Skip to contentSkip to conversation

Intel vendor events and TMA 5.02 metrics

PATCH Applied Ian Rogers 4 participants 29 messages Feb 11, 2025 – Feb 13, 2025 Page 2 of 3

Subsystems (2)
lore
Share & tools
lore
author reviewer
#6 lore raw

PATCH v8 6/24 perf vendor events: Update BroadwellX events/metrics

In reply to Ian Rogers

Update events from v22 to v23.
Update TMA metrics from 4.8 to 5.02.

Bring in the event updates v23:
https://github.com/intel/perfmon/commit/679982113f4bfa16cee19d5408a7f8e309e3ac23

The TMA 5.02 update is from (with subsequent fixes):
https://github.com/intel/perfmon/commit/1d72913b2d938781fb28f3cc3507aaec5c22d782

---
 .../arch/x86/broadwellx/bdx-metrics.json      | 344 ++++++++++--------
 .../pmu-events/arch/x86/broadwellx/cache.json |  10 +-
 .../arch/x86/broadwellx/frontend.json         |   4 +-
 .../arch/x86/broadwellx/memory.json           |   6 +-
 .../arch/x86/broadwellx/metricgroups.json     |   5 +
 .../arch/x86/broadwellx/pipeline.json         |  10 +-
 .../arch/x86/broadwellx/uncore-cache.json     |  28 +-
 .../x86/broadwellx/uncore-interconnect.json   |  36 +-
 .../arch/x86/broadwellx/uncore-memory.json    |   1 +
 tools/perf/pmu-events/arch/x86/mapfile.csv    |   2 +-
 10 files changed, 230 insertions(+), 216 deletions(-)
tools/perf/pmu-events/arch/x86/broadwellx/bdx-metrics.json +186 -158
index 0577d7460082..8016202bad1f 100644
@@ -55,7 +55,7 @@
         "MetricName": "UNCORE_FREQ"
     },
     {
-        "BriefDescription": "Cycles per instruction retired; indicating how much time each executed instruction took; in units of cycles.",
+        "BriefDescription": "Cycles per instruction retired; indicating how much time each executed instruction took; in units of cycles",
         "MetricExpr": "CPU_CLK_UNHALTED.THREAD / INST_RETIRED.ANY",
         "MetricName": "cpi",
         "ScaleUnit": "1per_instr"
@@ -76,24 +76,24 @@
         "BriefDescription": "Ratio of number of completed page walks (for all page sizes) caused by demand data loads to the total number of completed instructions",
         "MetricExpr": "DTLB_LOAD_MISSES.WALK_COMPLETED / INST_RETIRED.ANY",
         "MetricName": "dtlb_load_mpi",
-        "PublicDescription": "Ratio of number of completed page walks (for all page sizes) caused by demand data loads to the total number of completed instructions. This implies it missed in the DTLB and further levels of TLB.",
+        "PublicDescription": "Ratio of number of completed page walks (for all page sizes) caused by demand data loads to the total number of completed instructions. This implies it missed in the DTLB and further levels of TLB",
         "ScaleUnit": "1per_instr"
     },
     {
         "BriefDescription": "Ratio of number of completed page walks (for all page sizes) caused by demand data stores to the total number of completed instructions",
         "MetricExpr": "DTLB_STORE_MISSES.WALK_COMPLETED / INST_RETIRED.ANY",
         "MetricName": "dtlb_store_mpi",
-        "PublicDescription": "Ratio of number of completed page walks (for all page sizes) caused by demand data stores to the total number of completed instructions. This implies it missed in the DTLB and further levels of TLB.",
+        "PublicDescription": "Ratio of number of completed page walks (for all page sizes) caused by demand data stores to the total number of completed instructions. This implies it missed in the DTLB and further levels of TLB",
         "ScaleUnit": "1per_instr"
     },
     {
-        "BriefDescription": "Bandwidth of IO reads that are initiated by end device controllers that are requesting memory from the CPU.",
+        "BriefDescription": "Bandwidth of IO reads that are initiated by end device controllers that are requesting memory from the CPU",
         "MetricExpr": "cbox@UNC_C_TOR_INSERTS.OPCODE\\,filter_opc\\=0x19e@ * 64 / 1e6 / duration_time",
         "MetricName": "io_bandwidth_read",
         "ScaleUnit": "1MB/s"
     },
     {
-        "BriefDescription": "Bandwidth of IO writes that are initiated by end device controllers that are writing memory to the CPU.",
+        "BriefDescription": "Bandwidth of IO writes that are initiated by end device controllers that are writing memory to the CPU",
         "MetricExpr": "(cbox@UNC_C_TOR_INSERTS.OPCODE\\,filter_opc\\=0x1c8\\,filter_tid\\=0x3e@ + cbox@UNC_C_TOR_INSERTS.OPCODE\\,filter_opc\\=0x180\\,filter_tid\\=0x3e@) * 64 / 1e6 / duration_time",
         "MetricName": "io_bandwidth_write",
         "ScaleUnit": "1MB/s"
@@ -102,14 +102,14 @@
         "BriefDescription": "Ratio of number of completed page walks (for 2 megabyte and 4 megabyte page sizes) caused by a code fetch to the total number of completed instructions",
         "MetricExpr": "ITLB_MISSES.WALK_COMPLETED_2M_4M / INST_RETIRED.ANY",
         "MetricName": "itlb_large_page_mpi",
-        "PublicDescription": "Ratio of number of completed page walks (for 2 megabyte and 4 megabyte page sizes) caused by a code fetch to the total number of completed instructions. This implies it missed in the Instruction Translation Lookaside Buffer (ITLB) and further levels of TLB.",
+        "PublicDescription": "Ratio of number of completed page walks (for 2 megabyte and 4 megabyte page sizes) caused by a code fetch to the total number of completed instructions. This implies it missed in the Instruction Translation Lookaside Buffer (ITLB) and further levels of TLB",
         "ScaleUnit": "1per_instr"
     },
     {
         "BriefDescription": "Ratio of number of completed page walks (for all page sizes) caused by a code fetch to the total number of completed instructions",
         "MetricExpr": "ITLB_MISSES.WALK_COMPLETED / INST_RETIRED.ANY",
         "MetricName": "itlb_mpi",
-        "PublicDescription": "Ratio of number of completed page walks (for all page sizes) caused by a code fetch to the total number of completed instructions. This implies it missed in the ITLB (Instruction TLB) and further levels of TLB.",
+        "PublicDescription": "Ratio of number of completed page walks (for all page sizes) caused by a code fetch to the total number of completed instructions. This implies it missed in the ITLB (Instruction TLB) and further levels of TLB",
         "ScaleUnit": "1per_instr"
     },
     {
@@ -209,13 +209,13 @@
         "ScaleUnit": "1MB/s"
     },
     {
-        "BriefDescription": "Memory read that miss the last level cache (LLC) addressed to local DRAM as a percentage of total memory read accesses, does not include LLC prefetches.",
+        "BriefDescription": "Memory read that miss the last level cache (LLC) addressed to local DRAM as a percentage of total memory read accesses, does not include LLC prefetches",
         "MetricExpr": "cbox@UNC_C_TOR_INSERTS.MISS_LOCAL_OPCODE\\,filter_opc\\=0x182@ / (cbox@UNC_C_TOR_INSERTS.MISS_LOCAL_OPCODE\\,filter_opc\\=0x182@ + cbox@UNC_C_TOR_INSERTS.MISS_REMOTE_OPCODE\\,filter_opc\\=0x182@)",
         "MetricName": "numa_reads_addressed_to_local_dram",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "Memory reads that miss the last level cache (LLC) addressed to remote DRAM as a percentage of total memory read accesses, does not include LLC prefetches.",
+        "BriefDescription": "Memory reads that miss the last level cache (LLC) addressed to remote DRAM as a percentage of total memory read accesses, does not include LLC prefetches",
         "MetricExpr": "cbox@UNC_C_TOR_INSERTS.MISS_REMOTE_OPCODE\\,filter_opc\\=0x182@ / (cbox@UNC_C_TOR_INSERTS.MISS_LOCAL_OPCODE\\,filter_opc\\=0x182@ + cbox@UNC_C_TOR_INSERTS.MISS_REMOTE_OPCODE\\,filter_opc\\=0x182@)",
         "MetricName": "numa_reads_addressed_to_remote_dram",
         "ScaleUnit": "100%"
@@ -276,12 +276,12 @@
         "MetricExpr": "LD_BLOCKS_PARTIAL.ADDRESS_ALIAS / tma_info_thread_clks",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group",
         "MetricName": "tma_4k_aliasing",
-        "MetricThreshold": "tma_4k_aliasing > 0.2 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
-        "PublicDescription": "This metric estimates how often memory load accesses were aliased by preceding stores (in program order) with a 4K address offset. False match is possible; which incur a few cycles load re-issue. However; the short re-issue duration is often hidden by the out-of-order core and HW optimizations; hence a user may safely ignore a high value of this metric unless it manages to propagate up into parent nodes of the hierarchy (e.g. to L1_Bound).",
+        "MetricThreshold": "tma_4k_aliasing > 0.2 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "PublicDescription": "This metric estimates how often memory load accesses were aliased by preceding stores (in program order) with a 4K address offset. False match is possible; which incur a few cycles load re-issue. However; the short re-issue duration is often hidden by the out-of-order core and HW optimizations; hence a user may safely ignore a high value of this metric unless it manages to propagate up into parent nodes of the hierarchy (e.g. to L1_Bound)",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution ports for ALU operations.",
+        "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution ports for ALU operations",
         "MetricConstraint": "NO_GROUP_EVENTS_NMI",
         "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",
@@ -294,8 +294,8 @@
         "MetricExpr": "66 * OTHER_ASSISTS.ANY_WB_ASSIST / tma_info_thread_slots",
         "MetricGroup": "BvIO;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)",
-        "PublicDescription": "This metric estimates fraction of slots the CPU retired uops delivered by the Microcode_Sequencer as a result of Assists. Assists are long sequences of uops that are required in certain corner-cases for operations that cannot be handled natively by the execution pipeline. For example; when working with very small floating point values (so-called Denormals); the FP units are not set up to perform these operations natively. Instead; a sequence of instructions to perform the computation on the Denormals is injected into the pipeline. Since these microcode sequences might be dozens of uops long; Assists can be extremely deleterious to performance and they can be avoided in many cases. Sample with: OTHER_ASSISTS.ANY",
+        "MetricThreshold": "tma_assists > 0.1 & tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1",
+        "PublicDescription": "This metric estimates fraction of slots the CPU retired uops delivered by the Microcode_Sequencer as a result of Assists. Assists are long sequences of uops that are required in certain corner-cases for operations that cannot be handled natively by the execution pipeline. For example; when working with very small floating point values (so-called Denormals); the FP units are not set up to perform these operations natively. Instead; a sequence of instructions to perform the computation on the Denormals is injected into the pipeline. Since these microcode sequences might be dozens of uops long; Assists can be extremely deleterious to performance and they can be avoided in many cases. Sample with: OTHER_ASSISTS.ANY_WB_ASSIST",
         "ScaleUnit": "100%"
     },
     {
@@ -306,7 +306,7 @@
         "MetricName": "tma_backend_bound",
         "MetricThreshold": "tma_backend_bound > 0.2",
         "MetricgroupNoGroup": "TopdownL1",
-        "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound.",
+        "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound",
         "ScaleUnit": "100%"
     },
     {
@@ -316,7 +316,7 @@
         "MetricName": "tma_bad_speculation",
         "MetricThreshold": "tma_bad_speculation > 0.15",
         "MetricgroupNoGroup": "TopdownL1",
-        "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.",
+        "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example",
         "ScaleUnit": "100%"
     },
     {
@@ -327,7 +327,7 @@
         "MetricName": "tma_branch_mispredicts",
         "MetricThreshold": "tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15",
         "MetricgroupNoGroup": "TopdownL2",
-        "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction.  These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_info_bad_spec_branch_misprediction_cost, tma_mispredicts_resteers",
+        "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction.  These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_mispredicts_resteers",
         "ScaleUnit": "100%"
     },
     {
@@ -335,8 +335,8 @@
         "MetricExpr": "12 * (BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT + BACLEARS.ANY) / tma_info_thread_clks",
         "MetricGroup": "FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group",
         "MetricName": "tma_branch_resteers",
-        "MetricThreshold": "tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)",
-        "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers. Branch Resteers estimates the Frontend delay in fetching operations from corrected path; following all sorts of miss-predicted branches. For example; branchy code with lots of miss-predictions might get categorized under Branch Resteers. Note the value of this node may overlap with its siblings. Sample with: BR_MISP_RETIRED.ALL_BRANCHES",
+        "MetricThreshold": "tma_branch_resteers > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+        "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers. Branch Resteers estimates the Frontend delay in fetching operations from corrected path; following all sorts of miss-predicted branches. For example; branchy code with lots of miss-predictions might get categorized under Branch Resteers. Note the value of this node may overlap with its siblings. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_l3_hit_latency, tma_store_latency",
         "ScaleUnit": "100%"
     },
     {
@@ -345,8 +345,8 @@
         "MetricExpr": "max(0, tma_microcode_sequencer - tma_assists)",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_microcode_sequencer_group",
         "MetricName": "tma_cisc",
-        "MetricThreshold": "tma_cisc > 0.1 & (tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1)",
-        "PublicDescription": "This metric estimates fraction of cycles the CPU retired uops originated from CISC (complex instruction set computer) instruction. A CISC instruction has multiple uops that are required to perform the instruction's functionality as in the case of read-modify-write as an example. Since these instructions require multiple uops they may or may not imply sub-optimal use of machine resources.",
+        "MetricThreshold": "tma_cisc > 0.1 & tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1",
+        "PublicDescription": "This metric estimates fraction of cycles the CPU retired uops originated from CISC (complex instruction set computer) instruction. A CISC instruction has multiple uops that are required to perform the instruction's functionality as in the case of read-modify-write as an example. Since these instructions require multiple uops they may or may not imply sub-optimal use of machine resources",
         "ScaleUnit": "100%"
     },
     {
@@ -354,7 +354,7 @@
         "MetricExpr": "MACHINE_CLEARS.COUNT * tma_branch_resteers / (BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT + BACLEARS.ANY)",
         "MetricGroup": "BadSpec;MachineClears;TopdownL4;tma_L4_group;tma_branch_resteers_group;tma_issueMC",
         "MetricName": "tma_clears_resteers",
-        "MetricThreshold": "tma_clears_resteers > 0.05 & (tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))",
+        "MetricThreshold": "tma_clears_resteers > 0.05 & tma_branch_resteers > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
         "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Machine Clears. Related metrics: tma_l1_bound, tma_machine_clears, tma_microcode_sequencer, tma_ms_switches",
         "ScaleUnit": "100%"
     },
@@ -362,10 +362,10 @@
         "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses",
         "MetricConstraint": "NO_GROUP_EVENTS",
         "MetricExpr": "(60 * (MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.L3_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_L3_MISS_RETIRED.LOCAL_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_HITM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_FWD))) + 43 * (MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.L3_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_L3_MISS_RETIRED.LOCAL_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_HITM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_FWD)))) / tma_info_thread_clks",
-        "MetricGroup": "BvMS;DataSharing;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group",
+        "MetricGroup": "BvMS;DataSharing;LockCont;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))",
-        "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses. Contested accesses occur when data written by one Logical Processor are read by another Logical Processor on a different Physical Core. Examples of contested accesses include synchronizations such as locks; true data sharing such as modified locked variables; and false sharing. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM_PS;MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS_PS. Related metrics: tma_data_sharing, tma_false_sharing, tma_machine_clears, tma_remote_cache",
+        "MetricThreshold": "tma_contested_accesses > 0.05 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses. Contested accesses occur when data written by one Logical Processor are read by another Logical Processor on a different Physical Core. Examples of contested accesses include synchronizations such as locks; true data sharing such as modified locked variables; and false sharing. Sample with: MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM, MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS. Related metrics: tma_data_sharing, tma_false_sharing, tma_machine_clears, tma_remote_cache",
         "ScaleUnit": "100%"
     },
     {
@@ -376,7 +376,7 @@
         "MetricName": "tma_core_bound",
         "MetricThreshold": "tma_core_bound > 0.1 & tma_backend_bound > 0.2",
         "MetricgroupNoGroup": "TopdownL2",
-        "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck.  Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations).",
+        "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck.  Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations)",
         "ScaleUnit": "100%"
     },
     {
@@ -385,8 +385,8 @@
         "MetricExpr": "43 * (MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.L3_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_L3_MISS_RETIRED.LOCAL_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_HITM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_FWD))) / tma_info_thread_clks",
         "MetricGroup": "BvMS;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))",
-        "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses. Data shared by multiple Logical Processors (even just read shared) may cause increased access latency due to cache coherency. Excessive data sharing can drastically harm multithreaded performance. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_HIT_PS. Related metrics: tma_contested_accesses, tma_false_sharing, tma_machine_clears, tma_remote_cache",
+        "MetricThreshold": "tma_data_sharing > 0.05 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses. Data shared by multiple Logical Processors (even just read shared) may cause increased access latency due to cache coherency. Excessive data sharing can drastically harm multithreaded performance. Sample with: MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT. Related metrics: tma_contested_accesses, tma_false_sharing, tma_machine_clears, tma_remote_cache",
         "ScaleUnit": "100%"
     },
     {
@@ -394,8 +394,8 @@
         "MetricExpr": "ARITH.FPU_DIV_ACTIVE / tma_info_core_core_clks",
         "MetricGroup": "BvCB;TopdownL3;tma_L3_group;tma_core_bound_group",
         "MetricName": "tma_divider",
-        "MetricThreshold": "tma_divider > 0.2 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)",
-        "PublicDescription": "This metric represents fraction of cycles where the Divider unit was active. Divide and square root instructions are performed by the Divider unit and can take considerably longer latency than integer or Floating Point addition; subtraction; or multiplication. Sample with: ARITH.DIVIDER_UOPS",
+        "MetricThreshold": "tma_divider > 0.2 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
+        "PublicDescription": "This metric represents fraction of cycles where the Divider unit was active. Divide and square root instructions are performed by the Divider unit and can take considerably longer latency than integer or Floating Point addition; subtraction; or multiplication. Sample with: ARITH.FPU_DIV_ACTIVE",
         "ScaleUnit": "100%"
     },
     {
@@ -404,8 +404,8 @@
         "MetricExpr": "(1 - MEM_LOAD_UOPS_RETIRED.L3_HIT / (MEM_LOAD_UOPS_RETIRED.L3_HIT + 7 * MEM_LOAD_UOPS_RETIRED.L3_MISS)) * CYCLE_ACTIVITY.STALLS_L2_MISS / tma_info_thread_clks",
         "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group",
         "MetricName": "tma_dram_bound",
-        "MetricThreshold": "tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)",
-        "PublicDescription": "This metric estimates how often the CPU was stalled on accesses to external memory (DRAM) by loads. Better caching can improve the latency and increase performance. Sample with: MEM_LOAD_UOPS_RETIRED.L3_MISS_PS",
+        "MetricThreshold": "tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "PublicDescription": "This metric estimates how often the CPU was stalled on accesses to external memory (DRAM) by loads. Better caching can improve the latency and increase performance. Sample with: MEM_LOAD_UOPS_RETIRED.L3_MISS",
         "ScaleUnit": "100%"
     },
     {
@@ -414,7 +414,7 @@
         "MetricGroup": "DSB;FetchBW;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group",
         "MetricName": "tma_dsb",
         "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.",
+        "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%"
     },
     {
@@ -422,45 +422,45 @@
         "MetricExpr": "DSB2MITE_SWITCHES.PENALTY_CYCLES / tma_info_thread_clks",
         "MetricGroup": "DSBmiss;FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueFB",
         "MetricName": "tma_dsb_switches",
-        "MetricThreshold": "tma_dsb_switches > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)",
+        "MetricThreshold": "tma_dsb_switches > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
         "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines. The DSB (decoded i-cache) is a Uop Cache where the front-end directly delivers Uops (micro operations) avoiding heavy x86 decoding. The DSB pipeline has shorter latency and delivered higher bandwidth than the MITE (legacy instruction decode pipeline). Switching between the two pipelines can cause penalties hence this metric measures the exposed penalty. Related metrics: tma_fetch_bandwidth, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses",
-        "MetricExpr": "(8 * DTLB_LOAD_MISSES.STLB_HIT + cpu@DTLB_LOAD_MISSES.WALK_DURATION\\,cmask\\=1@ + 7 * DTLB_LOAD_MISSES.WALK_COMPLETED) / tma_info_thread_clks",
+        "MetricExpr": "(8 * DTLB_LOAD_MISSES.STLB_HIT + cpu@DTLB_LOAD_MISSES.WALK_DURATION\\,cmask\\=0x1@ + 7 * DTLB_LOAD_MISSES.WALK_COMPLETED) / tma_info_thread_clks",
         "MetricGroup": "BvMT;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_UOPS_RETIRED.STLB_MISS_LOADS_PS. Related metrics: tma_dtlb_store",
+        "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_UOPS_RETIRED.STLB_MISS_LOADS. Related metrics: tma_dtlb_store",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses",
-        "MetricExpr": "(8 * DTLB_STORE_MISSES.STLB_HIT + cpu@DTLB_STORE_MISSES.WALK_DURATION\\,cmask\\=1@ + 7 * DTLB_STORE_MISSES.WALK_COMPLETED) / tma_info_thread_clks",
+        "MetricExpr": "(8 * DTLB_STORE_MISSES.STLB_HIT + cpu@DTLB_STORE_MISSES.WALK_DURATION\\,cmask\\=0x1@ + 7 * DTLB_STORE_MISSES.WALK_COMPLETED) / tma_info_thread_clks",
         "MetricGroup": "BvMT;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_UOPS_RETIRED.STLB_MISS_STORES_PS. Related metrics: tma_dtlb_load",
+        "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_UOPS_RETIRED.STLB_MISS_STORES. Related metrics: tma_dtlb_load",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "This metric roughly estimates how often CPU was handling synchronizations due to False Sharing",
         "MetricExpr": "(200 * OFFCORE_RESPONSE.DEMAND_RFO.LLC_MISS.REMOTE_HITM + 60 * OFFCORE_RESPONSE.DEMAND_RFO.LLC_HIT.HITM_OTHER_CORE) / tma_info_thread_clks",
-        "MetricGroup": "BvMS;DataSharing;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_store_bound_group",
+        "MetricGroup": "BvMS;DataSharing;LockCont;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))",
-        "PublicDescription": "This metric roughly estimates how often CPU was handling synchronizations due to False Sharing. False Sharing is a multithreading hiccup; where multiple Logical Processors contend on different data-elements mapped into the same cache line. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM_PS;OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.SNOOP_HITM. Related metrics: tma_contested_accesses, tma_data_sharing, tma_machine_clears, tma_remote_cache",
+        "MetricThreshold": "tma_false_sharing > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "PublicDescription": "This metric roughly estimates how often CPU was handling synchronizations due to False Sharing. False Sharing is a multithreading hiccup; where multiple Logical Processors contend on different data-elements mapped into the same cache line. Sample with: MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM, MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_HITM, OFFCORE_RESPONSE.DEMAND_RFO.LLC_HIT.HITM_OTHER_CORE, OFFCORE_RESPONSE.DEMAND_RFO.LLC_MISS.REMOTE_HITM. Related metrics: tma_contested_accesses, tma_data_sharing, tma_machine_clears, tma_remote_cache",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed",
         "MetricConstraint": "NO_GROUP_EVENTS",
-        "MetricExpr": "tma_info_memory_load_miss_real_latency * cpu@L1D_PEND_MISS.FB_FULL\\,cmask\\=1@ / tma_info_thread_clks",
-        "MetricGroup": "BvMS;MemoryBW;TopdownL4;tma_L4_group;tma_issueBW;tma_issueSL;tma_issueSmSt;tma_l1_bound_group",
+        "MetricExpr": "tma_info_memory_load_miss_real_latency * cpu@L1D_PEND_MISS.FB_FULL\\,cmask\\=0x1@ / tma_info_thread_clks",
+        "MetricGroup": "BvMB;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_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_system_dram_bw_use, tma_mem_bandwidth, tma_sq_full, tma_store_latency",
         "ScaleUnit": "100%"
     },
     {
@@ -489,7 +489,7 @@
         "MetricGroup": "HPC;TopdownL3;tma_L3_group;tma_light_operations_group",
         "MetricName": "tma_fp_arith",
         "MetricThreshold": "tma_fp_arith > 0.2 & tma_light_operations > 0.6",
-        "PublicDescription": "This metric represents overall arithmetic floating-point (FP) operations fraction the CPU has executed (retired). Note this metric's value may exceed its parent due to use of \"Uops\" CountDomain and FMA double-counting.",
+        "PublicDescription": "This metric represents overall arithmetic floating-point (FP) operations fraction the CPU has executed (retired). Note this metric's value may exceed its parent due to use of \"Uops\" CountDomain and FMA double-counting",
         "ScaleUnit": "100%"
     },
     {
@@ -497,8 +497,8 @@
         "MetricExpr": "FP_ARITH_INST_RETIRED.SCALAR / UOPS_RETIRED.RETIRE_SLOTS",
         "MetricGroup": "Compute;Flops;TopdownL4;tma_L4_group;tma_fp_arith_group;tma_issue2P",
         "MetricName": "tma_fp_scalar",
-        "MetricThreshold": "tma_fp_scalar > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6)",
-        "PublicDescription": "This metric approximates arithmetic floating-point (FP) scalar uops fraction the CPU has retired. May overcount due to FMA double counting. Related metrics: tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2",
+        "MetricThreshold": "tma_fp_scalar > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6",
+        "PublicDescription": "This metric approximates arithmetic floating-point (FP) scalar uops fraction the CPU has retired. May overcount due to FMA double counting. Related metrics: tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2",
         "ScaleUnit": "100%"
     },
     {
@@ -506,8 +506,8 @@
         "MetricExpr": "FP_ARITH_INST_RETIRED.VECTOR / UOPS_RETIRED.RETIRE_SLOTS",
         "MetricGroup": "Compute;Flops;TopdownL4;tma_L4_group;tma_fp_arith_group;tma_issue2P",
         "MetricName": "tma_fp_vector",
-        "MetricThreshold": "tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6)",
-        "PublicDescription": "This metric approximates arithmetic floating-point (FP) vector uops fraction the CPU has retired aggregated across all vector widths. May overcount due to FMA double counting. Related metrics: tma_fp_scalar, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2",
+        "MetricThreshold": "tma_fp_vector > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6",
+        "PublicDescription": "This metric approximates arithmetic floating-point (FP) vector uops fraction the CPU has retired aggregated across all vector widths. May overcount due to FMA double counting. Related metrics: tma_fp_scalar, tma_fp_vector_128b, tma_fp_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2",
         "ScaleUnit": "100%"
     },
     {
@@ -515,8 +515,8 @@
         "MetricExpr": "(FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE) / UOPS_RETIRED.RETIRE_SLOTS",
         "MetricGroup": "Compute;Flops;TopdownL5;tma_L5_group;tma_fp_vector_group;tma_issue2P",
         "MetricName": "tma_fp_vector_128b",
-        "MetricThreshold": "tma_fp_vector_128b > 0.1 & (tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6))",
-        "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 128-bit wide vectors. May overcount due to FMA double counting. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2",
+        "MetricThreshold": "tma_fp_vector_128b > 0.1 & tma_fp_vector > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6",
+        "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 128-bit wide vectors. May overcount due to FMA double counting prior to LNL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2",
         "ScaleUnit": "100%"
     },
     {
@@ -524,8 +524,8 @@
         "MetricExpr": "(FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE) / UOPS_RETIRED.RETIRE_SLOTS",
         "MetricGroup": "Compute;Flops;TopdownL5;tma_L5_group;tma_fp_vector_group;tma_issue2P",
         "MetricName": "tma_fp_vector_256b",
-        "MetricThreshold": "tma_fp_vector_256b > 0.1 & (tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6))",
-        "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 256-bit wide vectors. May overcount due to FMA double counting. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2",
+        "MetricThreshold": "tma_fp_vector_256b > 0.1 & tma_fp_vector > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6",
+        "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 256-bit wide vectors. May overcount due to FMA double counting prior to LNL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2",
         "ScaleUnit": "100%"
     },
     {
@@ -535,33 +535,33 @@
         "MetricName": "tma_frontend_bound",
         "MetricThreshold": "tma_frontend_bound > 0.15",
         "MetricgroupNoGroup": "TopdownL1",
-        "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound.",
+        "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences",
+        "BriefDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations , instructions that require two or more uops or micro-coded sequences",
         "MetricExpr": "tma_microcode_sequencer",
         "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group",
         "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. ([ICL+] Note this may overcount due to approximation using indirect events; [ADL+] .)",
+        "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.",
+        "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to instruction cache misses",
         "MetricExpr": "ICACHE.IFDATA_STALL / tma_info_thread_clks",
         "MetricGroup": "BigFootprint;BvBC;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)",
+        "MetricThreshold": "tma_icache_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "Instructions per retired mispredicts for indirect CALL or JMP branches (lower number means higher occurrence rate).",
+        "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 * BR_MISP_EXEC.INDIRECT)",
         "MetricGroup": "Bad;BrMispredicts",
         "MetricName": "tma_info_bad_spec_ipmisp_indirect",
-        "MetricThreshold": "tma_info_bad_spec_ipmisp_indirect < 1e3"
+        "MetricThreshold": "tma_info_bad_spec_ipmisp_indirect < 1000"
     },
     {
         "BriefDescription": "Number of Instructions per non-speculative Branch Misprediction (JEClear) (lower number means higher occurrence rate)",
@@ -572,7 +572,7 @@
     },
     {
         "BriefDescription": "Core actual clocks when any Logical Processor is active on the Physical Core",
-        "MetricExpr": "(CPU_CLK_UNHALTED.THREAD / 2 * (1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK) if #core_wide < 1 else (CPU_CLK_UNHALTED.THREAD_ANY / 2 if #SMT_on else tma_info_thread_clks))",
+        "MetricExpr": "(CPU_CLK_UNHALTED.THREAD_ANY / 2 if #SMT_on else tma_info_thread_clks)",
         "MetricGroup": "SMT",
         "MetricName": "tma_info_core_core_clks"
     },
@@ -593,11 +593,11 @@
         "MetricExpr": "(FP_ARITH_INST_RETIRED.SCALAR + FP_ARITH_INST_RETIRED.VECTOR) / (2 * tma_info_core_core_clks)",
         "MetricGroup": "Cor;Flops;HPC",
         "MetricName": "tma_info_core_fp_arith_utilization",
-        "PublicDescription": "Actual per-core usage of the Floating Point non-X87 execution units (regardless of precision or vector-width). Values > 1 are possible due to ([BDW+] Fused-Multiply Add (FMA) counting - common; [ADL+] use all of ADD/MUL/FMA in Scalar or 128/256-bit vectors - less common)."
+        "PublicDescription": "Actual per-core usage of the Floating Point non-X87 execution units (regardless of precision or vector-width). Values > 1 are possible due to ([BDW+] Fused-Multiply Add (FMA) counting - common; [ADL+] use all of ADD/MUL/FMA in Scalar or 128/256-bit vectors - less common)"
     },
     {
         "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is execution) per thread (logical-processor)",
-        "MetricExpr": "UOPS_EXECUTED.THREAD / cpu@UOPS_EXECUTED.THREAD\\,cmask\\=1@",
+        "MetricExpr": "UOPS_EXECUTED.THREAD / cpu@UOPS_EXECUTED.THREAD\\,cmask\\=0x1@",
