perf vendor events intel: Update alderlake events/metrics

Update events to v21 including the new event SQ_MISC.BUS_LOCK and
improved comments. Metrics are updated to make TMA info metric names
synchronized. Events and metrics were generated by:
https://github.com/intel/perfmon/blob/main/scripts/create_perf_json.py

Reviewed-by: Kan Liang <kan.liang@linux.intel.com>
Signed-off-by: Ian Rogers <irogers@google.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: John Garry <john.g.garry@oracle.com>
Cc: Kajol Jain <kjain@linux.ibm.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Richter <tmricht@linux.ibm.com>
Cc: Xing Zhengjun <zhengjun.xing@linux.intel.com>
Link: https://lore.kernel.org/r/20230517173805.602113-2-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

5 files changed, 783 insertions, 824 deletions

diff --git a/tools/perf/pmu-events/arch/x86/alderlake/adl-metrics.json b/tools/perf/pmu-events/arch/x86/alderlake/adl-metrics.json
index 840f6f6fc8c5..c9f7e3d4ab08 100644
--- a/tools/perf/pmu-events/arch/x86/alderlake/adl-metrics.json
+++ b/tools/perf/pmu-events/arch/x86/alderlake/adl-metrics.json
@@ -71,7 +71,7 @@
     },
     {
         "BriefDescription": "Uncore frequency per die [GHZ]",
-        "MetricExpr": "tma_info_socket_clks / #num_dies / duration_time / 1e9",
+        "MetricExpr": "tma_info_system_socket_clks / #num_dies / duration_time / 1e9",
         "MetricGroup": "SoC",
         "MetricName": "UNCORE_FREQ"
     },
@@ -120,7 +120,7 @@
     },
     {
         "BriefDescription": "Counts the number of issue slots  that were not consumed by the backend due to certain allocation restrictions.",
-        "MetricExpr": "TOPDOWN_BE_BOUND.ALLOC_RESTRICTIONS / tma_info_slots",
+        "MetricExpr": "TOPDOWN_BE_BOUND.ALLOC_RESTRICTIONS / tma_info_core_slots",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_resource_bound_group",
         "MetricName": "tma_alloc_restriction",
         "MetricThreshold": "tma_alloc_restriction > 0.1",
@@ -129,7 +129,7 @@
     },
     {
         "BriefDescription": "Counts the total number of issue slots  that were not consumed by the backend due to backend stalls",
-        "MetricExpr": "TOPDOWN_BE_BOUND.ALL / tma_info_slots",
+        "MetricExpr": "TOPDOWN_BE_BOUND.ALL / tma_info_core_slots",
         "MetricGroup": "TopdownL1;tma_L1_group",
         "MetricName": "tma_backend_bound",
         "MetricThreshold": "tma_backend_bound > 0.1",
@@ -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 - (cpu_atom@TOPDOWN_FE_BOUND.ALL@ + cpu_atom@TOPDOWN_BE_BOUND.ALL@ + cpu_atom@TOPDOWN_RETIRING.ALL@)) / tma_info_slots",
+        "MetricExpr": "(tma_info_core_slots - (cpu_atom@TOPDOWN_FE_BOUND.ALL@ + cpu_atom@TOPDOWN_BE_BOUND.ALL@ + cpu_atom@TOPDOWN_RETIRING.ALL@)) / tma_info_core_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": "(cpu_atom@TOPDOWN_RETIRING.ALL@ - cpu_atom@UOPS_RETIRED.MS@) / tma_info_slots",
+        "MetricExpr": "(cpu_atom@TOPDOWN_RETIRING.ALL@ - cpu_atom@UOPS_RETIRED.MS@) / tma_info_core_slots",
         "MetricGroup": "TopdownL2;tma_L2_group;tma_retiring_group",
         "MetricName": "tma_base",
         "MetricThreshold": "tma_base > 0.6",
@@ -172,7 +172,7 @@
     },
     {
         "BriefDescription": "Counts the number of issue slots  that were not delivered by the frontend due to BACLEARS, which occurs when the Branch Target Buffer (BTB) prediction or lack thereof, was corrected by a later branch predictor in the frontend",
-        "MetricExpr": "TOPDOWN_FE_BOUND.BRANCH_DETECT / tma_info_slots",
+        "MetricExpr": "TOPDOWN_FE_BOUND.BRANCH_DETECT / tma_info_core_slots",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_fetch_latency_group",
         "MetricName": "tma_branch_detect",
         "MetricThreshold": "tma_branch_detect > 0.05",
@@ -182,7 +182,7 @@
     },
     {
         "BriefDescription": "Counts the number of issue slots  that were not consumed by the backend due to branch mispredicts.",
-        "MetricExpr": "TOPDOWN_BAD_SPECULATION.MISPREDICT / tma_info_slots",
+        "MetricExpr": "TOPDOWN_BAD_SPECULATION.MISPREDICT / tma_info_core_slots",
         "MetricGroup": "TopdownL2;tma_L2_group;tma_bad_speculation_group",
         "MetricName": "tma_branch_mispredicts",
         "MetricThreshold": "tma_branch_mispredicts > 0.05",
@@ -192,7 +192,7 @@
     },
     {
         "BriefDescription": "Counts the number of issue slots  that were not delivered by the frontend due to BTCLEARS, which occurs when the Branch Target Buffer (BTB) predicts a taken branch.",
-        "MetricExpr": "TOPDOWN_FE_BOUND.BRANCH_RESTEER / tma_info_slots",
+        "MetricExpr": "TOPDOWN_FE_BOUND.BRANCH_RESTEER / tma_info_core_slots",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_fetch_latency_group",
         "MetricName": "tma_branch_resteer",
         "MetricThreshold": "tma_branch_resteer > 0.05",
@@ -201,7 +201,7 @@
     },
     {
         "BriefDescription": "Counts the number of issue slots  that were not delivered by the frontend due to the microcode sequencer (MS).",
-        "MetricExpr": "TOPDOWN_FE_BOUND.CISC / tma_info_slots",
+        "MetricExpr": "TOPDOWN_FE_BOUND.CISC / tma_info_core_slots",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_fetch_bandwidth_group",
         "MetricName": "tma_cisc",
         "MetricThreshold": "tma_cisc > 0.05",
@@ -220,7 +220,7 @@
     },
     {
         "BriefDescription": "Counts the number of issue slots  that were not delivered by the frontend due to decode stalls.",
-        "MetricExpr": "TOPDOWN_FE_BOUND.DECODE / tma_info_slots",
+        "MetricExpr": "TOPDOWN_FE_BOUND.DECODE / tma_info_core_slots",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_fetch_bandwidth_group",
         "MetricName": "tma_decode",
         "MetricThreshold": "tma_decode > 0.05",
@@ -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": "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@",
+        "MetricExpr": "cpu_atom@MEM_BOUND_STALLS.LOAD_DRAM_HIT@ / tma_info_core_clks - max((cpu_atom@MEM_BOUND_STALLS.LOAD@ - cpu_atom@LD_HEAD.L1_MISS_AT_RET@) / tma_info_core_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",
@@ -248,7 +248,7 @@
     },
     {
         "BriefDescription": "Counts the number of issue slots  that were not consumed by the backend due to a machine clear classified as a fast nuke due to memory ordering, memory disambiguation and memory renaming.",
-        "MetricExpr": "TOPDOWN_BAD_SPECULATION.FASTNUKE / tma_info_slots",
+        "MetricExpr": "TOPDOWN_BAD_SPECULATION.FASTNUKE / tma_info_core_slots",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_machine_clears_group",
         "MetricName": "tma_fast_nuke",
         "MetricThreshold": "tma_fast_nuke > 0.05",
@@ -257,7 +257,7 @@
     },
     {
         "BriefDescription": "Counts the number of issue slots  that were not delivered by the frontend due to frontend bandwidth restrictions due to decode, predecode, cisc, and other limitations.",
-        "MetricExpr": "TOPDOWN_FE_BOUND.FRONTEND_BANDWIDTH / tma_info_slots",
+        "MetricExpr": "TOPDOWN_FE_BOUND.FRONTEND_BANDWIDTH / tma_info_core_slots",
         "MetricGroup": "TopdownL2;tma_L2_group;tma_frontend_bound_group",
         "MetricName": "tma_fetch_bandwidth",
         "MetricThreshold": "tma_fetch_bandwidth > 0.1",
@@ -267,7 +267,7 @@
     },
     {
         "BriefDescription": "Counts the number of issue slots  that were not delivered by the frontend due to frontend bandwidth restrictions due to decode, predecode, cisc, and other limitations.",
-        "MetricExpr": "TOPDOWN_FE_BOUND.FRONTEND_LATENCY / tma_info_slots",
+        "MetricExpr": "TOPDOWN_FE_BOUND.FRONTEND_LATENCY / tma_info_core_slots",
         "MetricGroup": "TopdownL2;tma_L2_group;tma_frontend_bound_group",
         "MetricName": "tma_fetch_latency",
         "MetricThreshold": "tma_fetch_latency > 0.15",
@@ -286,7 +286,7 @@
     },
     {
         "BriefDescription": "Counts the number of floating point divide operations per uop.",
-        "MetricExpr": "UOPS_RETIRED.FPDIV / tma_info_slots",
+        "MetricExpr": "UOPS_RETIRED.FPDIV / tma_info_core_slots",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_base_group",
         "MetricName": "tma_fpdiv_uops",
         "MetricThreshold": "tma_fpdiv_uops > 0.2",
@@ -295,7 +295,7 @@
     },
     {
         "BriefDescription": "Counts the number of issue slots  that were not consumed by the backend due to frontend stalls.",
-        "MetricExpr": "TOPDOWN_FE_BOUND.ALL / tma_info_slots",
+        "MetricExpr": "TOPDOWN_FE_BOUND.ALL / tma_info_core_slots",
         "MetricGroup": "TopdownL1;tma_L1_group",
         "MetricName": "tma_frontend_bound",
         "MetricThreshold": "tma_frontend_bound > 0.2",
@@ -305,7 +305,7 @@
     },
     {
         "BriefDescription": "Counts the number of issue slots  that were not delivered by the frontend due to instruction cache misses.",
-        "MetricExpr": "TOPDOWN_FE_BOUND.ICACHE / tma_info_slots",
+        "MetricExpr": "TOPDOWN_FE_BOUND.ICACHE / tma_info_core_slots",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_fetch_latency_group",
         "MetricName": "tma_icache_misses",
         "MetricThreshold": "tma_icache_misses > 0.05",
@@ -313,246 +313,220 @@
         "Unit": "cpu_atom"
     },
     {
-        "BriefDescription": "Percentage of total non-speculative loads with a address aliasing block",
-        "MetricExpr": "100 * cpu_atom@LD_BLOCKS.4K_ALIAS@ / MEM_UOPS_RETIRED.ALL_LOADS",
-        "MetricName": "tma_info_address_alias_blocks",
-        "Unit": "cpu_atom"
-    },
-    {
-        "BriefDescription": "Ratio of all branches which mispredict",
-        "MetricExpr": "BR_MISP_RETIRED.ALL_BRANCHES / BR_INST_RETIRED.ALL_BRANCHES",
-        "MetricGroup": " ",
-        "MetricName": "tma_info_branch_mispredict_ratio",
-        "Unit": "cpu_atom"
-    },
-    {
-        "BriefDescription": "Ratio between Mispredicted branches and unknown branches",
-        "MetricExpr": "BR_MISP_RETIRED.ALL_BRANCHES / BACLEARS.ANY",
-        "MetricGroup": " ",
-        "MetricName": "tma_info_branch_mispredict_to_unknown_branch_ratio",
-        "Unit": "cpu_atom"
-    },
-    {
         "BriefDescription": "",
         "MetricExpr": "cpu_atom@CPU_CLK_UNHALTED.CORE@",
-        "MetricGroup": " ",
-        "MetricName": "tma_info_clks",
+        "MetricName": "tma_info_core_clks",
         "Unit": "cpu_atom"
     },
     {
         "BriefDescription": "",
         "MetricExpr": "cpu_atom@CPU_CLK_UNHALTED.CORE_P@",
-        "MetricGroup": " ",
-        "MetricName": "tma_info_clks_p",
+        "MetricName": "tma_info_core_clks_p",
         "Unit": "cpu_atom"
     },
     {
         "BriefDescription": "Cycles Per Instruction",
-        "MetricExpr": "tma_info_clks / INST_RETIRED.ANY",
-        "MetricGroup": " ",
-        "MetricName": "tma_info_cpi",
+        "MetricExpr": "tma_info_core_clks / INST_RETIRED.ANY",
+        "MetricName": "tma_info_core_cpi",
         "Unit": "cpu_atom"
     },
     {
-        "BriefDescription": "Average CPU Utilization",
-        "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / TSC",
-        "MetricGroup": " ",
-        "MetricName": "tma_info_cpu_utilization",
+        "BriefDescription": "Instructions Per Cycle",
+        "MetricExpr": "INST_RETIRED.ANY / tma_info_core_clks",
+        "MetricName": "tma_info_core_ipc",
         "Unit": "cpu_atom"
     },
     {
-        "BriefDescription": "Cycle cost per DRAM hit",
-        "MetricExpr": "MEM_BOUND_STALLS.LOAD_DRAM_HIT / MEM_LOAD_UOPS_RETIRED.DRAM_HIT",
-        "MetricGroup": " ",
-        "MetricName": "tma_info_cycles_per_demand_load_dram_hit",
+        "BriefDescription": "",
+        "MetricExpr": "5 * tma_info_core_clks",
+        "MetricName": "tma_info_core_slots",
         "Unit": "cpu_atom"
     },
     {
-        "BriefDescription": "Cycle cost per L2 hit",
-        "MetricExpr": "MEM_BOUND_STALLS.LOAD_L2_HIT / MEM_LOAD_UOPS_RETIRED.L2_HIT",
-        "MetricGroup": " ",
-        "MetricName": "tma_info_cycles_per_demand_load_l2_hit",
+        "BriefDescription": "Uops Per Instruction",
+        "MetricExpr": "UOPS_RETIRED.ALL / INST_RETIRED.ANY",
+        "MetricName": "tma_info_core_upi",
         "Unit": "cpu_atom"
     },
     {
-        "BriefDescription": "Cycle cost per LLC hit",
-        "MetricExpr": "MEM_BOUND_STALLS.LOAD_LLC_HIT / MEM_LOAD_UOPS_RETIRED.L3_HIT",
-        "MetricGroup": " ",
-        "MetricName": "tma_info_cycles_per_demand_load_l3_hit",
+        "BriefDescription": "Percent of instruction miss cost that hit in DRAM",
+        "MetricExpr": "100 * cpu_atom@MEM_BOUND_STALLS.IFETCH_DRAM_HIT@ / cpu_atom@MEM_BOUND_STALLS.IFETCH@",
+        "MetricName": "tma_info_frontend_inst_miss_cost_dramhit_percent",
         "Unit": "cpu_atom"
     },
     {
-        "BriefDescription": "Percentage of all uops which are FPDiv uops",
-        "MetricExpr": "100 * cpu_atom@UOPS_RETIRED.FPDIV@ / UOPS_RETIRED.ALL",
-        "MetricGroup": " ",
-        "MetricName": "tma_info_fpdiv_uop_ratio",
+        "BriefDescription": "Percent of instruction miss cost that hit in the L2",
+        "MetricExpr": "100 * cpu_atom@MEM_BOUND_STALLS.IFETCH_L2_HIT@ / cpu_atom@MEM_BOUND_STALLS.IFETCH@",
+        "MetricName": "tma_info_frontend_inst_miss_cost_l2hit_percent",
         "Unit": "cpu_atom"
     },
     {
-        "BriefDescription": "Percentage of all uops which are IDiv uops",
-        "MetricExpr": "100 * cpu_atom@UOPS_RETIRED.IDIV@ / UOPS_RETIRED.ALL",
-        "MetricGroup": " ",
-        "MetricName": "tma_info_idiv_uop_ratio",
+        "BriefDescription": "Percent of instruction miss cost that hit in the L3",
+        "MetricExpr": "100 * cpu_atom@MEM_BOUND_STALLS.IFETCH_LLC_HIT@ / cpu_atom@MEM_BOUND_STALLS.IFETCH@",
+        "MetricName": "tma_info_frontend_inst_miss_cost_l3hit_percent",
         "Unit": "cpu_atom"
     },
     {
-        "BriefDescription": "Percent of instruction miss cost that hit in DRAM",
-        "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",
+        "BriefDescription": "Ratio of all branches which mispredict",
+        "MetricExpr": "BR_MISP_RETIRED.ALL_BRANCHES / BR_INST_RETIRED.ALL_BRANCHES",
+        "MetricName": "tma_info_inst_mix_branch_mispredict_ratio",
         "Unit": "cpu_atom"
     },
     {
-        "BriefDescription": "Percent of instruction miss cost that hit in the L2",
-        "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",
+        "BriefDescription": "Ratio between Mispredicted branches and unknown branches",
+        "MetricExpr": "BR_MISP_RETIRED.ALL_BRANCHES / BACLEARS.ANY",
+        "MetricName": "tma_info_inst_mix_branch_mispredict_to_unknown_branch_ratio",
         "Unit": "cpu_atom"
     },
     {
-        "BriefDescription": "Percent of instruction miss cost that hit in the L3",
-        "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",
+        "BriefDescription": "Percentage of all uops which are FPDiv uops",
+        "MetricExpr": "100 * cpu_atom@UOPS_RETIRED.FPDIV@ / UOPS_RETIRED.ALL",
+        "MetricName": "tma_info_inst_mix_fpdiv_uop_ratio",
         "Unit": "cpu_atom"
     },
     {
-        "BriefDescription": "Instructions per Branch (lower number means higher occurance rate)",
-        "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.ALL_BRANCHES",
-        "MetricGroup": " ",
-        "MetricName": "tma_info_ipbranch",
+        "BriefDescription": "Percentage of all uops which are IDiv uops",
+        "MetricExpr": "100 * cpu_atom@UOPS_RETIRED.IDIV@ / UOPS_RETIRED.ALL",
+        "MetricName": "tma_info_inst_mix_idiv_uop_ratio",
         "Unit": "cpu_atom"
     },
     {
-        "BriefDescription": "Instructions Per Cycle",
-        "MetricExpr": "INST_RETIRED.ANY / tma_info_clks",
-        "MetricGroup": " ",
-        "MetricName": "tma_info_ipc",
+        "BriefDescription": "Instructions per Branch (lower number means higher occurance rate)",
+        "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.ALL_BRANCHES",
+        "MetricName": "tma_info_inst_mix_ipbranch",
         "Unit": "cpu_atom"
     },
     {
         "BriefDescription": "Instruction per (near) call (lower number means higher occurance rate)",
         "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.CALL",
-        "MetricGroup": " ",
-        "MetricName": "tma_info_ipcall",
+        "MetricName": "tma_info_inst_mix_ipcall",
         "Unit": "cpu_atom"
     },
     {
         "BriefDescription": "Instructions per Far Branch",
         "MetricExpr": "INST_RETIRED.ANY / (cpu_atom@BR_INST_RETIRED.FAR_BRANCH@ / 2)",
-        "MetricGroup": " ",
-        "MetricName": "tma_info_ipfarbranch",
+        "MetricName": "tma_info_inst_mix_ipfarbranch",
         "Unit": "cpu_atom"
     },
     {
         "BriefDescription": "Instructions per Load",
         "MetricExpr": "INST_RETIRED.ANY / MEM_UOPS_RETIRED.ALL_LOADS",
-        "MetricGroup": " ",
-        "MetricName": "tma_info_ipload",
+        "MetricName": "tma_info_inst_mix_ipload",
         "Unit": "cpu_atom"
     },
     {
         "BriefDescription": "Instructions per retired conditional Branch Misprediction where the branch was not taken",
         "MetricExpr": "INST_RETIRED.ANY / (cpu_atom@BR_MISP_RETIRED.COND@ - cpu_atom@BR_MISP_RETIRED.COND_TAKEN@)",
-        "MetricName": "tma_info_ipmisp_cond_ntaken",
+        "MetricName": "tma_info_inst_mix_ipmisp_cond_ntaken",
         "Unit": "cpu_atom"
     },
     {
         "BriefDescription": "Instructions per retired conditional Branch Misprediction where the branch was taken",
         "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.COND_TAKEN",
-        "MetricName": "tma_info_ipmisp_cond_taken",
+        "MetricName": "tma_info_inst_mix_ipmisp_cond_taken",
         "Unit": "cpu_atom"
     },
     {
         "BriefDescription": "Instructions per retired indirect call or jump Branch Misprediction",
         "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.INDIRECT",
-        "MetricName": "tma_info_ipmisp_indirect",
+        "MetricName": "tma_info_inst_mix_ipmisp_indirect",
         "Unit": "cpu_atom"
     },
     {
         "BriefDescription": "Instructions per retired return Branch Misprediction",
         "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.RETURN",
-        "MetricName": "tma_info_ipmisp_ret",
+        "MetricName": "tma_info_inst_mix_ipmisp_ret",
         "Unit": "cpu_atom"
     },
     {
         "BriefDescription": "Instructions per retired Branch Misprediction",
         "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.ALL_BRANCHES",
-        "MetricGroup": " ",
-        "MetricName": "tma_info_ipmispredict",
+        "MetricName": "tma_info_inst_mix_ipmispredict",
         "Unit": "cpu_atom"
     },
     {
         "BriefDescription": "Instructions per Store",
         "MetricExpr": "INST_RETIRED.ANY / MEM_UOPS_RETIRED.ALL_STORES",
-        "MetricGroup": " ",
-        "MetricName": "tma_info_ipstore",
+        "MetricName": "tma_info_inst_mix_ipstore",
         "Unit": "cpu_atom"
     },
     {
-        "BriefDescription": "Fraction of cycles spent in Kernel mode",
-        "MetricExpr": "cpu_atom@CPU_CLK_UNHALTED.CORE@k / CPU_CLK_UNHALTED.CORE",
-        "MetricGroup": " ",
-        "MetricName": "tma_info_kernel_utilization",
+        "BriefDescription": "Percentage of all uops which are ucode ops",
+        "MetricExpr": "100 * cpu_atom@UOPS_RETIRED.MS@ / UOPS_RETIRED.ALL",
+        "MetricName": "tma_info_inst_mix_microcode_uop_ratio",
+        "Unit": "cpu_atom"
+    },
+    {
+        "BriefDescription": "Percentage of all uops which are x87 uops",
+        "MetricExpr": "100 * cpu_atom@UOPS_RETIRED.X87@ / UOPS_RETIRED.ALL",
+        "MetricName": "tma_info_inst_mix_x87_uop_ratio",
+        "Unit": "cpu_atom"
+    },
+    {
+        "BriefDescription": "Percentage of total non-speculative loads with a address aliasing block",
+        "MetricExpr": "100 * cpu_atom@LD_BLOCKS.4K_ALIAS@ / MEM_UOPS_RETIRED.ALL_LOADS",
+        "MetricName": "tma_info_l1_bound_address_alias_blocks",
         "Unit": "cpu_atom"
     },
     {
         "BriefDescription": "Percentage of total non-speculative loads that are splits",
         "MetricExpr": "100 * cpu_atom@MEM_UOPS_RETIRED.SPLIT_LOADS@ / MEM_UOPS_RETIRED.ALL_LOADS",
-        "MetricName": "tma_info_load_splits",
+        "MetricName": "tma_info_l1_bound_load_splits",
         "Unit": "cpu_atom"
     },
     {
-        "BriefDescription": "load ops retired per 1000 instruction",
-        "MetricExpr": "1e3 * cpu_atom@MEM_UOPS_RETIRED.ALL_LOADS@ / INST_RETIRED.ANY",
-        "MetricGroup": " ",
-        "MetricName": "tma_info_memloadpki",
+        "BriefDescription": "Percentage of total non-speculative loads with a store forward or unknown store address block",
+        "MetricExpr": "100 * cpu_atom@LD_BLOCKS.DATA_UNKNOWN@ / MEM_UOPS_RETIRED.ALL_LOADS",
+        "MetricName": "tma_info_l1_bound_store_fwd_blocks",
         "Unit": "cpu_atom"
     },
     {
-        "BriefDescription": "Percentage of all uops which are ucode ops",
-        "MetricExpr": "100 * cpu_atom@UOPS_RETIRED.MS@ / UOPS_RETIRED.ALL",
-        "MetricGroup": " ",
-        "MetricName": "tma_info_microcode_uop_ratio",
+        "BriefDescription": "Cycle cost per DRAM hit",
+        "MetricExpr": "MEM_BOUND_STALLS.LOAD_DRAM_HIT / MEM_LOAD_UOPS_RETIRED.DRAM_HIT",
+        "MetricName": "tma_info_memory_cycles_per_demand_load_dram_hit",
         "Unit": "cpu_atom"
     },
     {
-        "BriefDescription": "",
-        "MetricExpr": "5 * tma_info_clks",
-        "MetricGroup": " ",
-        "MetricName": "tma_info_slots",
+        "BriefDescription": "Cycle cost per L2 hit",
+        "MetricExpr": "MEM_BOUND_STALLS.LOAD_L2_HIT / MEM_LOAD_UOPS_RETIRED.L2_HIT",
+        "MetricName": "tma_info_memory_cycles_per_demand_load_l2_hit",
         "Unit": "cpu_atom"
     },
     {
-        "BriefDescription": "Percentage of total non-speculative loads with a store forward or unknown store address block",
-        "MetricExpr": "100 * cpu_atom@LD_BLOCKS.DATA_UNKNOWN@ / MEM_UOPS_RETIRED.ALL_LOADS",
-        "MetricName": "tma_info_store_fwd_blocks",
+        "BriefDescription": "Cycle cost per LLC hit",
+        "MetricExpr": "MEM_BOUND_STALLS.LOAD_LLC_HIT / MEM_LOAD_UOPS_RETIRED.L3_HIT",
+        "MetricName": "tma_info_memory_cycles_per_demand_load_l3_hit",
         "Unit": "cpu_atom"
     },
