perf vendor events intel: Update skylakex 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.
     - 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.
     - 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/20240214011820.644458-30-irogers@google.com

2 files changed, 392 insertions, 168 deletions

diff --git a/tools/perf/pmu-events/arch/x86/skylakex/metricgroups.json b/tools/perf/pmu-events/arch/x86/skylakex/metricgroups.json
index bc6a9a4d27a9..904d299c95a3 100644
--- a/tools/perf/pmu-events/arch/x86/skylakex/metricgroups.json
+++ b/tools/perf/pmu-events/arch/x86/skylakex/metricgroups.json
@@ -2,10 +2,10 @@
     "Backend": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
     "Bad": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
     "BadSpec": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
-    "BigFoot": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
+    "BigFootprint": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
     "BrMispredicts": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
     "Branches": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
-    "CacheMisses": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
+    "CacheHits": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
     "CodeGen": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
     "Compute": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
     "Cor": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
@@ -26,7 +26,9 @@
     "L2Evicts": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
     "LSD": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
     "MachineClears": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
+    "Machine_Clears": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
     "Mem": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
+    "MemOffcore": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
     "MemoryBW": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
     "MemoryBound": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
     "MemoryLat": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
@@ -64,8 +66,10 @@
     "tma_L5_group": "Metrics for top-down breakdown at level 5",
     "tma_L6_group": "Metrics for top-down breakdown at level 6",
     "tma_alu_op_utilization_group": "Metrics contributing to tma_alu_op_utilization category",
+    "tma_assists_group": "Metrics contributing to tma_assists category",
     "tma_backend_bound_group": "Metrics contributing to tma_backend_bound category",
     "tma_bad_speculation_group": "Metrics contributing to tma_bad_speculation category",
+    "tma_branch_mispredicts_group": "Metrics contributing to tma_branch_mispredicts category",
     "tma_branch_resteers_group": "Metrics contributing to tma_branch_resteers category",
     "tma_core_bound_group": "Metrics contributing to tma_core_bound category",
     "tma_dram_bound_group": "Metrics contributing to tma_dram_bound category",
@@ -78,9 +82,9 @@
     "tma_frontend_bound_group": "Metrics contributing to tma_frontend_bound category",
     "tma_heavy_operations_group": "Metrics contributing to tma_heavy_operations category",
     "tma_issue2P": "Metrics related by the issue $issue2P",
-    "tma_issueBC": "Metrics related by the issue $issueBC",
     "tma_issueBM": "Metrics related by the issue $issueBM",
     "tma_issueBW": "Metrics related by the issue $issueBW",
+    "tma_issueComp": "Metrics related by the issue $issueComp",
     "tma_issueD0": "Metrics related by the issue $issueD0",
     "tma_issueFB": "Metrics related by the issue $issueFB",
     "tma_issueFL": "Metrics related by the issue $issueFL",
@@ -100,10 +104,12 @@
     "tma_l3_bound_group": "Metrics contributing to tma_l3_bound category",
     "tma_light_operations_group": "Metrics contributing to tma_light_operations category",
     "tma_load_op_utilization_group": "Metrics contributing to tma_load_op_utilization category",
+    "tma_machine_clears_group": "Metrics contributing to tma_machine_clears category",
     "tma_mem_latency_group": "Metrics contributing to tma_mem_latency category",
     "tma_memory_bound_group": "Metrics contributing to tma_memory_bound category",
