perf vendor events intel: Update alderlake TMA metrics to 4.7

Top-Down Microarchitecture Analysis (TMA) metrics simplify
cycle-accounting using microarchitecture-abstracted metrics
organized in one hierarchy. This update is from version 4.5 to
4.7.

The update includes:

 - tma_info_bottleneck* metrics, an abstraction or summarization of
   the 100+ TMA tree nodes into 12-entry familiar performance metrics.
 - tma_c01_wait and tma_c02_wait metrics measure power-performance
   states.
 - Reduce number of events (multiplexing) for tma_info_system_gflops,
   tma_info_core_flopc, tma_info_inst_mix_ipflop and tma_ports_utilized_0.
 - Fixes for tma_info_bottleneck_mispredictions and
   tma_info_bad_spec_branch_misprediction_cost.
 - New tma_info_inst_mix_ippause metric.
 - tma_serializing_operation is raised to level 3.
 - Swapped tma_info_core_ilp (becomes per SMT thread) and
   tma_info_pipeline_execute (per physical core).
 - tma_nop_instructions and tma_shuffles_256b are lowered to level 4
   under tma_other_light_ops_group.
 - Reduced number of events when SMT is off.
 - Tuned thresholds for tma_info_bottleneck_branching_overhead,
   tma_fetch_bandwidth and tma_ports_utilized_3m.

The update came from:

https://github.com/intel/perfmon/pull/140
https://github.com/intel/perfmon/pull/138

Running the script:

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

Signed-off-by: Ian Rogers <irogers@google.com>
Reviewed-by: Kan Liang <kan.liang@linux.intel.com>
Cc: Stephane Eranian <eranian@google.com>
Cc: Caleb Biggers <caleb.biggers@intel.com>
Cc: Edward Baker <edward.baker@intel.com>
Cc: Perry Taylor <perry.taylor@intel.com>
Cc: Samantha Alt <samantha.alt@intel.com>
Cc: Weilin Wang <weilin.wang@intel.com>
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Link: https://lore.kernel.org/r/20240214011820.644458-14-irogers@google.com

2 files changed, 302 insertions, 168 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 bbfa3883e533..b72c0e2cb946 100644
--- a/tools/perf/pmu-events/arch/x86/alderlake/adl-metrics.json
+++ b/tools/perf/pmu-events/arch/x86/alderlake/adl-metrics.json
@@ -811,13 +811,13 @@
         "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",
+        "MetricThreshold": "tma_alu_op_utilization > 0.4",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
         "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_thread_slots",
+        "MetricExpr": "78 * cpu_core@ASSISTS.ANY@ / 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)",
@@ -880,6 +880,24 @@
         "Unit": "cpu_core"
     },
     {
+        "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due staying in C0.1 power-performance optimized state (Faster wakeup time; Smaller power savings).",
+        "MetricExpr": "cpu_core@CPU_CLK_UNHALTED.C01@ / tma_info_thread_clks",
+        "MetricGroup": "C0Wait;TopdownL4;tma_L4_group;tma_serializing_operation_group",
+        "MetricName": "tma_c01_wait",
+        "MetricThreshold": "tma_c01_wait > 0.05 & (tma_serializing_operation > 0.1 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))",
+        "ScaleUnit": "100%",
+        "Unit": "cpu_core"
+    },
+    {
+        "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due staying in C0.2 power-performance optimized state (Slower wakeup time; Larger power savings).",
+        "MetricExpr": "cpu_core@CPU_CLK_UNHALTED.C02@ / tma_info_thread_clks",
+        "MetricGroup": "C0Wait;TopdownL4;tma_L4_group;tma_serializing_operation_group",
+        "MetricName": "tma_c02_wait",
+        "MetricThreshold": "tma_c02_wait > 0.05 & (tma_serializing_operation > 0.1 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))",
+        "ScaleUnit": "100%",
+        "Unit": "cpu_core"
+    },
+    {
         "BriefDescription": "This metric estimates fraction of cycles the CPU retired uops originated from CISC (complex instruction set computer) instruction",
         "MetricExpr": "max(0, tma_microcode_sequencer - tma_assists)",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_microcode_sequencer_group",
@@ -901,7 +919,7 @@
     },
     {
         "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses",
-        "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",
