mirrors/linux
1
0
Fork 0
mirror of https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git synced 2026-05-01 00:02:19 -04:00
Code Issues Packages Projects Releases Wiki Activity

perf vendor events: Update/add Lunarlake events/metrics

Browse Source 
Update events from v1.01 to v1.10.
Add TMA metrics 5.02.

Bring in the event updates v1.11:
af329039e8
4a1cff8ceb
cbc3b0dc19
28f4b24f91
172900e962
dab0308f7a

The TMA 5.02 addition is from (with subsequent fixes):
1d72913b2d

Co-developed-by: Caleb Biggers <caleb.biggers@intel.com>
Signed-off-by: Caleb Biggers <caleb.biggers@intel.com>
Signed-off-by: Ian Rogers <irogers@google.com>
Acked-by: Kan Liang <kan.liang@linux.intel.com>
Tested-by: Thomas Falcon <thomas.falcon@intel.com>
Link: https://lore.kernel.org/r/20250211213031.114209-17-irogers@google.com
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
This commit is contained in:
Ian Rogers
2025-02-11 13:30:23 -08:00
committed by Namhyung Kim
parent c49b050915
commit 23878069de
11 changed files with 8174 additions and 101 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1288
tools/perf/pmu-events/arch/x86/lunarlake/cache.json
View File

File diff suppressed because it is too large Load Diff

484
tools/perf/pmu-events/arch/x86/lunarlake/floating-point.json Normal file
View File

@@ -0,0 +1,484 @@
[
{
"BriefDescription": "Counts the number of cycles when any of the floating point dividers are active.",
"Counter": "0,1,2,3,4,5,6,7",
"CounterMask": "1",
"EventCode": "0xcd",
"EventName": "ARITH.FPDIV_ACTIVE",
"SampleAfterValue": "1000003",
"UMask": "0x2",
"Unit": "cpu_atom"
},
{
"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 the number of active floating point dividers per cycle in the loop stage.",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xcd",
"EventName": "ARITH.FPDIV_OCCUPANCY",
"SampleAfterValue": "1000003",
"UMask": "0x2",
"Unit": "cpu_atom"
},
{
"BriefDescription": "Counts the number of floating point divider uops executed per cycle.",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xcd",
"EventName": "ARITH.FPDIV_UOPS",
"SampleAfterValue": "1000003",
"UMask": "0x8",
"Unit": "cpu_atom"
},
{
"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": "This event is deprecated. Refer to new event FP_ARITH_OPS_RETIRED.128B_PACKED_DOUBLE",
"Counter": "0,1,2,3,4,5,6,7,8,9",
"Deprecated": "1",
"EventCode": "0xc7",
"EventName": "FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE",
"SampleAfterValue": "100003",
"UMask": "0x4",
"Unit": "cpu_core"
},
{
"BriefDescription": "This event is deprecated. Refer to new event FP_ARITH_OPS_RETIRED.128B_PACKED_SINGLE",
"Counter": "0,1,2,3,4,5,6,7,8,9",
"Deprecated": "1",
"EventCode": "0xc7",
"EventName": "FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE",
"SampleAfterValue": "100003",
"UMask": "0x8",
"Unit": "cpu_core"
},
{
"BriefDescription": "This event is deprecated. Refer to new event FP_ARITH_OPS_RETIRED.256B_PACKED_DOUBLE",
"Counter": "0,1,2,3,4,5,6,7,8,9",
"Deprecated": "1",
"EventCode": "0xc7",
"EventName": "FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE",
"SampleAfterValue": "100003",
"UMask": "0x10",
"Unit": "cpu_core"
},
{
"BriefDescription": "This event is deprecated. Refer to new event FP_ARITH_OPS_RETIRED.256B_PACKED_SINGLE",
"Counter": "0,1,2,3,4,5,6,7,8,9",
"Deprecated": "1",
"EventCode": "0xc7",
"EventName": "FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE",
"SampleAfterValue": "100003",
"UMask": "0x20",
"Unit": "cpu_core"
},
{
"BriefDescription": "This event is deprecated. Refer to new event FP_ARITH_OPS_RETIRED.4_FLOPS",
"Counter": "0,1,2,3,4,5,6,7,8,9",
"Deprecated": "1",
"EventCode": "0xc7",
"EventName": "FP_ARITH_INST_RETIRED.4_FLOPS",
"SampleAfterValue": "100003",
"UMask": "0x18",
"Unit": "cpu_core"
},
{
"BriefDescription": "This event is deprecated. Refer to new event FP_ARITH_OPS_RETIRED.SCALAR",
"Counter": "0,1,2,3,4,5,6,7,8,9",
"Deprecated": "1",
"EventCode": "0xc7",
"EventName": "FP_ARITH_INST_RETIRED.SCALAR",
"SampleAfterValue": "1000003",
"UMask": "0x3",
"Unit": "cpu_core"
},
{
"BriefDescription": "This event is deprecated. Refer to new event FP_ARITH_OPS_RETIRED.SCALAR_DOUBLE",
"Counter": "0,1,2,3,4,5,6,7,8,9",
"Deprecated": "1",
"EventCode": "0xc7",
"EventName": "FP_ARITH_INST_RETIRED.SCALAR_DOUBLE",
"SampleAfterValue": "100003",
"UMask": "0x1",
"Unit": "cpu_core"
},
{
"BriefDescription": "This event is deprecated. Refer to new event FP_ARITH_OPS_RETIRED.SCALAR_SINGLE",
"Counter": "0,1,2,3,4,5,6,7,8,9",
"Deprecated": "1",
"EventCode": "0xc7",
"EventName": "FP_ARITH_INST_RETIRED.SCALAR_SINGLE",
"SampleAfterValue": "100003",
"UMask": "0x2",
"Unit": "cpu_core"
},
{
"BriefDescription": "This event is deprecated. Refer to new event FP_ARITH_OPS_RETIRED.VECTOR",
"Counter": "0,1,2,3,4,5,6,7,8,9",
"Deprecated": "1",
"EventCode": "0xc7",
"EventName": "FP_ARITH_INST_RETIRED.VECTOR",
"SampleAfterValue": "1000003",
"UMask": "0x3c",
"Unit": "cpu_core"
},
{
"BriefDescription": "FP_ARITH_INST_RETIRED.VECTOR_128B [This event is alias to FP_ARITH_OPS_RETIRED.VECTOR_128B]",
"Counter": "0,1,2,3,4,5,6,7,8,9",
"EventCode": "0xc7",
"EventName": "FP_ARITH_INST_RETIRED.VECTOR_128B",
"SampleAfterValue": "100003",
"UMask": "0xc",
"Unit": "cpu_core"
},
{
"BriefDescription": "FP_ARITH_INST_RETIRED.VECTOR_256B [This event is alias to FP_ARITH_OPS_RETIRED.VECTOR_256B]",
"Counter": "0,1,2,3,4,5,6,7,8,9",
"EventCode": "0xc7",
"EventName": "FP_ARITH_INST_RETIRED.VECTOR_256B",
"SampleAfterValue": "100003",
"UMask": "0x30",
"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 [This event is alias to FP_ARITH_INST_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 [This event is alias to FP_ARITH_INST_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",
"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",
"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",
"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",
"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",
"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",
"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",
"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",
"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",
"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",
"SampleAfterValue": "1000003",
"UMask": "0x3f",
"Unit": "cpu_atom"
},
{
"BriefDescription": "Counts the number of uops executed on all floating point ports.",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xb2",
"EventName": "FP_VINT_UOPS_EXECUTED.ALL",
"SampleAfterValue": "1000003",
"UMask": "0x1f",
"Unit": "cpu_atom"
},
{
"BriefDescription": "Counts the number of uops executed on floating point and vector integer port 0.",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xb2",
"EventName": "FP_VINT_UOPS_EXECUTED.P0",
"SampleAfterValue": "1000003",
"UMask": "0x2",
"Unit": "cpu_atom"
},
{
"BriefDescription": "Counts the number of uops executed on floating point and vector integer port 1.",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xb2",
"EventName": "FP_VINT_UOPS_EXECUTED.P1",
"SampleAfterValue": "1000003",
"UMask": "0x4",
"Unit": "cpu_atom"
},
{
"BriefDescription": "Counts the number of uops executed on floating point and vector integer port 2.",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xb2",
"EventName": "FP_VINT_UOPS_EXECUTED.P2",
"SampleAfterValue": "1000003",
"UMask": "0x8",
"Unit": "cpu_atom"
},
{
"BriefDescription": "Counts the number of uops executed on floating point and vector integer port 3.",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xb2",
"EventName": "FP_VINT_UOPS_EXECUTED.P3",
"SampleAfterValue": "1000003",
"UMask": "0x10",
"Unit": "cpu_atom"
},
{
"BriefDescription": "Counts the number of uops executed on floating point and vector integer port 0, 1, 2, 3.",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xb2",
"EventName": "FP_VINT_UOPS_EXECUTED.PRIMARY",
"SampleAfterValue": "1000003",
"UMask": "0x1e",
"Unit": "cpu_atom"
},
{
"BriefDescription": "Counts the number of uops executed on floating point and vector integer store data port.",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xb2",
"EventName": "FP_VINT_UOPS_EXECUTED.STD",
"SampleAfterValue": "1000003",
"UMask": "0x1",
"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": "20003",
"UMask": "0x4",
"Unit": "cpu_atom"
},
{
"BriefDescription": "Counts the number of floating point divide uops retired (x87 and sse, including x87 sqrt)",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc2",
"EventName": "UOPS_RETIRED.FPDIV",
"SampleAfterValue": "2000003",
"UMask": "0x8",
"Unit": "cpu_atom"
}
]

