0,0 +1,44 @@
[
{
"BriefDescription": "Count all other hardware assists or traps that are not necessarily architecturally exposed (through a software handler) beyond FP; SSE-AVX mix and A/D assists who are counted by dedicated sub-events.",
"Counter": "0,1,2,3,4,5,6,7,8,9",
"EventCode": "0xc1",
"EventName": "ASSISTS.HARDWARE",
"PublicDescription": "Count all other hardware assists or traps that are not necessarily architecturally exposed (through a software handler) beyond FP; SSE-AVX mix and A/D assists who are counted by dedicated sub-events. This includes, but not limited to, assists at EXE or MEM uop writeback like AVX* load/store/gather/scatter (non-FP GSSE-assist ) , assists generated by ROB like PEBS and RTIT, Uncore trap, RAR (Remote Action Request) and CET (Control flow Enforcement Technology) assists.",
"SampleAfterValue": "100003",
"UMask": "0x4",
"Unit": "cpu_core"
},
{
"BriefDescription": "ASSISTS.PAGE_FAULT",
"Counter": "0,1,2,3,4,5,6,7,8,9",
"EventCode": "0xc1",
"EventName": "ASSISTS.PAGE_FAULT",
"SampleAfterValue": "1000003",
"UMask": "0x8",
"Unit": "cpu_core"
},
{
"BriefDescription": "Counts streaming stores that have any type of response.",
"Counter": "0,1,2,3,4,5,6,7,8,9",
"EventCode": "0x2A,0x2B",
"EventName": "OCR.STREAMING_WR.ANY_RESPONSE",
"MSRIndex": "0x1a6,0x1a7",
"MSRValue": "0x10800",
"PublicDescription": "Counts streaming stores that have any type of response. Available PDIST counters: 0",
"SampleAfterValue": "100003",
"UMask": "0x1",
"Unit": "cpu_core"
},
{
"BriefDescription": "Cycles the uncore cannot take further requests",
"Counter": "0,1,2,3,4,5,6,7,8,9",
"CounterMask": "1",
"EventCode": "0x2d",
"EventName": "XQ.FULL",
"PublicDescription": "number of cycles when the thread is active and the uncore cannot take any further requests (for example prefetches, loads or stores initiated by the Core that miss the L2 cache).",
"SampleAfterValue": "1000003",
"UMask": "0x1",
"Unit": "cpu_core"
}
]

1600
tools/perf/pmu-events/arch/x86/pantherlake/pipeline.json
View File

File diff suppressed because it is too large Load Diff

26
tools/perf/pmu-events/arch/x86/pantherlake/uncore-memory.json Normal file
View File

@ -0,0 +1,26 @@
[
{
"BriefDescription": "Read CAS command sent to DRAM",
"Counter": "0,1,2,3,4",
"EventCode": "0x22",
"EventName": "UNC_M_CAS_COUNT_RD",
"PerPkg": "1",
"Unit": "iMC"
},
{
"BriefDescription": "Write CAS command sent to DRAM",
"Counter": "0,1,2,3,4",
"EventCode": "0x23",
"EventName": "UNC_M_CAS_COUNT_WR",
"PerPkg": "1",
"Unit": "iMC"
},
{
"BriefDescription": "Total number of read and write byte transfers to/from DRAM, in 32B chunk, per DDR channel. Counter increments by 1 after sending or receiving 32B chunk data.",
"Counter": "0,1,2,3,4",
"EventCode": "0x3C",
"EventName": "UNC_M_TOTAL_DATA",
"PerPkg": "1",
"Unit": "iMC"
}
]