     "tma_microcode_sequencer_group": "Metrics contributing to tma_microcode_sequencer category",
     "tma_mite_group": "Metrics contributing to tma_mite category",
+    "tma_other_light_ops_group": "Metrics contributing to tma_other_light_ops category",
     "tma_ports_utilization_group": "Metrics contributing to tma_ports_utilization category",
     "tma_ports_utilized_0_group": "Metrics contributing to tma_ports_utilized_0 category",
     "tma_ports_utilized_3m_group": "Metrics contributing to tma_ports_utilized_3m category",
diff --git a/tools/perf/pmu-events/arch/x86/skylakex/skx-metrics.json b/tools/perf/pmu-events/arch/x86/skylakex/skx-metrics.json
index ec3aa5ef00a3..025e836a1c80 100644
--- a/tools/perf/pmu-events/arch/x86/skylakex/skx-metrics.json
+++ b/tools/perf/pmu-events/arch/x86/skylakex/skx-metrics.json
@@ -210,6 +210,12 @@
         "ScaleUnit": "1MB/s"
     },
     {
+        "BriefDescription": "Bandwidth (MB/sec) of write requests that miss the last level cache (LLC) and go to remote memory.",
+        "MetricExpr": "UNC_CHA_REQUESTS.WRITES_REMOTE * 64 / 1e6 / duration_time",
+        "MetricName": "llc_miss_remote_memory_bandwidth_write",
+        "ScaleUnit": "1MB/s"
+    },
+    {
         "BriefDescription": "The ratio of number of completed memory load instructions to the total number completed instructions",
         "MetricExpr": "MEM_INST_RETIRED.ALL_LOADS / INST_RETIRED.ANY",
         "MetricName": "loads_per_instr",
@@ -298,12 +304,12 @@
         "MetricExpr": "(UOPS_DISPATCHED_PORT.PORT_0 + UOPS_DISPATCHED_PORT.PORT_1 + UOPS_DISPATCHED_PORT.PORT_5 + UOPS_DISPATCHED_PORT.PORT_6) / tma_info_thread_slots",
         "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%"
     },
     {
         "BriefDescription": "This metric estimates fraction of slots the CPU retired uops delivered by the Microcode_Sequencer as a result of Assists",
-        "MetricExpr": "100 * (FP_ASSIST.ANY + OTHER_ASSISTS.ANY) / tma_info_thread_slots",
+        "MetricExpr": "34 * (FP_ASSIST.ANY + OTHER_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)",
@@ -371,7 +377,7 @@
     {
         "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses",
         "MetricConstraint": "NO_GROUP_EVENTS",
-        "MetricExpr": "(44 * tma_info_system_average_frequency * (MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM * (OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.HITM_OTHER_CORE / (OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.HITM_OTHER_CORE + OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD))) + 44 * tma_info_system_average_frequency * MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks",
+        "MetricExpr": "(44 * tma_info_system_core_frequency * (MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM * (OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.HITM_OTHER_CORE / (OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.HITM_OTHER_CORE + OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD))) + 44 * tma_info_system_core_frequency * MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS) * (1 + MEM_LOAD_RETIRED.FB_HIT / 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))",
@@ -392,7 +398,7 @@
     {
         "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses",
         "MetricConstraint": "NO_GROUP_EVENTS",
-        "MetricExpr": "44 * tma_info_system_average_frequency * (MEM_LOAD_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM * (1 - OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.HITM_OTHER_CORE / (OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.HITM_OTHER_CORE + OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD))) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks",
+        "MetricExpr": "44 * tma_info_system_core_frequency * (MEM_LOAD_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM * (1 - OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.HITM_OTHER_CORE / (OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.HITM_OTHER_CORE + OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD))) * (1 + MEM_LOAD_RETIRED.FB_HIT / 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))",
@@ -404,7 +410,7 @@