654
tools/perf/pmu-events/arch/x86/lunarlake/frontend.json
View File

@@ -1,4 +1,446 @@
[
{
"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": "200003",
"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": "200003",
"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": "200003",
"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": "200003",
"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": "200003",
"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": "Counts the number of times a decode restriction reduces the decode throughput due to wrong instruction length prediction.",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xe9",
"EventName": "DECODE_RESTRICTION.PREDECODE_WRONG",
"SampleAfterValue": "200003",
"UMask": "0x1",
"Unit": "cpu_atom"
},
{
"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": "Counts the number of instructions retired that were tagged with having preceded with frontend bound behavior",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc6",
"EventName": "FRONTEND_RETIRED.ALL",
"SampleAfterValue": "1000003",
"Unit": "cpu_atom"
},
{
"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)",
"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.",
"SampleAfterValue": "100007",
"UMask": "0x3",
"Unit": "cpu_core"
},
{
"BriefDescription": "Counts the number of instruction retired that are tagged after a branch instruction causes bubbles/empty issue slots due to a baclear",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc6",
"EventName": "FRONTEND_RETIRED.BRANCH_DETECT",
"SampleAfterValue": "1000003",
"UMask": "0x2",
"Unit": "cpu_atom"
},
{
"BriefDescription": "Counts the number of instruction retired that are tagged after a branch instruction causes bubbles /empty issue slots due to a btclear",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc6",
"EventName": "FRONTEND_RETIRED.BRANCH_RESTEER",
"SampleAfterValue": "1000003",
"UMask": "0x40",
"Unit": "cpu_atom"
},
{
"BriefDescription": "Counts the number of instructions retired that were tagged following an ms flow due to the bubble/wasted issue slot from exiting long ms flow",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc6",
"EventName": "FRONTEND_RETIRED.CISC",
"PublicDescription": "Counts the number of instructions retired that were tagged following an ms flow due to the bubble/wasted issue slot from exiting long ms flow",
"SampleAfterValue": "1000003",
"UMask": "0x1",
"Unit": "cpu_atom"
},
{
"BriefDescription": "Counts the number of instructions retired that were tagged every cycle the decoder is unable to send 4 uops",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc6",
"EventName": "FRONTEND_RETIRED.DECODE",
"SampleAfterValue": "1000003",
"UMask": "0x8",
"Unit": "cpu_atom"
},
{
"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.",
"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 icache miss",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc6",
"EventName": "FRONTEND_RETIRED.ICACHE",
"SampleAfterValue": "1000003",
"UMask": "0x20",
"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",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc6",
"EventName": "FRONTEND_RETIRED.ITLB_MISS",
"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.",
"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.",
"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.",
"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.",
"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.",
"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.",
"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.",
"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.",
"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.",
"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.",
"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.",
"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.",
"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.",
"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",
"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",
"SampleAfterValue": "100007",
"UMask": "0x3",
"Unit": "cpu_core"
},
{
"BriefDescription": "Counts the number of instruction retired tagged after a wasted issue slot if none of the previous events occurred",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc6",
"EventName": "FRONTEND_RETIRED.OTHER",
"SampleAfterValue": "1000003",
"UMask": "0x80",
"Unit": "cpu_atom"
},
{
"BriefDescription": "Counts the number of instruction retired that are tagged after a branch instruction causes bubbles/empty issue slots due to a predecode wrong",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc6",
"EventName": "FRONTEND_RETIRED.PREDECODE",
"SampleAfterValue": "1000003",
"UMask": "0x4",
"Unit": "cpu_atom"
},
{
"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.",
"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.",
"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. Includes L2 Hit resulting from and L1D eviction of another core in the same module which is longer latency than a typical L2 hit.",
"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",
"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",
"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 +450,15 @@
"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": "200003",
"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",
@@ -18,13 +469,212 @@
"Unit": "cpu_atom"
},
{
"BriefDescription": "This event counts a subset of the Topdown Slots event that were no operation was delivered to the back-end pipeline due to instruction fetch limitations when the back-end could have accepted more operations. Common examples include instruction cache misses or x86 instruction decode limitations.",
"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",
"EventCode": "0x9c",
"EventName": "IDQ_BUBBLES.CORE",
"PublicDescription": "This event counts a subset of the Topdown Slots event that were no operation was delivered to the back-end pipeline due to instruction fetch limitations when the back-end could have accepted more operations. Common examples include instruction cache misses or x86 instruction decode limitations. Software can use this event as the numerator for the Frontend Bound metric (or top-level category) of the Top-down Microarchitecture Analysis method.",
"PublicDescription": "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. Software can use this event as the numerator for the Frontend Bound metric (or top-level category) of the Top-down Microarchitecture Analysis method.",
"SampleAfterValue": "1000003",
"UMask": "0x1",
"Unit": "cpu_core"
},
{
"BriefDescription": "This event is deprecated. [This event is alias to IDQ_BUBBLES.STARVATION_CYCLES]",
"Counter": "0,1,2,3,4,5,6,7,8,9",
"CounterMask": "8",
"Deprecated": "1",
"EventCode": "0x9c",
"EventName": "IDQ_BUBBLES.CYCLES_0_UOPS_DELIV.CORE",
"SampleAfterValue": "1000003",
"UMask": "0x1",
"Unit": "cpu_core"
},
{
"BriefDescription": "Cycles when optimal number of uops was delivered to the back-end when the back-end is not stalled",
"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 [This event is alias to IDQ_BUBBLES.CYCLES_0_UOPS_DELIV.CORE]",
"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. [This event is alias to IDQ_BUBBLES.CYCLES_0_UOPS_DELIV.CORE]",
"SampleAfterValue": "1000003",
"UMask": "0x1",
"Unit": "cpu_core"
},
{
"BriefDescription": "Counts the number of cycles that the micro-sequencer is busy.",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xe7",
"EventName": "MS_DECODED.MS_BUSY",
"SampleAfterValue": "200003",
"UMask": "0x4",
"Unit": "cpu_atom"
},
{
"BriefDescription": "Counts the number of times entered into a ucode flow in the FEC. Includes inserted flows due to front-end detected faults or assists.",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xe7",
"EventName": "MS_DECODED.MS_ENTRY",
"SampleAfterValue": "200003",
"UMask": "0x1",
"Unit": "cpu_atom"
},
{
"BriefDescription": "Counts the number of times nanocode flow is executed.",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xe7",
"EventName": "MS_DECODED.NANO_CODE",
"SampleAfterValue": "200003",
"UMask": "0x2",
"Unit": "cpu_atom"
}
]

