Skip to contentSkip to conversation

Fix perf on Intel hybrid CPUs

PATCH In review Ian Rogers 3 participants 58 messages May 2, 2023 – May 16, 2023 perf events Page 2 of 2

lore
Share & tools
lore
author reviewer
#44 lore raw

PATCH v4 40/44 perf vendor events intel: Correct alderlake metrics

In reply to Ian Rogers

Fix the metrics tma_memory_bound on alderlake cpu_core and tma_microcode_sequencer on alderlake cpu_atom, where metrics had be rewritten across PMUs. Fix MEM_BOUND_STALLS_AT_RET_CORRECTION which is an aux metric but lacks a hash prefix. Add PMU prefixes for cpu_core/cpu_atom events to avoid wildcard opening the events.

---
 .../arch/x86/alderlake/adl-metrics.json       | 238 +++++++++---------
 .../arch/x86/alderlaken/adln-metrics.json     |   6 +-
 2 files changed, 122 insertions(+), 122 deletions(-)
tools/perf/pmu-events/arch/x86/alderlake/adl-metrics.json +119 -119
index 4c2a14ea5a1c..840f6f6fc8c5 100644
@@ -151,7 +151,7 @@
     },
     {
         "BriefDescription": "Counts the total number of issue slots that were not consumed by the backend because allocation is stalled due to a mispredicted jump or a machine clear",
-        "MetricExpr": "(tma_info_slots - (TOPDOWN_FE_BOUND.ALL + TOPDOWN_BE_BOUND.ALL + TOPDOWN_RETIRING.ALL)) / tma_info_slots",
+        "MetricExpr": "(tma_info_slots - (cpu_atom@TOPDOWN_FE_BOUND.ALL@ + cpu_atom@TOPDOWN_BE_BOUND.ALL@ + cpu_atom@TOPDOWN_RETIRING.ALL@)) / tma_info_slots",
         "MetricGroup": "TopdownL1;tma_L1_group",
         "MetricName": "tma_bad_speculation",
         "MetricThreshold": "tma_bad_speculation > 0.15",
@@ -162,7 +162,7 @@
     },
     {
         "BriefDescription": "Counts the number of uops that are not from the microsequencer.",
-        "MetricExpr": "(TOPDOWN_RETIRING.ALL - UOPS_RETIRED.MS) / tma_info_slots",
+        "MetricExpr": "(cpu_atom@TOPDOWN_RETIRING.ALL@ - cpu_atom@UOPS_RETIRED.MS@) / tma_info_slots",
         "MetricGroup": "TopdownL2;tma_L2_group;tma_retiring_group",
         "MetricName": "tma_base",
         "MetricThreshold": "tma_base > 0.6",
@@ -229,7 +229,7 @@
     },
     {
         "BriefDescription": "Counts the number of machine clears relative to the number of nuke slots due to memory disambiguation.",
-        "MetricExpr": "tma_nuke * (MACHINE_CLEARS.DISAMBIGUATION / MACHINE_CLEARS.SLOW)",
+        "MetricExpr": "tma_nuke * (cpu_atom@MACHINE_CLEARS.DISAMBIGUATION@ / cpu_atom@MACHINE_CLEARS.SLOW@)",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_nuke_group",
         "MetricName": "tma_disambiguation",
         "MetricThreshold": "tma_disambiguation > 0.02",
@@ -239,7 +239,7 @@
     {
         "BriefDescription": "Counts the number of cycles the core is stalled due to a demand load miss which hit in DRAM or MMIO (Non-DRAM).",
         "MetricConstraint": "NO_GROUP_EVENTS",
-        "MetricExpr": "MEM_BOUND_STALLS.LOAD_DRAM_HIT / tma_info_clks - MEM_BOUND_STALLS_AT_RET_CORRECTION * MEM_BOUND_STALLS.LOAD_DRAM_HIT / MEM_BOUND_STALLS.LOAD",
+        "MetricExpr": "cpu_atom@MEM_BOUND_STALLS.LOAD_DRAM_HIT@ / tma_info_clks - max((cpu_atom@MEM_BOUND_STALLS.LOAD@ - cpu_atom@LD_HEAD.L1_MISS_AT_RET@) / tma_info_clks, 0) * cpu_atom@MEM_BOUND_STALLS.LOAD_DRAM_HIT@ / cpu_atom@MEM_BOUND_STALLS.LOAD@",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_memory_bound_group",
         "MetricName": "tma_dram_bound",
         "MetricThreshold": "tma_dram_bound > 0.1",
@@ -277,7 +277,7 @@
     },
     {
         "BriefDescription": "Counts the number of machine clears relative to the number of nuke slots due to FP assists.",
-        "MetricExpr": "tma_nuke * (MACHINE_CLEARS.FP_ASSIST / MACHINE_CLEARS.SLOW)",
+        "MetricExpr": "tma_nuke * (cpu_atom@MACHINE_CLEARS.FP_ASSIST@ / cpu_atom@MACHINE_CLEARS.SLOW@)",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_nuke_group",
         "MetricName": "tma_fp_assist",
         "MetricThreshold": "tma_fp_assist > 0.02",
@@ -314,7 +314,7 @@
     },
     {
         "BriefDescription": "Percentage of total non-speculative loads with a address aliasing block",
-        "MetricExpr": "100 * LD_BLOCKS.4K_ALIAS / MEM_UOPS_RETIRED.ALL_LOADS",
+        "MetricExpr": "100 * cpu_atom@LD_BLOCKS.4K_ALIAS@ / MEM_UOPS_RETIRED.ALL_LOADS",
         "MetricName": "tma_info_address_alias_blocks",
         "Unit": "cpu_atom"
     },
@@ -334,14 +334,14 @@
     },
     {
         "BriefDescription": "",
-        "MetricExpr": "CPU_CLK_UNHALTED.CORE",
+        "MetricExpr": "cpu_atom@CPU_CLK_UNHALTED.CORE@",
         "MetricGroup": " ",
         "MetricName": "tma_info_clks",
         "Unit": "cpu_atom"
     },
     {
         "BriefDescription": "",
-        "MetricExpr": "CPU_CLK_UNHALTED.CORE_P",
+        "MetricExpr": "cpu_atom@CPU_CLK_UNHALTED.CORE_P@",
         "MetricGroup": " ",
         "MetricName": "tma_info_clks_p",
         "Unit": "cpu_atom"
@@ -383,35 +383,35 @@
     },
     {
         "BriefDescription": "Percentage of all uops which are FPDiv uops",
-        "MetricExpr": "100 * UOPS_RETIRED.FPDIV / UOPS_RETIRED.ALL",
+        "MetricExpr": "100 * cpu_atom@UOPS_RETIRED.FPDIV@ / UOPS_RETIRED.ALL",
         "MetricGroup": " ",
         "MetricName": "tma_info_fpdiv_uop_ratio",
         "Unit": "cpu_atom"
     },
     {
         "BriefDescription": "Percentage of all uops which are IDiv uops",
-        "MetricExpr": "100 * UOPS_RETIRED.IDIV / UOPS_RETIRED.ALL",
+        "MetricExpr": "100 * cpu_atom@UOPS_RETIRED.IDIV@ / UOPS_RETIRED.ALL",
         "MetricGroup": " ",
         "MetricName": "tma_info_idiv_uop_ratio",
         "Unit": "cpu_atom"
     },
     {
         "BriefDescription": "Percent of instruction miss cost that hit in DRAM",
-        "MetricExpr": "100 * MEM_BOUND_STALLS.IFETCH_DRAM_HIT / MEM_BOUND_STALLS.IFETCH",
+        "MetricExpr": "100 * cpu_atom@MEM_BOUND_STALLS.IFETCH_DRAM_HIT@ / cpu_atom@MEM_BOUND_STALLS.IFETCH@",
         "MetricGroup": " ",
         "MetricName": "tma_info_inst_miss_cost_dramhit_percent",
         "Unit": "cpu_atom"
     },
     {
         "BriefDescription": "Percent of instruction miss cost that hit in the L2",
-        "MetricExpr": "100 * MEM_BOUND_STALLS.IFETCH_L2_HIT / MEM_BOUND_STALLS.IFETCH",
+        "MetricExpr": "100 * cpu_atom@MEM_BOUND_STALLS.IFETCH_L2_HIT@ / cpu_atom@MEM_BOUND_STALLS.IFETCH@",
         "MetricGroup": " ",
         "MetricName": "tma_info_inst_miss_cost_l2hit_percent",
         "Unit": "cpu_atom"
     },
     {
         "BriefDescription": "Percent of instruction miss cost that hit in the L3",
-        "MetricExpr": "100 * MEM_BOUND_STALLS.IFETCH_LLC_HIT / MEM_BOUND_STALLS.IFETCH",
+        "MetricExpr": "100 * cpu_atom@MEM_BOUND_STALLS.IFETCH_LLC_HIT@ / cpu_atom@MEM_BOUND_STALLS.IFETCH@",
         "MetricGroup": " ",
         "MetricName": "tma_info_inst_miss_cost_l3hit_percent",
         "Unit": "cpu_atom"
@@ -439,7 +439,7 @@
     },
     {
         "BriefDescription": "Instructions per Far Branch",
-        "MetricExpr": "INST_RETIRED.ANY / (BR_INST_RETIRED.FAR_BRANCH / 2)",
+        "MetricExpr": "INST_RETIRED.ANY / (cpu_atom@BR_INST_RETIRED.FAR_BRANCH@ / 2)",
         "MetricGroup": " ",
         "MetricName": "tma_info_ipfarbranch",
         "Unit": "cpu_atom"
@@ -453,7 +453,7 @@
     },
     {
         "BriefDescription": "Instructions per retired conditional Branch Misprediction where the branch was not taken",
-        "MetricExpr": "INST_RETIRED.ANY / (BR_MISP_RETIRED.COND - BR_MISP_RETIRED.COND_TAKEN)",
+        "MetricExpr": "INST_RETIRED.ANY / (cpu_atom@BR_MISP_RETIRED.COND@ - cpu_atom@BR_MISP_RETIRED.COND_TAKEN@)",
         "MetricName": "tma_info_ipmisp_cond_ntaken",
         "Unit": "cpu_atom"
     },
@@ -498,20 +498,20 @@
     },
     {
         "BriefDescription": "Percentage of total non-speculative loads that are splits",
-        "MetricExpr": "100 * MEM_UOPS_RETIRED.SPLIT_LOADS / MEM_UOPS_RETIRED.ALL_LOADS",
+        "MetricExpr": "100 * cpu_atom@MEM_UOPS_RETIRED.SPLIT_LOADS@ / MEM_UOPS_RETIRED.ALL_LOADS",
         "MetricName": "tma_info_load_splits",
         "Unit": "cpu_atom"
     },
     {
         "BriefDescription": "load ops retired per 1000 instruction",
-        "MetricExpr": "1e3 * MEM_UOPS_RETIRED.ALL_LOADS / INST_RETIRED.ANY",
+        "MetricExpr": "1e3 * cpu_atom@MEM_UOPS_RETIRED.ALL_LOADS@ / INST_RETIRED.ANY",
         "MetricGroup": " ",
         "MetricName": "tma_info_memloadpki",
         "Unit": "cpu_atom"
     },
     {
         "BriefDescription": "Percentage of all uops which are ucode ops",
-        "MetricExpr": "100 * UOPS_RETIRED.MS / UOPS_RETIRED.ALL",
+        "MetricExpr": "100 * cpu_atom@UOPS_RETIRED.MS@ / UOPS_RETIRED.ALL",
         "MetricGroup": " ",
         "MetricName": "tma_info_microcode_uop_ratio",
         "Unit": "cpu_atom"
@@ -525,7 +525,7 @@
     },
     {
         "BriefDescription": "Percentage of total non-speculative loads with a store forward or unknown store address block",
-        "MetricExpr": "100 * LD_BLOCKS.DATA_UNKNOWN / MEM_UOPS_RETIRED.ALL_LOADS",
+        "MetricExpr": "100 * cpu_atom@LD_BLOCKS.DATA_UNKNOWN@ / MEM_UOPS_RETIRED.ALL_LOADS",
         "MetricName": "tma_info_store_fwd_blocks",
         "Unit": "cpu_atom"
     },
@@ -545,7 +545,7 @@
     },
     {
         "BriefDescription": "Percentage of all uops which are x87 uops",
-        "MetricExpr": "100 * UOPS_RETIRED.X87 / UOPS_RETIRED.ALL",
+        "MetricExpr": "100 * cpu_atom@UOPS_RETIRED.X87@ / UOPS_RETIRED.ALL",
         "MetricGroup": " ",
         "MetricName": "tma_info_x87_uop_ratio",
         "Unit": "cpu_atom"
@@ -571,7 +571,7 @@
     {
         "BriefDescription": "Counts the number of cycles a core is stalled due to a demand load which hit in the L2 Cache.",
         "MetricConstraint": "NO_GROUP_EVENTS",
-        "MetricExpr": "MEM_BOUND_STALLS.LOAD_L2_HIT / tma_info_clks - MEM_BOUND_STALLS_AT_RET_CORRECTION * MEM_BOUND_STALLS.LOAD_L2_HIT / MEM_BOUND_STALLS.LOAD",
+        "MetricExpr": "cpu_atom@MEM_BOUND_STALLS.LOAD_L2_HIT@ / tma_info_clks - max((cpu_atom@MEM_BOUND_STALLS.LOAD@ - cpu_atom@LD_HEAD.L1_MISS_AT_RET@) / tma_info_clks, 0) * cpu_atom@MEM_BOUND_STALLS.LOAD_L2_HIT@ / cpu_atom@MEM_BOUND_STALLS.LOAD@",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_memory_bound_group",
         "MetricName": "tma_l2_bound",
         "MetricThreshold": "tma_l2_bound > 0.1",
@@ -580,7 +580,7 @@
     },
     {
         "BriefDescription": "Counts the number of cycles a core is stalled due to a demand load which hit in the Last Level Cache (LLC) or other core with HITE/F/M.",
-        "MetricExpr": "MEM_BOUND_STALLS.LOAD_LLC_HIT / tma_info_clks - MEM_BOUND_STALLS_AT_RET_CORRECTION * MEM_BOUND_STALLS.LOAD_LLC_HIT / MEM_BOUND_STALLS.LOAD",
+        "MetricExpr": "cpu_atom@MEM_BOUND_STALLS.LOAD_LLC_HIT@ / tma_info_clks - max((cpu_atom@MEM_BOUND_STALLS.LOAD@ - cpu_atom@LD_HEAD.L1_MISS_AT_RET@) / tma_info_clks, 0) * cpu_atom@MEM_BOUND_STALLS.LOAD_LLC_HIT@ / cpu_atom@MEM_BOUND_STALLS.LOAD@",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_memory_bound_group",
         "MetricName": "tma_l3_bound",
         "MetricThreshold": "tma_l3_bound > 0.1",
@@ -589,7 +589,7 @@
     },
     {
         "BriefDescription": "Counts the number of cycles, relative to the number of mem_scheduler slots, in which uops are blocked due to load buffer full",
-        "MetricExpr": "tma_mem_scheduler * MEM_SCHEDULER_BLOCK.LD_BUF / MEM_SCHEDULER_BLOCK.ALL",
+        "MetricExpr": "tma_mem_scheduler * cpu_atom@MEM_SCHEDULER_BLOCK.LD_BUF@ / MEM_SCHEDULER_BLOCK.ALL",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_mem_scheduler_group",
         "MetricName": "tma_ld_buffer",
         "MetricThreshold": "tma_ld_buffer > 0.05",
@@ -617,7 +617,7 @@
     },
     {
         "BriefDescription": "Counts the number of cycles the core is stalled due to stores or loads.",
-        "MetricExpr": "min(tma_backend_bound, LD_HEAD.ANY_AT_RET / tma_info_clks + tma_store_bound)",
+        "MetricExpr": "min(cpu_atom@TOPDOWN_BE_BOUND.ALL@ / tma_info_slots, cpu_atom@LD_HEAD.ANY_AT_RET@ / tma_info_clks + tma_store_bound)",
         "MetricGroup": "TopdownL2;tma_L2_group;tma_backend_bound_group",
         "MetricName": "tma_memory_bound",
         "MetricThreshold": "tma_memory_bound > 0.2",
@@ -627,7 +627,7 @@
     },
     {
         "BriefDescription": "Counts the number of machine clears relative to the number of nuke slots due to memory ordering.",
-        "MetricExpr": "tma_nuke * (MACHINE_CLEARS.MEMORY_ORDERING / MACHINE_CLEARS.SLOW)",
+        "MetricExpr": "tma_nuke * (cpu_atom@MACHINE_CLEARS.MEMORY_ORDERING@ / cpu_atom@MACHINE_CLEARS.SLOW@)",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_nuke_group",
         "MetricName": "tma_memory_ordering",
         "MetricThreshold": "tma_memory_ordering > 0.02",
@@ -636,7 +636,7 @@
     },
     {
         "BriefDescription": "Counts the number of uops that are from the complex flows issued by the micro-sequencer (MS)",
-        "MetricExpr": "tma_microcode_sequencer",
+        "MetricExpr": "UOPS_RETIRED.MS / tma_info_slots",
         "MetricGroup": "TopdownL2;tma_L2_group;tma_retiring_group",
         "MetricName": "tma_ms_uops",
         "MetricThreshold": "tma_ms_uops > 0.05",
@@ -692,7 +692,7 @@
     },
     {
         "BriefDescription": "Counts the number of uops retired excluding ms and fp div uops.",
-        "MetricExpr": "(TOPDOWN_RETIRING.ALL - UOPS_RETIRED.MS - UOPS_RETIRED.FPDIV) / tma_info_slots",
+        "MetricExpr": "(cpu_atom@TOPDOWN_RETIRING.ALL@ - cpu_atom@UOPS_RETIRED.MS@ - cpu_atom@UOPS_RETIRED.FPDIV@) / tma_info_slots",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_base_group",
         "MetricName": "tma_other_ret",
         "MetricThreshold": "tma_other_ret > 0.3",
@@ -701,7 +701,7 @@
     },
     {
         "BriefDescription": "Counts the number of machine clears relative to the number of nuke slots due to page faults.",
-        "MetricExpr": "tma_nuke * (MACHINE_CLEARS.PAGE_FAULT / MACHINE_CLEARS.SLOW)",
+        "MetricExpr": "tma_nuke * (cpu_atom@MACHINE_CLEARS.PAGE_FAULT@ / cpu_atom@MACHINE_CLEARS.SLOW@)",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_nuke_group",
         "MetricName": "tma_page_fault",
         "MetricThreshold": "tma_page_fault > 0.02",
@@ -758,7 +758,7 @@
     },
     {
         "BriefDescription": "Counts the number of cycles, relative to the number of mem_scheduler slots, in which uops are blocked due to RSV full relative",
-        "MetricExpr": "tma_mem_scheduler * MEM_SCHEDULER_BLOCK.RSV / MEM_SCHEDULER_BLOCK.ALL",
+        "MetricExpr": "tma_mem_scheduler * cpu_atom@MEM_SCHEDULER_BLOCK.RSV@ / MEM_SCHEDULER_BLOCK.ALL",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_mem_scheduler_group",
         "MetricName": "tma_rsv",
         "MetricThreshold": "tma_rsv > 0.05",
@@ -776,7 +776,7 @@
     },
     {
         "BriefDescription": "Counts the number of machine clears relative to the number of nuke slots due to SMC.",
-        "MetricExpr": "tma_nuke * (MACHINE_CLEARS.SMC / MACHINE_CLEARS.SLOW)",
+        "MetricExpr": "tma_nuke * (cpu_atom@MACHINE_CLEARS.SMC@ / cpu_atom@MACHINE_CLEARS.SLOW@)",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_nuke_group",
         "MetricName": "tma_smc",
         "MetricThreshold": "tma_smc > 0.02",
@@ -812,7 +812,7 @@
     },
     {
         "BriefDescription": "Counts the number of cycles the core is stalled due to store buffer full.",
-        "MetricExpr": "tma_mem_scheduler * (MEM_SCHEDULER_BLOCK.ST_BUF / MEM_SCHEDULER_BLOCK.ALL)",
+        "MetricExpr": "tma_mem_scheduler * (cpu_atom@MEM_SCHEDULER_BLOCK.ST_BUF@ / cpu_atom@MEM_SCHEDULER_BLOCK.ALL@)",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_memory_bound_group",
         "MetricName": "tma_store_bound",
         "MetricThreshold": "tma_store_bound > 0.1",
@@ -830,7 +830,7 @@
     },
     {
         "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution ports for ALU operations.",
-        "MetricExpr": "(UOPS_DISPATCHED.PORT_0 + UOPS_DISPATCHED.PORT_1 + UOPS_DISPATCHED.PORT_5_11 + UOPS_DISPATCHED.PORT_6) / (5 * tma_info_core_clks)",
+        "MetricExpr": "(cpu_core@UOPS_DISPATCHED.PORT_0@ + cpu_core@UOPS_DISPATCHED.PORT_1@ + cpu_core@UOPS_DISPATCHED.PORT_5_11@ + cpu_core@UOPS_DISPATCHED.PORT_6@) / (5 * tma_info_core_clks)",
         "MetricGroup": "TopdownL5;tma_L5_group;tma_ports_utilized_3m_group",
         "MetricName": "tma_alu_op_utilization",
         "MetricThreshold": "tma_alu_op_utilization > 0.6",
@@ -849,7 +849,7 @@
     },
     {
         "BriefDescription": "This metric estimates fraction of slots the CPU retired uops as a result of handing SSE to AVX* or AVX* to SSE transition Assists.",
-        "MetricExpr": "63 * ASSISTS.SSE_AVX_MIX / tma_info_slots",
+        "MetricExpr": "63 * [email protected]_AVX_MIX@ / tma_info_slots",
         "MetricGroup": "HPC;TopdownL5;tma_L5_group;tma_assists_group",
         "MetricName": "tma_avx_assists",
         "MetricThreshold": "tma_avx_assists > 0.1",
@@ -858,7 +858,7 @@
     },
     {
         "BriefDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend",
-        "MetricExpr": "topdown\\-be\\-bound / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * tma_info_slots",
+        "MetricExpr": "cpu_core@topdown\\-be\\-bound@ / (cpu_core@topdown\\-fe\\-bound@ + cpu_core@topdown\\-bad\\-spec@ + cpu_core@topdown\\-retiring@ + cpu_core@topdown\\-be\\-bound@) + 0 * tma_info_slots",
         "MetricGroup": "TmaL1;TopdownL1;tma_L1_group",
         "MetricName": "tma_backend_bound",
         "MetricThreshold": "tma_backend_bound > 0.2",
@@ -880,7 +880,7 @@
     },
     {
         "BriefDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction",
-        "MetricExpr": "topdown\\-br\\-mispredict / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * tma_info_slots",
+        "MetricExpr": "cpu_core@topdown\\-br\\-mispredict@ / (cpu_core@topdown\\-fe\\-bound@ + cpu_core@topdown\\-bad\\-spec@ + cpu_core@topdown\\-retiring@ + cpu_core@topdown\\-be\\-bound@) + 0 * tma_info_slots",