+        "MetricExpr": "(25 * tma_info_system_core_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_core_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))",
@@ -922,7 +940,7 @@
     },
     {
         "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses",
-        "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",
+        "MetricExpr": "24 * tma_info_system_core_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))",
@@ -935,7 +953,7 @@
         "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_thread_ipc / 6 > 0.35))",
+        "MetricThreshold": "tma_decoder0_alone > 0.1 & (tma_mite > 0.1 & tma_fetch_bandwidth > 0.2)",
         "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"
@@ -965,7 +983,7 @@
         "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_thread_ipc / 6 > 0.35)",
+        "MetricThreshold": "tma_dsb > 0.15 & tma_fetch_bandwidth > 0.2",
         "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"
@@ -986,7 +1004,7 @@
         "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_bottleneck_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, tma_info_bottleneck_memory_synchronization",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -996,13 +1014,13 @@
         "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_bottleneck_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, tma_info_bottleneck_memory_synchronization",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
         "BriefDescription": "This metric roughly estimates how often CPU was handling synchronizations due to False Sharing",
-        "MetricExpr": "28 * tma_info_system_average_frequency * cpu_core@OCR.DEMAND_RFO.L3_HIT.SNOOP_HITM@ / tma_info_thread_clks",
+        "MetricExpr": "28 * tma_info_system_core_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))",
@@ -1016,7 +1034,7 @@
         "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_bottleneck_memory_bandwidth, tma_info_system_dram_bw_use, 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_cache_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"
     },
@@ -1025,7 +1043,7 @@
         "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_thread_ipc / 6 > 0.35",
+        "MetricThreshold": "tma_fetch_bandwidth > 0.2",
         "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_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp",
         "ScaleUnit": "100%",
@@ -1127,10 +1145,10 @@
     {
         "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_thread_slots)",
-        "MetricGroup": "Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group",
+        "MetricGroup": "Branches;Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group",
         "MetricName": "tma_fused_instructions",
         "MetricThreshold": "tma_fused_instructions > 0.1 & tma_light_operations > 0.6",
-        "PublicDescription": "This metric represents fraction of slots where the CPU was retiring fused instructions -- where one uop can represent multiple contiguous instructions. The instruction pairs of CMP+JCC or DEC+JCC are commonly used examples.",
+        "PublicDescription": "This metric represents fraction of slots where the CPU was retiring fused instructions -- where one uop can represent multiple contiguous instructions. CMP+JCC or DEC+JCC are common examples of legacy fusions. {([MTL] Note new MOV+OP and Load+OP fusions appear under Other_Light_Ops in MTL!)}",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -1141,14 +1159,14 @@
         "MetricName": "tma_heavy_operations",
         "MetricThreshold": "tma_heavy_operations > 0.1",
         "MetricgroupNoGroup": "TopdownL2",
-        "PublicDescription": "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. This highly-correlates with the uop length of these instructions/sequences. Sample with: UOPS_RETIRED.HEAVY",
+        "PublicDescription": "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. This highly-correlates with the uop length of these instructions/sequences. ([ICL+] Note this may overcount due to approximation using indirect events; [ADL+] .). Sample with: UOPS_RETIRED.HEAVY",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
         "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to instruction cache misses",