2730
tools/perf/pmu-events/arch/x86/lunarlake/lnl-metrics.json Normal file
View File

File diff suppressed because it is too large Load Diff

264
tools/perf/pmu-events/arch/x86/lunarlake/memory.json
View File

@@ -1,13 +1,168 @@
[
{
"BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 1024 cycles.",
"BriefDescription": "Counts the number of cycles that the head (oldest load) of the load buffer is stalled due to any number of reasons, including an L1 miss, WCB full, pagewalk, store address block or store data block.",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0x05",
"EventName": "LD_HEAD.ANY",
"SampleAfterValue": "1000003",
"UMask": "0x7f",
"Unit": "cpu_atom"
},
{
"BriefDescription": "Counts the number of cycles that the head (oldest load) of the load buffer is stalled due to any number of reasons, including an L1 miss, WCB full, pagewalk, store address block or store data block, on a load that retires.",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0x05",
"EventName": "LD_HEAD.ANY_AT_RET",
"SampleAfterValue": "1000003",
"UMask": "0xff",
"Unit": "cpu_atom"
},
{
"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 cycles that the head (oldest load) of the load buffer is stalled due to a DL1 miss.",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0x05",
"EventName": "LD_HEAD.L1_MISS",
"SampleAfterValue": "1000003",
"UMask": "0x1",
"Unit": "cpu_atom"
},
{
"BriefDescription": "Counts the number of cycles that the head (oldest load) of the load buffer and retirement are both stalled due to a DL1 miss.",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0x05",
"EventName": "LD_HEAD.L1_MISS_AT_RET",
"SampleAfterValue": "1000003",
"UMask": "0x81",
"Unit": "cpu_atom"
},
{
"BriefDescription": "Counts the number of cycles that the head (oldest load) of the load buffer is stalled due to other block cases.",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0x05",
"EventName": "LD_HEAD.OTHER",
"PublicDescription": "Counts the number of cycles that the head (oldest load) of the load buffer is stalled due to other block cases such as pipeline conflicts, fences, etc.",
"SampleAfterValue": "1000003",
"UMask": "0x40",
"Unit": "cpu_atom"
},
{
"BriefDescription": "Counts the number of cycles that the head (oldest load) of the load buffer and retirement are both stalled due to other block cases.",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0x05",
"EventName": "LD_HEAD.OTHER_AT_RET",
"PublicDescription": "Counts the number of cycles that the head (oldest load) of the load buffer and retirement are both stalled due to other block cases such as pipeline conflicts, fences, etc.",
"SampleAfterValue": "1000003",
"UMask": "0xc0",
"Unit": "cpu_atom"
},
{
"BriefDescription": "Counts the number of cycles that the head (oldest load) of the load buffer is stalled due to a pagewalk.",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0x05",
"EventName": "LD_HEAD.PGWALK",
"SampleAfterValue": "1000003",
"UMask": "0x20",
"Unit": "cpu_atom"
},
{
"BriefDescription": "Counts the number of cycles that the head (oldest load) of the load buffer and retirement are both stalled due to a pagewalk.",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0x05",
"EventName": "LD_HEAD.PGWALK_AT_RET",
"SampleAfterValue": "1000003",
"UMask": "0xa0",
"Unit": "cpu_atom"
},
{
"BriefDescription": "Counts the number of cycles that the head (oldest load) of the load buffer is stalled due to a store address match.",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0x05",
"EventName": "LD_HEAD.ST_ADDR",
"SampleAfterValue": "1000003",
"UMask": "0x4",
"Unit": "cpu_atom"
},
{
"BriefDescription": "Counts the number of cycles that the head (oldest load) of the load buffer and retirement are both stalled due to a store address match.",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0x05",
"EventName": "LD_HEAD.ST_ADDR_AT_RET",
"SampleAfterValue": "1000003",
"UMask": "0x84",
"Unit": "cpu_atom"
},
{
"BriefDescription": "Counts the number of cycles that the head (oldest load) of the load buffer is stalled due to store data forward block.",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0x05",
"EventName": "LD_HEAD.ST_DATA",
"SampleAfterValue": "1000003",
"UMask": "0x8",
"Unit": "cpu_atom"
},
{
"BriefDescription": "Counts the number of cycles that the head (oldest load) of the load buffer is stalled due to request buffers full or lock in progress.",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0x05",
"EventName": "LD_HEAD.WCB_FULL",
"SampleAfterValue": "1000003",
"UMask": "0x2",
"Unit": "cpu_atom"
},
{
"BriefDescription": "Counts the number of cycles that the head (oldest load) of the load buffer and retirement are both stalled due to request buffers full or lock in progress.",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0x05",
"EventName": "LD_HEAD.WCB_FULL_AT_RET",
"SampleAfterValue": "1000003",
"UMask": "0x82",
"Unit": "cpu_atom"
},
{
"BriefDescription": "Counts the number of memory ordering machine clears triggered due to a snoop from an external agent. Does not count internally generated machine clears such as those due to disambiguations.",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc3",
"EventName": "MACHINE_CLEARS.MEMORY_ORDERING",
"SampleAfterValue": "20003",
"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 the number of machine clears that flush the pipeline and restart the machine without the use of microcode.",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc3",
"EventName": "MACHINE_CLEARS.MEMORY_ORDERING_FAST",
"SampleAfterValue": "20003",
"UMask": "0x82",
"Unit": "cpu_atom"
},
{
"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",
"Data_LA": "1",
"EventCode": "0xcd",
"EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_1024",
"MSRIndex": "0x3F6",
"MSRValue": "0x400",
"PEBS": "2",
"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.",
"SampleAfterValue": "53",
"UMask": "0x1",
@@ -15,13 +170,12 @@
},
{
"BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 128 cycles.",
"Counter": "0,1,2,3,4,5,6,7,8,9",
"Counter": "2,3,4,5,6,7,8,9",
"Data_LA": "1",
"EventCode": "0xcd",
"EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_128",
"MSRIndex": "0x3F6",
"MSRValue": "0x80",
"PEBS": "2",
"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.",
"SampleAfterValue": "1009",