     {
-        "BriefDescription": "Average Frequency Utilization relative nominal frequency",
-        "MetricExpr": "tma_info_clks / CPU_CLK_UNHALTED.REF_TSC",
-        "MetricGroup": " ",
-        "MetricName": "tma_info_turbo_utilization",
+        "BriefDescription": "load ops retired per 1000 instruction",
+        "MetricExpr": "1e3 * cpu_atom@MEM_UOPS_RETIRED.ALL_LOADS@ / INST_RETIRED.ANY",
+        "MetricName": "tma_info_memory_memloadpki",
         "Unit": "cpu_atom"
     },
     {
-        "BriefDescription": "Uops Per Instruction",
-        "MetricExpr": "UOPS_RETIRED.ALL / INST_RETIRED.ANY",
-        "MetricGroup": " ",
-        "MetricName": "tma_info_upi",
+        "BriefDescription": "Average CPU Utilization",
+        "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / TSC",
+        "MetricName": "tma_info_system_cpu_utilization",
         "Unit": "cpu_atom"
     },
     {
-        "BriefDescription": "Percentage of all uops which are x87 uops",
-        "MetricExpr": "100 * cpu_atom@UOPS_RETIRED.X87@ / UOPS_RETIRED.ALL",
-        "MetricGroup": " ",
-        "MetricName": "tma_info_x87_uop_ratio",
+        "BriefDescription": "Fraction of cycles spent in Kernel mode",
+        "MetricExpr": "cpu_atom@CPU_CLK_UNHALTED.CORE@k / CPU_CLK_UNHALTED.CORE",
+        "MetricGroup": "Summary",
+        "MetricName": "tma_info_system_kernel_utilization",
+        "Unit": "cpu_atom"
+    },
+    {
+        "BriefDescription": "Average Frequency Utilization relative nominal frequency",
+        "MetricExpr": "tma_info_core_clks / CPU_CLK_UNHALTED.REF_TSC",
+        "MetricGroup": "Power",
+        "MetricName": "tma_info_system_turbo_utilization",
         "Unit": "cpu_atom"
     },
     {
         "BriefDescription": "Counts the number of issue slots  that were not delivered by the frontend due to Instruction Table Lookaside Buffer (ITLB) misses.",
-        "MetricExpr": "TOPDOWN_FE_BOUND.ITLB / tma_info_slots",
+        "MetricExpr": "TOPDOWN_FE_BOUND.ITLB / tma_info_core_slots",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_fetch_latency_group",
         "MetricName": "tma_itlb_misses",
         "MetricThreshold": "tma_itlb_misses > 0.05",
@@ -561,7 +535,7 @@
     },
     {
         "BriefDescription": "Counts the number of cycles that the oldest load of the load buffer is stalled at retirement due to a load block.",
-        "MetricExpr": "LD_HEAD.L1_BOUND_AT_RET / tma_info_clks",
+        "MetricExpr": "LD_HEAD.L1_BOUND_AT_RET / tma_info_core_clks",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_memory_bound_group",
         "MetricName": "tma_l1_bound",
         "MetricThreshold": "tma_l1_bound > 0.1",
@@ -571,7 +545,7 @@
     {
         "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": "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@",
+        "MetricExpr": "cpu_atom@MEM_BOUND_STALLS.LOAD_L2_HIT@ / tma_info_core_clks - max((cpu_atom@MEM_BOUND_STALLS.LOAD@ - cpu_atom@LD_HEAD.L1_MISS_AT_RET@) / tma_info_core_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 +554,7 @@
     },
     {
         "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": "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@",
+        "MetricExpr": "cpu_atom@MEM_BOUND_STALLS.LOAD_LLC_HIT@ / tma_info_core_clks - max((cpu_atom@MEM_BOUND_STALLS.LOAD@ - cpu_atom@LD_HEAD.L1_MISS_AT_RET@) / tma_info_core_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",
@@ -598,7 +572,7 @@
     },
     {
         "BriefDescription": "Counts the total number of issue slots that were not consumed by the backend because allocation is stalled due to a machine clear (nuke) of any kind including memory ordering and memory disambiguation.",
-        "MetricExpr": "TOPDOWN_BAD_SPECULATION.MACHINE_CLEARS / tma_info_slots",
+        "MetricExpr": "TOPDOWN_BAD_SPECULATION.MACHINE_CLEARS / tma_info_core_slots",
         "MetricGroup": "TopdownL2;tma_L2_group;tma_bad_speculation_group",
         "MetricName": "tma_machine_clears",
         "MetricThreshold": "tma_machine_clears > 0.05",
@@ -608,7 +582,7 @@
     },
     {
         "BriefDescription": "Counts the number of issue slots  that were not consumed by the backend due to memory reservation stalls in which a scheduler is not able to accept uops.",
-        "MetricExpr": "TOPDOWN_BE_BOUND.MEM_SCHEDULER / tma_info_slots",
+        "MetricExpr": "TOPDOWN_BE_BOUND.MEM_SCHEDULER / tma_info_core_slots",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_resource_bound_group",
         "MetricName": "tma_mem_scheduler",
         "MetricThreshold": "tma_mem_scheduler > 0.1",
@@ -617,7 +591,7 @@
     },
     {
         "BriefDescription": "Counts the number of cycles the core is stalled due to stores or loads.",
-        "MetricExpr": "min(cpu_atom@TOPDOWN_BE_BOUND.ALL@ / tma_info_slots, cpu_atom@LD_HEAD.ANY_AT_RET@ / tma_info_clks + tma_store_bound)",
+        "MetricExpr": "min(cpu_atom@TOPDOWN_BE_BOUND.ALL@ / tma_info_core_slots, cpu_atom@LD_HEAD.ANY_AT_RET@ / tma_info_core_clks + tma_store_bound)",
         "MetricGroup": "TopdownL2;tma_L2_group;tma_backend_bound_group",
         "MetricName": "tma_memory_bound",
         "MetricThreshold": "tma_memory_bound > 0.2",
@@ -636,7 +610,7 @@
     },
     {
         "BriefDescription": "Counts the number of uops that are from the complex flows issued by the micro-sequencer (MS)",
-        "MetricExpr": "UOPS_RETIRED.MS / tma_info_slots",
+        "MetricExpr": "UOPS_RETIRED.MS / tma_info_core_slots",
         "MetricGroup": "TopdownL2;tma_L2_group;tma_retiring_group",
         "MetricName": "tma_ms_uops",
         "MetricThreshold": "tma_ms_uops > 0.05",
@@ -647,7 +621,7 @@
     },
     {
         "BriefDescription": "Counts the number of issue slots  that were not consumed by the backend due to IEC or FPC RAT stalls, which can be due to FIQ or IEC reservation stalls in which the integer, floating point or SIMD scheduler is not able to accept uops.",
-        "MetricExpr": "TOPDOWN_BE_BOUND.NON_MEM_SCHEDULER / tma_info_slots",
+        "MetricExpr": "TOPDOWN_BE_BOUND.NON_MEM_SCHEDULER / tma_info_core_slots",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_resource_bound_group",
         "MetricName": "tma_non_mem_scheduler",
         "MetricThreshold": "tma_non_mem_scheduler > 0.1",
@@ -656,7 +630,7 @@
     },
     {
         "BriefDescription": "Counts the number of issue slots  that were not consumed by the backend due to a machine clear (slow nuke).",
-        "MetricExpr": "TOPDOWN_BAD_SPECULATION.NUKE / tma_info_slots",
+        "MetricExpr": "TOPDOWN_BAD_SPECULATION.NUKE / tma_info_core_slots",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_machine_clears_group",
         "MetricName": "tma_nuke",
         "MetricThreshold": "tma_nuke > 0.05",
@@ -665,7 +639,7 @@
     },
     {
         "BriefDescription": "Counts the number of issue slots  that were not delivered by the frontend due to other common frontend stalls not categorized.",
-        "MetricExpr": "TOPDOWN_FE_BOUND.OTHER / tma_info_slots",
+        "MetricExpr": "TOPDOWN_FE_BOUND.OTHER / tma_info_core_slots",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_fetch_bandwidth_group",
         "MetricName": "tma_other_fb",
         "MetricThreshold": "tma_other_fb > 0.05",
@@ -674,7 +648,7 @@
     },
     {
         "BriefDescription": "Counts the number of cycles that the oldest load of the load buffer is stalled at retirement due to a number of other load blocks.",
-        "MetricExpr": "LD_HEAD.OTHER_AT_RET / tma_info_clks",
+        "MetricExpr": "LD_HEAD.OTHER_AT_RET / tma_info_core_clks",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group",
         "MetricName": "tma_other_l1",
         "MetricThreshold": "tma_other_l1 > 0.05",
@@ -692,7 +666,7 @@
     },
     {
         "BriefDescription": "Counts the number of uops retired excluding ms and fp div uops.",
-        "MetricExpr": "(cpu_atom@TOPDOWN_RETIRING.ALL@ - cpu_atom@UOPS_RETIRED.MS@ - cpu_atom@UOPS_RETIRED.FPDIV@) / tma_info_slots",
+        "MetricExpr": "(cpu_atom@TOPDOWN_RETIRING.ALL@ - cpu_atom@UOPS_RETIRED.MS@ - cpu_atom@UOPS_RETIRED.FPDIV@) / tma_info_core_slots",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_base_group",
         "MetricName": "tma_other_ret",
         "MetricThreshold": "tma_other_ret > 0.3",
@@ -710,7 +684,7 @@
     },
     {
         "BriefDescription": "Counts the number of issue slots  that were not delivered by the frontend due to wrong predecodes.",
-        "MetricExpr": "TOPDOWN_FE_BOUND.PREDECODE / tma_info_slots",
+        "MetricExpr": "TOPDOWN_FE_BOUND.PREDECODE / tma_info_core_slots",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_fetch_bandwidth_group",
         "MetricName": "tma_predecode",
         "MetricThreshold": "tma_predecode > 0.05",
@@ -719,7 +693,7 @@
     },
     {
         "BriefDescription": "Counts the number of issue slots  that were not consumed by the backend due to the physical register file unable to accept an entry (marble stalls).",
-        "MetricExpr": "TOPDOWN_BE_BOUND.REGISTER / tma_info_slots",
+        "MetricExpr": "TOPDOWN_BE_BOUND.REGISTER / tma_info_core_slots",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_resource_bound_group",
         "MetricName": "tma_register",
         "MetricThreshold": "tma_register > 0.1",
@@ -728,7 +702,7 @@
     },
     {
         "BriefDescription": "Counts the number of issue slots  that were not consumed by the backend due to the reorder buffer being full (ROB stalls).",
-        "MetricExpr": "TOPDOWN_BE_BOUND.REORDER_BUFFER / tma_info_slots",
+        "MetricExpr": "TOPDOWN_BE_BOUND.REORDER_BUFFER / tma_info_core_slots",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_resource_bound_group",
         "MetricName": "tma_reorder_buffer",
         "MetricThreshold": "tma_reorder_buffer > 0.1",
@@ -748,7 +722,7 @@
     },
     {
         "BriefDescription": "Counts the numer of issue slots  that result in retirement slots.",
-        "MetricExpr": "TOPDOWN_RETIRING.ALL / tma_info_slots",
+        "MetricExpr": "TOPDOWN_RETIRING.ALL / tma_info_core_slots",
         "MetricGroup": "TopdownL1;tma_L1_group",
         "MetricName": "tma_retiring",
         "MetricThreshold": "tma_retiring > 0.75",
@@ -767,7 +741,7 @@
     },
     {
         "BriefDescription": "Counts the number of issue slots  that were not consumed by the backend due to scoreboards from the instruction queue (IQ), jump execution unit (JEU), or microcode sequencer (MS).",
-        "MetricExpr": "TOPDOWN_BE_BOUND.SERIALIZATION / tma_info_slots",
+        "MetricExpr": "TOPDOWN_BE_BOUND.SERIALIZATION / tma_info_core_slots",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_resource_bound_group",
         "MetricName": "tma_serialization",
         "MetricThreshold": "tma_serialization > 0.1",
@@ -794,7 +768,7 @@
     },
     {
         "BriefDescription": "Counts the number of cycles that the oldest load of the load buffer is stalled at retirement due to a first level TLB miss.",
-        "MetricExpr": "LD_HEAD.DTLB_MISS_AT_RET / tma_info_clks",
+        "MetricExpr": "LD_HEAD.DTLB_MISS_AT_RET / tma_info_core_clks",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group",
         "MetricName": "tma_stlb_hit",
         "MetricThreshold": "tma_stlb_hit > 0.05",
@@ -803,7 +777,7 @@
     },
     {
         "BriefDescription": "Counts the number of cycles that the oldest load of the load buffer is stalled at retirement due to a second level TLB miss requiring a page walk.",
-        "MetricExpr": "LD_HEAD.PGWALK_AT_RET / tma_info_clks",
+        "MetricExpr": "LD_HEAD.PGWALK_AT_RET / tma_info_core_clks",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group",
         "MetricName": "tma_stlb_miss",
         "MetricThreshold": "tma_stlb_miss > 0.05",
@@ -821,7 +795,7 @@
     },
     {
         "BriefDescription": "Counts the number of cycles that the oldest load of the load buffer is stalled at retirement due to a store forward block.",
-        "MetricExpr": "LD_HEAD.ST_ADDR_AT_RET / tma_info_clks",
+        "MetricExpr": "LD_HEAD.ST_ADDR_AT_RET / tma_info_core_clks",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group",
         "MetricName": "tma_store_fwd_blk",
         "MetricThreshold": "tma_store_fwd_blk > 0.05",
@@ -830,7 +804,7 @@
     },
     {
         "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution ports for ALU operations.",
-        "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)",
+        "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_core_clks)",
         "MetricGroup": "TopdownL5;tma_L5_group;tma_ports_utilized_3m_group",
         "MetricName": "tma_alu_op_utilization",
         "MetricThreshold": "tma_alu_op_utilization > 0.6",
@@ -839,7 +813,7 @@
     },
     {
         "BriefDescription": "This metric estimates fraction of slots the CPU retired uops delivered by the Microcode_Sequencer as a result of Assists",
-        "MetricExpr": "100 * cpu_core@ASSISTS.ANY\\,umask\\=0x1B@ / tma_info_slots",
+        "MetricExpr": "100 * cpu_core@ASSISTS.ANY\\,umask\\=0x1B@ / tma_info_thread_slots",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_microcode_sequencer_group",
         "MetricName": "tma_assists",
         "MetricThreshold": "tma_assists > 0.1 & (tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1)",
@@ -849,7 +823,7 @@
     },
     {
         "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 * cpu_core@ASSISTS.SSE_AVX_MIX@ / tma_info_slots",
+        "MetricExpr": "63 * cpu_core@ASSISTS.SSE_AVX_MIX@ / tma_info_thread_slots",
         "MetricGroup": "HPC;TopdownL5;tma_L5_group;tma_assists_group",
         "MetricName": "tma_avx_assists",
         "MetricThreshold": "tma_avx_assists > 0.1",
@@ -858,7 +832,7 @@
     },
     {
         "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": "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",
+        "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_thread_slots",
         "MetricGroup": "TmaL1;TopdownL1;tma_L1_group",
         "MetricName": "tma_backend_bound",
         "MetricThreshold": "tma_backend_bound > 0.2",
@@ -880,18 +854,18 @@
     },
     {
         "BriefDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction",
-        "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",
+        "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_thread_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",
         "MetricgroupNoGroup": "TopdownL2",
-        "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction.  These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: TOPDOWN.BR_MISPREDICT_SLOTS. Related metrics: tma_info_branch_misprediction_cost, tma_info_mispredictions, tma_mispredicts_resteers",
+        "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction.  These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: TOPDOWN.BR_MISPREDICT_SLOTS. Related metrics: tma_info_bad_spec_branch_misprediction_cost, tma_info_bottleneck_mispredictions, tma_mispredicts_resteers",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
         "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers",
-        "MetricExpr": "INT_MISC.CLEAR_RESTEER_CYCLES / tma_info_clks + tma_unknown_branches",
+        "MetricExpr": "INT_MISC.CLEAR_RESTEER_CYCLES / tma_info_thread_clks + tma_unknown_branches",
         "MetricGroup": "FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group",
         "MetricName": "tma_branch_resteers",
         "MetricThreshold": "tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)",
@@ -911,7 +885,7 @@
     },
     {
         "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) * cpu_core@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_thread_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 +896,7 @@
     {
         "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 * (cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD@ * (cpu_core@OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM@ / (cpu_core@OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM@ + cpu_core@OCR.DEMAND_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",
+        "MetricExpr": "(25 * tma_info_system_average_frequency * (cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD@ * (cpu_core@OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM@ / (cpu_core@OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM@ + cpu_core@OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD@))) + 24 * tma_info_system_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_thread_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 +918,7 @@
     {
         "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 * (cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_NO_FWD@ + cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD@ * (1 - cpu_core@OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM@ / (cpu_core@OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM@ + cpu_core@OCR.DEMAND_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",
+        "MetricExpr": "24 * tma_info_system_average_frequency * (cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_NO_FWD@ + cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD@ * (1 - cpu_core@OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM@ / (cpu_core@OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM@ + cpu_core@OCR.DEMAND_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_thread_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))",
@@ -954,17 +928,17 @@
     },
     {
         "BriefDescription": "This metric represents fraction of cycles where decoder-0 was the only active decoder",
-        "MetricExpr": "(cpu_core@INST_DECODED.DECODERS\\,cmask\\=1@ - cpu_core@INST_DECODED.DECODERS\\,cmask\\=2@) / tma_info_core_clks / 2",
+        "MetricExpr": "(cpu_core@INST_DECODED.DECODERS\\,cmask\\=1@ - cpu_core@INST_DECODED.DECODERS\\,cmask\\=2@) / tma_info_core_core_clks / 2",
         "MetricGroup": "DSBmiss;FetchBW;TopdownL4;tma_L4_group;tma_issueD0;tma_mite_group",
         "MetricName": "tma_decoder0_alone",
-        "MetricThreshold": "tma_decoder0_alone > 0.1 & (tma_mite > 0.1 & (tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 6 > 0.35))",
+        "MetricThreshold": "tma_decoder0_alone > 0.1 & (tma_mite > 0.1 & (tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_thread_ipc / 6 > 0.35))",
         "PublicDescription": "This metric represents fraction of cycles where decoder-0 was the only active decoder. Related metrics: tma_few_uops_instructions",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
         "BriefDescription": "This metric represents fraction of cycles where the Divider unit was active",
-        "MetricExpr": "ARITH.DIV_ACTIVE / tma_info_clks",
+        "MetricExpr": "ARITH.DIV_ACTIVE / tma_info_thread_clks",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_core_bound_group",
         "MetricName": "tma_divider",
         "MetricThreshold": "tma_divider > 0.2 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)",
@@ -975,7 +949,7 @@
     {
         "BriefDescription": "This metric estimates how often the CPU was stalled on accesses to external memory (DRAM) by loads",
         "MetricConstraint": "NO_GROUP_EVENTS",
-        "MetricExpr": "cpu_core@MEMORY_ACTIVITY.STALLS_L3_MISS@ / tma_info_clks",
+        "MetricExpr": "cpu_core@MEMORY_ACTIVITY.STALLS_L3_MISS@ / tma_info_thread_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)",
@@ -985,47 +959,47 @@
     },
     {
         "BriefDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to DSB (decoded uop cache) fetch pipeline",
-        "MetricExpr": "(cpu_core@IDQ.DSB_CYCLES_ANY@ - cpu_core@IDQ.DSB_CYCLES_OK@) / tma_info_core_clks / 2",
+        "MetricExpr": "(cpu_core@IDQ.DSB_CYCLES_ANY@ - cpu_core@IDQ.DSB_CYCLES_OK@) / tma_info_core_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)",
+        "MetricThreshold": "tma_dsb > 0.15 & (tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_thread_ipc / 6 > 0.35)",
         "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to DSB (decoded uop cache) fetch pipeline.  For example; inefficient utilization of the DSB cache structure or bank conflict when reading from it; are categorized here.",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
         "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines",
-        "MetricExpr": "DSB2MITE_SWITCHES.PENALTY_CYCLES / tma_info_clks",
+        "MetricExpr": "DSB2MITE_SWITCHES.PENALTY_CYCLES / tma_info_thread_clks",
         "MetricGroup": "DSBmiss;FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueFB",
         "MetricName": "tma_dsb_switches",
         "MetricThreshold": "tma_dsb_switches > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)",
-        "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines. The DSB (decoded i-cache) is a Uop Cache where the front-end directly delivers Uops (micro operations) avoiding heavy x86 decoding. The DSB pipeline has shorter latency and delivered higher bandwidth than the MITE (legacy instruction decode pipeline). Switching between the two pipelines can cause penalties hence this metric measures the exposed penalty. Sample with: FRONTEND_RETIRED.DSB_MISS_PS. Related metrics: tma_fetch_bandwidth, tma_info_dsb_coverage, tma_info_dsb_misses, tma_info_iptb, tma_lcp",
+        "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines. The DSB (decoded i-cache) is a Uop Cache where the front-end directly delivers Uops (micro operations) avoiding heavy x86 decoding. The DSB pipeline has shorter latency and delivered higher bandwidth than the MITE (legacy instruction decode pipeline). Switching between the two pipelines can cause penalties hence this metric measures the exposed penalty. Sample with: FRONTEND_RETIRED.DSB_MISS_PS. Related metrics: tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
         "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@ + 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",
+        "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_thread_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))",