         "MetricGroup": "BadSpec;BrMispredicts;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueBM",
         "MetricName": "tma_branch_mispredicts",
         "MetricThreshold": "tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15",
@@ -911,7 +911,7 @@
     },
     {
         "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Machine Clears",
-        "MetricExpr": "(1 - tma_branch_mispredicts / tma_bad_speculation) * INT_MISC.CLEAR_RESTEER_CYCLES / tma_info_clks",
+        "MetricExpr": "(1 - tma_branch_mispredicts / tma_bad_speculation) * cpu_core@INT_MISC.CLEAR_RESTEER_CYCLES@ / tma_info_clks",
         "MetricGroup": "BadSpec;MachineClears;TopdownL4;tma_L4_group;tma_branch_resteers_group;tma_issueMC",
         "MetricName": "tma_clears_resteers",
         "MetricThreshold": "tma_clears_resteers > 0.05 & (tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))",
@@ -922,7 +922,7 @@
     {
         "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses",
         "MetricConstraint": "NO_GROUP_EVENTS",
-        "MetricExpr": "(25 * tma_info_average_frequency * (MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD * (OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM / (OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM + OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD))) + 24 * tma_info_average_frequency * MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_clks",
+        "MetricExpr": "(25 * tma_info_average_frequency * (cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD@ * ([email protected]_DATA_RD.L3_HIT.SNOOP_HITM@ / ([email protected]_DATA_RD.L3_HIT.SNOOP_HITM@ + [email protected]_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD@))) + 24 * tma_info_average_frequency * cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS@) * (1 + cpu_core@MEM_LOAD_RETIRED.FB_HIT@ / cpu_core@MEM_LOAD_RETIRED.L1_MISS@ / 2) / tma_info_clks",
         "MetricGroup": "DataSharing;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group",
         "MetricName": "tma_contested_accesses",
         "MetricThreshold": "tma_contested_accesses > 0.05 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
@@ -944,7 +944,7 @@
     {
         "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses",
         "MetricConstraint": "NO_GROUP_EVENTS",
-        "MetricExpr": "24 * tma_info_average_frequency * (MEM_LOAD_L3_HIT_RETIRED.XSNP_NO_FWD + MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD * (1 - OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM / (OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM + OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD))) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_clks",
+        "MetricExpr": "24 * tma_info_average_frequency * (cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_NO_FWD@ + cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD@ * (1 - [email protected]_DATA_RD.L3_HIT.SNOOP_HITM@ / ([email protected]_DATA_RD.L3_HIT.SNOOP_HITM@ + [email protected]_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD@))) * (1 + cpu_core@MEM_LOAD_RETIRED.FB_HIT@ / cpu_core@MEM_LOAD_RETIRED.L1_MISS@ / 2) / tma_info_clks",
         "MetricGroup": "Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group",
         "MetricName": "tma_data_sharing",
         "MetricThreshold": "tma_data_sharing > 0.05 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
@@ -975,7 +975,7 @@
     {
         "BriefDescription": "This metric estimates how often the CPU was stalled on accesses to external memory (DRAM) by loads",
         "MetricConstraint": "NO_GROUP_EVENTS",
-        "MetricExpr": "MEMORY_ACTIVITY.STALLS_L3_MISS / tma_info_clks",
+        "MetricExpr": "cpu_core@MEMORY_ACTIVITY.STALLS_L3_MISS@ / tma_info_clks",
         "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group",
         "MetricName": "tma_dram_bound",
         "MetricThreshold": "tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)",
@@ -985,7 +985,7 @@
     },
     {
         "BriefDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to DSB (decoded uop cache) fetch pipeline",
-        "MetricExpr": "(IDQ.DSB_CYCLES_ANY - IDQ.DSB_CYCLES_OK) / tma_info_core_clks / 2",
+        "MetricExpr": "([email protected]_CYCLES_ANY@ - [email protected]_CYCLES_OK@) / tma_info_core_clks / 2",
         "MetricGroup": "DSB;FetchBW;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group",
         "MetricName": "tma_dsb",
         "MetricThreshold": "tma_dsb > 0.15 & (tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 6 > 0.35)",
@@ -1005,7 +1005,7 @@
     },
     {
         "BriefDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses",
-        "MetricExpr": "min(7 * cpu_core@DTLB_LOAD_MISSES.STLB_HIT\\,cmask\\=1@ + DTLB_LOAD_MISSES.WALK_ACTIVE, max(CYCLE_ACTIVITY.CYCLES_MEM_ANY - MEMORY_ACTIVITY.CYCLES_L1D_MISS, 0)) / tma_info_clks",
+        "MetricExpr": "min(7 * cpu_core@DTLB_LOAD_MISSES.STLB_HIT\\,cmask\\=1@ + cpu_core@DTLB_LOAD_MISSES.WALK_ACTIVE@, max(cpu_core@CYCLE_ACTIVITY.CYCLES_MEM_ANY@ - cpu_core@MEMORY_ACTIVITY.CYCLES_L1D_MISS@, 0)) / tma_info_clks",
         "MetricGroup": "MemoryTLB;TopdownL4;tma_L4_group;tma_issueTLB;tma_l1_bound_group",
         "MetricName": "tma_dtlb_load",
         "MetricThreshold": "tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
@@ -1015,7 +1015,7 @@
     },
     {
         "BriefDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses",
-        "MetricExpr": "(7 * cpu_core@DTLB_STORE_MISSES.STLB_HIT\\,cmask\\=1@ + DTLB_STORE_MISSES.WALK_ACTIVE) / tma_info_core_clks",
+        "MetricExpr": "(7 * cpu_core@DTLB_STORE_MISSES.STLB_HIT\\,cmask\\=1@ + cpu_core@DTLB_STORE_MISSES.WALK_ACTIVE@) / tma_info_core_clks",
         "MetricGroup": "MemoryTLB;TopdownL4;tma_L4_group;tma_issueTLB;tma_store_bound_group",
         "MetricName": "tma_dtlb_store",
         "MetricThreshold": "tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
@@ -1025,7 +1025,7 @@
     },
     {
         "BriefDescription": "This metric roughly estimates how often CPU was handling synchronizations due to False Sharing",
-        "MetricExpr": "28 * tma_info_average_frequency * OCR.DEMAND_RFO.L3_HIT.SNOOP_HITM / tma_info_clks",
+        "MetricExpr": "28 * tma_info_average_frequency * [email protected]_RFO.L3_HIT.SNOOP_HITM@ / tma_info_clks",
         "MetricGroup": "DataSharing;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_store_bound_group",
         "MetricName": "tma_false_sharing",
         "MetricThreshold": "tma_false_sharing > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
@@ -1056,7 +1056,7 @@
     },
     {
         "BriefDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues",
-        "MetricExpr": "topdown\\-fetch\\-lat / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) - INT_MISC.UOP_DROPPING / tma_info_slots",
+        "MetricExpr": "cpu_core@topdown\\-fetch\\-lat@ / (cpu_core@topdown\\-fe\\-bound@ + cpu_core@topdown\\-bad\\-spec@ + cpu_core@topdown\\-retiring@ + cpu_core@topdown\\-be\\-bound@) - cpu_core@INT_MISC.UOP_DROPPING@ / tma_info_slots",
         "MetricGroup": "Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group",
         "MetricName": "tma_fetch_latency",
         "MetricThreshold": "tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
@@ -1088,7 +1088,7 @@
     },
     {
         "BriefDescription": "This metric roughly estimates fraction of slots the CPU retired uops as a result of handing Floating Point (FP) Assists",
-        "MetricExpr": "30 * ASSISTS.FP / tma_info_slots",
+        "MetricExpr": "30 * [email protected]@ / tma_info_slots",
         "MetricGroup": "HPC;TopdownL5;tma_L5_group;tma_assists_group",
         "MetricName": "tma_fp_assists",
         "MetricThreshold": "tma_fp_assists > 0.1",
@@ -1118,7 +1118,7 @@
     },
     {
         "BriefDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 128-bit wide vectors",
-        "MetricExpr": "(FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE) / (tma_retiring * tma_info_slots)",
+        "MetricExpr": "(cpu_core@FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE@ + cpu_core@FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE@) / (tma_retiring * tma_info_slots)",
         "MetricGroup": "Compute;Flops;TopdownL5;tma_L5_group;tma_fp_vector_group;tma_issue2P",
         "MetricName": "tma_fp_vector_128b",
         "MetricThreshold": "tma_fp_vector_128b > 0.1 & (tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6))",
@@ -1128,7 +1128,7 @@
     },
     {
         "BriefDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 256-bit wide vectors",
-        "MetricExpr": "(FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE) / (tma_retiring * tma_info_slots)",
+        "MetricExpr": "(cpu_core@FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE@ + cpu_core@FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE@) / (tma_retiring * tma_info_slots)",
         "MetricGroup": "Compute;Flops;TopdownL5;tma_L5_group;tma_fp_vector_group;tma_issue2P",
         "MetricName": "tma_fp_vector_256b",
         "MetricThreshold": "tma_fp_vector_256b > 0.1 & (tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6))",
@@ -1138,7 +1138,7 @@
     },
     {
         "BriefDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend",
-        "MetricExpr": "topdown\\-fe\\-bound / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) - INT_MISC.UOP_DROPPING / tma_info_slots",
+        "MetricExpr": "cpu_core@topdown\\-fe\\-bound@ / (cpu_core@topdown\\-fe\\-bound@ + cpu_core@topdown\\-bad\\-spec@ + cpu_core@topdown\\-retiring@ + cpu_core@topdown\\-be\\-bound@) - cpu_core@INT_MISC.UOP_DROPPING@ / tma_info_slots",
         "MetricGroup": "PGO;TmaL1;TopdownL1;tma_L1_group",
         "MetricName": "tma_frontend_bound",
         "MetricThreshold": "tma_frontend_bound > 0.15",
@@ -1149,7 +1149,7 @@
     },
     {
         "BriefDescription": "This metric represents fraction of slots where the CPU was retiring fused instructions -- where one uop can represent multiple contiguous instructions",
-        "MetricExpr": "tma_light_operations * INST_RETIRED.MACRO_FUSED / (tma_retiring * tma_info_slots)",
+        "MetricExpr": "tma_light_operations * cpu_core@INST_RETIRED.MACRO_FUSED@ / (tma_retiring * tma_info_slots)",
         "MetricGroup": "Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group",
         "MetricName": "tma_fused_instructions",
         "MetricThreshold": "tma_fused_instructions > 0.1 & tma_light_operations > 0.6",
@@ -1159,7 +1159,7 @@
     },
     {
         "BriefDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences",
-        "MetricExpr": "topdown\\-heavy\\-ops / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * tma_info_slots",
+        "MetricExpr": "cpu_core@topdown\\-heavy\\-ops@ / (cpu_core@topdown\\-fe\\-bound@ + cpu_core@topdown\\-bad\\-spec@ + cpu_core@topdown\\-retiring@ + cpu_core@topdown\\-be\\-bound@) + 0 * tma_info_slots",
         "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group",
         "MetricName": "tma_heavy_operations",
         "MetricThreshold": "tma_heavy_operations > 0.1",
@@ -1213,7 +1213,7 @@
     },
     {
         "BriefDescription": "Total pipeline cost of branch related instructions (used for program control-flow including function calls)",
-        "MetricExpr": "100 * ((BR_INST_RETIRED.COND + 3 * BR_INST_RETIRED.NEAR_CALL + (BR_INST_RETIRED.NEAR_TAKEN - BR_INST_RETIRED.COND_TAKEN - 2 * BR_INST_RETIRED.NEAR_CALL)) / tma_info_slots)",
+        "MetricExpr": "100 * ((cpu_core@BR_INST_RETIRED.COND@ + 3 * cpu_core@BR_INST_RETIRED.NEAR_CALL@ + (cpu_core@BR_INST_RETIRED.NEAR_TAKEN@ - cpu_core@BR_INST_RETIRED.COND_TAKEN@ - 2 * cpu_core@BR_INST_RETIRED.NEAR_CALL@)) / tma_info_slots)",
         "MetricGroup": "Ret;tma_issueBC",
         "MetricName": "tma_info_branching_overhead",
         "MetricThreshold": "tma_info_branching_overhead > 10",
@@ -1222,21 +1222,21 @@
     },
     {
         "BriefDescription": "Fraction of branches that are CALL or RET",
-        "MetricExpr": "(BR_INST_RETIRED.NEAR_CALL + BR_INST_RETIRED.NEAR_RETURN) / BR_INST_RETIRED.ALL_BRANCHES",
+        "MetricExpr": "(cpu_core@BR_INST_RETIRED.NEAR_CALL@ + cpu_core@BR_INST_RETIRED.NEAR_RETURN@) / BR_INST_RETIRED.ALL_BRANCHES",
         "MetricGroup": "Bad;Branches",
         "MetricName": "tma_info_callret",
         "Unit": "cpu_core"
     },
     {
         "BriefDescription": "Per-Logical Processor actual clocks when the Logical Processor is active.",
-        "MetricExpr": "CPU_CLK_UNHALTED.THREAD",
+        "MetricExpr": "cpu_core@CPU_CLK_UNHALTED.THREAD@",
         "MetricGroup": "Pipeline",
         "MetricName": "tma_info_clks",
         "Unit": "cpu_core"
     },
     {
         "BriefDescription": "STLB (2nd level TLB) code speculative misses per kilo instruction (misses of any page-size that complete the page walk)",
-        "MetricExpr": "1e3 * ITLB_MISSES.WALK_COMPLETED / INST_RETIRED.ANY",
+        "MetricExpr": "1e3 * cpu_core@ITLB_MISSES.WALK_COMPLETED@ / INST_RETIRED.ANY",
         "MetricGroup": "Fed;MemoryTLB",
         "MetricName": "tma_info_code_stlb_mpki",
         "Unit": "cpu_core"
@@ -1266,7 +1266,7 @@
     },
     {
         "BriefDescription": "Core actual clocks when any Logical Processor is active on the Physical Core",
-        "MetricExpr": "CPU_CLK_UNHALTED.DISTRIBUTED",
+        "MetricExpr": "cpu_core@CPU_CLK_UNHALTED.DISTRIBUTED@",
         "MetricGroup": "SMT",
         "MetricName": "tma_info_core_clks",
         "Unit": "cpu_core"
@@ -1309,7 +1309,7 @@
     },
     {
         "BriefDescription": "Fraction of Uops delivered by the DSB (aka Decoded ICache; or Uop Cache)",
-        "MetricExpr": "IDQ.DSB_UOPS / UOPS_ISSUED.ANY",
+        "MetricExpr": "IDQ.DSB_UOPS / cpu_core@UOPS_ISSUED.ANY@",
         "MetricGroup": "DSB;Fed;FetchBW;tma_issueFB",
         "MetricName": "tma_info_dsb_coverage",
         "MetricThreshold": "tma_info_dsb_coverage < 0.7 & tma_info_ipc / 6 > 0.35",
@@ -1350,7 +1350,7 @@
     },
     {
         "BriefDescription": "Fill Buffer (FB) hits per kilo instructions for retired demand loads (L1D misses that merge into ongoing miss-handling entries)",
-        "MetricExpr": "1e3 * MEM_LOAD_RETIRED.FB_HIT / INST_RETIRED.ANY",
+        "MetricExpr": "1e3 * cpu_core@MEM_LOAD_RETIRED.FB_HIT@ / INST_RETIRED.ANY",
         "MetricGroup": "CacheMisses;Mem",
         "MetricName": "tma_info_fb_hpki",
         "Unit": "cpu_core"
@@ -1365,7 +1365,7 @@
     {
         "BriefDescription": "Floating Point Operations Per Cycle",
         "MetricConstraint": "NO_GROUP_EVENTS",
-        "MetricExpr": "(FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * (FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE) + 8 * FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE) / tma_info_core_clks",
+        "MetricExpr": "(cpu_core@FP_ARITH_INST_RETIRED.SCALAR_SINGLE@ + cpu_core@FP_ARITH_INST_RETIRED.SCALAR_DOUBLE@ + 2 * cpu_core@FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE@ + 4 * (cpu_core@FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE@ + cpu_core@FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE@) + 8 * cpu_core@FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE@) / tma_info_core_clks",
         "MetricGroup": "Flops;Ret",
         "MetricName": "tma_info_flopc",
         "Unit": "cpu_core"
@@ -1373,7 +1373,7 @@
     {
         "BriefDescription": "Actual per-core usage of the Floating Point non-X87 execution units (regardless of precision or vector-width)",
         "MetricConstraint": "NO_GROUP_EVENTS",
-        "MetricExpr": "(FP_ARITH_DISPATCHED.PORT_0 + FP_ARITH_DISPATCHED.PORT_1 + FP_ARITH_DISPATCHED.PORT_5) / (2 * tma_info_core_clks)",
+        "MetricExpr": "(cpu_core@FP_ARITH_DISPATCHED.PORT_0@ + cpu_core@FP_ARITH_DISPATCHED.PORT_1@ + cpu_core@FP_ARITH_DISPATCHED.PORT_5@) / (2 * tma_info_core_clks)",
         "MetricGroup": "Cor;Flops;HPC",
         "MetricName": "tma_info_fp_arith_utilization",
         "PublicDescription": "Actual per-core usage of the Floating Point non-X87 execution units (regardless of precision or vector-width). Values > 1 are possible due to ([BDW+] Fused-Multiply Add (FMA) counting - common; [ADL+] use all of ADD/MUL/FMA in Scalar or 128/256-bit vectors - less common).",
@@ -1381,7 +1381,7 @@
     },
     {
         "BriefDescription": "Giga Floating Point Operations Per Second",
-        "MetricExpr": "(FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * (FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE) + 8 * FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE) / 1e9 / duration_time",
+        "MetricExpr": "(cpu_core@FP_ARITH_INST_RETIRED.SCALAR_SINGLE@ + cpu_core@FP_ARITH_INST_RETIRED.SCALAR_DOUBLE@ + 2 * cpu_core@FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE@ + 4 * (cpu_core@FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE@ + cpu_core@FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE@) + 8 * cpu_core@FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE@) / 1e9 / duration_time",
         "MetricGroup": "Cor;Flops;HPC",
         "MetricName": "tma_info_gflops",
         "PublicDescription": "Giga Floating Point Operations Per Second. Aggregate across all supported options of: FP precisions, scalar and vector instructions, vector-width and AMX engine.",
@@ -1405,7 +1405,7 @@
     },
     {
         "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is execution) per-core",
-        "MetricExpr": "UOPS_EXECUTED.THREAD / (UOPS_EXECUTED.CORE_CYCLES_GE_1 / 2 if #SMT_on else UOPS_EXECUTED.CORE_CYCLES_GE_1)",
+        "MetricExpr": "UOPS_EXECUTED.THREAD / (cpu_core@UOPS_EXECUTED.CORE_CYCLES_GE_1@ / 2 if #SMT_on else cpu_core@UOPS_EXECUTED.CORE_CYCLES_GE_1@)",
         "MetricGroup": "Backend;Cor;Pipeline;PortsUtil",
         "MetricName": "tma_info_ilp",
         "Unit": "cpu_core"
@@ -1421,7 +1421,7 @@
     },
     {
         "BriefDescription": "Total number of retired Instructions",
-        "MetricExpr": "INST_RETIRED.ANY",