"UMask": "0x1",
@@ -29,13 +183,12 @@
},
{
"BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 16 cycles.",
"Counter": "0,1,2,3,4,5,6,7,8,9",
"Counter": "2,3,4,5,6,7,8,9",
"Data_LA": "1",
"EventCode": "0xcd",
"EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_16",
"MSRIndex": "0x3F6",
"MSRValue": "0x10",
"PEBS": "2",
"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.",
"SampleAfterValue": "20011",
"UMask": "0x1",
@@ -43,13 +196,12 @@
},
{
"BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 2048 cycles.",
"Counter": "0,1,2,3,4,5,6,7,8,9",
"Counter": "2,3,4,5,6,7,8,9",
"Data_LA": "1",
"EventCode": "0xcd",
"EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_2048",
"MSRIndex": "0x3F6",
"MSRValue": "0x800",
"PEBS": "2",
"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.",
"SampleAfterValue": "23",
"UMask": "0x1",
@@ -57,13 +209,12 @@
},
{
"BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 256 cycles.",
"Counter": "0,1,2,3,4,5,6,7,8,9",
"Counter": "2,3,4,5,6,7,8,9",
"Data_LA": "1",
"EventCode": "0xcd",
"EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_256",
"MSRIndex": "0x3F6",
"MSRValue": "0x100",
"PEBS": "2",
"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.",
"SampleAfterValue": "503",
"UMask": "0x1",
@@ -71,13 +222,12 @@
},
{
"BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 32 cycles.",
"Counter": "0,1,2,3,4,5,6,7,8,9",
"Counter": "2,3,4,5,6,7,8,9",
"Data_LA": "1",
"EventCode": "0xcd",
"EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_32",
"MSRIndex": "0x3F6",
"MSRValue": "0x20",
"PEBS": "2",
"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.",
"SampleAfterValue": "100007",
"UMask": "0x1",
@@ -85,13 +235,12 @@
},
{
"BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 4 cycles.",
"Counter": "0,1,2,3,4,5,6,7,8,9",
"Counter": "2,3,4,5,6,7,8,9",
"Data_LA": "1",
"EventCode": "0xcd",
"EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_4",
"MSRIndex": "0x3F6",
"MSRValue": "0x4",
"PEBS": "2",
"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.",
"SampleAfterValue": "100003",
"UMask": "0x1",
@@ -99,13 +248,12 @@
},
{
"BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 512 cycles.",
"Counter": "0,1,2,3,4,5,6,7,8,9",
"Counter": "2,3,4,5,6,7,8,9",
"Data_LA": "1",
"EventCode": "0xcd",
"EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_512",
"MSRIndex": "0x3F6",
"MSRValue": "0x200",
"PEBS": "2",
"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.",
"SampleAfterValue": "101",
"UMask": "0x1",
@@ -113,13 +261,12 @@
},
{
"BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 64 cycles.",
"Counter": "0,1,2,3,4,5,6,7,8,9",
"Counter": "2,3,4,5,6,7,8,9",
"Data_LA": "1",
"EventCode": "0xcd",
"EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_64",
"MSRIndex": "0x3F6",
"MSRValue": "0x40",
"PEBS": "2",
"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.",
"SampleAfterValue": "2003",
"UMask": "0x1",
@@ -127,13 +274,12 @@
},
{
"BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 8 cycles.",
"Counter": "0,1,2,3,4,5,6,7,8,9",
"Counter": "2,3,4,5,6,7,8,9",
"Data_LA": "1",
"EventCode": "0xcd",
"EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_8",
"MSRIndex": "0x3F6",
"MSRValue": "0x8",
"PEBS": "2",
"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.",
"SampleAfterValue": "50021",
"UMask": "0x1",
@@ -145,54 +291,112 @@
"Data_LA": "1",
"EventCode": "0xcd",
"EventName": "MEM_TRANS_RETIRED.STORE_SAMPLE",
"PEBS": "2",
"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",
"SampleAfterValue": "1000003",
"UMask": "0x2",
"Unit": "cpu_core"
},
{
"BriefDescription": "Counts cacheable demand data reads were not supplied by the L3 cache.",
"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",
"SampleAfterValue": "200003",
"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",
"SampleAfterValue": "200003",
"UMask": "0x4",
"Unit": "cpu_atom"
},
{
"BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were not supplied by the L3 cache and were supplied by the system memory (DRAM, MSC, or MMIO).",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xB7",
"EventName": "OCR.DEMAND_DATA_RD.L3_MISS",
"EventName": "OCR.DEMAND_CODE_RD.L3_MISS",
"MSRIndex": "0x1a6,0x1a7",
"MSRValue": "0x3FBFC00001",
"MSRValue": "0x13FBFC00004",
"SampleAfterValue": "100003",
"UMask": "0x1",
"Unit": "cpu_atom"
},
{
"BriefDescription": "Counts demand data reads that were not supplied by the L3 cache.",
"BriefDescription": "Counts demand data reads that were not supplied by the L3 cache and were supplied by the system memory (DRAM, MSC, or MMIO).",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xB7",
"EventName": "OCR.DEMAND_DATA_RD.L3_MISS",
"MSRIndex": "0x1a6,0x1a7",
"MSRValue": "0x13FBFC00001",
"SampleAfterValue": "100003",
"UMask": "0x1",
"Unit": "cpu_atom"
},
{
"BriefDescription": "Counts demand data reads that were not supplied by the L3 cache and were supplied by the system memory (DRAM, MSC, or MMIO).",
"Counter": "0,1,2,3",
"EventCode": "0x2A,0x2B",
"EventName": "OCR.DEMAND_DATA_RD.L3_MISS",
"MSRIndex": "0x1a6,0x1a7",
"MSRValue": "0xFE7F8000001",
"MSRValue": "0x9E7FA000001",
"SampleAfterValue": "100003",
"UMask": "0x1",
"Unit": "cpu_core"
},
{
"BriefDescription": "Counts demand reads for ownership, including SWPREFETCHW which is an RFO were not supplied by the L3 cache.",
"BriefDescription": "Counts demand read for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that were not supplied by the L3 cache and were supplied by the system memory (DRAM, MSC, or MMIO).",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xB7",
"EventName": "OCR.DEMAND_RFO.L3_MISS",
"MSRIndex": "0x1a6,0x1a7",
"MSRValue": "0x3FBFC00002",
"MSRValue": "0x13FBFC00002",
"SampleAfterValue": "100003",
"UMask": "0x1",
"Unit": "cpu_atom"
},
{
"BriefDescription": "Counts demand read for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that were not supplied by the L3 cache.",
"BriefDescription": "Counts demand read for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that were not supplied by the L3 cache and were supplied by the system memory (DRAM, MSC, or MMIO).",
"Counter": "0,1,2,3",
"EventCode": "0x2A,0x2B",
"EventName": "OCR.DEMAND_RFO.L3_MISS",
"MSRIndex": "0x1a6,0x1a7",
"MSRValue": "0xFE7F8000002",
"MSRValue": "0x9E7FA000002",
"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"
}
]