-        "PublicDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses. TLBs (Translation Look-aside Buffers) are processor caches for recently used entries out of the Page Tables that are used to map virtual- to physical-addresses by the operating system. This metric approximates the potential delay of demand loads missing the first-level data TLB (assuming worst case scenario with back to back misses to different pages). This includes hitting in the second-level TLB (STLB) as well as performing a hardware page walk on an STLB miss. Sample with: MEM_INST_RETIRED.STLB_MISS_LOADS_PS. Related metrics: tma_dtlb_store, tma_info_memory_data_tlbs",
+        "PublicDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses. TLBs (Translation Look-aside Buffers) are processor caches for recently used entries out of the Page Tables that are used to map virtual- to physical-addresses by the operating system. This metric approximates the potential delay of demand loads missing the first-level data TLB (assuming worst case scenario with back to back misses to different pages). This includes hitting in the second-level TLB (STLB) as well as performing a hardware page walk on an STLB miss. Sample with: MEM_INST_RETIRED.STLB_MISS_LOADS_PS. Related metrics: tma_dtlb_store, tma_info_bottleneck_memory_data_tlbs",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
         "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@ + cpu_core@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_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))",
-        "PublicDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses.  As with ordinary data caching; focus on improving data locality and reducing working-set size to reduce DTLB overhead.  Additionally; consider using profile-guided optimization (PGO) to collocate frequently-used data on the same page.  Try using larger page sizes for large amounts of frequently-used data. Sample with: MEM_INST_RETIRED.STLB_MISS_STORES_PS. Related metrics: tma_dtlb_load, tma_info_memory_data_tlbs",
+        "PublicDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses.  As with ordinary data caching; focus on improving data locality and reducing working-set size to reduce DTLB overhead.  Additionally; consider using profile-guided optimization (PGO) to collocate frequently-used data on the same page.  Try using larger page sizes for large amounts of frequently-used data. Sample with: MEM_INST_RETIRED.STLB_MISS_STORES_PS. Related metrics: tma_dtlb_load, tma_info_bottleneck_memory_data_tlbs",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
         "BriefDescription": "This metric roughly estimates how often CPU was handling synchronizations due to False Sharing",
-        "MetricExpr": "28 * tma_info_average_frequency * cpu_core@OCR.DEMAND_RFO.L3_HIT.SNOOP_HITM@ / tma_info_clks",
+        "MetricExpr": "28 * tma_info_system_average_frequency * cpu_core@OCR.DEMAND_RFO.L3_HIT.SNOOP_HITM@ / tma_info_thread_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))",
@@ -1035,11 +1009,11 @@
     },
     {
         "BriefDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed",
-        "MetricExpr": "L1D_PEND_MISS.FB_FULL / tma_info_clks",
+        "MetricExpr": "L1D_PEND_MISS.FB_FULL / tma_info_thread_clks",
         "MetricGroup": "MemoryBW;TopdownL4;tma_L4_group;tma_issueBW;tma_issueSL;tma_issueSmSt;tma_l1_bound_group",
         "MetricName": "tma_fb_full",
         "MetricThreshold": "tma_fb_full > 0.3",
-        "PublicDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed. The higher the metric value; the deeper the memory hierarchy level the misses are satisfied from (metric values >1 are valid). Often it hints on approaching bandwidth limits (to L2 cache; L3 cache or external memory). Related metrics: tma_info_dram_bw_use, tma_info_memory_bandwidth, tma_mem_bandwidth, tma_sq_full, tma_store_latency, tma_streaming_stores",
+        "PublicDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed. The higher the metric value; the deeper the memory hierarchy level the misses are satisfied from (metric values >1 are valid). Often it hints on approaching bandwidth limits (to L2 cache; L3 cache or external memory). Related metrics: tma_info_bottleneck_memory_bandwidth, tma_info_system_dram_bw_use, tma_mem_bandwidth, tma_sq_full, tma_store_latency, tma_streaming_stores",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -1048,15 +1022,15 @@
         "MetricExpr": "max(0, tma_frontend_bound - tma_fetch_latency)",
         "MetricGroup": "FetchBW;Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group;tma_issueFB",
         "MetricName": "tma_fetch_bandwidth",
-        "MetricThreshold": "tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 6 > 0.35",
+        "MetricThreshold": "tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_thread_ipc / 6 > 0.35",
         "MetricgroupNoGroup": "TopdownL2",
-        "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues.  For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Sample with: FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1_PS;FRONTEND_RETIRED.LATENCY_GE_1_PS;FRONTEND_RETIRED.LATENCY_GE_2_PS. Related metrics: tma_dsb_switches, tma_info_dsb_coverage, tma_info_dsb_misses, tma_info_iptb, tma_lcp",
+        "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues.  For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Sample with: FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1_PS;FRONTEND_RETIRED.LATENCY_GE_1_PS;FRONTEND_RETIRED.LATENCY_GE_2_PS. Related metrics: tma_dsb_switches, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
         "BriefDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues",
-        "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",
+        "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_thread_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 +1062,7 @@
     },
     {
         "BriefDescription": "This metric roughly estimates fraction of slots the CPU retired uops as a result of handing Floating Point (FP) Assists",
-        "MetricExpr": "30 * cpu_core@ASSISTS.FP@ / tma_info_slots",
+        "MetricExpr": "30 * cpu_core@ASSISTS.FP@ / tma_info_thread_slots",
         "MetricGroup": "HPC;TopdownL5;tma_L5_group;tma_assists_group",
         "MetricName": "tma_fp_assists",
         "MetricThreshold": "tma_fp_assists > 0.1",
@@ -1098,7 +1072,7 @@
     },
     {
         "BriefDescription": "This metric approximates arithmetic floating-point (FP) scalar uops fraction the CPU has retired",
-        "MetricExpr": "cpu_core@FP_ARITH_INST_RETIRED.SCALAR_SINGLE\\,umask\\=0x03@ / (tma_retiring * tma_info_slots)",
+        "MetricExpr": "cpu_core@FP_ARITH_INST_RETIRED.SCALAR_SINGLE\\,umask\\=0x03@ / (tma_retiring * tma_info_thread_slots)",
         "MetricGroup": "Compute;Flops;TopdownL4;tma_L4_group;tma_fp_arith_group;tma_issue2P",
         "MetricName": "tma_fp_scalar",
         "MetricThreshold": "tma_fp_scalar > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6)",
@@ -1108,7 +1082,7 @@
     },
     {
         "BriefDescription": "This metric approximates arithmetic floating-point (FP) vector uops fraction the CPU has retired aggregated across all vector widths",
-        "MetricExpr": "cpu_core@FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE\\,umask\\=0x3c@ / (tma_retiring * tma_info_slots)",
+        "MetricExpr": "cpu_core@FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE\\,umask\\=0x3c@ / (tma_retiring * tma_info_thread_slots)",
         "MetricGroup": "Compute;Flops;TopdownL4;tma_L4_group;tma_fp_arith_group;tma_issue2P",
         "MetricName": "tma_fp_vector",
         "MetricThreshold": "tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6)",
@@ -1118,7 +1092,7 @@
     },
     {
         "BriefDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 128-bit wide vectors",
-        "MetricExpr": "(cpu_core@FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE@ + cpu_core@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_thread_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 +1102,7 @@
     },
     {
         "BriefDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 256-bit wide vectors",
-        "MetricExpr": "(cpu_core@FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE@ + cpu_core@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_thread_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 +1112,7 @@
     },
     {
         "BriefDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend",
-        "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",
+        "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_thread_slots",
         "MetricGroup": "PGO;TmaL1;TopdownL1;tma_L1_group",
         "MetricName": "tma_frontend_bound",
         "MetricThreshold": "tma_frontend_bound > 0.15",
@@ -1149,7 +1123,7 @@
     },
     {
         "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 * cpu_core@INST_RETIRED.MACRO_FUSED@ / (tma_retiring * tma_info_slots)",
+        "MetricExpr": "tma_light_operations * cpu_core@INST_RETIRED.MACRO_FUSED@ / (tma_retiring * tma_info_thread_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 +1133,7 @@
     },
     {
         "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": "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",
+        "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_thread_slots",
         "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group",
         "MetricName": "tma_heavy_operations",
         "MetricThreshold": "tma_heavy_operations > 0.1",
@@ -1170,7 +1144,7 @@
     },
     {
         "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to instruction cache misses",
-        "MetricExpr": "ICACHE_DATA.STALLS / tma_info_clks",
+        "MetricExpr": "ICACHE_DATA.STALLS / tma_info_thread_clks",
         "MetricGroup": "BigFoot;FetchLat;IcMiss;TopdownL3;tma_L3_group;tma_fetch_latency_group",
         "MetricName": "tma_icache_misses",
         "MetricThreshold": "tma_icache_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)",
@@ -1179,10 +1153,80 @@
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "Measured Average Frequency for unhalted processors [GHz]",
-        "MetricExpr": "tma_info_turbo_utilization * TSC / 1e9 / duration_time",
-        "MetricGroup": "Power;Summary",
-        "MetricName": "tma_info_average_frequency",
+        "BriefDescription": "Branch Misprediction Cost: Fraction of TMA slots wasted per non-speculative branch misprediction (retired JEClear)",
+        "MetricConstraint": "NO_GROUP_EVENTS",
+        "MetricExpr": "(tma_branch_mispredicts + tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches)) * tma_info_thread_slots / BR_MISP_RETIRED.ALL_BRANCHES",
+        "MetricGroup": "Bad;BrMispredicts;tma_issueBM",
+        "MetricName": "tma_info_bad_spec_branch_misprediction_cost",
+        "PublicDescription": "Branch Misprediction Cost: Fraction of TMA slots wasted per non-speculative branch misprediction (retired JEClear). Related metrics: tma_branch_mispredicts, tma_info_bottleneck_mispredictions, tma_mispredicts_resteers",
+        "Unit": "cpu_core"
+    },
+    {
+        "BriefDescription": "Instructions per retired mispredicts for conditional non-taken branches (lower number means higher occurrence rate).",
+        "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.COND_NTAKEN",
+        "MetricGroup": "Bad;BrMispredicts",
+        "MetricName": "tma_info_bad_spec_ipmisp_cond_ntaken",
+        "MetricThreshold": "tma_info_bad_spec_ipmisp_cond_ntaken < 200",
+        "Unit": "cpu_core"
+    },
+    {
+        "BriefDescription": "Instructions per retired mispredicts for conditional taken branches (lower number means higher occurrence rate).",
+        "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.COND_TAKEN",
+        "MetricGroup": "Bad;BrMispredicts",
+        "MetricName": "tma_info_bad_spec_ipmisp_cond_taken",
+        "MetricThreshold": "tma_info_bad_spec_ipmisp_cond_taken < 200",
+        "Unit": "cpu_core"
+    },
+    {
+        "BriefDescription": "Instructions per retired mispredicts for indirect CALL or JMP branches (lower number means higher occurrence rate).",
+        "MetricExpr": "cpu_core@BR_MISP_RETIRED.INDIRECT_CALL\\,umask\\=0x80@ / BR_MISP_RETIRED.INDIRECT",
+        "MetricGroup": "Bad;BrMispredicts",
+        "MetricName": "tma_info_bad_spec_ipmisp_indirect",
+        "MetricThreshold": "tma_info_bad_spec_ipmisp_indirect < 1e3",
+        "Unit": "cpu_core"
+    },
+    {
+        "BriefDescription": "Instructions per retired mispredicts for return branches (lower number means higher occurrence rate).",
+        "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.RET",
+        "MetricGroup": "Bad;BrMispredicts",
+        "MetricName": "tma_info_bad_spec_ipmisp_ret",
+        "MetricThreshold": "tma_info_bad_spec_ipmisp_ret < 500",
+        "Unit": "cpu_core"
+    },
+    {
+        "BriefDescription": "Number of Instructions per non-speculative Branch Misprediction (JEClear) (lower number means higher occurrence rate)",
+        "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.ALL_BRANCHES",
+        "MetricGroup": "Bad;BadSpec;BrMispredicts",
+        "MetricName": "tma_info_bad_spec_ipmispredict",
+        "MetricThreshold": "tma_info_bad_spec_ipmispredict < 200",
+        "Unit": "cpu_core"
+    },
+    {
+        "BriefDescription": "Probability of Core Bound bottleneck hidden by SMT-profiling artifacts",
+        "MetricConstraint": "NO_GROUP_EVENTS",
+        "MetricExpr": "(100 * (1 - tma_core_bound / tma_ports_utilization if tma_core_bound < tma_ports_utilization else 1) if tma_info_system_smt_2t_utilization > 0.5 else 0)",
+        "MetricGroup": "Cor;SMT",
+        "MetricName": "tma_info_botlnk_l0_core_bound_likely",
+        "MetricThreshold": "tma_info_botlnk_l0_core_bound_likely > 0.5",
+        "Unit": "cpu_core"
+    },
+    {
+        "BriefDescription": "Total pipeline cost of DSB (uop cache) misses - subset of the Instruction_Fetch_BW Bottleneck",
+        "MetricConstraint": "NO_GROUP_EVENTS",
+        "MetricExpr": "100 * (tma_fetch_latency * tma_dsb_switches / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) + tma_fetch_bandwidth * tma_mite / (tma_dsb + tma_lsd + tma_mite))",
+        "MetricGroup": "DSBmiss;Fed;tma_issueFB",
+        "MetricName": "tma_info_botlnk_l2_dsb_misses",
+        "MetricThreshold": "tma_info_botlnk_l2_dsb_misses > 10",
+        "PublicDescription": "Total pipeline cost of DSB (uop cache) misses - subset of the Instruction_Fetch_BW Bottleneck. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp",
+        "Unit": "cpu_core"
+    },
+    {
+        "BriefDescription": "Total pipeline cost of Instruction Cache misses - subset of the Big_Code Bottleneck",
+        "MetricExpr": "100 * (tma_fetch_latency * tma_icache_misses / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches))",
+        "MetricGroup": "Fed;FetchLat;IcMiss;tma_issueFL",
+        "MetricName": "tma_info_botlnk_l2_ic_misses",
+        "MetricThreshold": "tma_info_botlnk_l2_ic_misses > 5",
+        "PublicDescription": "Total pipeline cost of Instruction Cache misses - subset of the Big_Code Bottleneck. Related metrics: ",
         "Unit": "cpu_core"
     },
     {
@@ -1190,240 +1234,219 @@
         "MetricConstraint": "NO_GROUP_EVENTS",
         "MetricExpr": "100 * tma_fetch_latency * (tma_itlb_misses + tma_icache_misses + tma_unknown_branches) / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches)",
         "MetricGroup": "BigFoot;Fed;Frontend;IcMiss;MemoryTLB;tma_issueBC",
-        "MetricName": "tma_info_big_code",
-        "MetricThreshold": "tma_info_big_code > 20",
-        "PublicDescription": "Total pipeline cost of instruction fetch related bottlenecks by large code footprint programs (i-side cache; TLB and BTB misses). Related metrics: tma_info_branching_overhead",
+        "MetricName": "tma_info_bottleneck_big_code",
+        "MetricThreshold": "tma_info_bottleneck_big_code > 20",
+        "PublicDescription": "Total pipeline cost of instruction fetch related bottlenecks by large code footprint programs (i-side cache; TLB and BTB misses). Related metrics: tma_info_bottleneck_branching_overhead",
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "Branch instructions per taken branch.",
-        "MetricExpr": "BR_INST_RETIRED.ALL_BRANCHES / BR_INST_RETIRED.NEAR_TAKEN",
-        "MetricGroup": "Branches;Fed;PGO",
-        "MetricName": "tma_info_bptkbranch",
+        "BriefDescription": "Total pipeline cost of branch related instructions (used for program control-flow including function calls)",
+        "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_thread_slots)",
+        "MetricGroup": "Ret;tma_issueBC",
+        "MetricName": "tma_info_bottleneck_branching_overhead",
+        "MetricThreshold": "tma_info_bottleneck_branching_overhead > 10",
+        "PublicDescription": "Total pipeline cost of branch related instructions (used for program control-flow including function calls). Related metrics: tma_info_bottleneck_big_code",
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "Branch Misprediction Cost: Fraction of TMA slots wasted per non-speculative branch misprediction (retired JEClear)",
+        "BriefDescription": "Total pipeline cost of instruction fetch bandwidth related bottlenecks",
         "MetricConstraint": "NO_GROUP_EVENTS",
-        "MetricExpr": "(tma_branch_mispredicts + tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches)) * tma_info_slots / BR_MISP_RETIRED.ALL_BRANCHES",
-        "MetricGroup": "Bad;BrMispredicts;tma_issueBM",
-        "MetricName": "tma_info_branch_misprediction_cost",
-        "PublicDescription": "Branch Misprediction Cost: Fraction of TMA slots wasted per non-speculative branch misprediction (retired JEClear). Related metrics: tma_branch_mispredicts, tma_info_mispredictions, tma_mispredicts_resteers",
+        "MetricExpr": "100 * (tma_frontend_bound - tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches)) - tma_info_bottleneck_big_code",
+        "MetricGroup": "Fed;FetchBW;Frontend",
+        "MetricName": "tma_info_bottleneck_instruction_fetch_bw",
+        "MetricThreshold": "tma_info_bottleneck_instruction_fetch_bw > 20",
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "Total pipeline cost of branch related instructions (used for program control-flow including function calls)",
-        "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",
-        "PublicDescription": "Total pipeline cost of branch related instructions (used for program control-flow including function calls). Related metrics: tma_info_big_code",
+        "BriefDescription": "Total pipeline cost of (external) Memory Bandwidth related bottlenecks",
+        "MetricExpr": "100 * tma_memory_bound * (tma_dram_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_mem_bandwidth / (tma_mem_bandwidth + tma_mem_latency)) + tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_sq_full / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full))) + tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_fb_full / (tma_dtlb_load + tma_fb_full + tma_lock_latency + tma_split_loads + tma_store_fwd_blk))",
+        "MetricGroup": "Mem;MemoryBW;Offcore;tma_issueBW",
+        "MetricName": "tma_info_bottleneck_memory_bandwidth",
+        "MetricThreshold": "tma_info_bottleneck_memory_bandwidth > 20",
+        "PublicDescription": "Total pipeline cost of (external) Memory Bandwidth related bottlenecks. Related metrics: tma_fb_full, tma_info_system_dram_bw_use, tma_mem_bandwidth, tma_sq_full",
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "Fraction of branches that are CALL or RET",
-        "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",
+        "BriefDescription": "Total pipeline cost of Memory Address Translation related bottlenecks (data-side TLBs)",
+        "MetricConstraint": "NO_GROUP_EVENTS",
+        "MetricExpr": "100 * tma_memory_bound * (tma_l1_bound / max(tma_memory_bound, tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_dtlb_load / max(tma_l1_bound, tma_dtlb_load + tma_fb_full + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_dtlb_store / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency + tma_streaming_stores)))",
+        "MetricGroup": "Mem;MemoryTLB;Offcore;tma_issueTLB",
+        "MetricName": "tma_info_bottleneck_memory_data_tlbs",
+        "MetricThreshold": "tma_info_bottleneck_memory_data_tlbs > 20",
+        "PublicDescription": "Total pipeline cost of Memory Address Translation related bottlenecks (data-side TLBs). Related metrics: tma_dtlb_load, tma_dtlb_store",
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "Per-Logical Processor actual clocks when the Logical Processor is active.",
-        "MetricExpr": "cpu_core@CPU_CLK_UNHALTED.THREAD@",
-        "MetricGroup": "Pipeline",
-        "MetricName": "tma_info_clks",
+        "BriefDescription": "Total pipeline cost of Memory Latency related bottlenecks (external memory and off-core caches)",
+        "MetricConstraint": "NO_GROUP_EVENTS",
+        "MetricExpr": "100 * tma_memory_bound * (tma_dram_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_mem_latency / (tma_mem_bandwidth + tma_mem_latency)) + tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_l3_hit_latency / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_l2_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound))",
+        "MetricGroup": "Mem;MemoryLat;Offcore;tma_issueLat",
+        "MetricName": "tma_info_bottleneck_memory_latency",
+        "MetricThreshold": "tma_info_bottleneck_memory_latency > 20",
+        "PublicDescription": "Total pipeline cost of Memory Latency related bottlenecks (external memory and off-core caches). Related metrics: tma_l3_hit_latency, tma_mem_latency",
         "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 * cpu_core@ITLB_MISSES.WALK_COMPLETED@ / INST_RETIRED.ANY",
-        "MetricGroup": "Fed;MemoryTLB",
-        "MetricName": "tma_info_code_stlb_mpki",
+        "BriefDescription": "Total pipeline cost of Branch Misprediction related bottlenecks",
+        "MetricConstraint": "NO_GROUP_EVENTS",
+        "MetricExpr": "100 * (tma_branch_mispredicts + tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches))",
+        "MetricGroup": "Bad;BadSpec;BrMispredicts;tma_issueBM",
+        "MetricName": "tma_info_bottleneck_mispredictions",
+        "MetricThreshold": "tma_info_bottleneck_mispredictions > 20",
+        "PublicDescription": "Total pipeline cost of Branch Misprediction related bottlenecks. Related metrics: tma_branch_mispredicts, tma_info_bad_spec_branch_misprediction_cost, tma_mispredicts_resteers",