+        "MetricExpr": "cpu_core@INST_RETIRED.ANY@",
         "MetricGroup": "Summary;TmaL1;tma_L1_group",
         "MetricName": "tma_info_instructions",
         "PublicDescription": "Total number of retired Instructions. Sample with: INST_RETIRED.PREC_DIST",
@@ -1438,7 +1438,7 @@
     },
     {
         "BriefDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number means higher occurrence rate)",
-        "MetricExpr": "INST_RETIRED.ANY / (FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE)",
+        "MetricExpr": "INST_RETIRED.ANY / (cpu_core@FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE@ + cpu_core@FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE@)",
         "MetricGroup": "Flops;FpVector;InsType",
         "MetricName": "tma_info_iparith_avx128",
         "MetricThreshold": "tma_info_iparith_avx128 < 10",
@@ -1447,7 +1447,7 @@
     },
     {
         "BriefDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means higher occurrence rate)",
-        "MetricExpr": "INST_RETIRED.ANY / (FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE)",
+        "MetricExpr": "INST_RETIRED.ANY / (cpu_core@FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE@ + cpu_core@FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE@)",
         "MetricGroup": "Flops;FpVector;InsType",
         "MetricName": "tma_info_iparith_avx256",
         "MetricThreshold": "tma_info_iparith_avx256 < 10",
@@ -1514,7 +1514,7 @@
     },
     {
         "BriefDescription": "Instructions per Far Branch ( Far Branches apply upon transition from application to operating system, handling interrupts, exceptions) [lower number means higher occurrence rate]",
-        "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.FAR_BRANCH:u",
+        "MetricExpr": "INST_RETIRED.ANY / cpu_core@BR_INST_RETIRED.FAR_BRANCH@u",
         "MetricGroup": "Branches;OS",
         "MetricName": "tma_info_ipfarbranch",
         "MetricThreshold": "tma_info_ipfarbranch < 1e6",
@@ -1522,7 +1522,7 @@
     },
     {
         "BriefDescription": "Instructions per Floating Point (FP) Operation (lower number means higher occurrence rate)",
-        "MetricExpr": "INST_RETIRED.ANY / (FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * (FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE) + 8 * FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE)",
+        "MetricExpr": "INST_RETIRED.ANY / (cpu_core@FP_ARITH_INST_RETIRED.SCALAR_SINGLE@ + cpu_core@FP_ARITH_INST_RETIRED.SCALAR_DOUBLE@ + 2 * cpu_core@FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE@ + 4 * (cpu_core@FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE@ + cpu_core@FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE@) + 8 * cpu_core@FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE@)",
         "MetricGroup": "Flops;InsType",
         "MetricName": "tma_info_ipflop",
         "MetricThreshold": "tma_info_ipflop < 10",
@@ -1610,14 +1610,14 @@
     },
     {
         "BriefDescription": "Fraction of branches that are unconditional (direct or indirect) jumps",
-        "MetricExpr": "(BR_INST_RETIRED.NEAR_TAKEN - BR_INST_RETIRED.COND_TAKEN - 2 * BR_INST_RETIRED.NEAR_CALL) / BR_INST_RETIRED.ALL_BRANCHES",
+        "MetricExpr": "(cpu_core@BR_INST_RETIRED.NEAR_TAKEN@ - cpu_core@BR_INST_RETIRED.COND_TAKEN@ - 2 * cpu_core@BR_INST_RETIRED.NEAR_CALL@) / BR_INST_RETIRED.ALL_BRANCHES",
         "MetricGroup": "Bad;Branches",
         "MetricName": "tma_info_jump",
         "Unit": "cpu_core"
     },
     {
         "BriefDescription": "Cycles Per Instruction for the Operating System (OS) Kernel mode",
-        "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P:k / INST_RETIRED.ANY_P:k",
+        "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P:k / cpu_core@INST_RETIRED.ANY_P@k",
         "MetricGroup": "OS",
         "MetricName": "tma_info_kernel_cpi",
         "Unit": "cpu_core"
@@ -1632,7 +1632,7 @@
     },
     {
         "BriefDescription": "Average per-core data fill bandwidth to the L1 data cache [GB / sec]",
-        "MetricExpr": "64 * L1D.REPLACEMENT / 1e9 / duration_time",
+        "MetricExpr": "64 * [email protected]@ / 1e9 / duration_time",
         "MetricGroup": "Mem;MemoryBW",
         "MetricName": "tma_info_l1d_cache_fill_bw",
         "Unit": "cpu_core"
@@ -1646,21 +1646,21 @@
     },
     {
         "BriefDescription": "L1 cache true misses per kilo instruction for retired demand loads",
-        "MetricExpr": "1e3 * MEM_LOAD_RETIRED.L1_MISS / INST_RETIRED.ANY",
+        "MetricExpr": "1e3 * cpu_core@MEM_LOAD_RETIRED.L1_MISS@ / INST_RETIRED.ANY",
         "MetricGroup": "CacheMisses;Mem",
         "MetricName": "tma_info_l1mpki",
         "Unit": "cpu_core"
     },
     {
         "BriefDescription": "L1 cache true misses per kilo instruction for all demand loads (including speculative)",
-        "MetricExpr": "1e3 * L2_RQSTS.ALL_DEMAND_DATA_RD / INST_RETIRED.ANY",
+        "MetricExpr": "1e3 * cpu_core@L2_RQSTS.ALL_DEMAND_DATA_RD@ / INST_RETIRED.ANY",
         "MetricGroup": "CacheMisses;Mem",
         "MetricName": "tma_info_l1mpki_load",
         "Unit": "cpu_core"
     },
     {
         "BriefDescription": "Average per-core data fill bandwidth to the L2 cache [GB / sec]",
-        "MetricExpr": "64 * L2_LINES_IN.ALL / 1e9 / duration_time",
+        "MetricExpr": "64 * cpu_core@L2_LINES_IN.ALL@ / 1e9 / duration_time",
         "MetricGroup": "Mem;MemoryBW",
         "MetricName": "tma_info_l2_cache_fill_bw",
         "Unit": "cpu_core"
@@ -1674,56 +1674,56 @@
     },
     {
         "BriefDescription": "L2 cache hits per kilo instruction for all request types (including speculative)",
-        "MetricExpr": "1e3 * (L2_RQSTS.REFERENCES - L2_RQSTS.MISS) / INST_RETIRED.ANY",
+        "MetricExpr": "1e3 * (cpu_core@L2_RQSTS.REFERENCES@ - cpu_core@L2_RQSTS.MISS@) / INST_RETIRED.ANY",
         "MetricGroup": "CacheMisses;Mem",
         "MetricName": "tma_info_l2hpki_all",
         "Unit": "cpu_core"
     },
     {
         "BriefDescription": "L2 cache hits per kilo instruction for all demand loads  (including speculative)",
-        "MetricExpr": "1e3 * L2_RQSTS.DEMAND_DATA_RD_HIT / INST_RETIRED.ANY",
+        "MetricExpr": "1e3 * cpu_core@L2_RQSTS.DEMAND_DATA_RD_HIT@ / INST_RETIRED.ANY",
         "MetricGroup": "CacheMisses;Mem",
         "MetricName": "tma_info_l2hpki_load",
         "Unit": "cpu_core"
     },
     {
         "BriefDescription": "L2 cache true misses per kilo instruction for retired demand loads",
-        "MetricExpr": "1e3 * MEM_LOAD_RETIRED.L2_MISS / INST_RETIRED.ANY",
+        "MetricExpr": "1e3 * cpu_core@MEM_LOAD_RETIRED.L2_MISS@ / INST_RETIRED.ANY",
         "MetricGroup": "Backend;CacheMisses;Mem",
         "MetricName": "tma_info_l2mpki",
         "Unit": "cpu_core"
     },
     {
         "BriefDescription": "L2 cache ([RKL+] true) misses per kilo instruction for all request types (including speculative)",
-        "MetricExpr": "1e3 * L2_RQSTS.MISS / INST_RETIRED.ANY",
+        "MetricExpr": "1e3 * cpu_core@L2_RQSTS.MISS@ / INST_RETIRED.ANY",
         "MetricGroup": "CacheMisses;Mem;Offcore",
         "MetricName": "tma_info_l2mpki_all",
         "Unit": "cpu_core"
     },
     {
         "BriefDescription": "L2 cache true code cacheline misses per kilo instruction",
-        "MetricExpr": "1e3 * FRONTEND_RETIRED.L2_MISS / INST_RETIRED.ANY",
+        "MetricExpr": "1e3 * cpu_core@FRONTEND_RETIRED.L2_MISS@ / INST_RETIRED.ANY",
         "MetricGroup": "IcMiss",
         "MetricName": "tma_info_l2mpki_code",
         "Unit": "cpu_core"
     },
     {
         "BriefDescription": "L2 cache speculative code cacheline misses per kilo instruction",
-        "MetricExpr": "1e3 * L2_RQSTS.CODE_RD_MISS / INST_RETIRED.ANY",
+        "MetricExpr": "1e3 * cpu_core@L2_RQSTS.CODE_RD_MISS@ / INST_RETIRED.ANY",
         "MetricGroup": "IcMiss",
         "MetricName": "tma_info_l2mpki_code_all",
         "Unit": "cpu_core"
     },
     {
         "BriefDescription": "L2 cache ([RKL+] true) misses per kilo instruction for all demand loads  (including speculative)",
-        "MetricExpr": "1e3 * L2_RQSTS.DEMAND_DATA_RD_MISS / INST_RETIRED.ANY",
+        "MetricExpr": "1e3 * cpu_core@L2_RQSTS.DEMAND_DATA_RD_MISS@ / INST_RETIRED.ANY",
         "MetricGroup": "CacheMisses;Mem",
         "MetricName": "tma_info_l2mpki_load",
         "Unit": "cpu_core"
     },
     {
         "BriefDescription": "Average per-core data access bandwidth to the L3 cache [GB / sec]",
-        "MetricExpr": "64 * OFFCORE_REQUESTS.ALL_REQUESTS / 1e9 / duration_time",
+        "MetricExpr": "64 * cpu_core@OFFCORE_REQUESTS.ALL_REQUESTS@ / 1e9 / duration_time",
         "MetricGroup": "Mem;MemoryBW;Offcore",
         "MetricName": "tma_info_l3_cache_access_bw",
         "Unit": "cpu_core"
@@ -1737,7 +1737,7 @@
     },
     {
         "BriefDescription": "Average per-core data fill bandwidth to the L3 cache [GB / sec]",
-        "MetricExpr": "64 * LONGEST_LAT_CACHE.MISS / 1e9 / duration_time",
+        "MetricExpr": "64 * cpu_core@LONGEST_LAT_CACHE.MISS@ / 1e9 / duration_time",
         "MetricGroup": "Mem;MemoryBW",
         "MetricName": "tma_info_l3_cache_fill_bw",
         "Unit": "cpu_core"
@@ -1751,7 +1751,7 @@
     },
     {
         "BriefDescription": "L3 cache true misses per kilo instruction for retired demand loads",
-        "MetricExpr": "1e3 * MEM_LOAD_RETIRED.L3_MISS / INST_RETIRED.ANY",
+        "MetricExpr": "1e3 * cpu_core@MEM_LOAD_RETIRED.L3_MISS@ / INST_RETIRED.ANY",
         "MetricGroup": "CacheMisses;Mem",
         "MetricName": "tma_info_l3mpki",
         "Unit": "cpu_core"
@@ -1786,14 +1786,14 @@
     },
     {
         "BriefDescription": "STLB (2nd level TLB) data load speculative misses per kilo instruction (misses of any page-size that complete the page walk)",
-        "MetricExpr": "1e3 * DTLB_LOAD_MISSES.WALK_COMPLETED / INST_RETIRED.ANY",
+        "MetricExpr": "1e3 * cpu_core@DTLB_LOAD_MISSES.WALK_COMPLETED@ / INST_RETIRED.ANY",
         "MetricGroup": "Mem;MemoryTLB",
         "MetricName": "tma_info_load_stlb_mpki",
         "Unit": "cpu_core"
     },
     {
         "BriefDescription": "Fraction of Uops delivered by the LSD (Loop Stream Detector; aka Loop Cache)",
-        "MetricExpr": "LSD.UOPS / UOPS_ISSUED.ANY",
+        "MetricExpr": "LSD.UOPS / cpu_core@UOPS_ISSUED.ANY@",
         "MetricGroup": "Fed;LSD",
         "MetricName": "tma_info_lsd_coverage",
         "Unit": "cpu_core"
@@ -1877,7 +1877,7 @@
     },
     {
         "BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses",
-        "MetricExpr": "(ITLB_MISSES.WALK_PENDING + DTLB_LOAD_MISSES.WALK_PENDING + DTLB_STORE_MISSES.WALK_PENDING) / (4 * tma_info_core_clks)",
+        "MetricExpr": "(cpu_core@ITLB_MISSES.WALK_PENDING@ + cpu_core@DTLB_LOAD_MISSES.WALK_PENDING@ + cpu_core@DTLB_STORE_MISSES.WALK_PENDING@) / (4 * tma_info_core_clks)",
         "MetricGroup": "Mem;MemoryTLB",
         "MetricName": "tma_info_page_walks_utilization",
         "MetricThreshold": "tma_info_page_walks_utilization > 0.5",
@@ -1893,21 +1893,21 @@
     },
     {
         "BriefDescription": "Total issue-pipeline slots (per-Physical Core till ICL; per-Logical Processor ICL onward)",
-        "MetricExpr": "TOPDOWN.SLOTS",
+        "MetricExpr": "[email protected]@",
         "MetricGroup": "TmaL1;tma_L1_group",
         "MetricName": "tma_info_slots",
         "Unit": "cpu_core"
     },
     {
         "BriefDescription": "Fraction of Physical Core issue-slots utilized by this Logical Processor",
-        "MetricExpr": "(tma_info_slots / (TOPDOWN.SLOTS / 2) if #SMT_on else 1)",
+        "MetricExpr": "(tma_info_slots / ([email protected]@ / 2) if #SMT_on else 1)",
         "MetricGroup": "SMT;TmaL1;tma_L1_group",
         "MetricName": "tma_info_slots_utilization",
         "Unit": "cpu_core"
     },
     {
         "BriefDescription": "Fraction of cycles where both hardware Logical Processors were active",
-        "MetricExpr": "(1 - CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_DISTRIBUTED if #SMT_on else 0)",
+        "MetricExpr": "(1 - cpu_core@CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE@ / cpu_core@CPU_CLK_UNHALTED.REF_DISTRIBUTED@ if #SMT_on else 0)",
         "MetricGroup": "SMT",
         "MetricName": "tma_info_smt_2t_utilization",
         "Unit": "cpu_core"
@@ -1921,7 +1921,7 @@
     },
     {
         "BriefDescription": "STLB (2nd level TLB) data store speculative misses per kilo instruction (misses of any page-size that complete the page walk)",
-        "MetricExpr": "1e3 * DTLB_STORE_MISSES.WALK_COMPLETED / INST_RETIRED.ANY",
+        "MetricExpr": "1e3 * cpu_core@DTLB_STORE_MISSES.WALK_COMPLETED@ / INST_RETIRED.ANY",
         "MetricGroup": "Mem;MemoryTLB",
         "MetricName": "tma_info_store_stlb_mpki",
         "Unit": "cpu_core"
@@ -1969,7 +1969,7 @@
     },
     {
         "BriefDescription": "This metric represents 128-bit vector Integer ADD/SUB/SAD or VNNI (Vector Neural Network Instructions) uops fraction the CPU has retired",
-        "MetricExpr": "(INT_VEC_RETIRED.ADD_128 + INT_VEC_RETIRED.VNNI_128) / (tma_retiring * tma_info_slots)",
+        "MetricExpr": "(cpu_core@INT_VEC_RETIRED.ADD_128@ + cpu_core@INT_VEC_RETIRED.VNNI_128@) / (tma_retiring * tma_info_slots)",
         "MetricGroup": "Compute;IntVector;Pipeline;TopdownL4;tma_L4_group;tma_int_operations_group;tma_issue2P",
         "MetricName": "tma_int_vector_128b",
         "MetricThreshold": "tma_int_vector_128b > 0.1 & (tma_int_operations > 0.1 & tma_light_operations > 0.6)",
@@ -1979,7 +1979,7 @@
     },
     {
         "BriefDescription": "This metric represents 256-bit vector Integer ADD/SUB/SAD or VNNI (Vector Neural Network Instructions) uops fraction the CPU has retired",
-        "MetricExpr": "(INT_VEC_RETIRED.ADD_256 + INT_VEC_RETIRED.MUL_256 + INT_VEC_RETIRED.VNNI_256) / (tma_retiring * tma_info_slots)",
+        "MetricExpr": "(cpu_core@INT_VEC_RETIRED.ADD_256@ + cpu_core@INT_VEC_RETIRED.MUL_256@ + cpu_core@INT_VEC_RETIRED.VNNI_256@) / (tma_retiring * tma_info_slots)",
         "MetricGroup": "Compute;IntVector;Pipeline;TopdownL4;tma_L4_group;tma_int_operations_group;tma_issue2P",
         "MetricName": "tma_int_vector_256b",
         "MetricThreshold": "tma_int_vector_256b > 0.1 & (tma_int_operations > 0.1 & tma_light_operations > 0.6)",
@@ -1999,7 +1999,7 @@
     },
     {
         "BriefDescription": "This metric estimates how often the CPU was stalled without loads missing the L1 data cache",
-        "MetricExpr": "max((EXE_ACTIVITY.BOUND_ON_LOADS - MEMORY_ACTIVITY.STALLS_L1D_MISS) / tma_info_clks, 0)",
+        "MetricExpr": "max((cpu_core@EXE_ACTIVITY.BOUND_ON_LOADS@ - cpu_core@MEMORY_ACTIVITY.STALLS_L1D_MISS@) / tma_info_clks, 0)",
         "MetricGroup": "CacheMisses;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_issueL1;tma_issueMC;tma_memory_bound_group",
         "MetricName": "tma_l1_bound",
         "MetricThreshold": "tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)",
@@ -2010,7 +2010,7 @@
     {
         "BriefDescription": "This metric estimates how often the CPU was stalled due to L2 cache accesses by loads",
         "MetricConstraint": "NO_GROUP_EVENTS",
-        "MetricExpr": "(MEMORY_ACTIVITY.STALLS_L1D_MISS - MEMORY_ACTIVITY.STALLS_L2_MISS) / tma_info_clks",
+        "MetricExpr": "(cpu_core@MEMORY_ACTIVITY.STALLS_L1D_MISS@ - cpu_core@MEMORY_ACTIVITY.STALLS_L2_MISS@) / tma_info_clks",
         "MetricGroup": "CacheMisses;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group",
         "MetricName": "tma_l2_bound",
         "MetricThreshold": "tma_l2_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)",
@@ -2020,7 +2020,7 @@
     },
     {
         "BriefDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core",
-        "MetricExpr": "(MEMORY_ACTIVITY.STALLS_L2_MISS - MEMORY_ACTIVITY.STALLS_L3_MISS) / tma_info_clks",
+        "MetricExpr": "(cpu_core@MEMORY_ACTIVITY.STALLS_L2_MISS@ - cpu_core@MEMORY_ACTIVITY.STALLS_L3_MISS@) / tma_info_clks",
         "MetricGroup": "CacheMisses;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group",
         "MetricName": "tma_l3_bound",
         "MetricThreshold": "tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)",
@@ -2030,7 +2030,7 @@
     },
     {
         "BriefDescription": "This metric represents fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited)",
-        "MetricExpr": "9 * tma_info_average_frequency * MEM_LOAD_RETIRED.L3_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_clks",
+        "MetricExpr": "9 * tma_info_average_frequency * cpu_core@MEM_LOAD_RETIRED.L3_HIT@ * (1 + cpu_core@MEM_LOAD_RETIRED.FB_HIT@ / cpu_core@MEM_LOAD_RETIRED.L1_MISS@ / 2) / tma_info_clks",
         "MetricGroup": "MemoryLat;TopdownL4;tma_L4_group;tma_issueLat;tma_l3_bound_group",
         "MetricName": "tma_l3_hit_latency",
         "MetricThreshold": "tma_l3_hit_latency > 0.1 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
@@ -2090,7 +2090,7 @@
     {
         "BriefDescription": "This metric represents fraction of cycles the CPU spent handling cache misses due to lock operations",
         "MetricConstraint": "NO_GROUP_EVENTS",
-        "MetricExpr": "(16 * max(0, MEM_INST_RETIRED.LOCK_LOADS - L2_RQSTS.ALL_RFO) + MEM_INST_RETIRED.LOCK_LOADS / MEM_INST_RETIRED.ALL_STORES * (10 * L2_RQSTS.RFO_HIT + min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO))) / tma_info_clks",
+        "MetricExpr": "(16 * max(0, cpu_core@MEM_INST_RETIRED.LOCK_LOADS@ - cpu_core@L2_RQSTS.ALL_RFO@) + cpu_core@MEM_INST_RETIRED.LOCK_LOADS@ / cpu_core@MEM_INST_RETIRED.ALL_STORES@ * (10 * cpu_core@L2_RQSTS.RFO_HIT@ + min(cpu_core@CPU_CLK_UNHALTED.THREAD@, cpu_core@OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO@))) / tma_info_clks",
         "MetricGroup": "Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_l1_bound_group",
         "MetricName": "tma_lock_latency",
         "MetricThreshold": "tma_lock_latency > 0.2 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