         "MetricExpr": "(cpu@INST_DECODED.DECODERS\\,cmask\\=1@ - cpu@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 / 4 > 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%"
     },
@@ -429,10 +435,10 @@
     },
     {
         "BriefDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to DSB (decoded uop cache) fetch pipeline",
-        "MetricExpr": "(IDQ.ALL_DSB_CYCLES_ANY_UOPS - IDQ.ALL_DSB_CYCLES_4_UOPS) / tma_info_core_core_clks / 2",
+        "MetricExpr": "(IDQ.DSB_CYCLES_ANY - 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 / 4 > 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%"
     },
@@ -452,7 +458,7 @@
         "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%"
     },
     {
@@ -461,13 +467,13 @@
         "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%"
     },
     {
         "BriefDescription": "This metric roughly estimates how often CPU was handling synchronizations due to False Sharing",
         "MetricConstraint": "NO_GROUP_EVENTS",
-        "MetricExpr": "(110 * tma_info_system_average_frequency * (OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS.REMOTE_HITM + OFFCORE_RESPONSE.PF_L2_RFO.L3_MISS.REMOTE_HITM) + 47.5 * tma_info_system_average_frequency * (OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.HITM_OTHER_CORE + OFFCORE_RESPONSE.PF_L2_RFO.L3_HIT.HITM_OTHER_CORE)) / tma_info_thread_clks",
+        "MetricExpr": "(110 * tma_info_system_core_frequency * (OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS.REMOTE_HITM + OFFCORE_RESPONSE.PF_L2_RFO.L3_MISS.REMOTE_HITM) + 47.5 * tma_info_system_core_frequency * (OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.HITM_OTHER_CORE + OFFCORE_RESPONSE.PF_L2_RFO.L3_HIT.HITM_OTHER_CORE)) / 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))",
@@ -481,7 +487,7 @@
         "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%"
     },
     {
@@ -489,7 +495,7 @@
         "MetricExpr": "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 / 4 > 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%"
@@ -524,6 +530,15 @@
         "ScaleUnit": "100%"
     },
     {
+        "BriefDescription": "This metric roughly estimates fraction of slots the CPU retired uops as a result of handing Floating Point (FP) Assists",
+        "MetricExpr": "34 * FP_ASSIST.ANY / tma_info_thread_slots",
+        "MetricGroup": "HPC;TopdownL5;tma_L5_group;tma_assists_group",
+        "MetricName": "tma_fp_assists",
+        "MetricThreshold": "tma_fp_assists > 0.1",
+        "PublicDescription": "This metric roughly estimates fraction of slots the CPU retired uops as a result of handing Floating Point (FP) Assists. FP Assist may apply when working with very small floating point values (so-called Denormals).",
+        "ScaleUnit": "100%"
+    },
+    {
         "BriefDescription": "This metric approximates arithmetic floating-point (FP) scalar uops fraction the CPU has retired",
         "MetricExpr": "cpu@FP_ARITH_INST_RETIRED.SCALAR_SINGLE\\,umask\\=0x03@ / UOPS_RETIRED.RETIRE_SLOTS",
         "MetricGroup": "Compute;Flops;TopdownL4;tma_L4_group;tma_fp_arith_group;tma_issue2P",
@@ -582,10 +597,10 @@
     {
         "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 * UOPS_RETIRED.MACRO_FUSED / UOPS_RETIRED.RETIRE_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%"
     },
     {
@@ -595,13 +610,13 @@
         "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.",
+        "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+] .)",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to instruction cache misses",
         "MetricExpr": "(ICACHE_16B.IFDATA_STALL + 2 * cpu@ICACHE_16B.IFDATA_STALL\\,cmask\\=1\\,edge@) / 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",
@@ -609,26 +624,53 @@
     },
     {
         "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 / 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"
     },
     {
         "BriefDescription": "Instructions per retired mispredicts for indirect CALL or JMP branches (lower number means higher occurrence rate).",
-        "MetricExpr": "tma_info_inst_mix_instructions / (UOPS_RETIRED.RETIRE_SLOTS / UOPS_ISSUED.ANY * cpu@BR_MISP_EXEC.ALL_BRANCHES\\,umask\\=0xE4@)",
+        "MetricExpr": "tma_info_inst_mix_instructions / (UOPS_RETIRED.RETIRE_SLOTS / UOPS_ISSUED.ANY * BR_MISP_EXEC.INDIRECT)",