248
tools/perf/pmu-events/arch/x86/pantherlake/virtual-memory.json
View File

@ -1,4 +1,43 @@
[
{
"BriefDescription": "Counts the number of page walks initiated by a demand load that missed the first and second level TLBs.",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0x08",
"EventName": "DTLB_LOAD_MISSES.MISS_CAUSED_WALK",
"SampleAfterValue": "1000003",
"UMask": "0x1",
"Unit": "cpu_atom"
},
{
"BriefDescription": "Counts the number of first level TLB misses but second level hits due to a demand load that did not start a page walk. Accounts for all page sizes. Will result in a DTLB write from STLB.",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0x08",
"EventName": "DTLB_LOAD_MISSES.STLB_HIT",
"SampleAfterValue": "1000003",
"UMask": "0x20",
"Unit": "cpu_atom"
},
{
"BriefDescription": "Loads that miss the DTLB and hit the STLB.",
"Counter": "0,1,2,3,4,5,6,7,8,9",
"EventCode": "0x12",
"EventName": "DTLB_LOAD_MISSES.STLB_HIT",
"PublicDescription": "Counts loads that miss the DTLB (Data TLB) and hit the STLB (Second level TLB).",
"SampleAfterValue": "100003",
"UMask": "0x320",
"Unit": "cpu_core"
},
{
"BriefDescription": "Cycles when at least one PMH is busy with a page walk for a demand load.",
"Counter": "0,1,2,3,4,5,6,7,8,9",
"CounterMask": "1",
"EventCode": "0x12",
"EventName": "DTLB_LOAD_MISSES.WALK_ACTIVE",
"PublicDescription": "Counts cycles when at least one PMH (Page Miss Handler) is busy with a page walk for a demand load.",
"SampleAfterValue": "100003",
"UMask": "0x10",
"Unit": "cpu_core"
},
{
"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",
@ -19,6 +58,86 @@
"UMask": "0xe",
"Unit": "cpu_core"
},
{
"BriefDescription": "Page walks completed due to a demand data load to a 1G page.",
"Counter": "0,1,2,3,4,5,6,7,8,9",
"EventCode": "0x12",
"EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED_1G",
"PublicDescription": "Counts completed page walks (1G sizes) caused by demand data loads. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.",
"SampleAfterValue": "100003",
"UMask": "0x8",
"Unit": "cpu_core"
},
{
"BriefDescription": "Page walks completed due to a demand data load to a 2M/4M page.",
"Counter": "0,1,2,3,4,5,6,7,8,9",
"EventCode": "0x12",
"EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M",
"PublicDescription": "Counts completed page walks (2M/4M sizes) caused by demand data loads. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.",
"SampleAfterValue": "100003",
"UMask": "0x4",
"Unit": "cpu_core"
},
{
"BriefDescription": "Page walks completed due to a demand data load to a 4K page.",
"Counter": "0,1,2,3,4,5,6,7,8,9",
"EventCode": "0x12",
"EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED_4K",
"PublicDescription": "Counts completed page walks (4K sizes) caused by demand data loads. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.",
"SampleAfterValue": "100003",
"UMask": "0x2",
"Unit": "cpu_core"
},
{
"BriefDescription": "Number of page walks outstanding for a demand load in the PMH each cycle.",
"Counter": "0,1,2,3,4,5,6,7,8,9",
"EventCode": "0x12",
"EventName": "DTLB_LOAD_MISSES.WALK_PENDING",
"PublicDescription": "Counts the number of page walks outstanding for a demand load in the PMH (Page Miss Handler) each cycle.",
"SampleAfterValue": "100003",
"UMask": "0x10",
"Unit": "cpu_core"
},
{
"BriefDescription": "Counts the number of page walks initiated by a store that missed the first and second level TLBs.",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0x49",
"EventName": "DTLB_STORE_MISSES.MISS_CAUSED_WALK",
"SampleAfterValue": "1000003",
"UMask": "0x1",
"Unit": "cpu_atom"
},
{
"BriefDescription": "Counts the number of first level TLB misses but second level hits due to stores that did not start a page walk. Accounts for all page sizes. Will result in a DTLB write from STLB.",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0x49",
"EventName": "DTLB_STORE_MISSES.STLB_HIT",
"PublicDescription": "Counts the number of first level TLB misses but second level hits due to a demand load that did not start a page walk. Accounts for all page sizes. Will result in a DTLB write from STLB.",
"SampleAfterValue": "1000003",
"UMask": "0x20",
"Unit": "cpu_atom"
},
{
"BriefDescription": "Stores that miss the DTLB and hit the STLB.",
"Counter": "0,1,2,3,4,5,6,7,8,9",
"EventCode": "0x13",
"EventName": "DTLB_STORE_MISSES.STLB_HIT",
"PublicDescription": "Counts stores that miss the DTLB (Data TLB) and hit the STLB (2nd Level TLB).",
"SampleAfterValue": "100003",
"UMask": "0x320",
"Unit": "cpu_core"
},
{
"BriefDescription": "Cycles when at least one PMH is busy with a page walk for a store.",
"Counter": "0,1,2,3,4,5,6,7,8,9",
"CounterMask": "1",
"EventCode": "0x13",
"EventName": "DTLB_STORE_MISSES.WALK_ACTIVE",
"PublicDescription": "Counts cycles when at least one PMH (Page Miss Handler) is busy with a page walk for a store.",
"SampleAfterValue": "100003",
"UMask": "0x10",
"Unit": "cpu_core"
},
{
"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",
@ -39,6 +158,85 @@
"UMask": "0xe",
"Unit": "cpu_core"
},
{
"BriefDescription": "Page walks completed due to a demand data store to a 1G page.",
"Counter": "0,1,2,3,4,5,6,7,8,9",
"EventCode": "0x13",
"EventName": "DTLB_STORE_MISSES.WALK_COMPLETED_1G",