@@ -2100,7 +2100,7 @@
     },
     {
         "BriefDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to LSD (Loop Stream Detector) unit",
-        "MetricExpr": "(LSD.CYCLES_ACTIVE - LSD.CYCLES_OK) / tma_info_core_clks / 2",
+        "MetricExpr": "([email protected]_ACTIVE@ - [email protected]_OK@) / tma_info_core_clks / 2",
         "MetricGroup": "FetchBW;LSD;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group",
         "MetricName": "tma_lsd",
         "MetricThreshold": "tma_lsd > 0.15 & (tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 6 > 0.35)",
@@ -2121,7 +2121,7 @@
     },
     {
         "BriefDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory (DRAM)",
-        "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, cpu_core@OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD\\,cmask\\=4@) / tma_info_clks",
+        "MetricExpr": "min(cpu_core@CPU_CLK_UNHALTED.THREAD@, cpu_core@OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD\\,cmask\\=4@) / tma_info_clks",
         "MetricGroup": "MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueBW",
         "MetricName": "tma_mem_bandwidth",
         "MetricThreshold": "tma_mem_bandwidth > 0.2 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
@@ -2131,7 +2131,7 @@
     },
     {
         "BriefDescription": "This metric estimates fraction of cycles where the performance was likely hurt due to latency from external memory (DRAM)",
-        "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD) / tma_info_clks - tma_mem_bandwidth",
+        "MetricExpr": "min(cpu_core@CPU_CLK_UNHALTED.THREAD@, cpu_core@OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD@) / tma_info_clks - tma_mem_bandwidth",
         "MetricGroup": "MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueLat",
         "MetricName": "tma_mem_latency",
         "MetricThreshold": "tma_mem_latency > 0.1 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
@@ -2141,7 +2141,7 @@
     },
     {
         "BriefDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck",
-        "MetricExpr": "min(tma_backend_bound, LD_HEAD.ANY_AT_RET / tma_info_clks + tma_store_bound)",
+        "MetricExpr": "cpu_core@topdown\\-mem\\-bound@ / (cpu_core@topdown\\-fe\\-bound@ + cpu_core@topdown\\-bad\\-spec@ + cpu_core@topdown\\-retiring@ + cpu_core@topdown\\-be\\-bound@) + 0 * tma_info_slots",
         "MetricGroup": "Backend;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group",
         "MetricName": "tma_memory_bound",
         "MetricThreshold": "tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
@@ -2152,7 +2152,7 @@
     },
     {
         "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to LFENCE Instructions.",
-        "MetricExpr": "13 * MISC2_RETIRED.LFENCE / tma_info_clks",
+        "MetricExpr": "13 * cpu_core@MISC2_RETIRED.LFENCE@ / tma_info_clks",
         "MetricGroup": "TopdownL6;tma_L6_group;tma_serializing_operation_group",
         "MetricName": "tma_memory_fence",
         "MetricThreshold": "tma_memory_fence > 0.05 & (tma_serializing_operation > 0.1 & (tma_ports_utilized_0 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))))",
@@ -2162,7 +2162,7 @@
     {
         "BriefDescription": "This metric represents fraction of slots where the CPU was retiring memory operations -- uops for memory load or store accesses.",
         "MetricConstraint": "NO_GROUP_EVENTS",
-        "MetricExpr": "tma_light_operations * MEM_UOP_RETIRED.ANY / (tma_retiring * tma_info_slots)",
+        "MetricExpr": "tma_light_operations * cpu_core@MEM_UOP_RETIRED.ANY@ / (tma_retiring * tma_info_slots)",
         "MetricGroup": "Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group",
         "MetricName": "tma_memory_operations",
         "MetricThreshold": "tma_memory_operations > 0.1 & tma_light_operations > 0.6",
@@ -2181,7 +2181,7 @@
     },
     {
         "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Branch Misprediction at execution stage",
-        "MetricExpr": "tma_branch_mispredicts / tma_bad_speculation * INT_MISC.CLEAR_RESTEER_CYCLES / tma_info_clks",
+        "MetricExpr": "tma_branch_mispredicts / tma_bad_speculation * cpu_core@INT_MISC.CLEAR_RESTEER_CYCLES@ / tma_info_clks",
         "MetricGroup": "BadSpec;BrMispredicts;TopdownL4;tma_L4_group;tma_branch_resteers_group;tma_issueBM",
         "MetricName": "tma_mispredicts_resteers",
         "MetricThreshold": "tma_mispredicts_resteers > 0.05 & (tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))",
@@ -2191,7 +2191,7 @@
     },
     {
         "BriefDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to the MITE pipeline (the legacy decode pipeline)",
-        "MetricExpr": "(IDQ.MITE_CYCLES_ANY - IDQ.MITE_CYCLES_OK) / tma_info_core_clks / 2",
+        "MetricExpr": "([email protected]_CYCLES_ANY@ - [email protected]_CYCLES_OK@) / tma_info_core_clks / 2",
         "MetricGroup": "DSBmiss;FetchBW;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group",
         "MetricName": "tma_mite",
         "MetricThreshold": "tma_mite > 0.1 & (tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 6 > 0.35)",
@@ -2201,7 +2201,7 @@
     },
     {
         "BriefDescription": "The Mixing_Vectors metric gives the percentage of injected blend uops out of all uops issued",
-        "MetricExpr": "160 * ASSISTS.SSE_AVX_MIX / tma_info_clks",
+        "MetricExpr": "160 * [email protected]_AVX_MIX@ / tma_info_clks",
         "MetricGroup": "TopdownL5;tma_L5_group;tma_issueMV;tma_ports_utilized_0_group",
         "MetricName": "tma_mixing_vectors",
         "MetricThreshold": "tma_mixing_vectors > 0.05",
@@ -2211,7 +2211,7 @@
     },
     {
         "BriefDescription": "This metric estimates the fraction of cycles when the CPU was stalled due to switches of uop delivery to the Microcode Sequencer (MS)",
-        "MetricExpr": "3 * cpu_core@UOPS_RETIRED.MS\\,cmask\\=1\\,edge@ / (tma_retiring * tma_info_slots / UOPS_ISSUED.ANY) / tma_info_clks",
+        "MetricExpr": "3 * cpu_core@UOPS_RETIRED.MS\\,cmask\\=1\\,edge@ / (tma_retiring * tma_info_slots / cpu_core@UOPS_ISSUED.ANY@) / tma_info_clks",
         "MetricGroup": "FetchLat;MicroSeq;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueMC;tma_issueMS;tma_issueMV;tma_issueSO",
         "MetricName": "tma_ms_switches",
         "MetricThreshold": "tma_ms_switches > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)",
@@ -2221,7 +2221,7 @@
     },
     {
         "BriefDescription": "This metric represents fraction of slots where the CPU was retiring branch instructions that were not fused",
-        "MetricExpr": "tma_light_operations * (BR_INST_RETIRED.ALL_BRANCHES - INST_RETIRED.MACRO_FUSED) / (tma_retiring * tma_info_slots)",
+        "MetricExpr": "tma_light_operations * (cpu_core@BR_INST_RETIRED.ALL_BRANCHES@ - cpu_core@INST_RETIRED.MACRO_FUSED@) / (tma_retiring * tma_info_slots)",
         "MetricGroup": "Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group",
         "MetricName": "tma_non_fused_branches",
         "MetricThreshold": "tma_non_fused_branches > 0.1 & tma_light_operations > 0.6",
@@ -2231,7 +2231,7 @@
     },
     {
         "BriefDescription": "This metric represents fraction of slots where the CPU was retiring NOP (no op) instructions",
-        "MetricExpr": "tma_light_operations * INST_RETIRED.NOP / (tma_retiring * tma_info_slots)",
+        "MetricExpr": "tma_light_operations * cpu_core@INST_RETIRED.NOP@ / (tma_retiring * tma_info_slots)",
         "MetricGroup": "Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group",
         "MetricName": "tma_nop_instructions",
         "MetricThreshold": "tma_nop_instructions > 0.1 & tma_light_operations > 0.6",
@@ -2252,7 +2252,7 @@
     },
     {
         "BriefDescription": "This metric roughly estimates fraction of slots the CPU retired uops as a result of handing Page Faults",
-        "MetricExpr": "99 * ASSISTS.PAGE_FAULT / tma_info_slots",
+        "MetricExpr": "99 * [email protected]_FAULT@ / tma_info_slots",
         "MetricGroup": "TopdownL5;tma_L5_group;tma_assists_group",
         "MetricName": "tma_page_faults",
         "MetricThreshold": "tma_page_faults > 0.05",
@@ -2292,7 +2292,7 @@
     },
     {
         "BriefDescription": "This metric estimates fraction of cycles the CPU performance was potentially limited due to Core computation issues (non divider-related)",
-        "MetricExpr": "((cpu_core@EXE_ACTIVITY.3_PORTS_UTIL\\,umask\\=0x80@ + tma_serializing_operation * (CYCLE_ACTIVITY.STALLS_TOTAL - EXE_ACTIVITY.BOUND_ON_LOADS) + (EXE_ACTIVITY.1_PORTS_UTIL + tma_retiring * cpu_core@EXE_ACTIVITY.2_PORTS_UTIL\\,umask\\=0xc@)) / tma_info_clks if ARITH.DIV_ACTIVE < CYCLE_ACTIVITY.STALLS_TOTAL - EXE_ACTIVITY.BOUND_ON_LOADS else (EXE_ACTIVITY.1_PORTS_UTIL + tma_retiring * cpu_core@EXE_ACTIVITY.2_PORTS_UTIL\\,umask\\=0xc@) / tma_info_clks)",
+        "MetricExpr": "((cpu_core@EXE_ACTIVITY.3_PORTS_UTIL\\,umask\\=0x80@ + tma_serializing_operation * (cpu_core@CYCLE_ACTIVITY.STALLS_TOTAL@ - cpu_core@EXE_ACTIVITY.BOUND_ON_LOADS@) + (cpu_core@EXE_ACTIVITY.1_PORTS_UTIL@ + tma_retiring * cpu_core@EXE_ACTIVITY.2_PORTS_UTIL\\,umask\\=0xc@)) / tma_info_clks if [email protected]_ACTIVE@ < cpu_core@CYCLE_ACTIVITY.STALLS_TOTAL@ - cpu_core@EXE_ACTIVITY.BOUND_ON_LOADS@ else (cpu_core@EXE_ACTIVITY.1_PORTS_UTIL@ + tma_retiring * cpu_core@EXE_ACTIVITY.2_PORTS_UTIL\\,umask\\=0xc@) / tma_info_clks)",
         "MetricGroup": "PortsUtil;TopdownL3;tma_L3_group;tma_core_bound_group",
         "MetricName": "tma_ports_utilization",
         "MetricThreshold": "tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)",
@@ -2302,7 +2302,7 @@
     },
     {
         "BriefDescription": "This metric represents fraction of cycles CPU executed no uops on any execution port (Logical Processor cycles since ICL, Physical Core cycles otherwise)",
-        "MetricExpr": "cpu_core@EXE_ACTIVITY.3_PORTS_UTIL\\,umask\\=0x80@ / tma_info_clks + tma_serializing_operation * (CYCLE_ACTIVITY.STALLS_TOTAL - EXE_ACTIVITY.BOUND_ON_LOADS) / tma_info_clks",
+        "MetricExpr": "cpu_core@EXE_ACTIVITY.3_PORTS_UTIL\\,umask\\=0x80@ / tma_info_clks + tma_serializing_operation * (cpu_core@CYCLE_ACTIVITY.STALLS_TOTAL@ - cpu_core@EXE_ACTIVITY.BOUND_ON_LOADS@) / tma_info_clks",
         "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group",
         "MetricName": "tma_ports_utilized_0",
         "MetricThreshold": "tma_ports_utilized_0 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))",
@@ -2342,7 +2342,7 @@
     },
     {
         "BriefDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired",
-        "MetricExpr": "topdown\\-retiring / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * tma_info_slots",
+        "MetricExpr": "cpu_core@topdown\\-retiring@ / (cpu_core@topdown\\-fe\\-bound@ + cpu_core@topdown\\-bad\\-spec@ + cpu_core@topdown\\-retiring@ + cpu_core@topdown\\-be\\-bound@) + 0 * tma_info_slots",
         "MetricGroup": "TmaL1;TopdownL1;tma_L1_group",
         "MetricName": "tma_retiring",
         "MetricThreshold": "tma_retiring > 0.7 | tma_heavy_operations > 0.1",
@@ -2382,7 +2382,7 @@
     },
     {
         "BriefDescription": "This metric estimates fraction of cycles handling memory load split accesses - load that cross 64-byte cache line boundary",
-        "MetricExpr": "tma_info_load_miss_real_latency * LD_BLOCKS.NO_SR / tma_info_clks",
+        "MetricExpr": "tma_info_load_miss_real_latency * cpu_core@LD_BLOCKS.NO_SR@ / tma_info_clks",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group",
         "MetricName": "tma_split_loads",
         "MetricThreshold": "tma_split_loads > 0.2 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
@@ -2402,7 +2402,7 @@
     },
     {
         "BriefDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors)",
-        "MetricExpr": "(XQ.FULL_CYCLES + L1D_PEND_MISS.L2_STALLS) / tma_info_clks",
+        "MetricExpr": "([email protected]_CYCLES@ + cpu_core@L1D_PEND_MISS.L2_STALLS@) / tma_info_clks",
         "MetricGroup": "MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_issueBW;tma_l3_bound_group",
         "MetricName": "tma_sq_full",
         "MetricThreshold": "tma_sq_full > 0.3 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
@@ -2422,7 +2422,7 @@
     },
     {
         "BriefDescription": "This metric roughly estimates fraction of cycles when the memory subsystem had loads blocked since they could not forward data from earlier (in program order) overlapping stores",
-        "MetricExpr": "13 * LD_BLOCKS.STORE_FORWARD / tma_info_clks",
+        "MetricExpr": "13 * cpu_core@LD_BLOCKS.STORE_FORWARD@ / tma_info_clks",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group",
         "MetricName": "tma_store_fwd_blk",
         "MetricThreshold": "tma_store_fwd_blk > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
@@ -2432,7 +2432,7 @@
     },
     {
         "BriefDescription": "This metric estimates fraction of cycles the CPU spent handling L1D store misses",
-        "MetricExpr": "(MEM_STORE_RETIRED.L2_HIT * 10 * (1 - MEM_INST_RETIRED.LOCK_LOADS / MEM_INST_RETIRED.ALL_STORES) + (1 - MEM_INST_RETIRED.LOCK_LOADS / MEM_INST_RETIRED.ALL_STORES) * min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO)) / tma_info_clks",
+        "MetricExpr": "(cpu_core@MEM_STORE_RETIRED.L2_HIT@ * 10 * (1 - cpu_core@MEM_INST_RETIRED.LOCK_LOADS@ / cpu_core@MEM_INST_RETIRED.ALL_STORES@) + (1 - cpu_core@MEM_INST_RETIRED.LOCK_LOADS@ / cpu_core@MEM_INST_RETIRED.ALL_STORES@) * min(cpu_core@CPU_CLK_UNHALTED.THREAD@, cpu_core@OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO@)) / tma_info_clks",
         "MetricGroup": "MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_issueSL;tma_store_bound_group",
         "MetricName": "tma_store_latency",
         "MetricThreshold": "tma_store_latency > 0.1 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
@@ -2442,7 +2442,7 @@
     },
     {
         "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port for Store operations",
-        "MetricExpr": "(UOPS_DISPATCHED.PORT_4_9 + UOPS_DISPATCHED.PORT_7_8) / (4 * tma_info_core_clks)",
+        "MetricExpr": "(cpu_core@UOPS_DISPATCHED.PORT_4_9@ + cpu_core@UOPS_DISPATCHED.PORT_7_8@) / (4 * tma_info_core_clks)",
         "MetricGroup": "TopdownL5;tma_L5_group;tma_ports_utilized_3m_group",
         "MetricName": "tma_store_op_utilization",
         "MetricThreshold": "tma_store_op_utilization > 0.6",
@@ -2470,7 +2470,7 @@
     },
     {
         "BriefDescription": "This metric estimates how often CPU was stalled  due to Streaming store memory accesses; Streaming store optimize out a read request required by RFO stores",
-        "MetricExpr": "9 * OCR.STREAMING_WR.ANY_RESPONSE / tma_info_clks",
+        "MetricExpr": "9 * [email protected]_WR.ANY_RESPONSE@ / tma_info_clks",
         "MetricGroup": "MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_issueSmSt;tma_store_bound_group",
         "MetricName": "tma_streaming_stores",
         "MetricThreshold": "tma_streaming_stores > 0.2 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
@@ -2490,7 +2490,7 @@
     },
     {
         "BriefDescription": "This metric serves as an approximation of legacy x87 usage",
-        "MetricExpr": "tma_retiring * UOPS_EXECUTED.X87 / UOPS_EXECUTED.THREAD",
+        "MetricExpr": "tma_retiring * cpu_core@UOPS_EXECUTED.X87@ / UOPS_EXECUTED.THREAD",
         "MetricGroup": "Compute;TopdownL4;tma_L4_group;tma_fp_arith_group",
         "MetricName": "tma_x87_use",
         "MetricThreshold": "tma_x87_use > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6)",
tools/perf/pmu-events/arch/x86/alderlaken/adln-metrics.json +3 -3
index 0402adbf7d92..f4b3c3883643 100644
@@ -193,7 +193,7 @@
     {
         "BriefDescription": "Counts the number of cycles the core is stalled due to a demand load miss which hit in DRAM or MMIO (Non-DRAM).",
         "MetricConstraint": "NO_GROUP_EVENTS",
-        "MetricExpr": "MEM_BOUND_STALLS.LOAD_DRAM_HIT / tma_info_clks - MEM_BOUND_STALLS_AT_RET_CORRECTION * MEM_BOUND_STALLS.LOAD_DRAM_HIT / MEM_BOUND_STALLS.LOAD",
+        "MetricExpr": "MEM_BOUND_STALLS.LOAD_DRAM_HIT / tma_info_clks - max((MEM_BOUND_STALLS.LOAD - LD_HEAD.L1_MISS_AT_RET) / tma_info_clks, 0) * MEM_BOUND_STALLS.LOAD_DRAM_HIT / MEM_BOUND_STALLS.LOAD",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_memory_bound_group",
         "MetricName": "tma_dram_bound",
         "MetricThreshold": "tma_dram_bound > 0.1",
@@ -480,7 +480,7 @@
     {
         "BriefDescription": "Counts the number of cycles a core is stalled due to a demand load which hit in the L2 Cache.",
         "MetricConstraint": "NO_GROUP_EVENTS",
-        "MetricExpr": "MEM_BOUND_STALLS.LOAD_L2_HIT / tma_info_clks - MEM_BOUND_STALLS_AT_RET_CORRECTION * MEM_BOUND_STALLS.LOAD_L2_HIT / MEM_BOUND_STALLS.LOAD",
+        "MetricExpr": "MEM_BOUND_STALLS.LOAD_L2_HIT / tma_info_clks - max((MEM_BOUND_STALLS.LOAD - LD_HEAD.L1_MISS_AT_RET) / tma_info_clks, 0) * MEM_BOUND_STALLS.LOAD_L2_HIT / MEM_BOUND_STALLS.LOAD",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_memory_bound_group",
         "MetricName": "tma_l2_bound",
         "MetricThreshold": "tma_l2_bound > 0.1",
@@ -488,7 +488,7 @@
     },
     {
         "BriefDescription": "Counts the number of cycles a core is stalled due to a demand load which hit in the Last Level Cache (LLC) or other core with HITE/F/M.",
-        "MetricExpr": "MEM_BOUND_STALLS.LOAD_LLC_HIT / tma_info_clks - MEM_BOUND_STALLS_AT_RET_CORRECTION * MEM_BOUND_STALLS.LOAD_LLC_HIT / MEM_BOUND_STALLS.LOAD",
+        "MetricExpr": "MEM_BOUND_STALLS.LOAD_LLC_HIT / tma_info_clks - max((MEM_BOUND_STALLS.LOAD - LD_HEAD.L1_MISS_AT_RET) / tma_info_clks, 0) * MEM_BOUND_STALLS.LOAD_LLC_HIT / MEM_BOUND_STALLS.LOAD",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_memory_bound_group",
         "MetricName": "tma_l3_bound",
         "MetricThreshold": "tma_l3_bound > 0.1",
Signature · 1 line
2.40.1.495.gc816e09b53d-goog
author reviewer
#45 lore raw