         "MetricGroup": "Backend;Cor;Pipeline;PortsUtil",
         "MetricName": "tma_info_core_ilp"
     },
@@ -616,7 +616,13 @@
         "MetricName": "tma_info_frontend_ipunknown_branch"
     },
     {
-        "BriefDescription": "Branch instructions per taken branch.",
+        "BriefDescription": "Taken Branches retired Per Cycle",
+        "MetricExpr": "BR_INST_RETIRED.NEAR_TAKEN / tma_info_thread_clks",
+        "MetricGroup": "Branches;FetchBW",
+        "MetricName": "tma_info_frontend_tbpc"
+    },
+    {
+        "BriefDescription": "Branch instructions per taken branch",
         "MetricExpr": "BR_INST_RETIRED.ALL_BRANCHES / BR_INST_RETIRED.NEAR_TAKEN",
         "MetricGroup": "Branches;Fed;PGO",
         "MetricName": "tma_info_inst_mix_bptkbranch"
@@ -634,7 +640,7 @@
         "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). Values < 1 are possible due to intentional 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"
     },
     {
         "BriefDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number means higher occurrence rate)",
@@ -642,7 +648,7 @@
         "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). Values < 1 are possible due to intentional 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"
     },
     {
         "BriefDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means higher occurrence rate)",
@@ -650,7 +656,7 @@
         "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). Values < 1 are possible due to intentional 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"
     },
     {
         "BriefDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction (lower number means higher occurrence rate)",
@@ -658,7 +664,7 @@
         "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). Values < 1 are possible due to intentional 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"
     },
     {
         "BriefDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction (lower number means higher occurrence rate)",
@@ -666,7 +672,7 @@
         "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). Values < 1 are possible due to intentional 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"
     },
     {
         "BriefDescription": "Instructions per Branch (lower number means higher occurrence rate)",
@@ -708,7 +714,7 @@
         "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_TAKEN",
         "MetricGroup": "Branches;Fed;FetchBW;Frontend;PGO;tma_issueFB",
         "MetricName": "tma_info_inst_mix_iptb",
-        "MetricThreshold": "tma_info_inst_mix_iptb < 9",
+        "MetricThreshold": "tma_info_inst_mix_iptb < 4 * 2 + 1",
         "PublicDescription": "Instructions per taken branch. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_frontend_dsb_coverage, tma_lcp"
     },
     {
@@ -731,7 +737,7 @@
     },
     {
         "BriefDescription": "Average per-thread data fill bandwidth to the L1 data cache [GB / sec]",
-        "MetricExpr": "64 * L1D.REPLACEMENT / 1e9 / duration_time",
+        "MetricExpr": "64 * L1D.REPLACEMENT / 1e9 / tma_info_system_time",
         "MetricGroup": "Mem;MemoryBW",
         "MetricName": "tma_info_memory_l1d_cache_fill_bw"
     },
@@ -743,7 +749,7 @@
     },
     {
         "BriefDescription": "Average per-thread data fill bandwidth to the L2 cache [GB / sec]",
-        "MetricExpr": "64 * L2_LINES_IN.ALL / 1e9 / duration_time",
+        "MetricExpr": "64 * L2_LINES_IN.ALL / 1e9 / tma_info_system_time",
         "MetricGroup": "Mem;MemoryBW",
         "MetricName": "tma_info_memory_l2_cache_fill_bw"
     },
@@ -785,7 +791,7 @@
     },
     {
         "BriefDescription": "Average per-thread data fill bandwidth to the L3 cache [GB / sec]",
-        "MetricExpr": "64 * LONGEST_LAT_CACHE.MISS / 1e9 / duration_time",
+        "MetricExpr": "64 * LONGEST_LAT_CACHE.MISS / 1e9 / tma_info_system_time",
         "MetricGroup": "Mem;MemoryBW",
         "MetricName": "tma_info_memory_l3_cache_fill_bw"
     },
@@ -804,7 +810,7 @@
     {
         "BriefDescription": "Average Latency for L2 cache miss demand Loads",
         "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD / OFFCORE_REQUESTS.DEMAND_DATA_RD",
-        "MetricGroup": "Memory_Lat;Offcore",
+        "MetricGroup": "LockCont;Memory_Lat;Offcore",
         "MetricName": "tma_info_memory_latency_load_l2_miss_latency"
     },
     {
@@ -837,19 +843,19 @@
     },
     {
         "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is execution) per core",
-        "MetricExpr": "UOPS_EXECUTED.THREAD / (cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ / 2 if #SMT_on else UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC)",
+        "MetricExpr": "UOPS_EXECUTED.THREAD / (cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x1@ / 2 if #SMT_on else UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC)",
         "MetricGroup": "Cor;Pipeline;PortsUtil;SMT",
         "MetricName": "tma_info_pipeline_execute"
     },
     {
-        "BriefDescription": "Average number of Uops retired in cycles where at least one uop has retired.",
-        "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / cpu@UOPS_RETIRED.RETIRE_SLOTS\\,cmask\\=1@",
+        "BriefDescription": "Average number of Uops retired in cycles where at least one uop has retired",
+        "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / cpu@UOPS_RETIRED.RETIRE_SLOTS\\,cmask\\=0x1@",
         "MetricGroup": "Pipeline;Ret",
         "MetricName": "tma_info_pipeline_retire"
     },
     {
         "BriefDescription": "Measured Average Core Frequency for unhalted processors [GHz]",
-        "MetricExpr": "tma_info_system_turbo_utilization * TSC / 1e9 / duration_time",
+        "MetricExpr": "tma_info_system_turbo_utilization * TSC / 1e9 / tma_info_system_time",
         "MetricGroup": "Power;Summary",
         "MetricName": "tma_info_system_core_frequency"
     },
@@ -867,14 +873,14 @@
     },
     {
         "BriefDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]",
-        "MetricExpr": "64 * (UNC_M_CAS_COUNT.RD + UNC_M_CAS_COUNT.WR) / 1e9 / duration_time",
+        "MetricExpr": "64 * (UNC_M_CAS_COUNT.RD + UNC_M_CAS_COUNT.WR) / 1e9 / tma_info_system_time",
         "MetricGroup": "HPC;MemOffcore;MemoryBW;SoC;tma_issueBW",
         "MetricName": "tma_info_system_dram_bw_use",
         "PublicDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]. Related metrics: tma_fb_full, tma_mem_bandwidth, tma_sq_full"
     },
     {
         "BriefDescription": "Giga Floating Point Operations Per Second",
-        "MetricExpr": "(FP_ARITH_INST_RETIRED.SCALAR + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * FP_ARITH_INST_RETIRED.4_FLOPS + 8 * FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE) / 1e9 / duration_time",
+        "MetricExpr": "(FP_ARITH_INST_RETIRED.SCALAR + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * FP_ARITH_INST_RETIRED.4_FLOPS + 8 * FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE) / 1e9 / tma_info_system_time",
         "MetricGroup": "Cor;Flops;HPC",
         "MetricName": "tma_info_system_gflops",
         "PublicDescription": "Giga Floating Point Operations Per Second. Aggregate across all supported options of: FP precisions, scalar and vector instructions, vector-width"
@@ -884,13 +890,14 @@
         "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.FAR_BRANCH:u",
         "MetricGroup": "Branches;OS",
         "MetricName": "tma_info_system_ipfarbranch",
-        "MetricThreshold": "tma_info_system_ipfarbranch < 1e6"
+        "MetricThreshold": "tma_info_system_ipfarbranch < 1000000"
     },
     {
         "BriefDescription": "Cycles Per Instruction for the Operating System (OS) Kernel mode",
         "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P:k / INST_RETIRED.ANY_P:k",
         "MetricGroup": "OS",
-        "MetricName": "tma_info_system_kernel_cpi"
+        "MetricName": "tma_info_system_kernel_cpi",
+        "ScaleUnit": "1per_instr"
     },
     {
         "BriefDescription": "Fraction of cycles spent in the Operating System (OS) Kernel mode",
@@ -901,18 +908,31 @@
     },
     {
         "BriefDescription": "Average number of parallel data read requests to external memory",
-        "MetricExpr": "UNC_C_TOR_OCCUPANCY.MISS_OPCODE@filter_opc\\=0x182@ / UNC_C_TOR_OCCUPANCY.MISS_OPCODE@filter_opc\\=0x182\\,thresh\\=1@",
+        "MetricExpr": "cbox@UNC_C_TOR_OCCUPANCY.MISS_OPCODE\\,filter_opc\\=0x182@ / cbox@UNC_C_TOR_OCCUPANCY.MISS_OPCODE\\,filter_opc\\=0x182@",
         "MetricGroup": "Mem;MemoryBW;SoC",
         "MetricName": "tma_info_system_mem_parallel_reads",
         "PublicDescription": "Average number of parallel data read requests to external memory. Accounts for demand loads and L1/L2 prefetches"
     },
     {
         "BriefDescription": "Average latency of data read request to external memory (in nanoseconds)",
-        "MetricExpr": "1e9 * (UNC_C_TOR_OCCUPANCY.MISS_OPCODE@filter_opc\\=0x182@ / UNC_C_TOR_INSERTS.MISS_OPCODE@filter_opc\\=0x182@) / (tma_info_system_socket_clks / duration_time)",
+        "MetricExpr": "1e9 * (cbox@UNC_C_TOR_OCCUPANCY.MISS_OPCODE\\,filter_opc\\=0x182@ / cbox@UNC_C_TOR_INSERTS.MISS_OPCODE\\,filter_opc\\=0x182@) / (tma_info_system_socket_clks / tma_info_system_time)",
         "MetricGroup": "Mem;MemoryLat;SoC",
         "MetricName": "tma_info_system_mem_read_latency",
         "PublicDescription": "Average latency of data read request to external memory (in nanoseconds). Accounts for demand loads and L1/L2 prefetches. ([RKL+]memory-controller only)"
     },
+    {
+        "BriefDescription": "PerfMon Event Multiplexing accuracy indicator",
+        "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P / CPU_CLK_UNHALTED.THREAD",
+        "MetricGroup": "Summary",
+        "MetricName": "tma_info_system_mux",
+        "MetricThreshold": "tma_info_system_mux > 1.1 | tma_info_system_mux < 0.9"
+    },
+    {
+        "BriefDescription": "Total package Power in Watts",
+        "MetricExpr": "(power@energy\\-pkg@ * 61 + 15.6 * power@energy\\-ram@) / (duration_time * 1e6)",
+        "MetricGroup": "Power;SoC",
+        "MetricName": "tma_info_system_power"
+    },
     {
         "BriefDescription": "Fraction of cycles where both hardware Logical Processors were active",
         "MetricExpr": "(1 - CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / (CPU_CLK_UNHALTED.REF_XCLK_ANY / 2) if #SMT_on else 0)",
@@ -925,6 +945,13 @@
         "MetricGroup": "SoC",
         "MetricName": "tma_info_system_socket_clks"
     },
+    {
+        "BriefDescription": "Run duration time in seconds",
+        "MetricExpr": "duration_time",
+        "MetricGroup": "Summary",
+        "MetricName": "tma_info_system_time",
+        "MetricThreshold": "tma_info_system_time < 1"
+    },
     {
         "BriefDescription": "Average Frequency Utilization relative nominal frequency",
         "MetricExpr": "tma_info_thread_clks / CPU_CLK_UNHALTED.REF_TSC",
@@ -933,12 +960,12 @@
     },
     {
         "BriefDescription": "Measured Average Uncore Frequency for the SoC [GHz]",
-        "MetricExpr": "tma_info_system_socket_clks / 1e9 / duration_time",
+        "MetricExpr": "tma_info_system_socket_clks / 1e9 / tma_info_system_time",
         "MetricGroup": "SoC",
         "MetricName": "tma_info_system_uncore_frequency"
     },
     {
-        "BriefDescription": "Per-Logical Processor actual clocks when the Logical Processor is active.",
+        "BriefDescription": "Per-Logical Processor actual clocks when the Logical Processor is active",
         "MetricExpr": "CPU_CLK_UNHALTED.THREAD",
         "MetricGroup": "Pipeline",
         "MetricName": "tma_info_thread_clks"
@@ -947,14 +974,15 @@
         "BriefDescription": "Cycles Per Instruction (per Logical Processor)",
         "MetricExpr": "1 / tma_info_thread_ipc",
         "MetricGroup": "Mem;Pipeline",
-        "MetricName": "tma_info_thread_cpi"
+        "MetricName": "tma_info_thread_cpi",
+        "ScaleUnit": "1per_instr"
     },
     {
         "BriefDescription": "The ratio of Executed- by Issued-Uops",
         "MetricExpr": "UOPS_EXECUTED.THREAD / UOPS_ISSUED.ANY",
         "MetricGroup": "Cor;Pipeline",
         "MetricName": "tma_info_thread_execute_per_issue",
-        "PublicDescription": "The ratio of Executed- by Issued-Uops. Ratio > 1 suggests high rate of uop micro-fusions. Ratio < 1 suggest high rate of \"execute\" at rename stage."
+        "PublicDescription": "The ratio of Executed- by Issued-Uops. Ratio > 1 suggests high rate of uop micro-fusions. Ratio < 1 suggest high rate of \"execute\" at rename stage"
     },
     {
         "BriefDescription": "Instructions Per Cycle (per Logical Processor)",
@@ -980,24 +1008,24 @@
         "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / BR_INST_RETIRED.NEAR_TAKEN",
         "MetricGroup": "Branches;Fed;FetchBW",
         "MetricName": "tma_info_thread_uptb",
-        "MetricThreshold": "tma_info_thread_uptb < 6"
+        "MetricThreshold": "tma_info_thread_uptb < 4 * 1.5"
     },
     {
         "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to Instruction TLB (ITLB) misses",
-        "MetricExpr": "(14 * ITLB_MISSES.STLB_HIT + cpu@ITLB_MISSES.WALK_DURATION\\,cmask\\=1@ + 7 * ITLB_MISSES.WALK_COMPLETED) / tma_info_thread_clks",
+        "MetricExpr": "(14 * ITLB_MISSES.STLB_HIT + cpu@ITLB_MISSES.WALK_DURATION\\,cmask\\=0x1@ + 7 * ITLB_MISSES.WALK_COMPLETED) / tma_info_thread_clks",
         "MetricGroup": "BigFootprint;BvBC;FetchLat;MemoryTLB;TopdownL3;tma_L3_group;tma_fetch_latency_group",
         "MetricName": "tma_itlb_misses",
-        "MetricThreshold": "tma_itlb_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)",
+        "MetricThreshold": "tma_itlb_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 TLB (ITLB) misses. Sample with: ITLB_MISSES.WALK_COMPLETED",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric estimates how often the CPU was stalled without loads missing the L1 data cache",
+        "BriefDescription": "This metric estimates how often the CPU was stalled without loads missing the L1 Data (L1D) cache",
         "MetricExpr": "max((CYCLE_ACTIVITY.STALLS_MEM_ANY - CYCLE_ACTIVITY.STALLS_L1D_MISS) / tma_info_thread_clks, 0)",
         "MetricGroup": "CacheHits;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_issueL1;tma_issueMC;tma_memory_bound_group",
         "MetricName": "tma_l1_bound",
-        "MetricThreshold": "tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)",
-        "PublicDescription": "This metric estimates how often the CPU was stalled without loads missing the L1 data cache.  The L1 data cache typically has the shortest latency.  However; in certain cases like loads blocked on older stores; a load might suffer due to high latency even though it is being satisfied by the L1. Another example is loads who miss in the TLB. These cases are characterized by execution unit stalls; while some non-completed demand load lives in the machine without having that demand load missing the L1 cache. Sample with: MEM_LOAD_UOPS_RETIRED.L1_HIT_PS;MEM_LOAD_UOPS_RETIRED.HIT_LFB_PS. Related metrics: tma_clears_resteers, tma_machine_clears, tma_microcode_sequencer, tma_ms_switches, tma_ports_utilized_1",
+        "MetricThreshold": "tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "PublicDescription": "This metric estimates how often the CPU was stalled without loads missing the L1 Data (L1D) cache.  The L1D cache typically has the shortest latency.  However; in certain cases like loads blocked on older stores; a load might suffer due to high latency even though it is being satisfied by the L1D. Another example is loads who miss in the TLB. These cases are characterized by execution unit stalls; while some non-completed demand load lives in the machine without having that demand load missing the L1 cache. Sample with: MEM_LOAD_UOPS_RETIRED.L1_HIT. Related metrics: tma_clears_resteers, tma_machine_clears, tma_microcode_sequencer, tma_ms_switches, tma_ports_utilized_1",
         "ScaleUnit": "100%"
     },
     {
@@ -1005,8 +1033,8 @@
         "MetricExpr": "(CYCLE_ACTIVITY.STALLS_L1D_MISS - CYCLE_ACTIVITY.STALLS_L2_MISS) / tma_info_thread_clks",
         "MetricGroup": "BvML;CacheHits;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group",
         "MetricName": "tma_l2_bound",
-        "MetricThreshold": "tma_l2_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)",
-        "PublicDescription": "This metric estimates how often the CPU was stalled due to L2 cache accesses by loads.  Avoiding cache misses (i.e. L1 misses/L2 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_UOPS_RETIRED.L2_HIT_PS",
+        "MetricThreshold": "tma_l2_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "PublicDescription": "This metric estimates how often the CPU was stalled due to L2 cache accesses by loads.  Avoiding cache misses (i.e. L1 misses/L2 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_UOPS_RETIRED.L2_HIT",
         "ScaleUnit": "100%"
     },
     {
@@ -1015,8 +1043,8 @@
         "MetricExpr": "MEM_LOAD_UOPS_RETIRED.L3_HIT / (MEM_LOAD_UOPS_RETIRED.L3_HIT + 7 * MEM_LOAD_UOPS_RETIRED.L3_MISS) * CYCLE_ACTIVITY.STALLS_L2_MISS / tma_info_thread_clks",
         "MetricGroup": "CacheHits;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group",
         "MetricName": "tma_l3_bound",
-        "MetricThreshold": "tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)",
-        "PublicDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core.  Avoiding cache misses (i.e. L2 misses/L3 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_UOPS_RETIRED.L3_HIT_PS",
+        "MetricThreshold": "tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "PublicDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core.  Avoiding cache misses (i.e. L2 misses/L3 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_UOPS_RETIRED.L3_HIT",
         "ScaleUnit": "100%"
     },
     {
@@ -1025,8 +1053,8 @@
         "MetricExpr": "41 * (MEM_LOAD_UOPS_RETIRED.L3_HIT * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.L3_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_L3_MISS_RETIRED.LOCAL_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_HITM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_FWD))) / tma_info_thread_clks",
         "MetricGroup": "BvML;MemoryLat;TopdownL4;tma_L4_group;tma_issueLat;tma_l3_bound_group",
         "MetricName": "tma_l3_hit_latency",
-        "MetricThreshold": "tma_l3_hit_latency > 0.1 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
-        "PublicDescription": "This metric estimates fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited).  Avoiding private cache misses (i.e. L2 misses/L3 hits) will improve the latency; reduce contention with sibling physical cores and increase performance.  Note the value of this node may overlap with its siblings. Sample with: MEM_LOAD_UOPS_RETIRED.L3_HIT_PS. Related metrics: tma_mem_latency",
+        "MetricThreshold": "tma_l3_hit_latency > 0.1 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "PublicDescription": "This metric estimates fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited).  Avoiding private cache misses (i.e. L2 misses/L3 hits) will improve the latency; reduce contention with sibling physical cores and increase performance.  Note the value of this node may overlap with its siblings. Sample with: MEM_LOAD_UOPS_RETIRED.L3_HIT. Related metrics: tma_branch_resteers, tma_mem_latency, tma_store_latency",
         "ScaleUnit": "100%"
     },
     {
@@ -1034,18 +1062,18 @@
         "MetricExpr": "ILD_STALL.LCP / tma_info_thread_clks",
         "MetricGroup": "FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueFB",
         "MetricName": "tma_lcp",
-        "MetricThreshold": "tma_lcp > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)",
-        "PublicDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs). Using proper compiler flags or Intel Compiler by default will certainly avoid this. #Link: Optimization Guide about LCP BKMs. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb",
+        "MetricThreshold": "tma_lcp > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+        "PublicDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs). Using proper compiler flags or Intel Compiler by default will certainly avoid this. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation)",
+        "BriefDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations , instructions that require no more than one uop (micro-operation)",
         "MetricExpr": "tma_retiring - tma_heavy_operations",
         "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group",
         "MetricName": "tma_light_operations",
         "MetricThreshold": "tma_light_operations > 0.6",
         "MetricgroupNoGroup": "TopdownL2",
-        "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized code running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. ([ICL+] Note this may undercount due to approximation using indirect events; [ADL+] .). Sample with: INST_RETIRED.PREC_DIST",
+        "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations , instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized code running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. ([ICL+] Note this may undercount due to approximation using indirect events; [ADL+] .). Sample with: INST_RETIRED.PREC_DIST",
         "ScaleUnit": "100%"
     },
     {
@@ -1063,18 +1091,18 @@
         "MetricExpr": "200 * (MEM_LOAD_UOPS_L3_MISS_RETIRED.LOCAL_DRAM * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.L3_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_L3_MISS_RETIRED.LOCAL_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_HITM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_FWD))) / tma_info_thread_clks",
         "MetricGroup": "Server;TopdownL5;tma_L5_group;tma_mem_latency_group",
         "MetricName": "tma_local_mem",
-        "MetricThreshold": "tma_local_mem > 0.1 & (tma_mem_latency > 0.1 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))",
-        "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from local memory. Caching will improve the latency and increase performance. Sample with: MEM_LOAD_UOPS_L3_MISS_RETIRED.LOCAL_DRAM_PS",
+        "MetricThreshold": "tma_local_mem > 0.1 & tma_mem_latency > 0.1 & tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from local memory. Caching will improve the latency and increase performance. Sample with: MEM_LOAD_UOPS_L3_MISS_RETIRED.LOCAL_DRAM",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "This metric represents fraction of cycles the CPU spent handling cache misses due to lock operations",
         "MetricConstraint": "NO_GROUP_EVENTS",
         "MetricExpr": "MEM_UOPS_RETIRED.LOCK_LOADS / MEM_UOPS_RETIRED.ALL_STORES * min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO) / tma_info_thread_clks",
-        "MetricGroup": "Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_l1_bound_group",
+        "MetricGroup": "LockCont;Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_l1_bound_group",
         "MetricName": "tma_lock_latency",
-        "MetricThreshold": "tma_lock_latency > 0.2 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
-        "PublicDescription": "This metric represents fraction of cycles the CPU spent handling cache misses due to lock operations. Due to the microarchitecture handling of locks; they are classified as L1_Bound regardless of what memory source satisfied them. Sample with: MEM_UOPS_RETIRED.LOCK_LOADS_PS. Related metrics: tma_store_latency",
+        "MetricThreshold": "tma_lock_latency > 0.2 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "PublicDescription": "This metric represents fraction of cycles the CPU spent handling cache misses due to lock operations. Due to the microarchitecture handling of locks; they are classified as L1_Bound regardless of what memory source satisfied them. Sample with: MEM_UOPS_RETIRED.LOCK_LOADS. Related metrics: tma_store_latency",
         "ScaleUnit": "100%"
     },
     {
@@ -1090,10 +1118,10 @@
     },
     {
         "BriefDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory - DRAM ([SPR-HBM] and/or HBM)",
-        "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, cpu@OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD\\,cmask\\=4@) / tma_info_thread_clks",
-        "MetricGroup": "BvMS;MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueBW",
+        "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, cpu@OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD\\,cmask\\=0x4@) / tma_info_thread_clks",
+        "MetricGroup": "BvMB;MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueBW",
         "MetricName": "tma_mem_bandwidth",
-        "MetricThreshold": "tma_mem_bandwidth > 0.2 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+        "MetricThreshold": "tma_mem_bandwidth > 0.2 & tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
         "PublicDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory - DRAM ([SPR-HBM] and/or HBM).  The underlying heuristic assumes that a similar off-core traffic is generated by all IA cores. This metric does not aggregate non-data-read requests by this logical processor; requests from other IA Logical Processors/Physical Cores/sockets; or other non-IA devices like GPU; hence the maximum external memory bandwidth limits may or may not be approached when this metric is flagged (see Uncore counters for that). Related metrics: tma_fb_full, tma_info_system_dram_bw_use, tma_sq_full",
         "ScaleUnit": "100%"
     },
@@ -1102,7 +1130,7 @@
         "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD) / tma_info_thread_clks - tma_mem_bandwidth",
         "MetricGroup": "BvML;MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueLat",
         "MetricName": "tma_mem_latency",
-        "MetricThreshold": "tma_mem_latency > 0.1 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+        "MetricThreshold": "tma_mem_latency > 0.1 & tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
         "PublicDescription": "This metric estimates fraction of cycles where the performance was likely hurt due to latency from external memory - DRAM ([SPR-HBM] and/or HBM).  This metric does not aggregate requests from other Logical Processors/Physical Cores/sockets (see Uncore counters for that). Related metrics: tma_l3_hit_latency",
         "ScaleUnit": "100%"
     },
@@ -1114,7 +1142,7 @@
         "MetricName": "tma_memory_bound",
         "MetricThreshold": "tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
         "MetricgroupNoGroup": "TopdownL2",
-        "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck.  Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two).",
+        "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck.  Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two)",
         "ScaleUnit": "100%"
     },
     {
@@ -1131,8 +1159,8 @@
         "MetricExpr": "BR_MISP_RETIRED.ALL_BRANCHES * tma_branch_resteers / (BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT + BACLEARS.ANY)",
         "MetricGroup": "BadSpec;BrMispredicts;BvMP;TopdownL4;tma_L4_group;tma_branch_resteers_group;tma_issueBM",
         "MetricName": "tma_mispredicts_resteers",
-        "MetricThreshold": "tma_mispredicts_resteers > 0.05 & (tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))",
-        "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Branch Misprediction at execution stage. Related metrics: tma_branch_mispredicts, tma_info_bad_spec_branch_misprediction_cost",
+        "MetricThreshold": "tma_mispredicts_resteers > 0.05 & tma_branch_resteers > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+        "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Branch Misprediction at execution stage. Related metrics: tma_branch_mispredicts",
         "ScaleUnit": "100%"
     },
     {
@@ -1141,7 +1169,7 @@
         "MetricGroup": "DSBmiss;FetchBW;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group",
         "MetricName": "tma_mite",
         "MetricThreshold": "tma_mite > 0.1 & tma_fetch_bandwidth > 0.2",
-        "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to the MITE pipeline (the legacy decode pipeline). This pipeline is used for code that was not pre-cached in the DSB or LSD. For example; inefficiencies due to asymmetric decoders; use of long immediate or LCP can manifest as MITE fetch bandwidth bottleneck.",
+        "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to the MITE pipeline (the legacy decode pipeline). This pipeline is used for code that was not pre-cached in the DSB or LSD. For example; inefficiencies due to asymmetric decoders; use of long immediate or LCP can manifest as MITE fetch bandwidth bottleneck",
         "ScaleUnit": "100%"
     },
     {
@@ -1149,8 +1177,8 @@
         "MetricExpr": "2 * IDQ.MS_SWITCHES / tma_info_thread_clks",
         "MetricGroup": "FetchLat;MicroSeq;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueMC;tma_issueMS;tma_issueMV;tma_issueSO",
         "MetricName": "tma_ms_switches",
-        "MetricThreshold": "tma_ms_switches > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)",
-        "PublicDescription": "This metric estimates the fraction of cycles when the CPU was stalled due to switches of uop delivery to the Microcode Sequencer (MS). Commonly used instructions are optimized for delivery by the DSB (decoded i-cache) or MITE (legacy instruction decode) pipelines. Certain operations cannot be handled natively by the execution pipeline; and must be performed by microcode (small programs injected into the execution stream). Switching to the MS too often can negatively impact performance. The MS is designated to deliver long uop flows required by CISC instructions like CPUID; or uncommon conditions like Floating Point Assists when dealing with Denormals. Sample with: IDQ.MS_SWITCHES. Related metrics: tma_clears_resteers, tma_l1_bound, tma_machine_clears, tma_microcode_sequencer, tma_mixing_vectors, tma_serializing_operation",
+        "MetricThreshold": "tma_ms_switches > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+        "PublicDescription": "This metric estimates the fraction of cycles when the CPU was stalled due to switches of uop delivery to the Microcode Sequencer (MS). Commonly used instructions are optimized for delivery by the DSB (decoded i-cache) or MITE (legacy instruction decode) pipelines. Certain operations cannot be handled natively by the execution pipeline; and must be performed by microcode (small programs injected into the execution stream). Switching to the MS too often can negatively impact performance. The MS is designated to deliver long uop flows required by CISC instructions like CPUID; or uncommon conditions like Floating Point Assists when dealing with Denormals. Sample with: IDQ.MS_SWITCHES. Related metrics: tma_clears_resteers, tma_l1_bound, tma_machine_clears, tma_microcode_sequencer",
         "ScaleUnit": "100%"
     },
     {
@@ -1159,7 +1187,7 @@
         "MetricGroup": "Compute;TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P",
         "MetricName": "tma_port_0",
         "MetricThreshold": "tma_port_0 > 0.6",
-        "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 0 ([SNB+] ALU; [HSW+] ALU and 2nd branch). Sample with: UOPS_DISPATCHED_PORT.PORT_0. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2",
+        "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 0 ([SNB+] ALU; [HSW+] ALU and 2nd branch). Sample with: UOPS_DISPATCHED_PORT.PORT_0. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2",
         "ScaleUnit": "100%"
     },
     {
@@ -1168,7 +1196,7 @@
         "MetricGroup": "TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P",
         "MetricName": "tma_port_1",
         "MetricThreshold": "tma_port_1 > 0.6",
-        "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 1 (ALU). Sample with: UOPS_DISPATCHED_PORT.PORT_1. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_5, tma_port_6, tma_ports_utilized_2",
+        "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 1 (ALU). Sample with: UOPS_DISPATCHED_PORT.PORT_1. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_port_0, tma_port_5, tma_port_6, tma_ports_utilized_2",
         "ScaleUnit": "100%"
     },
     {
@@ -1204,7 +1232,7 @@
         "MetricGroup": "TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P",
         "MetricName": "tma_port_5",
         "MetricThreshold": "tma_port_5 > 0.6",
-        "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 5 ([SNB+] Branches and ALU; [HSW+] ALU). Sample with: UOPS_DISPATCHED.PORT_5. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_6, tma_ports_utilized_2",
+        "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 5 ([SNB+] Branches and ALU; [HSW+] ALU). Sample with: UOPS_DISPATCHED_PORT.PORT_5. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_port_0, tma_port_1, tma_port_6, tma_ports_utilized_2",
         "ScaleUnit": "100%"
     },
     {
@@ -1213,7 +1241,7 @@
         "MetricGroup": "TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P",
         "MetricName": "tma_port_6",
         "MetricThreshold": "tma_port_6 > 0.6",
-        "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 6 ([HSW+] Primary Branch and simple ALU). Sample with: UOPS_DISPATCHED_PORT.PORT_6. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_ports_utilized_2",
+        "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 6 ([HSW+] Primary Branch and simple ALU). Sample with: UOPS_DISPATCHED_PORT.PORT_1. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_ports_utilized_2",
         "ScaleUnit": "100%"
     },
     {
@@ -1231,43 +1259,43 @@
         "MetricExpr": "(CYCLE_ACTIVITY.STALLS_TOTAL + UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC - (UOPS_EXECUTED.CYCLES_GE_3_UOPS_EXEC if tma_info_thread_ipc > 1.8 else UOPS_EXECUTED.CYCLES_GE_2_UOPS_EXEC) - (RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else 0) + RESOURCE_STALLS.SB - RESOURCE_STALLS.SB - CYCLE_ACTIVITY.STALLS_MEM_ANY) / tma_info_thread_clks",
         "MetricGroup": "PortsUtil;TopdownL3;tma_L3_group;tma_core_bound_group",
         "MetricName": "tma_ports_utilization",
-        "MetricThreshold": "tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)",
-        "PublicDescription": "This metric estimates fraction of cycles the CPU performance was potentially limited due to Core computation issues (non divider-related).  Two distinct categories can be attributed into this metric: (1) heavy data-dependency among contiguous instructions would manifest in this metric - such cases are often referred to as low Instruction Level Parallelism (ILP). (2) Contention on some hardware execution unit other than Divider. For example; when there are too many multiply operations.",
+        "MetricThreshold": "tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