150
tools/perf/pmu-events/arch/x86/lunarlake/metricgroups.json Normal file
View File

@@ -0,0 +1,150 @@
{
"Backend": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
"Bad": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
"BadSpec": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
"BigFootprint": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
"BrMispredicts": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
"Branches": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
"BvBC": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
"BvBO": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
"BvCB": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
"BvFB": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
"BvIO": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
"BvMB": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
"BvML": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
"BvMP": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
"BvMS": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
"BvMT": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
"BvOB": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
"BvUW": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
"C0Wait": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
"CacheHits": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
"CacheMisses": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
"CodeGen": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
"Compute": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
"Cor": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
"DSB": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
"DSBmiss": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
"DataSharing": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
"Fed": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
"FetchBW": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
"FetchLat": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
"Flops": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
"FpScalar": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
"FpVector": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
"Frontend": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
"HPC": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
"IcMiss": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
"Ifetch": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
"InsType": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
"IntVector": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
"L2Evicts": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
"LSD": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
"Load_Store_Miss": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
"LockCont": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
"MachineClears": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
"Machine_Clears": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
"Mem": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
"MemOffcore": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
"Mem_Exec": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
"MemoryBW": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
"MemoryBound": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
"MemoryLat": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
"MemoryTLB": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
"Memory_BW": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
"Memory_Lat": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
"MicroSeq": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
"OS": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
"Offcore": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
"PGO": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
"Pipeline": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
"PortsUtil": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
"Power": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
"Prefetches": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
"Ret": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
"Retire": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
"SMT": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
"Server": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
"Snoop": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
"SoC": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
"Summary": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
"TmaL1": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
"TmaL2": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
"TmaL3mem": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
"TopdownL1": "Metrics for top-down breakdown at level 1",
"TopdownL2": "Metrics for top-down breakdown at level 2",
"TopdownL3": "Metrics for top-down breakdown at level 3",
"TopdownL4": "Metrics for top-down breakdown at level 4",
"TopdownL5": "Metrics for top-down breakdown at level 5",
"TopdownL6": "Metrics for top-down breakdown at level 6",
"load_store_bound": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
"tma_L1_group": "Metrics for top-down breakdown at level 1",
"tma_L2_group": "Metrics for top-down breakdown at level 2",
"tma_L3_group": "Metrics for top-down breakdown at level 3",
"tma_L4_group": "Metrics for top-down breakdown at level 4",
"tma_L5_group": "Metrics for top-down breakdown at level 5",
"tma_L6_group": "Metrics for top-down breakdown at level 6",
"tma_alu_op_utilization_group": "Metrics contributing to tma_alu_op_utilization category",
"tma_assists_group": "Metrics contributing to tma_assists category",
"tma_backend_bound_group": "Metrics contributing to tma_backend_bound category",
"tma_bad_speculation_group": "Metrics contributing to tma_bad_speculation category",
"tma_branch_mispredicts_group": "Metrics contributing to tma_branch_mispredicts category",
"tma_branch_resteers_group": "Metrics contributing to tma_branch_resteers category",
"tma_code_stlb_miss_group": "Metrics contributing to tma_code_stlb_miss category",
"tma_core_bound_group": "Metrics contributing to tma_core_bound category",
"tma_divider_group": "Metrics contributing to tma_divider category",
"tma_dram_bound_group": "Metrics contributing to tma_dram_bound category",
"tma_dtlb_load_group": "Metrics contributing to tma_dtlb_load category",
"tma_dtlb_store_group": "Metrics contributing to tma_dtlb_store category",
"tma_fetch_bandwidth_group": "Metrics contributing to tma_fetch_bandwidth category",
"tma_fetch_latency_group": "Metrics contributing to tma_fetch_latency category",
"tma_fp_arith_group": "Metrics contributing to tma_fp_arith category",
"tma_fp_vector_group": "Metrics contributing to tma_fp_vector category",
"tma_frontend_bound_group": "Metrics contributing to tma_frontend_bound category",
"tma_heavy_operations_group": "Metrics contributing to tma_heavy_operations category",
"tma_icache_misses_group": "Metrics contributing to tma_icache_misses category",
"tma_ifetch_bandwidth_group": "Metrics contributing to tma_ifetch_bandwidth category",
"tma_ifetch_latency_group": "Metrics contributing to tma_ifetch_latency category",
"tma_int_operations_group": "Metrics contributing to tma_int_operations category",
"tma_issue2P": "Metrics related by the issue $issue2P",
"tma_issueBM": "Metrics related by the issue $issueBM",
"tma_issueBW": "Metrics related by the issue $issueBW",
"tma_issueComp": "Metrics related by the issue $issueComp",
"tma_issueD0": "Metrics related by the issue $issueD0",
"tma_issueFB": "Metrics related by the issue $issueFB",
"tma_issueFL": "Metrics related by the issue $issueFL",
"tma_issueL1": "Metrics related by the issue $issueL1",
"tma_issueLat": "Metrics related by the issue $issueLat",
"tma_issueMC": "Metrics related by the issue $issueMC",
"tma_issueMS": "Metrics related by the issue $issueMS",
"tma_issueMV": "Metrics related by the issue $issueMV",
"tma_issueRFO": "Metrics related by the issue $issueRFO",
"tma_issueSL": "Metrics related by the issue $issueSL",
"tma_issueSO": "Metrics related by the issue $issueSO",
"tma_issueSmSt": "Metrics related by the issue $issueSmSt",
"tma_issueSpSt": "Metrics related by the issue $issueSpSt",
"tma_issueSyncxn": "Metrics related by the issue $issueSyncxn",
"tma_issueTLB": "Metrics related by the issue $issueTLB",
"tma_itlb_misses_group": "Metrics contributing to tma_itlb_misses category",
"tma_l1_bound_group": "Metrics contributing to tma_l1_bound category",
"tma_l2_bound_group": "Metrics contributing to tma_l2_bound category",
"tma_l3_bound_group": "Metrics contributing to tma_l3_bound category",
"tma_light_operations_group": "Metrics contributing to tma_light_operations category",
"tma_load_op_utilization_group": "Metrics contributing to tma_load_op_utilization category",
"tma_load_stlb_miss_group": "Metrics contributing to tma_load_stlb_miss category",
"tma_machine_clears_group": "Metrics contributing to tma_machine_clears category",
"tma_mem_latency_group": "Metrics contributing to tma_mem_latency category",
"tma_memory_bound_group": "Metrics contributing to tma_memory_bound category",
"tma_microcode_sequencer_group": "Metrics contributing to tma_microcode_sequencer category",
"tma_mite_group": "Metrics contributing to tma_mite category",
"tma_other_light_ops_group": "Metrics contributing to tma_other_light_ops category",
"tma_ports_utilization_group": "Metrics contributing to tma_ports_utilization category",
"tma_ports_utilized_0_group": "Metrics contributing to tma_ports_utilized_0 category",
"tma_ports_utilized_3m_group": "Metrics contributing to tma_ports_utilized_3m category",
"tma_resource_bound_group": "Metrics contributing to tma_resource_bound category",
"tma_retiring_group": "Metrics contributing to tma_retiring category",
"tma_serializing_operation_group": "Metrics contributing to tma_serializing_operation category",
"tma_store_bound_group": "Metrics contributing to tma_store_bound category",
"tma_store_op_utilization_group": "Metrics contributing to tma_store_op_utilization category",
"tma_store_stlb_miss_group": "Metrics contributing to tma_store_stlb_miss category"
}