         "MetricExpr": "cpu_core@ICACHE_DATA.STALLS@ / tma_info_thread_clks",
-        "MetricGroup": "BigFoot;FetchLat;IcMiss;TopdownL3;tma_L3_group;tma_fetch_latency_group",
+        "MetricGroup": "BigFootprint;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)",
         "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to instruction cache misses. Sample with: FRONTEND_RETIRED.L2_MISS_PS;FRONTEND_RETIRED.L1I_MISS_PS",
@@ -1157,7 +1175,7 @@
     },
     {
         "BriefDescription": "Branch Misprediction Cost: Fraction of TMA slots wasted per non-speculative branch misprediction (retired JEClear)",
-        "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",
+        "MetricExpr": "tma_info_bottleneck_mispredictions * tma_info_thread_slots / cpu_core@BR_MISP_RETIRED.ALL_BRANCHES@ / 100",
         "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",
@@ -1181,7 +1199,7 @@
     },
     {
         "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",
+        "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / BR_MISP_RETIRED.INDIRECT",
         "MetricGroup": "Bad;BrMispredicts",
         "MetricName": "tma_info_bad_spec_ipmisp_indirect",
         "MetricThreshold": "tma_info_bad_spec_ipmisp_indirect < 1e3",
@@ -1204,6 +1222,13 @@
         "Unit": "cpu_core"
     },
     {
+        "BriefDescription": "Speculative to Retired ratio of all clears (covering mispredicts and nukes)",
+        "MetricExpr": "cpu_core@INT_MISC.CLEARS_COUNT@ / (cpu_core@BR_MISP_RETIRED.ALL_BRANCHES@ + cpu_core@MACHINE_CLEARS.COUNT@)",
+        "MetricGroup": "BrMispredicts",
+        "MetricName": "tma_info_bad_spec_spec_clears_ratio",
+        "Unit": "cpu_core"
+    },
+    {
         "BriefDescription": "Probability of Core Bound bottleneck hidden by SMT-profiling artifacts",
         "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",
@@ -1230,61 +1255,94 @@
         "Unit": "cpu_core"
     },
     {
+        "BriefDescription": "Total pipeline cost of \"useful operations\" - the baseline operations not covered by Branching_Overhead nor Irregular_Overhead.",
+        "MetricExpr": "100 * (tma_retiring - (cpu_core@BR_INST_RETIRED.ALL_BRANCHES@ + cpu_core@BR_INST_RETIRED.NEAR_CALL@) / tma_info_thread_slots - tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * tma_heavy_operations)",
+        "MetricGroup": "Ret",
+        "MetricName": "tma_info_bottleneck_base_non_br",
+        "MetricThreshold": "tma_info_bottleneck_base_non_br > 20",
+        "Unit": "cpu_core"
+    },
+    {
         "BriefDescription": "Total pipeline cost of instruction fetch related bottlenecks by large code footprint programs (i-side cache; TLB and BTB misses)",
         "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",
+        "MetricGroup": "BigFootprint;Fed;Frontend;IcMiss;MemoryTLB",
         "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": "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",
+        "MetricExpr": "100 * ((cpu_core@BR_INST_RETIRED.ALL_BRANCHES@ + cpu_core@BR_INST_RETIRED.NEAR_CALL@) / tma_info_thread_slots)",
+        "MetricGroup": "Ret",
         "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",
+        "MetricThreshold": "tma_info_bottleneck_branching_overhead > 5",
+        "Unit": "cpu_core"
+    },
+    {
+        "BriefDescription": "Total pipeline cost of external Memory- or Cache-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_memory_bound * (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_memory_bound * (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_cache_memory_bandwidth",
+        "MetricThreshold": "tma_info_bottleneck_cache_memory_bandwidth > 20",
+        "PublicDescription": "Total pipeline cost of external Memory- or Cache-Bandwidth related bottlenecks. Related metrics: tma_fb_full, tma_info_system_dram_bw_use, tma_mem_bandwidth, tma_sq_full",
+        "Unit": "cpu_core"
+    },
+    {
+        "BriefDescription": "Total pipeline cost of external Memory- or Cache-Latency 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_latency / (tma_mem_bandwidth + tma_mem_latency)) + tma_memory_bound * (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_memory_bound * tma_l2_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) + tma_memory_bound * (tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_store_latency / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency + tma_streaming_stores)))",