PATCH v4 41/44 perf jevents: Don't rewrite metrics across PMUs

In reply to Ian Rogers

Don't rewrite metrics across PMUs as the result events likely won't be found. Identify metrics with a pair of PMU name and metric name.

---
 tools/perf/pmu-events/jevents.py     |  4 ++--
 tools/perf/pmu-events/metric.py      | 28 +++++++++++++++++-----------
 tools/perf/pmu-events/metric_test.py |  6 +++---
 3 files changed, 22 insertions(+), 16 deletions(-)
tools/perf/pmu-events/jevents.py +2 -2
index b18dd2fcbf04..487ff01baf1b 100755
@@ -391,11 +391,11 @@ def read_json_events(path: str, topic: str) -> Sequence[JsonEvent]:
   except BaseException as err:
     print(f"Exception processing {path}")
     raise
-  metrics: list[Tuple[str, metric.Expression]] = []
+  metrics: list[Tuple[str, str, metric.Expression]] = []
   for event in events:
     event.topic = topic
     if event.metric_name and '-' not in event.metric_name:
-      metrics.append((event.metric_name, event.metric_expr))
+      metrics.append((event.pmu, event.metric_name, event.metric_expr))
   updates = metric.RewriteMetricsInTermsOfOthers(metrics)
   if updates:
     for event in events:
tools/perf/pmu-events/metric.py +17 -11
index 8ec0ba884673..af58b74d1644 100644
@@ -552,28 +552,34 @@ def ParsePerfJson(orig: str) -> Expression:
   return _Constify(eval(compile(parsed, orig, 'eval')))
 
 
-def RewriteMetricsInTermsOfOthers(metrics: List[Tuple[str, Expression]]
-                                  )-> Dict[str, Expression]:
+def RewriteMetricsInTermsOfOthers(metrics: List[Tuple[str, str, Expression]]
+                                  )-> Dict[Tuple[str, str], Expression]:
   """Shorten metrics by rewriting in terms of others.
 
   Args:
-    metrics (list): pairs of metric names and their expressions.
+    metrics (list): pmus, metric names and their expressions.
   Returns:
-    Dict: mapping from a metric name to a shortened expression.
+    Dict: mapping from a pmu, metric name pair to a shortened expression.
   """
-  updates: Dict[str, Expression] = dict()
-  for outer_name, outer_expression in metrics:
+  updates: Dict[Tuple[str, str], Expression] = dict()
+  for outer_pmu, outer_name, outer_expression in metrics:
+    if outer_pmu is None:
+      outer_pmu = 'cpu'
     updated = outer_expression
     while True:
-      for inner_name, inner_expression in metrics:
+      for inner_pmu, inner_name, inner_expression in metrics:
+        if inner_pmu is None:
+          inner_pmu = 'cpu'
+        if inner_pmu.lower() != outer_pmu.lower():
+          continue
         if inner_name.lower() == outer_name.lower():
           continue
-        if inner_name in updates:
-          inner_expression = updates[inner_name]
+        if (inner_pmu, inner_name) in updates:
+          inner_expression = updates[(inner_pmu, inner_name)]
         updated = updated.Substitute(inner_name, inner_expression)
       if updated.Equals(outer_expression):
         break
-      if outer_name in updates and updated.Equals(updates[outer_name]):
+      if (outer_pmu, outer_name) in updates and updated.Equals(updates[(outer_pmu, outer_name)]):
         break
-      updates[outer_name] = updated
+      updates[(outer_pmu, outer_name)] = updated
   return updates
tools/perf/pmu-events/metric_test.py +3 -3
index 40a3c7d8b2bc..ee22ff43ddd7 100755
@@ -158,9 +158,9 @@ class TestMetricExpressions(unittest.TestCase):
 
   def test_RewriteMetricsInTermsOfOthers(self):
     Expression.__eq__ = lambda e1, e2: e1.Equals(e2)
-    before = [('m1', ParsePerfJson('a + b + c + d')),
-              ('m2', ParsePerfJson('a + b + c'))]
-    after = {'m1': ParsePerfJson('m2 + d')}
+    before = [('cpu', 'm1', ParsePerfJson('a + b + c + d')),
+              ('cpu', 'm2', ParsePerfJson('a + b + c'))]
+    after = {('cpu', 'm1'): ParsePerfJson('m2 + d')}
     self.assertEqual(RewriteMetricsInTermsOfOthers(before), after)
     Expression.__eq__ = None
 
Signature · 1 line
2.40.1.495.gc816e09b53d-goog
author reviewer
#46 lore raw

PATCH v4 42/44 perf metrics: Be PMU specific in event match

In reply to Ian Rogers

Ids/events from a metric are turned into an event string and parsed; setup_metric_events matches the id back to the parsed evsel. With hybrid the same event may exist on both PMUs with the same name and be being used by metrics at the same time. A metric on cpu_core therefore shouldn't match against evsels on cpu_atom, or the metric will compute the wrong value. Make the matching sensitive to the PMU being parsed.

---
 tools/perf/util/metricgroup.c | 10 +++++++---
 1 file changed, 7 insertions(+), 3 deletions(-)
tools/perf/util/metricgroup.c +7 -3
index 4245b23d8efe..490561f430f2 100644
@@ -274,7 +274,7 @@ static int setup_metric_events(const char *pmu, struct hashmap *ids,
 	const char *metric_id;
 	struct evsel *ev;
 	size_t ids_size, matched_events, i;
-	bool all_pmus = !strcmp(pmu, "all");
+	bool all_pmus = !strcmp(pmu, "all") || !perf_pmu__is_hybrid(pmu);
 
 	*out_metric_events = NULL;
 	ids_size = hashmap__size(ids);
@@ -287,7 +287,10 @@ static int setup_metric_events(const char *pmu, struct hashmap *ids,
 	evlist__for_each_entry(metric_evlist, ev) {
 		struct expr_id_data *val_ptr;
 
-		if (!all_pmus && strcmp(ev->pmu_name, pmu))
+		/* Don't match events for the wrong hybrid PMU. */
+		if (!all_pmus && ev->pmu_name &&
+		    perf_pmu__is_hybrid(ev->pmu_name) &&
+		    strcmp(ev->pmu_name, pmu))
 			continue;
 		/*
 		 * Check for duplicate events with the same name. For
@@ -304,6 +307,7 @@ static int setup_metric_events(const char *pmu, struct hashmap *ids,
 		 * about this event.
 		 */
 		if (hashmap__find(ids, metric_id, &val_ptr)) {
+			pr_debug("Matched metric-id %s to %s\n", metric_id, evsel__name(ev));
 			metric_events[matched_events++] = ev;
 
 			if (matched_events >= ids_size)
@@ -1592,7 +1596,7 @@ static int parse_groups(struct evlist *perf_evlist,
 		ret = setup_metric_events(fake_pmu ? "all" : m->pmu, m->pctx->ids,
 					  metric_evlist, &metric_events);
 		if (ret) {
-			pr_debug("Cannot resolve IDs for %s: %s\n",
+			pr_err("Cannot resolve IDs for %s: %s\n",
 				m->metric_name, m->metric_expr);
 			goto out;
 		}
Signature · 1 line
2.40.1.495.gc816e09b53d-goog
author reviewer
#47 lore raw

PATCH v4 43/44 perf stat: Don't disable TopdownL1 metric on hybrid

In reply to Ian Rogers

Now that hybrid bugs are fixed sufficient to run TopdownL1 metrics, don't implicitly disable them for hybrid.

---
 tools/perf/builtin-stat.c | 7 +------
 1 file changed, 1 insertion(+), 6 deletions(-)
tools/perf/builtin-stat.c +1 -6
index f4e572f9de6b..67dc69270ae4 100644
@@ -1900,12 +1900,7 @@ static int add_default_attributes(void)
 		 * Add TopdownL1 metrics if they exist. To minimize
 		 * multiplexing, don't request threshold computation.
 		 */
-		/*
-		 * TODO: TopdownL1 is disabled on hybrid CPUs to avoid a crashes
-		 * caused by exposing latent bugs. This is fixed properly in:
-		 * https://lore.kernel.org/lkml/[email protected]/
-		 */
-		if (metricgroup__has_metric(pmu, "TopdownL1") && !perf_pmu__has_hybrid()) {
+		if (metricgroup__has_metric(pmu, "TopdownL1")) {
 			struct evlist *metric_evlist = evlist__new();
 			struct evsel *metric_evsel;
 
Signature · 1 line
2.40.1.495.gc816e09b53d-goog
author reviewer
#48 lore raw

PATCH v4 44/44 perf parse-events: Reduce scope of is_event_supported

In reply to Ian Rogers

Move to print-events.c and make static.

---
 tools/perf/util/parse-events.c | 39 ----------------------------------
 tools/perf/util/parse-events.h |  2 --
 tools/perf/util/print-events.c | 39 ++++++++++++++++++++++++++++++++++
 3 files changed, 39 insertions(+), 41 deletions(-)
tools/perf/util/parse-events.c +0 -39
index 2dad88a6bf19..b93264f8a37c 100644
@@ -28,7 +28,6 @@
 #include "util/bpf-filter.h"
 #include "util/util.h"
 #include "tracepoint.h"
-#include "thread_map.h"
 
 #define MAX_NAME_LEN 100
 
@@ -133,44 +132,6 @@ struct event_symbol event_symbols_sw[PERF_COUNT_SW_MAX] = {
 	},
 };
 
-bool is_event_supported(u8 type, u64 config)
-{
-	bool ret = true;
-	int open_return;
-	struct evsel *evsel;
-	struct perf_event_attr attr = {
-		.type = type,
-		.config = config,
-		.disabled = 1,
-	};
-	struct perf_thread_map *tmap = thread_map__new_by_tid(0);
-
-	if (tmap == NULL)
-		return false;
-
-	evsel = evsel__new(&attr);
-	if (evsel) {
-		open_return = evsel__open(evsel, NULL, tmap);
-		ret = open_return >= 0;
-
-		if (open_return == -EACCES) {
-			/*
-			 * This happens if the paranoid value
-			 * /proc/sys/kernel/perf_event_paranoid is set to 2
-			 * Re-run with exclude_kernel set; we don't do that
-			 * by default as some ARM machines do not support it.
-			 *
-			 */
-			evsel->core.attr.exclude_kernel = 1;
-			ret = evsel__open(evsel, NULL, tmap) >= 0;
-		}
-		evsel__delete(evsel);
-	}
-
-	perf_thread_map__put(tmap);
-	return ret;
-}
-
 const char *event_type(int type)
 {
 	switch (type) {
tools/perf/util/parse-events.h +0 -2
index 2a8cafe0ee8f..2021fe145410 100644
@@ -18,8 +18,6 @@ struct parse_events_error;
 struct option;
 struct perf_pmu;
 
-bool is_event_supported(u8 type, u64 config);
-
 const char *event_type(int type);
 
 /* Arguments encoded in opt->value. */
tools/perf/util/print-events.c +39 -0
index d148842b205a..69492cbd6921 100644
@@ -27,6 +27,7 @@
 #include "tracepoint.h"
 #include "pfm.h"
 #include "pmu-hybrid.h"
+#include "thread_map.h"
 
 #define MAX_NAME_LEN 100
 
@@ -228,6 +229,44 @@ void print_sdt_events(const struct print_callbacks *print_cb, void *print_state)
 	strlist__delete(sdtlist);
 }
 
+static bool is_event_supported(u8 type, u64 config)
+{
+	bool ret = true;
+	int open_return;
+	struct evsel *evsel;
+	struct perf_event_attr attr = {
+		.type = type,
+		.config = config,
+		.disabled = 1,
+	};
+	struct perf_thread_map *tmap = thread_map__new_by_tid(0);
+
+	if (tmap == NULL)
+		return false;
+
+	evsel = evsel__new(&attr);
+	if (evsel) {
+		open_return = evsel__open(evsel, NULL, tmap);
+		ret = open_return >= 0;
+
+		if (open_return == -EACCES) {
+			/*
+			 * This happens if the paranoid value
+			 * /proc/sys/kernel/perf_event_paranoid is set to 2
+			 * Re-run with exclude_kernel set; we don't do that
+			 * by default as some ARM machines do not support it.
+			 *
+			 */
+			evsel->core.attr.exclude_kernel = 1;
+			ret = evsel__open(evsel, NULL, tmap) >= 0;
+		}
+		evsel__delete(evsel);
+	}
+
+	perf_thread_map__put(tmap);
+	return ret;
+}
+
 int print_hwcache_events(const struct print_callbacks *print_cb, void *print_state)
 {
 	struct perf_pmu *pmu = NULL;
Signature · 1 line
2.40.1.495.gc816e09b53d-goog
#49 lore raw
In reply to Ian Rogers
Quoted 51 lines · Ian Rogers

TL;DR: hybrid doesn't crash, json metrics work on hybrid on both PMUs or individually, event parsing doesn't always scan all PMUs, more and new tests that also run without hybrid, less code.

The first 4 patches are aimed at Linux 6.4 to address issues raised, in particular by Kan, on the existing perf stat behavior with json metrics. They avoid duplicated events by removing groups. They don't hide events and metrics to make event multiplexing obvious. They avoid terminating perf when paranoia is higher due to certain events that always fail. They avoid rearranging events by PMUs when the events aren't in a group.

The next 5 patches avoid grouping events for metrics where they could never succeed and were previously posted as:
"perf vendor events intel: Add xxx metric constraints"
https://lore.kernel.org/all/[email protected]/
In general the generated json is coming from:
https://github.com/intel/perfmon/pull/73

Next are some general and test improvements.

Next event parsing is rewritten to not scan all PMUs for the benefit of raw and legacy cache parsing, instead these are handled by the lexer and a new term type. This ultimately removes the need for the event parser for hybrid to be recursive as legacy cache can be just a term. Tests are re-enabled for events with hyphens, so AMD's branch-brs event is now parsable.

The cputype option is made a generic pmu filter flag and is tested even on non-hybrid systems.

The final patches address specific json metric issues on hybrid, in both the json metrics and the metric code.

The patches add slightly more code than they remove, in areas like better json metric constraints and tests, but in the core util code, the removal of hybrid is a net reduction:

 22 files changed, 711 insertions(+), 1016 deletions(-)

Sample output is contained in the v1 patch set:
https://lore.kernel.org/lkml/[email protected]/

Tested on Tigerlake, Skylake and Alderlake CPUs.

The v4 patch set:
- rebase, 1 of the Linux 6.4 recommended patches are merged leaving:
1) perf metric: Change divide by zero and !support events behavior
2) perf stat: Introduce skippable evsels
3) perf metric: Json flag to not group events if gathering a metric group
4) perf parse-events: Don't reorder ungrouped events by pmu whose diffstat is:

Quoted 4 lines
    30 files changed, 326 insertions(+), 33 deletions(-)
   but without the vendor event updates (the tend to be large as they
   repeat something per architecture per metric) is just:
    10 files changed, 90 insertions(+), 32 deletions(-)

I have tested the 4 patches on top of the perf-tools-next branch on both Cascade Lake and Raptor Lake. The result looks good to me.

They address the permission error found in the default mode of perf stat on the Cascade Lake. Thanks Ian for the fix.

Arnaldo, could you please consider to back port them for the 6.4?

Thanks,
Kan

#50 lore raw

Em Wed, May 03, 2023 at 04:56:36PM -0400, Liang, Kan escreveu:

Quoted 59 lines · Ian Rogers
Quoted 51 lines

TL;DR: hybrid doesn't crash, json metrics work on hybrid on both PMUs or individually, event parsing doesn't always scan all PMUs, more and new tests that also run without hybrid, less code.

The first 4 patches are aimed at Linux 6.4 to address issues raised, in particular by Kan, on the existing perf stat behavior with json metrics. They avoid duplicated events by removing groups. They don't hide events and metrics to make event multiplexing obvious. They avoid terminating perf when paranoia is higher due to certain events that always fail. They avoid rearranging events by PMUs when the events aren't in a group.

The next 5 patches avoid grouping events for metrics where they could never succeed and were previously posted as:
"perf vendor events intel: Add xxx metric constraints"
https://lore.kernel.org/all/[email protected]/
In general the generated json is coming from:
https://github.com/intel/perfmon/pull/73

Next are some general and test improvements.

Next event parsing is rewritten to not scan all PMUs for the benefit of raw and legacy cache parsing, instead these are handled by the lexer and a new term type. This ultimately removes the need for the event parser for hybrid to be recursive as legacy cache can be just a term. Tests are re-enabled for events with hyphens, so AMD's branch-brs event is now parsable.

The cputype option is made a generic pmu filter flag and is tested even on non-hybrid systems.

The final patches address specific json metric issues on hybrid, in both the json metrics and the metric code.

The patches add slightly more code than they remove, in areas like better json metric constraints and tests, but in the core util code, the removal of hybrid is a net reduction:

 22 files changed, 711 insertions(+), 1016 deletions(-)

Sample output is contained in the v1 patch set:
https://lore.kernel.org/lkml/[email protected]/

Tested on Tigerlake, Skylake and Alderlake CPUs.

The v4 patch set:
- rebase, 1 of the Linux 6.4 recommended patches are merged leaving:
1) perf metric: Change divide by zero and !support events behavior
2) perf stat: Introduce skippable evsels
3) perf metric: Json flag to not group events if gathering a metric group
4) perf parse-events: Don't reorder ungrouped events by pmu whose diffstat is:

Quoted 4 lines
    30 files changed, 326 insertions(+), 33 deletions(-)
   but without the vendor event updates (the tend to be large as they
   repeat something per architecture per metric) is just:
    10 files changed, 90 insertions(+), 32 deletions(-)
Quoted 7 lines

I have tested the 4 patches on top of the perf-tools-next branch on both Cascade Lake and Raptor Lake. The result looks good to me.