496
tools/perf/pmu-events/arch/x86/lunarlake/other.json
View File

@@ -1,6 +1,345 @@
[
{
"BriefDescription": "Counts cacheable demand data reads Catch all value for any response types - this includes response types not define in the OCR. If this is set all other response types will be ignored",
"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 cycles where the pipeline is stalled due to serializing operations.",
"Counter": "0,1,2,3,4,5,6,7,8,9",
"EventCode": "0xa2",
"EventName": "BE_STALLS.SCOREBOARD",
"SampleAfterValue": "100003",
"UMask": "0x2",
"Unit": "cpu_core"
},
{
"BriefDescription": "Counts the number of unhalted cycles a Core is blocked due to a lock In Progress issued by another core",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0x63",
"EventName": "BUS_LOCK.BLOCKED_CYCLES",
"PublicDescription": "Counts the number of unhalted cycles a Core is blocked due to a lock In Progress issued by another core. Counts on a per core basis.",
"SampleAfterValue": "1000003",
"UMask": "0x1",
"Unit": "cpu_atom"
},
{
"BriefDescription": "Counts the number of unhalted cycles a Core is blocked due to an Accepted lock it issued, includes both split and non-split lock cycles.",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0x63",
"EventName": "BUS_LOCK.LOCK_CYCLES",
"PublicDescription": "Counts the number of unhalted cycles a Core is blocked due to an Accepted lock it issued, includes both split and non-split lock cycles. Counts on a per core basis.",
"SampleAfterValue": "1000003",
"UMask": "0x2",
"Unit": "cpu_atom"
},
{
"BriefDescription": "Counts the number of non-split locks such as UC locks issued by a Core (does not include cache locks)",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0x63",
"EventName": "BUS_LOCK.NON_SPLIT_LOCKS",
"SampleAfterValue": "1000003",
"UMask": "0x4",
"Unit": "cpu_atom"
},
{
"BriefDescription": "Counts the number of split locks issued by a Core",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0x63",
"EventName": "BUS_LOCK.SPLIT_LOCKS",
"SampleAfterValue": "1000003",
"UMask": "0x8",
"Unit": "cpu_atom"
},
{
"BriefDescription": "Count number of times a load is depending on another load that had just write back its data or in previous or 2 cycles back. This event supports in-direct dependency through a single uop.",
"Counter": "0,1,2,3,4,5,6,7,8,9",
"EventCode": "0x02",
"EventName": "DEPENDENT_LOADS.ANY",
"SampleAfterValue": "1000003",
"UMask": "0x7",
"Unit": "cpu_core"
},
{
"BriefDescription": "Counts the number of cycles the L2 Prefetchers are at throttle level 0",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0x32",
"EventName": "DYNAMIC_PREFETCH_THROTTLER.LEVEL0_SOC",
"SampleAfterValue": "1000003",
"UMask": "0x1",
"Unit": "cpu_atom"
},
{
"BriefDescription": "Counts the number of cycles the L2 Prefetcher throttle level is at 1",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0x32",
"EventName": "DYNAMIC_PREFETCH_THROTTLER.LEVEL1_SOC",
"SampleAfterValue": "1000003",
"UMask": "0x2",
"Unit": "cpu_atom"
},
{
"BriefDescription": "Counts the number of cycles the L2 Prefetcher throttle level is at 2",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0x32",
"EventName": "DYNAMIC_PREFETCH_THROTTLER.LEVEL2_SOC",
"SampleAfterValue": "1000003",
"UMask": "0x4",
"Unit": "cpu_atom"
},
{
"BriefDescription": "Counts the number of cycles the L2 Prefetcher throttle level is at 3",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0x32",
"EventName": "DYNAMIC_PREFETCH_THROTTLER.LEVEL3_SOC",
"SampleAfterValue": "1000003",
"UMask": "0x8",
"Unit": "cpu_atom"
},
{
"BriefDescription": "Counts the number of cycles the L2 Prefetcher throttle level is at 4",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0x32",
"EventName": "DYNAMIC_PREFETCH_THROTTLER.LEVEL4_SOC",
"SampleAfterValue": "1000003",
"UMask": "0x10",
"Unit": "cpu_atom"
},
{
"BriefDescription": "Counts the number of uops executed on all Integer ports.",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xb3",
"EventName": "INT_UOPS_EXECUTED.ALL",
"SampleAfterValue": "1000003",
"UMask": "0xff",
"Unit": "cpu_atom"
},
{
"BriefDescription": "Counts the number of uops executed on a load port.",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xb3",
"EventName": "INT_UOPS_EXECUTED.LD",
"PublicDescription": "Counts the number of uops executed on a load port. This event counts for integer uops even if the destination is FP/vector",
"SampleAfterValue": "1000003",
"UMask": "0x1",
"Unit": "cpu_atom"
},
{
"BriefDescription": "Counts the number of uops executed on integer port 0.",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xb3",
"EventName": "INT_UOPS_EXECUTED.P0",
"SampleAfterValue": "1000003",
"UMask": "0x8",
"Unit": "cpu_atom"
},
{
"BriefDescription": "Counts the number of uops executed on integer port 1.",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xb3",
"EventName": "INT_UOPS_EXECUTED.P1",
"SampleAfterValue": "1000003",
"UMask": "0x10",
"Unit": "cpu_atom"
},
{
"BriefDescription": "Counts the number of uops executed on integer port 2.",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xb3",
"EventName": "INT_UOPS_EXECUTED.P2",
"SampleAfterValue": "1000003",
"UMask": "0x20",
"Unit": "cpu_atom"
},
{
"BriefDescription": "Counts the number of uops executed on integer port 3.",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xb3",
"EventName": "INT_UOPS_EXECUTED.P3",
"SampleAfterValue": "1000003",
"UMask": "0x40",
"Unit": "cpu_atom"
},
{
"BriefDescription": "Counts the number of uops executed on integer port 0,1, 2, 3.",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xb3",
"EventName": "INT_UOPS_EXECUTED.PRIMARY",
"SampleAfterValue": "1000003",
"UMask": "0x78",
"Unit": "cpu_atom"
},
{
"BriefDescription": "Counts the number of uops executed on a Store address port.",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xb3",
"EventName": "INT_UOPS_EXECUTED.STA",
"PublicDescription": "Counts the number of uops executed on a Store address port. This event counts integer uops even if the data source is FP/vector",
"SampleAfterValue": "1000003",
"UMask": "0x2",
"Unit": "cpu_atom"
},
{
"BriefDescription": "Counts the number of uops executed on an integer store data and jump port.",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xb3",
"EventName": "INT_UOPS_EXECUTED.STD_JMP",
"SampleAfterValue": "1000003",
"UMask": "0x4",
"Unit": "cpu_atom"
},
{
"BriefDescription": "Counts the number of LLC prefetches that were throttled due to Dynamic Prefetch Throttling. The throttle requestor/source could be from the uncore/SOC or the Dead Block Predictor. Counts on a per core basis.",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0x29",
"EventName": "LLC_PREFETCHES_THROTTLED.DPT",
"SampleAfterValue": "1000003",
"UMask": "0x1",
"Unit": "cpu_atom"
},
{
"BriefDescription": "Counts the number of LLC prefetches throttled due to Demand Throttle Prefetcher. DTP Global Triggered with no Local Override. Counts on a per core basis.",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0x29",
"EventName": "LLC_PREFETCHES_THROTTLED.DTP",
"SampleAfterValue": "1000003",
"UMask": "0x2",
"Unit": "cpu_atom"
},
{
"BriefDescription": "Counts the number of LLC prefetches not throttled by DTP due to local override. These prefetches may still be throttled due to another throttler mechanism. Counts on a per core basis.",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0x29",
"EventName": "LLC_PREFETCHES_THROTTLED.DTP_OVERRIDE",
"SampleAfterValue": "1000003",
"UMask": "0x4",
"Unit": "cpu_atom"
},
{
"BriefDescription": "Counts the number of LLC prefetches throttled due to LLC hit rate in <insert knob name here>. Counts on a per core basis.",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0x29",
"EventName": "LLC_PREFETCHES_THROTTLED.HIT_RATE",
"SampleAfterValue": "1000003",
"UMask": "0x10",
"Unit": "cpu_atom"
},
{
"BriefDescription": "Counts the number of LLC prefetches throttled due to exceeding the XQ threshold set by either XQ_THRESOLD_DTP or LLC_XQ_THRESHOLD. Counts on a per core basis.",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0x29",
"EventName": "LLC_PREFETCHES_THROTTLED.XQ_THRESH",
"SampleAfterValue": "1000003",
"UMask": "0x8",
"Unit": "cpu_atom"
},
{
"BriefDescription": "Counts cycles where no execution is happening due to loads waiting for L1 cache (that is: no execution & load in flight & no load missed L1 cache)",