+        "MetricGroup": "Mem;MemoryLat;Offcore;tma_issueLat",
+        "MetricName": "tma_info_bottleneck_cache_memory_latency",
+        "MetricThreshold": "tma_info_bottleneck_cache_memory_latency > 20",
+        "PublicDescription": "Total pipeline cost of external Memory- or Cache-Latency related bottlenecks. Related metrics: tma_l3_hit_latency, tma_mem_latency",
+        "Unit": "cpu_core"
+    },
+    {
+        "BriefDescription": "Total pipeline cost when the execution is compute-bound - an estimation",
+        "MetricExpr": "100 * (tma_core_bound * tma_divider / (tma_divider + tma_ports_utilization + tma_serializing_operation) + tma_core_bound * (tma_ports_utilization / (tma_divider + tma_ports_utilization + tma_serializing_operation)) * (tma_ports_utilized_3m / (tma_ports_utilized_0 + tma_ports_utilized_1 + tma_ports_utilized_2 + tma_ports_utilized_3m)))",
+        "MetricGroup": "Cor;tma_issueComp",
+        "MetricName": "tma_info_bottleneck_compute_bound_est",
+        "MetricThreshold": "tma_info_bottleneck_compute_bound_est > 20",
+        "PublicDescription": "Total pipeline cost when the execution is compute-bound - an estimation. Covers Core Bound when High ILP as well as when long-latency execution units are busy. Related metrics: ",
         "Unit": "cpu_core"
     },
     {
         "BriefDescription": "Total pipeline cost of instruction fetch bandwidth related bottlenecks",
-        "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",
+        "MetricExpr": "100 * (tma_frontend_bound - (1 - 10 * tma_microcode_sequencer * tma_other_mispredicts / 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) - (1 - cpu_core@INST_RETIRED.REP_ITERATION@ / cpu_core@UOPS_RETIRED.MS\\,cmask\\=1@) * (tma_fetch_latency * (tma_ms_switches + tma_branch_resteers * (tma_clears_resteers + tma_mispredicts_resteers * tma_other_mispredicts / tma_branch_mispredicts) / (tma_clears_resteers + tma_mispredicts_resteers + tma_unknown_branches)) / (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 (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",
+        "BriefDescription": "Total pipeline cost of irregular execution (e.g",
+        "MetricExpr": "100 * ((1 - cpu_core@INST_RETIRED.REP_ITERATION@ / cpu_core@UOPS_RETIRED.MS\\,cmask\\=1@) * (tma_fetch_latency * (tma_ms_switches + tma_branch_resteers * (tma_clears_resteers + tma_mispredicts_resteers * tma_other_mispredicts / tma_branch_mispredicts) / (tma_clears_resteers + tma_mispredicts_resteers + tma_unknown_branches)) / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches)) + 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts * tma_branch_mispredicts + tma_machine_clears * tma_other_nukes / tma_other_nukes + tma_core_bound * (tma_serializing_operation + cpu_core@RS.EMPTY\\,umask\\=1@ / tma_info_thread_clks * tma_ports_utilized_0) / (tma_divider + tma_ports_utilization + tma_serializing_operation) + tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * tma_heavy_operations)",
+        "MetricGroup": "Bad;Cor;Ret;tma_issueMS",
+        "MetricName": "tma_info_bottleneck_irregular_overhead",
+        "MetricThreshold": "tma_info_bottleneck_irregular_overhead > 10",
+        "PublicDescription": "Total pipeline cost of irregular execution (e.g. FP-assists in HPC, Wait time with work imbalance multithreaded workloads, overhead in system services or virtualized environments). Related metrics: tma_microcode_sequencer, tma_ms_switches",
         "Unit": "cpu_core"
     },
     {
         "BriefDescription": "Total pipeline cost of Memory Address Translation related bottlenecks (data-side TLBs)",
-        "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)))",
+        "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_memory_bound * (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",
+        "PublicDescription": "Total pipeline cost of Memory Address Translation related bottlenecks (data-side TLBs). Related metrics: tma_dtlb_load, tma_dtlb_store, tma_info_bottleneck_memory_synchronization",