+        "PublicDescription": "This metric estimates fraction of cycles the CPU performance was potentially limited due to Core computation issues (non divider-related).  Two distinct categories can be attributed into this metric: (1) heavy data-dependency among contiguous instructions would manifest in this metric - such cases are often referred to as low Instruction Level Parallelism (ILP). (2) Contention on some hardware execution unit other than Divider. For example; when there are too many multiply operations",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "This metric represents fraction of cycles CPU executed no uops on any execution port (Logical Processor cycles since ICL, Physical Core cycles otherwise)",
-        "MetricExpr": "(cpu@UOPS_EXECUTED.CORE\\,inv\\,cmask\\=1@ / 2 if #SMT_on else (CYCLE_ACTIVITY.STALLS_TOTAL - (RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else 0)) / tma_info_core_core_clks)",
+        "MetricExpr": "(cpu@UOPS_EXECUTED.CORE\\,inv\\=0x1\\,cmask\\=0x1@ / 2 if #SMT_on else CYCLE_ACTIVITY.STALLS_TOTAL - (RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else 0)) / tma_info_core_core_clks",
         "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group",
         "MetricName": "tma_ports_utilized_0",
-        "MetricThreshold": "tma_ports_utilized_0 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))",
-        "PublicDescription": "This metric represents fraction of cycles CPU executed no uops on any execution port (Logical Processor cycles since ICL, Physical Core cycles otherwise). Long-latency instructions like divides may contribute to this metric.",
+        "MetricThreshold": "tma_ports_utilized_0 > 0.2 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
+        "PublicDescription": "This metric represents fraction of cycles CPU executed no uops on any execution port (Logical Processor cycles since ICL, Physical Core cycles otherwise). Long-latency instructions like divides may contribute to this metric",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "This metric represents fraction of cycles where the CPU executed total of 1 uop per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise)",
-        "MetricExpr": "((cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ - cpu@UOPS_EXECUTED.CORE\\,cmask\\=2@) / 2 if #SMT_on else (UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC - UOPS_EXECUTED.CYCLES_GE_2_UOPS_EXEC) / tma_info_core_core_clks)",
+        "MetricExpr": "((cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x1@ - cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x2@) / 2 if #SMT_on else UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC - UOPS_EXECUTED.CYCLES_GE_2_UOPS_EXEC) / tma_info_core_core_clks",
         "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_issueL1;tma_ports_utilization_group",
         "MetricName": "tma_ports_utilized_1",
-        "MetricThreshold": "tma_ports_utilized_1 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))",
+        "MetricThreshold": "tma_ports_utilized_1 > 0.2 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
         "PublicDescription": "This metric represents fraction of cycles where the CPU executed total of 1 uop per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise). This can be due to heavy data-dependency among software instructions; or over oversubscribing a particular hardware resource. In some other cases with high 1_Port_Utilized and L1_Bound; this metric can point to L1 data-cache latency bottleneck that may not necessarily manifest with complete execution starvation (due to the short L1 latency e.g. walking a linked list) - looking at the assembly can be helpful. Related metrics: tma_l1_bound",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "This metric represents fraction of cycles CPU executed total of 2 uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise)",
-        "MetricExpr": "((cpu@UOPS_EXECUTED.CORE\\,cmask\\=2@ - cpu@UOPS_EXECUTED.CORE\\,cmask\\=3@) / 2 if #SMT_on else (UOPS_EXECUTED.CYCLES_GE_2_UOPS_EXEC - UOPS_EXECUTED.CYCLES_GE_3_UOPS_EXEC) / tma_info_core_core_clks)",
+        "MetricExpr": "((cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x2@ - cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x3@) / 2 if #SMT_on else UOPS_EXECUTED.CYCLES_GE_2_UOPS_EXEC - UOPS_EXECUTED.CYCLES_GE_3_UOPS_EXEC) / tma_info_core_core_clks",
         "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_issue2P;tma_ports_utilization_group",
         "MetricName": "tma_ports_utilized_2",
-        "MetricThreshold": "tma_ports_utilized_2 > 0.15 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))",
-        "PublicDescription": "This metric represents fraction of cycles CPU executed total of 2 uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise).  Loop Vectorization -most compilers feature auto-Vectorization options today- reduces pressure on the execution ports as multiple elements are calculated with same uop. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6",
+        "MetricThreshold": "tma_ports_utilized_2 > 0.15 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
+        "PublicDescription": "This metric represents fraction of cycles CPU executed total of 2 uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise).  Loop Vectorization -most compilers feature auto-Vectorization options today- reduces pressure on the execution ports as multiple elements are calculated with same uop. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_port_6",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric represents fraction of cycles CPU executed total of 3 or more uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise).",
-        "MetricExpr": "(cpu@UOPS_EXECUTED.CORE\\,cmask\\=3@ / 2 if #SMT_on else UOPS_EXECUTED.CYCLES_GE_3_UOPS_EXEC) / tma_info_core_core_clks",
+        "BriefDescription": "This metric represents fraction of cycles CPU executed total of 3 or more uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise)",
+        "MetricExpr": "(cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x3@ / 2 if #SMT_on else UOPS_EXECUTED.CYCLES_GE_3_UOPS_EXEC) / tma_info_core_core_clks",
         "MetricGroup": "BvCB;PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group",
         "MetricName": "tma_ports_utilized_3m",
-        "MetricThreshold": "tma_ports_utilized_3m > 0.4 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))",
+        "MetricThreshold": "tma_ports_utilized_3m > 0.4 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
         "ScaleUnit": "100%"
     },
     {
@@ -1276,8 +1304,8 @@
         "MetricExpr": "(200 * (MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_HITM * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.L3_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_L3_MISS_RETIRED.LOCAL_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_HITM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_FWD))) + 180 * (MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_FWD * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.L3_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_L3_MISS_RETIRED.LOCAL_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_HITM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_FWD)))) / tma_info_thread_clks",
         "MetricGroup": "Offcore;Server;Snoop;TopdownL5;tma_L5_group;tma_issueSyncxn;tma_mem_latency_group",
         "MetricName": "tma_remote_cache",
-        "MetricThreshold": "tma_remote_cache > 0.05 & (tma_mem_latency > 0.1 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))",
-        "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from remote cache in other sockets including synchronizations issues. This is caused often due to non-optimal NUMA allocations. #link to NUMA article. Sample with: MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_HITM_PS;MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_FWD_PS. Related metrics: tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_machine_clears",
+        "MetricThreshold": "tma_remote_cache > 0.05 & tma_mem_latency > 0.1 & tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from remote cache in other sockets including synchronizations issues. This is caused often due to non-optimal NUMA allocations. Sample with: MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_HITM, MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_FWD. Related metrics: tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_machine_clears",
         "ScaleUnit": "100%"
     },
     {
@@ -1285,8 +1313,8 @@
         "MetricExpr": "310 * (MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_DRAM * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.L3_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_L3_MISS_RETIRED.LOCAL_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_HITM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_FWD))) / tma_info_thread_clks",
         "MetricGroup": "Server;Snoop;TopdownL5;tma_L5_group;tma_mem_latency_group",
         "MetricName": "tma_remote_mem",
-        "MetricThreshold": "tma_remote_mem > 0.1 & (tma_mem_latency > 0.1 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))",
-        "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from remote memory. This is caused often due to non-optimal NUMA allocations. #link to NUMA article. Sample with: MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_DRAM_PS",
+        "MetricThreshold": "tma_remote_mem > 0.1 & tma_mem_latency > 0.1 & tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from remote memory. This is caused often due to non-optimal NUMA allocations. Sample with: MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_DRAM",
         "ScaleUnit": "100%"
     },
     {
@@ -1305,8 +1333,8 @@
         "MetricExpr": "tma_info_memory_load_miss_real_latency * LD_BLOCKS.NO_SR / tma_info_thread_clks",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group",
         "MetricName": "tma_split_loads",
-        "MetricThreshold": "tma_split_loads > 0.2 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
-        "PublicDescription": "This metric estimates fraction of cycles handling memory load split accesses - load that cross 64-byte cache line boundary. Sample with: MEM_UOPS_RETIRED.SPLIT_LOADS_PS",
+        "MetricThreshold": "tma_split_loads > 0.3",
+        "PublicDescription": "This metric estimates fraction of cycles handling memory load split accesses - load that cross 64-byte cache line boundary. Sample with: MEM_UOPS_RETIRED.SPLIT_LOADS",
         "ScaleUnit": "100%"
     },
     {
@@ -1314,16 +1342,16 @@
         "MetricExpr": "2 * MEM_UOPS_RETIRED.SPLIT_STORES / tma_info_core_core_clks",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_issueSpSt;tma_store_bound_group",
         "MetricName": "tma_split_stores",
-        "MetricThreshold": "tma_split_stores > 0.2 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
-        "PublicDescription": "This metric represents rate of split store accesses.  Consider aligning your data to the 64-byte cache line granularity. Sample with: MEM_UOPS_RETIRED.SPLIT_STORES_PS. Related metrics: tma_port_4",
+        "MetricThreshold": "tma_split_stores > 0.2 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "PublicDescription": "This metric represents rate of split store accesses.  Consider aligning your data to the 64-byte cache line granularity. Sample with: MEM_UOPS_RETIRED.SPLIT_STORES. Related metrics: tma_port_4",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors)",
         "MetricExpr": "(OFFCORE_REQUESTS_BUFFER.SQ_FULL / 2 if #SMT_on else OFFCORE_REQUESTS_BUFFER.SQ_FULL) / tma_info_core_core_clks",
-        "MetricGroup": "BvMS;MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_issueBW;tma_l3_bound_group",
+        "MetricGroup": "BvMB;MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_issueBW;tma_l3_bound_group",
         "MetricName": "tma_sq_full",
-        "MetricThreshold": "tma_sq_full > 0.3 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+        "MetricThreshold": "tma_sq_full > 0.3 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
         "PublicDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors). Related metrics: tma_fb_full, tma_info_system_dram_bw_use, tma_mem_bandwidth",
         "ScaleUnit": "100%"
     },
@@ -1332,8 +1360,8 @@
         "MetricExpr": "RESOURCE_STALLS.SB / tma_info_thread_clks",
         "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group",
         "MetricName": "tma_store_bound",
-        "MetricThreshold": "tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)",
-        "PublicDescription": "This metric estimates how often CPU was stalled  due to RFO store memory accesses; RFO store issue a read-for-ownership request before the write. Even though store accesses do not typically stall out-of-order CPUs; there are few cases where stores can lead to actual stalls. This metric will be flagged should RFO stores be a bottleneck. Sample with: MEM_UOPS_RETIRED.ALL_STORES_PS",
+        "MetricThreshold": "tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "PublicDescription": "This metric estimates how often CPU was stalled  due to RFO store memory accesses; RFO store issue a read-for-ownership request before the write. Even though store accesses do not typically stall out-of-order CPUs; there are few cases where stores can lead to actual stalls. This metric will be flagged should RFO stores be a bottleneck. Sample with: MEM_UOPS_RETIRED.ALL_STORES",
         "ScaleUnit": "100%"
     },
     {
@@ -1341,18 +1369,18 @@
         "MetricExpr": "13 * LD_BLOCKS.STORE_FORWARD / tma_info_thread_clks",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group",
         "MetricName": "tma_store_fwd_blk",
-        "MetricThreshold": "tma_store_fwd_blk > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
-        "PublicDescription": "This metric roughly estimates fraction of cycles when the memory subsystem had loads blocked since they could not forward data from earlier (in program order) overlapping stores. To streamline memory operations in the pipeline; a load can avoid waiting for memory if a prior in-flight store is writing the data that the load wants to read (store forwarding process). However; in some cases the load may be blocked for a significant time pending the store forward. For example; when the prior store is writing a smaller region than the load is reading.",
+        "MetricThreshold": "tma_store_fwd_blk > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "PublicDescription": "This metric roughly estimates fraction of cycles when the memory subsystem had loads blocked since they could not forward data from earlier (in program order) overlapping stores. To streamline memory operations in the pipeline; a load can avoid waiting for memory if a prior in-flight store is writing the data that the load wants to read (store forwarding process). However; in some cases the load may be blocked for a significant time pending the store forward. For example; when the prior store is writing a smaller region than the load is reading",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "This metric estimates fraction of cycles the CPU spent handling L1D store misses",
         "MetricConstraint": "NO_GROUP_EVENTS",
         "MetricExpr": "(L2_RQSTS.RFO_HIT * 9 * (1 - MEM_UOPS_RETIRED.LOCK_LOADS / MEM_UOPS_RETIRED.ALL_STORES) + (1 - MEM_UOPS_RETIRED.LOCK_LOADS / MEM_UOPS_RETIRED.ALL_STORES) * min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO)) / tma_info_thread_clks",
-        "MetricGroup": "BvML;MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_issueSL;tma_store_bound_group",
+        "MetricGroup": "BvML;LockCont;MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_issueSL;tma_store_bound_group",
         "MetricName": "tma_store_latency",
-        "MetricThreshold": "tma_store_latency > 0.1 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
-        "PublicDescription": "This metric estimates fraction of cycles the CPU spent handling L1D store misses. Store accesses usually less impact out-of-order core performance; however; holding resources for longer time can lead into undesired implications (e.g. contention on L1D fill-buffer entries - see FB_Full). Related metrics: tma_fb_full, tma_lock_latency",
+        "MetricThreshold": "tma_store_latency > 0.1 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "PublicDescription": "This metric estimates fraction of cycles the CPU spent handling L1D store misses. Store accesses usually less impact out-of-order core performance; however; holding resources for longer time can lead into undesired implications (e.g. contention on L1D fill-buffer entries - see FB_Full). Related metrics: tma_branch_resteers, tma_fb_full, tma_l3_hit_latency, tma_lock_latency",
         "ScaleUnit": "100%"
     },
     {
@@ -1368,7 +1396,7 @@
         "MetricExpr": "tma_branch_resteers - tma_mispredicts_resteers - tma_clears_resteers",
         "MetricGroup": "BigFootprint;BvBC;FetchLat;TopdownL4;tma_L4_group;tma_branch_resteers_group",
         "MetricName": "tma_unknown_branches",
-        "MetricThreshold": "tma_unknown_branches > 0.05 & (tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))",
+        "MetricThreshold": "tma_unknown_branches > 0.05 & tma_branch_resteers > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
         "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to new branch address clears. These are fetched branches the Branch Prediction Unit was unable to recognize (e.g. first time the branch is fetched or hitting BTB capacity limit) hence called Unknown Branches. Sample with: BACLEARS.ANY",
         "ScaleUnit": "100%"
     },
@@ -1377,8 +1405,8 @@
         "MetricExpr": "INST_RETIRED.X87 * tma_info_thread_uoppi / UOPS_RETIRED.RETIRE_SLOTS",
         "MetricGroup": "Compute;TopdownL4;tma_L4_group;tma_fp_arith_group",
         "MetricName": "tma_x87_use",
-        "MetricThreshold": "tma_x87_use > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6)",
-        "PublicDescription": "This metric serves as an approximation of legacy x87 usage. It accounts for instructions beyond X87 FP arithmetic operations; hence may be used as a thermometer to avoid X87 high usage and preferably upgrade to modern ISA. See Tip under Tuning Hint.",
+        "MetricThreshold": "tma_x87_use > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6",
+        "PublicDescription": "This metric serves as an approximation of legacy x87 usage. It accounts for instructions beyond X87 FP arithmetic operations; hence may be used as a thermometer to avoid X87 high usage and preferably upgrade to modern ISA. See Tip under Tuning Hint",
         "ScaleUnit": "100%"
     },
     {
tools/perf/pmu-events/arch/x86/broadwellx/cache.json +5 -5
index beeda41b428a..59bc8c71487e 100644
@@ -22,7 +22,7 @@
         "Counter": "2",
         "EventCode": "0x48",
         "EventName": "L1D_PEND_MISS.PENDING",
-        "PublicDescription": "This event counts duration of L1D miss outstanding, that is each cycle number of Fill Buffers (FB) outstanding required by Demand Reads. FB either is held by demand loads, or it is held by non-demand loads and gets hit at least once by demand. The valid outstanding interval is defined until the FB deallocation by one of the following ways: from FB allocation, if FB is allocated by demand; from the demand Hit FB, if it is allocated by hardware or software prefetch.\nNote: In the L1D, a Demand Read contains cacheable or noncacheable demand loads, including ones causing cache-line splits and reads due to page walks resulted from any request type.",
+        "PublicDescription": "This event counts duration of L1D miss outstanding, that is each cycle number of Fill Buffers (FB) outstanding required by Demand Reads. FB either is held by demand loads, or it is held by non-demand loads and gets hit at least once by demand. The valid outstanding interval is defined until the FB deallocation by one of the following ways: from FB allocation, if FB is allocated by demand; from the demand Hit FB, if it is allocated by hardware or software prefetch. Note: In the L1D, a Demand Read contains cacheable or noncacheable demand loads, including ones causing cache-line splits and reads due to page walks resulted from any request type.",
         "SampleAfterValue": "2000003",
         "UMask": "0x1"
     },
@@ -434,7 +434,7 @@
         "EventCode": "0xD1",
         "EventName": "MEM_LOAD_UOPS_RETIRED.HIT_LFB",
         "PEBS": "1",
-        "PublicDescription": "This event counts retired load uops which data sources were load uops missed L1 but hit a fill buffer due to a preceding miss to the same cache line with the data not ready.\nNote: Only two data-sources of L1/FB are applicable for AVX-256bit  even though the corresponding AVX load could be serviced by a deeper level in the memory hierarchy. Data source is reported for the Low-half load.",
+        "PublicDescription": "This event counts retired load uops which data sources were load uops missed L1 but hit a fill buffer due to a preceding miss to the same cache line with the data not ready. Note: Only two data-sources of L1/FB are applicable for AVX-256bit  even though the corresponding AVX load could be serviced by a deeper level in the memory hierarchy. Data source is reported for the Low-half load.",
         "SampleAfterValue": "100003",
         "UMask": "0x40"
     },
@@ -445,7 +445,7 @@
         "EventCode": "0xD1",
         "EventName": "MEM_LOAD_UOPS_RETIRED.L1_HIT",
         "PEBS": "1",
-        "PublicDescription": "This event counts retired load uops which data sources were hits in the nearest-level (L1) cache.\nNote: Only two data-sources of L1/FB are applicable for AVX-256bit  even though the corresponding AVX load could be serviced by a deeper level in the memory hierarchy. Data source is reported for the Low-half load. This event also counts SW prefetches independent of the actual data source.",
+        "PublicDescription": "This event counts retired load uops which data sources were hits in the nearest-level (L1) cache. Note: Only two data-sources of L1/FB are applicable for AVX-256bit  even though the corresponding AVX load could be serviced by a deeper level in the memory hierarchy. Data source is reported for the Low-half load. This event also counts SW prefetches independent of the actual data source.",
         "SampleAfterValue": "2000003",
         "UMask": "0x1"
     },
@@ -634,7 +634,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0xb2",
         "EventName": "OFFCORE_REQUESTS_BUFFER.SQ_FULL",
-        "PublicDescription": "This event counts the number of cases when the offcore requests buffer cannot take more entries for the core. This can happen when the superqueue does not contain eligible entries, or when L1D writeback pending FIFO requests is full.\nNote: Writeback pending FIFO has six entries.",
+        "PublicDescription": "This event counts the number of cases when the offcore requests buffer cannot take more entries for the core. This can happen when the superqueue does not contain eligible entries, or when L1D writeback pending FIFO requests is full. Note: Writeback pending FIFO has six entries.",
         "SampleAfterValue": "2000003",
         "UMask": "0x1"
     },
@@ -697,7 +697,7 @@
         "Errata": "BDM76",
         "EventCode": "0x60",
         "EventName": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD",
-        "PublicDescription": "This event counts the number of offcore outstanding Demand Data Read transactions in the super queue (SQ) every cycle. A transaction is considered to be in the Offcore outstanding state between L2 miss and transaction completion sent to requestor. See the corresponding Umask under OFFCORE_REQUESTS.\nNote: A prefetch promoted to Demand is counted from the promotion point.",
+        "PublicDescription": "This event counts the number of offcore outstanding Demand Data Read transactions in the super queue (SQ) every cycle. A transaction is considered to be in the Offcore outstanding state between L2 miss and transaction completion sent to requestor. See the corresponding Umask under OFFCORE_REQUESTS. Note: A prefetch promoted to Demand is counted from the promotion point.",
         "SampleAfterValue": "2000003",
         "UMask": "0x1"
     },
tools/perf/pmu-events/arch/x86/broadwellx/frontend.json +2 -2
index db3488abf9fc..018020a51436 100644
@@ -12,7 +12,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0xAB",
         "EventName": "DSB2MITE_SWITCHES.PENALTY_CYCLES",
-        "PublicDescription": "This event counts Decode Stream Buffer (DSB)-to-MITE switch true penalty cycles. These cycles do not include uops routed through because of the switch itself, for example, when Instruction Decode Queue (IDQ) pre-allocation is unavailable, or Instruction Decode Queue (IDQ) is full. SBD-to-MITE switch true penalty cycles happen after the merge mux (MM) receives Decode Stream Buffer (DSB) Sync-indication until receiving the first MITE uop. \nMM is placed before Instruction Decode Queue (IDQ) to merge uops being fed from the MITE and Decode Stream Buffer (DSB) paths. Decode Stream Buffer (DSB) inserts the Sync-indication whenever a Decode Stream Buffer (DSB)-to-MITE switch occurs.\nPenalty: A Decode Stream Buffer (DSB) hit followed by a Decode Stream Buffer (DSB) miss can cost up to six cycles in which no uops are delivered to the IDQ. Most often, such switches from the Decode Stream Buffer (DSB) to the legacy pipeline cost 02 cycles.",
+        "PublicDescription": "This event counts Decode Stream Buffer (DSB)-to-MITE switch true penalty cycles. These cycles do not include uops routed through because of the switch itself, for example, when Instruction Decode Queue (IDQ) pre-allocation is unavailable, or Instruction Decode Queue (IDQ) is full. SBD-to-MITE switch true penalty cycles happen after the merge mux (MM) receives Decode Stream Buffer (DSB) Sync-indication until receiving the first MITE uop.  MM is placed before Instruction Decode Queue (IDQ) to merge uops being fed from the MITE and Decode Stream Buffer (DSB) paths. Decode Stream Buffer (DSB) inserts the Sync-indication whenever a Decode Stream Buffer (DSB)-to-MITE switch occurs. Penalty: A Decode Stream Buffer (DSB) hit followed by a Decode Stream Buffer (DSB) miss can cost up to six cycles in which no uops are delivered to the IDQ. Most often, such switches from the Decode Stream Buffer (DSB) to the legacy pipeline cost 02 cycles.",
         "SampleAfterValue": "2000003",
         "UMask": "0x2"
     },
@@ -212,7 +212,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x9C",
         "EventName": "IDQ_UOPS_NOT_DELIVERED.CORE",
-        "PublicDescription": "This event counts the number of uops not delivered to Resource Allocation Table (RAT) per thread adding 4  x when Resource Allocation Table (RAT) is not stalled and Instruction Decode Queue (IDQ) delivers x uops to Resource Allocation Table (RAT) (where x belongs to {0,1,2,3}). Counting does not cover cases when:\n a. IDQ-Resource Allocation Table (RAT) pipe serves the other thread;\n b. Resource Allocation Table (RAT) is stalled for the thread (including uop drops and clear BE conditions); \n c. Instruction Decode Queue (IDQ) delivers four uops.",
+        "PublicDescription": "This event counts the number of uops not delivered to Resource Allocation Table (RAT) per thread adding 4  x when Resource Allocation Table (RAT) is not stalled and Instruction Decode Queue (IDQ) delivers x uops to Resource Allocation Table (RAT) (where x belongs to {0,1,2,3}). Counting does not cover cases when:  a. IDQ-Resource Allocation Table (RAT) pipe serves the other thread;  b. Resource Allocation Table (RAT) is stalled for the thread (including uop drops and clear BE conditions);   c. Instruction Decode Queue (IDQ) delivers four uops.",
         "SampleAfterValue": "2000003",
         "UMask": "0x1"
     },
tools/perf/pmu-events/arch/x86/broadwellx/memory.json +3 -3
index 86246f632d79..093c8b564fc0 100644
@@ -68,7 +68,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0xc8",
         "EventName": "HLE_RETIRED.START",
-        "PublicDescription": "Number of times we entered an HLE region\n does not count nested transactions.",
+        "PublicDescription": "Number of times we entered an HLE region  does not count nested transactions.",
         "SampleAfterValue": "2000003",
         "UMask": "0x1"
     },
@@ -77,7 +77,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0xC3",
         "EventName": "MACHINE_CLEARS.MEMORY_ORDERING",
-        "PublicDescription": "This event counts the number of memory ordering Machine Clears detected. Memory Ordering Machine Clears can result from one of the following:\n1. memory disambiguation,\n2. external snoop, or\n3. cross SMT-HW-thread snoop (stores) hitting load buffer.",
+        "PublicDescription": "This event counts the number of memory ordering Machine Clears detected. Memory Ordering Machine Clears can result from one of the following: 1. memory disambiguation, 2. external snoop, or 3. cross SMT-HW-thread snoop (stores) hitting load buffer.",
         "SampleAfterValue": "100003",
         "UMask": "0x2"
     },
@@ -470,7 +470,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0xc9",
         "EventName": "RTM_RETIRED.START",
-        "PublicDescription": "Number of times we entered an RTM region\n does not count nested transactions.",
+        "PublicDescription": "Number of times we entered an RTM region  does not count nested transactions.",
         "SampleAfterValue": "2000003",
         "UMask": "0x1"
     },
tools/perf/pmu-events/arch/x86/broadwellx/metricgroups.json +5 -0
index 4193c90c3459..0863375bdead 100644
@@ -9,6 +9,7 @@
     "BvCB": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
     "BvFB": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
     "BvIO": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
+    "BvMB": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
     "BvML": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
     "BvMP": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
     "BvMS": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
@@ -34,6 +35,7 @@
     "InsType": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
     "L2Evicts": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
     "LSD": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
+    "LockCont": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
     "MachineClears": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
     "Machine_Clears": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
     "Mem": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
@@ -51,6 +53,7 @@
     "Pipeline": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
     "PortsUtil": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
     "Power": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
+    "Prefetches": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
     "Ret": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
     "Retire": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
     "SMT": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
@@ -78,6 +81,7 @@
     "tma_bad_speculation_group": "Metrics contributing to tma_bad_speculation category",
     "tma_branch_resteers_group": "Metrics contributing to tma_branch_resteers category",
     "tma_core_bound_group": "Metrics contributing to tma_core_bound category",
+    "tma_divider_group": "Metrics contributing to tma_divider category",
     "tma_dram_bound_group": "Metrics contributing to tma_dram_bound category",
     "tma_dtlb_load_group": "Metrics contributing to tma_dtlb_load category",
     "tma_dtlb_store_group": "Metrics contributing to tma_dtlb_store category",
@@ -103,6 +107,7 @@
     "tma_issueSpSt": "Metrics related by the issue $issueSpSt",
     "tma_issueSyncxn": "Metrics related by the issue $issueSyncxn",
     "tma_issueTLB": "Metrics related by the issue $issueTLB",
+    "tma_itlb_misses_group": "Metrics contributing to tma_itlb_misses category",
     "tma_l1_bound_group": "Metrics contributing to tma_l1_bound category",
     "tma_l3_bound_group": "Metrics contributing to tma_l3_bound category",
     "tma_light_operations_group": "Metrics contributing to tma_light_operations category",
tools/perf/pmu-events/arch/x86/broadwellx/pipeline.json +5 -5
index c03f77539362..962cd07eb307 100644
@@ -379,7 +379,7 @@
         "BriefDescription": "Reference cycles when the core is not in halt state.",
         "Counter": "Fixed counter 2",
         "EventName": "CPU_CLK_UNHALTED.REF_TSC",
-        "PublicDescription": "This event counts the number of reference cycles when the core is not in a halt state. The core enters the halt state when it is running the HLT instruction or the MWAIT instruction. This event is not affected by core frequency changes (for example, P states, TM2 transitions) but has the same incrementing frequency as the time stamp counter. This event can approximate elapsed time while the core was not in a halt state. This event has a constant ratio with the CPU_CLK_UNHALTED.REF_XCLK event. It is counted on a dedicated fixed counter, leaving the four (eight when Hyperthreading is disabled) programmable counters available for other events. \nNote: On all current platforms this event stops counting during 'throttling (TM)' states duty off periods the processor is 'halted'.  This event is clocked by base clock (100 Mhz) on Sandy Bridge. The counter update is done at a lower clock rate then the core clock the overflow status bit for this counter may appear 'sticky'.  After the counter has overflowed and software clears the overflow status bit and resets the counter to less than MAX. The reset value to the counter is not clocked immediately so the overflow status bit will flip 'high (1)' and generate another PMI (if enabled) after which the reset value gets clocked into the counter. Therefore, software will get the interrupt, read the overflow status bit '1 for bit 34 while the counter value is less than MAX. Software should ignore this case.",
+        "PublicDescription": "This event counts the number of reference cycles when the core is not in a halt state. The core enters the halt state when it is running the HLT instruction or the MWAIT instruction. This event is not affected by core frequency changes (for example, P states, TM2 transitions) but has the same incrementing frequency as the time stamp counter. This event can approximate elapsed time while the core was not in a halt state. This event has a constant ratio with the CPU_CLK_UNHALTED.REF_XCLK event. It is counted on a dedicated fixed counter, leaving the four (eight when Hyperthreading is disabled) programmable counters available for other events.  Note: On all current platforms this event stops counting during 'throttling (TM)' states duty off periods the processor is 'halted'.  This event is clocked by base clock (100 Mhz) on Sandy Bridge. The counter update is done at a lower clock rate then the core clock the overflow status bit for this counter may appear 'sticky'.  After the counter has overflowed and software clears the overflow status bit and resets the counter to less than MAX. The reset value to the counter is not clocked immediately so the overflow status bit will flip 'high (1)' and generate another PMI (if enabled) after which the reset value gets clocked into the counter. Therefore, software will get the interrupt, read the overflow status bit '1 for bit 34 while the counter value is less than MAX. Software should ignore this case.",