"Counter": "0,1,2,3,4,5,6,7,8,9",
"EventCode": "0x46",
"EventName": "MEMORY_STALLS.L1",
"SampleAfterValue": "1000003",
"UMask": "0x1",
"Unit": "cpu_core"
},
{
"BriefDescription": "Counts cycles where no execution is happening due to loads waiting for L2 cache (that is: no execution & load in flight & load missed L1 & no load missed L2 cache)",
"Counter": "0,1,2,3,4,5,6,7,8,9",
"EventCode": "0x46",
"EventName": "MEMORY_STALLS.L2",
"SampleAfterValue": "1000003",
"UMask": "0x2",
"Unit": "cpu_core"
},
{
"BriefDescription": "Counts cycles where no execution is happening due to loads waiting for L3 cache (that is: no execution & load in flight & load missed L1 & load missed L2 cache & no load missed L3 Cache)",
"Counter": "0,1,2,3,4,5,6,7,8,9",
"EventCode": "0x46",
"EventName": "MEMORY_STALLS.L3",
"SampleAfterValue": "1000003",
"UMask": "0x4",
"Unit": "cpu_core"
},
{
"BriefDescription": "Counts cycles where no execution is happening due to loads waiting for Memory (that is: no execution & load in flight & a load missed L3 cache)",
"Counter": "0,1,2,3,4,5,6,7,8,9",
"EventCode": "0x46",
"EventName": "MEMORY_STALLS.MEM",
"SampleAfterValue": "1000003",
"UMask": "0x8",
"Unit": "cpu_core"
},
{
"BriefDescription": "Counts all requests that have any type of response.",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xB7",
"EventName": "OCR.ALL_REQUESTS.ANY_RESPONSE",
"MSRIndex": "0x1a6,0x1a7",
"MSRValue": "0xFF0000001DFFF",
"SampleAfterValue": "100003",
"UMask": "0x1",
"Unit": "cpu_atom"
},
{
"BriefDescription": "Counts writebacks of modified cachelines that have any type of response.",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xB7",
"EventName": "OCR.COREWB_M.ANY_RESPONSE",
"MSRIndex": "0x1a6,0x1a7",
"MSRValue": "0x10008",
"SampleAfterValue": "100003",
"UMask": "0x1",
"Unit": "cpu_atom"
},
{
"BriefDescription": "Counts writebacks of non-modified cachelines that have any type of response.",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xB7",
"EventName": "OCR.COREWB_NONM.ANY_RESPONSE",
"MSRIndex": "0x1a6,0x1a7",
"MSRValue": "0x11000",
"SampleAfterValue": "100003",
"UMask": "0x1",
"Unit": "cpu_atom"
},
{
"BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that have any type of response.",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xB7",
"EventName": "OCR.DEMAND_CODE_RD.ANY_RESPONSE",
"MSRIndex": "0x1a6,0x1a7",
"MSRValue": "0x10004",
"SampleAfterValue": "100003",
"UMask": "0x1",
"Unit": "cpu_atom"
},
{
"BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were supplied by DRAM.",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xB7",
"EventName": "OCR.DEMAND_CODE_RD.DRAM",
"MSRIndex": "0x1a6,0x1a7",
"MSRValue": "0x1FBC000004",
"SampleAfterValue": "100003",
"UMask": "0x1",
"Unit": "cpu_atom"
},
{
"BriefDescription": "Counts demand data reads that have any type of response.",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xB7",
"EventName": "OCR.DEMAND_DATA_RD.ANY_RESPONSE",
@@ -22,7 +361,7 @@
"Unit": "cpu_core"
},
{
"BriefDescription": "Counts cacheable demand data reads were supplied by DRAM.",
"BriefDescription": "Counts demand data reads that were supplied by DRAM.",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xB7",
"EventName": "OCR.DEMAND_DATA_RD.DRAM",
@@ -44,7 +383,7 @@
"Unit": "cpu_core"
},
{
"BriefDescription": "Counts demand reads for ownership, including SWPREFETCHW which is an RFO Catch all value for any response types - this includes response types not define in the OCR. If this is set all other response types will be ignored",
"BriefDescription": "Counts demand read for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that have any type of response.",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xB7",
"EventName": "OCR.DEMAND_RFO.ANY_RESPONSE",
@@ -64,5 +403,156 @@
"SampleAfterValue": "100003",
"UMask": "0x1",
"Unit": "cpu_core"
},
{
"BriefDescription": "Counts demand read for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that were supplied by DRAM.",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xB7",
"EventName": "OCR.DEMAND_RFO.DRAM",
"MSRIndex": "0x1a6,0x1a7",
"MSRValue": "0x1FBC000002",
"SampleAfterValue": "100003",
"UMask": "0x1",
"Unit": "cpu_atom"
},
{
"BriefDescription": "Counts full streaming stores (64 bytes, WCiLF) that have any type of response.",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xB7",
"EventName": "OCR.FULL_STREAMING_WR.ANY_RESPONSE",
"MSRIndex": "0x1a6,0x1a7",
"MSRValue": "0x800000010000",
"SampleAfterValue": "100003",
"UMask": "0x1",
"Unit": "cpu_atom"
},
{
"BriefDescription": "Counts partial streaming stores (less than 64 bytes, WCiL) that have any type of response.",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xB7",
"EventName": "OCR.PARTIAL_STREAMING_WR.ANY_RESPONSE",
"MSRIndex": "0x1a6,0x1a7",
"MSRValue": "0x400000010000",
"SampleAfterValue": "100003",
"UMask": "0x1",
"Unit": "cpu_atom"
},
{
"BriefDescription": "Counts streaming stores that have any type of response.",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xB7",
"EventName": "OCR.STREAMING_WR.ANY_RESPONSE",
"MSRIndex": "0x1a6,0x1a7",
"MSRValue": "0x10800",
"SampleAfterValue": "100003",
"UMask": "0x1",
"Unit": "cpu_atom"
},
{
"BriefDescription": "Counts streaming stores that have any type of response.",
"Counter": "0,1,2,3",
"EventCode": "0x2A,0x2B",
"EventName": "OCR.STREAMING_WR.ANY_RESPONSE",
"MSRIndex": "0x1a6,0x1a7",
"MSRValue": "0x10800",
"SampleAfterValue": "100003",
"UMask": "0x1",
"Unit": "cpu_core"
},
{
"BriefDescription": "Cycles when Reservation Station (RS) is empty for the thread.",
"Counter": "0,1,2,3,4,5,6,7,8,9",
"EventCode": "0xa5",
"EventName": "RS.EMPTY",
"PublicDescription": "Counts cycles during which the reservation station (RS) is empty for this logical processor. This is usually caused when the front-end pipeline runs into starvation periods (e.g. branch mispredictions or i-cache misses)",
"SampleAfterValue": "1000003",
"UMask": "0x7",
"Unit": "cpu_core"
},
{
"BriefDescription": "Counts end of periods where the Reservation Station (RS) was empty.",
"Counter": "0,1,2,3,4,5,6,7,8,9",
"CounterMask": "1",
"EdgeDetect": "1",
"EventCode": "0xa5",
"EventName": "RS.EMPTY_COUNT",
"Invert": "1",
"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)",
"SampleAfterValue": "100003",
"UMask": "0x7",
"Unit": "cpu_core"
},
{
"BriefDescription": "Cycles when RS was empty and a resource allocation stall is asserted",
"Counter": "0,1,2,3,4,5,6,7,8,9",
"EventCode": "0xa5",
"EventName": "RS.EMPTY_RESOURCE",
"SampleAfterValue": "1000003",
"UMask": "0x1",
"Unit": "cpu_core"
},
{
"BriefDescription": "Counts the number of issue slots in a UMWAIT or TPAUSE instruction where no uop issues due to the instruction putting the CPU into the C0.1 activity state.",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0x75",
"EventName": "SERIALIZATION.C01_MS_SCB",
"SampleAfterValue": "1000003",
"UMask": "0x4",
"Unit": "cpu_atom"
},
{
"BriefDescription": "Counts the number issue slots not consumed due to a color request for an FCW or MXCSR control register when all 4 colors (copies) are already in use",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0x75",
"EventName": "SERIALIZATION.COLOR_STALLS",
"SampleAfterValue": "1000003",
"UMask": "0x8",
"Unit": "cpu_atom"
},
{
"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"
},
{
"BriefDescription": "Counts the number of prefetch requests that were promoted in the XQ to a demand request.",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xf4",
"EventName": "XQ_PROMOTION.ALL",
"SampleAfterValue": "1000003",
"Unit": "cpu_atom"
},
{
"BriefDescription": "Counts the number of prefetch requests that were promoted in the XQ to a demand code read.",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xf4",
"EventName": "XQ_PROMOTION.CRDS",
"SampleAfterValue": "1000003",
"UMask": "0x4",
"Unit": "cpu_atom"
},
{
"BriefDescription": "Counts the number of prefetch requests that were promoted in the XQ to a demand read.",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xf4",
"EventName": "XQ_PROMOTION.DRDS",
"SampleAfterValue": "1000003",
"UMask": "0x1",
"Unit": "cpu_atom"
},
{
"BriefDescription": "Counts the number of prefetch requests that were promoted in the XQ to a demand RFO.",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xf4",
"EventName": "XQ_PROMOTION.RFOS",
"SampleAfterValue": "1000003",
"UMask": "0x2",
"Unit": "cpu_atom"
}
]