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "Total pipeline cost of Memory Latency related bottlenecks (external memory and off-core caches)",
-        "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",
+        "BriefDescription": "Total pipeline cost of Memory Synchronization related bottlenecks (data transfers and coherency updates across processors)",
+        "MetricExpr": "100 * (tma_memory_bound * (tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_contested_accesses + tma_data_sharing) / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full) + tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * tma_false_sharing / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency + tma_streaming_stores - tma_store_latency)) + tma_machine_clears * (1 - tma_other_nukes / tma_other_nukes))",
+        "MetricGroup": "Mem;Offcore;tma_issueTLB",
+        "MetricName": "tma_info_bottleneck_memory_synchronization",
+        "MetricThreshold": "tma_info_bottleneck_memory_synchronization > 10",
+        "PublicDescription": "Total pipeline cost of Memory Synchronization related bottlenecks (data transfers and coherency updates across processors). Related metrics: tma_dtlb_load, tma_dtlb_store, tma_info_bottleneck_memory_data_tlbs",
         "Unit": "cpu_core"
     },
     {
         "BriefDescription": "Total pipeline cost of Branch Misprediction related bottlenecks",
-        "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))",
+        "MetricExpr": "100 * (1 - 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts) * (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",
@@ -1292,6 +1350,15 @@
         "Unit": "cpu_core"
     },
     {
+        "BriefDescription": "Total pipeline cost of remaining bottlenecks (apart from those listed in the Info.Bottlenecks metrics class)",
+        "MetricExpr": "100 - (tma_info_bottleneck_big_code + tma_info_bottleneck_instruction_fetch_bw + tma_info_bottleneck_mispredictions + tma_info_bottleneck_cache_memory_bandwidth + tma_info_bottleneck_cache_memory_latency + tma_info_bottleneck_memory_data_tlbs + tma_info_bottleneck_memory_synchronization + tma_info_bottleneck_compute_bound_est + tma_info_bottleneck_irregular_overhead + tma_info_bottleneck_branching_overhead + tma_info_bottleneck_base_non_br)",
+        "MetricGroup": "Cor;Offcore",
+        "MetricName": "tma_info_bottleneck_other_bottlenecks",
+        "MetricThreshold": "tma_info_bottleneck_other_bottlenecks > 20",
+        "PublicDescription": "Total pipeline cost of remaining bottlenecks (apart from those listed in the Info.Bottlenecks metrics class). Examples include data-dependencies (Core Bound when Low ILP) and other unlisted memory-related stalls.",
+        "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",
@@ -1328,7 +1395,7 @@
     },
     {
         "BriefDescription": "Core actual clocks when any Logical Processor is active on the Physical Core",
-        "MetricExpr": "cpu_core@CPU_CLK_UNHALTED.DISTRIBUTED@",
+        "MetricExpr": "(cpu_core@CPU_CLK_UNHALTED.DISTRIBUTED@ if #SMT_on else tma_info_thread_clks)",
         "MetricGroup": "SMT",
         "MetricName": "tma_info_core_core_clks",
         "Unit": "cpu_core"
@@ -1341,8 +1408,15 @@
         "Unit": "cpu_core"
     },
     {
+        "BriefDescription": "uops Executed per Cycle",
+        "MetricExpr": "cpu_core@UOPS_EXECUTED.THREAD@ / tma_info_thread_clks",
+        "MetricGroup": "Power",
+        "MetricName": "tma_info_core_epc",
+        "Unit": "cpu_core"
+    },
+    {
         "BriefDescription": "Floating Point Operations Per Cycle",
-        "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",
+        "MetricExpr": "(cpu_core@FP_ARITH_INST_RETIRED.SCALAR@ + 2 * cpu_core@FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE@ + 4 * cpu_core@FP_ARITH_INST_RETIRED.4_FLOPS@ + 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"
@@ -1356,8 +1430,8 @@
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is execution) per-core",
-        "MetricExpr": "cpu_core@UOPS_EXECUTED.THREAD@ / (cpu_core@UOPS_EXECUTED.CORE_CYCLES_GE_1@ / 2 if #SMT_on else cpu_core@UOPS_EXECUTED.CORE_CYCLES_GE_1@)",
+        "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is execution) per thread (logical-processor)",