They address the permission error found in the default mode of perf stat on the Cascade Lake. Thanks Ian for the fix.

Arnaldo, could you please consider to back port them for the 6.4?

Yes, its in perf-tools now, will go to Linus next week.

What about the other patches? I saw some you provided your review, what about the others, are you ok with them?

- Arnaldo

Tested-by
#51 lore raw
Quoted 63 lines · Arnaldo Carvalho de Melo

Em Wed, May 03, 2023 at 04:56:36PM -0400, Liang, Kan escreveu:

Quoted 62 lines · Ian Rogers
Quoted 51 lines

TL;DR: hybrid doesn't crash, json metrics work on hybrid on both PMUs or individually, event parsing doesn't always scan all PMUs, more and new tests that also run without hybrid, less code.

The first 4 patches are aimed at Linux 6.4 to address issues raised, in particular by Kan, on the existing perf stat behavior with json metrics. They avoid duplicated events by removing groups. They don't hide events and metrics to make event multiplexing obvious. They avoid terminating perf when paranoia is higher due to certain events that always fail. They avoid rearranging events by PMUs when the events aren't in a group.

The next 5 patches avoid grouping events for metrics where they could never succeed and were previously posted as:
"perf vendor events intel: Add xxx metric constraints"
https://lore.kernel.org/all/[email protected]/
In general the generated json is coming from:
https://github.com/intel/perfmon/pull/73

Next are some general and test improvements.

Next event parsing is rewritten to not scan all PMUs for the benefit of raw and legacy cache parsing, instead these are handled by the lexer and a new term type. This ultimately removes the need for the event parser for hybrid to be recursive as legacy cache can be just a term. Tests are re-enabled for events with hyphens, so AMD's branch-brs event is now parsable.

The cputype option is made a generic pmu filter flag and is tested even on non-hybrid systems.

The final patches address specific json metric issues on hybrid, in both the json metrics and the metric code.

The patches add slightly more code than they remove, in areas like better json metric constraints and tests, but in the core util code, the removal of hybrid is a net reduction:

 22 files changed, 711 insertions(+), 1016 deletions(-)

Sample output is contained in the v1 patch set:
https://lore.kernel.org/lkml/[email protected]/

Tested on Tigerlake, Skylake and Alderlake CPUs.

The v4 patch set:
- rebase, 1 of the Linux 6.4 recommended patches are merged leaving:
1) perf metric: Change divide by zero and !support events behavior
2) perf stat: Introduce skippable evsels
3) perf metric: Json flag to not group events if gathering a metric group
4) perf parse-events: Don't reorder ungrouped events by pmu whose diffstat is:

Quoted 4 lines
    30 files changed, 326 insertions(+), 33 deletions(-)
   but without the vendor event updates (the tend to be large as they
   repeat something per architecture per metric) is just:
    10 files changed, 90 insertions(+), 32 deletions(-)

I have tested the 4 patches on top of the perf-tools-next branch on both Cascade Lake and Raptor Lake. The result looks good to me.

Quoted 6 lines
Quoted 4 lines

They address the permission error found in the default mode of perf stat on the Cascade Lake. Thanks Ian for the fix.

Arnaldo, could you please consider to back port them for the 6.4?

Yes, its in perf-tools now, will go to Linus next week.

Thanks Arnaldo!

Quoted 4 lines

What about the other patches? I saw some you provided your review, what about the others, are you ok with them?

Yes, I'm OK with the patch set. It fixes many issues. Thanks Ian. (My tests mainly focus on the area in which the patch set may touch. I did the tests on various platforms, ADL (hybrid), Cascade Lake, SPR.)

But there are still some issues. I don't think they are introduced by this patch set. We may fix them later separately.

- Segmentation fault with perf stat --topdown on ADL (hybrid) and Cascade Lake.
It looks like a legacy issue, may not be introduced by this patch set. Here is the backtrace. It looks like there is a NULL metric_group.

(gdb) backtrace
#0 0x00007ffff73035d1 in __strstr_sse2_unaligned () from /lib64/libc.so.6 #1 0x00000000004f9019 in metricgroup__topdown_max_level_callback (pm=<optimized out>, table=<optimized out>,

    data=0x7fffffff92f4) at util/metricgroup.c:1722
#2  0x00000000005e8a31 in pmu_metrics_table_for_each_metric
(table=0xcb74d0 <pmu_events_map+368>,
    fn=fn@entry=0x4f8ff0 <metricgroup__topdown_max_level_callback>,
data=data@entry=0x7fffffff92f4)
    at pmu-events/pmu-events.c:61123
#3  0x00000000004fbc3b in metricgroups__topdown_max_level () at
util/metricgroup.c:1742
#4  0x000000000042c135 in add_default_attributes () at builtin-stat.c:1845
#5  cmd_stat (argc=0, argv=0x7fffffffe3e0) at builtin-stat.c:2446
#6  0x00000000004b922b in run_builtin (p=p@entry=0xd5c530
<commands+336>, argc=argc@entry=2,
    argv=argv@entry=0x7fffffffe3e0) at perf.c:323

#7 0x000000000040e373 in handle_internal_command (argv=0x7fffffffe3e0, argc=2) at perf.c:377
#8 run_argv (argv=<synthetic pointer>, argcp=<synthetic pointer>) at perf.c:421
#9 main (argc=2, argv=0x7fffffffe3e0) at perf.c:537
(gdb)

Also, the return type is unsigned int, but a bool is given.

unsigned int metricgroups__topdown_max_level(void)

{
        unsigned int max_level = 0;
        const struct pmu_metrics_table *table = pmu_metrics_table__find();

        if (!table)
                return false;

- The perf metric and metricgroups fail on different platforms. Ian and I have discussed it. We agree to address it later separately.

102: perf all metricgroups test
ADL (hybrid)
103: perf all metrics test
ADL (hybrid), Cascade Lake, SPR

- perf list: The [Kernel PMU event] is missed for all the hardware cache events.
It impacts both hybrid and non-hybrid platforms.
It's a user-visible change introduced by the patch set.
I don't know if anyone cares whether it's a kernel event or a regular
event. It doesn't bother me. So I'm OK with it.

cpu:
L1-dcache-loads OR cpu/L1-dcache-loads/ L1-dcache-load-misses OR cpu/L1-dcache-load-misses/ L1-dcache-stores OR cpu/L1-dcache-stores/ L1-icache-load-misses OR cpu/L1-icache-load-misses/ LLC-loads OR cpu/LLC-loads/
LLC-load-misses OR cpu/LLC-load-misses/ LLC-stores OR cpu/LLC-stores/ LLC-store-misses OR cpu/LLC-store-misses/ dTLB-loads OR cpu/dTLB-loads/ dTLB-load-misses OR cpu/dTLB-load-misses/ dTLB-stores OR cpu/dTLB-stores/ dTLB-store-misses OR cpu/dTLB-store-misses/ iTLB-load-misses OR cpu/iTLB-load-misses/ branch-loads OR cpu/branch-loads/ branch-load-misses OR cpu/branch-load-misses/ node-loads OR cpu/node-loads/ node-load-misses OR cpu/node-load-misses/

  branch-instructions OR cpu/branch-instructions/    [Kernel PMU event]
  branch-misses OR cpu/branch-misses/                [Kernel PMU event]
  bus-cycles OR cpu/bus-cycles/                      [Kernel PMU event]
  cache-misses OR cpu/cache-misses/                  [Kernel PMU event]
  cache-references OR cpu/cache-references/          [Kernel PMU event]
  cpu-cycles OR cpu/cpu-cycles/                      [Kernel PMU event]
  instructions OR cpu/instructions/                  [Kernel PMU event]

- The --cputype only works for the metric in the default mode. I can still see the cpu_atom events with --cputype core It may be something we can improve later.

# ./perf stat --cputype core sleep 2

Performance counter stats for 'sleep 2':

0.52 msec task-clock # 0.000 CPUs
utilized

                 1      context-switches                 #    1.939 K/sec
                 0      cpu-migrations                   #    0.000 /sec
                69      page-faults                      #  133.770 K/sec
         2,569,423      cpu_core/cycles/                 #    4.981 G/sec
     <not counted>      cpu_atom/cycles/
                       (0.00%)
         3,287,691      cpu_core/instructions/           #    6.374 G/sec
     <not counted>      cpu_atom/instructions/
                       (0.00%)
           555,848      cpu_core/branches/               #    1.078 G/sec
     <not counted>      cpu_atom/branches/
                       (0.00%)
             8,398      cpu_core/branch-misses/          #   16.281 M/sec
     <not counted>      cpu_atom/branch-misses/
                       (0.00%)
        15,416,538      cpu_core/TOPDOWN.SLOTS/          #     36.1 %
tma_backend_bound
                                                  #     23.9 %  tma_retiring
                                                  #      5.6 %
tma_bad_speculation
                                                  #     34.4 %
tma_frontend_bound
         3,687,877      cpu_core/topdown-retiring/
           846,398      cpu_core/topdown-bad-spec/
         5,320,217      cpu_core/topdown-fe-bound/
         5,562,045      cpu_core/topdown-be-bound/
            14,149      cpu_core/INT_MISC.UOP_DROPPING/  #   27.431 M/sec

Thanks,
Kan

#52 lore raw

Em Sun, May 14, 2023 at 08:03:38AM -0400, Liang, Kan escreveu:

Quoted 76 lines · Arnaldo Carvalho de Melo
Quoted 61 lines

Em Wed, May 03, 2023 at 04:56:36PM -0400, Liang, Kan escreveu:

Quoted 60 lines · Ian Rogers
Quoted 51 lines

TL;DR: hybrid doesn't crash, json metrics work on hybrid on both PMUs or individually, event parsing doesn't always scan all PMUs, more and new tests that also run without hybrid, less code.

The first 4 patches are aimed at Linux 6.4 to address issues raised, in particular by Kan, on the existing perf stat behavior with json metrics. They avoid duplicated events by removing groups. They don't hide events and metrics to make event multiplexing obvious. They avoid terminating perf when paranoia is higher due to certain events that always fail. They avoid rearranging events by PMUs when the events aren't in a group.

The next 5 patches avoid grouping events for metrics where they could never succeed and were previously posted as:
"perf vendor events intel: Add xxx metric constraints"
https://lore.kernel.org/all/[email protected]/
In general the generated json is coming from:
https://github.com/intel/perfmon/pull/73

Next are some general and test improvements.

Next event parsing is rewritten to not scan all PMUs for the benefit of raw and legacy cache parsing, instead these are handled by the lexer and a new term type. This ultimately removes the need for the event parser for hybrid to be recursive as legacy cache can be just a term. Tests are re-enabled for events with hyphens, so AMD's branch-brs event is now parsable.

The cputype option is made a generic pmu filter flag and is tested even on non-hybrid systems.

The final patches address specific json metric issues on hybrid, in both the json metrics and the metric code.

The patches add slightly more code than they remove, in areas like better json metric constraints and tests, but in the core util code, the removal of hybrid is a net reduction:

 22 files changed, 711 insertions(+), 1016 deletions(-)

Sample output is contained in the v1 patch set:
https://lore.kernel.org/lkml/[email protected]/

Tested on Tigerlake, Skylake and Alderlake CPUs.

The v4 patch set:
- rebase, 1 of the Linux 6.4 recommended patches are merged leaving:
1) perf metric: Change divide by zero and !support events behavior
2) perf stat: Introduce skippable evsels
3) perf metric: Json flag to not group events if gathering a metric group
4) perf parse-events: Don't reorder ungrouped events by pmu whose diffstat is:

Quoted 4 lines
    30 files changed, 326 insertions(+), 33 deletions(-)
   but without the vendor event updates (the tend to be large as they
   repeat something per architecture per metric) is just:
    10 files changed, 90 insertions(+), 32 deletions(-)

I have tested the 4 patches on top of the perf-tools-next branch on both Cascade Lake and Raptor Lake. The result looks good to me.

Quoted 6 lines
Quoted 4 lines

They address the permission error found in the default mode of perf stat on the Cascade Lake. Thanks Ian for the fix.

Arnaldo, could you please consider to back port them for the 6.4?

Yes, its in perf-tools now, will go to Linus next week.

Thanks Arnaldo!

Quoted 4 lines

What about the other patches? I saw some you provided your review, what about the others, are you ok with them?

Quoted 5 lines

Yes, I'm OK with the patch set. It fixes many issues. Thanks Ian. (My tests mainly focus on the area in which the patch set may touch. I did the tests on various platforms, ADL (hybrid), Cascade Lake, SPR.)

Thanks!

Quoted 2 lines

But there are still some issues. I don't think they are introduced by this patch set. We may fix them later separately.

Yeah, look forward to receiving the patches :-)

- Arnaldo

Quoted 124 lines

- Segmentation fault with perf stat --topdown on ADL (hybrid) and Cascade Lake.
It looks like a legacy issue, may not be introduced by this patch set. Here is the backtrace. It looks like there is a NULL metric_group.

(gdb) backtrace
#0 0x00007ffff73035d1 in __strstr_sse2_unaligned () from /lib64/libc.so.6 #1 0x00000000004f9019 in metricgroup__topdown_max_level_callback (pm=<optimized out>, table=<optimized out>,

    data=0x7fffffff92f4) at util/metricgroup.c:1722
#2  0x00000000005e8a31 in pmu_metrics_table_for_each_metric
(table=0xcb74d0 <pmu_events_map+368>,
    fn=fn@entry=0x4f8ff0 <metricgroup__topdown_max_level_callback>,
data=data@entry=0x7fffffff92f4)
    at pmu-events/pmu-events.c:61123
#3  0x00000000004fbc3b in metricgroups__topdown_max_level () at
util/metricgroup.c:1742
#4  0x000000000042c135 in add_default_attributes () at builtin-stat.c:1845
#5  cmd_stat (argc=0, argv=0x7fffffffe3e0) at builtin-stat.c:2446
#6  0x00000000004b922b in run_builtin (p=p@entry=0xd5c530
<commands+336>, argc=argc@entry=2,
    argv=argv@entry=0x7fffffffe3e0) at perf.c:323

#7 0x000000000040e373 in handle_internal_command (argv=0x7fffffffe3e0, argc=2) at perf.c:377
#8 run_argv (argv=<synthetic pointer>, argcp=<synthetic pointer>) at perf.c:421
#9 main (argc=2, argv=0x7fffffffe3e0) at perf.c:537
(gdb)

Also, the return type is unsigned int, but a bool is given.

unsigned int metricgroups__topdown_max_level(void)

{
        unsigned int max_level = 0;
        const struct pmu_metrics_table *table = pmu_metrics_table__find();

        if (!table)
                return false;

- The perf metric and metricgroups fail on different platforms. Ian and I have discussed it. We agree to address it later separately.

102: perf all metricgroups test
ADL (hybrid)
103: perf all metrics test
ADL (hybrid), Cascade Lake, SPR

- perf list: The [Kernel PMU event] is missed for all the hardware cache events.
It impacts both hybrid and non-hybrid platforms.
It's a user-visible change introduced by the patch set.
I don't know if anyone cares whether it's a kernel event or a regular
event. It doesn't bother me. So I'm OK with it.

cpu:
L1-dcache-loads OR cpu/L1-dcache-loads/ L1-dcache-load-misses OR cpu/L1-dcache-load-misses/ L1-dcache-stores OR cpu/L1-dcache-stores/ L1-icache-load-misses OR cpu/L1-icache-load-misses/ LLC-loads OR cpu/LLC-loads/
LLC-load-misses OR cpu/LLC-load-misses/ LLC-stores OR cpu/LLC-stores/ LLC-store-misses OR cpu/LLC-store-misses/ dTLB-loads OR cpu/dTLB-loads/ dTLB-load-misses OR cpu/dTLB-load-misses/ dTLB-stores OR cpu/dTLB-stores/ dTLB-store-misses OR cpu/dTLB-store-misses/ iTLB-load-misses OR cpu/iTLB-load-misses/ branch-loads OR cpu/branch-loads/ branch-load-misses OR cpu/branch-load-misses/ node-loads OR cpu/node-loads/ node-load-misses OR cpu/node-load-misses/

  branch-instructions OR cpu/branch-instructions/    [Kernel PMU event]
  branch-misses OR cpu/branch-misses/                [Kernel PMU event]
  bus-cycles OR cpu/bus-cycles/                      [Kernel PMU event]
  cache-misses OR cpu/cache-misses/                  [Kernel PMU event]
  cache-references OR cpu/cache-references/          [Kernel PMU event]
  cpu-cycles OR cpu/cpu-cycles/                      [Kernel PMU event]
  instructions OR cpu/instructions/                  [Kernel PMU event]

- The --cputype only works for the metric in the default mode. I can still see the cpu_atom events with --cputype core It may be something we can improve later.

# ./perf stat --cputype core sleep 2

Performance counter stats for 'sleep 2':

0.52 msec task-clock # 0.000 CPUs
utilized

                 1      context-switches                 #    1.939 K/sec
                 0      cpu-migrations                   #    0.000 /sec
                69      page-faults                      #  133.770 K/sec
         2,569,423      cpu_core/cycles/                 #    4.981 G/sec
     <not counted>      cpu_atom/cycles/
                       (0.00%)
         3,287,691      cpu_core/instructions/           #    6.374 G/sec
     <not counted>      cpu_atom/instructions/
                       (0.00%)
           555,848      cpu_core/branches/               #    1.078 G/sec
     <not counted>      cpu_atom/branches/
                       (0.00%)
             8,398      cpu_core/branch-misses/          #   16.281 M/sec
     <not counted>      cpu_atom/branch-misses/
                       (0.00%)
        15,416,538      cpu_core/TOPDOWN.SLOTS/          #     36.1 %
tma_backend_bound
                                                  #     23.9 %  tma_retiring
                                                  #      5.6 %
tma_bad_speculation
                                                  #     34.4 %
tma_frontend_bound
         3,687,877      cpu_core/topdown-retiring/
           846,398      cpu_core/topdown-bad-spec/
         5,320,217      cpu_core/topdown-fe-bound/
         5,562,045      cpu_core/topdown-be-bound/
            14,149      cpu_core/INT_MISC.UOP_DROPPING/  #   27.431 M/sec

Thanks,
Kan

Signature · 1 line
- Arnaldo
author reviewer
#53 lore raw
In reply to Liang, Kan
Quoted 112 lines · Kan
Quoted 63 lines · Arnaldo Carvalho de Melo

Em Wed, May 03, 2023 at 04:56:36PM -0400, Liang, Kan escreveu:

Quoted 62 lines · Ian Rogers
Quoted 51 lines

TL;DR: hybrid doesn't crash, json metrics work on hybrid on both PMUs or individually, event parsing doesn't always scan all PMUs, more and new tests that also run without hybrid, less code.

The first 4 patches are aimed at Linux 6.4 to address issues raised, in particular by Kan, on the existing perf stat behavior with json metrics. They avoid duplicated events by removing groups. They don't hide events and metrics to make event multiplexing obvious. They avoid terminating perf when paranoia is higher due to certain events that always fail. They avoid rearranging events by PMUs when the events aren't in a group.

The next 5 patches avoid grouping events for metrics where they could never succeed and were previously posted as:
"perf vendor events intel: Add xxx metric constraints"
https://lore.kernel.org/all/[email protected]/
In general the generated json is coming from:
https://github.com/intel/perfmon/pull/73

Next are some general and test improvements.

Next event parsing is rewritten to not scan all PMUs for the benefit of raw and legacy cache parsing, instead these are handled by the lexer and a new term type. This ultimately removes the need for the event parser for hybrid to be recursive as legacy cache can be just a term. Tests are re-enabled for events with hyphens, so AMD's branch-brs event is now parsable.

The cputype option is made a generic pmu filter flag and is tested even on non-hybrid systems.

The final patches address specific json metric issues on hybrid, in both the json metrics and the metric code.

The patches add slightly more code than they remove, in areas like better json metric constraints and tests, but in the core util code, the removal of hybrid is a net reduction:

 22 files changed, 711 insertions(+), 1016 deletions(-)

Sample output is contained in the v1 patch set:
https://lore.kernel.org/lkml/[email protected]/

Tested on Tigerlake, Skylake and Alderlake CPUs.