         "SampleAfterValue": "2000003",
         "UMask": "0x3"
     },
@@ -579,7 +579,7 @@
         "BriefDescription": "Instructions retired from execution.",
         "Counter": "Fixed counter 0",
         "EventName": "INST_RETIRED.ANY",
-        "PublicDescription": "This event counts the number of instructions retired from execution. For instructions that consist of multiple micro-ops, this event counts the retirement of the last micro-op of the instruction. Counting continues during hardware interrupts, traps, and inside interrupt handlers. \nNotes: INST_RETIRED.ANY is counted by a designated fixed counter, leaving the four (eight when Hyperthreading is disabled) programmable counters available for other events. INST_RETIRED.ANY_P is counted by a programmable counter and it is an architectural performance event. \nCounting: Faulting executions of GETSEC/VM entry/VM Exit/MWait will not count as retired instructions.",
+        "PublicDescription": "This event counts the number of instructions retired from execution. For instructions that consist of multiple micro-ops, this event counts the retirement of the last micro-op of the instruction. Counting continues during hardware interrupts, traps, and inside interrupt handlers.  Notes: INST_RETIRED.ANY is counted by a designated fixed counter, leaving the four (eight when Hyperthreading is disabled) programmable counters available for other events. INST_RETIRED.ANY_P is counted by a programmable counter and it is an architectural performance event.  Counting: Faulting executions of GETSEC/VM entry/VM Exit/MWait will not count as retired instructions.",
         "SampleAfterValue": "2000003",
         "UMask": "0x1"
     },
@@ -654,7 +654,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x03",
         "EventName": "LD_BLOCKS.STORE_FORWARD",
-        "PublicDescription": "This event counts how many times the load operation got the true Block-on-Store blocking code preventing store forwarding. This includes cases when:\n - preceding store conflicts with the load (incomplete overlap);\n - store forwarding is impossible due to u-arch limitations;\n - preceding lock RMW operations are not forwarded;\n - store has the no-forward bit set (uncacheable/page-split/masked stores);\n - all-blocking stores are used (mostly, fences and port I/O);\nand others.\nThe most common case is a load blocked due to its address range overlapping with a preceding smaller uncompleted store. Note: This event does not take into account cases of out-of-SW-control (for example, SbTailHit), unknown physical STA, and cases of blocking loads on store due to being non-WB memory type or a lock. These cases are covered by other events.\nSee the table of not supported store forwards in the Optimization Guide.",
+        "PublicDescription": "This event counts how many times the load operation got the true Block-on-Store blocking code preventing store forwarding. This includes cases when:  - preceding store conflicts with the load (incomplete overlap);  - store forwarding is impossible due to u-arch limitations;  - preceding lock RMW operations are not forwarded;  - store has the no-forward bit set (uncacheable/page-split/masked stores);  - all-blocking stores are used (mostly, fences and port I/O); and others. The most common case is a load blocked due to its address range overlapping with a preceding smaller uncompleted store. Note: This event does not take into account cases of out-of-SW-control (for example, SbTailHit), unknown physical STA, and cases of blocking loads on store due to being non-WB memory type or a lock. These cases are covered by other events. See the table of not supported store forwards in the Optimization Guide.",
         "SampleAfterValue": "100003",
         "UMask": "0x2"
     },
@@ -822,7 +822,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x5E",
         "EventName": "RS_EVENTS.EMPTY_CYCLES",
-        "PublicDescription": "This event counts cycles during which the reservation station (RS) is empty for the thread.\nNote: In ST-mode, not active thread should drive 0. This is usually caused by severely costly branch mispredictions, or allocator/FE issues.",
+        "PublicDescription": "This event counts cycles during which the reservation station (RS) is empty for the thread. Note: In ST-mode, not active thread should drive 0. This is usually caused by severely costly branch mispredictions, or allocator/FE issues.",
         "SampleAfterValue": "2000003",
         "UMask": "0x1"
     },
@@ -1177,7 +1177,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x0E",
         "EventName": "UOPS_ISSUED.FLAGS_MERGE",
-        "PublicDescription": "Number of flags-merge uops being allocated. Such uops considered perf sensitive\n added by GSR u-arch.",
+        "PublicDescription": "Number of flags-merge uops being allocated. Such uops considered perf sensitive  added by GSR u-arch.",
         "SampleAfterValue": "2000003",
         "UMask": "0x10"
     },
tools/perf/pmu-events/arch/x86/broadwellx/uncore-cache.json +14 -14
index b55b305aecaa..8f6955615bfd 100644
@@ -802,7 +802,7 @@
         "EventCode": "0x12",
         "EventName": "UNC_C_RxR_EXT_STARVED.IPQ",
         "PerPkg": "1",
-        "PublicDescription": "Counts cycles in external starvation.  This occurs when one of the ingress queues is being starved by the other queues.; IPQ is externally startved and therefore we are blocking the IRQ.",
+        "PublicDescription": "Counts cycles in external starvation.  This occurs when one of the ingress queues is being starved by the other queues.; IPQ is externally starved and therefore we are blocking the IRQ.",
         "UMask": "0x2",
         "Unit": "CBOX"
     },
@@ -1859,7 +1859,7 @@
         "EventCode": "0x14",
         "EventName": "UNC_H_BYPASS_IMC.NOT_TAKEN",
         "PerPkg": "1",
-        "PublicDescription": "Counts the number of times when the HA was able to bypass was attempted.  This is a latency optimization for situations when there is light loadings on the memory subsystem.  This can be filted by when the bypass was taken and when it was not.; Filter for transactions that could not take the bypass.",
+        "PublicDescription": "Counts the number of times when the HA was able to bypass was attempted.  This is a latency optimization for situations when there is light loadings on the memory subsystem.  This can be filtered by when the bypass was taken and when it was not.; Filter for transactions that could not take the bypass.",
         "UMask": "0x2",
         "Unit": "HA"
     },
@@ -1869,7 +1869,7 @@
         "EventCode": "0x14",
         "EventName": "UNC_H_BYPASS_IMC.TAKEN",
         "PerPkg": "1",
-        "PublicDescription": "Counts the number of times when the HA was able to bypass was attempted.  This is a latency optimization for situations when there is light loadings on the memory subsystem.  This can be filted by when the bypass was taken and when it was not.; Filter for transactions that succeeded in taking the bypass.",
+        "PublicDescription": "Counts the number of times when the HA was able to bypass was attempted.  This is a latency optimization for situations when there is light loadings on the memory subsystem.  This can be filtered by when the bypass was taken and when it was not.; Filter for transactions that succeeded in taking the bypass.",
         "UMask": "0x1",
         "Unit": "HA"
     },
@@ -2884,7 +2884,7 @@
         "EventCode": "0x15",
         "EventName": "UNC_H_RPQ_CYCLES_NO_REG_CREDITS.CHN0",
         "PerPkg": "1",
-        "PublicDescription": "Counts the number of cycles when there are no regular credits available for posting reads from the HA into the iMC.  In order to send reads into the memory controller, the HA must first acquire a credit for the iMC's RPQ (read pending queue).  This queue is broken into regular credits/buffers that are used by general reads, and special requests such as ISOCH reads.  This count only tracks the regular credits  Common high banwidth workloads should be able to make use of all of the regular buffers, but it will be difficult (and uncommon) to make use of both the regular and special buffers at the same time.  One can filter based on the memory controller channel.  One or more channels can be tracked at a given time.; Filter for memory controller channel 0 only.",
+        "PublicDescription": "Counts the number of cycles when there are no regular credits available for posting reads from the HA into the iMC.  In order to send reads into the memory controller, the HA must first acquire a credit for the iMC's RPQ (read pending queue).  This queue is broken into regular credits/buffers that are used by general reads, and special requests such as ISOCH reads.  This count only tracks the regular credits  Common high bandwidth workloads should be able to make use of all of the regular buffers, but it will be difficult (and uncommon) to make use of both the regular and special buffers at the same time.  One can filter based on the memory controller channel.  One or more channels can be tracked at a given time.; Filter for memory controller channel 0 only.",
         "UMask": "0x1",
         "Unit": "HA"
     },
@@ -2894,7 +2894,7 @@
         "EventCode": "0x15",
         "EventName": "UNC_H_RPQ_CYCLES_NO_REG_CREDITS.CHN1",
         "PerPkg": "1",
-        "PublicDescription": "Counts the number of cycles when there are no regular credits available for posting reads from the HA into the iMC.  In order to send reads into the memory controller, the HA must first acquire a credit for the iMC's RPQ (read pending queue).  This queue is broken into regular credits/buffers that are used by general reads, and special requests such as ISOCH reads.  This count only tracks the regular credits  Common high banwidth workloads should be able to make use of all of the regular buffers, but it will be difficult (and uncommon) to make use of both the regular and special buffers at the same time.  One can filter based on the memory controller channel.  One or more channels can be tracked at a given time.; Filter for memory controller channel 1 only.",
+        "PublicDescription": "Counts the number of cycles when there are no regular credits available for posting reads from the HA into the iMC.  In order to send reads into the memory controller, the HA must first acquire a credit for the iMC's RPQ (read pending queue).  This queue is broken into regular credits/buffers that are used by general reads, and special requests such as ISOCH reads.  This count only tracks the regular credits  Common high bandwidth workloads should be able to make use of all of the regular buffers, but it will be difficult (and uncommon) to make use of both the regular and special buffers at the same time.  One can filter based on the memory controller channel.  One or more channels can be tracked at a given time.; Filter for memory controller channel 1 only.",
         "UMask": "0x2",
         "Unit": "HA"
     },
@@ -2904,7 +2904,7 @@
         "EventCode": "0x15",
         "EventName": "UNC_H_RPQ_CYCLES_NO_REG_CREDITS.CHN2",
         "PerPkg": "1",
-        "PublicDescription": "Counts the number of cycles when there are no regular credits available for posting reads from the HA into the iMC.  In order to send reads into the memory controller, the HA must first acquire a credit for the iMC's RPQ (read pending queue).  This queue is broken into regular credits/buffers that are used by general reads, and special requests such as ISOCH reads.  This count only tracks the regular credits  Common high banwidth workloads should be able to make use of all of the regular buffers, but it will be difficult (and uncommon) to make use of both the regular and special buffers at the same time.  One can filter based on the memory controller channel.  One or more channels can be tracked at a given time.; Filter for memory controller channel 2 only.",
+        "PublicDescription": "Counts the number of cycles when there are no regular credits available for posting reads from the HA into the iMC.  In order to send reads into the memory controller, the HA must first acquire a credit for the iMC's RPQ (read pending queue).  This queue is broken into regular credits/buffers that are used by general reads, and special requests such as ISOCH reads.  This count only tracks the regular credits  Common high bandwidth workloads should be able to make use of all of the regular buffers, but it will be difficult (and uncommon) to make use of both the regular and special buffers at the same time.  One can filter based on the memory controller channel.  One or more channels can be tracked at a given time.; Filter for memory controller channel 2 only.",
         "UMask": "0x4",
         "Unit": "HA"
     },
@@ -2914,7 +2914,7 @@
         "EventCode": "0x15",
         "EventName": "UNC_H_RPQ_CYCLES_NO_REG_CREDITS.CHN3",
         "PerPkg": "1",
-        "PublicDescription": "Counts the number of cycles when there are no regular credits available for posting reads from the HA into the iMC.  In order to send reads into the memory controller, the HA must first acquire a credit for the iMC's RPQ (read pending queue).  This queue is broken into regular credits/buffers that are used by general reads, and special requests such as ISOCH reads.  This count only tracks the regular credits  Common high banwidth workloads should be able to make use of all of the regular buffers, but it will be difficult (and uncommon) to make use of both the regular and special buffers at the same time.  One can filter based on the memory controller channel.  One or more channels can be tracked at a given time.; Filter for memory controller channel 3 only.",
+        "PublicDescription": "Counts the number of cycles when there are no regular credits available for posting reads from the HA into the iMC.  In order to send reads into the memory controller, the HA must first acquire a credit for the iMC's RPQ (read pending queue).  This queue is broken into regular credits/buffers that are used by general reads, and special requests such as ISOCH reads.  This count only tracks the regular credits  Common high bandwidth workloads should be able to make use of all of the regular buffers, but it will be difficult (and uncommon) to make use of both the regular and special buffers at the same time.  One can filter based on the memory controller channel.  One or more channels can be tracked at a given time.; Filter for memory controller channel 3 only.",
         "UMask": "0x8",
         "Unit": "HA"
     },
@@ -3448,7 +3448,7 @@
         "EventCode": "0x3",
         "EventName": "UNC_H_TRACKER_CYCLES_NE.ALL",
         "PerPkg": "1",
-        "PublicDescription": "Counts the number of cycles when the local HA tracker pool is not empty.  This can be used with edge detect to identify the number of situations when the pool became empty.  This should not be confused with RTID credit usage -- which must be tracked inside each cbo individually -- but represents the actual tracker buffer structure.  In other words, this buffer could be completely empty, but there may still be credits in use by the CBos.  This stat can be used in conjunction with the occupancy accumulation stat in order to calculate average queue occpancy.  HA trackers are allocated as soon as a request enters the HA if an HT (Home Tracker) entry is available and is released after the snoop response and data return (or post in the case of a write) and the response is returned on the ring.; Requests coming from both local and remote sockets.",
+        "PublicDescription": "Counts the number of cycles when the local HA tracker pool is not empty.  This can be used with edge detect to identify the number of situations when the pool became empty.  This should not be confused with RTID credit usage -- which must be tracked inside each cbo individually -- but represents the actual tracker buffer structure.  In other words, this buffer could be completely empty, but there may still be credits in use by the CBos.  This stat can be used in conjunction with the occupancy accumulation stat in order to calculate average queue occupancy.  HA trackers are allocated as soon as a request enters the HA if an HT (Home Tracker) entry is available and is released after the snoop response and data return (or post in the case of a write) and the response is returned on the ring.; Requests coming from both local and remote sockets.",
         "UMask": "0x3",
         "Unit": "HA"
     },
@@ -3458,7 +3458,7 @@
         "EventCode": "0x3",
         "EventName": "UNC_H_TRACKER_CYCLES_NE.LOCAL",
         "PerPkg": "1",
-        "PublicDescription": "Counts the number of cycles when the local HA tracker pool is not empty.  This can be used with edge detect to identify the number of situations when the pool became empty.  This should not be confused with RTID credit usage -- which must be tracked inside each cbo individually -- but represents the actual tracker buffer structure.  In other words, this buffer could be completely empty, but there may still be credits in use by the CBos.  This stat can be used in conjunction with the occupancy accumulation stat in order to calculate average queue occpancy.  HA trackers are allocated as soon as a request enters the HA if an HT (Home Tracker) entry is available and is released after the snoop response and data return (or post in the case of a write) and the response is returned on the ring.; This filter includes only requests coming from the local socket.",
+        "PublicDescription": "Counts the number of cycles when the local HA tracker pool is not empty.  This can be used with edge detect to identify the number of situations when the pool became empty.  This should not be confused with RTID credit usage -- which must be tracked inside each cbo individually -- but represents the actual tracker buffer structure.  In other words, this buffer could be completely empty, but there may still be credits in use by the CBos.  This stat can be used in conjunction with the occupancy accumulation stat in order to calculate average queue occupancy.  HA trackers are allocated as soon as a request enters the HA if an HT (Home Tracker) entry is available and is released after the snoop response and data return (or post in the case of a write) and the response is returned on the ring.; This filter includes only requests coming from the local socket.",
         "UMask": "0x1",
         "Unit": "HA"
     },
@@ -3468,7 +3468,7 @@
         "EventCode": "0x3",
         "EventName": "UNC_H_TRACKER_CYCLES_NE.REMOTE",
         "PerPkg": "1",
-        "PublicDescription": "Counts the number of cycles when the local HA tracker pool is not empty.  This can be used with edge detect to identify the number of situations when the pool became empty.  This should not be confused with RTID credit usage -- which must be tracked inside each cbo individually -- but represents the actual tracker buffer structure.  In other words, this buffer could be completely empty, but there may still be credits in use by the CBos.  This stat can be used in conjunction with the occupancy accumulation stat in order to calculate average queue occpancy.  HA trackers are allocated as soon as a request enters the HA if an HT (Home Tracker) entry is available and is released after the snoop response and data return (or post in the case of a write) and the response is returned on the ring.; This filter includes only requests coming from remote sockets.",
+        "PublicDescription": "Counts the number of cycles when the local HA tracker pool is not empty.  This can be used with edge detect to identify the number of situations when the pool became empty.  This should not be confused with RTID credit usage -- which must be tracked inside each cbo individually -- but represents the actual tracker buffer structure.  In other words, this buffer could be completely empty, but there may still be credits in use by the CBos.  This stat can be used in conjunction with the occupancy accumulation stat in order to calculate average queue occupancy.  HA trackers are allocated as soon as a request enters the HA if an HT (Home Tracker) entry is available and is released after the snoop response and data return (or post in the case of a write) and the response is returned on the ring.; This filter includes only requests coming from remote sockets.",
         "UMask": "0x2",
         "Unit": "HA"
     },
@@ -3888,7 +3888,7 @@
         "EventCode": "0x18",
         "EventName": "UNC_H_WPQ_CYCLES_NO_REG_CREDITS.CHN0",
         "PerPkg": "1",
-        "PublicDescription": "Counts the number of cycles when there are no regular credits available for posting writes from the HA into the iMC.  In order to send writes into the memory controller, the HA must first acquire a credit for the iMC's WPQ (write pending queue).  This queue is broken into regular credits/buffers that are used by general writes, and special requests such as ISOCH writes.  This count only tracks the regular credits  Common high banwidth workloads should be able to make use of all of the regular buffers, but it will be difficult (and uncommon) to make use of both the regular and special buffers at the same time.  One can filter based on the memory controller channel.  One or more channels can be tracked at a given time.; Filter for memory controller channel 0 only.",
+        "PublicDescription": "Counts the number of cycles when there are no regular credits available for posting writes from the HA into the iMC.  In order to send writes into the memory controller, the HA must first acquire a credit for the iMC's WPQ (write pending queue).  This queue is broken into regular credits/buffers that are used by general writes, and special requests such as ISOCH writes.  This count only tracks the regular credits  Common high bandwidth workloads should be able to make use of all of the regular buffers, but it will be difficult (and uncommon) to make use of both the regular and special buffers at the same time.  One can filter based on the memory controller channel.  One or more channels can be tracked at a given time.; Filter for memory controller channel 0 only.",
         "UMask": "0x1",
         "Unit": "HA"
     },
@@ -3898,7 +3898,7 @@
         "EventCode": "0x18",
         "EventName": "UNC_H_WPQ_CYCLES_NO_REG_CREDITS.CHN1",
         "PerPkg": "1",
-        "PublicDescription": "Counts the number of cycles when there are no regular credits available for posting writes from the HA into the iMC.  In order to send writes into the memory controller, the HA must first acquire a credit for the iMC's WPQ (write pending queue).  This queue is broken into regular credits/buffers that are used by general writes, and special requests such as ISOCH writes.  This count only tracks the regular credits  Common high banwidth workloads should be able to make use of all of the regular buffers, but it will be difficult (and uncommon) to make use of both the regular and special buffers at the same time.  One can filter based on the memory controller channel.  One or more channels can be tracked at a given time.; Filter for memory controller channel 1 only.",
+        "PublicDescription": "Counts the number of cycles when there are no regular credits available for posting writes from the HA into the iMC.  In order to send writes into the memory controller, the HA must first acquire a credit for the iMC's WPQ (write pending queue).  This queue is broken into regular credits/buffers that are used by general writes, and special requests such as ISOCH writes.  This count only tracks the regular credits  Common high bandwidth workloads should be able to make use of all of the regular buffers, but it will be difficult (and uncommon) to make use of both the regular and special buffers at the same time.  One can filter based on the memory controller channel.  One or more channels can be tracked at a given time.; Filter for memory controller channel 1 only.",
         "UMask": "0x2",
         "Unit": "HA"
     },
@@ -3908,7 +3908,7 @@
         "EventCode": "0x18",
         "EventName": "UNC_H_WPQ_CYCLES_NO_REG_CREDITS.CHN2",
         "PerPkg": "1",
-        "PublicDescription": "Counts the number of cycles when there are no regular credits available for posting writes from the HA into the iMC.  In order to send writes into the memory controller, the HA must first acquire a credit for the iMC's WPQ (write pending queue).  This queue is broken into regular credits/buffers that are used by general writes, and special requests such as ISOCH writes.  This count only tracks the regular credits  Common high banwidth workloads should be able to make use of all of the regular buffers, but it will be difficult (and uncommon) to make use of both the regular and special buffers at the same time.  One can filter based on the memory controller channel.  One or more channels can be tracked at a given time.; Filter for memory controller channel 2 only.",
+        "PublicDescription": "Counts the number of cycles when there are no regular credits available for posting writes from the HA into the iMC.  In order to send writes into the memory controller, the HA must first acquire a credit for the iMC's WPQ (write pending queue).  This queue is broken into regular credits/buffers that are used by general writes, and special requests such as ISOCH writes.  This count only tracks the regular credits  Common high bandwidth workloads should be able to make use of all of the regular buffers, but it will be difficult (and uncommon) to make use of both the regular and special buffers at the same time.  One can filter based on the memory controller channel.  One or more channels can be tracked at a given time.; Filter for memory controller channel 2 only.",
         "UMask": "0x4",
         "Unit": "HA"
     },
@@ -3918,7 +3918,7 @@
         "EventCode": "0x18",
         "EventName": "UNC_H_WPQ_CYCLES_NO_REG_CREDITS.CHN3",
         "PerPkg": "1",
-        "PublicDescription": "Counts the number of cycles when there are no regular credits available for posting writes from the HA into the iMC.  In order to send writes into the memory controller, the HA must first acquire a credit for the iMC's WPQ (write pending queue).  This queue is broken into regular credits/buffers that are used by general writes, and special requests such as ISOCH writes.  This count only tracks the regular credits  Common high banwidth workloads should be able to make use of all of the regular buffers, but it will be difficult (and uncommon) to make use of both the regular and special buffers at the same time.  One can filter based on the memory controller channel.  One or more channels can be tracked at a given time.; Filter for memory controller channel 3 only.",
+        "PublicDescription": "Counts the number of cycles when there are no regular credits available for posting writes from the HA into the iMC.  In order to send writes into the memory controller, the HA must first acquire a credit for the iMC's WPQ (write pending queue).  This queue is broken into regular credits/buffers that are used by general writes, and special requests such as ISOCH writes.  This count only tracks the regular credits  Common high bandwidth workloads should be able to make use of all of the regular buffers, but it will be difficult (and uncommon) to make use of both the regular and special buffers at the same time.  One can filter based on the memory controller channel.  One or more channels can be tracked at a given time.; Filter for memory controller channel 3 only.",
         "UMask": "0x8",
         "Unit": "HA"
     },
tools/perf/pmu-events/arch/x86/broadwellx/uncore-interconnect.json +8 -28
index 765d44012bba..56d729c8e946 100644
@@ -1,24 +1,4 @@
 [
-    {
-        "BriefDescription": "Number of non data (control) flits transmitted . Derived from unc_q_txl_flits_g0.non_data",
-        "Counter": "0,1,2,3",
-        "EventName": "QPI_CTL_BANDWIDTH_TX",
-        "PerPkg": "1",
-        "PublicDescription": "Counts the number of flits transmitted across the QPI Link.  It includes filters for Idle, protocol, and Data Flits.  Each flit is made up of 80 bits of information (in addition to some ECC data).  In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data).   In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit.  When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits.  Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed.  One can calculate the bandwidth of the link by taking: flits*80b/time.  Note that this is not the same as data bandwidth.  For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information.  To calculate data bandwidth, one should therefore do: data flits * 8B / time (for L0) or 4B instead of 8B for L0p.; Number of non-NULL non-data flits transmitted across QPI.  This basically tracks the protocol overhead on the QPI link.  One can get a good picture of the QPI-link characteristics by evaluating the protocol flits, data flits, and idle/null flits.  This includes the header flits for data packets.",
-        "ScaleUnit": "8Bytes",
-        "UMask": "0x4",
-        "Unit": "QPI"
-    },
-    {
-        "BriefDescription": "Number of data flits transmitted . Derived from unc_q_txl_flits_g0.data",
-        "Counter": "0,1,2,3",
-        "EventName": "QPI_DATA_BANDWIDTH_TX",
-        "PerPkg": "1",
-        "PublicDescription": "Counts the number of flits transmitted across the QPI Link.  It includes filters for Idle, protocol, and Data Flits.  Each flit is made up of 80 bits of information (in addition to some ECC data).  In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data).   In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit.  When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits.  Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed.  One can calculate the bandwidth of the link by taking: flits*80b/time.  Note that this is not the same as data bandwidth.  For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information.  To calculate data bandwidth, one should therefore do: data flits * 8B / time (for L0) or 4B instead of 8B for L0p.; Number of data flits transmitted over QPI.  Each flit contains 64b of data.  This includes both DRS and NCB data flits (coherent and non-coherent).  This can be used to calculate the data bandwidth of the QPI link.  One can get a good picture of the QPI-link characteristics by evaluating the protocol flits, data flits, and idle/null flits.  This does not include the header flits that go in data packets.",
-        "ScaleUnit": "8Bytes",
-        "UMask": "0x2",
-        "Unit": "QPI"
-    },
     {
         "BriefDescription": "Total Write Cache Occupancy; Any Source",
         "Counter": "0,1",
@@ -53,7 +33,7 @@
         "EventCode": "0x13",
         "EventName": "UNC_I_COHERENT_OPS.CLFLUSH",
         "PerPkg": "1",
-        "PublicDescription": "Counts the number of coherency related operations servied by the IRP",
+        "PublicDescription": "Counts the number of coherency related operations serviced by the IRP",
         "UMask": "0x80",
         "Unit": "IRP"
     },
@@ -63,7 +43,7 @@
         "EventCode": "0x13",
         "EventName": "UNC_I_COHERENT_OPS.CRD",
         "PerPkg": "1",
-        "PublicDescription": "Counts the number of coherency related operations servied by the IRP",
+        "PublicDescription": "Counts the number of coherency related operations serviced by the IRP",
         "UMask": "0x2",
         "Unit": "IRP"
     },
@@ -73,7 +53,7 @@
         "EventCode": "0x13",
         "EventName": "UNC_I_COHERENT_OPS.DRD",
         "PerPkg": "1",
-        "PublicDescription": "Counts the number of coherency related operations servied by the IRP",
+        "PublicDescription": "Counts the number of coherency related operations serviced by the IRP",
         "UMask": "0x4",
         "Unit": "IRP"
     },
@@ -83,7 +63,7 @@
         "EventCode": "0x13",
         "EventName": "UNC_I_COHERENT_OPS.PCIDCAHINT",
         "PerPkg": "1",
-        "PublicDescription": "Counts the number of coherency related operations servied by the IRP",
+        "PublicDescription": "Counts the number of coherency related operations serviced by the IRP",
         "UMask": "0x20",
         "Unit": "IRP"
     },
@@ -93,7 +73,7 @@
         "EventCode": "0x13",
         "EventName": "UNC_I_COHERENT_OPS.PCIRDCUR",
         "PerPkg": "1",
-        "PublicDescription": "Counts the number of coherency related operations servied by the IRP",
+        "PublicDescription": "Counts the number of coherency related operations serviced by the IRP",
         "UMask": "0x1",
         "Unit": "IRP"
     },
@@ -103,7 +83,7 @@
         "EventCode": "0x13",
         "EventName": "UNC_I_COHERENT_OPS.PCITOM",
         "PerPkg": "1",
-        "PublicDescription": "Counts the number of coherency related operations servied by the IRP",
+        "PublicDescription": "Counts the number of coherency related operations serviced by the IRP",
         "UMask": "0x10",
         "Unit": "IRP"
     },
@@ -113,7 +93,7 @@
         "EventCode": "0x13",
         "EventName": "UNC_I_COHERENT_OPS.RFO",
         "PerPkg": "1",
-        "PublicDescription": "Counts the number of coherency related operations servied by the IRP",
+        "PublicDescription": "Counts the number of coherency related operations serviced by the IRP",
         "UMask": "0x8",
         "Unit": "IRP"
     },
@@ -123,7 +103,7 @@
         "EventCode": "0x13",
         "EventName": "UNC_I_COHERENT_OPS.WBMTOI",
         "PerPkg": "1",
-        "PublicDescription": "Counts the number of coherency related operations servied by the IRP",
+        "PublicDescription": "Counts the number of coherency related operations serviced by the IRP",
         "UMask": "0x40",
         "Unit": "IRP"
     },
tools/perf/pmu-events/arch/x86/broadwellx/uncore-memory.json +1 -0
index 45555316f8ea..ca09c1286485 100644
@@ -184,6 +184,7 @@
     {
         "BriefDescription": "This event is deprecated. Refer to new event UNC_M_CLOCKTICKS_P",
         "Counter": "0,1,2,3",
+        "Deprecated": "1",
         "EventName": "UNC_M_DCLOCKTICKS",
         "PerPkg": "1",
         "Unit": "iMC"
tools/perf/pmu-events/arch/x86/mapfile.csv +1 -1
index ccbe9be240b3..6405c7627e27 100644
@@ -5,7 +5,7 @@ GenuineIntel-6-C[56],v1.07,arrowlake,core
 GenuineIntel-6-(1C|26|27|35|36),v5,bonnell,core
 GenuineIntel-6-(3D|47),v30,broadwell,core
 GenuineIntel-6-56,v12,broadwellde,core
-GenuineIntel-6-4F,v22,broadwellx,core
+GenuineIntel-6-4F,v23,broadwellx,core
 GenuineIntel-6-55-[56789ABCDEF],v1.22,cascadelakex,core
 GenuineIntel-6-9[6C],v1.05,elkhartlake,core
 GenuineIntel-6-CF,v1.09,emeraldrapids,core
Signature · 1 line
2.48.1.502.g6dc24dfdaf-goog
author reviewer
#7 lore raw