"PublicDescription": "Counts completed page walks (1G sizes) caused by demand data stores. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.",
"SampleAfterValue": "100003",
"UMask": "0x8",
"Unit": "cpu_core"
},
{
"BriefDescription": "Page walks completed due to a demand data store to a 2M/4M page.",
"Counter": "0,1,2,3,4,5,6,7,8,9",
"EventCode": "0x13",
"EventName": "DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M",
"PublicDescription": "Counts completed page walks (2M/4M sizes) caused by demand data stores. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.",
"SampleAfterValue": "100003",
"UMask": "0x4",
"Unit": "cpu_core"
},
{
"BriefDescription": "Page walks completed due to a demand data store to a 4K page.",
"Counter": "0,1,2,3,4,5,6,7,8,9",
"EventCode": "0x13",
"EventName": "DTLB_STORE_MISSES.WALK_COMPLETED_4K",
"PublicDescription": "Counts completed page walks (4K sizes) caused by demand data stores. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.",
"SampleAfterValue": "100003",
"UMask": "0x2",
"Unit": "cpu_core"
},
{
"BriefDescription": "Number of page walks outstanding for a store in the PMH each cycle.",
"Counter": "0,1,2,3,4,5,6,7,8,9",
"EventCode": "0x13",
"EventName": "DTLB_STORE_MISSES.WALK_PENDING",
"PublicDescription": "Counts the number of page walks outstanding for a store in the PMH (Page Miss Handler) each cycle.",
"SampleAfterValue": "100003",
"UMask": "0x10",
"Unit": "cpu_core"
},
{
"BriefDescription": "Counts the number of page walks initiated by a instruction fetch that missed the first and second level TLBs.",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0x85",
"EventName": "ITLB_MISSES.MISS_CAUSED_WALK",
"SampleAfterValue": "1000003",
"UMask": "0x1",
"Unit": "cpu_atom"
},
{
"BriefDescription": "Counts the number of first level TLB misses but second level hits due to an instruction fetch that did not start a page walk. Account for all pages sizes. Will result in an ITLB write from STLB.",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0x85",
"EventName": "ITLB_MISSES.STLB_HIT",
"SampleAfterValue": "1000003",
"UMask": "0x20",
"Unit": "cpu_atom"
},
{
"BriefDescription": "Instruction fetch requests that miss the ITLB and hit the STLB.",
"Counter": "0,1,2,3,4,5,6,7,8,9",
"EventCode": "0x11",
"EventName": "ITLB_MISSES.STLB_HIT",
"PublicDescription": "Counts instruction fetch requests that miss the ITLB (Instruction TLB) and hit the STLB (Second-level TLB).",
"SampleAfterValue": "100003",
"UMask": "0x120",
"Unit": "cpu_core"
},
{
"BriefDescription": "Cycles when at least one PMH is busy with a page walk for code (instruction fetch) request.",
"Counter": "0,1,2,3,4,5,6,7,8,9",
"CounterMask": "1",
"EventCode": "0x11",
"EventName": "ITLB_MISSES.WALK_ACTIVE",
"PublicDescription": "Counts cycles when at least one PMH (Page Miss Handler) is busy with a page walk for a code (instruction fetch) request.",
"SampleAfterValue": "100003",
"UMask": "0x10",
"Unit": "cpu_core"
},
{
"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",
@ -58,5 +256,55 @@
"SampleAfterValue": "100003",
"UMask": "0xe",
"Unit": "cpu_core"
},
{
"BriefDescription": "Code miss in all TLB levels causes a page walk that completes. (2M/4M)",
"Counter": "0,1,2,3,4,5,6,7,8,9",
"EventCode": "0x11",
"EventName": "ITLB_MISSES.WALK_COMPLETED_2M_4M",
"PublicDescription": "Counts completed page walks (2M/4M 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.",
"SampleAfterValue": "100003",
"UMask": "0x4",
"Unit": "cpu_core"
},
{
"BriefDescription": "Code miss in all TLB levels causes a page walk that completes. (4K)",
"Counter": "0,1,2,3,4,5,6,7,8,9",
"EventCode": "0x11",
"EventName": "ITLB_MISSES.WALK_COMPLETED_4K",
"PublicDescription": "Counts completed page walks (4K 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.",
"SampleAfterValue": "100003",
"UMask": "0x2",
"Unit": "cpu_core"
},
{
"BriefDescription": "Counts the number of page walks outstanding for iside in PMH every cycle.",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0x85",
"EventName": "ITLB_MISSES.WALK_PENDING",
"PublicDescription": "Counts the number of page walks outstanding for iside in PMH every cycle. A PMH page walk is outstanding from page walk start till PMH becomes idle again (ready to serve next walk). Includes EPT-walk intervals. Walks could be counted by edge detecting on this event, but would count restarted suspended walks.",
"SampleAfterValue": "1000003",
"UMask": "0x10",
"Unit": "cpu_atom"
},
{
"BriefDescription": "Number of page walks outstanding for an outstanding code request in the PMH each cycle.",
"Counter": "0,1,2,3,4,5,6,7,8,9",
"EventCode": "0x11",
"EventName": "ITLB_MISSES.WALK_PENDING",
"PublicDescription": "Counts the number of page walks outstanding for an outstanding code (instruction fetch) request in the PMH (Page Miss Handler) each cycle.",
"SampleAfterValue": "100003",
"UMask": "0x10",
"Unit": "cpu_core"
},
{
"BriefDescription": "Counts the number of retired loads that are blocked due to a first level TLB miss.",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0x03",
"EventName": "LD_BLOCKS.DTLB_MISS",
"PublicDescription": "Counts the number of retired loads that are blocked due to a first level TLB miss. Available PDIST counters: 0,1",
"SampleAfterValue": "1000003",
"UMask": "0x8",
"Unit": "cpu_atom"
}
]