+        "Unit": "cpu_core"
+    },
+    {
+        "BriefDescription": "Fraction of branches that are CALL or RET",
+        "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_branches_callret",
         "Unit": "cpu_core"
     },
     {
         "BriefDescription": "Fraction of branches that are non-taken conditionals",
         "MetricExpr": "BR_INST_RETIRED.COND_NTAKEN / BR_INST_RETIRED.ALL_BRANCHES",
         "MetricGroup": "Bad;Branches;CodeGen;PGO",
-        "MetricName": "tma_info_cond_nt",
+        "MetricName": "tma_info_branches_cond_nt",
         "Unit": "cpu_core"
     },
     {
         "BriefDescription": "Fraction of branches that are taken conditionals",
         "MetricExpr": "BR_INST_RETIRED.COND_TAKEN / BR_INST_RETIRED.ALL_BRANCHES",
         "MetricGroup": "Bad;Branches;CodeGen;PGO",
-        "MetricName": "tma_info_cond_tk",
+        "MetricName": "tma_info_branches_cond_tk",
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "Probability of Core Bound bottleneck hidden by SMT-profiling artifacts",
-        "MetricConstraint": "NO_GROUP_EVENTS",
-        "MetricExpr": "(100 * (1 - tma_core_bound / tma_ports_utilization if tma_core_bound < tma_ports_utilization else 1) if tma_info_smt_2t_utilization > 0.5 else 0)",
-        "MetricGroup": "Cor;SMT",
-        "MetricName": "tma_info_core_bound_likely",
-        "MetricThreshold": "tma_info_core_bound_likely > 0.5",
+        "BriefDescription": "Fraction of branches that are unconditional (direct or indirect) jumps",
+        "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_branches_jump",
+        "Unit": "cpu_core"
+    },
+    {
+        "BriefDescription": "Fraction of branches of other types (not individually covered by other metrics in Info.Branches group)",
+        "MetricExpr": "1 - (tma_info_branches_cond_nt + tma_info_branches_cond_tk + tma_info_branches_callret + tma_info_branches_jump)",
+        "MetricGroup": "Bad;Branches",
+        "MetricName": "tma_info_branches_other_branches",
         "Unit": "cpu_core"
     },
     {
         "BriefDescription": "Core actual clocks when any Logical Processor is active on the Physical Core",
         "MetricExpr": "cpu_core@CPU_CLK_UNHALTED.DISTRIBUTED@",
         "MetricGroup": "SMT",
-        "MetricName": "tma_info_core_clks",
+        "MetricName": "tma_info_core_core_clks",
         "Unit": "cpu_core"
     },
     {
         "BriefDescription": "Instructions Per Cycle across hyper-threads (per physical core)",
-        "MetricExpr": "INST_RETIRED.ANY / tma_info_core_clks",
+        "MetricExpr": "INST_RETIRED.ANY / tma_info_core_core_clks",
         "MetricGroup": "Ret;SMT;TmaL1;tma_L1_group",
-        "MetricName": "tma_info_coreipc",
-        "Unit": "cpu_core"
-    },
-    {
-        "BriefDescription": "Cycles Per Instruction (per Logical Processor)",
-        "MetricExpr": "1 / tma_info_ipc",
-        "MetricGroup": "Mem;Pipeline",
-        "MetricName": "tma_info_cpi",
+        "MetricName": "tma_info_core_coreipc",
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "Average CPU Utilization",
-        "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / TSC",
-        "MetricGroup": "HPC;Summary",
-        "MetricName": "tma_info_cpu_utilization",
+        "BriefDescription": "Floating Point Operations Per Cycle",
+        "MetricConstraint": "NO_GROUP_EVENTS",
+        "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_core_clks",
+        "MetricGroup": "Flops;Ret",
+        "MetricName": "tma_info_core_flopc",
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "Average Parallel L2 cache miss data reads",
-        "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD / OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD",
-        "MetricGroup": "Memory_BW;Offcore",
-        "MetricName": "tma_info_data_l2_mlp",
+        "BriefDescription": "Actual per-core usage of the Floating Point non-X87 execution units (regardless of precision or vector-width)",
+        "MetricConstraint": "NO_GROUP_EVENTS",
+        "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_core_clks)",
+        "MetricGroup": "Cor;Flops;HPC",
+        "MetricName": "tma_info_core_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).",
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]",
-        "MetricExpr": "64 * (UNC_ARB_TRK_REQUESTS.ALL + UNC_ARB_COH_TRK_REQUESTS.ALL) / 1e6 / duration_time / 1e3",
-        "MetricGroup": "HPC;Mem;MemoryBW;SoC;tma_issueBW",
-        "MetricName": "tma_info_dram_bw_use",
-        "PublicDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]. Related metrics: tma_fb_full, tma_info_memory_bandwidth, tma_mem_bandwidth, tma_sq_full",
+        "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is execution) per-core",
+        "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_core_ilp",
         "Unit": "cpu_core"
     },
     {
         "BriefDescription": "Fraction of Uops delivered by the DSB (aka Decoded ICache; or Uop Cache)",
         "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",
-        "PublicDescription": "Fraction of Uops delivered by the DSB (aka Decoded ICache; or Uop Cache). Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_dsb_misses, tma_info_iptb, tma_lcp",
-        "Unit": "cpu_core"
-    },
-    {
-        "BriefDescription": "Total pipeline cost of DSB (uop cache) misses - subset of the Instruction_Fetch_BW Bottleneck",
-        "MetricConstraint": "NO_GROUP_EVENTS",
-        "MetricExpr": "100 * (tma_fetch_latency * tma_dsb_switches / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) + tma_fetch_bandwidth * tma_mite / (tma_dsb + tma_lsd + tma_mite))",
-        "MetricGroup": "DSBmiss;Fed;tma_issueFB",
-        "MetricName": "tma_info_dsb_misses",
-        "MetricThreshold": "tma_info_dsb_misses > 10",
-        "PublicDescription": "Total pipeline cost of DSB (uop cache) misses - subset of the Instruction_Fetch_BW Bottleneck. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_dsb_coverage, tma_info_iptb, tma_lcp",
+        "MetricName": "tma_info_frontend_dsb_coverage",
+        "MetricThreshold": "tma_info_frontend_dsb_coverage < 0.7 & tma_info_thread_ipc / 6 > 0.35",
+        "PublicDescription": "Fraction of Uops delivered by the DSB (aka Decoded ICache; or Uop Cache). Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_inst_mix_iptb, tma_lcp",
         "Unit": "cpu_core"
     },
     {
         "BriefDescription": "Average number of cycles of a switch from the DSB fetch-unit to MITE fetch unit - see DSB_Switches tree node for details.",
         "MetricExpr": "DSB2MITE_SWITCHES.PENALTY_CYCLES / cpu_core@DSB2MITE_SWITCHES.PENALTY_CYCLES\\,cmask\\=1\\,edge@",
         "MetricGroup": "DSBmiss",
-        "MetricName": "tma_info_dsb_switch_cost",
-        "Unit": "cpu_core"
-    },
-    {
-        "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is execution) per-thread",
-        "MetricExpr": "UOPS_EXECUTED.THREAD / cpu_core@UOPS_EXECUTED.THREAD\\,cmask\\=1@",
-        "MetricGroup": "Cor;Pipeline;PortsUtil;SMT",
-        "MetricName": "tma_info_execute",
-        "Unit": "cpu_core"
-    },
-    {
-        "BriefDescription": "The ratio of Executed- by Issued-Uops",
-        "MetricExpr": "UOPS_EXECUTED.THREAD / UOPS_ISSUED.ANY",
-        "MetricGroup": "Cor;Pipeline",
-        "MetricName": "tma_info_execute_per_issue",
-        "PublicDescription": "The ratio of Executed- by Issued-Uops. Ratio > 1 suggests high rate of uop micro-fusions. Ratio < 1 suggest high rate of \"execute\" at rename stage.",
-        "Unit": "cpu_core"
-    },
-    {
-        "BriefDescription": "Fill Buffer (FB) hits per kilo instructions for retired demand loads (L1D misses that merge into ongoing miss-handling entries)",
-        "MetricExpr": "1e3 * cpu_core@MEM_LOAD_RETIRED.FB_HIT@ / INST_RETIRED.ANY",
-        "MetricGroup": "CacheMisses;Mem",
-        "MetricName": "tma_info_fb_hpki",
+        "MetricName": "tma_info_frontend_dsb_switch_cost",
         "Unit": "cpu_core"
     },
     {
         "BriefDescription": "Average number of Uops issued by front-end when it issued something",
         "MetricExpr": "UOPS_ISSUED.ANY / cpu_core@UOPS_ISSUED.ANY\\,cmask\\=1@",
         "MetricGroup": "Fed;FetchBW",
-        "MetricName": "tma_info_fetch_upc",
+        "MetricName": "tma_info_frontend_fetch_upc",
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "Floating Point Operations Per Cycle",
-        "MetricConstraint": "NO_GROUP_EVENTS",
-        "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",
+        "BriefDescription": "Average Latency for L1 instruction cache misses",
+        "MetricExpr": "ICACHE_DATA.STALLS / cpu_core@ICACHE_DATA.STALLS\\,cmask\\=1\\,edge@",
+        "MetricGroup": "Fed;FetchLat;IcMiss",
+        "MetricName": "tma_info_frontend_icache_miss_latency",
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "Actual per-core usage of the Floating Point non-X87 execution units (regardless of precision or vector-width)",
-        "MetricConstraint": "NO_GROUP_EVENTS",
-        "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).",
+        "BriefDescription": "Instructions per non-speculative DSB miss (lower number means higher occurrence rate)",
+        "MetricExpr": "INST_RETIRED.ANY / FRONTEND_RETIRED.ANY_DSB_MISS",
+        "MetricGroup": "DSBmiss;Fed",
+        "MetricName": "tma_info_frontend_ipdsb_miss_ret",
+        "MetricThreshold": "tma_info_frontend_ipdsb_miss_ret < 50",
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "Giga Floating Point Operations Per Second",
-        "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.",
+        "BriefDescription": "Instructions per speculative Unknown Branch Misprediction (BAClear) (lower number means higher occurrence rate)",
+        "MetricExpr": "tma_info_inst_mix_instructions / BACLEARS.ANY",
+        "MetricGroup": "Fed",
+        "MetricName": "tma_info_frontend_ipunknown_branch",
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "Total pipeline cost of Instruction Cache misses - subset of the Big_Code Bottleneck",
-        "MetricExpr": "100 * (tma_fetch_latency * tma_icache_misses / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches))",
-        "MetricGroup": "Fed;FetchLat;IcMiss;tma_issueFL",
-        "MetricName": "tma_info_ic_misses",
-        "MetricThreshold": "tma_info_ic_misses > 5",
-        "PublicDescription": "Total pipeline cost of Instruction Cache misses - subset of the Big_Code Bottleneck. Related metrics: ",
+        "BriefDescription": "L2 cache true code cacheline misses per kilo instruction",
+        "MetricExpr": "1e3 * cpu_core@FRONTEND_RETIRED.L2_MISS@ / INST_RETIRED.ANY",
+        "MetricGroup": "IcMiss",
+        "MetricName": "tma_info_frontend_l2mpki_code",
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "Average Latency for L1 instruction cache misses",
-        "MetricExpr": "ICACHE_DATA.STALLS / cpu_core@ICACHE_DATA.STALLS\\,cmask\\=1\\,edge@",
-        "MetricGroup": "Fed;FetchLat;IcMiss",
-        "MetricName": "tma_info_icache_miss_latency",
+        "BriefDescription": "L2 cache speculative code cacheline misses per kilo instruction",
+        "MetricExpr": "1e3 * cpu_core@L2_RQSTS.CODE_RD_MISS@ / INST_RETIRED.ANY",
+        "MetricGroup": "IcMiss",
+        "MetricName": "tma_info_frontend_l2mpki_code_all",
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is execution) per-core",
-        "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",
+        "BriefDescription": "Fraction of Uops delivered by the LSD (Loop Stream Detector; aka Loop Cache)",
+        "MetricExpr": "LSD.UOPS / cpu_core@UOPS_ISSUED.ANY@",
+        "MetricGroup": "Fed;LSD",
+        "MetricName": "tma_info_frontend_lsd_coverage",
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "Total pipeline cost of instruction fetch bandwidth related bottlenecks",
-        "MetricConstraint": "NO_GROUP_EVENTS",
-        "MetricExpr": "100 * (tma_frontend_bound - tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches)) - tma_info_big_code",
-        "MetricGroup": "Fed;FetchBW;Frontend",
-        "MetricName": "tma_info_instruction_fetch_bw",
-        "MetricThreshold": "tma_info_instruction_fetch_bw > 20",
+        "BriefDescription": "Branch instructions per taken branch.",
+        "MetricExpr": "BR_INST_RETIRED.ALL_BRANCHES / BR_INST_RETIRED.NEAR_TAKEN",
+        "MetricGroup": "Branches;Fed;PGO",
+        "MetricName": "tma_info_inst_mix_bptkbranch",
         "Unit": "cpu_core"
     },
     {
         "BriefDescription": "Total number of retired Instructions",
         "MetricExpr": "cpu_core@INST_RETIRED.ANY@",
         "MetricGroup": "Summary;TmaL1;tma_L1_group",
-        "MetricName": "tma_info_instructions",
+        "MetricName": "tma_info_inst_mix_instructions",
         "PublicDescription": "Total number of retired Instructions. Sample with: INST_RETIRED.PREC_DIST",
         "Unit": "cpu_core"
     },
@@ -1431,8 +1454,8 @@
         "BriefDescription": "Instructions per FP Arithmetic instruction (lower number means higher occurrence rate)",
         "MetricExpr": "INST_RETIRED.ANY / (cpu_core@FP_ARITH_INST_RETIRED.SCALAR_SINGLE\\,umask\\=0x03@ + cpu_core@FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE\\,umask\\=0x3c@)",
         "MetricGroup": "Flops;InsType",
-        "MetricName": "tma_info_iparith",
-        "MetricThreshold": "tma_info_iparith < 10",
+        "MetricName": "tma_info_inst_mix_iparith",
+        "MetricThreshold": "tma_info_inst_mix_iparith < 10",
         "PublicDescription": "Instructions per FP Arithmetic instruction (lower number means higher occurrence rate). May undercount due to FMA double counting. Approximated prior to BDW.",
         "Unit": "cpu_core"
     },
@@ -1440,8 +1463,8 @@
         "BriefDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number means higher occurrence rate)",
         "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",
+        "MetricName": "tma_info_inst_mix_iparith_avx128",
+        "MetricThreshold": "tma_info_inst_mix_iparith_avx128 < 10",
         "PublicDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number means higher occurrence rate). May undercount due to FMA double counting.",
         "Unit": "cpu_core"
     },
@@ -1449,8 +1472,8 @@
         "BriefDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means higher occurrence rate)",
         "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",
+        "MetricName": "tma_info_inst_mix_iparith_avx256",
+        "MetricThreshold": "tma_info_inst_mix_iparith_avx256 < 10",
         "PublicDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means higher occurrence rate). May undercount due to FMA double counting.",
         "Unit": "cpu_core"
     },
@@ -1458,8 +1481,8 @@
         "BriefDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction (lower number means higher occurrence rate)",
         "MetricExpr": "INST_RETIRED.ANY / FP_ARITH_INST_RETIRED.SCALAR_DOUBLE",
         "MetricGroup": "Flops;FpScalar;InsType",
-        "MetricName": "tma_info_iparith_scalar_dp",
-        "MetricThreshold": "tma_info_iparith_scalar_dp < 10",
+        "MetricName": "tma_info_inst_mix_iparith_scalar_dp",
+        "MetricThreshold": "tma_info_inst_mix_iparith_scalar_dp < 10",
         "PublicDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction (lower number means higher occurrence rate). May undercount due to FMA double counting.",
         "Unit": "cpu_core"
     },
@@ -1467,494 +1490,445 @@
         "BriefDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction (lower number means higher occurrence rate)",
         "MetricExpr": "INST_RETIRED.ANY / FP_ARITH_INST_RETIRED.SCALAR_SINGLE",
         "MetricGroup": "Flops;FpScalar;InsType",
-        "MetricName": "tma_info_iparith_scalar_sp",
-        "MetricThreshold": "tma_info_iparith_scalar_sp < 10",
+        "MetricName": "tma_info_inst_mix_iparith_scalar_sp",
+        "MetricThreshold": "tma_info_inst_mix_iparith_scalar_sp < 10",
         "PublicDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction (lower number means higher occurrence rate). May undercount due to FMA double counting.",
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "Instructions per a microcode Assist invocation",
-        "MetricExpr": "INST_RETIRED.ANY / cpu_core@ASSISTS.ANY\\,umask\\=0x1B@",
-        "MetricGroup": "Pipeline;Ret;Retire",
-        "MetricName": "tma_info_ipassist",
-        "MetricThreshold": "tma_info_ipassist < 100e3",
-        "PublicDescription": "Instructions per a microcode Assist invocation. See Assists tree node for details (lower number means higher occurrence rate)",
-        "Unit": "cpu_core"
-    },
-    {
         "BriefDescription": "Instructions per Branch (lower number means higher occurrence rate)",
         "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.ALL_BRANCHES",
         "MetricGroup": "Branches;Fed;InsType",
-        "MetricName": "tma_info_ipbranch",
-        "MetricThreshold": "tma_info_ipbranch < 8",
-        "Unit": "cpu_core"
-    },
-    {
-        "BriefDescription": "Instructions Per Cycle (per Logical Processor)",
-        "MetricExpr": "INST_RETIRED.ANY / tma_info_clks",
-        "MetricGroup": "Ret;Summary",
-        "MetricName": "tma_info_ipc",
+        "MetricName": "tma_info_inst_mix_ipbranch",
+        "MetricThreshold": "tma_info_inst_mix_ipbranch < 8",
         "Unit": "cpu_core"
     },
     {
         "BriefDescription": "Instructions per (near) call (lower number means higher occurrence rate)",
         "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_CALL",
         "MetricGroup": "Branches;Fed;PGO",
-        "MetricName": "tma_info_ipcall",
-        "MetricThreshold": "tma_info_ipcall < 200",
-        "Unit": "cpu_core"
-    },
-    {
-        "BriefDescription": "Instructions per non-speculative DSB miss (lower number means higher occurrence rate)",
-        "MetricExpr": "INST_RETIRED.ANY / FRONTEND_RETIRED.ANY_DSB_MISS",
-        "MetricGroup": "DSBmiss;Fed",
-        "MetricName": "tma_info_ipdsb_miss_ret",
-        "MetricThreshold": "tma_info_ipdsb_miss_ret < 50",
-        "Unit": "cpu_core"
-    },
-    {
-        "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 / cpu_core@BR_INST_RETIRED.FAR_BRANCH@u",
-        "MetricGroup": "Branches;OS",
-        "MetricName": "tma_info_ipfarbranch",
-        "MetricThreshold": "tma_info_ipfarbranch < 1e6",
+        "MetricName": "tma_info_inst_mix_ipcall",
+        "MetricThreshold": "tma_info_inst_mix_ipcall < 200",
         "Unit": "cpu_core"
     },
     {
         "BriefDescription": "Instructions per Floating Point (FP) Operation (lower number means higher occurrence rate)",
         "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",
+        "MetricName": "tma_info_inst_mix_ipflop",
+        "MetricThreshold": "tma_info_inst_mix_ipflop < 10",
         "Unit": "cpu_core"
     },
     {
         "BriefDescription": "Instructions per Load (lower number means higher occurrence rate)",
         "MetricExpr": "INST_RETIRED.ANY / MEM_INST_RETIRED.ALL_LOADS",
         "MetricGroup": "InsType",
-        "MetricName": "tma_info_ipload",
-        "MetricThreshold": "tma_info_ipload < 3",
-        "Unit": "cpu_core"
-    },
-    {
-        "BriefDescription": "Instructions per retired mispredicts for conditional non-taken branches (lower number means higher occurrence rate).",
-        "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.COND_NTAKEN",
-        "MetricGroup": "Bad;BrMispredicts",
-        "MetricName": "tma_info_ipmisp_cond_ntaken",
-        "MetricThreshold": "tma_info_ipmisp_cond_ntaken < 200",
-        "Unit": "cpu_core"
-    },
-    {
-        "BriefDescription": "Instructions per retired mispredicts for conditional taken branches (lower number means higher occurrence rate).",
-        "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.COND_TAKEN",
-        "MetricGroup": "Bad;BrMispredicts",
-        "MetricName": "tma_info_ipmisp_cond_taken",
-        "MetricThreshold": "tma_info_ipmisp_cond_taken < 200",
-        "Unit": "cpu_core"
-    },
-    {
-        "BriefDescription": "Instructions per retired mispredicts for indirect CALL or JMP branches (lower number means higher occurrence rate).",
-        "MetricExpr": "cpu_core@BR_MISP_RETIRED.INDIRECT_CALL\\,umask\\=0x80@ / BR_MISP_RETIRED.INDIRECT",
-        "MetricGroup": "Bad;BrMispredicts",
-        "MetricName": "tma_info_ipmisp_indirect",
-        "MetricThreshold": "tma_info_ipmisp_indirect < 1e3",
-        "Unit": "cpu_core"
-    },
-    {
-        "BriefDescription": "Instructions per retired mispredicts for return branches (lower number means higher occurrence rate).",
-        "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.RET",
-        "MetricGroup": "Bad;BrMispredicts",
-        "MetricName": "tma_info_ipmisp_ret",
-        "MetricThreshold": "tma_info_ipmisp_ret < 500",
-        "Unit": "cpu_core"
-    },
-    {
-        "BriefDescription": "Number of Instructions per non-speculative Branch Misprediction (JEClear) (lower number means higher occurrence rate)",
-        "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.ALL_BRANCHES",
-        "MetricGroup": "Bad;BadSpec;BrMispredicts",
-        "MetricName": "tma_info_ipmispredict",
-        "MetricThreshold": "tma_info_ipmispredict < 200",
+        "MetricName": "tma_info_inst_mix_ipload",
+        "MetricThreshold": "tma_info_inst_mix_ipload < 3",
         "Unit": "cpu_core"
     },
     {
         "BriefDescription": "Instructions per Store (lower number means higher occurrence rate)",
         "MetricExpr": "INST_RETIRED.ANY / MEM_INST_RETIRED.ALL_STORES",
         "MetricGroup": "InsType",
-        "MetricName": "tma_info_ipstore",
-        "MetricThreshold": "tma_info_ipstore < 8",
+        "MetricName": "tma_info_inst_mix_ipstore",
+        "MetricThreshold": "tma_info_inst_mix_ipstore < 8",
         "Unit": "cpu_core"
     },
     {
         "BriefDescription": "Instructions per Software prefetch instruction (of any type: NTA/T0/T1/T2/Prefetch) (lower number means higher occurrence rate)",
         "MetricExpr": "INST_RETIRED.ANY / cpu_core@SW_PREFETCH_ACCESS.T0\\,umask\\=0xF@",
         "MetricGroup": "Prefetches",
-        "MetricName": "tma_info_ipswpf",
-        "MetricThreshold": "tma_info_ipswpf < 100",
+        "MetricName": "tma_info_inst_mix_ipswpf",