         "MetricGroup": "Bad;BrMispredicts",
         "MetricName": "tma_info_bad_spec_ipmisp_indirect",
         "MetricThreshold": "tma_info_bad_spec_ipmisp_indirect < 1e3"
     },
     {
         "BriefDescription": "Number of Instructions per non-speculative Branch Misprediction (JEClear) (lower number means higher occurrence rate)",
-        "MetricExpr": "tma_info_core_ipmispredict",
+        "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"
     },
     {
+        "BriefDescription": "Speculative to Retired ratio of all clears (covering mispredicts and nukes)",
+        "MetricExpr": "INT_MISC.CLEARS_COUNT / (BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT)",
+        "MetricGroup": "BrMispredicts",
+        "MetricName": "tma_info_bad_spec_spec_clears_ratio"
+    },
+    {
+        "BriefDescription": "Probability of Core Bound bottleneck hidden by SMT-profiling artifacts",
+        "MetricExpr": "(100 * (1 - tma_core_bound / (((EXE_ACTIVITY.EXE_BOUND_0_PORTS + tma_core_bound * RS_EVENTS.EMPTY_CYCLES) / CPU_CLK_UNHALTED.THREAD * (CYCLE_ACTIVITY.STALLS_TOTAL - CYCLE_ACTIVITY.STALLS_MEM_ANY) / CPU_CLK_UNHALTED.THREAD * CPU_CLK_UNHALTED.THREAD + (EXE_ACTIVITY.1_PORTS_UTIL + tma_retiring * EXE_ACTIVITY.2_PORTS_UTIL)) / CPU_CLK_UNHALTED.THREAD if ARITH.DIVIDER_ACTIVE < CYCLE_ACTIVITY.STALLS_TOTAL - CYCLE_ACTIVITY.STALLS_MEM_ANY else (EXE_ACTIVITY.1_PORTS_UTIL + tma_retiring * EXE_ACTIVITY.2_PORTS_UTIL) / CPU_CLK_UNHALTED.THREAD) if tma_core_bound < (((EXE_ACTIVITY.EXE_BOUND_0_PORTS + tma_core_bound * RS_EVENTS.EMPTY_CYCLES) / CPU_CLK_UNHALTED.THREAD * (CYCLE_ACTIVITY.STALLS_TOTAL - CYCLE_ACTIVITY.STALLS_MEM_ANY) / CPU_CLK_UNHALTED.THREAD * CPU_CLK_UNHALTED.THREAD + (EXE_ACTIVITY.1_PORTS_UTIL + tma_retiring * EXE_ACTIVITY.2_PORTS_UTIL)) / CPU_CLK_UNHALTED.THREAD if ARITH.DIVIDER_ACTIVE < CYCLE_ACTIVITY.STALLS_TOTAL - CYCLE_ACTIVITY.STALLS_MEM_ANY else (EXE_ACTIVITY.1_PORTS_UTIL + tma_retiring * EXE_ACTIVITY.2_PORTS_UTIL) / CPU_CLK_UNHALTED.THREAD) else 1) if tma_info_system_smt_2t_utilization > 0.5 else 0)",
+        "MetricGroup": "Cor;SMT;TopdownL1;tma_L1_group",
+        "MetricName": "tma_info_botlnk_core_bound_likely",
+        "MetricgroupNoGroup": "TopdownL1"
+    },
+    {
+        "BriefDescription": "Total pipeline cost of DSB (uop cache) misses - subset of the Instruction_Fetch_BW Bottleneck.",
+        "MetricExpr": "100 * (100 * (tma_fetch_latency * (DSB2MITE_SWITCHES.PENALTY_CYCLES / CPU_CLK_UNHALTED.THREAD) / ((ICACHE_16B.IFDATA_STALL + 2 * cpu@ICACHE_16B.IFDATA_STALL\\,cmask\\=0x1\\,edge\\=0x1@) / CPU_CLK_UNHALTED.THREAD + ICACHE_TAG.STALLS / CPU_CLK_UNHALTED.THREAD + (INT_MISC.CLEAR_RESTEER_CYCLES / CPU_CLK_UNHALTED.THREAD + 9 * BACLEARS.ANY / CPU_CLK_UNHALTED.THREAD) + min(2 * IDQ.MS_SWITCHES / CPU_CLK_UNHALTED.THREAD, 1) + DECODE.LCP / CPU_CLK_UNHALTED.THREAD + DSB2MITE_SWITCHES.PENALTY_CYCLES / CPU_CLK_UNHALTED.THREAD) + tma_fetch_bandwidth * tma_mite / (tma_mite + tma_dsb)))",
+        "MetricGroup": "DSBmiss;Fed;TopdownL1;tma_L1_group",
+        "MetricName": "tma_info_botlnk_dsb_misses",
+        "MetricgroupNoGroup": "TopdownL1"
+    },
+    {
+        "BriefDescription": "Total pipeline cost of Instruction Cache misses - subset of the Big_Code Bottleneck.",
+        "MetricExpr": "100 * (100 * (tma_fetch_latency * ((ICACHE_16B.IFDATA_STALL + 2 * cpu@ICACHE_16B.IFDATA_STALL\\,cmask\\=0x1\\,edge\\=0x1@) / CPU_CLK_UNHALTED.THREAD) / ((ICACHE_16B.IFDATA_STALL + 2 * cpu@ICACHE_16B.IFDATA_STALL\\,cmask\\=0x1\\,edge\\=0x1@) / CPU_CLK_UNHALTED.THREAD + ICACHE_TAG.STALLS / CPU_CLK_UNHALTED.THREAD + (INT_MISC.CLEAR_RESTEER_CYCLES / CPU_CLK_UNHALTED.THREAD + 9 * BACLEARS.ANY / CPU_CLK_UNHALTED.THREAD) + min(2 * IDQ.MS_SWITCHES / CPU_CLK_UNHALTED.THREAD, 1) + DECODE.LCP / CPU_CLK_UNHALTED.THREAD + DSB2MITE_SWITCHES.PENALTY_CYCLES / CPU_CLK_UNHALTED.THREAD)))",
+        "MetricGroup": "Fed;FetchLat;IcMiss;TopdownL1;tma_L1_group",
+        "MetricName": "tma_info_botlnk_ic_misses",
+        "MetricgroupNoGroup": "TopdownL1"
+    },
+    {
         "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)",
@@ -654,67 +696,102 @@