PATCH v8 7/24 perf vendor events: Update CascadelakeX events/metrics

In reply to Ian Rogers

Update events from v1.22 to v1.23.
Update TMA metrics from 4.8 to 5.02.

Bring in the event updates v1.23:
https://github.com/intel/perfmon/commit/8f3665f6be4688fd1dd1e713ba49ca16ec93b856

The TMA 5.02 update is from (with subsequent fixes):
https://github.com/intel/perfmon/commit/1d72913b2d938781fb28f3cc3507aaec5c22d782

---
 .../arch/x86/cascadelakex/clx-metrics.json    | 767 ++++++++++--------
 .../arch/x86/cascadelakex/metricgroups.json   |   9 +-
 .../arch/x86/cascadelakex/uncore-cache.json   |  60 +-
 .../x86/cascadelakex/uncore-interconnect.json |  11 -
 tools/perf/pmu-events/arch/x86/mapfile.csv    |   2 +-
 5 files changed, 464 insertions(+), 385 deletions(-)
tools/perf/pmu-events/arch/x86/cascadelakex/clx-metrics.json +425 -342
index b02a89e14c5d..5729b93a9c68 100644
@@ -55,7 +55,7 @@
         "MetricName": "UNCORE_FREQ"
     },
     {
-        "BriefDescription": "Cycles per instruction retired; indicating how much time each executed instruction took; in units of cycles.",
+        "BriefDescription": "Cycles per instruction retired; indicating how much time each executed instruction took; in units of cycles",
         "MetricExpr": "CPU_CLK_UNHALTED.THREAD / INST_RETIRED.ANY",
         "MetricName": "cpi",
         "ScaleUnit": "1per_instr"
@@ -76,31 +76,31 @@
         "BriefDescription": "Ratio of number of completed page walks (for 2 megabyte page sizes) caused by demand data loads to the total number of completed instructions",
         "MetricExpr": "DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M / INST_RETIRED.ANY",
         "MetricName": "dtlb_2mb_large_page_load_mpi",
-        "PublicDescription": "Ratio of number of completed page walks (for 2 megabyte page sizes) caused by demand data loads to the total number of completed instructions. This implies it missed in the Data Translation Lookaside Buffer (DTLB) and further levels of TLB.",
+        "PublicDescription": "Ratio of number of completed page walks (for 2 megabyte page sizes) caused by demand data loads to the total number of completed instructions. This implies it missed in the Data Translation Lookaside Buffer (DTLB) and further levels of TLB",
         "ScaleUnit": "1per_instr"
     },
     {
         "BriefDescription": "Ratio of number of completed page walks (for all page sizes) caused by demand data loads to the total number of completed instructions",
         "MetricExpr": "DTLB_LOAD_MISSES.WALK_COMPLETED / INST_RETIRED.ANY",
         "MetricName": "dtlb_load_mpi",
-        "PublicDescription": "Ratio of number of completed page walks (for all page sizes) caused by demand data loads to the total number of completed instructions. This implies it missed in the DTLB and further levels of TLB.",
+        "PublicDescription": "Ratio of number of completed page walks (for all page sizes) caused by demand data loads to the total number of completed instructions. This implies it missed in the DTLB and further levels of TLB",
         "ScaleUnit": "1per_instr"
     },
     {
         "BriefDescription": "Ratio of number of completed page walks (for all page sizes) caused by demand data stores to the total number of completed instructions",
         "MetricExpr": "DTLB_STORE_MISSES.WALK_COMPLETED / INST_RETIRED.ANY",
         "MetricName": "dtlb_store_mpi",
-        "PublicDescription": "Ratio of number of completed page walks (for all page sizes) caused by demand data stores to the total number of completed instructions. This implies it missed in the DTLB and further levels of TLB.",
+        "PublicDescription": "Ratio of number of completed page walks (for all page sizes) caused by demand data stores to the total number of completed instructions. This implies it missed in the DTLB and further levels of TLB",
         "ScaleUnit": "1per_instr"
     },
     {
-        "BriefDescription": "Bandwidth of IO reads that are initiated by end device controllers that are requesting memory from the CPU.",
+        "BriefDescription": "Bandwidth of IO reads that are initiated by end device controllers that are requesting memory from the CPU",
         "MetricExpr": "(UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART0 + UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART1 + UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART2 + UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART3) * 4 / 1e6 / duration_time",
         "MetricName": "io_bandwidth_read",
         "ScaleUnit": "1MB/s"
     },
     {
-        "BriefDescription": "Bandwidth of IO writes that are initiated by end device controllers that are writing memory to the CPU.",
+        "BriefDescription": "Bandwidth of IO writes that are initiated by end device controllers that are writing memory to the CPU",
         "MetricExpr": "(UNC_IIO_PAYLOAD_BYTES_IN.MEM_WRITE.PART0 + UNC_IIO_PAYLOAD_BYTES_IN.MEM_WRITE.PART1 + UNC_IIO_PAYLOAD_BYTES_IN.MEM_WRITE.PART2 + UNC_IIO_PAYLOAD_BYTES_IN.MEM_WRITE.PART3) * 4 / 1e6 / duration_time",
         "MetricName": "io_bandwidth_write",
         "ScaleUnit": "1MB/s"
@@ -109,14 +109,14 @@
         "BriefDescription": "Ratio of number of completed page walks (for 2 megabyte and 4 megabyte page sizes) caused by a code fetch to the total number of completed instructions",
         "MetricExpr": "ITLB_MISSES.WALK_COMPLETED_2M_4M / INST_RETIRED.ANY",
         "MetricName": "itlb_large_page_mpi",
-        "PublicDescription": "Ratio of number of completed page walks (for 2 megabyte and 4 megabyte page sizes) caused by a code fetch to the total number of completed instructions. This implies it missed in the Instruction Translation Lookaside Buffer (ITLB) and further levels of TLB.",
+        "PublicDescription": "Ratio of number of completed page walks (for 2 megabyte and 4 megabyte page sizes) caused by a code fetch to the total number of completed instructions. This implies it missed in the Instruction Translation Lookaside Buffer (ITLB) and further levels of TLB",
         "ScaleUnit": "1per_instr"
     },
     {
         "BriefDescription": "Ratio of number of completed page walks (for all page sizes) caused by a code fetch to the total number of completed instructions",
         "MetricExpr": "ITLB_MISSES.WALK_COMPLETED / INST_RETIRED.ANY",
         "MetricName": "itlb_mpi",
-        "PublicDescription": "Ratio of number of completed page walks (for all page sizes) caused by a code fetch to the total number of completed instructions. This implies it missed in the ITLB (Instruction TLB) and further levels of TLB.",
+        "PublicDescription": "Ratio of number of completed page walks (for all page sizes) caused by a code fetch to the total number of completed instructions. This implies it missed in the ITLB (Instruction TLB) and further levels of TLB",
         "ScaleUnit": "1per_instr"
     },
     {
@@ -192,25 +192,25 @@
         "ScaleUnit": "1per_instr"
     },
     {
-        "BriefDescription": "Bandwidth (MB/sec) of read requests that miss the last level cache (LLC) and go to local memory.",
+        "BriefDescription": "Bandwidth (MB/sec) of read requests that miss the last level cache (LLC) and go to local memory",
         "MetricExpr": "UNC_CHA_REQUESTS.READS_LOCAL * 64 / 1e6 / duration_time",
         "MetricName": "llc_miss_local_memory_bandwidth_read",
         "ScaleUnit": "1MB/s"
     },
     {
-        "BriefDescription": "Bandwidth (MB/sec) of write requests that miss the last level cache (LLC) and go to local memory.",
+        "BriefDescription": "Bandwidth (MB/sec) of write requests that miss the last level cache (LLC) and go to local memory",
         "MetricExpr": "UNC_CHA_REQUESTS.WRITES_LOCAL * 64 / 1e6 / duration_time",
         "MetricName": "llc_miss_local_memory_bandwidth_write",
         "ScaleUnit": "1MB/s"
     },
     {
-        "BriefDescription": "Bandwidth (MB/sec) of read requests that miss the last level cache (LLC) and go to remote memory.",
+        "BriefDescription": "Bandwidth (MB/sec) of read requests that miss the last level cache (LLC) and go to remote memory",
         "MetricExpr": "UNC_CHA_REQUESTS.READS_REMOTE * 64 / 1e6 / duration_time",
         "MetricName": "llc_miss_remote_memory_bandwidth_read",
         "ScaleUnit": "1MB/s"
     },
     {
-        "BriefDescription": "Bandwidth (MB/sec) of write requests that miss the last level cache (LLC) and go to remote memory.",
+        "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"
@@ -240,13 +240,13 @@
         "ScaleUnit": "1MB/s"
     },
     {
-        "BriefDescription": "Memory read that miss the last level cache (LLC) addressed to local DRAM as a percentage of total memory read accesses, does not include LLC prefetches.",
+        "BriefDescription": "Memory read that miss the last level cache (LLC) addressed to local DRAM as a percentage of total memory read accesses, does not include LLC prefetches",
         "MetricExpr": "cha@UNC_CHA_TOR_INSERTS.IA_MISS\\,config1\\=0x40432@ / (cha@UNC_CHA_TOR_INSERTS.IA_MISS\\,config1\\=0x40432@ + cha@UNC_CHA_TOR_INSERTS.IA_MISS\\,config1\\=0x40431@)",
         "MetricName": "numa_reads_addressed_to_local_dram",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "Memory reads that miss the last level cache (LLC) addressed to remote DRAM as a percentage of total memory read accesses, does not include LLC prefetches.",
+        "BriefDescription": "Memory reads that miss the last level cache (LLC) addressed to remote DRAM as a percentage of total memory read accesses, does not include LLC prefetches",
         "MetricExpr": "cha@UNC_CHA_TOR_INSERTS.IA_MISS\\,config1\\=0x40431@ / (cha@UNC_CHA_TOR_INSERTS.IA_MISS\\,config1\\=0x40432@ + cha@UNC_CHA_TOR_INSERTS.IA_MISS\\,config1\\=0x40431@)",
         "MetricName": "numa_reads_addressed_to_remote_dram",
         "ScaleUnit": "100%"
@@ -313,12 +313,12 @@
         "MetricExpr": "LD_BLOCKS_PARTIAL.ADDRESS_ALIAS / tma_info_thread_clks",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group",
         "MetricName": "tma_4k_aliasing",
-        "MetricThreshold": "tma_4k_aliasing > 0.2 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
-        "PublicDescription": "This metric estimates how often memory load accesses were aliased by preceding stores (in program order) with a 4K address offset. False match is possible; which incur a few cycles load re-issue. However; the short re-issue duration is often hidden by the out-of-order core and HW optimizations; hence a user may safely ignore a high value of this metric unless it manages to propagate up into parent nodes of the hierarchy (e.g. to L1_Bound).",
+        "MetricThreshold": "tma_4k_aliasing > 0.2 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "PublicDescription": "This metric estimates how often memory load accesses were aliased by preceding stores (in program order) with a 4K address offset. False match is possible; which incur a few cycles load re-issue. However; the short re-issue duration is often hidden by the out-of-order core and HW optimizations; hence a user may safely ignore a high value of this metric unless it manages to propagate up into parent nodes of the hierarchy (e.g. to L1_Bound)",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution ports for ALU operations.",
+        "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution ports for ALU operations",
         "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",
@@ -330,7 +330,7 @@
         "MetricExpr": "34 * (FP_ASSIST.ANY + OTHER_ASSISTS.ANY) / tma_info_thread_slots",
         "MetricGroup": "BvIO;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)",
+        "MetricThreshold": "tma_assists > 0.1 & tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1",
         "PublicDescription": "This metric estimates fraction of slots the CPU retired uops delivered by the Microcode_Sequencer as a result of Assists. Assists are long sequences of uops that are required in certain corner-cases for operations that cannot be handled natively by the execution pipeline. For example; when working with very small floating point values (so-called Denormals); the FP units are not set up to perform these operations natively. Instead; a sequence of instructions to perform the computation on the Denormals is injected into the pipeline. Since these microcode sequences might be dozens of uops long; Assists can be extremely deleterious to performance and they can be avoided in many cases. Sample with: OTHER_ASSISTS.ANY",
         "ScaleUnit": "100%"
     },
@@ -341,7 +341,7 @@
         "MetricName": "tma_backend_bound",
         "MetricThreshold": "tma_backend_bound > 0.2",
         "MetricgroupNoGroup": "TopdownL1",
-        "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound.",
+        "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound",
         "ScaleUnit": "100%"
     },
     {
@@ -351,9 +351,102 @@
         "MetricName": "tma_bad_speculation",
         "MetricThreshold": "tma_bad_speculation > 0.15",
         "MetricgroupNoGroup": "TopdownL1",
-        "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.",
+        "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example",
         "ScaleUnit": "100%"
     },
+    {
+        "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_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches)",
+        "MetricGroup": "BigFootprint;BvBC;Fed;Frontend;IcMiss;MemoryTLB",
+        "MetricName": "tma_bottleneck_big_code",
+        "MetricThreshold": "tma_bottleneck_big_code > 20"
+    },
+    {
+        "BriefDescription": "Total pipeline cost of instructions used for program control-flow - a subset of the Retiring category in TMA",
+        "MetricExpr": "100 * ((BR_INST_RETIRED.ALL_BRANCHES + 2 * BR_INST_RETIRED.NEAR_CALL + INST_RETIRED.NOP) / tma_info_thread_slots)",
+        "MetricGroup": "BvBO;Ret",
+        "MetricName": "tma_bottleneck_branching_overhead",
+        "MetricThreshold": "tma_bottleneck_branching_overhead > 5",
+        "PublicDescription": "Total pipeline cost of instructions used for program control-flow - a subset of the Retiring category in TMA. Examples include function calls; loops and alignments. (A lower bound)"
+    },
+    {
+        "BriefDescription": "Total pipeline cost of external Memory- or Cache-Bandwidth related bottlenecks",
+        "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_mem_bandwidth / (tma_mem_bandwidth + tma_mem_latency)) + tma_memory_bound * (tma_l3_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_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_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_fb_full / (tma_dtlb_load + tma_store_fwd_blk + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_4k_aliasing + tma_fb_full)))",
+        "MetricGroup": "BvMB;Mem;MemoryBW;Offcore;tma_issueBW",
+        "MetricName": "tma_bottleneck_cache_memory_bandwidth",
+        "MetricThreshold": "tma_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_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_mem_latency / (tma_mem_bandwidth + tma_mem_latency)) + tma_memory_bound * (tma_l3_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_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_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound) + tma_memory_bound * (tma_l1_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_l1_latency_dependency / (tma_dtlb_load + tma_store_fwd_blk + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_4k_aliasing + tma_fb_full)) + tma_memory_bound * (tma_l1_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_lock_latency / (tma_dtlb_load + tma_store_fwd_blk + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_4k_aliasing + tma_fb_full)) + tma_memory_bound * (tma_l1_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_split_loads / (tma_dtlb_load + tma_store_fwd_blk + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_4k_aliasing + tma_fb_full)) + tma_memory_bound * (tma_store_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_split_stores / (tma_store_latency + tma_false_sharing + tma_split_stores + tma_dtlb_store)) + tma_memory_bound * (tma_store_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_store_latency / (tma_store_latency + tma_false_sharing + tma_split_stores + tma_dtlb_store)))",
+        "MetricGroup": "BvML;Mem;MemoryLat;Offcore;tma_issueLat",
+        "MetricName": "tma_bottleneck_cache_memory_latency",
+        "MetricThreshold": "tma_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_serializing_operation + tma_ports_utilization) + tma_core_bound * (tma_ports_utilization / (tma_divider + tma_serializing_operation + tma_ports_utilization)) * (tma_ports_utilized_3m / (tma_ports_utilized_0 + tma_ports_utilized_1 + tma_ports_utilized_2 + tma_ports_utilized_3m)))",
+        "MetricGroup": "BvCB;Cor;tma_issueComp",
+        "MetricName": "tma_bottleneck_compute_bound_est",
+        "MetricThreshold": "tma_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"
+    },
+    {
+        "BriefDescription": "Total pipeline cost of instruction fetch bandwidth related bottlenecks (when the front-end could not sustain operations delivery to the back-end)",
+        "MetricExpr": "100 * (tma_frontend_bound - (1 - 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts) * tma_fetch_latency * tma_mispredicts_resteers / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_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_mispredicts_resteers + tma_clears_resteers + tma_unknown_branches)) / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches)) - tma_bottleneck_big_code",
+        "MetricGroup": "BvFB;Fed;FetchBW;Frontend",
+        "MetricName": "tma_bottleneck_instruction_fetch_bw",
+        "MetricThreshold": "tma_bottleneck_instruction_fetch_bw > 20"
+    },
+    {
+        "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_mispredicts_resteers + tma_clears_resteers + tma_unknown_branches)) / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_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_serializing_operation + tma_ports_utilization) + tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * tma_heavy_operations)",
+        "MetricGroup": "Bad;BvIO;Cor;Ret;tma_issueMS",
+        "MetricName": "tma_bottleneck_irregular_overhead",
+        "MetricThreshold": "tma_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)",
+        "MetricExpr": "100 * (tma_memory_bound * (tma_l1_bound / max(tma_memory_bound, tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_dtlb_load / max(tma_l1_bound, tma_dtlb_load + tma_store_fwd_blk + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_4k_aliasing + tma_fb_full)) + tma_memory_bound * (tma_store_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_dtlb_store / (tma_store_latency + tma_false_sharing + tma_split_stores + tma_dtlb_store)))",
+        "MetricGroup": "BvMT;Mem;MemoryTLB;Offcore;tma_issueTLB",
+        "MetricName": "tma_bottleneck_memory_data_tlbs",
+        "MetricThreshold": "tma_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"
+    },
+    {
+        "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_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound) * (tma_mem_latency / (tma_mem_bandwidth + tma_mem_latency)) * tma_remote_cache / (tma_local_mem + tma_remote_mem + tma_remote_cache) + tma_l3_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_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_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound) * tma_false_sharing / (tma_store_latency + tma_false_sharing + tma_split_stores + tma_dtlb_store - tma_store_latency)) + tma_machine_clears * (1 - tma_other_nukes / tma_other_nukes))",
+        "MetricGroup": "BvMS;LockCont;Mem;Offcore;tma_issueSyncxn",
+        "MetricName": "tma_bottleneck_memory_synchronization",
+        "MetricThreshold": "tma_bottleneck_memory_synchronization > 10",
+        "PublicDescription": "Total pipeline cost of Memory Synchronization related bottlenecks (data transfers and coherency updates across processors). Related metrics: tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_machine_clears, tma_remote_cache"
+    },
+    {
+        "BriefDescription": "Total pipeline cost of Branch Misprediction related bottlenecks",
+        "MetricExpr": "100 * (1 - 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts) * (tma_branch_mispredicts + tma_fetch_latency * tma_mispredicts_resteers / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches))",
+        "MetricGroup": "Bad;BadSpec;BrMispredicts;BvMP;tma_issueBM",
+        "MetricName": "tma_bottleneck_mispredictions",
+        "MetricThreshold": "tma_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 in the back-end",
+        "MetricExpr": "100 - (tma_bottleneck_big_code + tma_bottleneck_instruction_fetch_bw + tma_bottleneck_mispredictions + tma_bottleneck_cache_memory_bandwidth + tma_bottleneck_cache_memory_latency + tma_bottleneck_memory_data_tlbs + tma_bottleneck_memory_synchronization + tma_bottleneck_compute_bound_est + tma_bottleneck_irregular_overhead + tma_bottleneck_branching_overhead + tma_bottleneck_useful_work)",
+        "MetricGroup": "BvOB;Cor;Offcore",
+        "MetricName": "tma_bottleneck_other_bottlenecks",
+        "MetricThreshold": "tma_bottleneck_other_bottlenecks > 20",
+        "PublicDescription": "Total pipeline cost of remaining bottlenecks in the back-end. Examples include data-dependencies (Core Bound when Low ILP) and other unlisted memory-related stalls"
+    },
+    {
+        "BriefDescription": "Total pipeline cost of \"useful operations\" - the portion of Retiring category not covered by Branching_Overhead nor Irregular_Overhead",
+        "MetricExpr": "100 * (tma_retiring - (BR_INST_RETIRED.ALL_BRANCHES + 2 * BR_INST_RETIRED.NEAR_CALL + INST_RETIRED.NOP) / tma_info_thread_slots - tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * tma_heavy_operations)",
+        "MetricGroup": "BvUW;Ret",
+        "MetricName": "tma_bottleneck_useful_work",
+        "MetricThreshold": "tma_bottleneck_useful_work > 20"
+    },
     {
         "BriefDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction",
         "MetricConstraint": "NO_GROUP_EVENTS",
@@ -362,7 +455,7 @@
         "MetricName": "tma_branch_mispredicts",
         "MetricThreshold": "tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15",
         "MetricgroupNoGroup": "TopdownL2",
-        "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction.  These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_info_bad_spec_branch_misprediction_cost, tma_info_bottleneck_mispredictions, tma_mispredicts_resteers",
+        "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction.  These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_bottleneck_mispredictions, tma_info_bad_spec_branch_misprediction_cost, tma_mispredicts_resteers",
         "ScaleUnit": "100%"
     },
     {
@@ -370,8 +463,8 @@
         "MetricExpr": "INT_MISC.CLEAR_RESTEER_CYCLES / tma_info_thread_clks + tma_unknown_branches",
         "MetricGroup": "FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group",
         "MetricName": "tma_branch_resteers",
-        "MetricThreshold": "tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)",
-        "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers. Branch Resteers estimates the Frontend delay in fetching operations from corrected path; following all sorts of miss-predicted branches. For example; branchy code with lots of miss-predictions might get categorized under Branch Resteers. Note the value of this node may overlap with its siblings. Sample with: BR_MISP_RETIRED.ALL_BRANCHES",
+        "MetricThreshold": "tma_branch_resteers > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+        "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers. Branch Resteers estimates the Frontend delay in fetching operations from corrected path; following all sorts of miss-predicted branches. For example; branchy code with lots of miss-predictions might get categorized under Branch Resteers. Note the value of this node may overlap with its siblings. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_l3_hit_latency, tma_store_latency",
         "ScaleUnit": "100%"
     },
     {
@@ -379,8 +472,8 @@
         "MetricExpr": "max(0, tma_microcode_sequencer - tma_assists)",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_microcode_sequencer_group",
         "MetricName": "tma_cisc",
-        "MetricThreshold": "tma_cisc > 0.1 & (tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1)",
-        "PublicDescription": "This metric estimates fraction of cycles the CPU retired uops originated from CISC (complex instruction set computer) instruction. A CISC instruction has multiple uops that are required to perform the instruction's functionality as in the case of read-modify-write as an example. Since these instructions require multiple uops they may or may not imply sub-optimal use of machine resources.",
+        "MetricThreshold": "tma_cisc > 0.1 & tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1",
+        "PublicDescription": "This metric estimates fraction of cycles the CPU retired uops originated from CISC (complex instruction set computer) instruction. A CISC instruction has multiple uops that are required to perform the instruction's functionality as in the case of read-modify-write as an example. Since these instructions require multiple uops they may or may not imply sub-optimal use of machine resources",
         "ScaleUnit": "100%"
     },
     {
@@ -388,18 +481,50 @@
         "MetricExpr": "(1 - BR_MISP_RETIRED.ALL_BRANCHES / (BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT)) * INT_MISC.CLEAR_RESTEER_CYCLES / tma_info_thread_clks",
         "MetricGroup": "BadSpec;MachineClears;TopdownL4;tma_L4_group;tma_branch_resteers_group;tma_issueMC",
         "MetricName": "tma_clears_resteers",
-        "MetricThreshold": "tma_clears_resteers > 0.05 & (tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))",
+        "MetricThreshold": "tma_clears_resteers > 0.05 & tma_branch_resteers > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
         "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Machine Clears. Sample with: INT_MISC.CLEAR_RESTEER_CYCLES. Related metrics: tma_l1_bound, tma_machine_clears, tma_microcode_sequencer, tma_ms_switches",
         "ScaleUnit": "100%"
     },
+    {
+        "BriefDescription": "This metric roughly estimates the fraction of cycles where the (first level) ITLB was missed by instructions fetches, that later on hit in second-level TLB (STLB)",
+        "MetricExpr": "max(0, tma_itlb_misses - tma_code_stlb_miss)",
+        "MetricGroup": "FetchLat;MemoryTLB;TopdownL4;tma_L4_group;tma_itlb_misses_group",
+        "MetricName": "tma_code_stlb_hit",
+        "MetricThreshold": "tma_code_stlb_hit > 0.05 & tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+        "ScaleUnit": "100%"
+    },
+    {
+        "BriefDescription": "This metric estimates the fraction of cycles where the Second-level TLB (STLB) was missed by instruction fetches, performing a hardware page walk",
+        "MetricExpr": "ITLB_MISSES.WALK_ACTIVE / tma_info_thread_clks",
+        "MetricGroup": "FetchLat;MemoryTLB;TopdownL4;tma_L4_group;tma_itlb_misses_group",
+        "MetricName": "tma_code_stlb_miss",
+        "MetricThreshold": "tma_code_stlb_miss > 0.05 & tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+        "ScaleUnit": "100%"
+    },
+    {
+        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 2 or 4 MB pages for (instruction) code accesses",
+        "MetricExpr": "tma_code_stlb_miss * ITLB_MISSES.WALK_COMPLETED_2M_4M / (ITLB_MISSES.WALK_COMPLETED_4K + ITLB_MISSES.WALK_COMPLETED_2M_4M)",
+        "MetricGroup": "FetchLat;MemoryTLB;TopdownL5;tma_L5_group;tma_code_stlb_miss_group",
+        "MetricName": "tma_code_stlb_miss_2m",
+        "MetricThreshold": "tma_code_stlb_miss_2m > 0.05 & tma_code_stlb_miss > 0.05 & tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+        "ScaleUnit": "100%"
+    },
+    {
+        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 4 KB pages for (instruction) code accesses",
+        "MetricExpr": "tma_code_stlb_miss * ITLB_MISSES.WALK_COMPLETED_4K / (ITLB_MISSES.WALK_COMPLETED_4K + ITLB_MISSES.WALK_COMPLETED_2M_4M)",
+        "MetricGroup": "FetchLat;MemoryTLB;TopdownL5;tma_L5_group;tma_code_stlb_miss_group",
+        "MetricName": "tma_code_stlb_miss_4k",
+        "MetricThreshold": "tma_code_stlb_miss_4k > 0.05 & tma_code_stlb_miss > 0.05 & tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+        "ScaleUnit": "100%"
+    },
     {
         "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_core_frequency * (MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM * (OCR.DEMAND_DATA_RD.L3_HIT.HITM_OTHER_CORE / (OCR.DEMAND_DATA_RD.L3_HIT.HITM_OTHER_CORE + OCR.DEMAND_DATA_RD.L3_HIT.HIT_OTHER_CORE_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": "BvMS;DataSharing;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group",
+        "MetricExpr": "((47.5 * tma_info_system_core_frequency - 3.5 * tma_info_system_core_frequency) * (MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM * (OCR.DEMAND_DATA_RD.L3_HIT.HITM_OTHER_CORE / (OCR.DEMAND_DATA_RD.L3_HIT.HITM_OTHER_CORE + OCR.DEMAND_DATA_RD.L3_HIT.HIT_OTHER_CORE_FWD))) + (47.5 * tma_info_system_core_frequency - 3.5 * 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": "BvMS;DataSharing;LockCont;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))",
-        "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses. Contested accesses occur when data written by one Logical Processor are read by another Logical Processor on a different Physical Core. Examples of contested accesses include synchronizations such as locks; true data sharing such as modified locked variables; and false sharing. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM_PS;MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS_PS. Related metrics: tma_data_sharing, tma_false_sharing, tma_machine_clears, tma_remote_cache",
+        "MetricThreshold": "tma_contested_accesses > 0.05 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses. Contested accesses occur when data written by one Logical Processor are read by another Logical Processor on a different Physical Core. Examples of contested accesses include synchronizations such as locks; true data sharing such as modified locked variables; and false sharing. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM, MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS. Related metrics: tma_bottleneck_memory_synchronization, tma_data_sharing, tma_false_sharing, tma_machine_clears, tma_remote_cache",
         "ScaleUnit": "100%"
     },
     {
@@ -410,25 +535,25 @@
         "MetricName": "tma_core_bound",
         "MetricThreshold": "tma_core_bound > 0.1 & tma_backend_bound > 0.2",
         "MetricgroupNoGroup": "TopdownL2",
-        "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck.  Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations).",
+        "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck.  Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations)",
         "ScaleUnit": "100%"
     },
     {
         "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_core_frequency * (MEM_LOAD_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM * (1 - OCR.DEMAND_DATA_RD.L3_HIT.HITM_OTHER_CORE / (OCR.DEMAND_DATA_RD.L3_HIT.HITM_OTHER_CORE + OCR.DEMAND_DATA_RD.L3_HIT.HIT_OTHER_CORE_FWD))) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks",