+        "MetricThreshold": "tma_info_inst_mix_ipswpf < 100",
         "Unit": "cpu_core"
     },
     {
         "BriefDescription": "Instruction per taken branch",
         "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_TAKEN",
         "MetricGroup": "Branches;Fed;FetchBW;Frontend;PGO;tma_issueFB",
-        "MetricName": "tma_info_iptb",
-        "MetricThreshold": "tma_info_iptb < 13",
-        "PublicDescription": "Instruction per taken branch. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_dsb_coverage, tma_info_dsb_misses, tma_lcp",
-        "Unit": "cpu_core"
-    },
-    {
-        "BriefDescription": "Instructions per speculative Unknown Branch Misprediction (BAClear) (lower number means higher occurrence rate)",
-        "MetricExpr": "tma_info_instructions / BACLEARS.ANY",
-        "MetricGroup": "Fed",
-        "MetricName": "tma_info_ipunknown_branch",
+        "MetricName": "tma_info_inst_mix_iptb",
+        "MetricThreshold": "tma_info_inst_mix_iptb < 13",
+        "PublicDescription": "Instruction per taken branch. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_lcp",
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "Fraction of branches that are unconditional (direct or indirect) jumps",
-        "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",
+        "BriefDescription": "Average per-core data fill bandwidth to the L1 data cache [GB / sec]",
+        "MetricExpr": "64 * cpu_core@L1D.REPLACEMENT@ / 1e9 / duration_time",
+        "MetricGroup": "Mem;MemoryBW",
+        "MetricName": "tma_info_memory_core_l1d_cache_fill_bw",
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "Cycles Per Instruction for the Operating System (OS) Kernel mode",
-        "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P:k / cpu_core@INST_RETIRED.ANY_P@k",
-        "MetricGroup": "OS",
-        "MetricName": "tma_info_kernel_cpi",
+        "BriefDescription": "Average per-core data fill bandwidth to the L2 cache [GB / sec]",
+        "MetricExpr": "64 * cpu_core@L2_LINES_IN.ALL@ / 1e9 / duration_time",
+        "MetricGroup": "Mem;MemoryBW",
+        "MetricName": "tma_info_memory_core_l2_cache_fill_bw",
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "Fraction of cycles spent in the Operating System (OS) Kernel mode",
-        "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P:k / CPU_CLK_UNHALTED.THREAD",
-        "MetricGroup": "OS",
-        "MetricName": "tma_info_kernel_utilization",
-        "MetricThreshold": "tma_info_kernel_utilization > 0.05",
+        "BriefDescription": "Average per-core data access bandwidth to the L3 cache [GB / sec]",
+        "MetricExpr": "64 * cpu_core@OFFCORE_REQUESTS.ALL_REQUESTS@ / 1e9 / duration_time",
+        "MetricGroup": "Mem;MemoryBW;Offcore",
+        "MetricName": "tma_info_memory_core_l3_cache_access_bw",
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "Average per-core data fill bandwidth to the L1 data cache [GB / sec]",
-        "MetricExpr": "64 * cpu_core@L1D.REPLACEMENT@ / 1e9 / duration_time",
+        "BriefDescription": "Average per-core data fill bandwidth to the L3 cache [GB / sec]",
+        "MetricExpr": "64 * cpu_core@LONGEST_LAT_CACHE.MISS@ / 1e9 / duration_time",
         "MetricGroup": "Mem;MemoryBW",
-        "MetricName": "tma_info_l1d_cache_fill_bw",
+        "MetricName": "tma_info_memory_core_l3_cache_fill_bw",
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "Average per-thread data fill bandwidth to the L1 data cache [GB / sec]",
-        "MetricExpr": "tma_info_l1d_cache_fill_bw",
-        "MetricGroup": "Mem;MemoryBW",
-        "MetricName": "tma_info_l1d_cache_fill_bw_1t",
+        "BriefDescription": "Fill Buffer (FB) hits per kilo instructions for retired demand loads (L1D misses that merge into ongoing miss-handling entries)",
+        "MetricExpr": "1e3 * cpu_core@MEM_LOAD_RETIRED.FB_HIT@ / INST_RETIRED.ANY",
+        "MetricGroup": "CacheMisses;Mem",
+        "MetricName": "tma_info_memory_fb_hpki",
         "Unit": "cpu_core"
     },
     {
         "BriefDescription": "L1 cache true misses per kilo instruction for retired demand loads",
         "MetricExpr": "1e3 * cpu_core@MEM_LOAD_RETIRED.L1_MISS@ / INST_RETIRED.ANY",
         "MetricGroup": "CacheMisses;Mem",
-        "MetricName": "tma_info_l1mpki",
+        "MetricName": "tma_info_memory_l1mpki",
         "Unit": "cpu_core"
     },
     {
         "BriefDescription": "L1 cache true misses per kilo instruction for all demand loads (including speculative)",
         "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 * cpu_core@L2_LINES_IN.ALL@ / 1e9 / duration_time",
-        "MetricGroup": "Mem;MemoryBW",
-        "MetricName": "tma_info_l2_cache_fill_bw",
-        "Unit": "cpu_core"
-    },
-    {
-        "BriefDescription": "Average per-thread data fill bandwidth to the L2 cache [GB / sec]",
-        "MetricExpr": "tma_info_l2_cache_fill_bw",
-        "MetricGroup": "Mem;MemoryBW",
-        "MetricName": "tma_info_l2_cache_fill_bw_1t",
+        "MetricName": "tma_info_memory_l1mpki_load",
         "Unit": "cpu_core"
     },
     {
         "BriefDescription": "L2 cache hits per kilo instruction for all request types (including speculative)",
         "MetricExpr": "1e3 * (cpu_core@L2_RQSTS.REFERENCES@ - cpu_core@L2_RQSTS.MISS@) / INST_RETIRED.ANY",
         "MetricGroup": "CacheMisses;Mem",
-        "MetricName": "tma_info_l2hpki_all",
+        "MetricName": "tma_info_memory_l2hpki_all",
         "Unit": "cpu_core"
     },
     {
         "BriefDescription": "L2 cache hits per kilo instruction for all demand loads  (including speculative)",
         "MetricExpr": "1e3 * cpu_core@L2_RQSTS.DEMAND_DATA_RD_HIT@ / INST_RETIRED.ANY",
         "MetricGroup": "CacheMisses;Mem",
-        "MetricName": "tma_info_l2hpki_load",
+        "MetricName": "tma_info_memory_l2hpki_load",
         "Unit": "cpu_core"
     },
     {
         "BriefDescription": "L2 cache true misses per kilo instruction for retired demand loads",
         "MetricExpr": "1e3 * cpu_core@MEM_LOAD_RETIRED.L2_MISS@ / INST_RETIRED.ANY",
         "MetricGroup": "Backend;CacheMisses;Mem",
-        "MetricName": "tma_info_l2mpki",
+        "MetricName": "tma_info_memory_l2mpki",
         "Unit": "cpu_core"
     },
     {
         "BriefDescription": "L2 cache ([RKL+] true) misses per kilo instruction for all request types (including speculative)",
         "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 * 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 * cpu_core@L2_RQSTS.CODE_RD_MISS@ / INST_RETIRED.ANY",
-        "MetricGroup": "IcMiss",
-        "MetricName": "tma_info_l2mpki_code_all",
+        "MetricName": "tma_info_memory_l2mpki_all",
         "Unit": "cpu_core"
     },
     {
         "BriefDescription": "L2 cache ([RKL+] true) misses per kilo instruction for all demand loads  (including speculative)",
         "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 * cpu_core@OFFCORE_REQUESTS.ALL_REQUESTS@ / 1e9 / duration_time",
-        "MetricGroup": "Mem;MemoryBW;Offcore",
-        "MetricName": "tma_info_l3_cache_access_bw",
+        "MetricName": "tma_info_memory_l2mpki_load",
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "Average per-thread data access bandwidth to the L3 cache [GB / sec]",
-        "MetricExpr": "tma_info_l3_cache_access_bw",
-        "MetricGroup": "Mem;MemoryBW;Offcore",
-        "MetricName": "tma_info_l3_cache_access_bw_1t",
+        "BriefDescription": "L3 cache true misses per kilo instruction for retired demand loads",
+        "MetricExpr": "1e3 * cpu_core@MEM_LOAD_RETIRED.L3_MISS@ / INST_RETIRED.ANY",
+        "MetricGroup": "CacheMisses;Mem",
+        "MetricName": "tma_info_memory_l3mpki",
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "Average per-core data fill bandwidth to the L3 cache [GB / sec]",
-        "MetricExpr": "64 * cpu_core@LONGEST_LAT_CACHE.MISS@ / 1e9 / duration_time",
-        "MetricGroup": "Mem;MemoryBW",
-        "MetricName": "tma_info_l3_cache_fill_bw",
+        "BriefDescription": "Actual Average Latency for L1 data-cache miss demand load operations (in core cycles)",
+        "MetricExpr": "L1D_PEND_MISS.PENDING / MEM_LOAD_COMPLETED.L1_MISS_ANY",
+        "MetricGroup": "Mem;MemoryBound;MemoryLat",
+        "MetricName": "tma_info_memory_load_miss_real_latency",
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "Average per-thread data fill bandwidth to the L3 cache [GB / sec]",
-        "MetricExpr": "tma_info_l3_cache_fill_bw",
-        "MetricGroup": "Mem;MemoryBW",
-        "MetricName": "tma_info_l3_cache_fill_bw_1t",
+        "BriefDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least one such miss",
+        "MetricExpr": "L1D_PEND_MISS.PENDING / L1D_PEND_MISS.PENDING_CYCLES",
+        "MetricGroup": "Mem;MemoryBW;MemoryBound",
+        "MetricName": "tma_info_memory_mlp",
+        "PublicDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least one such miss. Per-Logical Processor)",
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "L3 cache true misses per kilo instruction for retired demand loads",
-        "MetricExpr": "1e3 * cpu_core@MEM_LOAD_RETIRED.L3_MISS@ / INST_RETIRED.ANY",
-        "MetricGroup": "CacheMisses;Mem",
-        "MetricName": "tma_info_l3mpki",
+        "BriefDescription": "Average Parallel L2 cache miss data reads",
+        "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD / OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD",
+        "MetricGroup": "Memory_BW;Offcore",
+        "MetricName": "tma_info_memory_oro_data_l2_mlp",
         "Unit": "cpu_core"
     },
     {
         "BriefDescription": "Average Latency for L2 cache miss demand Loads",
         "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD / OFFCORE_REQUESTS.DEMAND_DATA_RD",
         "MetricGroup": "Memory_Lat;Offcore",
-        "MetricName": "tma_info_load_l2_miss_latency",
+        "MetricName": "tma_info_memory_oro_load_l2_miss_latency",
         "Unit": "cpu_core"
     },
     {
         "BriefDescription": "Average Parallel L2 cache miss demand Loads",
         "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD / cpu_core@OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD\\,cmask\\=1@",
         "MetricGroup": "Memory_BW;Offcore",
-        "MetricName": "tma_info_load_l2_mlp",
+        "MetricName": "tma_info_memory_oro_load_l2_mlp",
         "Unit": "cpu_core"
     },
     {
         "BriefDescription": "Average Latency for L3 cache miss demand Loads",
         "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.L3_MISS_DEMAND_DATA_RD / OFFCORE_REQUESTS.L3_MISS_DEMAND_DATA_RD",
         "MetricGroup": "Memory_Lat;Offcore",
-        "MetricName": "tma_info_load_l3_miss_latency",
+        "MetricName": "tma_info_memory_oro_load_l3_miss_latency",
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "Actual Average Latency for L1 data-cache miss demand load operations (in core cycles)",
-        "MetricExpr": "L1D_PEND_MISS.PENDING / MEM_LOAD_COMPLETED.L1_MISS_ANY",
-        "MetricGroup": "Mem;MemoryBound;MemoryLat",
-        "MetricName": "tma_info_load_miss_real_latency",
+        "BriefDescription": "Average per-thread data fill bandwidth to the L1 data cache [GB / sec]",
+        "MetricExpr": "tma_info_memory_core_l1d_cache_fill_bw",
+        "MetricGroup": "Mem;MemoryBW",
+        "MetricName": "tma_info_memory_thread_l1d_cache_fill_bw_1t",
+        "Unit": "cpu_core"
+    },
+    {
+        "BriefDescription": "Average per-thread data fill bandwidth to the L2 cache [GB / sec]",
+        "MetricExpr": "tma_info_memory_core_l2_cache_fill_bw",
+        "MetricGroup": "Mem;MemoryBW",
+        "MetricName": "tma_info_memory_thread_l2_cache_fill_bw_1t",
+        "Unit": "cpu_core"
+    },
+    {
+        "BriefDescription": "Average per-thread data access bandwidth to the L3 cache [GB / sec]",
+        "MetricExpr": "tma_info_memory_core_l3_cache_access_bw",
+        "MetricGroup": "Mem;MemoryBW;Offcore",
+        "MetricName": "tma_info_memory_thread_l3_cache_access_bw_1t",
+        "Unit": "cpu_core"
+    },
+    {
+        "BriefDescription": "Average per-thread data fill bandwidth to the L3 cache [GB / sec]",
+        "MetricExpr": "tma_info_memory_core_l3_cache_fill_bw",
+        "MetricGroup": "Mem;MemoryBW",
+        "MetricName": "tma_info_memory_thread_l3_cache_fill_bw_1t",
+        "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 * cpu_core@ITLB_MISSES.WALK_COMPLETED@ / INST_RETIRED.ANY",
+        "MetricGroup": "Fed;MemoryTLB",
+        "MetricName": "tma_info_memory_tlb_code_stlb_mpki",
         "Unit": "cpu_core"
     },
     {
         "BriefDescription": "STLB (2nd level TLB) data load speculative misses per kilo instruction (misses of any page-size that complete the page walk)",
         "MetricExpr": "1e3 * cpu_core@DTLB_LOAD_MISSES.WALK_COMPLETED@ / INST_RETIRED.ANY",
         "MetricGroup": "Mem;MemoryTLB",
-        "MetricName": "tma_info_load_stlb_mpki",
+        "MetricName": "tma_info_memory_tlb_load_stlb_mpki",
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "Fraction of Uops delivered by the LSD (Loop Stream Detector; aka Loop Cache)",
-        "MetricExpr": "LSD.UOPS / cpu_core@UOPS_ISSUED.ANY@",
-        "MetricGroup": "Fed;LSD",
-        "MetricName": "tma_info_lsd_coverage",
+        "BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses",
+        "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_core_clks)",
+        "MetricGroup": "Mem;MemoryTLB",
+        "MetricName": "tma_info_memory_tlb_page_walks_utilization",
+        "MetricThreshold": "tma_info_memory_tlb_page_walks_utilization > 0.5",
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "Average number of parallel data read requests to external memory",
-        "MetricExpr": "UNC_ARB_DAT_OCCUPANCY.RD / cpu_core@UNC_ARB_DAT_OCCUPANCY.RD\\,cmask\\=1@",
-        "MetricGroup": "Mem;MemoryBW;SoC",
-        "MetricName": "tma_info_mem_parallel_reads",
-        "PublicDescription": "Average number of parallel data read requests to external memory. Accounts for demand loads and L1/L2 prefetches",
+        "BriefDescription": "STLB (2nd level TLB) data store speculative misses per kilo instruction (misses of any page-size that complete the page walk)",
+        "MetricExpr": "1e3 * cpu_core@DTLB_STORE_MISSES.WALK_COMPLETED@ / INST_RETIRED.ANY",
+        "MetricGroup": "Mem;MemoryTLB",
+        "MetricName": "tma_info_memory_tlb_store_stlb_mpki",
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "Average latency of data read request to external memory (in nanoseconds)",
-        "MetricExpr": "(UNC_ARB_TRK_OCCUPANCY.RD + UNC_ARB_DAT_OCCUPANCY.RD) / UNC_ARB_TRK_REQUESTS.RD",
-        "MetricGroup": "Mem;MemoryLat;SoC",
-        "MetricName": "tma_info_mem_read_latency",
-        "PublicDescription": "Average latency of data read request to external memory (in nanoseconds). Accounts for demand loads and L1/L2 prefetches. ([RKL+]memory-controller only)",
+        "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is execution) per-thread",
+        "MetricExpr": "UOPS_EXECUTED.THREAD / cpu_core@UOPS_EXECUTED.THREAD\\,cmask\\=1@",
+        "MetricGroup": "Cor;Pipeline;PortsUtil;SMT",
+        "MetricName": "tma_info_pipeline_execute",
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "Average latency of all requests to external memory (in Uncore cycles)",
-        "MetricExpr": "(UNC_ARB_TRK_OCCUPANCY.ALL + UNC_ARB_DAT_OCCUPANCY.RD) / UNC_ARB_TRK_REQUESTS.ALL",
-        "MetricGroup": "Mem;SoC",
-        "MetricName": "tma_info_mem_request_latency",
+        "BriefDescription": "Instructions per a microcode Assist invocation",
+        "MetricExpr": "INST_RETIRED.ANY / cpu_core@ASSISTS.ANY\\,umask\\=0x1B@",
+        "MetricGroup": "Pipeline;Ret;Retire",
+        "MetricName": "tma_info_pipeline_ipassist",
+        "MetricThreshold": "tma_info_pipeline_ipassist < 100e3",
+        "PublicDescription": "Instructions per a microcode Assist invocation. See Assists tree node for details (lower number means higher occurrence rate)",
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "Total pipeline cost of (external) Memory Bandwidth related bottlenecks",
-        "MetricExpr": "100 * tma_memory_bound * (tma_dram_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_mem_bandwidth / (tma_mem_bandwidth + tma_mem_latency)) + tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_sq_full / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full))) + tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_fb_full / (tma_dtlb_load + tma_fb_full + tma_lock_latency + tma_split_loads + tma_store_fwd_blk))",
-        "MetricGroup": "Mem;MemoryBW;Offcore;tma_issueBW",
-        "MetricName": "tma_info_memory_bandwidth",
-        "MetricThreshold": "tma_info_memory_bandwidth > 20",
-        "PublicDescription": "Total pipeline cost of (external) Memory Bandwidth related bottlenecks. Related metrics: tma_fb_full, tma_info_dram_bw_use, tma_mem_bandwidth, tma_sq_full",
+        "BriefDescription": "Average number of Uops retired in cycles where at least one uop has retired.",
+        "MetricConstraint": "NO_GROUP_EVENTS",
+        "MetricExpr": "tma_retiring * tma_info_thread_slots / cpu_core@UOPS_RETIRED.SLOTS\\,cmask\\=1@",
+        "MetricGroup": "Pipeline;Ret",
+        "MetricName": "tma_info_pipeline_retire",
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "Total pipeline cost of Memory Address Translation related bottlenecks (data-side TLBs)",
-        "MetricConstraint": "NO_GROUP_EVENTS",
-        "MetricExpr": "100 * tma_memory_bound * (tma_l1_bound / max(tma_memory_bound, tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_dtlb_load / max(tma_l1_bound, tma_dtlb_load + tma_fb_full + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_dtlb_store / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency + tma_streaming_stores)))",
-        "MetricGroup": "Mem;MemoryTLB;Offcore;tma_issueTLB",
-        "MetricName": "tma_info_memory_data_tlbs",
-        "MetricThreshold": "tma_info_memory_data_tlbs > 20",
-        "PublicDescription": "Total pipeline cost of Memory Address Translation related bottlenecks (data-side TLBs). Related metrics: tma_dtlb_load, tma_dtlb_store",
+        "BriefDescription": "Estimated fraction of retirement-cycles dealing with repeat instructions",
+        "MetricExpr": "INST_RETIRED.REP_ITERATION / cpu_core@UOPS_RETIRED.SLOTS\\,cmask\\=1@",
+        "MetricGroup": "Pipeline;Ret",
+        "MetricName": "tma_info_pipeline_strings_cycles",
+        "MetricThreshold": "tma_info_pipeline_strings_cycles > 0.1",
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "Total pipeline cost of Memory Latency related bottlenecks (external memory and off-core caches)",
-        "MetricConstraint": "NO_GROUP_EVENTS",
-        "MetricExpr": "100 * tma_memory_bound * (tma_dram_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_mem_latency / (tma_mem_bandwidth + tma_mem_latency)) + tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_l3_hit_latency / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_l2_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound))",
-        "MetricGroup": "Mem;MemoryLat;Offcore;tma_issueLat",
-        "MetricName": "tma_info_memory_latency",
-        "MetricThreshold": "tma_info_memory_latency > 20",
-        "PublicDescription": "Total pipeline cost of Memory Latency related bottlenecks (external memory and off-core caches). Related metrics: tma_l3_hit_latency, tma_mem_latency",
+        "BriefDescription": "Measured Average Frequency for unhalted processors [GHz]",
+        "MetricExpr": "tma_info_system_turbo_utilization * TSC / 1e9 / duration_time",
+        "MetricGroup": "Power;Summary",
+        "MetricName": "tma_info_system_average_frequency",
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "Total pipeline cost of Branch Misprediction related bottlenecks",
-        "MetricConstraint": "NO_GROUP_EVENTS",
-        "MetricExpr": "100 * (tma_branch_mispredicts + tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches))",
-        "MetricGroup": "Bad;BadSpec;BrMispredicts;tma_issueBM",
-        "MetricName": "tma_info_mispredictions",
-        "MetricThreshold": "tma_info_mispredictions > 20",
-        "PublicDescription": "Total pipeline cost of Branch Misprediction related bottlenecks. Related metrics: tma_branch_mispredicts, tma_info_branch_misprediction_cost, tma_mispredicts_resteers",
+        "BriefDescription": "Average CPU Utilization",
+        "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / TSC",
+        "MetricGroup": "HPC;Summary",
+        "MetricName": "tma_info_system_cpu_utilization",
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least one such miss",
-        "MetricExpr": "L1D_PEND_MISS.PENDING / L1D_PEND_MISS.PENDING_CYCLES",
-        "MetricGroup": "Mem;MemoryBW;MemoryBound",
-        "MetricName": "tma_info_mlp",
-        "PublicDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least one such miss. Per-Logical Processor)",
+        "BriefDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]",
+        "MetricExpr": "64 * (UNC_ARB_TRK_REQUESTS.ALL + UNC_ARB_COH_TRK_REQUESTS.ALL) / 1e6 / duration_time / 1e3",
+        "MetricGroup": "HPC;Mem;MemoryBW;SoC;tma_issueBW",
+        "MetricName": "tma_info_system_dram_bw_use",
+        "PublicDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]. Related metrics: tma_fb_full, tma_info_bottleneck_memory_bandwidth, tma_mem_bandwidth, tma_sq_full",
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "Fraction of branches of other types (not individually covered by other metrics in Info.Branches group)",
-        "MetricExpr": "1 - (tma_info_cond_nt + tma_info_cond_tk + tma_info_callret + tma_info_jump)",
-        "MetricGroup": "Bad;Branches",
-        "MetricName": "tma_info_other_branches",
+        "BriefDescription": "Giga Floating Point Operations Per Second",
+        "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_system_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.",
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses",
-        "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",
+        "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 / cpu_core@BR_INST_RETIRED.FAR_BRANCH@u",
+        "MetricGroup": "Branches;OS",
+        "MetricName": "tma_info_system_ipfarbranch",