The v4 patch set:
- rebase, 1 of the Linux 6.4 recommended patches are merged leaving:
1) perf metric: Change divide by zero and !support events behavior
2) perf stat: Introduce skippable evsels
3) perf metric: Json flag to not group events if gathering a metric group
4) perf parse-events: Don't reorder ungrouped events by pmu whose diffstat is:

Quoted 4 lines
    30 files changed, 326 insertions(+), 33 deletions(-)
   but without the vendor event updates (the tend to be large as they
   repeat something per architecture per metric) is just:
    10 files changed, 90 insertions(+), 32 deletions(-)

I have tested the 4 patches on top of the perf-tools-next branch on both Cascade Lake and Raptor Lake. The result looks good to me.

Quoted 6 lines
Quoted 4 lines

They address the permission error found in the default mode of perf stat on the Cascade Lake. Thanks Ian for the fix.

Arnaldo, could you please consider to back port them for the 6.4?

Yes, its in perf-tools now, will go to Linus next week.

Thanks Arnaldo!

Quoted 4 lines

What about the other patches? I saw some you provided your review, what about the others, are you ok with them?

Yes, I'm OK with the patch set. It fixes many issues. Thanks Ian. (My tests mainly focus on the area in which the patch set may touch. I did the tests on various platforms, ADL (hybrid), Cascade Lake, SPR.)

But there are still some issues. I don't think they are introduced by this patch set. We may fix them later separately.

- Segmentation fault with perf stat --topdown on ADL (hybrid) and Cascade Lake.
It looks like a legacy issue, may not be introduced by this patch set. Here is the backtrace. It looks like there is a NULL metric_group.

(gdb) backtrace
#0 0x00007ffff73035d1 in __strstr_sse2_unaligned () from /lib64/libc.so.6 #1 0x00000000004f9019 in metricgroup__topdown_max_level_callback (pm=<optimized out>, table=<optimized out>,

    data=0x7fffffff92f4) at util/metricgroup.c:1722
#2  0x00000000005e8a31 in pmu_metrics_table_for_each_metric
(table=0xcb74d0 <pmu_events_map+368>,
    fn=fn@entry=0x4f8ff0 <metricgroup__topdown_max_level_callback>,
data=data@entry=0x7fffffff92f4)
    at pmu-events/pmu-events.c:61123
#3  0x00000000004fbc3b in metricgroups__topdown_max_level () at
util/metricgroup.c:1742
#4  0x000000000042c135 in add_default_attributes () at builtin-stat.c:1845
#5  cmd_stat (argc=0, argv=0x7fffffffe3e0) at builtin-stat.c:2446
#6  0x00000000004b922b in run_builtin (p=p@entry=0xd5c530
<commands+336>, argc=argc@entry=2,
    argv=argv@entry=0x7fffffffe3e0) at perf.c:323
Quoted 6 lines

#7 0x000000000040e373 in handle_internal_command (argv=0x7fffffffe3e0, argc=2) at perf.c:377
#8 run_argv (argv=<synthetic pointer>, argcp=<synthetic pointer>) at perf.c:421
#9 main (argc=2, argv=0x7fffffffe3e0) at perf.c:537
(gdb)

Thanks, there's a 1-liner for the segv:
https://lore.kernel.org/lkml/[email protected]/
Arnaldo, can we make sure this goes toward the next 6.4 release candidate?

Thanks,
Ian

Quoted 95 lines

Also, the return type is unsigned int, but a bool is given.

unsigned int metricgroups__topdown_max_level(void)

{
        unsigned int max_level = 0;
        const struct pmu_metrics_table *table = pmu_metrics_table__find();

        if (!table)
                return false;

- The perf metric and metricgroups fail on different platforms. Ian and I have discussed it. We agree to address it later separately.

102: perf all metricgroups test
ADL (hybrid)
103: perf all metrics test
ADL (hybrid), Cascade Lake, SPR

- perf list: The [Kernel PMU event] is missed for all the hardware cache events.
It impacts both hybrid and non-hybrid platforms.
It's a user-visible change introduced by the patch set.
I don't know if anyone cares whether it's a kernel event or a regular
event. It doesn't bother me. So I'm OK with it.

cpu:
L1-dcache-loads OR cpu/L1-dcache-loads/ L1-dcache-load-misses OR cpu/L1-dcache-load-misses/ L1-dcache-stores OR cpu/L1-dcache-stores/ L1-icache-load-misses OR cpu/L1-icache-load-misses/ LLC-loads OR cpu/LLC-loads/
LLC-load-misses OR cpu/LLC-load-misses/ LLC-stores OR cpu/LLC-stores/ LLC-store-misses OR cpu/LLC-store-misses/ dTLB-loads OR cpu/dTLB-loads/ dTLB-load-misses OR cpu/dTLB-load-misses/ dTLB-stores OR cpu/dTLB-stores/ dTLB-store-misses OR cpu/dTLB-store-misses/ iTLB-load-misses OR cpu/iTLB-load-misses/ branch-loads OR cpu/branch-loads/ branch-load-misses OR cpu/branch-load-misses/ node-loads OR cpu/node-loads/ node-load-misses OR cpu/node-load-misses/

  branch-instructions OR cpu/branch-instructions/    [Kernel PMU event]
  branch-misses OR cpu/branch-misses/                [Kernel PMU event]
  bus-cycles OR cpu/bus-cycles/                      [Kernel PMU event]
  cache-misses OR cpu/cache-misses/                  [Kernel PMU event]
  cache-references OR cpu/cache-references/          [Kernel PMU event]
  cpu-cycles OR cpu/cpu-cycles/                      [Kernel PMU event]
  instructions OR cpu/instructions/                  [Kernel PMU event]

- The --cputype only works for the metric in the default mode. I can still see the cpu_atom events with --cputype core It may be something we can improve later.

# ./perf stat --cputype core sleep 2

Performance counter stats for 'sleep 2':

0.52 msec task-clock # 0.000 CPUs
utilized

                 1      context-switches                 #    1.939 K/sec
                 0      cpu-migrations                   #    0.000 /sec
                69      page-faults                      #  133.770 K/sec
         2,569,423      cpu_core/cycles/                 #    4.981 G/sec
     <not counted>      cpu_atom/cycles/
                       (0.00%)
         3,287,691      cpu_core/instructions/           #    6.374 G/sec
     <not counted>      cpu_atom/instructions/
                       (0.00%)
           555,848      cpu_core/branches/               #    1.078 G/sec
     <not counted>      cpu_atom/branches/
                       (0.00%)
             8,398      cpu_core/branch-misses/          #   16.281 M/sec
     <not counted>      cpu_atom/branch-misses/
                       (0.00%)
        15,416,538      cpu_core/TOPDOWN.SLOTS/          #     36.1 %
tma_backend_bound
                                                  #     23.9 %  tma_retiring
                                                  #      5.6 %
tma_bad_speculation
                                                  #     34.4 %
tma_frontend_bound
         3,687,877      cpu_core/topdown-retiring/
           846,398      cpu_core/topdown-bad-spec/
         5,320,217      cpu_core/topdown-fe-bound/
         5,562,045      cpu_core/topdown-be-bound/
            14,149      cpu_core/INT_MISC.UOP_DROPPING/  #   27.431 M/sec

Thanks,
Kan

#54 lore raw

Em Mon, May 15, 2023 at 03:49:45PM -0700, Ian Rogers escreveu:

Quoted 30 lines · Kan
Quoted 22 lines

- Segmentation fault with perf stat --topdown on ADL (hybrid) and Cascade Lake.
It looks like a legacy issue, may not be introduced by this patch set. Here is the backtrace. It looks like there is a NULL metric_group.

(gdb) backtrace
#0 0x00007ffff73035d1 in __strstr_sse2_unaligned () from /lib64/libc.so.6 #1 0x00000000004f9019 in metricgroup__topdown_max_level_callback (pm=<optimized out>, table=<optimized out>,

    data=0x7fffffff92f4) at util/metricgroup.c:1722
#2  0x00000000005e8a31 in pmu_metrics_table_for_each_metric
(table=0xcb74d0 <pmu_events_map+368>,
    fn=fn@entry=0x4f8ff0 <metricgroup__topdown_max_level_callback>,
data=data@entry=0x7fffffff92f4)
    at pmu-events/pmu-events.c:61123
#3  0x00000000004fbc3b in metricgroups__topdown_max_level () at
util/metricgroup.c:1742
#4  0x000000000042c135 in add_default_attributes () at builtin-stat.c:1845
#5  cmd_stat (argc=0, argv=0x7fffffffe3e0) at builtin-stat.c:2446
#6  0x00000000004b922b in run_builtin (p=p@entry=0xd5c530
<commands+336>, argc=argc@entry=2,
    argv=argv@entry=0x7fffffffe3e0) at perf.c:323
Quoted 6 lines

#7 0x000000000040e373 in handle_internal_command (argv=0x7fffffffe3e0, argc=2) at perf.c:377
#8 run_argv (argv=<synthetic pointer>, argcp=<synthetic pointer>) at perf.c:421
#9 main (argc=2, argv=0x7fffffffe3e0) at perf.c:537
(gdb)

Quoted 3 lines

Thanks, there's a 1-liner for the segv:
https://lore.kernel.org/lkml/[email protected]/
Arnaldo, can we make sure this goes toward the next 6.4 release candidate?

Sure.

- Arnaldo

#55 lore raw
In reply to Ian Rogers

Em Tue, May 02, 2023 at 03:38:07PM -0700, Ian Rogers escreveu:

Quoted 11 lines

TL;DR: hybrid doesn't crash, json metrics work on hybrid on both PMUs or individually, event parsing doesn't always scan all PMUs, more and new tests that also run without hybrid, less code.

The first 4 patches are aimed at Linux 6.4 to address issues raised, in particular by Kan, on the existing perf stat behavior with json metrics. They avoid duplicated events by removing groups. They don't hide events and metrics to make event multiplexing obvious. They avoid terminating perf when paranoia is higher due to certain events that always fail. They avoid rearranging events by PMUs when the events aren't in a group.

Applied the first 4, soon I'll go over the rest of the patchkit.

- Arnaldo

Quoted 183 lines

The next 5 patches avoid grouping events for metrics where they could never succeed and were previously posted as:
"perf vendor events intel: Add xxx metric constraints"
https://lore.kernel.org/all/[email protected]/
In general the generated json is coming from:
https://github.com/intel/perfmon/pull/73

Next are some general and test improvements.

Next event parsing is rewritten to not scan all PMUs for the benefit of raw and legacy cache parsing, instead these are handled by the lexer and a new term type. This ultimately removes the need for the event parser for hybrid to be recursive as legacy cache can be just a term. Tests are re-enabled for events with hyphens, so AMD's branch-brs event is now parsable.

The cputype option is made a generic pmu filter flag and is tested even on non-hybrid systems.

The final patches address specific json metric issues on hybrid, in both the json metrics and the metric code.

The patches add slightly more code than they remove, in areas like better json metric constraints and tests, but in the core util code, the removal of hybrid is a net reduction:

 22 files changed, 711 insertions(+), 1016 deletions(-)

Sample output is contained in the v1 patch set:
https://lore.kernel.org/lkml/[email protected]/

Tested on Tigerlake, Skylake and Alderlake CPUs.

The v4 patch set:
- rebase, 1 of the Linux 6.4 recommended patches are merged leaving:
1) perf metric: Change divide by zero and !support events behavior
2) perf stat: Introduce skippable evsels
3) perf metric: Json flag to not group events if gathering a metric group
4) perf parse-events: Don't reorder ungrouped events by pmu whose diffstat is:

    30 files changed, 326 insertions(+), 33 deletions(-)
   but without the vendor event updates (the tend to be large as they
   repeat something per architecture per metric) is just:
    10 files changed, 90 insertions(+), 32 deletions(-)

- Address review comments from Ravi Bangoria <[email protected]> that are only in the patches targeting Linux 6.5.

The v3 patch set:
- for Linux 6.4 the first 5 patches are recommended:
- changes skippable evsels to always print in case short running benchmarks meet the 0 enable and 0 count condition (suggested by Stephane).
- changes metrics to show "nan" so that it is more obvious they couldn't be computed (suggested by Stephane).
- fixes a reordering issue that reordered events that lacked a group, especially when the core PMU isn't "cpu".
- for Linux 6.5 added extra hybrid type tests in the x86 hybrid test as suggested by Kan.
- note, the patches aren't rebased against the tmp.perf-tools branch meaning patches 1 and 11 should be dropped there.

The v2 patch set:
- restructures the 3 Linux 6.4 patches first;
- makes it so that is_event_supported isn't called during core event parsing;
- displays skippable 0 count events that were enabled;
- addresses output formatting review comments;
- addresses some test issues and an uninitialized variable use in strchr;
- addresses checkpatch.pl reported issues;
- adds reviewed-by to some patches.

Ian Rogers (44):
perf metric: Change divide by zero and !support events behavior perf stat: Introduce skippable evsels
perf metric: Json flag to not group events if gathering a metric group perf parse-events: Don't reorder ungrouped events by pmu perf vendor events intel: Add alderlake metric constraints perf vendor events intel: Add icelake metric constraints perf vendor events intel: Add icelakex metric constraints perf vendor events intel: Add sapphirerapids metric constraints perf vendor events intel: Add tigerlake metric constraints perf test: Test more sysfs events
perf test: Use valid for PMU tests
perf test: Mask configs with extended types then test
perf test: Test more with config_cache
perf test: Roundtrip name, don't assume 1 event per name perf parse-events: Set attr.type to PMU type early
perf parse-events: Set pmu_name whenever a pmu is given perf print-events: Avoid unnecessary strlist
perf parse-events: Avoid scanning PMUs before parsing
perf evsel: Modify group pmu name for software events
perf test: Move x86 hybrid tests to arch/x86
perf test x86 hybrid: Update test expectations
perf test x86 hybrid: Add hybrid extended type checks
perf parse-events: Support PMUs for legacy cache events perf parse-events: Wildcard legacy cache events
perf print-events: Print legacy cache events for each PMU perf parse-events: Support wildcards on raw events
perf parse-events: Remove now unused hybrid logic
perf parse-events: Minor type safety cleanup
perf parse-events: Add pmu filter
perf stat: Make cputype filter generic
perf test: Add cputype testing to perf stat
perf test: Fix parse-events tests for >1 core PMU
perf parse-events: Support hardware events as terms
perf parse-events: Avoid error when assigning a term
perf parse-events: Avoid error when assigning a legacy cache term perf parse-events: Don't auto merge hybrid wildcard events perf parse-events: Don't reorder atom cpu events
perf metrics: Be PMU specific for referenced metrics.
perf stat: Command line PMU metric filtering
perf vendor events intel: Correct alderlake metrics
perf jevents: Don't rewrite metrics across PMUs
perf metrics: Be PMU specific in event match
perf stat: Don't disable TopdownL1 metric on hybrid
perf parse-events: Reduce scope of is_event_supported

 tools/perf/arch/x86/include/arch-tests.h      |   1 +
 tools/perf/arch/x86/tests/Build               |   1 +
 tools/perf/arch/x86/tests/arch-tests.c        |  10 +
 tools/perf/arch/x86/tests/hybrid.c            | 287 ++++++
 tools/perf/arch/x86/util/evlist.c             |   4 +-
 tools/perf/builtin-list.c                     |  21 +-
 tools/perf/builtin-record.c                   |  13 +-
 tools/perf/builtin-stat.c                     |  77 +-
 tools/perf/builtin-top.c                      |   5 +-
 tools/perf/builtin-trace.c                    |   5 +-
 .../arch/x86/alderlake/adl-metrics.json       | 275 +++---
 .../arch/x86/alderlaken/adln-metrics.json     |  20 +-
 .../arch/x86/broadwell/bdw-metrics.json       |  12 +
 .../arch/x86/broadwellde/bdwde-metrics.json   |  12 +
 .../arch/x86/broadwellx/bdx-metrics.json      |  12 +
 .../arch/x86/cascadelakex/clx-metrics.json    |  12 +
 .../arch/x86/haswell/hsw-metrics.json         |  12 +
 .../arch/x86/haswellx/hsx-metrics.json        |  12 +
 .../arch/x86/icelake/icl-metrics.json         |  23 +
 .../arch/x86/icelakex/icx-metrics.json        |  23 +
 .../arch/x86/ivybridge/ivb-metrics.json       |  12 +
 .../arch/x86/ivytown/ivt-metrics.json         |  12 +
 .../arch/x86/jaketown/jkt-metrics.json        |  12 +
 .../arch/x86/sandybridge/snb-metrics.json     |  12 +
 .../arch/x86/sapphirerapids/spr-metrics.json  |  23 +
 .../arch/x86/skylake/skl-metrics.json         |  12 +
 .../arch/x86/skylakex/skx-metrics.json        |  12 +
 .../arch/x86/tigerlake/tgl-metrics.json       |  23 +
 tools/perf/pmu-events/jevents.py              |  10 +-
 tools/perf/pmu-events/metric.py               |  28 +-
 tools/perf/pmu-events/metric_test.py          |   6 +-
 tools/perf/pmu-events/pmu-events.h            |   2 +
 tools/perf/tests/evsel-roundtrip-name.c       | 119 +--
 tools/perf/tests/expr.c                       |   3 +-
 tools/perf/tests/parse-events.c               | 858 +++++++++---------
 tools/perf/tests/parse-metric.c               |   1 +
 tools/perf/tests/pmu-events.c                 |  12 +-
 tools/perf/tests/shell/stat.sh                |  44 +
 tools/perf/util/Build                         |   1 -
 tools/perf/util/evlist.h                      |   1 -
 tools/perf/util/evsel.c                       |  30 +-
 tools/perf/util/evsel.h                       |   1 +
 tools/perf/util/expr.y                        |   6 +-
 tools/perf/util/metricgroup.c                 | 111 ++-
 tools/perf/util/metricgroup.h                 |   3 +-
 tools/perf/util/parse-events-hybrid.c         | 214 -----
 tools/perf/util/parse-events-hybrid.h         |  25 -
 tools/perf/util/parse-events.c                | 720 ++++++---------
 tools/perf/util/parse-events.h                |  63 +-
 tools/perf/util/parse-events.l                | 108 +--
 tools/perf/util/parse-events.y                | 222 ++---
 tools/perf/util/pmu-hybrid.c                  |  20 -
 tools/perf/util/pmu-hybrid.h                  |   1 -
 tools/perf/util/pmu.c                         |  16 +-
 tools/perf/util/pmu.h                         |   3 +
 tools/perf/util/pmus.c                        |  25 +-
 tools/perf/util/pmus.h                        |   3 +
 tools/perf/util/print-events.c                | 127 ++-
 tools/perf/util/stat-display.c                |   2 +-
 tools/perf/util/stat-shadow.c                 |  25 +-
 60 files changed, 2066 insertions(+), 1699 deletions(-)
 create mode 100644 tools/perf/arch/x86/tests/hybrid.c
 delete mode 100644 tools/perf/util/parse-events-hybrid.c
 delete mode 100644 tools/perf/util/parse-events-hybrid.h
Signature · 1 line
2.40.1.495.gc816e09b53d-goog
Signature · 1 line
- Arnaldo
#56 lore raw
In reply to Ian Rogers

Em Tue, May 02, 2023 at 03:38:07PM -0700, Ian Rogers escreveu:

Quoted 11 lines

TL;DR: hybrid doesn't crash, json metrics work on hybrid on both PMUs or individually, event parsing doesn't always scan all PMUs, more and new tests that also run without hybrid, less code.

The first 4 patches are aimed at Linux 6.4 to address issues raised, in particular by Kan, on the existing perf stat behavior with json metrics. They avoid duplicated events by removing groups. They don't hide events and metrics to make event multiplexing obvious. They avoid terminating perf when paranoia is higher due to certain events that always fail. They avoid rearranging events by PMUs when the events aren't in a group.

Took the first 4, skipped patch 19 that Adrian asked to be in 6.4 and then went all the way to:

Applying: perf test: Add cputype testing to perf stat
error: patch failed: tools/perf/tests/shell/stat.sh:91
error: tools/perf/tests/shell/stat.sh: patch does not apply Patch failed at 0012 perf test: Add cputype testing to perf stat
hint: Use 'git am --show-current-patch=diff' to see the failed patch When you have resolved this problem, run "git am --continue". If you prefer to skip this patch, run "git am --skip" instead. To restore the original branch and stop patching, run "git am --abort". ⬢[acme@toolbox perf-tools-next]$ git am --abort ⬢[acme@toolbox perf-tools-next]$

Will test with it and put what I have in tmp.perf-tools-next, testing now.