+        "MetricExpr": "(47.5 * tma_info_system_core_frequency - 3.5 * tma_info_system_core_frequency) * (MEM_LOAD_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM * (1 - OCR.DEMAND_DATA_RD.L3_HIT.HITM_OTHER_CORE / (OCR.DEMAND_DATA_RD.L3_HIT.HITM_OTHER_CORE + OCR.DEMAND_DATA_RD.L3_HIT.HIT_OTHER_CORE_FWD))) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks",
         "MetricGroup": "BvMS;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))",
-        "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses. Data shared by multiple Logical Processors (even just read shared) may cause increased access latency due to cache coherency. Excessive data sharing can drastically harm multithreaded performance. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_HIT_PS. Related metrics: tma_contested_accesses, tma_false_sharing, tma_machine_clears, tma_remote_cache",
+        "MetricThreshold": "tma_data_sharing > 0.05 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses. Data shared by multiple Logical Processors (even just read shared) may cause increased access latency due to cache coherency. Excessive data sharing can drastically harm multithreaded performance. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_HIT. Related metrics: tma_bottleneck_memory_synchronization, tma_contested_accesses, tma_false_sharing, tma_machine_clears, tma_remote_cache",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "This metric represents fraction of cycles where decoder-0 was the only active decoder",
-        "MetricExpr": "(cpu@INST_DECODED.DECODERS\\,cmask\\=1@ - cpu@INST_DECODED.DECODERS\\,cmask\\=2@) / tma_info_core_core_clks / 2",
+        "MetricExpr": "(cpu@INST_DECODED.DECODERS\\,cmask\\=0x1@ - cpu@INST_DECODED.DECODERS\\,cmask\\=0x2@) / 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 > 0.2)",
+        "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%"
     },
@@ -437,18 +562,18 @@
         "MetricExpr": "ARITH.DIVIDER_ACTIVE / tma_info_thread_clks",
         "MetricGroup": "BvCB;TopdownL3;tma_L3_group;tma_core_bound_group",
         "MetricName": "tma_divider",
-        "MetricThreshold": "tma_divider > 0.2 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)",
+        "MetricThreshold": "tma_divider > 0.2 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
         "PublicDescription": "This metric represents fraction of cycles where the Divider unit was active. Divide and square root instructions are performed by the Divider unit and can take considerably longer latency than integer or Floating Point addition; subtraction; or multiplication. Sample with: ARITH.DIVIDER_ACTIVE",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "This metric estimates how often the CPU was stalled on accesses to external memory (DRAM) by loads",
         "MetricConstraint": "NO_GROUP_EVENTS",
-        "MetricExpr": "(CYCLE_ACTIVITY.STALLS_L3_MISS / tma_info_thread_clks + (CYCLE_ACTIVITY.STALLS_L1D_MISS - CYCLE_ACTIVITY.STALLS_L2_MISS) / tma_info_thread_clks - tma_l2_bound - tma_pmm_bound if #has_pmem > 0 else CYCLE_ACTIVITY.STALLS_L3_MISS / tma_info_thread_clks + (CYCLE_ACTIVITY.STALLS_L1D_MISS - CYCLE_ACTIVITY.STALLS_L2_MISS) / tma_info_thread_clks - tma_l2_bound)",
+        "MetricExpr": "CYCLE_ACTIVITY.STALLS_L3_MISS / tma_info_thread_clks + (CYCLE_ACTIVITY.STALLS_L1D_MISS - CYCLE_ACTIVITY.STALLS_L2_MISS) / tma_info_thread_clks - tma_l2_bound",
         "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group",
         "MetricName": "tma_dram_bound",
-        "MetricThreshold": "tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)",
-        "PublicDescription": "This metric estimates how often the CPU was stalled on accesses to external memory (DRAM) by loads. Better caching can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L3_MISS_PS",
+        "MetricThreshold": "tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "PublicDescription": "This metric estimates how often the CPU was stalled on accesses to external memory (DRAM) by loads. Better caching can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L3_MISS",
         "ScaleUnit": "100%"
     },
     {
@@ -457,7 +582,7 @@
         "MetricGroup": "DSB;FetchBW;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group",
         "MetricName": "tma_dsb",
         "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.",
+        "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%"
     },
     {
@@ -465,47 +590,47 @@
         "MetricExpr": "DSB2MITE_SWITCHES.PENALTY_CYCLES / tma_info_thread_clks",
         "MetricGroup": "DSBmiss;FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueFB",
         "MetricName": "tma_dsb_switches",
-        "MetricThreshold": "tma_dsb_switches > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)",
-        "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines. The DSB (decoded i-cache) is a Uop Cache where the front-end directly delivers Uops (micro operations) avoiding heavy x86 decoding. The DSB pipeline has shorter latency and delivered higher bandwidth than the MITE (legacy instruction decode pipeline). Switching between the two pipelines can cause penalties hence this metric measures the exposed penalty. Sample with: FRONTEND_RETIRED.DSB_MISS_PS. Related metrics: tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp",
+        "MetricThreshold": "tma_dsb_switches > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+        "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines. The DSB (decoded i-cache) is a Uop Cache where the front-end directly delivers Uops (micro operations) avoiding heavy x86 decoding. The DSB pipeline has shorter latency and delivered higher bandwidth than the MITE (legacy instruction decode pipeline). Switching between the two pipelines can cause penalties hence this metric measures the exposed penalty. Sample with: FRONTEND_RETIRED.DSB_MISS. Related metrics: tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses",
         "MetricConstraint": "NO_GROUP_EVENTS_NMI",
-        "MetricExpr": "min(9 * cpu@DTLB_LOAD_MISSES.STLB_HIT\\,cmask\\=1@ + DTLB_LOAD_MISSES.WALK_ACTIVE, max(CYCLE_ACTIVITY.CYCLES_MEM_ANY - CYCLE_ACTIVITY.CYCLES_L1D_MISS, 0)) / tma_info_thread_clks",
+        "MetricExpr": "min(9 * cpu@DTLB_LOAD_MISSES.STLB_HIT\\,cmask\\=0x1@ + DTLB_LOAD_MISSES.WALK_ACTIVE, max(CYCLE_ACTIVITY.CYCLES_MEM_ANY - CYCLE_ACTIVITY.CYCLES_L1D_MISS, 0)) / tma_info_thread_clks",
         "MetricGroup": "BvMT;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, tma_info_bottleneck_memory_synchronization",
+        "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. Related metrics: tma_bottleneck_memory_data_tlbs, tma_dtlb_store",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses",
-        "MetricExpr": "(9 * cpu@DTLB_STORE_MISSES.STLB_HIT\\,cmask\\=1@ + DTLB_STORE_MISSES.WALK_ACTIVE) / tma_info_core_core_clks",
+        "MetricExpr": "(9 * cpu@DTLB_STORE_MISSES.STLB_HIT\\,cmask\\=0x1@ + DTLB_STORE_MISSES.WALK_ACTIVE) / tma_info_core_core_clks",
         "MetricGroup": "BvMT;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, tma_info_bottleneck_memory_synchronization",
+        "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. Related metrics: tma_bottleneck_memory_data_tlbs, tma_dtlb_load",
         "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_core_frequency * (OCR.DEMAND_RFO.L3_MISS.REMOTE_HITM + OCR.PF_L2_RFO.L3_MISS.REMOTE_HITM) + 47.5 * tma_info_system_core_frequency * (OCR.DEMAND_RFO.L3_HIT.HITM_OTHER_CORE + OCR.PF_L2_RFO.L3_HIT.HITM_OTHER_CORE)) / tma_info_thread_clks",
-        "MetricGroup": "BvMS;DataSharing;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_store_bound_group",
+        "MetricGroup": "BvMS;DataSharing;LockCont;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))",
-        "PublicDescription": "This metric roughly estimates how often CPU was handling synchronizations due to False Sharing. False Sharing is a multithreading hiccup; where multiple Logical Processors contend on different data-elements mapped into the same cache line. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM_PS;OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.SNOOP_HITM. Related metrics: tma_contested_accesses, tma_data_sharing, tma_machine_clears, tma_remote_cache",
+        "MetricThreshold": "tma_false_sharing > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "PublicDescription": "This metric roughly estimates how often CPU was handling synchronizations due to False Sharing. False Sharing is a multithreading hiccup; where multiple Logical Processors contend on different data-elements mapped into the same cache line. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM, OCR.DEMAND_RFO.L3_HIT.HITM_OTHER_CORE. Related metrics: tma_bottleneck_memory_synchronization, tma_contested_accesses, tma_data_sharing, tma_machine_clears, tma_remote_cache",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed",
         "MetricConstraint": "NO_GROUP_EVENTS_NMI",
-        "MetricExpr": "tma_info_memory_load_miss_real_latency * cpu@L1D_PEND_MISS.FB_FULL\\,cmask\\=1@ / tma_info_thread_clks",
-        "MetricGroup": "BvMS;MemoryBW;TopdownL4;tma_L4_group;tma_issueBW;tma_issueSL;tma_issueSmSt;tma_l1_bound_group",
+        "MetricExpr": "tma_info_memory_load_miss_real_latency * cpu@L1D_PEND_MISS.FB_FULL\\,cmask\\=0x1@ / tma_info_thread_clks",
+        "MetricGroup": "BvMB;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_cache_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_bottleneck_cache_memory_bandwidth, tma_info_system_dram_bw_use, tma_mem_bandwidth, tma_sq_full, tma_store_latency",
         "ScaleUnit": "100%"
     },
     {
@@ -515,7 +640,7 @@
         "MetricName": "tma_fetch_bandwidth",
         "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_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp",
+        "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues.  For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Sample with: FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1, FRONTEND_RETIRED.LATENCY_GE_1, FRONTEND_RETIRED.LATENCY_GE_2. Related metrics: tma_dsb_switches, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp",
         "ScaleUnit": "100%"
     },
     {
@@ -525,17 +650,17 @@
         "MetricName": "tma_fetch_latency",
         "MetricThreshold": "tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
         "MetricgroupNoGroup": "TopdownL2",
-        "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues.  For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: FRONTEND_RETIRED.LATENCY_GE_16_PS;FRONTEND_RETIRED.LATENCY_GE_8_PS",
+        "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues.  For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: FRONTEND_RETIRED.LATENCY_GE_16, FRONTEND_RETIRED.LATENCY_GE_8",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric represents fraction of slots where the CPU was retiring instructions that that are decoder into two or up to ([SNB+] four; [ADL+] five) uops",
+        "BriefDescription": "This metric represents fraction of slots where the CPU was retiring instructions that that are decoder into two or more uops",
         "MetricConstraint": "NO_GROUP_EVENTS_NMI",
         "MetricExpr": "tma_heavy_operations - tma_microcode_sequencer",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_heavy_operations_group;tma_issueD0",
         "MetricName": "tma_few_uops_instructions",
         "MetricThreshold": "tma_few_uops_instructions > 0.05 & tma_heavy_operations > 0.1",
-        "PublicDescription": "This metric represents fraction of slots where the CPU was retiring instructions that that are decoder into two or up to ([SNB+] four; [ADL+] five) uops. This highly-correlates with the number of uops in such instructions. Related metrics: tma_decoder0_alone",
+        "PublicDescription": "This metric represents fraction of slots where the CPU was retiring instructions that that are decoder into two or more uops. This highly-correlates with the number of uops in such instructions. Related metrics: tma_decoder0_alone",
         "ScaleUnit": "100%"
     },
     {
@@ -545,7 +670,7 @@
         "MetricGroup": "HPC;TopdownL3;tma_L3_group;tma_light_operations_group",
         "MetricName": "tma_fp_arith",
         "MetricThreshold": "tma_fp_arith > 0.2 & tma_light_operations > 0.6",
-        "PublicDescription": "This metric represents overall arithmetic floating-point (FP) operations fraction the CPU has executed (retired). Note this metric's value may exceed its parent due to use of \"Uops\" CountDomain and FMA double-counting.",
+        "PublicDescription": "This metric represents overall arithmetic floating-point (FP) operations fraction the CPU has executed (retired). Note this metric's value may exceed its parent due to use of \"Uops\" CountDomain and FMA double-counting",
         "ScaleUnit": "100%"
     },
     {
@@ -554,7 +679,7 @@
         "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).",
+        "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%"
     },
     {
@@ -562,17 +687,17 @@
         "MetricExpr": "FP_ARITH_INST_RETIRED.SCALAR / UOPS_RETIRED.RETIRE_SLOTS",
         "MetricGroup": "Compute;Flops;TopdownL4;tma_L4_group;tma_fp_arith_group;tma_issue2P",
         "MetricName": "tma_fp_scalar",
-        "MetricThreshold": "tma_fp_scalar > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6)",
+        "MetricThreshold": "tma_fp_scalar > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6",
         "PublicDescription": "This metric approximates arithmetic floating-point (FP) scalar uops fraction the CPU has retired. May overcount due to FMA double counting. Related metrics: tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "This metric approximates arithmetic floating-point (FP) vector uops fraction the CPU has retired aggregated across all vector widths",
         "MetricConstraint": "NO_GROUP_EVENTS",
-        "MetricExpr": "cpu@FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE\\,umask\\=0xfc@ / UOPS_RETIRED.RETIRE_SLOTS",
+        "MetricExpr": "cpu@FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE\\,umask\\=0xFC@ / UOPS_RETIRED.RETIRE_SLOTS",
         "MetricGroup": "Compute;Flops;TopdownL4;tma_L4_group;tma_fp_arith_group;tma_issue2P",
         "MetricName": "tma_fp_vector",
-        "MetricThreshold": "tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6)",
+        "MetricThreshold": "tma_fp_vector > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6",
         "PublicDescription": "This metric approximates arithmetic floating-point (FP) vector uops fraction the CPU has retired aggregated across all vector widths. May overcount due to FMA double counting. Related metrics: tma_fp_scalar, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2",
         "ScaleUnit": "100%"
     },
@@ -581,8 +706,8 @@
         "MetricExpr": "(FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE) / UOPS_RETIRED.RETIRE_SLOTS",
         "MetricGroup": "Compute;Flops;TopdownL5;tma_L5_group;tma_fp_vector_group;tma_issue2P",
         "MetricName": "tma_fp_vector_128b",
-        "MetricThreshold": "tma_fp_vector_128b > 0.1 & (tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6))",
-        "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 128-bit wide vectors. May overcount due to FMA double counting. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2",
+        "MetricThreshold": "tma_fp_vector_128b > 0.1 & tma_fp_vector > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6",
+        "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 128-bit wide vectors. May overcount due to FMA double counting prior to LNL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2",
         "ScaleUnit": "100%"
     },
     {
@@ -590,8 +715,8 @@
         "MetricExpr": "(FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE) / UOPS_RETIRED.RETIRE_SLOTS",
         "MetricGroup": "Compute;Flops;TopdownL5;tma_L5_group;tma_fp_vector_group;tma_issue2P",
         "MetricName": "tma_fp_vector_256b",
-        "MetricThreshold": "tma_fp_vector_256b > 0.1 & (tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6))",
-        "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 256-bit wide vectors. May overcount due to FMA double counting. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2",
+        "MetricThreshold": "tma_fp_vector_256b > 0.1 & tma_fp_vector > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6",
+        "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 256-bit wide vectors. May overcount due to FMA double counting prior to LNL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2",
         "ScaleUnit": "100%"
     },
     {
@@ -599,7 +724,7 @@
         "MetricExpr": "(FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE) / UOPS_RETIRED.RETIRE_SLOTS",
         "MetricGroup": "Compute;Flops;TopdownL5;tma_L5_group;tma_fp_vector_group;tma_issue2P",
         "MetricName": "tma_fp_vector_512b",
-        "MetricThreshold": "tma_fp_vector_512b > 0.1 & (tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6))",
+        "MetricThreshold": "tma_fp_vector_512b > 0.1 & tma_fp_vector > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6",
         "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 512-bit wide vectors. May overcount due to FMA double counting. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2",
         "ScaleUnit": "100%"
     },
@@ -610,50 +735,50 @@
         "MetricName": "tma_frontend_bound",
         "MetricThreshold": "tma_frontend_bound > 0.15",
         "MetricgroupNoGroup": "TopdownL1",
-        "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound. Sample with: FRONTEND_RETIRED.LATENCY_GE_4_PS",
+        "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound. Sample with: FRONTEND_RETIRED.LATENCY_GE_4",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric represents fraction of slots where the CPU was retiring fused instructions -- where one uop can represent multiple contiguous instructions",
+        "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": "Branches;BvBO;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. 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!)}",
+        "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%"
     },
     {
-        "BriefDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences",
+        "BriefDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations , instructions that require two or more uops or micro-coded sequences",
         "MetricExpr": "(UOPS_RETIRED.RETIRE_SLOTS + UOPS_RETIRED.MACRO_FUSED - INST_RETIRED.ANY) / tma_info_thread_slots",
         "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group",
         "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. ([ICL+] Note this may overcount due to approximation using indirect events; [ADL+] .)",
+        "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",
+        "MetricExpr": "(ICACHE_16B.IFDATA_STALL + 2 * cpu@ICACHE_16B.IFDATA_STALL\\,cmask\\=0x1\\,edge\\=0x1@) / tma_info_thread_clks",
         "MetricGroup": "BigFootprint;BvBC;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",
+        "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, FRONTEND_RETIRED.L1I_MISS",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "Branch Misprediction Cost: Fraction of TMA slots wasted per non-speculative branch misprediction (retired JEClear)",
-        "MetricExpr": "tma_info_bottleneck_mispredictions * tma_info_thread_slots / BR_MISP_RETIRED.ALL_BRANCHES / 100",
+        "BriefDescription": "Branch Misprediction Cost: Cycles representing fraction of TMA slots wasted per non-speculative branch misprediction (retired JEClear)",
+        "MetricExpr": "tma_bottleneck_mispredictions * tma_info_thread_slots / 4 / 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"
+        "PublicDescription": "Branch Misprediction Cost: Cycles representing fraction of TMA slots wasted per non-speculative branch misprediction (retired JEClear). Related metrics: tma_bottleneck_mispredictions, tma_branch_mispredicts, tma_mispredicts_resteers"
     },
     {
-        "BriefDescription": "Instructions per retired mispredicts for indirect CALL or JMP branches (lower number means higher occurrence rate).",
+        "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 * BR_MISP_EXEC.INDIRECT)",
         "MetricGroup": "Bad;BrMispredicts",
         "MetricName": "tma_info_bad_spec_ipmisp_indirect",
-        "MetricThreshold": "tma_info_bad_spec_ipmisp_indirect < 1e3"
+        "MetricThreshold": "tma_info_bad_spec_ipmisp_indirect < 1000"
     },
     {
         "BriefDescription": "Number of Instructions per non-speculative Branch Misprediction (JEClear) (lower number means higher occurrence rate)",
@@ -663,7 +788,7 @@
         "MetricThreshold": "tma_info_bad_spec_ipmispredict < 200"
     },
     {
-        "BriefDescription": "Speculative to Retired ratio of all clears (covering mispredicts and nukes)",
+        "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"
@@ -678,8 +803,8 @@
     },
     {
         "BriefDescription": "Total pipeline cost of DSB (uop cache) hits - subset of the Instruction_Fetch_BW Bottleneck",
-        "MetricExpr": "100 * (tma_frontend_bound * (tma_fetch_bandwidth / (tma_fetch_bandwidth + tma_fetch_latency)) * (tma_dsb / (tma_dsb + tma_mite)))",
-        "MetricGroup": "DSB;FetchBW;tma_issueFB",
+        "MetricExpr": "100 * (tma_frontend_bound * (tma_fetch_bandwidth / (tma_fetch_latency + tma_fetch_bandwidth)) * (tma_dsb / (tma_mite + tma_dsb)))",
+        "MetricGroup": "DSB;Fed;FetchBW;tma_issueFB",
         "MetricName": "tma_info_botlnk_l2_dsb_bandwidth",
         "MetricThreshold": "tma_info_botlnk_l2_dsb_bandwidth > 10",
         "PublicDescription": "Total pipeline cost of DSB (uop cache) hits - subset of the Instruction_Fetch_BW Bottleneck. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp"
@@ -687,7 +812,7 @@
     {
         "BriefDescription": "Total pipeline cost of DSB (uop cache) misses - subset of the Instruction_Fetch_BW Bottleneck",
         "MetricConstraint": "NO_GROUP_EVENTS",
-        "MetricExpr": "100 * (tma_fetch_latency * tma_dsb_switches / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) + tma_fetch_bandwidth * tma_mite / (tma_dsb + tma_mite))",
+        "MetricExpr": "100 * (tma_fetch_latency * tma_dsb_switches / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches) + tma_fetch_bandwidth * tma_mite / (tma_mite + tma_dsb))",
         "MetricGroup": "DSBmiss;Fed;tma_issueFB",
         "MetricName": "tma_info_botlnk_l2_dsb_misses",
         "MetricThreshold": "tma_info_botlnk_l2_dsb_misses > 10",
@@ -695,108 +820,10 @@
     },
     {
         "BriefDescription": "Total pipeline cost of Instruction Cache misses - subset of the Big_Code Bottleneck",
-        "MetricExpr": "100 * (tma_fetch_latency * tma_icache_misses / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches))",
+        "MetricExpr": "100 * (tma_fetch_latency * tma_icache_misses / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches))",
         "MetricGroup": "Fed;FetchLat;IcMiss;tma_issueFL",
         "MetricName": "tma_info_botlnk_l2_ic_misses",
-        "MetricThreshold": "tma_info_botlnk_l2_ic_misses > 5",
-        "PublicDescription": "Total pipeline cost of Instruction Cache misses - subset of the Big_Code Bottleneck. Related metrics: "
-    },
-    {
-        "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": "BigFootprint;BvBC;Fed;Frontend;IcMiss;MemoryTLB",
-        "MetricName": "tma_info_bottleneck_big_code",
-        "MetricThreshold": "tma_info_bottleneck_big_code > 20"
-    },
-    {
-        "BriefDescription": "Total pipeline cost of instructions used for program control-flow - a subset of the Retiring category in TMA",
-        "MetricExpr": "100 * ((BR_INST_RETIRED.ALL_BRANCHES + 2 * BR_INST_RETIRED.NEAR_CALL + INST_RETIRED.NOP) / tma_info_thread_slots)",
-        "MetricGroup": "BvBO;Ret",
-        "MetricName": "tma_info_bottleneck_branching_overhead",
-        "MetricThreshold": "tma_info_bottleneck_branching_overhead > 5",
-        "PublicDescription": "Total pipeline cost of instructions used for program control-flow - a subset of the Retiring category in TMA. Examples include function calls; loops and alignments. (A lower bound)"
-    },
-    {
-        "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_pmm_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_pmm_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_pmm_bound + tma_store_bound)) * (tma_fb_full / (tma_4k_aliasing + tma_dtlb_load + tma_fb_full + tma_l1_hit_latency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)))",
-        "MetricGroup": "BvMB;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_pmm_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_pmm_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_pmm_bound + tma_store_bound) + tma_memory_bound * (tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_pmm_bound + tma_store_bound)) * (tma_store_latency / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency)) + tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_pmm_bound + tma_store_bound)) * (tma_l1_hit_latency / (tma_4k_aliasing + tma_dtlb_load + tma_fb_full + tma_l1_hit_latency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)))",
-        "MetricGroup": "BvML;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": "BvCB;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 (when the front-end could not sustain operations delivery to the back-end)",
-        "MetricConstraint": "NO_GROUP_EVENTS",
-        "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": "BvFB;Fed;FetchBW;Frontend",
-        "MetricName": "tma_info_bottleneck_instruction_fetch_bw",
-        "MetricThreshold": "tma_info_bottleneck_instruction_fetch_bw > 20"
-    },
-    {
-        "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;BvIO;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_pmm_bound + tma_store_bound)) * (tma_dtlb_load / max(tma_l1_bound, tma_4k_aliasing + tma_dtlb_load + tma_fb_full + tma_l1_hit_latency + 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_pmm_bound + tma_store_bound)) * (tma_dtlb_store / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency)))",
-        "MetricGroup": "BvMT;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, tma_info_bottleneck_memory_synchronization"
-    },
-    {
-        "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_pmm_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_pmm_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_pmm_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": "BvMS;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 * (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;BvMP;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 in the back-end",
-        "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_useful_work)",
-        "MetricGroup": "BvOB;Cor;Offcore",
-        "MetricName": "tma_info_bottleneck_other_bottlenecks",
-        "MetricThreshold": "tma_info_bottleneck_other_bottlenecks > 20",
-        "PublicDescription": "Total pipeline cost of remaining bottlenecks in the back-end. Examples include data-dependencies (Core Bound when Low ILP) and other unlisted memory-related stalls."
-    },
-    {
-        "BriefDescription": "Total pipeline cost of \"useful operations\" - the portion of Retiring category not covered by Branching_Overhead nor Irregular_Overhead.",
-        "MetricExpr": "100 * (tma_retiring - (BR_INST_RETIRED.ALL_BRANCHES + 2 * BR_INST_RETIRED.NEAR_CALL + INST_RETIRED.NOP) / tma_info_thread_slots - tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * tma_heavy_operations)",
-        "MetricGroup": "BvUW;Ret",
-        "MetricName": "tma_info_bottleneck_useful_work",
-        "MetricThreshold": "tma_info_bottleneck_useful_work > 20"
+        "MetricThreshold": "tma_info_botlnk_l2_ic_misses > 5"
     },
     {
         "BriefDescription": "Fraction of branches that are CALL or RET",
@@ -825,7 +852,7 @@
     },
     {
         "BriefDescription": "Core actual clocks when any Logical Processor is active on the Physical Core",
-        "MetricExpr": "(CPU_CLK_UNHALTED.THREAD / 2 * (1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK) if #core_wide < 1 else (CPU_CLK_UNHALTED.THREAD_ANY / 2 if #SMT_on else tma_info_thread_clks))",
+        "MetricExpr": "(CPU_CLK_UNHALTED.THREAD_ANY / 2 if #SMT_on else tma_info_thread_clks)",
         "MetricGroup": "SMT",
         "MetricName": "tma_info_core_core_clks"
     },
@@ -850,14 +877,14 @@
     },
     {
         "BriefDescription": "Actual per-core usage of the Floating Point non-X87 execution units (regardless of precision or vector-width)",
-        "MetricExpr": "(FP_ARITH_INST_RETIRED.SCALAR + cpu@FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE\\,umask\\=0xfc@) / (2 * tma_info_core_core_clks)",
+        "MetricExpr": "(FP_ARITH_INST_RETIRED.SCALAR + cpu@FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE\\,umask\\=0xFC@) / (2 * tma_info_core_core_clks)",
         "MetricGroup": "Cor;Flops;HPC",
         "MetricName": "tma_info_core_fp_arith_utilization",
-        "PublicDescription": "Actual per-core usage of the Floating Point non-X87 execution units (regardless of precision or vector-width). Values > 1 are possible due to ([BDW+] Fused-Multiply Add (FMA) counting - common; [ADL+] use all of ADD/MUL/FMA in Scalar or 128/256-bit vectors - less common)."
+        "PublicDescription": "Actual per-core usage of the Floating Point non-X87 execution units (regardless of precision or vector-width). Values > 1 are possible due to ([BDW+] Fused-Multiply Add (FMA) counting - common; [ADL+] use all of ADD/MUL/FMA in Scalar or 128/256-bit vectors - less common)"
     },
     {
         "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is execution) per thread (logical-processor)",
-        "MetricExpr": "UOPS_EXECUTED.THREAD / cpu@UOPS_EXECUTED.THREAD\\,cmask\\=1@",
+        "MetricExpr": "UOPS_EXECUTED.THREAD / cpu@UOPS_EXECUTED.THREAD\\,cmask\\=0x1@",
         "MetricGroup": "Backend;Cor;Pipeline;PortsUtil",
         "MetricName": "tma_info_core_ilp"
     },
@@ -870,20 +897,20 @@
         "PublicDescription": "Fraction of Uops delivered by the DSB (aka Decoded ICache; or Uop Cache). Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_inst_mix_iptb, tma_lcp"
     },
     {
-        "BriefDescription": "Average number of cycles of a switch from the DSB fetch-unit to MITE fetch unit - see DSB_Switches tree node for details.",
+        "BriefDescription": "Average number of cycles of a switch from the DSB fetch-unit to MITE fetch unit - see DSB_Switches tree node for details",
         "MetricExpr": "DSB2MITE_SWITCHES.PENALTY_CYCLES / DSB2MITE_SWITCHES.COUNT",
         "MetricGroup": "DSBmiss",
         "MetricName": "tma_info_frontend_dsb_switch_cost"
     },
     {
         "BriefDescription": "Average number of Uops issued by front-end when it issued something",
-        "MetricExpr": "UOPS_ISSUED.ANY / cpu@UOPS_ISSUED.ANY\\,cmask\\=1@",
+        "MetricExpr": "UOPS_ISSUED.ANY / cpu@UOPS_ISSUED.ANY\\,cmask\\=0x1@",
         "MetricGroup": "Fed;FetchBW",
         "MetricName": "tma_info_frontend_fetch_upc"
     },
     {
         "BriefDescription": "Average Latency for L1 instruction cache misses",