         "PublicDescription": "Total pipeline cost of Instruction Cache misses - subset of the Big_Code Bottleneck. Related metrics: "
     },
     {
+        "BriefDescription": "Total pipeline cost of \"useful operations\" - the baseline operations not covered by Branching_Overhead nor Irregular_Overhead.",
+        "MetricExpr": "100 * (tma_retiring - (BR_INST_RETIRED.ALL_BRANCHES + 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"
+    },
+    {
         "BriefDescription": "Total pipeline cost of instruction fetch related bottlenecks by large code footprint programs (i-side cache; TLB and BTB misses)",
         "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",
+        "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"
+        "MetricThreshold": "tma_info_bottleneck_big_code > 20"
     },
     {
         "BriefDescription": "Total pipeline cost of branch related instructions (used for program control-flow including function calls)",
-        "MetricExpr": "100 * ((BR_INST_RETIRED.CONDITIONAL + 3 * BR_INST_RETIRED.NEAR_CALL + (BR_INST_RETIRED.NEAR_TAKEN - (BR_INST_RETIRED.CONDITIONAL - BR_INST_RETIRED.NOT_TAKEN) - 2 * BR_INST_RETIRED.NEAR_CALL)) / tma_info_thread_slots)",
-        "MetricGroup": "Ret;tma_issueBC",
+        "MetricExpr": "100 * ((BR_INST_RETIRED.ALL_BRANCHES + 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"
+    },
+    {
+        "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_4k_aliasing + 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"
+    },
+    {
+        "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)))",
+        "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"
+    },
+    {
+        "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: "
     },
     {
         "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_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) - tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * tma_fetch_latency * (tma_ms_switches + tma_branch_resteers * (tma_clears_resteers + tma_mispredicts_resteers * (10 * tma_microcode_sequencer * 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"
     },
     {
-        "BriefDescription": "Total pipeline cost of (external) Memory Bandwidth related bottlenecks",
-        "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_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_4k_aliasing + 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 * (tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * tma_fetch_latency * (tma_ms_switches + tma_branch_resteers * (tma_clears_resteers + tma_mispredicts_resteers * (10 * tma_microcode_sequencer * 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 + tma_core_bound * RS_EVENTS.EMPTY_CYCLES / 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"
     },
     {
         "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_4k_aliasing + 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)))",
+        "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_4k_aliasing + 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)))",
         "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"
     },
     {
-        "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"
+        "BriefDescription": "Total pipeline cost of Memory Synchronization related bottlenecks (data transfers and coherency updates across processors)",
+        "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_remote_cache / (tma_local_mem + tma_remote_cache + tma_remote_mem) + 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_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"
     },
     {
         "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))",
+        "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",
         "PublicDescription": "Total pipeline cost of Branch Misprediction related bottlenecks. Related metrics: tma_branch_mispredicts, tma_info_bad_spec_branch_misprediction_cost, tma_mispredicts_resteers"
     },
     {
+        "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."
+    },
+    {
         "BriefDescription": "Fraction of branches that are CALL or RET",
         "MetricExpr": "(BR_INST_RETIRED.NEAR_CALL + BR_INST_RETIRED.NEAR_RETURN) / BR_INST_RETIRED.ALL_BRANCHES",
         "Met