- Arnaldo

Quoted 183 lines

The next 5 patches avoid grouping events for metrics where they could never succeed and were previously posted as:
"perf vendor events intel: Add xxx metric constraints"
https://lore.kernel.org/all/[email protected]/
In general the generated json is coming from:
https://github.com/intel/perfmon/pull/73

Next are some general and test improvements.

Next event parsing is rewritten to not scan all PMUs for the benefit of raw and legacy cache parsing, instead these are handled by the lexer and a new term type. This ultimately removes the need for the event parser for hybrid to be recursive as legacy cache can be just a term. Tests are re-enabled for events with hyphens, so AMD's branch-brs event is now parsable.

The cputype option is made a generic pmu filter flag and is tested even on non-hybrid systems.

The final patches address specific json metric issues on hybrid, in both the json metrics and the metric code.

The patches add slightly more code than they remove, in areas like better json metric constraints and tests, but in the core util code, the removal of hybrid is a net reduction:

 22 files changed, 711 insertions(+), 1016 deletions(-)

Sample output is contained in the v1 patch set:
https://lore.kernel.org/lkml/[email protected]/

Tested on Tigerlake, Skylake and Alderlake CPUs.

The v4 patch set:
- rebase, 1 of the Linux 6.4 recommended patches are merged leaving:
1) perf metric: Change divide by zero and !support events behavior
2) perf stat: Introduce skippable evsels
3) perf metric: Json flag to not group events if gathering a metric group
4) perf parse-events: Don't reorder ungrouped events by pmu whose diffstat is:

    30 files changed, 326 insertions(+), 33 deletions(-)
   but without the vendor event updates (the tend to be large as they
   repeat something per architecture per metric) is just:
    10 files changed, 90 insertions(+), 32 deletions(-)

- Address review comments from Ravi Bangoria <[email protected]> that are only in the patches targeting Linux 6.5.

The v3 patch set:
- for Linux 6.4 the first 5 patches are recommended:
- changes skippable evsels to always print in case short running benchmarks meet the 0 enable and 0 count condition (suggested by Stephane).
- changes metrics to show "nan" so that it is more obvious they couldn't be computed (suggested by Stephane).
- fixes a reordering issue that reordered events that lacked a group, especially when the core PMU isn't "cpu".
- for Linux 6.5 added extra hybrid type tests in the x86 hybrid test as suggested by Kan.
- note, the patches aren't rebased against the tmp.perf-tools branch meaning patches 1 and 11 should be dropped there.

The v2 patch set:
- restructures the 3 Linux 6.4 patches first;
- makes it so that is_event_supported isn't called during core event parsing;
- displays skippable 0 count events that were enabled;
- addresses output formatting review comments;
- addresses some test issues and an uninitialized variable use in strchr;
- addresses checkpatch.pl reported issues;
- adds reviewed-by to some patches.

Ian Rogers (44):
perf metric: Change divide by zero and !support events behavior perf stat: Introduce skippable evsels
perf metric: Json flag to not group events if gathering a metric group perf parse-events: Don't reorder ungrouped events by pmu perf vendor events intel: Add alderlake metric constraints perf vendor events intel: Add icelake metric constraints perf vendor events intel: Add icelakex metric constraints perf vendor events intel: Add sapphirerapids metric constraints perf vendor events intel: Add tigerlake metric constraints perf test: Test more sysfs events
perf test: Use valid for PMU tests
perf test: Mask configs with extended types then test
perf test: Test more with config_cache
perf test: Roundtrip name, don't assume 1 event per name perf parse-events: Set attr.type to PMU type early
perf parse-events: Set pmu_name whenever a pmu is given perf print-events: Avoid unnecessary strlist
perf parse-events: Avoid scanning PMUs before parsing
perf evsel: Modify group pmu name for software events
perf test: Move x86 hybrid tests to arch/x86
perf test x86 hybrid: Update test expectations
perf test x86 hybrid: Add hybrid extended type checks
perf parse-events: Support PMUs for legacy cache events perf parse-events: Wildcard legacy cache events
perf print-events: Print legacy cache events for each PMU perf parse-events: Support wildcards on raw events
perf parse-events: Remove now unused hybrid logic
perf parse-events: Minor type safety cleanup
perf parse-events: Add pmu filter
perf stat: Make cputype filter generic
perf test: Add cputype testing to perf stat
perf test: Fix parse-events tests for >1 core PMU
perf parse-events: Support hardware events as terms
perf parse-events: Avoid error when assigning a term
perf parse-events: Avoid error when assigning a legacy cache term perf parse-events: Don't auto merge hybrid wildcard events perf parse-events: Don't reorder atom cpu events
perf metrics: Be PMU specific for referenced metrics.
perf stat: Command line PMU metric filtering
perf vendor events intel: Correct alderlake metrics
perf jevents: Don't rewrite metrics across PMUs
perf metrics: Be PMU specific in event match
perf stat: Don't disable TopdownL1 metric on hybrid
perf parse-events: Reduce scope of is_event_supported

 tools/perf/arch/x86/include/arch-tests.h      |   1 +
 tools/perf/arch/x86/tests/Build               |   1 +
 tools/perf/arch/x86/tests/arch-tests.c        |  10 +
 tools/perf/arch/x86/tests/hybrid.c            | 287 ++++++
 tools/perf/arch/x86/util/evlist.c             |   4 +-
 tools/perf/builtin-list.c                     |  21 +-
 tools/perf/builtin-record.c                   |  13 +-
 tools/perf/builtin-stat.c                     |  77 +-
 tools/perf/builtin-top.c                      |   5 +-
 tools/perf/builtin-trace.c                    |   5 +-
 .../arch/x86/alderlake/adl-metrics.json       | 275 +++---
 .../arch/x86/alderlaken/adln-metrics.json     |  20 +-
 .../arch/x86/broadwell/bdw-metrics.json       |  12 +
 .../arch/x86/broadwellde/bdwde-metrics.json   |  12 +
 .../arch/x86/broadwellx/bdx-metrics.json      |  12 +
 .../arch/x86/cascadelakex/clx-metrics.json    |  12 +
 .../arch/x86/haswell/hsw-metrics.json         |  12 +
 .../arch/x86/haswellx/hsx-metrics.json        |  12 +
 .../arch/x86/icelake/icl-metrics.json         |  23 +
 .../arch/x86/icelakex/icx-metrics.json        |  23 +
 .../arch/x86/ivybridge/ivb-metrics.json       |  12 +
 .../arch/x86/ivytown/ivt-metrics.json         |  12 +
 .../arch/x86/jaketown/jkt-metrics.json        |  12 +
 .../arch/x86/sandybridge/snb-metrics.json     |  12 +
 .../arch/x86/sapphirerapids/spr-metrics.json  |  23 +
 .../arch/x86/skylake/skl-metrics.json         |  12 +
 .../arch/x86/skylakex/skx-metrics.json        |  12 +
 .../arch/x86/tigerlake/tgl-metrics.json       |  23 +
 tools/perf/pmu-events/jevents.py              |  10 +-
 tools/perf/pmu-events/metric.py               |  28 +-
 tools/perf/pmu-events/metric_test.py          |   6 +-
 tools/perf/pmu-events/pmu-events.h            |   2 +
 tools/perf/tests/evsel-roundtrip-name.c       | 119 +--
 tools/perf/tests/expr.c                       |   3 +-
 tools/perf/tests/parse-events.c               | 858 +++++++++---------
 tools/perf/tests/parse-metric.c               |   1 +
 tools/perf/tests/pmu-events.c                 |  12 +-
 tools/perf/tests/shell/stat.sh                |  44 +
 tools/perf/util/Build                         |   1 -
 tools/perf/util/evlist.h                      |   1 -
 tools/perf/util/evsel.c                       |  30 +-
 tools/perf/util/evsel.h                       |   1 +
 tools/perf/util/expr.y                        |   6 +-
 tools/perf/util/metricgroup.c                 | 111 ++-
 tools/perf/util/metricgroup.h                 |   3 +-
 tools/perf/util/parse-events-hybrid.c         | 214 -----
 tools/perf/util/parse-events-hybrid.h         |  25 -
 tools/perf/util/parse-events.c                | 720 ++++++---------
 tools/perf/util/parse-events.h                |  63 +-
 tools/perf/util/parse-events.l                | 108 +--
 tools/perf/util/parse-events.y                | 222 ++---
 tools/perf/util/pmu-hybrid.c                  |  20 -
 tools/perf/util/pmu-hybrid.h                  |   1 -
 tools/perf/util/pmu.c                         |  16 +-
 tools/perf/util/pmu.h                         |   3 +
 tools/perf/util/pmus.c                        |  25 +-
 tools/perf/util/pmus.h                        |   3 +
 tools/perf/util/print-events.c                | 127 ++-
 tools/perf/util/stat-display.c                |   2 +-
 tools/perf/util/stat-shadow.c                 |  25 +-
 60 files changed, 2066 insertions(+), 1699 deletions(-)
 create mode 100644 tools/perf/arch/x86/tests/hybrid.c
 delete mode 100644 tools/perf/util/parse-events-hybrid.c
 delete mode 100644 tools/perf/util/parse-events-hybrid.h
Signature · 1 line
2.40.1.495.gc816e09b53d-goog
Signature · 1 line
- Arnaldo
author reviewer
#57 lore raw
Quoted 28 lines · Arnaldo Carvalho de Melo

Em Tue, May 02, 2023 at 03:38:07PM -0700, Ian Rogers escreveu:

Quoted 11 lines

TL;DR: hybrid doesn't crash, json metrics work on hybrid on both PMUs or individually, event parsing doesn't always scan all PMUs, more and new tests that also run without hybrid, less code.

The first 4 patches are aimed at Linux 6.4 to address issues raised, in particular by Kan, on the existing perf stat behavior with json metrics. They avoid duplicated events by removing groups. They don't hide events and metrics to make event multiplexing obvious. They avoid terminating perf when paranoia is higher due to certain events that always fail. They avoid rearranging events by PMUs when the events aren't in a group.

Took the first 4, skipped patch 19 that Adrian asked to be in 6.4 and then went all the way to:

Applying: perf test: Add cputype testing to perf stat
error: patch failed: tools/perf/tests/shell/stat.sh:91
error: tools/perf/tests/shell/stat.sh: patch does not apply Patch failed at 0012 perf test: Add cputype testing to perf stat
hint: Use 'git am --show-current-patch=diff' to see the failed patch When you have resolved this problem, run "git am --continue". If you prefer to skip this patch, run "git am --skip" instead. To restore the original branch and stop patching, run "git am --abort". ⬢[acme@toolbox perf-tools-next]$ git am --abort ⬢[acme@toolbox perf-tools-next]$

Quoted 4 lines

Will test with it and put what I have in tmp.perf-tools-next, testing now.

- Arnaldo

Thanks Arnaldo, I checked that all the patches are there (tmp.perf-tools-next) and tested on a non-hybrid system. Everything looks good. I resent the missing test patch:
https://lore.kernel.org/lkml/[email protected]/
It applied cleanly for me, so I'm not sure what the issue was. Getting the other cherry-picked was no small thing, so I'll not complain :-)

Thanks,
Ian

Quoted 187 lines
Quoted 180 lines

The next 5 patches avoid grouping events for metrics where they could never succeed and were previously posted as:
"perf vendor events intel: Add xxx metric constraints"
https://lore.kernel.org/all/[email protected]/
In general the generated json is coming from:
https://github.com/intel/perfmon/pull/73

Next are some general and test improvements.

Next event parsing is rewritten to not scan all PMUs for the benefit of raw and legacy cache parsing, instead these are handled by the lexer and a new term type. This ultimately removes the need for the event parser for hybrid to be recursive as legacy cache can be just a term. Tests are re-enabled for events with hyphens, so AMD's branch-brs event is now parsable.

The cputype option is made a generic pmu filter flag and is tested even on non-hybrid systems.

The final patches address specific json metric issues on hybrid, in both the json metrics and the metric code.

The patches add slightly more code than they remove, in areas like better json metric constraints and tests, but in the core util code, the removal of hybrid is a net reduction:

 22 files changed, 711 insertions(+), 1016 deletions(-)

Sample output is contained in the v1 patch set:
https://lore.kernel.org/lkml/[email protected]/

Tested on Tigerlake, Skylake and Alderlake CPUs.

The v4 patch set:
- rebase, 1 of the Linux 6.4 recommended patches are merged leaving:
1) perf metric: Change divide by zero and !support events behavior
2) perf stat: Introduce skippable evsels
3) perf metric: Json flag to not group events if gathering a metric group
4) perf parse-events: Don't reorder ungrouped events by pmu whose diffstat is:

    30 files changed, 326 insertions(+), 33 deletions(-)
   but without the vendor event updates (the tend to be large as they
   repeat something per architecture per metric) is just:
    10 files changed, 90 insertions(+), 32 deletions(-)

- Address review comments from Ravi Bangoria <[email protected]> that are only in the patches targeting Linux 6.5.

The v3 patch set:
- for Linux 6.4 the first 5 patches are recommended:
- changes skippable evsels to always print in case short running benchmarks meet the 0 enable and 0 count condition (suggested by Stephane).
- changes metrics to show "nan" so that it is more obvious they couldn't be computed (suggested by Stephane).
- fixes a reordering issue that reordered events that lacked a group, especially when the core PMU isn't "cpu".
- for Linux 6.5 added extra hybrid type tests in the x86 hybrid test as suggested by Kan.
- note, the patches aren't rebased against the tmp.perf-tools branch meaning patches 1 and 11 should be dropped there.

The v2 patch set:
- restructures the 3 Linux 6.4 patches first;
- makes it so that is_event_supported isn't called during core event parsing;
- displays skippable 0 count events that were enabled;
- addresses output formatting review comments;
- addresses some test issues and an uninitialized variable use in strchr;
- addresses checkpatch.pl reported issues;
- adds reviewed-by to some patches.

Ian Rogers (44):
perf metric: Change divide by zero and !support events behavior perf stat: Introduce skippable evsels
perf metric: Json flag to not group events if gathering a metric group perf parse-events: Don't reorder ungrouped events by pmu perf vendor events intel: Add alderlake metric constraints perf vendor events intel: Add icelake metric constraints perf vendor events intel: Add icelakex metric constraints perf vendor events intel: Add sapphirerapids metric constraints perf vendor events intel: Add tigerlake metric constraints perf test: Test more sysfs events
perf test: Use valid for PMU tests
perf test: Mask configs with extended types then test
perf test: Test more with config_cache
perf test: Roundtrip name, don't assume 1 event per name perf parse-events: Set attr.type to PMU type early
perf parse-events: Set pmu_name whenever a pmu is given perf print-events: Avoid unnecessary strlist
perf parse-events: Avoid scanning PMUs before parsing
perf evsel: Modify group pmu name for software events
perf test: Move x86 hybrid tests to arch/x86
perf test x86 hybrid: Update test expectations
perf test x86 hybrid: Add hybrid extended type checks
perf parse-events: Support PMUs for legacy cache events perf parse-events: Wildcard legacy cache events
perf print-events: Print legacy cache events for each PMU perf parse-events: Support wildcards on raw events
perf parse-events: Remove now unused hybrid logic
perf parse-events: Minor type safety cleanup
perf parse-events: Add pmu filter
perf stat: Make cputype filter generic
perf test: Add cputype testing to perf stat
perf test: Fix parse-events tests for >1 core PMU
perf parse-events: Support hardware events as terms
perf parse-events: Avoid error when assigning a term
perf parse-events: Avoid error when assigning a legacy cache term perf parse-events: Don't auto merge hybrid wildcard events perf parse-events: Don't reorder atom cpu events
perf metrics: Be PMU specific for referenced metrics.
perf stat: Command line PMU metric filtering
perf vendor events intel: Correct alderlake metrics
perf jevents: Don't rewrite metrics across PMUs
perf metrics: Be PMU specific in event match
perf stat: Don't disable TopdownL1 metric on hybrid
perf parse-events: Reduce scope of is_event_supported

 tools/perf/arch/x86/include/arch-tests.h      |   1 +
 tools/perf/arch/x86/tests/Build               |   1 +
 tools/perf/arch/x86/tests/arch-tests.c        |  10 +
 tools/perf/arch/x86/tests/hybrid.c            | 287 ++++++
 tools/perf/arch/x86/util/evlist.c             |   4 +-
 tools/perf/builtin-list.c                     |  21 +-
 tools/perf/builtin-record.c                   |  13 +-
 tools/perf/builtin-stat.c                     |  77 +-
 tools/perf/builtin-top.c                      |   5 +-
 tools/perf/builtin-trace.c                    |   5 +-
 .../arch/x86/alderlake/adl-metrics.json       | 275 +++---
 .../arch/x86/alderlaken/adln-metrics.json     |  20 +-
 .../arch/x86/broadwell/bdw-metrics.json       |  12 +
 .../arch/x86/broadwellde/bdwde-metrics.json   |  12 +
 .../arch/x86/broadwellx/bdx-metrics.json      |  12 +
 .../arch/x86/cascadelakex/clx-metrics.json    |  12 +
 .../arch/x86/haswell/hsw-metrics.json         |  12 +
 .../arch/x86/haswellx/hsx-metrics.json        |  12 +
 .../arch/x86/icelake/icl-metrics.json         |  23 +
 .../arch/x86/icelakex/icx-metrics.json        |  23 +
 .../arch/x86/ivybridge/ivb-metrics.json       |  12 +
 .../arch/x86/ivytown/ivt-metrics.json         |  12 +
 .../arch/x86/jaketown/jkt-metrics.json        |  12 +
 .../arch/x86/sandybridge/snb-metrics.json     |  12 +
 .../arch/x86/sapphirerapids/spr-metrics.json  |  23 +
 .../arch/x86/skylake/skl-metrics.json         |  12 +
 .../arch/x86/skylakex/skx-metrics.json        |  12 +
 .../arch/x86/tigerlake/tgl-metrics.json       |  23 +
 tools/perf/pmu-events/jevents.py              |  10 +-
 tools/perf/pmu-events/metric.py               |  28 +-
 tools/perf/pmu-events/metric_test.py          |   6 +-
 tools/perf/pmu-events/pmu-events.h            |   2 +
 tools/perf/tests/evsel-roundtrip-name.c       | 119 +--
 tools/perf/tests/expr.c                       |   3 +-
 tools/perf/tests/parse-events.c               | 858 +++++++++---------
 tools/perf/tests/parse-metric.c               |   1 +
 tools/perf/tests/pmu-events.c                 |  12 +-
 tools/perf/tests/shell/stat.sh                |  44 +
 tools/perf/util/Build                         |   1 -
 tools/perf/util/evlist.h                      |   1 -
 tools/perf/util/evsel.c                       |  30 +-
 tools/perf/util/evsel.h                       |   1 +
 tools/perf/util/expr.y                        |   6 +-
 tools/perf/util/metricgroup.c                 | 111 ++-
 tools/perf/util/metricgroup.h                 |   3 +-
 tools/perf/util/parse-events-hybrid.c         | 214 -----
 tools/perf/util/parse-events-hybrid.h         |  25 -
 tools/perf/util/parse-events.c                | 720 ++++++---------
 tools/perf/util/parse-events.h                |  63 +-
 tools/perf/util/parse-events.l                | 108 +--
 tools/perf/util/parse-events.y                | 222 ++---
 tools/perf/util/pmu-hybrid.c                  |  20 -
 tools/perf/util/pmu-hybrid.h                  |   1 -
 tools/perf/util/pmu.c                         |  16 +-
 tools/perf/util/pmu.h                         |   3 +
 tools/perf/util/pmus.c                        |  25 +-
 tools/perf/util/pmus.h                        |   3 +
 tools/perf/util/print-events.c                | 127 ++-
 tools/perf/util/stat-display.c                |   2 +-
 tools/perf/util/stat-shadow.c                 |  25 +-
 60 files changed, 2066 insertions(+), 1699 deletions(-)
 create mode 100644 tools/perf/arch/x86/tests/hybrid.c
 delete mode 100644 tools/perf/util/parse-events-hybrid.c
 delete mode 100644 tools/perf/util/parse-events-hybrid.h
Quoted 3 lines

--
2.40.1.495.gc816e09b53d-goog

--

- Arnaldo