-        "MetricExpr": "ICACHE_16B.IFDATA_STALL / cpu@ICACHE_16B.IFDATA_STALL\\,cmask\\=1\\,edge@ + 2",
+        "MetricExpr": "ICACHE_16B.IFDATA_STALL / cpu@ICACHE_16B.IFDATA_STALL\\,cmask\\=0x1\\,edge\\=0x1@ + 2",
         "MetricGroup": "Fed;FetchLat;IcMiss",
         "MetricName": "tma_info_frontend_icache_miss_latency"
     },
@@ -913,7 +940,13 @@
         "MetricName": "tma_info_frontend_l2mpki_code_all"
     },
     {
-        "BriefDescription": "Branch instructions per taken branch.",
+        "BriefDescription": "Taken Branches retired Per Cycle",
+        "MetricExpr": "BR_INST_RETIRED.NEAR_TAKEN / tma_info_thread_clks",
+        "MetricGroup": "Branches;FetchBW",
+        "MetricName": "tma_info_frontend_tbpc"
+    },
+    {
+        "BriefDescription": "Branch instructions per taken branch",
         "MetricExpr": "BR_INST_RETIRED.ALL_BRANCHES / BR_INST_RETIRED.NEAR_TAKEN",
         "MetricGroup": "Branches;Fed;PGO",
         "MetricName": "tma_info_inst_mix_bptkbranch"
@@ -928,11 +961,11 @@
     {
         "BriefDescription": "Instructions per FP Arithmetic instruction (lower number means higher occurrence rate)",
         "MetricConstraint": "NO_GROUP_EVENTS",
-        "MetricExpr": "INST_RETIRED.ANY / (FP_ARITH_INST_RETIRED.SCALAR + cpu@FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE\\,umask\\=0xfc@)",
+        "MetricExpr": "INST_RETIRED.ANY / (FP_ARITH_INST_RETIRED.SCALAR + cpu@FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE\\,umask\\=0xFC@)",
         "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). Values < 1 are possible due to intentional 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"
     },
     {
         "BriefDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number means higher occurrence rate)",
@@ -940,7 +973,7 @@
         "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). Values < 1 are possible due to intentional 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"
     },
     {
         "BriefDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means higher occurrence rate)",
@@ -948,7 +981,7 @@
         "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). Values < 1 are possible due to intentional 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"
     },
     {
         "BriefDescription": "Instructions per FP Arithmetic AVX 512-bit instruction (lower number means higher occurrence rate)",
@@ -956,7 +989,7 @@
         "MetricGroup": "Flops;FpVector;InsType",
         "MetricName": "tma_info_inst_mix_iparith_avx512",
         "MetricThreshold": "tma_info_inst_mix_iparith_avx512 < 10",
-        "PublicDescription": "Instructions per FP Arithmetic AVX 512-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting."
+        "PublicDescription": "Instructions per FP Arithmetic AVX 512-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting"
     },
     {
         "BriefDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction (lower number means higher occurrence rate)",
@@ -964,7 +997,7 @@
         "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). Values < 1 are possible due to intentional 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"
     },
     {
         "BriefDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction (lower number means higher occurrence rate)",
@@ -972,7 +1005,7 @@
         "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). Values < 1 are possible due to intentional 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"
     },
     {
         "BriefDescription": "Instructions per Branch (lower number means higher occurrence rate)",
@@ -1018,7 +1051,7 @@
     },
     {
         "BriefDescription": "Instructions per Software prefetch instruction (of any type: NTA/T0/T1/T2/Prefetch) (lower number means higher occurrence rate)",
-        "MetricExpr": "INST_RETIRED.ANY / cpu@SW_PREFETCH_ACCESS.T0\\,umask\\=0xF@",
+        "MetricExpr": "INST_RETIRED.ANY / SW_PREFETCH_ACCESS.ANY",
         "MetricGroup": "Prefetches",
         "MetricName": "tma_info_inst_mix_ipswpf",
         "MetricThreshold": "tma_info_inst_mix_ipswpf < 100"
@@ -1028,7 +1061,7 @@
         "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_TAKEN",
         "MetricGroup": "Branches;Fed;FetchBW;Frontend;PGO;tma_issueFB",
         "MetricName": "tma_info_inst_mix_iptb",
-        "MetricThreshold": "tma_info_inst_mix_iptb < 9",
+        "MetricThreshold": "tma_info_inst_mix_iptb < 4 * 2 + 1",
         "PublicDescription": "Instructions per taken branch. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_lcp"
     },
     {
@@ -1075,7 +1108,7 @@
     },
     {
         "BriefDescription": "Average per-thread data fill bandwidth to the L1 data cache [GB / sec]",
-        "MetricExpr": "64 * L1D.REPLACEMENT / 1e9 / duration_time",
+        "MetricExpr": "64 * L1D.REPLACEMENT / 1e9 / tma_info_system_time",
         "MetricGroup": "Mem;MemoryBW",
         "MetricName": "tma_info_memory_l1d_cache_fill_bw"
     },
@@ -1093,7 +1126,7 @@
     },
     {
         "BriefDescription": "Average per-thread data fill bandwidth to the L2 cache [GB / sec]",
-        "MetricExpr": "64 * L2_LINES_IN.ALL / 1e9 / duration_time",
+        "MetricExpr": "64 * L2_LINES_IN.ALL / 1e9 / tma_info_system_time",
         "MetricGroup": "Mem;MemoryBW",
         "MetricName": "tma_info_memory_l2_cache_fill_bw"
     },
@@ -1135,13 +1168,13 @@
     },
     {
         "BriefDescription": "Average per-thread data access bandwidth to the L3 cache [GB / sec]",
-        "MetricExpr": "64 * OFFCORE_REQUESTS.ALL_REQUESTS / 1e9 / duration_time",
+        "MetricExpr": "64 * OFFCORE_REQUESTS.ALL_REQUESTS / 1e9 / tma_info_system_time",
         "MetricGroup": "Mem;MemoryBW;Offcore",
         "MetricName": "tma_info_memory_l3_cache_access_bw"
     },
     {
         "BriefDescription": "Average per-thread data fill bandwidth to the L3 cache [GB / sec]",
-        "MetricExpr": "64 * LONGEST_LAT_CACHE.MISS / 1e9 / duration_time",
+        "MetricExpr": "64 * LONGEST_LAT_CACHE.MISS / 1e9 / tma_info_system_time",
         "MetricGroup": "Mem;MemoryBW",
         "MetricName": "tma_info_memory_l3_cache_fill_bw"
     },
@@ -1160,7 +1193,7 @@
     {
         "BriefDescription": "Average Latency for L2 cache miss demand Loads",
         "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD / OFFCORE_REQUESTS.DEMAND_DATA_RD",
-        "MetricGroup": "Memory_Lat;Offcore",
+        "MetricGroup": "LockCont;Memory_Lat;Offcore",
         "MetricName": "tma_info_memory_latency_load_l2_miss_latency"
     },
     {
@@ -1216,7 +1249,7 @@
     },
     {
         "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is execution) per core",
-        "MetricExpr": "UOPS_EXECUTED.THREAD / (UOPS_EXECUTED.CORE_CYCLES_GE_1 / 2 if #SMT_on else cpu@UOPS_EXECUTED.THREAD\\,cmask\\=1@)",
+        "MetricExpr": "UOPS_EXECUTED.THREAD / (UOPS_EXECUTED.CORE_CYCLES_GE_1 / 2 if #SMT_on else cpu@UOPS_EXECUTED.THREAD\\,cmask\\=0x1@)",
         "MetricGroup": "Cor;Pipeline;PortsUtil;SMT",
         "MetricName": "tma_info_pipeline_execute"
     },
@@ -1237,18 +1270,18 @@
         "MetricExpr": "INST_RETIRED.ANY / (FP_ASSIST.ANY + OTHER_ASSISTS.ANY)",
         "MetricGroup": "MicroSeq;Pipeline;Ret;Retire",
         "MetricName": "tma_info_pipeline_ipassist",
-        "MetricThreshold": "tma_info_pipeline_ipassist < 100e3",
+        "MetricThreshold": "tma_info_pipeline_ipassist < 100000",
         "PublicDescription": "Instructions per a microcode Assist invocation. See Assists tree node for details (lower number means higher occurrence rate)"
     },
     {
-        "BriefDescription": "Average number of Uops retired in cycles where at least one uop has retired.",
-        "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / cpu@UOPS_RETIRED.RETIRE_SLOTS\\,cmask\\=1@",
+        "BriefDescription": "Average number of Uops retired in cycles where at least one uop has retired",
+        "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / cpu@UOPS_RETIRED.RETIRE_SLOTS\\,cmask\\=0x1@",
         "MetricGroup": "Pipeline;Ret",
         "MetricName": "tma_info_pipeline_retire"
     },
     {
         "BriefDescription": "Measured Average Core Frequency for unhalted processors [GHz]",
-        "MetricExpr": "tma_info_system_turbo_utilization * TSC / 1e9 / duration_time",
+        "MetricExpr": "tma_info_system_turbo_utilization * TSC / 1e9 / tma_info_system_time",
         "MetricGroup": "Power;Summary",
         "MetricName": "tma_info_system_core_frequency"
     },
@@ -1266,29 +1299,29 @@
     },
     {
         "BriefDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]",
-        "MetricExpr": "64 * (UNC_M_CAS_COUNT.RD + UNC_M_CAS_COUNT.WR) / 1e9 / duration_time",
+        "MetricExpr": "64 * (UNC_M_CAS_COUNT.RD + UNC_M_CAS_COUNT.WR) / 1e9 / tma_info_system_time",
         "MetricGroup": "HPC;MemOffcore;MemoryBW;SoC;tma_issueBW",
         "MetricName": "tma_info_system_dram_bw_use",
-        "PublicDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]. Related metrics: tma_fb_full, tma_info_bottleneck_cache_memory_bandwidth, tma_mem_bandwidth, tma_sq_full"
+        "PublicDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]. Related metrics: tma_bottleneck_cache_memory_bandwidth, tma_fb_full, tma_mem_bandwidth, tma_sq_full"
     },
     {
         "BriefDescription": "Giga Floating Point Operations Per Second",
         "MetricConstraint": "NO_GROUP_EVENTS",
-        "MetricExpr": "(FP_ARITH_INST_RETIRED.SCALAR + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * FP_ARITH_INST_RETIRED.4_FLOPS + 8 * FP_ARITH_INST_RETIRED.8_FLOPS + 16 * FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE) / 1e9 / duration_time",
+        "MetricExpr": "(FP_ARITH_INST_RETIRED.SCALAR + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * FP_ARITH_INST_RETIRED.4_FLOPS + 8 * FP_ARITH_INST_RETIRED.8_FLOPS + 16 * FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE) / 1e9 / tma_info_system_time",
         "MetricGroup": "Cor;Flops;HPC",
         "MetricName": "tma_info_system_gflops",
         "PublicDescription": "Giga Floating Point Operations Per Second. Aggregate across all supported options of: FP precisions, scalar and vector instructions, vector-width"
     },
     {
         "BriefDescription": "Average IO (network or disk) Bandwidth Use for Reads [GB / sec]",
-        "MetricExpr": "(UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART0 + UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART1 + UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART2 + UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART3) * 4 / 1e9 / duration_time",
+        "MetricExpr": "(UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART0 + UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART1 + UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART2 + UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART3) * 4 / 1e9 / tma_info_system_time",
         "MetricGroup": "IoBW;MemOffcore;Server;SoC",
         "MetricName": "tma_info_system_io_read_bw",
         "PublicDescription": "Average IO (network or disk) Bandwidth Use for Reads [GB / sec]. Bandwidth of IO reads that are initiated by end device controllers that are requesting memory from the CPU"
     },
     {
         "BriefDescription": "Average IO (network or disk) Bandwidth Use for Writes [GB / sec]",
-        "MetricExpr": "(UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART0 + UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART1 + UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART2 + UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART3) * 4 / 1e9 / duration_time",
+        "MetricExpr": "(UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART0 + UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART1 + UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART2 + UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART3) * 4 / 1e9 / tma_info_system_time",
         "MetricGroup": "IoBW;MemOffcore;Server;SoC",
         "MetricName": "tma_info_system_io_write_bw",
         "PublicDescription": "Average IO (network or disk) Bandwidth Use for Writes [GB / sec]. Bandwidth of IO writes that are initiated by end device controllers that are writing memory to the CPU"
@@ -1298,13 +1331,14 @@
         "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.FAR_BRANCH:u",
         "MetricGroup": "Branches;OS",
         "MetricName": "tma_info_system_ipfarbranch",
-        "MetricThreshold": "tma_info_system_ipfarbranch < 1e6"
+        "MetricThreshold": "tma_info_system_ipfarbranch < 1000000"
     },
     {
         "BriefDescription": "Cycles Per Instruction for the Operating System (OS) Kernel mode",
         "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P:k / INST_RETIRED.ANY_P:k",
         "MetricGroup": "OS",
-        "MetricName": "tma_info_system_kernel_cpi"
+        "MetricName": "tma_info_system_kernel_cpi",
+        "ScaleUnit": "1per_instr"
     },
     {
         "BriefDescription": "Fraction of cycles spent in the Operating System (OS) Kernel mode",
@@ -1322,43 +1356,37 @@
     },
     {
         "BriefDescription": "Average number of parallel data read requests to external memory",
-        "MetricExpr": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD / UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD@thresh\\=1@",
+        "MetricExpr": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD / cha@UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD\\,thresh\\=0x1@",
         "MetricGroup": "Mem;MemoryBW;SoC",
         "MetricName": "tma_info_system_mem_parallel_reads",
         "PublicDescription": "Average number of parallel data read requests to external memory. Accounts for demand loads and L1/L2 prefetches"
     },
-    {
-        "BriefDescription": "Average latency of data read request to external 3D X-Point memory [in nanoseconds]",
-        "MetricExpr": "(1e9 * (UNC_M_PMM_RPQ_OCCUPANCY.ALL / UNC_M_PMM_RPQ_INSERTS) / imc_0@event\\=0x0@ if #has_pmem > 0 else 0)",
-        "MetricGroup": "MemOffcore;MemoryLat;Server;SoC",
-        "MetricName": "tma_info_system_mem_pmm_read_latency",
-        "PublicDescription": "Average latency of data read request to external 3D X-Point memory [in nanoseconds]. Accounts for demand loads and L1/L2 data-read prefetches"
-    },
     {
         "BriefDescription": "Average latency of data read request to external memory (in nanoseconds)",
-        "MetricExpr": "1e9 * (UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD / UNC_CHA_TOR_INSERTS.IA_MISS_DRD) / (tma_info_system_socket_clks / duration_time)",
+        "MetricExpr": "1e9 * (UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD / UNC_CHA_TOR_INSERTS.IA_MISS_DRD) / (tma_info_system_socket_clks / tma_info_system_time)",
         "MetricGroup": "Mem;MemoryLat;SoC",
         "MetricName": "tma_info_system_mem_read_latency",
         "PublicDescription": "Average latency of data read request to external memory (in nanoseconds). Accounts for demand loads and L1/L2 prefetches. ([RKL+]memory-controller only)"
     },
     {
-        "BriefDescription": "Average 3DXP Memory Bandwidth Use for reads [GB / sec]",
-        "MetricExpr": "(64 * UNC_M_PMM_RPQ_INSERTS / 1e9 / duration_time if #has_pmem > 0 else 0)",
-        "MetricGroup": "MemOffcore;MemoryBW;Server;SoC",
-        "MetricName": "tma_info_system_pmm_read_bw"
+        "BriefDescription": "PerfMon Event Multiplexing accuracy indicator",
+        "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P / CPU_CLK_UNHALTED.THREAD",
+        "MetricGroup": "Summary",
+        "MetricName": "tma_info_system_mux",
+        "MetricThreshold": "tma_info_system_mux > 1.1 | tma_info_system_mux < 0.9"
     },
     {
-        "BriefDescription": "Average 3DXP Memory Bandwidth Use for Writes [GB / sec]",
-        "MetricExpr": "(64 * UNC_M_PMM_WPQ_INSERTS / 1e9 / duration_time if #has_pmem > 0 else 0)",
-        "MetricGroup": "MemOffcore;MemoryBW;Server;SoC",
-        "MetricName": "tma_info_system_pmm_write_bw"
+        "BriefDescription": "Total package Power in Watts",
+        "MetricExpr": "(power@energy\\-pkg@ * 61 + 15.6 * power@energy\\-ram@) / (duration_time * 1e6)",
+        "MetricGroup": "Power;SoC",
+        "MetricName": "tma_info_system_power"
     },
     {
         "BriefDescription": "Fraction of Core cycles where the core was running with power-delivery for baseline license level 0",
         "MetricExpr": "(CORE_POWER.LVL0_TURBO_LICENSE / 2 / tma_info_core_core_clks if #SMT_on else CORE_POWER.LVL0_TURBO_LICENSE / tma_info_core_core_clks)",
         "MetricGroup": "Power",
         "MetricName": "tma_info_system_power_license0_utilization",
-        "PublicDescription": "Fraction of Core cycles where the core was running with power-delivery for baseline license level 0.  This includes non-AVX codes, SSE, AVX 128-bit, and low-current AVX 256-bit codes."
+        "PublicDescription": "Fraction of Core cycles where the core was running with power-delivery for baseline license level 0.  This includes non-AVX codes, SSE, AVX 128-bit, and low-current AVX 256-bit codes"
     },
     {
         "BriefDescription": "Fraction of Core cycles where the core was running with power-delivery for license level 1",
@@ -1366,7 +1394,7 @@
         "MetricGroup": "Power",
         "MetricName": "tma_info_system_power_license1_utilization",
         "MetricThreshold": "tma_info_system_power_license1_utilization > 0.5",
-        "PublicDescription": "Fraction of Core cycles where the core was running with power-delivery for license level 1.  This includes high current AVX 256-bit instructions as well as low current AVX 512-bit instructions."
+        "PublicDescription": "Fraction of Core cycles where the core was running with power-delivery for license level 1.  This includes high current AVX 256-bit instructions as well as low current AVX 512-bit instructions"
     },
     {
         "BriefDescription": "Fraction of Core cycles where the core was running with power-delivery for license level 2 (introduced in SKX)",
@@ -1374,7 +1402,7 @@
         "MetricGroup": "Power",
         "MetricName": "tma_info_system_power_license2_utilization",
         "MetricThreshold": "tma_info_system_power_license2_utilization > 0.5",
-        "PublicDescription": "Fraction of Core cycles where the core was running with power-delivery for license level 2 (introduced in SKX).  This includes high current AVX 512-bit instructions."
+        "PublicDescription": "Fraction of Core cycles where the core was running with power-delivery for license level 2 (introduced in SKX).  This includes high current AVX 512-bit instructions"
     },
     {
         "BriefDescription": "Fraction of cycles where both hardware Logical Processors were active",
@@ -1388,6 +1416,13 @@
         "MetricGroup": "SoC",
         "MetricName": "tma_info_system_socket_clks"
     },
+    {
+        "BriefDescription": "Run duration time in seconds",
+        "MetricExpr": "duration_time",
+        "MetricGroup": "Summary",
+        "MetricName": "tma_info_system_time",
+        "MetricThreshold": "tma_info_system_time < 1"
+    },
     {
         "BriefDescription": "Average Frequency Utilization relative nominal frequency",
         "MetricExpr": "tma_info_thread_clks / CPU_CLK_UNHALTED.REF_TSC",
@@ -1396,12 +1431,12 @@
     },
     {
         "BriefDescription": "Measured Average Uncore Frequency for the SoC [GHz]",
-        "MetricExpr": "tma_info_system_socket_clks / 1e9 / duration_time",
+        "MetricExpr": "tma_info_system_socket_clks / 1e9 / tma_info_system_time",
         "MetricGroup": "SoC",
         "MetricName": "tma_info_system_uncore_frequency"
     },
     {
-        "BriefDescription": "Per-Logical Processor actual clocks when the Logical Processor is active.",
+        "BriefDescription": "Per-Logical Processor actual clocks when the Logical Processor is active",
         "MetricExpr": "CPU_CLK_UNHALTED.THREAD",
         "MetricGroup": "Pipeline",
         "MetricName": "tma_info_thread_clks"
@@ -1410,14 +1445,15 @@
         "BriefDescription": "Cycles Per Instruction (per Logical Processor)",
         "MetricExpr": "1 / tma_info_thread_ipc",
         "MetricGroup": "Mem;Pipeline",
-        "MetricName": "tma_info_thread_cpi"
+        "MetricName": "tma_info_thread_cpi",
+        "ScaleUnit": "1per_instr"
     },
     {
         "BriefDescription": "The ratio of Executed- by Issued-Uops",
         "MetricExpr": "UOPS_EXECUTED.THREAD / UOPS_ISSUED.ANY",
         "MetricGroup": "Cor;Pipeline",
         "MetricName": "tma_info_thread_execute_per_issue",
-        "PublicDescription": "The ratio of Executed- by Issued-Uops. Ratio > 1 suggests high rate of uop micro-fusions. Ratio < 1 suggest high rate of \"execute\" at rename stage."
+        "PublicDescription": "The ratio of Executed- by Issued-Uops. Ratio > 1 suggests high rate of uop micro-fusions. Ratio < 1 suggest high rate of \"execute\" at rename stage"
     },
     {
         "BriefDescription": "Instructions Per Cycle (per Logical Processor)",
@@ -1443,43 +1479,52 @@
         "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / BR_INST_RETIRED.NEAR_TAKEN",
         "MetricGroup": "Branches;Fed;FetchBW",
         "MetricName": "tma_info_thread_uptb",
-        "MetricThreshold": "tma_info_thread_uptb < 6"
+        "MetricThreshold": "tma_info_thread_uptb < 4 * 1.5"
     },
     {
         "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to Instruction TLB (ITLB) misses",
         "MetricExpr": "ICACHE_TAG.STALLS / tma_info_thread_clks",
         "MetricGroup": "BigFootprint;BvBC;FetchLat;MemoryTLB;TopdownL3;tma_L3_group;tma_fetch_latency_group",
         "MetricName": "tma_itlb_misses",
-        "MetricThreshold": "tma_itlb_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)",
-        "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Instruction TLB (ITLB) misses. Sample with: FRONTEND_RETIRED.STLB_MISS_PS;FRONTEND_RETIRED.ITLB_MISS_PS",
+        "MetricThreshold": "tma_itlb_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 TLB (ITLB) misses. Sample with: FRONTEND_RETIRED.STLB_MISS, FRONTEND_RETIRED.ITLB_MISS",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric estimates how often the CPU was stalled without loads missing the L1 data cache",
+        "BriefDescription": "This metric estimates how often the CPU was stalled without loads missing the L1 Data (L1D) cache",
         "MetricExpr": "max((CYCLE_ACTIVITY.STALLS_MEM_ANY - CYCLE_ACTIVITY.STALLS_L1D_MISS) / tma_info_thread_clks, 0)",
         "MetricGroup": "CacheHits;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_issueL1;tma_issueMC;tma_memory_bound_group",
         "MetricName": "tma_l1_bound",
-        "MetricThreshold": "tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)",
-        "PublicDescription": "This metric estimates how often the CPU was stalled without loads missing the L1 data cache.  The L1 data cache typically has the shortest latency.  However; in certain cases like loads blocked on older stores; a load might suffer due to high latency even though it is being satisfied by the L1. Another example is loads who miss in the TLB. These cases are characterized by execution unit stalls; while some non-completed demand load lives in the machine without having that demand load missing the L1 cache. Sample with: MEM_LOAD_RETIRED.L1_HIT_PS;MEM_LOAD_RETIRED.FB_HIT_PS. Related metrics: tma_clears_resteers, tma_machine_clears, tma_microcode_sequencer, tma_ms_switches, tma_ports_utilized_1",
+        "MetricThreshold": "tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "PublicDescription": "This metric estimates how often the CPU was stalled without loads missing the L1 Data (L1D) cache.  The L1D cache typically has the shortest latency.  However; in certain cases like loads blocked on older stores; a load might suffer due to high latency even though it is being satisfied by the L1D. Another example is loads who miss in the TLB. These cases are characterized by execution unit stalls; while some non-completed demand load lives in the machine without having that demand load missing the L1 cache. Sample with: MEM_LOAD_RETIRED.L1_HIT. Related metrics: tma_clears_resteers, tma_machine_clears, tma_microcode_sequencer, tma_ms_switches, tma_ports_utilized_1",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric roughly estimates fraction of cycles with demand load accesses that hit the L1 cache",
+        "BriefDescription": "This metric([SKL+] roughly; [LNL]) estimates fraction of cycles with demand load accesses that hit the L1D cache",
         "MetricExpr": "min(2 * (MEM_INST_RETIRED.ALL_LOADS - MEM_LOAD_RETIRED.FB_HIT - MEM_LOAD_RETIRED.L1_MISS) * 20 / 100, max(CYCLE_ACTIVITY.CYCLES_MEM_ANY - CYCLE_ACTIVITY.CYCLES_L1D_MISS, 0)) / tma_info_thread_clks",
         "MetricGroup": "BvML;MemoryLat;TopdownL4;tma_L4_group;tma_l1_bound_group",
-        "MetricName": "tma_l1_hit_latency",
-        "MetricThreshold": "tma_l1_hit_latency > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
-        "PublicDescription": "This metric roughly estimates fraction of cycles with demand load accesses that hit the L1 cache. The short latency of the L1 data cache may be exposed in pointer-chasing memory access patterns as an example. Sample with: MEM_LOAD_RETIRED.L1_HIT",
+        "MetricName": "tma_l1_latency_dependency",
+        "MetricThreshold": "tma_l1_latency_dependency > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "PublicDescription": "This metric([SKL+] roughly; [LNL]) estimates fraction of cycles with demand load accesses that hit the L1D cache. The short latency of the L1D cache may be exposed in pointer-chasing memory access patterns as an example. Sample with: MEM_LOAD_RETIRED.L1_HIT",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "This metric estimates how often the CPU was stalled due to L2 cache accesses by loads",
         "MetricConstraint": "NO_GROUP_EVENTS",
-        "MetricExpr": "MEM_LOAD_RETIRED.L2_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) / (MEM_LOAD_RETIRED.L2_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) + cpu@L1D_PEND_MISS.FB_FULL\\,cmask\\=1@) * ((CYCLE_ACTIVITY.STALLS_L1D_MISS - CYCLE_ACTIVITY.STALLS_L2_MISS) / tma_info_thread_clks)",
+        "MetricExpr": "MEM_LOAD_RETIRED.L2_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) / (MEM_LOAD_RETIRED.L2_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) + cpu@L1D_PEND_MISS.FB_FULL\\,cmask\\=0x1@) * ((CYCLE_ACTIVITY.STALLS_L1D_MISS - CYCLE_ACTIVITY.STALLS_L2_MISS) / tma_info_thread_clks)",
         "MetricGroup": "BvML;CacheHits;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group",
         "MetricName": "tma_l2_bound",
-        "MetricThreshold": "tma_l2_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)",
-        "PublicDescription": "This metric estimates how often the CPU was stalled due to L2 cache accesses by loads.  Avoiding cache misses (i.e. L1 misses/L2 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L2_HIT_PS",
+        "MetricThreshold": "tma_l2_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "PublicDescription": "This metric estimates how often the CPU was stalled due to L2 cache accesses by loads.  Avoiding cache misses (i.e. L1 misses/L2 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L2_HIT",
+        "ScaleUnit": "100%"
+    },
+    {
+        "BriefDescription": "This metric represents fraction of cycles with demand load accesses that hit the L2 cache under unloaded scenarios (possibly L2 latency limited)",
+        "MetricExpr": "3.5 * tma_info_system_core_frequency * MEM_LOAD_RETIRED.L2_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks",
+        "MetricGroup": "MemoryLat;TopdownL4;tma_L4_group;tma_l2_bound_group",
+        "MetricName": "tma_l2_hit_latency",
+        "MetricThreshold": "tma_l2_hit_latency > 0.05 & tma_l2_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "PublicDescription": "This metric represents fraction of cycles with demand load accesses that hit the L2 cache under unloaded scenarios (possibly L2 latency limited).  Avoiding L1 cache misses (i.e. L1 misses/L2 hits) will improve the latency. Sample with: MEM_LOAD_RETIRED.L2_HIT",
         "ScaleUnit": "100%"
     },
     {
@@ -1487,17 +1532,17 @@
         "MetricExpr": "(CYCLE_ACTIVITY.STALLS_L2_MISS - CYCLE_ACTIVITY.STALLS_L3_MISS) / tma_info_thread_clks",
         "MetricGroup": "CacheHits;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group",
         "MetricName": "tma_l3_bound",
-        "MetricThreshold": "tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)",
-        "PublicDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core.  Avoiding cache misses (i.e. L2 misses/L3 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L3_HIT_PS",
+        "MetricThreshold": "tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "PublicDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core.  Avoiding cache misses (i.e. L2 misses/L3 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L3_HIT",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "This metric estimates fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited)",
-        "MetricExpr": "17 * tma_info_system_core_frequency * (MEM_LOAD_RETIRED.L3_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2)) / tma_info_thread_clks",
+        "MetricExpr": "(20.5 * tma_info_system_core_frequency - 3.5 * tma_info_system_core_frequency) * (MEM_LOAD_RETIRED.L3_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2)) / tma_info_thread_clks",
         "MetricGroup": "BvML;MemoryLat;TopdownL4;tma_L4_group;tma_issueLat;tma_l3_bound_group",
         "MetricName": "tma_l3_hit_latency",
-        "MetricThreshold": "tma_l3_hit_latency > 0.1 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
-        "PublicDescription": "This metric estimates fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited).  Avoiding private cache misses (i.e. L2 misses/L3 hits) will improve the latency; reduce contention with sibling physical cores and increase performance.  Note the value of this node may overlap with its siblings. Sample with: MEM_LOAD_RETIRED.L3_HIT_PS. Related metrics: tma_info_bottleneck_cache_memory_latency, tma_mem_latency",
+        "MetricThreshold": "tma_l3_hit_latency > 0.1 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "PublicDescription": "This metric estimates fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited).  Avoiding private cache misses (i.e. L2 misses/L3 hits) will improve the latency; reduce contention with sibling physical cores and increase performance.  Note the value of this node may overlap with its siblings. Sample with: MEM_LOAD_RETIRED.L3_HIT. Related metrics: tma_bottleneck_cache_memory_latency, tma_branch_resteers, tma_mem_latency, tma_store_latency",
         "ScaleUnit": "100%"
     },
     {
@@ -1505,18 +1550,18 @@
         "MetricExpr": "DECODE.LCP / tma_info_thread_clks",
         "MetricGroup": "FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueFB",
         "MetricName": "tma_lcp",
-        "MetricThreshold": "tma_lcp > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)",
-        "PublicDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs). Using proper compiler flags or Intel Compiler by default will certainly avoid this. #Link: Optimization Guide about LCP BKMs. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb",