+        "MetricExpr": "cpu_core@UOPS_EXECUTED.THREAD@ / cpu_core@UOPS_EXECUTED.THREAD\\,cmask\\=1@",
         "MetricGroup": "Backend;Cor;Pipeline;PortsUtil",
         "MetricName": "tma_info_core_ilp",
         "Unit": "cpu_core"
@@ -1429,6 +1503,14 @@
         "Unit": "cpu_core"
     },
     {
+        "BriefDescription": "Average number of cycles the front-end was delayed due to an Unknown Branch detection",
+        "MetricExpr": "cpu_core@INT_MISC.UNKNOWN_BRANCH_CYCLES@ / cpu_core@INT_MISC.UNKNOWN_BRANCH_CYCLES\\,cmask\\=1\\,edge@",
+        "MetricGroup": "Fed",
+        "MetricName": "tma_info_frontend_unknown_branch_cost",
+        "PublicDescription": "Average number of cycles the front-end was delayed due to an Unknown Branch detection. See Unknown_Branches node.",
+        "Unit": "cpu_core"
+    },
+    {
         "BriefDescription": "Branch instructions per taken branch.",
         "MetricExpr": "cpu_core@BR_INST_RETIRED.ALL_BRANCHES@ / BR_INST_RETIRED.NEAR_TAKEN",
         "MetricGroup": "Branches;Fed;PGO",
@@ -1449,7 +1531,7 @@
         "MetricGroup": "Flops;InsType",
         "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.",
+        "PublicDescription": "Instructions per FP Arithmetic instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting. Approximated prior to BDW.",
         "Unit": "cpu_core"
     },
     {
@@ -1458,7 +1540,7 @@
         "MetricGroup": "Flops;FpVector;InsType",
         "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.",
+        "PublicDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting.",
         "Unit": "cpu_core"
     },
     {
@@ -1467,7 +1549,7 @@
         "MetricGroup": "Flops;FpVector;InsType",
         "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.",
+        "PublicDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting.",
         "Unit": "cpu_core"
     },
     {
@@ -1476,7 +1558,7 @@
         "MetricGroup": "Flops;FpScalar;InsType",
         "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.",
+        "PublicDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting.",
         "Unit": "cpu_core"
     },
     {
@@ -1485,7 +1567,7 @@
         "MetricGroup": "Flops;FpScalar;InsType",
         "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.",
+        "PublicDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting.",
         "Unit": "cpu_core"
     },
     {
@@ -1506,7 +1588,7 @@
     },
     {
         "BriefDescription": "Instructions per Floating Point (FP) Operation (lower number means higher occurrence rate)",
-        "MetricExpr": "cpu_core@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@)",
+        "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / (cpu_core@FP_ARITH_INST_RETIRED.SCALAR@ + 2 * cpu_core@FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE@ + 4 * cpu_core@FP_ARITH_INST_RETIRED.4_FLOPS@ + 8 * cpu_core@FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE@)",
         "MetricGroup": "Flops;InsType",
         "MetricName": "tma_info_inst_mix_ipflop",
         "MetricThreshold": "tma_info_inst_mix_ipflop < 10",
@@ -1521,6 +1603,13 @@
         "Unit": "cpu_core"
     },
     {
+        "BriefDescription": "Instructions per PAUSE (lower number means higher occurrence rate)",
+        "MetricExpr": "tma_info_inst_mix_instructions / CPU_CLK_UNHALTED.PAUSE_INST",
+        "MetricGroup": "Flops;FpVector;InsType",
+        "MetricName": "tma_info_inst_mix_ippause",
+        "Unit": "cpu_core"
+    },
+    {
         "BriefDescription": "Instructions per Store (lower number means higher occurrence rate)",
         "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / MEM_INST_RETIRED.ALL_STORES",
         "MetricGroup": "InsType",
@@ -1547,164 +1636,178 @@
     },
     {
         "BriefDescription": "Average per-core data fill bandwidth to the L1 data cache [GB / sec]",
-        "MetricExpr": "64 * cpu_core@L1D.REPLACEMENT@ / 1e9 / duration_time",
+        "MetricExpr": "tma_info_memory_l1d_cache_fill_bw",
         "MetricGroup": "Mem;MemoryBW",
-        "MetricName": "tma_info_memory_core_l1d_cache_fill_bw",
+        "MetricName": "tma_info_memory_core_l1d_cache_fill_bw_2t",
         "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",