+        "MetricThreshold": "tma_info_system_ipfarbranch < 1e6",
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "Average number of Uops retired in cycles where at least one uop has retired.",
-        "MetricConstraint": "NO_GROUP_EVENTS",
-        "MetricExpr": "tma_retiring * tma_info_slots / cpu_core@UOPS_RETIRED.SLOTS\\,cmask\\=1@",
-        "MetricGroup": "Pipeline;Ret",
-        "MetricName": "tma_info_retire",
+        "BriefDescription": "Cycles Per Instruction for the Operating System (OS) Kernel mode",
+        "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P:k / cpu_core@INST_RETIRED.ANY_P@k",
+        "MetricGroup": "OS",
+        "MetricName": "tma_info_system_kernel_cpi",
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "Total issue-pipeline slots (per-Physical Core till ICL; per-Logical Processor ICL onward)",
-        "MetricExpr": "cpu_core@TOPDOWN.SLOTS@",
-        "MetricGroup": "TmaL1;tma_L1_group",
-        "MetricName": "tma_info_slots",
+        "BriefDescription": "Fraction of cycles spent in the Operating System (OS) Kernel mode",
+        "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P:k / CPU_CLK_UNHALTED.THREAD",
+        "MetricGroup": "OS",
+        "MetricName": "tma_info_system_kernel_utilization",
+        "MetricThreshold": "tma_info_system_kernel_utilization > 0.05",
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "Fraction of Physical Core issue-slots utilized by this Logical Processor",
-        "MetricExpr": "(tma_info_slots / (cpu_core@TOPDOWN.SLOTS@ / 2) if #SMT_on else 1)",
-        "MetricGroup": "SMT;TmaL1;tma_L1_group",
-        "MetricName": "tma_info_slots_utilization",
+        "BriefDescription": "Average number of parallel data read requests to external memory",
+        "MetricExpr": "UNC_ARB_DAT_OCCUPANCY.RD / cpu_core@UNC_ARB_DAT_OCCUPANCY.RD\\,cmask\\=1@",
+        "MetricGroup": "Mem;MemoryBW;SoC",
+        "MetricName": "tma_info_system_mem_parallel_reads",
+        "PublicDescription": "Average number of parallel data read requests to external memory. Accounts for demand loads and L1/L2 prefetches",
+        "Unit": "cpu_core"
+    },
+    {
+        "BriefDescription": "Average latency of data read request to external memory (in nanoseconds)",
+        "MetricExpr": "(UNC_ARB_TRK_OCCUPANCY.RD + UNC_ARB_DAT_OCCUPANCY.RD) / UNC_ARB_TRK_REQUESTS.RD",
+        "MetricGroup": "Mem;MemoryLat;SoC",
+        "MetricName": "tma_info_system_mem_read_latency",
+        "PublicDescription": "Average latency of data read request to external memory (in nanoseconds). Accounts for demand loads and L1/L2 prefetches. ([RKL+]memory-controller only)",
+        "Unit": "cpu_core"
+    },
+    {
+        "BriefDescription": "Average latency of all requests to external memory (in Uncore cycles)",
+        "MetricExpr": "(UNC_ARB_TRK_OCCUPANCY.ALL + UNC_ARB_DAT_OCCUPANCY.RD) / UNC_ARB_TRK_REQUESTS.ALL",
+        "MetricGroup": "Mem;SoC",
+        "MetricName": "tma_info_system_mem_request_latency",
         "Unit": "cpu_core"
     },
     {
         "BriefDescription": "Fraction of cycles where both hardware Logical Processors were active",
         "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",
+        "MetricName": "tma_info_system_smt_2t_utilization",
         "Unit": "cpu_core"
     },
     {
         "BriefDescription": "Socket actual clocks when any core is active on that socket",
         "MetricExpr": "UNC_CLOCK.SOCKET",
         "MetricGroup": "SoC",
-        "MetricName": "tma_info_socket_clks",
+        "MetricName": "tma_info_system_socket_clks",
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "STLB (2nd level TLB) data store speculative misses per kilo instruction (misses of any page-size that complete the page walk)",
-        "MetricExpr": "1e3 * cpu_core@DTLB_STORE_MISSES.WALK_COMPLETED@ / INST_RETIRED.ANY",
-        "MetricGroup": "Mem;MemoryTLB",
-        "MetricName": "tma_info_store_stlb_mpki",
+        "BriefDescription": "Average Frequency Utilization relative nominal frequency",
+        "MetricExpr": "tma_info_thread_clks / CPU_CLK_UNHALTED.REF_TSC",
+        "MetricGroup": "Power",
+        "MetricName": "tma_info_system_turbo_utilization",
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "Estimated fraction of retirement-cycles dealing with repeat instructions",
-        "MetricExpr": "INST_RETIRED.REP_ITERATION / cpu_core@UOPS_RETIRED.SLOTS\\,cmask\\=1@",
-        "MetricGroup": "Pipeline;Ret",
-        "MetricName": "tma_info_strings_cycles",
-        "MetricThreshold": "tma_info_strings_cycles > 0.1",
+        "BriefDescription": "Per-Logical Processor actual clocks when the Logical Processor is active.",
+        "MetricExpr": "cpu_core@CPU_CLK_UNHALTED.THREAD@",
+        "MetricGroup": "Pipeline",
+        "MetricName": "tma_info_thread_clks",
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "Average Frequency Utilization relative nominal frequency",
-        "MetricExpr": "tma_info_clks / CPU_CLK_UNHALTED.REF_TSC",
-        "MetricGroup": "Power",
-        "MetricName": "tma_info_turbo_utilization",
+        "BriefDescription": "Cycles Per Instruction (per Logical Processor)",
+        "MetricExpr": "1 / tma_info_thread_ipc",
+        "MetricGroup": "Mem;Pipeline",
+        "MetricName": "tma_info_thread_cpi",
+        "Unit": "cpu_core"
+    },
+    {
+        "BriefDescription": "The ratio of Executed- by Issued-Uops",
+        "MetricExpr": "UOPS_EXECUTED.THREAD / UOPS_ISSUED.ANY",
+        "MetricGroup": "Cor;Pipeline",
+        "MetricName": "tma_info_thread_execute_per_issue",
+        "PublicDescription": "The ratio of Executed- by Issued-Uops. Ratio > 1 suggests high rate of uop micro-fusions. Ratio < 1 suggest high rate of \"execute\" at rename stage.",
+        "Unit": "cpu_core"
+    },
+    {
+        "BriefDescription": "Instructions Per Cycle (per Logical Processor)",
+        "MetricExpr": "INST_RETIRED.ANY / tma_info_thread_clks",
+        "MetricGroup": "Ret;Summary",
+        "MetricName": "tma_info_thread_ipc",
+        "Unit": "cpu_core"
+    },
+    {
+        "BriefDescription": "Total issue-pipeline slots (per-Physical Core till ICL; per-Logical Processor ICL onward)",
+        "MetricExpr": "cpu_core@TOPDOWN.SLOTS@",
+        "MetricGroup": "TmaL1;tma_L1_group",
+        "MetricName": "tma_info_thread_slots",
+        "Unit": "cpu_core"
+    },
+    {
+        "BriefDescription": "Fraction of Physical Core issue-slots utilized by this Logical Processor",
+        "MetricExpr": "(tma_info_thread_slots / (cpu_core@TOPDOWN.SLOTS@ / 2) if #SMT_on else 1)",
+        "MetricGroup": "SMT;TmaL1;tma_L1_group",
+        "MetricName": "tma_info_thread_slots_utilization",
         "Unit": "cpu_core"
     },
     {
         "BriefDescription": "Uops Per Instruction",
-        "MetricExpr": "tma_retiring * tma_info_slots / INST_RETIRED.ANY",
+        "MetricExpr": "tma_retiring * tma_info_thread_slots / INST_RETIRED.ANY",
         "MetricGroup": "Pipeline;Ret;Retire",
-        "MetricName": "tma_info_uoppi",
-        "MetricThreshold": "tma_info_uoppi > 1.05",
+        "MetricName": "tma_info_thread_uoppi",
+        "MetricThreshold": "tma_info_thread_uoppi > 1.05",
         "Unit": "cpu_core"
     },
     {
         "BriefDescription": "Instruction per taken branch",
-        "MetricExpr": "tma_retiring * tma_info_slots / BR_INST_RETIRED.NEAR_TAKEN",
+        "MetricExpr": "tma_retiring * tma_info_thread_slots / BR_INST_RETIRED.NEAR_TAKEN",
         "MetricGroup": "Branches;Fed;FetchBW",
-        "MetricName": "tma_info_uptb",
-        "MetricThreshold": "tma_info_uptb < 9",
+        "MetricName": "tma_info_thread_uptb",
+        "MetricThreshold": "tma_info_thread_uptb < 9",
         "Unit": "cpu_core"
     },
     {
@@ -1969,7 +1943,7 @@
     },
     {
         "BriefDescription": "This metric represents 128-bit vector Integer ADD/SUB/SAD or VNNI (Vector Neural Network Instructions) uops fraction the CPU has retired",
-        "MetricExpr": "(cpu_core@INT_VEC_RETIRED.ADD_128@ + cpu_core@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_thread_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 +1953,7 @@
     },
     {
         "BriefDescription": "This metric represents 256-bit vector Integer ADD/SUB/SAD or VNNI (Vector Neural Network Instructions) uops fraction the CPU has retired",
-        "MetricExpr": "(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)",
+        "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_thread_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)",
@@ -1989,7 +1963,7 @@
     },
     {
         "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to Instruction TLB (ITLB) misses",
-        "MetricExpr": "ICACHE_TAG.STALLS / tma_info_clks",
+        "MetricExpr": "ICACHE_TAG.STALLS / tma_info_thread_clks",
         "MetricGroup": "BigFoot;FetchLat;MemoryTLB;TopdownL3;tma_L3_group;tma_fetch_latency_group",
         "MetricName": "tma_itlb_misses",
         "MetricThreshold": "tma_itlb_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)",
@@ -1999,7 +1973,7 @@
     },
     {
         "BriefDescription": "This metric estimates how often the CPU was stalled without loads missing the L1 data cache",
-        "MetricExpr": "max((cpu_core@EXE_ACTIVITY.BOUND_ON_LOADS@ - cpu_core@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_thread_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 +1984,7 @@
     {
         "BriefDescription": "This metric estimates how often the CPU was stalled due to L2 cache accesses by loads",
         "MetricConstraint": "NO_GROUP_EVENTS",
-        "MetricExpr": "(cpu_core@MEMORY_ACTIVITY.STALLS_L1D_MISS@ - cpu_core@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_thread_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 +1994,7 @@
     },
     {
         "BriefDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core",
-        "MetricExpr": "(cpu_core@MEMORY_ACTIVITY.STALLS_L2_MISS@ - cpu_core@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_thread_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)",
@@ -2030,21 +2004,21 @@
     },
     {
         "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 * 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",
+        "MetricExpr": "9 * tma_info_system_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_thread_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))",
-        "PublicDescription": "This metric represents fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited).  Avoiding private cache misses (i.e. L2 misses/L3 hits) will improve the latency; reduce contention with sibling physical cores and increase performance.  Note the value of this node may overlap with its siblings. Sample with: MEM_LOAD_RETIRED.L3_HIT_PS. Related metrics: tma_info_memory_latency, tma_mem_latency",
+        "PublicDescription": "This metric represents fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited).  Avoiding private cache misses (i.e. L2 misses/L3 hits) will improve the latency; reduce contention with sibling physical cores and increase performance.  Note the value of this node may overlap with its siblings. Sample with: MEM_LOAD_RETIRED.L3_HIT_PS. Related metrics: tma_info_bottleneck_memory_latency, tma_mem_latency",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
         "BriefDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs)",
-        "MetricExpr": "DECODE.LCP / tma_info_clks",
+        "MetricExpr": "DECODE.LCP / tma_info_thread_clks",
         "MetricGroup": "FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueFB",
         "MetricName": "tma_lcp",
         "MetricThreshold": "tma_lcp > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)",
-        "PublicDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs). Using proper compiler flags or Intel Compiler by default will certainly avoid this. #Link: Optimization Guide about LCP BKMs. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_dsb_coverage, tma_info_dsb_misses, tma_info_iptb",
+        "PublicDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs). Using proper compiler flags or Intel Compiler by default will certainly avoid this. #Link: Optimization Guide about LCP BKMs. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -2061,7 +2035,7 @@
     },
     {
         "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port for Load operations",
-        "MetricExpr": "UOPS_DISPATCHED.PORT_2_3_10 / (3 * tma_info_core_clks)",
+        "MetricExpr": "UOPS_DISPATCHED.PORT_2_3_10 / (3 * tma_info_core_core_clks)",
         "MetricGroup": "TopdownL5;tma_L5_group;tma_ports_utilized_3m_group",
         "MetricName": "tma_load_op_utilization",
         "MetricThreshold": "tma_load_op_utilization > 0.6",
@@ -2080,7 +2054,7 @@
     },
     {
         "BriefDescription": "This metric estimates the fraction of cycles where the Second-level TLB (STLB) was missed by load accesses, performing a hardware page walk",
-        "MetricExpr": "DTLB_LOAD_MISSES.WALK_ACTIVE / tma_info_clks",
+        "MetricExpr": "DTLB_LOAD_MISSES.WALK_ACTIVE / tma_info_thread_clks",
         "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_load_group",
         "MetricName": "tma_load_stlb_miss",
         "MetricThreshold": "tma_load_stlb_miss > 0.05 & (tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))",
@@ -2090,7 +2064,7 @@
     {
         "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, 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",
+        "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_thread_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))",
@@ -2100,10 +2074,10 @@
     },
     {
         "BriefDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to LSD (Loop Stream Detector) unit",
-        "MetricExpr": "(cpu_core@LSD.CYCLES_ACTIVE@ - cpu_core@LSD.CYCLES_OK@) / tma_info_core_clks / 2",
+        "MetricExpr": "(cpu_core@LSD.CYCLES_ACTIVE@ - cpu_core@LSD.CYCLES_OK@) / tma_info_core_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)",
+        "MetricThreshold": "tma_lsd > 0.15 & (tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_thread_ipc / 6 > 0.35)",
         "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to LSD (Loop Stream Detector) unit.  LSD typically does well sustaining Uop supply. However; in some rare cases; optimal uop-delivery could not be reached for small loops whose size (in terms of number of uops) does not suit well the LSD structure.",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
@@ -2121,27 +2095,27 @@
     },
     {
         "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_core@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_thread_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))",
-        "PublicDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory (DRAM).  The underlying heuristic assumes that a similar off-core traffic is generated by all IA cores. This metric does not aggregate non-data-read requests by this logical processor; requests from other IA Logical Processors/Physical Cores/sockets; or other non-IA devices like GPU; hence the maximum external memory bandwidth limits may or may not be approached when this metric is flagged (see Uncore counters for that). Related metrics: tma_fb_full, tma_info_dram_bw_use, tma_info_memory_bandwidth, tma_sq_full",
+        "PublicDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory (DRAM).  The underlying heuristic assumes that a similar off-core traffic is generated by all IA cores. This metric does not aggregate non-data-read requests by this logical processor; requests from other IA Logical Processors/Physical Cores/sockets; or other non-IA devices like GPU; hence the maximum external memory bandwidth limits may or may not be approached when this metric is flagged (see Uncore counters for that). Related metrics: tma_fb_full, tma_info_bottleneck_memory_bandwidth, tma_info_system_dram_bw_use, tma_sq_full",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
         "BriefDescription": "This metric estimates fraction of cycles where the performance was likely hurt due to latency from external memory (DRAM)",
-        "MetricExpr": "min(cpu_core@CPU_CLK_UNHALTED.THREAD@, cpu_core@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_thread_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))",
-        "PublicDescription": "This metric estimates fraction of cycles where the performance was likely hurt due to latency from external memory (DRAM).  This metric does not aggregate requests from other Logical Processors/Physical Cores/sockets (see Uncore counters for that). Related metrics: tma_info_memory_latency, tma_l3_hit_latency",
+        "PublicDescription": "This metric estimates fraction of cycles where the performance was likely hurt due to latency from external memory (DRAM).  This metric does not aggregate requests from other Logical Processors/Physical Cores/sockets (see Uncore counters for that). Related metrics: tma_info_bottleneck_memory_latency, tma_l3_hit_latency",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
         "BriefDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck",
-        "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",
+        "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_thread_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 +2126,7 @@
     },
     {
         "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to LFENCE Instructions.",
-        "MetricExpr": "13 * cpu_core@MISC2_RETIRED.LFENCE@ / tma_info_clks",
+        "MetricExpr": "13 * cpu_core@MISC2_RETIRED.LFENCE@ / tma_info_thread_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 +2136,7 @@
     {
         "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 * cpu_core@MEM_UOP_RETIRED.ANY@ / (tma_retiring * tma_info_slots)",
+        "MetricExpr": "tma_light_operations * cpu_core@MEM_UOP_RETIRED.ANY@ / (tma_retiring * tma_info_thread_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",
@@ -2171,7 +2145,7 @@
     },
     {
         "BriefDescription": "This metric represents fraction of slots the CPU was retiring uops fetched by the Microcode Sequencer (MS) unit",
-        "MetricExpr": "UOPS_RETIRED.MS / tma_info_slots",
+        "MetricExpr": "UOPS_RETIRED.MS / tma_info_thread_slots",
         "MetricGroup": "MicroSeq;TopdownL3;tma_L3_group;tma_heavy_operations_group;tma_issueMC;tma_issueMS",
         "MetricName": "tma_microcode_sequencer",
         "MetricThreshold": "tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1",
@@ -2181,27 +2155,27 @@
     },
     {
         "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 * cpu_core@INT_MISC.CLEAR_RESTEER_CYCLES@ / tma_info_clks",
+        "MetricExpr": "tma_branch_mispredicts / tma_bad_speculation * cpu_core@INT_MISC.CLEAR_RESTEER_CYCLES@ / tma_info_thread_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))",
-        "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Branch Misprediction at execution stage. Sample with: INT_MISC.CLEAR_RESTEER_CYCLES. Related metrics: tma_branch_mispredicts, tma_info_branch_misprediction_cost, tma_info_mispredictions",
+        "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Branch Misprediction at execution stage. Sample with: INT_MISC.CLEAR_RESTEER_CYCLES. Related metrics: tma_branch_mispredicts, tma_info_bad_spec_branch_misprediction_cost, tma_info_bottleneck_mispredictions",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
         "BriefDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to the MITE pipeline (the legacy decode pipeline)",
-        "MetricExpr": "(cpu_core@IDQ.MITE_CYCLES_ANY@ - cpu_core@IDQ.MITE_CYCLES_OK@) / tma_info_core_clks / 2",
+        "MetricExpr": "(cpu_core@IDQ.MITE_CYCLES_ANY@ - cpu_core@IDQ.MITE_CYCLES_OK@) / tma_info_core_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)",
+        "MetricThreshold": "tma_mite > 0.1 & (tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_thread_ipc / 6 > 0.35)",
         "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to the MITE pipeline (the legacy decode pipeline). This pipeline is used for code that was not pre-cached in the DSB or LSD. For example; inefficiencies due to asymmetric decoders; use of long immediate or LCP can manifest as MITE fetch bandwidth bottleneck. Sample with: FRONTEND_RETIRED.ANY_DSB_MISS",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
         "BriefDescription": "The Mixing_Vectors metric gives the percentage of injected blend uops out of all uops issued",
-        "MetricExpr": "160 * cpu_core@ASSISTS.SSE_AVX_MIX@ / tma_info_clks",
+        "MetricExpr": "160 * cpu_core@ASSISTS.SSE_AVX_MIX@ / tma_info_thread_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 +2185,7 @@
     },
     {
         "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 / cpu_core@UOPS_ISSUED.ANY@) / tma_info_clks",
+        "MetricExpr": "3 * cpu_core@UOPS_RETIRED.MS\\,cmask\\=1\\,edge@ / (tma_retiring * tma_info_thread_slots / cpu_core@UOPS_ISSUED.ANY@) / tma_info_thread_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 +2195,7 @@
     },
     {
         "BriefDescription": "This metric represents fraction of slots where the CPU was retiring branch instructions that were not fused",
-        "MetricExpr": "tma_light_operations * (cpu_core@BR_INST_RETIRED.ALL_BRANCHES@ - cpu_core@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_thread_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 +2205,7 @@
     },
     {
         "BriefDescription": "This metric represents fraction of slots where the CPU was retiring NOP (no op) instructions",
-        "MetricExpr": "tma_light_operations * cpu_core@INST_RETIRED.NOP@ / (tma_retiring * tma_info_slots)",
+        "MetricExpr": "tma_light_operations * cpu_core@INST_RETIRED.NOP@ / (tma_retiring * tma_info_thread_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 +2226,7 @@
     },
     {
         "BriefDescription": "This metric roughly estimates fraction of slots the CPU retired uops as a result of handing Page Faults",
-        "MetricExpr": "99 * cpu_core@ASSISTS.PAGE_FAULT@ / tma_info_slots",
+        "MetricExpr": "99 * cpu_core@ASSISTS.PAGE_FAULT@ / tma_info_thread_slots",
         "MetricGroup": "TopdownL5;tma_L5_group;tma_assists_group",
         "MetricName": "tma_page_faults",
         "MetricThreshold": "tma_page_faults > 0.05",
@@ -2262,7 +2236,7 @@
     },
     {