1743
tools/perf/pmu-events/arch/x86/lunarlake/pipeline.json
View File

File diff suppressed because it is too large Load Diff

36
tools/perf/pmu-events/arch/x86/lunarlake/uncore-memory.json Normal file
View File

@@ -0,0 +1,36 @@
[
{
"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": "Any Rank at Hot state",
"Counter": "0,1,2,3,4",
"EventCode": "0x19",
"EventName": "UNC_M_DRAM_THERMAL_HOT",
"Experimental": "1",
"PerPkg": "1",
"Unit": "iMC"
},
{
"BriefDescription": "Any Rank at Warm state",
"Counter": "0,1,2,3,4",
"EventCode": "0x1A",
"EventName": "UNC_M_DRAM_THERMAL_WARM",
"Experimental": "1",
"PerPkg": "1",
"Unit": "iMC"
}
]

428
tools/perf/pmu-events/arch/x86/lunarlake/virtual-memory.json
View File

@@ -1,4 +1,70 @@
[
{
"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": "200003",
"UMask": "0x1",
"Unit": "cpu_atom"
},
{
"BriefDescription": "Counts walks that miss the PDE_CACHE",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0x08",
"EventName": "DTLB_LOAD_MISSES.PDE_CACHE_MISS",
"SampleAfterValue": "200003",
"UMask": "0x80",
"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": "200003",
"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": "Counts the number of first level TLB misses but second level hits due to a demand load that did not start a page walk. Account for 4k page size only. 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_4K",
"SampleAfterValue": "200003",
"UMask": "0x20",
"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. Account for large page sizes only. 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_LGPG",
"SampleAfterValue": "200003",
"UMask": "0x40",
"Unit": "cpu_atom"
},
{
"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 +85,125 @@
"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": "Counts the number of page walks completed due to load DTLB misses to a 2M or 4M page.",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0x08",
"EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M",
"PublicDescription": "Counts the number of page walks completed due to loads (including SW prefetches) whose address translations missed in all Translation Lookaside Buffer (TLB) levels and were mapped to 2M or 4M pages. Includes page walks that page fault.",
"SampleAfterValue": "200003",
"UMask": "0x4",
"Unit": "cpu_atom"
},
{
"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": "Counts the number of page walks completed due to load DTLB misses to a 4K page.",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0x08",
"EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED_4K",
"PublicDescription": "Counts the number of page walks completed due to loads (including SW prefetches) whose address translations missed in all Translation Lookaside Buffer (TLB) levels and were mapped to 4K pages. Includes page walks that page fault.",
"SampleAfterValue": "200003",
"UMask": "0x2",
"Unit": "cpu_atom"
},
{
"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": "Counts the number of page walks outstanding for Loads (demand or SW prefetch) in PMH every cycle.",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0x08",
"EventName": "DTLB_LOAD_MISSES.WALK_PENDING",
"PublicDescription": "Counts the number of page walks outstanding for Loads (demand or SW prefetch) 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.",
"SampleAfterValue": "200003",
"UMask": "0x10",
"Unit": "cpu_atom"
},
{
"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": "2000003",
"UMask": "0x1",
"Unit": "cpu_atom"
},
{
"BriefDescription": "Counts walks that miss the PDE_CACHE",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0x49",
"EventName": "DTLB_STORE_MISSES.PDE_CACHE_MISS",
"SampleAfterValue": "2000003",
"UMask": "0x80",
"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": "2000003",
"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 +224,134 @@
"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": "Counts the number of page walks completed due to store DTLB misses to a 2M or 4M page.",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0x49",
"EventName": "DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M",
"PublicDescription": "Counts the number of page walks completed due to stores whose address translations missed in all Translation Lookaside Buffer (TLB) levels and were mapped to 2M or 4M pages. Includes page walks that page fault.",
"SampleAfterValue": "2000003",
"UMask": "0x4",
"Unit": "cpu_atom"
},
{
"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": "Counts the number of page walks completed due to store DTLB misses to a 4K page.",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0x49",
"EventName": "DTLB_STORE_MISSES.WALK_COMPLETED_4K",
"PublicDescription": "Counts the number of page walks completed due to stores whose address translations missed in all Translation Lookaside Buffer (TLB) levels and were mapped to 4K pages. Includes page walks that page fault.",
"SampleAfterValue": "2000003",
"UMask": "0x2",
"Unit": "cpu_atom"
},
{
"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": "Counts the number of page walks outstanding in the page miss handler (PMH) for stores every cycle.",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0x49",
"EventName": "DTLB_STORE_MISSES.WALK_PENDING",
"PublicDescription": "Counts the number of page walks outstanding in the page miss handler (PMH) for stores 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.",
"SampleAfterValue": "200003",
"UMask": "0x10",
"Unit": "cpu_atom"
},
{
"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 times there was an ITLB miss and a new translation was filled into the ITLB.",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0x81",
"EventName": "ITLB.FILLS",
"PublicDescription": "Counts the number of times the machine was unable to find a translation in the Instruction Translation Lookaside Buffer (ITLB) and a new translation was filled into the ITLB. The event is speculative in nature, but will not count translations (page walks) that are begun and not finished, or translations that are finished but not filled into the ITLB.",
"SampleAfterValue": "200003",
"UMask": "0x4",
"Unit": "cpu_atom"
},
{
"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": "2000003",
"UMask": "0x1",
"Unit": "cpu_atom"
},
{
"BriefDescription": "Counts walks that miss the PDE_CACHE",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0x85",
"EventName": "ITLB_MISSES.PDE_CACHE_MISS",
"SampleAfterValue": "2000003",
"UMask": "0x80",
"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": "2000003",
"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 +371,120 @@
"SampleAfterValue": "100003",
"UMask": "0xe",
"Unit": "cpu_core"
},
{
"BriefDescription": "Counts the number of page walks completed due to instruction fetch misses to a 2M or 4M page.",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0x85",
"EventName": "ITLB_MISSES.WALK_COMPLETED_2M_4M",
"PublicDescription": "Counts the number of page walks completed due to instruction fetches whose address translations missed in all Translation Lookaside Buffer (TLB) levels and were mapped to 2M or 4M pages. Includes page walks that page fault.",
"SampleAfterValue": "2000003",
"UMask": "0x4",
"Unit": "cpu_atom"
},
{
"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": "Counts the number of page walks completed due to instruction fetch misses to a 4K page.",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0x85",
"EventName": "ITLB_MISSES.WALK_COMPLETED_4K",
"PublicDescription": "Counts the number of page walks completed due to instruction fetches whose address translations missed in all Translation Lookaside Buffer (TLB) levels and were mapped to 4K pages. Includes page walks that page fault.",
"SampleAfterValue": "2000003",
"UMask": "0x2",
"Unit": "cpu_atom"
},
{
"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": "200003",
"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 occurrences a load gets blocked because of a micro TLB miss",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0x03",
"EventName": "LD_BLOCKS.DTLB_MISS",
"SampleAfterValue": "1000003",
"UMask": "0x8",
"Unit": "cpu_atom"
},
{
"BriefDescription": "Counts the number of cycles that the head (oldest load) of the load buffer is stalled due to a DTLB miss",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0x05",
"EventName": "LD_HEAD.DTLB_MISS",
"SampleAfterValue": "1000003",
"UMask": "0x10",
"Unit": "cpu_atom"
},
{
"BriefDescription": "Counts the number of cycles that the head (oldest load) of the load buffer and retirement are both stalled due to a DTLB miss.",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0x05",
"EventName": "LD_HEAD.DTLB_MISS_AT_RET",
"SampleAfterValue": "1000003",
"UMask": "0x90",
"Unit": "cpu_atom"
},
{
"BriefDescription": "Counts the number of PMH walks that hit in the L1 or WCBs",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xbc",
"EventName": "PAGE_WALKER_LOADS.DTLB_L1_HIT",
"SampleAfterValue": "1000003",
"UMask": "0x1",
"Unit": "cpu_atom"
},
{
"BriefDescription": "Counts the number of PMH walks that hit in the L2",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xbc",
"EventName": "PAGE_WALKER_LOADS.DTLB_L2_HIT",
"PublicDescription": "Counts the number of PMH walks that hit in the L2. Includes L2 Hit resulting from and L1D eviction of another core in the same module which is longer latency than a typical L2 hit.",
"SampleAfterValue": "1000003",
"UMask": "0x2",
"Unit": "cpu_atom"
},
{
"BriefDescription": "Count number of any STLB flush attempts (Entire, PCID, InvPage, CR3 write, etc)",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xbd",
"EventName": "TLB_FLUSHES.STLB_ANY",
"SampleAfterValue": "20003",
"UMask": "0x20",
"Unit": "cpu_atom"
}
]

2
tools/perf/pmu-events/arch/x86/mapfile.csv
View File

@@ -22,7 +22,7 @@ GenuineIntel-6-3A,v24,ivybridge,core
GenuineIntel-6-3E,v24,ivytown,core
GenuineIntel-6-2D,v24,jaketown,core
GenuineIntel-6-(57|85),v16,knightslanding,core
GenuineIntel-6-BD,v1.01,lunarlake,core
GenuineIntel-6-BD,v1.11,lunarlake,core
GenuineIntel-6-A[AC],v1.10,meteorlake,core
GenuineIntel-6-1[AEF],v4,nehalemep,core
GenuineIntel-6-2E,v4,nehalemex,core
1 Family-model Version Filename EventType
22 GenuineIntel-6-3E v24 ivytown core
23 GenuineIntel-6-2D v24 jaketown core
24 GenuineIntel-6-(57|85) v16 knightslanding core
25 GenuineIntel-6-BD v1.01 v1.11 lunarlake core
26 GenuineIntel-6-A[AC] v1.10 meteorlake core
27 GenuineIntel-6-1[AEF] v4 nehalemep core
28 GenuineIntel-6-2E v4 nehalemex core