         "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 0 ([SNB+] ALU; [HSW+] ALU and 2nd branch)",
-        "MetricExpr": "UOPS_DISPATCHED.PORT_0 / tma_info_core_clks",
+        "MetricExpr": "UOPS_DISPATCHED.PORT_0 / tma_info_core_core_clks",
         "MetricGroup": "Compute;TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P",
         "MetricName": "tma_port_0",
         "MetricThreshold": "tma_port_0 > 0.6",
@@ -2272,7 +2246,7 @@
     },
     {
         "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 1 (ALU)",
-        "MetricExpr": "UOPS_DISPATCHED.PORT_1 / tma_info_core_clks",
+        "MetricExpr": "UOPS_DISPATCHED.PORT_1 / tma_info_core_core_clks",
         "MetricGroup": "TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P",
         "MetricName": "tma_port_1",
         "MetricThreshold": "tma_port_1 > 0.6",
@@ -2282,7 +2256,7 @@
     },
     {
         "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 6 ([HSW+]Primary Branch and simple ALU)",
-        "MetricExpr": "UOPS_DISPATCHED.PORT_6 / tma_info_core_clks",
+        "MetricExpr": "UOPS_DISPATCHED.PORT_6 / tma_info_core_core_clks",
         "MetricGroup": "TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P",
         "MetricName": "tma_port_6",
         "MetricThreshold": "tma_port_6 > 0.6",
@@ -2292,7 +2266,7 @@
     },
     {
         "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 * (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 cpu_core@ARITH.DIV_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)",
+        "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_thread_clks if cpu_core@ARITH.DIV_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_thread_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 +2276,7 @@
     },
     {
         "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 * (cpu_core@CYCLE_ACTIVITY.STALLS_TOTAL@ - cpu_core@EXE_ACTIVITY.BOUND_ON_LOADS@) / tma_info_clks",
+        "MetricExpr": "cpu_core@EXE_ACTIVITY.3_PORTS_UTIL\\,umask\\=0x80@ / tma_info_thread_clks + tma_serializing_operation * (cpu_core@CYCLE_ACTIVITY.STALLS_TOTAL@ - cpu_core@EXE_ACTIVITY.BOUND_ON_LOADS@) / tma_info_thread_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))",
@@ -2312,7 +2286,7 @@
     },
     {
         "BriefDescription": "This metric represents fraction of cycles where the CPU executed total of 1 uop per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise)",
-        "MetricExpr": "EXE_ACTIVITY.1_PORTS_UTIL / tma_info_clks",
+        "MetricExpr": "EXE_ACTIVITY.1_PORTS_UTIL / tma_info_thread_clks",
         "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_issueL1;tma_ports_utilization_group",
         "MetricName": "tma_ports_utilized_1",
         "MetricThreshold": "tma_ports_utilized_1 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))",
@@ -2322,7 +2296,7 @@
     },
     {
         "BriefDescription": "This metric represents fraction of cycles CPU executed total of 2 uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise)",
-        "MetricExpr": "EXE_ACTIVITY.2_PORTS_UTIL / tma_info_clks",
+        "MetricExpr": "EXE_ACTIVITY.2_PORTS_UTIL / tma_info_thread_clks",
         "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_issue2P;tma_ports_utilization_group",
         "MetricName": "tma_ports_utilized_2",
         "MetricThreshold": "tma_ports_utilized_2 > 0.15 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))",
@@ -2332,7 +2306,7 @@
     },
     {
         "BriefDescription": "This metric represents fraction of cycles CPU executed total of 3 or more uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise)",
-        "MetricExpr": "UOPS_EXECUTED.CYCLES_GE_3 / tma_info_clks",
+        "MetricExpr": "UOPS_EXECUTED.CYCLES_GE_3 / tma_info_thread_clks",
         "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group",
         "MetricName": "tma_ports_utilized_3m",
         "MetricThreshold": "tma_ports_utilized_3m > 0.7 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))",
@@ -2342,7 +2316,7 @@
     },
     {
         "BriefDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired",
-        "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",
+        "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_thread_slots",
         "MetricGroup": "TmaL1;TopdownL1;tma_L1_group",
         "MetricName": "tma_retiring",
         "MetricThreshold": "tma_retiring > 0.7 | tma_heavy_operations > 0.1",
@@ -2353,7 +2327,7 @@
     },
     {
         "BriefDescription": "This metric represents fraction of cycles the CPU issue-pipeline was stalled due to serializing operations",
-        "MetricExpr": "RESOURCE_STALLS.SCOREBOARD / tma_info_clks",
+        "MetricExpr": "RESOURCE_STALLS.SCOREBOARD / tma_info_thread_clks",
         "MetricGroup": "PortsUtil;TopdownL5;tma_L5_group;tma_issueSO;tma_ports_utilized_0_group",
         "MetricName": "tma_serializing_operation",
         "MetricThreshold": "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)))",
@@ -2363,7 +2337,7 @@
     },
     {
         "BriefDescription": "This metric represents Shuffle (cross \"vector lane\" data transfers) uops fraction the CPU has retired.",
-        "MetricExpr": "INT_VEC_RETIRED.SHUFFLES / (tma_retiring * tma_info_slots)",
+        "MetricExpr": "INT_VEC_RETIRED.SHUFFLES / (tma_retiring * tma_info_thread_slots)",
         "MetricGroup": "HPC;Pipeline;TopdownL4;tma_L4_group;tma_int_operations_group",
         "MetricName": "tma_shuffles",
         "MetricThreshold": "tma_shuffles > 0.1 & (tma_int_operations > 0.1 & tma_light_operations > 0.6)",
@@ -2372,7 +2346,7 @@
     },
     {
         "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to PAUSE Instructions",
-        "MetricExpr": "CPU_CLK_UNHALTED.PAUSE / tma_info_clks",
+        "MetricExpr": "CPU_CLK_UNHALTED.PAUSE / tma_info_thread_clks",
         "MetricGroup": "TopdownL6;tma_L6_group;tma_serializing_operation_group",
         "MetricName": "tma_slow_pause",
         "MetricThreshold": "tma_slow_pause > 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))))",
@@ -2382,7 +2356,7 @@
     },
     {
         "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 * cpu_core@LD_BLOCKS.NO_SR@ / tma_info_clks",
+        "MetricExpr": "tma_info_memory_load_miss_real_latency * cpu_core@LD_BLOCKS.NO_SR@ / tma_info_thread_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))",
@@ -2392,7 +2366,7 @@
     },
     {
         "BriefDescription": "This metric represents rate of split store accesses",
-        "MetricExpr": "MEM_INST_RETIRED.SPLIT_STORES / tma_info_core_clks",
+        "MetricExpr": "MEM_INST_RETIRED.SPLIT_STORES / tma_info_core_core_clks",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_issueSpSt;tma_store_bound_group",
         "MetricName": "tma_split_stores",
         "MetricThreshold": "tma_split_stores > 0.2 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
@@ -2402,17 +2376,17 @@
     },
     {
         "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": "(cpu_core@XQ.FULL_CYCLES@ + cpu_core@L1D_PEND_MISS.L2_STALLS@) / tma_info_clks",
+        "MetricExpr": "(cpu_core@XQ.FULL_CYCLES@ + cpu_core@L1D_PEND_MISS.L2_STALLS@) / tma_info_thread_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))",
-        "PublicDescription": "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). Related metrics: tma_fb_full, tma_info_dram_bw_use, tma_info_memory_bandwidth, tma_mem_bandwidth",
+        "PublicDescription": "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). Related metrics: tma_fb_full, tma_info_bottleneck_memory_bandwidth, tma_info_system_dram_bw_use, tma_mem_bandwidth",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
         "BriefDescription": "This metric estimates how often CPU was stalled  due to RFO store memory accesses; RFO store issue a read-for-ownership request before the write",
-        "MetricExpr": "EXE_ACTIVITY.BOUND_ON_STORES / tma_info_clks",
+        "MetricExpr": "EXE_ACTIVITY.BOUND_ON_STORES / tma_info_thread_clks",
         "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group",
         "MetricName": "tma_store_bound",
         "MetricThreshold": "tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)",
@@ -2422,7 +2396,7 @@
     },
     {
         "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 * cpu_core@LD_BLOCKS.STORE_FORWARD@ / tma_info_clks",
+        "MetricExpr": "13 * cpu_core@LD_BLOCKS.STORE_FORWARD@ / tma_info_thread_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 +2406,7 @@
     },
     {
         "BriefDescription": "This metric estimates fraction of cycles the CPU spent handling L1D store misses",
-        "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",
+        "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_thread_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 +2416,7 @@
     },
     {
         "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port for Store operations",
-        "MetricExpr": "(cpu_core@UOPS_DISPATCHED.PORT_4_9@ + cpu_core@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_core_clks)",
         "MetricGroup": "TopdownL5;tma_L5_group;tma_ports_utilized_3m_group",
         "MetricName": "tma_store_op_utilization",
         "MetricThreshold": "tma_store_op_utilization > 0.6",
@@ -2461,7 +2435,7 @@
     },
     {
         "BriefDescription": "This metric estimates the fraction of cycles where the STLB was missed by store accesses, performing a hardware page walk",
-        "MetricExpr": "DTLB_STORE_MISSES.WALK_ACTIVE / tma_info_core_clks",
+        "MetricExpr": "DTLB_STORE_MISSES.WALK_ACTIVE / tma_info_core_core_clks",
         "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_store_group",
         "MetricName": "tma_store_stlb_miss",
         "MetricThreshold": "tma_store_stlb_miss > 0.05 & (tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))",
@@ -2470,7 +2444,7 @@
     },
     {
         "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 * cpu_core@OCR.STREAMING_WR.ANY_RESPONSE@ / tma_info_clks",
+        "MetricExpr": "9 * cpu_core@OCR.STREAMING_WR.ANY_RESPONSE@ / tma_info_thread_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))",
@@ -2480,7 +2454,7 @@
     },
     {
         "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to new branch address clears",
-        "MetricExpr": "INT_MISC.UNKNOWN_BRANCH_CYCLES / tma_info_clks",
+        "MetricExpr": "INT_MISC.UNKNOWN_BRANCH_CYCLES / tma_info_thread_clks",
         "MetricGroup": "BigFoot;FetchLat;TopdownL4;tma_L4_group;tma_branch_resteers_group",
         "MetricName": "tma_unknown_branches",
         "MetricThreshold": "tma_unknown_branches > 0.05 & (tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))",
diff --git a/tools/perf/pmu-events/arch/x86/alderlake/cache.json b/tools/perf/pmu-events/arch/x86/alderlake/cache.json
index 51770416bcc2..b3d7f8fb50df 100644
--- a/tools/perf/pmu-events/arch/x86/alderlake/cache.json
+++ b/tools/perf/pmu-events/arch/x86/alderlake/cache.json
@@ -1018,6 +1018,15 @@
         "Unit": "cpu_core"
     },
     {
+        "BriefDescription": "Counts bus locks, accounts for cache line split locks and UC locks.",
+        "EventCode": "0x2c",
+        "EventName": "SQ_MISC.BUS_LOCK",
+        "PublicDescription": "Counts the more expensive bus lock needed to enforce cache coherency for certain memory accesses that need to be done atomically.  Can be created by issuing an atomic instruction (via the LOCK prefix) which causes a cache line split or accesses uncacheable memory.",
+        "SampleAfterValue": "100003",
+        "UMask": "0x10",
+        "Unit": "cpu_core"
+    },
+    {
         "BriefDescription": "Number of PREFETCHNTA instructions executed.",
         "EventCode": "0x40",
         "EventName": "SW_PREFETCH_ACCESS.NTA",
diff --git a/tools/perf/pmu-events/arch/x86/alderlake/memory.json b/tools/perf/pmu-events/arch/x86/alderlake/memory.json
index 55827b276e6e..73d92d5c9f9d 100644
--- a/tools/perf/pmu-events/arch/x86/alderlake/memory.json
+++ b/tools/perf/pmu-events/arch/x86/alderlake/memory.json
@@ -93,19 +93,21 @@
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "MEMORY_ACTIVITY.STALLS_L2_MISS",
+        "BriefDescription": "Execution stalls while L2 cache miss demand cacheable load request is outstanding.",
         "CounterMask": "5",
         "EventCode": "0x47",
         "EventName": "MEMORY_ACTIVITY.STALLS_L2_MISS",
+        "PublicDescription": "Execution stalls while L2 cache miss demand cacheable load request is outstanding (will not count for uncacheable demand requests e.g. bus lock).",
         "SampleAfterValue": "1000003",
         "UMask": "0x5",
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "MEMORY_ACTIVITY.STALLS_L3_MISS",
+        "BriefDescription": "Execution stalls while L3 cache miss demand cacheable load request is outstanding.",
         "CounterMask": "9",
         "EventCode": "0x47",
         "EventName": "MEMORY_ACTIVITY.STALLS_L3_MISS",
+        "PublicDescription": "Execution stalls while L3 cache miss demand cacheable load request is outstanding (will not count for uncacheable demand requests e.g. bus lock).",
         "SampleAfterValue": "1000003",
         "UMask": "0x9",
         "Unit": "cpu_core"
diff --git a/tools/perf/pmu-events/arch/x86/alderlaken/adln-metrics.json b/tools/perf/pmu-events/arch/x86/alderlaken/adln-metrics.json
index f4b3c3883643..ed9ff25a03cf 100644
--- a/tools/perf/pmu-events/arch/x86/alderlaken/adln-metrics.json
+++ b/tools/perf/pmu-events/arch/x86/alderlaken/adln-metrics.json
@@ -86,7 +86,7 @@
     },
     {
         "BriefDescription": "Counts the number of issue slots  that were not consumed by the backend due to certain allocation restrictions.",
-        "MetricExpr": "TOPDOWN_BE_BOUND.ALLOC_RESTRICTIONS / tma_info_slots",
+        "MetricExpr": "TOPDOWN_BE_BOUND.ALLOC_RESTRICTIONS / tma_info_core_slots",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_resource_bound_group",
         "MetricName": "tma_alloc_restriction",
         "MetricThreshold": "tma_alloc_restriction > 0.1",
@@ -94,7 +94,7 @@
     },
     {
         "BriefDescription": "Counts the total number of issue slots  that were not consumed by the backend due to backend stalls",
-        "MetricExpr": "TOPDOWN_BE_BOUND.ALL / tma_info_slots",
+        "MetricExpr": "TOPDOWN_BE_BOUND.ALL / tma_info_core_slots",
         "MetricGroup": "TopdownL1;tma_L1_group",
         "MetricName": "tma_backend_bound",
         "MetricThreshold": "tma_backend_bound > 0.1",
@@ -114,7 +114,7 @@
     },
     {
         "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_core_slots - (TOPDOWN_FE_BOUND.ALL + TOPDOWN_BE_BOUND.ALL + TOPDOWN_RETIRING.ALL)) / tma_info_core_slots",
         "MetricGroup": "TopdownL1;tma_L1_group",
         "MetricName": "tma_bad_speculation",
         "MetricThreshold": "tma_bad_speculation > 0.15",
@@ -124,7 +124,7 @@
     },
     {
         "BriefDescription": "Counts the number of uops that are not from the microsequencer.",
-        "MetricExpr": "(TOPDOWN_RETIRING.ALL - UOPS_RETIRED.MS) / tma_info_slots",
+        "MetricExpr": "(TOPDOWN_RETIRING.ALL - UOPS_RETIRED.MS) / tma_info_core_slots",
         "MetricGroup": "TopdownL2;tma_L2_group;tma_retiring_group",
         "MetricName": "tma_base",
         "MetricThreshold": "tma_base > 0.6",
@@ -133,7 +133,7 @@
     },
     {
         "BriefDescription": "Counts the number of issue slots  that were not delivered by the frontend due to BACLEARS, which occurs when the Branch Target Buffer (BTB) prediction or lack thereof, was corrected by a later branch predictor in the frontend",
-        "MetricExpr": "TOPDOWN_FE_BOUND.BRANCH_DETECT / tma_info_slots",
+        "MetricExpr": "TOPDOWN_FE_BOUND.BRANCH_DETECT / tma_info_core_slots",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_fetch_latency_group",
         "MetricName": "tma_branch_detect",
         "MetricThreshold": "tma_branch_detect > 0.05",
@@ -142,7 +142,7 @@
     },
     {
         "BriefDescription": "Counts the number of issue slots  that were not consumed by the backend due to branch mispredicts.",
-        "MetricExpr": "TOPDOWN_BAD_SPECULATION.MISPREDICT / tma_info_slots",
+        "MetricExpr": "TOPDOWN_BAD_SPECULATION.MISPREDICT / tma_info_core_slots",
         "MetricGroup": "TopdownL2;tma_L2_group;tma_bad_speculation_group",
         "MetricName": "tma_branch_mispredicts",
         "MetricThreshold": "tma_branch_mispredicts > 0.05",
@@ -151,7 +151,7 @@
     },
     {
         "BriefDescription": "Counts the number of issue slots  that were not delivered by the frontend due to BTCLEARS, which occurs when the Branch Target Buffer (BTB) predicts a taken branch.",
-        "MetricExpr": "TOPDOWN_FE_BOUND.BRANCH_RESTEER / tma_info_slots",
+        "MetricExpr": "TOPDOWN_FE_BOUND.BRANCH_RESTEER / tma_info_core_slots",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_fetch_latency_group",
         "MetricName": "tma_branch_resteer",
         "MetricThreshold": "tma_branch_resteer > 0.05",
@@ -159,7 +159,7 @@
     },
     {
         "BriefDescription": "Counts the number of issue slots  that were not delivered by the frontend due to the microcode sequencer (MS).",
-        "MetricExpr": "TOPDOWN_FE_BOUND.CISC / tma_info_slots",
+        "MetricExpr": "TOPDOWN_FE_BOUND.CISC / tma_info_core_slots",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_fetch_bandwidth_group",
         "MetricName": "tma_cisc",
         "MetricThreshold": "tma_cisc > 0.05",
@@ -176,7 +176,7 @@
     },
     {
         "BriefDescription": "Counts the number of issue slots  that were not delivered by the frontend due to decode stalls.",
-        "MetricExpr": "TOPDOWN_FE_BOUND.DECODE / tma_info_slots",
+        "MetricExpr": "TOPDOWN_FE_BOUND.DECODE / tma_info_core_slots",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_fetch_bandwidth_group",
         "MetricName": "tma_decode",
         "MetricThreshold": "tma_decode > 0.05",
@@ -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 - 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",
+        "MetricExpr": "MEM_BOUND_STALLS.LOAD_DRAM_HIT / tma_info_core_clks - max((MEM_BOUND_STALLS.LOAD - LD_HEAD.L1_MISS_AT_RET) / tma_info_core_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",
@@ -201,7 +201,7 @@
     },
     {
         "BriefDescription": "Counts the number of issue slots  that were not consumed by the backend due to a machine clear classified as a fast nuke due to memory ordering, memory disambiguation and memory renaming.",
-        "MetricExpr": "TOPDOWN_BAD_SPECULATION.FASTNUKE / tma_info_slots",
+        "MetricExpr": "TOPDOWN_BAD_SPECULATION.FASTNUKE / tma_info_core_slots",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_machine_clears_group",
         "MetricName": "tma_fast_nuke",
         "MetricThreshold": "tma_fast_nuke > 0.05",
@@ -209,7 +209,7 @@
     },
     {
         "BriefDescription": "Counts the number of issue slots  that were not delivered by the frontend due to frontend bandwidth restrictions due to decode, predecode, cisc, and other limitations.",
-        "MetricExpr": "TOPDOWN_FE_BOUND.FRONTEND_BANDWIDTH / tma_info_slots",
+        "MetricExpr": "TOPDOWN_FE_BOUND.FRONTEND_BANDWIDTH / tma_info_core_slots",
         "MetricGroup": "TopdownL2;tma_L2_group;tma_frontend_bound_group",
         "MetricName": "tma_fetch_bandwidth",
         "MetricThreshold": "tma_fetch_bandwidth > 0.1",
@@ -218,7 +218,7 @@
     },
     {
         "BriefDescription": "Counts the number of issue slots  that were not delivered by the frontend due to frontend bandwidth restrictions due to decode, predecode, cisc, and other limitations.",
-        "MetricExpr": "TOPDOWN_FE_BOUND.FRONTEND_LATENCY / tma_info_slots",
+        "MetricExpr": "TOPDOWN_FE_BOUND.FRONTEND_LATENCY / tma_info_core_slots",
         "MetricGroup": "TopdownL2;tma_L2_group;tma_frontend_bound_group",
         "MetricName": "tma_fetch_latency",
         "MetricThreshold": "tma_fetch_latency > 0.15",
@@ -235,7 +235,7 @@
     },
     {
         "BriefDescription": "Counts the number of floating point divide operations per uop.",
-        "MetricExpr": "UOPS_RETIRED.FPDIV / tma_info_slots",
+        "MetricExpr": "UOPS_RETIRED.FPDIV / tma_info_core_slots",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_base_group",
         "MetricName": "tma_fpdiv_uops",
         "MetricThreshold": "tma_fpdiv_uops > 0.2",
@@ -243,7 +243,7 @@
     },
     {
         "BriefDescription": "Counts the number of issue slots  that were not consumed by the backend due to frontend stalls.",
-        "MetricExpr": "TOPDOWN_FE_BOUND.ALL / tma_info_slots",
+        "MetricExpr": "TOPDOWN_FE_BOUND.ALL / tma_info_core_slots",
         "MetricGroup": "TopdownL1;tma_L1_group",
         "MetricName": "tma_frontend_bound",
         "MetricThreshold": "tma_frontend_bound > 0.2",
@@ -252,218 +252,192 @@
     },
     {
         "BriefDescription": "Counts the number of issue slots  that were not delivered by the frontend due to instruction cache misses.",
-        "MetricExpr": "TOPDOWN_FE_BOUND.ICACHE / tma_info_slots",
+        "MetricExpr": "TOPDOWN_FE_BOUND.ICACHE / tma_info_core_slots",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_fetch_latency_group",
         "MetricName": "tma_icache_misses",
         "MetricThreshold": "tma_icache_misses > 0.05",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "Percentage of total non-speculative loads with a address aliasing block",
-        "MetricExpr": "100 * LD_BLOCKS.4K_ALIAS / MEM_UOPS_RETIRED.ALL_LOADS",
-        "MetricName": "tma_info_address_alias_blocks"
-    },
-    {
-        "BriefDescription": "Ratio of all branches which mispredict",
-        "MetricExpr": "BR_MISP_RETIRED.ALL_BRANCHES / BR_INST_RETIRED.ALL_BRANCHES",
-        "MetricGroup": " ",
-        "MetricName": "tma_info_branch_mispredict_ratio"
-    },
-    {
-        "BriefDescription": "Ratio between Mispredicted branches and unknown branches",
-        "MetricExpr": "BR_MISP_RETIRED.ALL_BRANCHES / BACLEARS.ANY",
-        "MetricGroup": " ",
-        "MetricName": "tma_info_branch_mispredict_to_unknown_branch_ratio"
-    },
-    {
         "BriefDescription": "",
         "MetricExpr": "CPU_CLK_UNHALTED.CORE",
-        "MetricGroup": " ",
-        "MetricName": "tma_info_clks"
+        "MetricName": "tma_info_core_clks"
     },
     {
         "BriefDescription": "",
         "MetricExpr": "CPU_CLK_UNHALTED.CORE_P",
-        "MetricGroup": " ",
-        "MetricName": "tma_info_clks_p"
+        "MetricName": "tma_info_core_clks_p"
     },
     {
         "BriefDescription": "Cycles Per Instruction",
-        "MetricExpr": "tma_info_clks / INST_RETIRED.ANY",
-        "MetricGroup": " ",
-        "MetricName": "tma_info_cpi"
-    },
-    {
-        "BriefDescription": "Average CPU Utilization",
-        "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / TSC",
-        "MetricGroup": " ",
-        "MetricName": "tma_info_cpu_utilization"
-    },
-    {
-        "BriefDescription": "Cycle cost per DRAM hit",
-        "MetricExpr": "MEM_BOUND_STALLS.LOAD_DRAM_HIT / MEM_LOAD_UOPS_RETIRED.DRAM_HIT",
-        "MetricGroup": " ",
-        "MetricName": "tma_info_cycles_per_demand_load_dram_hit"
-    },
-    {
-        "BriefDescription": "Cycle cost per L2 hit",
-        "MetricExpr": "MEM_BOUND_STALLS.LOAD_L2_HIT / MEM_LOAD_UOPS_RETIRED.L2_HIT",
-        "MetricGroup": " ",
-        "MetricName": "tma_info_cycles_per_demand_load_l2_hit"
+        "MetricExpr": "tma_info_core_clks / INST_RETIRED.ANY",
+        "MetricName": "tma_info_core_cpi"
     },
     {
-        "BriefDescription": "Cycle cost per LLC hit",
-        "MetricExpr": "MEM_BOUND_STALLS.LOAD_LLC_HIT / MEM_LOAD_UOPS_RETIRED.L3_HIT",
-        "MetricGroup": " ",
-        "MetricName": "tma_info_cycles_per_demand_load_l3_hit"
+        "BriefDescription": "Instructions Per Cycle",
+        "MetricExpr": "INST_RETIRED.ANY / tma_info_core_clks",
+        "MetricName": "tma_info_core_ipc"
     },
     {
-        "BriefDescription": "Percentage of all uops which are FPDiv uops",
-        "MetricExpr": "100 * UOPS_RETIRED.FPDIV / UOPS_RETIRED.ALL",
-        "MetricGroup": " ",
-        "MetricName": "tma_info_fpdiv_uop_ratio"
+        "BriefDescription": "",
+        "MetricExpr": "5 * tma_info_core_clks",
+        "MetricName": "tma_info_core_slots"
     },
     {
-        "BriefDescription": "Percentage of all uops which are IDiv uops",
-        "MetricExpr": "100 * UOPS_RETIRED.IDIV / UOPS_RETIRED.ALL",
-        "MetricGroup": " ",
-        "MetricName": "tma_info_idiv_uop_ratio"
+        "BriefDescription": "Uops Per Instruction",
+        "MetricExpr": "UOPS_RETIRED.ALL / INST_RETIRED.ANY",
+        "MetricName": "tma_info_core_upi"
     },
     {
         "BriefDescription": "Percent of instruction miss cost that hit in DRAM",
         "MetricExpr": "100 * MEM_BOUND_STALLS.IFETCH_DRAM_HIT / MEM_BOUND_STALLS.IFETCH",
-        "MetricGroup": " ",
-        "MetricName": "tma_info_inst_miss_cost_dramhit_percent"
+        "MetricName": "tma_info_frontend_inst_miss_cost_dramhit_percent"
     },
     {
         "BriefDescription": "Percent of instruction miss cost that hit in the L2",
         "MetricExpr": "100 * MEM_BOUND_STALLS.IFETCH_L2_HIT / MEM_BOUND_STALLS.IFETCH",
-        "MetricGroup": " ",
-        "MetricName": "tma_info_inst_miss_cost_l2hit_percent"
+        "MetricName": "tma_info_frontend_inst_miss_cost_l2hit_percent"
     },
     {
         "BriefDescription": "Percent of instruction miss cost that hit in the L3",
         "MetricExpr": "100 * MEM_BOUND_STALLS.IFETCH_LLC_HIT / MEM_BOUND_STALLS.IFETCH",
-        "MetricGroup": " ",
-        "MetricName": "tma_info_inst_miss_cost_l3hit_percent"
+        "MetricName": "tma_info_frontend_inst_miss_cost_l3hit_percent"
     },
     {
-        "BriefDescription": "Instructions per Branch (lower number means higher occurance rate)",
-        "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.ALL_BRANCHES",
-        "MetricGroup": " ",
-        "MetricName": "tma_info_ipbranch"
+        "BriefDescription": "Ratio of all branches which mispredict",
+        "MetricExpr": "BR_MISP_RETIRED.ALL_BRANCHES / BR_INST_RETIRED.ALL_BRANCHES",
+        "MetricName": "tma_info_inst_mix_branch_mispredict_ratio"
     },
     {
-        "BriefDescription": "Instructions Per Cycle",
-        "MetricExpr": "INST_RETIRED.ANY / tma_info_clks",
-        "MetricGroup": " ",
-        "MetricName": "tma_info_ipc"
+        "BriefDescription": "Ratio between Mispredicted branches and unknown branches",
+        "MetricExpr": "BR_MISP_RETIRED.ALL_BRANCHES / BACLEARS.ANY",
+        "MetricName": "tma_info_inst_mix_branch_mispredict_to_unknown_branch_ratio"
+    },
+    {
+        "BriefDescription": "Percentage of all uops which are FPDiv uops",
+        "MetricExpr": "100 * UOPS_RETIRED.FPDIV / UOPS_RETIRED.ALL",
+        "MetricName": "tma_info_inst_mix_fpdiv_uop_ratio"
+    },
+    {
+        "BriefDescription": "Percentage of all uops which are IDiv uops",
+        "MetricExpr": "100 * UOPS_RETIRED.IDIV / UOPS_RETIRED.ALL",
+        "MetricName": "tma_info_inst_mix_idiv_uop_ratio"
+    },
+    {
+        "BriefDescription": "Instructions per Branch (lower number means higher occurance rate)",
+        "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.ALL_BRANCHES",
+        "MetricName": "tma_info_inst_mix_ipbranch"
     },
     {
         "BriefDescription": "Instruction per (near) call (lower number means higher occurance rate)",
         "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.CALL",
-        "MetricGroup": " ",
-        "MetricName": "tma_info_ipcall"
+        "MetricName": "tma_info_inst_mix_ipcall"
     },
     {
         "BriefDescription": "Instructions per Far Branch",
         "MetricExpr": "INST_RETIRED.ANY / (BR_INST_RETIRED.FAR_BRANCH / 2)",
-        "MetricGroup": " ",
-        "MetricName": "tma_info_ipfarbranch"
+        "MetricName": "tma_info_inst_mix_ipfarbranch"
     },
     {
         "BriefDescription": "Instructions per Load",
         "MetricExpr": "INST_RETIRED.ANY / MEM_UOPS_RETIRED.ALL_LOADS",
-        "MetricGroup": " ",
-        "MetricName": "tma_info_ipload"
+        "MetricName": "tma_info_inst_mix_ipload"
     },
     {
         "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)",
-        "MetricName": "tma_info_ipmisp_cond_ntaken"
+        "MetricName": "tma_info_inst_mix_ipmisp_cond_ntaken"
     },
     {
         "BriefDescription": "Instructions per retired conditional Branch Misprediction where the branch was taken",
         "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.COND_TAKEN",
-        "MetricName": "tma_info_ipmisp_cond_taken"
+        "MetricName": "tma_info_inst_mix_ipmisp_cond_taken"
     },
     {
         "BriefDescription": "Instructions per retired indirect call or jump Branch Misprediction",
         "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.INDIRECT",
-        "MetricName": "tma_info_ipmisp_indirect"
+        "MetricName": "tma_info_inst_mix_ipmisp_indirect"
     },
     {
         "BriefDescription": "Instructions per retired return Branch Misprediction",
         "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.RETURN",
-        "MetricName": "tma_info_ipmisp_ret"
+        "MetricName": "tma_info_inst_mix_ipmisp_ret"
     },
     {
         "BriefDescription": "Instructions per retired Branch Misprediction",
         "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.ALL_BRANCHES",
-        "MetricGroup": " ",
-        "MetricName": "tma_info_ipmispredict"
+        "MetricName": "tma_info_inst_mix_ipmispredict"
     },
     {
         "BriefDescription": "Instructions per Store",
         "MetricExpr": "INST_RETIRED.ANY / MEM_UOPS_RETIRED.ALL_STORES",
-        "MetricGroup": " ",
-        "MetricName": "tma_info_ipstore"
+        "MetricName": "tma_info_inst_mix_ipstore"
     },
     {
-        "BriefDescription": "Fraction of cycles spent in Kernel mode",
-        "MetricExpr": "cpu@CPU_CLK_UNHALTED.CORE@k / CPU_CLK_UNHALTED.CORE",
-        "MetricGroup": " ",
-        "MetricName": "tma_info_kernel_utilization"
+        "BriefDescription": "Percentage of all uops which are ucode ops",
+        "MetricExpr": "100 * UOPS_RETIRED.MS / UOPS_RETIRED.ALL",
+        "MetricName": "tma_info_inst_mix_microcode_uop_ratio"
+    },
+    {
+        "BriefDescription": "Percentage of all uops which are x87 uops",
+        "MetricExpr": "100 * UOPS_RETIRED.X87 / UOPS_RETIRED.ALL",
+        "MetricName": "tma_info_inst_mix_x87_uop_ratio"
+    },
+    {
+        "BriefDescription": "Percentage of total non-speculative loads with a address aliasing block",
+        "MetricExpr": "100 * LD_BLOCKS.4K_ALIAS / MEM_UOPS_RETIRED.ALL_LOADS",
+        "MetricName": "tma_info_l1_bound_address_alias_blocks"
     },
     {
         "BriefDescription": "Percentage of total non-speculative loads that are splits",
         "MetricExpr": "100 * MEM_UOPS_RETIRED.SPLIT_LOADS / MEM_UOPS_RETIRED.ALL_LOADS",
-        "MetricName": "tma_info_load_splits"
+        "MetricName": "tma_info_l1_bound_load_splits"
     },
     {
-        "BriefDescription": "load ops retired per 1000 instruction",
-        "MetricExpr": "1e3 * MEM_UOPS_RETIRED.ALL_LOADS / INST_RETIRED.ANY",
-        "MetricGroup": " ",
-        "MetricName": "tma_info_memloadpki"
+        "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",
+        "MetricName": "tma_info_l1_bound_store_fwd_blocks"
     },
     {
-        "BriefDescription": "Percentage of all uops which are ucode ops",
-        "MetricExpr": "100 * UOPS_RETIRED.MS / UOPS_RETIRED.ALL",
-        "MetricGroup": " ",
-        "MetricName": "tma_info_microcode_uop_ratio"
+        "BriefDescription": "Cycle cost per DRAM hit",
+        "MetricExpr": "MEM_BOUND_STALLS.LOAD_DRAM_HIT / MEM_LOAD_UOPS_RETIRED.DRAM_HIT",
+        "MetricName": "tma_info_memory_cycles_per_demand_load_dram_hit"
     },
     {
-        "BriefDescription": "",
-        "MetricExpr": "5 * tma_info_clks",
-        "MetricGroup": " ",
-        "MetricName": "tma_info_slots"
+        "BriefDescription": "Cycle cost per L2 hit",
+        "MetricExpr": "MEM_BOUND_STALLS.LOAD_L2_HIT / MEM_LOAD_UOPS_RETIRED.L2_HIT",
+        "MetricName": "tma_info_memory_cycles_per_demand_load_l2_hit"
     },
     {
-        "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",
-        "MetricName": "tma_info_store_fwd_blocks"
+        "BriefDescription": "Cycle cost per LLC hit",
+        "MetricExpr": "MEM_BOUND_STALLS.LOAD_LLC_HIT / MEM_LOAD_UOPS_RETIRED.L3_HIT",
+        "MetricName": "tma_info_memory_cycles_per_demand_load_l3_hit"
     },
     {
-        "BriefDescription": "Average Frequency Utilization relative nominal frequency",
-        "MetricExpr": "tma_info_clks / CPU_CLK_UNHALTED.REF_TSC",
-        "MetricGroup": " ",
-        "MetricName": "tma_info_turbo_utilization"
+        "BriefDescription": "load ops retired per 1000 instruction",
+        "MetricExpr": "1e3 * MEM_UOPS_RETIRED.ALL_LOADS / INST_RETIRED.ANY",
+        "MetricName": "tma_info_memory_memloadpki"
     },
     {
-        "BriefDescription": "Uops Per Instruction",
-        "MetricExpr": "UOPS_RETIRED.ALL / INST_RETIRED.ANY",
-        "MetricGroup": " ",
-        "MetricName": "tma_info_upi"
+        "BriefDescription": "Average CPU Utilization",
+        "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / TSC",
+        "MetricName": "tma_info_system_cpu_utilization"
     },
     {
-        "BriefDescription": "Percentage of all uops which are x87 uops",
-        "MetricExpr": "100 * UOPS_RETIRED.X87 / UOPS_RETIRED.ALL",
-        "MetricGroup": " ",
-        "MetricName": "tma_info_x87_uop_ratio"
+        "BriefDescription": "Fraction of cycles spent in Kernel mode",
+        "MetricExpr": "cpu@CPU_CLK_UNHALTED.CORE@k / CPU_CLK_UNHALTED.CORE",
+        "MetricGroup": "Summary",
+        "MetricName": "tma_info_system_kernel_utilization"
+    },
+    {
+        "BriefDescription": "Average Frequency Utilization relative nominal frequency",
+        "MetricExpr": "tma_info_core_clks / CPU_CLK_UNHALTED.REF_TSC",
+        "MetricGroup": "Power",
+        "MetricName": "tma_info_system_turbo_utilization"
     },
     {
         "BriefDescription": "Counts the number of issue slots  that were not delivered by the frontend due to Instruction Table Lookaside Buffer (ITLB) misses.",
-        "MetricExpr": "TOPDOWN_FE_BOUND.ITLB / tma_info_slots",
+        "MetricExpr": "TOPDOWN_FE_BOUND.ITLB / tma_info_core_slots",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_fetch_latency_group",
         "MetricName": "tma_itlb_misses",
         "MetricThreshold": "tma_itlb_misses > 0.05",
@@ -471,7 +445,7 @@
     },
     {
         "BriefDescription": "Counts the number of cycles that the oldest load of the load buffer is stalled at retirement due to a load block.",
-        "MetricExpr": "LD_HEAD.L1_BOUND_AT_RET / tma_info_clks",
+        "MetricExpr": "LD_HEAD.L1_BOUND_AT_RET / tma_info_core_clks",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_memory_bound_group",
         "MetricName": "tma_l1_bound",
         "MetricThreshold": "tma_l1_bound > 0.1",
@@ -480,7 +454,7 @@
     {
         "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 - 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",
+        "MetricExpr": "MEM_BOUND_STALLS.LOAD_L2_HIT / tma_info_core_clks - max((MEM_BOUND_STALLS.LOAD - LD_HEAD.L1_MISS_AT_RET) / tma_info_core_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 +462,7 @@
     },
     {
         "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 - 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",
+        "MetricExpr": "MEM_BOUND_STALLS.LOAD_LLC_HIT / tma_info_core_clks - max((MEM_BOUND_STALLS.LOAD - LD_HEAD.L1_MISS_AT_RET) / tma_info_core_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",
@@ -504,7 +478,7 @@
     },
     {
         "BriefDescription": "Counts the total number of issue slots that were not consumed by the backend because allocation is stalled due to a machine clear (nuke) of any kind including memory ordering and memory disambiguation.",
-        "MetricExpr": "TOPDOWN_BAD_SPECULATION.MACHINE_CLEARS / tma_info_slots",
+        "MetricExpr": "TOPDOWN_BAD_SPECULATION.MACHINE_CLEARS / tma_info_core_slots",
         "MetricGroup": "TopdownL2;tma_L2_group;tma_bad_speculation_group",
         "MetricName": "tma_machine_clears",
         "MetricThreshold": "tma_machine_clears > 0.05",
@@ -513,7 +487,7 @@
     },
     {
         "BriefDescription": "Counts the number of issue slots  that were not consumed by the backend due to memory reservation stalls in which a scheduler is not able to accept uops.",
-        "MetricExpr": "TOPDOWN_BE_BOUND.MEM_SCHEDULER / tma_info_slots",
+        "MetricExpr": "TOPDOWN_BE_BOUND.MEM_SCHEDULER / tma_info_core_slots",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_resource_bound_group",
         "MetricName": "tma_mem_scheduler",
         "MetricThreshold": "tma_mem_scheduler > 0.1",
@@ -521,7 +495,7 @@
     },
     {
         "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(tma_backend_bound, LD_HEAD.ANY_AT_RET / tma_info_core_clks + tma_store_bound)",
         "MetricGroup": "TopdownL2;tma_L2_group;tma_backend_bound_group",
         "MetricName": "tma_memory_bound",
         "MetricThreshold": "tma_memory_bound > 0.2",
@@ -538,7 +512,7 @@
     },
     {
         "BriefDescription": "Counts the number of uops that are from the complex flows issued by the micro-sequencer (MS)",
-        "MetricExpr": "UOPS_RETIRED.MS / tma_info_slots",
+        "MetricExpr": "UOPS_RETIRED.MS / tma_info_core_slots",
         "MetricGroup": "TopdownL2;tma_L2_group;tma_retiring_group",
         "MetricName": "tma_ms_uops",
         "MetricThreshold": "tma_ms_uops > 0.05",
@@ -548,7 +522,7 @@
     },
     {
         "BriefDescription": "Counts the number of issue slots  that were not consumed by the backend due to IEC or FPC RAT stalls, which can be due to FIQ or IEC reservation stalls in which the integer, floating point or SIMD scheduler is not able to accept uops.",
-        "MetricExpr": "TOPDOWN_BE_BOUND.NON_MEM_SCHEDULER / tma_info_slots",
+        "MetricExpr": "TOPDOWN_BE_BOUND.NON_MEM_SCHEDULER / tma_info_core_slots",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_resource_bound_group",
         "MetricName": "tma_non_mem_scheduler",
         "MetricThreshold": "tma_non_mem_scheduler > 0.1",
@@ -556,7 +530,7 @@
     },
     {
         "BriefDescription": "Counts the number of issue slots  that were not consumed by the backend due to a machine clear (slow nuke).",
-        "MetricExpr": "TOPDOWN_BAD_SPECULATION.NUKE / tma_info_slots",
+        "MetricExpr": "TOPDOWN_BAD_SPECULATION.NUKE / tma_info_core_slots",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_machine_clears_group",
         "MetricName": "tma_nuke",
         "MetricThreshold": "tma_nuke > 0.05",
@@ -564,7 +538,7 @@
     },
     {
         "BriefDescription": "Counts the number of issue slots  that were not delivered by the frontend due to other common frontend stalls not categorized.",
-        "MetricExpr": "TOPDOWN_FE_BOUND.OTHER / tma_info_slots",
+        "MetricExpr": "TOPDOWN_FE_BOUND.OTHER / tma_info_core_slots",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_fetch_bandwidth_group",
         "MetricName": "tma_other_fb",
         "MetricThreshold": "tma_other_fb > 0.05",
@@ -572,7 +546,7 @@
     },
     {
         "BriefDescription": "Counts the number of cycles that the oldest load of the load buffer is stalled at retirement due to a number of other load blocks.",
-        "MetricExpr": "LD_HEAD.OTHER_AT_RET / tma_info_clks",
+        "MetricExpr": "LD_HEAD.OTHER_AT_RET / tma_info_core_clks",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group",
         "MetricName": "tma_other_l1",
         "MetricThreshold": "tma_other_l1 > 0.05",
@@ -588,7 +562,7 @@
     },
     {
         "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": "(TOPDOWN_RETIRING.ALL - UOPS_RETIRED.MS - UOPS_RETIRED.FPDIV) / tma_info_core_slots",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_base_group",
         "MetricName": "tma_other_ret",
         "MetricThreshold": "tma_other_ret > 0.3",
@@ -604,7 +578,7 @@
     },
     {
         "BriefDescription": "Counts the number of issue slots  that were not delivered by the frontend due to wrong predecodes.",
-        "MetricExpr": "TOPDOWN_FE_BOUND.PREDECODE / tma_info_slots",
+        "MetricExpr": "TOPDOWN_FE_BOUND.PREDECODE / tma_info_core_slots",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_fetch_bandwidth_group",
         "MetricName": "tma_predecode",
         "MetricThreshold": "tma_predecode > 0.05",
@@ -612,7 +586,7 @@
     },
     {
         "BriefDescription": "Counts the number of issue slots  that were not consumed by the backend due to the physical register file unable to accept an entry (marble stalls).",
-        "MetricExpr": "TOPDOWN_BE_BOUND.REGISTER / tma_info_slots",
+        "MetricExpr": "TOPDOWN_BE_BOUND.REGISTER / tma_info_core_slots",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_resource_bound_group",
         "MetricName": "tma_register",
         "MetricThreshold": "tma_register > 0.1",
@@ -620,7 +594,7 @@
     },
     {
         "BriefDescription": "Counts the number of issue slots  that were not consumed by the backend due to the reorder buffer being full (ROB stalls).",
-        "MetricExpr": "TOPDOWN_BE_BOUND.REORDER_BUFFER / tma_info_slots",
+        "MetricExpr": "TOPDOWN_BE_BOUND.REORDER_BUFFER / tma_info_core_slots",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_resource_bound_group",
         "MetricName": "tma_reorder_buffer",
         "MetricThreshold": "tma_reorder_buffer > 0.1",
@@ -638,7 +612,7 @@
     },
     {
         "BriefDescription": "Counts the numer of issue slots  that result in retirement slots.",
-        "MetricExpr": "TOPDOWN_RETIRING.ALL / tma_info_slots",
+        "MetricExpr": "TOPDOWN_RETIRING.ALL / tma_info_core_slots",
         "MetricGroup": "TopdownL1;tma_L1_group",
         "MetricName": "tma_retiring",
         "MetricThreshold": "tma_retiring > 0.75",
@@ -655,7 +629,7 @@
     },
     {
         "BriefDescription": "Counts the number of issue slots  that were not consumed by the backend due to scoreboards from the instruction queue (IQ), jump execution unit (JEU), or microcode sequencer (MS).",
-        "MetricExpr": "TOPDOWN_BE_BOUND.SERIALIZATION / tma_info_slots",
+        "MetricExpr": "TOPDOWN_BE_BOUND.SERIALIZATION / tma_info_core_slots",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_resource_bound_group",
         "MetricName": "tma_serialization",
         "MetricThreshold": "tma_serialization > 0.1",
@@ -679,7 +653,7 @@
     },
     {
         "BriefDescription": "Counts the number of cycles that the oldest load of the load buffer is stalled at retirement due to a first level TLB miss.",
-        "MetricExpr": "LD_HEAD.DTLB_MISS_AT_RET / tma_info_clks",
+        "MetricExpr": "LD_HEAD.DTLB_MISS_AT_RET / tma_info_core_clks",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group",
         "MetricName": "tma_stlb_hit",
         "MetricThreshold": "tma_stlb_hit > 0.05",
@@ -687,7 +661,7 @@
     },
     {
         "BriefDescription": "Counts the number of cycles that the oldest load of the load buffer is stalled at retirement due to a second level TLB miss requiring a page walk.",
-        "MetricExpr": "LD_HEAD.PGWALK_AT_RET / tma_info_clks",
+        "MetricExpr": "LD_HEAD.PGWALK_AT_RET / tma_info_core_clks",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group",
         "MetricName": "tma_stlb_miss",
         "MetricThreshold": "tma_stlb_miss > 0.05",
@@ -703,7 +677,7 @@
     },
     {
         "BriefDescription": "Counts the number of cycles that the oldest load of the load buffer is stalled at retirement due to a store forward block.",
-        "MetricExpr": "LD_HEAD.ST_ADDR_AT_RET / tma_info_clks",
+        "MetricExpr": "LD_HEAD.ST_ADDR_AT_RET / tma_info_core_clks",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group",
         "MetricName": "tma_store_fwd_blk",
         "MetricThreshold": "tma_store_fwd_blk > 0.05",
diff --git a/tools/perf/pmu-events/arch/x86/mapfile.csv b/tools/perf/pmu-events/arch/x86/mapfile.csv
index 66c37a3cbf43..c8d564f6091d 100644
--- a/tools/perf/pmu-events/arch/x86/mapfile.csv
+++ b/tools/perf/pmu-events/arch/x86/mapfile.csv
@@ -1,6 +1,6 @@
 Family-model,Version,Filename,EventType
-GenuineIntel-6-(97|9A|B7|BA|BF),v1.20,alderlake,core
-GenuineIntel-6-BE,v1.20,alderlaken,core
+GenuineIntel-6-(97|9A|B7|BA|BF),v1.21,alderlake,core
+GenuineIntel-6-BE,v1.21,alderlaken,core
 GenuineIntel-6-(1C|26|27|35|36),v4,bonnell,core
 GenuineIntel-6-(3D|47),v27,broadwell,core
 GenuineIntel-6-56,v9,broadwellde,core