+        "MetricThreshold": "tma_lcp > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+        "PublicDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs). Using proper compiler flags or Intel Compiler by default will certainly avoid this. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation)",
+        "BriefDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations , instructions that require no more than one uop (micro-operation)",
         "MetricExpr": "tma_retiring - tma_heavy_operations",
         "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group",
         "MetricName": "tma_light_operations",
         "MetricThreshold": "tma_light_operations > 0.6",
         "MetricgroupNoGroup": "TopdownL2",
-        "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized code running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. ([ICL+] Note this may undercount due to approximation using indirect events; [ADL+] .). Sample with: INST_RETIRED.PREC_DIST",
+        "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations , instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized code running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. ([ICL+] Note this may undercount due to approximation using indirect events; [ADL+] .). Sample with: INST_RETIRED.PREC_DIST",
         "ScaleUnit": "100%"
     },
     {
@@ -1534,7 +1579,7 @@
         "MetricExpr": "tma_dtlb_load - tma_load_stlb_miss",
         "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_load_group",
         "MetricName": "tma_load_stlb_hit",
-        "MetricThreshold": "tma_load_stlb_hit > 0.05 & (tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))",
+        "MetricThreshold": "tma_load_stlb_hit > 0.05 & tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
         "ScaleUnit": "100%"
     },
     {
@@ -1542,24 +1587,48 @@
         "MetricExpr": "DTLB_LOAD_MISSES.WALK_ACTIVE / tma_info_thread_clks",
         "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_load_group",
         "MetricName": "tma_load_stlb_miss",
-        "MetricThreshold": "tma_load_stlb_miss > 0.05 & (tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))",
+        "MetricThreshold": "tma_load_stlb_miss > 0.05 & tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "ScaleUnit": "100%"
+    },
+    {
+        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 1 GB pages for data load accesses",
+        "MetricExpr": "tma_load_stlb_miss * DTLB_LOAD_MISSES.WALK_COMPLETED_1G / (DTLB_LOAD_MISSES.WALK_COMPLETED_4K + DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M + DTLB_LOAD_MISSES.WALK_COMPLETED_1G)",
+        "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_load_stlb_miss_group",
+        "MetricName": "tma_load_stlb_miss_1g",
+        "MetricThreshold": "tma_load_stlb_miss_1g > 0.05 & tma_load_stlb_miss > 0.05 & tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "ScaleUnit": "100%"
+    },
+    {
+        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 2 or 4 MB pages for data load accesses",
+        "MetricExpr": "tma_load_stlb_miss * DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M / (DTLB_LOAD_MISSES.WALK_COMPLETED_4K + DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M + DTLB_LOAD_MISSES.WALK_COMPLETED_1G)",
+        "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_load_stlb_miss_group",
+        "MetricName": "tma_load_stlb_miss_2m",
+        "MetricThreshold": "tma_load_stlb_miss_2m > 0.05 & tma_load_stlb_miss > 0.05 & tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "ScaleUnit": "100%"
+    },
+    {
+        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 4 KB pages for data load accesses",
+        "MetricExpr": "tma_load_stlb_miss * DTLB_LOAD_MISSES.WALK_COMPLETED_4K / (DTLB_LOAD_MISSES.WALK_COMPLETED_4K + DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M + DTLB_LOAD_MISSES.WALK_COMPLETED_1G)",
+        "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_load_stlb_miss_group",
+        "MetricName": "tma_load_stlb_miss_4k",
+        "MetricThreshold": "tma_load_stlb_miss_4k > 0.05 & tma_load_stlb_miss > 0.05 & tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from local memory",
-        "MetricExpr": "59.5 * tma_info_system_core_frequency * MEM_LOAD_L3_MISS_RETIRED.LOCAL_DRAM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks",
+        "MetricExpr": "(80 * tma_info_system_core_frequency - 20.5 * tma_info_system_core_frequency) * MEM_LOAD_L3_MISS_RETIRED.LOCAL_DRAM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks",
         "MetricGroup": "Server;TopdownL5;tma_L5_group;tma_mem_latency_group",
         "MetricName": "tma_local_mem",
-        "MetricThreshold": "tma_local_mem > 0.1 & (tma_mem_latency > 0.1 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))",
+        "MetricThreshold": "tma_local_mem > 0.1 & tma_mem_latency > 0.1 & tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
         "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from local memory. Caching will improve the latency and increase performance. Sample with: MEM_LOAD_L3_MISS_RETIRED.LOCAL_DRAM",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "This metric represents fraction of cycles the CPU spent handling cache misses due to lock operations",
         "MetricExpr": "(12 * max(0, MEM_INST_RETIRED.LOCK_LOADS - L2_RQSTS.ALL_RFO) + MEM_INST_RETIRED.LOCK_LOADS / MEM_INST_RETIRED.ALL_STORES * (11 * L2_RQSTS.RFO_HIT + min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO))) / tma_info_thread_clks",
-        "MetricGroup": "Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_l1_bound_group",
+        "MetricGroup": "LockCont;Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_l1_bound_group",
         "MetricName": "tma_lock_latency",
-        "MetricThreshold": "tma_lock_latency > 0.2 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+        "MetricThreshold": "tma_lock_latency > 0.2 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
         "PublicDescription": "This metric represents fraction of cycles the CPU spent handling cache misses due to lock operations. Due to the microarchitecture handling of locks; they are classified as L1_Bound regardless of what memory source satisfied them. Sample with: MEM_INST_RETIRED.LOCK_LOADS. Related metrics: tma_store_latency",
         "ScaleUnit": "100%"
     },
@@ -1571,16 +1640,16 @@
         "MetricName": "tma_machine_clears",
         "MetricThreshold": "tma_machine_clears > 0.1 & tma_bad_speculation > 0.15",
         "MetricgroupNoGroup": "TopdownL2",
-        "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears.  These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT. Related metrics: tma_clears_resteers, tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_l1_bound, tma_microcode_sequencer, tma_ms_switches, tma_remote_cache",
+        "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears.  These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT. Related metrics: tma_bottleneck_memory_synchronization, tma_clears_resteers, tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_l1_bound, tma_microcode_sequencer, tma_ms_switches, tma_remote_cache",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory - DRAM ([SPR-HBM] and/or HBM)",
-        "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, cpu@OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD\\,cmask\\=4@) / tma_info_thread_clks",
-        "MetricGroup": "BvMS;MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueBW",
+        "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, cpu@OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD\\,cmask\\=0x4@) / tma_info_thread_clks",
+        "MetricGroup": "BvMB;MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueBW",
         "MetricName": "tma_mem_bandwidth",
-        "MetricThreshold": "tma_mem_bandwidth > 0.2 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
-        "PublicDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory - DRAM ([SPR-HBM] and/or HBM).  The underlying heuristic assumes that a similar off-core traffic is generated by all IA cores. This metric does not aggregate non-data-read requests by this logical processor; requests from other IA Logical Processors/Physical Cores/sockets; or other non-IA devices like GPU; hence the maximum external memory bandwidth limits may or may not be approached when this metric is flagged (see Uncore counters for that). Related metrics: tma_fb_full, tma_info_bottleneck_cache_memory_bandwidth, tma_info_system_dram_bw_use, tma_sq_full",
+        "MetricThreshold": "tma_mem_bandwidth > 0.2 & tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "PublicDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory - DRAM ([SPR-HBM] and/or HBM).  The underlying heuristic assumes that a similar off-core traffic is generated by all IA cores. This metric does not aggregate non-data-read requests by this logical processor; requests from other IA Logical Processors/Physical Cores/sockets; or other non-IA devices like GPU; hence the maximum external memory bandwidth limits may or may not be approached when this metric is flagged (see Uncore counters for that). Related metrics: tma_bottleneck_cache_memory_bandwidth, tma_fb_full, tma_info_system_dram_bw_use, tma_sq_full",
         "ScaleUnit": "100%"
     },
     {
@@ -1588,8 +1657,8 @@
         "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD) / tma_info_thread_clks - tma_mem_bandwidth",
         "MetricGroup": "BvML;MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueLat",
         "MetricName": "tma_mem_latency",
-        "MetricThreshold": "tma_mem_latency > 0.1 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
-        "PublicDescription": "This metric estimates fraction of cycles where the performance was likely hurt due to latency from external memory - DRAM ([SPR-HBM] and/or HBM).  This metric does not aggregate requests from other Logical Processors/Physical Cores/sockets (see Uncore counters for that). Related metrics: tma_info_bottleneck_cache_memory_latency, tma_l3_hit_latency",
+        "MetricThreshold": "tma_mem_latency > 0.1 & tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "PublicDescription": "This metric estimates fraction of cycles where the performance was likely hurt due to latency from external memory - DRAM ([SPR-HBM] and/or HBM).  This metric does not aggregate requests from other Logical Processors/Physical Cores/sockets (see Uncore counters for that). Related metrics: tma_bottleneck_cache_memory_latency, tma_l3_hit_latency",
         "ScaleUnit": "100%"
     },
     {
@@ -1600,11 +1669,11 @@
         "MetricName": "tma_memory_bound",
         "MetricThreshold": "tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
         "MetricgroupNoGroup": "TopdownL2",
-        "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck.  Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two).",
+        "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck.  Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two)",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric represents fraction of slots where the CPU was retiring memory operations -- uops for memory load or store accesses.",
+        "BriefDescription": "This metric represents fraction of slots where the CPU was retiring memory operations , uops for memory load or store accesses",
         "MetricExpr": "tma_light_operations * MEM_INST_RETIRED.ANY / INST_RETIRED.ANY",
         "MetricGroup": "Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group",
         "MetricName": "tma_memory_operations",
@@ -1618,7 +1687,7 @@
         "MetricGroup": "MicroSeq;TopdownL3;tma_L3_group;tma_heavy_operations_group;tma_issueMC;tma_issueMS",
         "MetricName": "tma_microcode_sequencer",
         "MetricThreshold": "tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1",
-        "PublicDescription": "This metric represents fraction of slots the CPU was retiring uops fetched by the Microcode Sequencer (MS) unit.  The MS is used for CISC instructions not supported by the default decoders (like repeat move strings; or CPUID); or by microcode assists used to address some operation modes (like in Floating Point assists). These cases can often be avoided. Sample with: IDQ.MS_UOPS. Related metrics: tma_clears_resteers, tma_info_bottleneck_irregular_overhead, tma_l1_bound, tma_machine_clears, tma_ms_switches",
+        "PublicDescription": "This metric represents fraction of slots the CPU was retiring uops fetched by the Microcode Sequencer (MS) unit.  The MS is used for CISC instructions not supported by the default decoders (like repeat move strings; or CPUID); or by microcode assists used to address some operation modes (like in Floating Point assists). These cases can often be avoided. Sample with: IDQ.MS_UOPS. Related metrics: tma_bottleneck_irregular_overhead, tma_clears_resteers, tma_l1_bound, tma_machine_clears, tma_ms_switches",
         "ScaleUnit": "100%"
     },
     {
@@ -1626,8 +1695,8 @@
         "MetricExpr": "BR_MISP_RETIRED.ALL_BRANCHES / (BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT) * INT_MISC.CLEAR_RESTEER_CYCLES / tma_info_thread_clks",
         "MetricGroup": "BadSpec;BrMispredicts;BvMP;TopdownL4;tma_L4_group;tma_branch_resteers_group;tma_issueBM",
         "MetricName": "tma_mispredicts_resteers",
-        "MetricThreshold": "tma_mispredicts_resteers > 0.05 & (tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))",
-        "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Branch Misprediction at execution stage. Sample with: INT_MISC.CLEAR_RESTEER_CYCLES. Related metrics: tma_branch_mispredicts, tma_info_bad_spec_branch_misprediction_cost, tma_info_bottleneck_mispredictions",
+        "MetricThreshold": "tma_mispredicts_resteers > 0.05 & tma_branch_resteers > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+        "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Branch Misprediction at execution stage. Sample with: INT_MISC.CLEAR_RESTEER_CYCLES. Related metrics: tma_bottleneck_mispredictions, tma_branch_mispredicts, tma_info_bad_spec_branch_misprediction_cost",
         "ScaleUnit": "100%"
     },
     {
@@ -1640,12 +1709,12 @@
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric estimates penalty in terms of percentage of([SKL+] injected blend uops out of all Uops Issued -- the Count Domain; [ADL+] cycles)",
+        "BriefDescription": "This metric estimates penalty in terms of percentage of([SKL+] injected blend uops out of all Uops Issued , the Count Domain; [ADL+] cycles)",
         "MetricExpr": "UOPS_ISSUED.VECTOR_WIDTH_MISMATCH / UOPS_ISSUED.ANY",
         "MetricGroup": "TopdownL5;tma_L5_group;tma_issueMV;tma_ports_utilized_0_group",
         "MetricName": "tma_mixing_vectors",
         "MetricThreshold": "tma_mixing_vectors > 0.05",
-        "PublicDescription": "This metric estimates penalty in terms of percentage of([SKL+] injected blend uops out of all Uops Issued -- the Count Domain; [ADL+] cycles). Usually a Mixing_Vectors over 5% is worth investigating. Read more in Appendix B1 of the Optimizations Guide for this topic. Related metrics: tma_ms_switches",
+        "PublicDescription": "This metric estimates penalty in terms of percentage of([SKL+] injected blend uops out of all Uops Issued , the Count Domain; [ADL+] cycles). Usually a Mixing_Vectors over 5% is worth investigating. Read more in Appendix B1 of the Optimizations Guide for this topic. Related metrics: tma_ms_switches",
         "ScaleUnit": "100%"
     },
     {
@@ -1653,8 +1722,8 @@
         "MetricExpr": "2 * IDQ.MS_SWITCHES / tma_info_thread_clks",
         "MetricGroup": "FetchLat;MicroSeq;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueMC;tma_issueMS;tma_issueMV;tma_issueSO",
         "MetricName": "tma_ms_switches",
-        "MetricThreshold": "tma_ms_switches > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)",
-        "PublicDescription": "This metric estimates the fraction of cycles when the CPU was stalled due to switches of uop delivery to the Microcode Sequencer (MS). Commonly used instructions are optimized for delivery by the DSB (decoded i-cache) or MITE (legacy instruction decode) pipelines. Certain operations cannot be handled natively by the execution pipeline; and must be performed by microcode (small programs injected into the execution stream). Switching to the MS too often can negatively impact performance. The MS is designated to deliver long uop flows required by CISC instructions like CPUID; or uncommon conditions like Floating Point Assists when dealing with Denormals. Sample with: IDQ.MS_SWITCHES. Related metrics: tma_clears_resteers, tma_info_bottleneck_irregular_overhead, tma_l1_bound, tma_machine_clears, tma_microcode_sequencer, tma_mixing_vectors, tma_serializing_operation",
+        "MetricThreshold": "tma_ms_switches > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+        "PublicDescription": "This metric estimates the fraction of cycles when the CPU was stalled due to switches of uop delivery to the Microcode Sequencer (MS). Commonly used instructions are optimized for delivery by the DSB (decoded i-cache) or MITE (legacy instruction decode) pipelines. Certain operations cannot be handled natively by the execution pipeline; and must be performed by microcode (small programs injected into the execution stream). Switching to the MS too often can negatively impact performance. The MS is designated to deliver long uop flows required by CISC instructions like CPUID; or uncommon conditions like Floating Point Assists when dealing with Denormals. Sample with: IDQ.MS_SWITCHES. Related metrics: tma_bottleneck_irregular_overhead, tma_clears_resteers, tma_l1_bound, tma_machine_clears, tma_microcode_sequencer, tma_mixing_vectors, tma_serializing_operation",
         "ScaleUnit": "100%"
     },
     {
@@ -1663,7 +1732,7 @@
         "MetricGroup": "Branches;BvBO;Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group",
         "MetricName": "tma_non_fused_branches",
         "MetricThreshold": "tma_non_fused_branches > 0.1 & tma_light_operations > 0.6",
-        "PublicDescription": "This metric represents fraction of slots where the CPU was retiring branch instructions that were not fused. Non-conditional branches like direct JMP or CALL would count here. Can be used to examine fusible conditional jumps that were not fused.",
+        "PublicDescription": "This metric represents fraction of slots where the CPU was retiring branch instructions that were not fused. Non-conditional branches like direct JMP or CALL would count here. Can be used to examine fusible conditional jumps that were not fused",
         "ScaleUnit": "100%"
     },
     {
@@ -1671,7 +1740,7 @@
         "MetricExpr": "tma_light_operations * INST_RETIRED.NOP / UOPS_RETIRED.RETIRE_SLOTS",
         "MetricGroup": "BvBO;Pipeline;TopdownL4;tma_L4_group;tma_other_light_ops_group",
         "MetricName": "tma_nop_instructions",
-        "MetricThreshold": "tma_nop_instructions > 0.1 & (tma_other_light_ops > 0.3 & tma_light_operations > 0.6)",
+        "MetricThreshold": "tma_nop_instructions > 0.1 & tma_other_light_ops > 0.3 & tma_light_operations > 0.6",
         "PublicDescription": "This metric represents fraction of slots where the CPU was retiring NOP (no op) instructions. Compilers often use NOPs for certain address alignments - e.g. start address of a function or loop body. Sample with: INST_RETIRED.NOP",
         "ScaleUnit": "100%"
     },
@@ -1685,29 +1754,19 @@
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric estimates fraction of slots the CPU was stalled due to other cases of misprediction (non-retired x86 branches or other types).",
+        "BriefDescription": "This metric estimates fraction of slots the CPU was stalled due to other cases of misprediction (non-retired x86 branches or other types)",
         "MetricExpr": "max(tma_branch_mispredicts * (1 - BR_MISP_RETIRED.ALL_BRANCHES / (INT_MISC.CLEARS_COUNT - MACHINE_CLEARS.COUNT)), 0.0001)",
         "MetricGroup": "BrMispredicts;BvIO;TopdownL3;tma_L3_group;tma_branch_mispredicts_group",
         "MetricName": "tma_other_mispredicts",
-        "MetricThreshold": "tma_other_mispredicts > 0.05 & (tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15)",
+        "MetricThreshold": "tma_other_mispredicts > 0.05 & tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric represents fraction of slots the CPU has wasted due to Nukes (Machine Clears) not related to memory ordering.",
+        "BriefDescription": "This metric represents fraction of slots the CPU has wasted due to Nukes (Machine Clears) not related to memory ordering",
         "MetricExpr": "max(tma_machine_clears * (1 - MACHINE_CLEARS.MEMORY_ORDERING / MACHINE_CLEARS.COUNT), 0.0001)",
         "MetricGroup": "BvIO;Machine_Clears;TopdownL3;tma_L3_group;tma_machine_clears_group",
         "MetricName": "tma_other_nukes",
-        "MetricThreshold": "tma_other_nukes > 0.05 & (tma_machine_clears > 0.1 & tma_bad_speculation > 0.15)",
-        "ScaleUnit": "100%"
-    },
-    {
-        "BriefDescription": "This metric roughly estimates (based on idle latencies) how often the CPU was stalled on accesses to external 3D-Xpoint (Crystal Ridge, a.k.a",
-        "MetricConstraint": "NO_GROUP_EVENTS",
-        "MetricExpr": "(((1 - (19 * (MEM_LOAD_L3_MISS_RETIRED.REMOTE_DRAM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS)) + 10 * (MEM_LOAD_L3_MISS_RETIRED.LOCAL_DRAM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) + MEM_LOAD_L3_MISS_RETIRED.REMOTE_FWD * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) + MEM_LOAD_L3_MISS_RETIRED.REMOTE_HITM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS))) / (19 * (MEM_LOAD_L3_MISS_RETIRED.REMOTE_DRAM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS)) + 10 * (MEM_LOAD_L3_MISS_RETIRED.LOCAL_DRAM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) + MEM_LOAD_L3_MISS_RETIRED.REMOTE_FWD * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) + MEM_LOAD_L3_MISS_RETIRED.REMOTE_HITM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS)) + (25 * (MEM_LOAD_RETIRED.LOCAL_PMM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS)) + 33 * (MEM_LOAD_L3_MISS_RETIRED.REMOTE_PMM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS))))) * (CYCLE_ACTIVITY.STALLS_L3_MISS / tma_info_thread_clks + (CYCLE_ACTIVITY.STALLS_L1D_MISS - CYCLE_ACTIVITY.STALLS_L2_MISS) / tma_info_thread_clks - tma_l2_bound) if 1e6 * (MEM_LOAD_L3_MISS_RETIRED.REMOTE_PMM + MEM_LOAD_RETIRED.LOCAL_PMM) > MEM_LOAD_RETIRED.L1_MISS else 0) if #has_pmem > 0 else 0)",
-        "MetricGroup": "MemoryBound;Server;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group",
-        "MetricName": "tma_pmm_bound",
-        "MetricThreshold": "tma_pmm_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)",
-        "PublicDescription": "This metric roughly estimates (based on idle latencies) how often the CPU was stalled on accesses to external 3D-Xpoint (Crystal Ridge, a.k.a. IXP) memory by loads, PMM stands for Persistent Memory Module.",
+        "MetricThreshold": "tma_other_nukes > 0.05 & tma_machine_clears > 0.1 & tma_bad_speculation > 0.15",
         "ScaleUnit": "100%"
     },
     {
@@ -1761,7 +1820,7 @@
         "MetricGroup": "TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P",
         "MetricName": "tma_port_5",
         "MetricThreshold": "tma_port_5 > 0.6",
-        "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 5 ([SNB+] Branches and ALU; [HSW+] ALU). Sample with: UOPS_DISPATCHED.PORT_5. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_6, tma_ports_utilized_2",
+        "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 5 ([SNB+] Branches and ALU; [HSW+] ALU). Sample with: UOPS_DISPATCHED_PORT.PORT_5. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_6, tma_ports_utilized_2",
         "ScaleUnit": "100%"
     },
     {
@@ -1770,7 +1829,7 @@
         "MetricGroup": "TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P",
         "MetricName": "tma_port_6",
         "MetricThreshold": "tma_port_6 > 0.6",
-        "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 6 ([HSW+] Primary Branch and simple ALU). Sample with: UOPS_DISPATCHED_PORT.PORT_6. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_ports_utilized_2",
+        "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 6 ([HSW+] Primary Branch and simple ALU). Sample with: UOPS_DISPATCHED_PORT.PORT_1. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_ports_utilized_2",
         "ScaleUnit": "100%"
     },
     {
@@ -1787,8 +1846,8 @@
         "MetricExpr": "((tma_ports_utilized_0 * tma_info_thread_clks + (EXE_ACTIVITY.1_PORTS_UTIL + tma_retiring * EXE_ACTIVITY.2_PORTS_UTIL)) / tma_info_thread_clks 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) / tma_info_thread_clks)",
         "MetricGroup": "PortsUtil;TopdownL3;tma_L3_group;tma_core_bound_group",
         "MetricName": "tma_ports_utilization",
-        "MetricThreshold": "tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)",
-        "PublicDescription": "This metric estimates fraction of cycles the CPU performance was potentially limited due to Core computation issues (non divider-related).  Two distinct categories can be attributed into this metric: (1) heavy data-dependency among contiguous instructions would manifest in this metric - such cases are often referred to as low Instruction Level Parallelism (ILP). (2) Contention on some hardware execution unit other than Divider. For example; when there are too many multiply operations.",
+        "MetricThreshold": "tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
+        "PublicDescription": "This metric estimates fraction of cycles the CPU performance was potentially limited due to Core computation issues (non divider-related).  Two distinct categories can be attributed into this metric: (1) heavy data-dependency among contiguous instructions would manifest in this metric - such cases are often referred to as low Instruction Level Parallelism (ILP). (2) Contention on some hardware execution unit other than Divider. For example; when there are too many multiply operations",
         "ScaleUnit": "100%"
     },
     {
@@ -1796,8 +1855,8 @@
         "MetricExpr": "EXE_ACTIVITY.EXE_BOUND_0_PORTS / tma_info_thread_clks",
         "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group",
         "MetricName": "tma_ports_utilized_0",
-        "MetricThreshold": "tma_ports_utilized_0 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))",
-        "PublicDescription": "This metric represents fraction of cycles CPU executed no uops on any execution port (Logical Processor cycles since ICL, Physical Core cycles otherwise). Long-latency instructions like divides may contribute to this metric.",
+        "MetricThreshold": "tma_ports_utilized_0 > 0.2 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
+        "PublicDescription": "This metric represents fraction of cycles CPU executed no uops on any execution port (Logical Processor cycles since ICL, Physical Core cycles otherwise). Long-latency instructions like divides may contribute to this metric",
         "ScaleUnit": "100%"
     },
     {
@@ -1805,7 +1864,7 @@
         "MetricExpr": "((UOPS_EXECUTED.CORE_CYCLES_GE_1 - UOPS_EXECUTED.CORE_CYCLES_GE_2) / 2 if #SMT_on else EXE_ACTIVITY.1_PORTS_UTIL) / tma_info_core_core_clks",
         "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_issueL1;tma_ports_utilization_group",
         "MetricName": "tma_ports_utilized_1",
-        "MetricThreshold": "tma_ports_utilized_1 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))",
+        "MetricThreshold": "tma_ports_utilized_1 > 0.2 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
         "PublicDescription": "This metric represents fraction of cycles where the CPU executed total of 1 uop per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise). This can be due to heavy data-dependency among software instructions; or over oversubscribing a particular hardware resource. In some other cases with high 1_Port_Utilized and L1_Bound; this metric can point to L1 data-cache latency bottleneck that may not necessarily manifest with complete execution starvation (due to the short L1 latency e.g. walking a linked list) - looking at the assembly can be helpful. Related metrics: tma_l1_bound",
         "ScaleUnit": "100%"
     },
@@ -1814,35 +1873,35 @@
         "MetricExpr": "((UOPS_EXECUTED.CORE_CYCLES_GE_2 - UOPS_EXECUTED.CORE_CYCLES_GE_3) / 2 if #SMT_on else EXE_ACTIVITY.2_PORTS_UTIL) / tma_info_core_core_clks",
         "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_issue2P;tma_ports_utilization_group",
         "MetricName": "tma_ports_utilized_2",
-        "MetricThreshold": "tma_ports_utilized_2 > 0.15 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))",
+        "MetricThreshold": "tma_ports_utilized_2 > 0.15 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
         "PublicDescription": "This metric represents fraction of cycles CPU executed total of 2 uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise).  Loop Vectorization -most compilers feature auto-Vectorization options today- reduces pressure on the execution ports as multiple elements are calculated with same uop. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric represents fraction of cycles CPU executed total of 3 or more uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise).",
+        "BriefDescription": "This metric represents fraction of cycles CPU executed total of 3 or more uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise)",
         "MetricExpr": "(UOPS_EXECUTED.CORE_CYCLES_GE_3 / 2 if #SMT_on else UOPS_EXECUTED.CORE_CYCLES_GE_3) / tma_info_core_core_clks",
         "MetricGroup": "BvCB;PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group",
         "MetricName": "tma_ports_utilized_3m",
-        "MetricThreshold": "tma_ports_utilized_3m > 0.4 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))",
+        "MetricThreshold": "tma_ports_utilized_3m > 0.4 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from remote cache in other sockets including synchronizations issues",
         "MetricConstraint": "NO_GROUP_EVENTS_NMI",
-        "MetricExpr": "(89.5 * tma_info_system_core_frequency * MEM_LOAD_L3_MISS_RETIRED.REMOTE_HITM + 89.5 * tma_info_system_core_frequency * MEM_LOAD_L3_MISS_RETIRED.REMOTE_FWD) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks",
+        "MetricExpr": "((110 * tma_info_system_core_frequency - 20.5 * tma_info_system_core_frequency) * MEM_LOAD_L3_MISS_RETIRED.REMOTE_HITM + (110 * tma_info_system_core_frequency - 20.5 * tma_info_system_core_frequency) * MEM_LOAD_L3_MISS_RETIRED.REMOTE_FWD) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks",
         "MetricGroup": "Offcore;Server;Snoop;TopdownL5;tma_L5_group;tma_issueSyncxn;tma_mem_latency_group",
         "MetricName": "tma_remote_cache",
-        "MetricThreshold": "tma_remote_cache > 0.05 & (tma_mem_latency > 0.1 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))",
-        "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from remote cache in other sockets including synchronizations issues. This is caused often due to non-optimal NUMA allocations. #link to NUMA article. Sample with: MEM_LOAD_L3_MISS_RETIRED.REMOTE_HITM_PS;MEM_LOAD_L3_MISS_RETIRED.REMOTE_FWD_PS. Related metrics: tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_machine_clears",
+        "MetricThreshold": "tma_remote_cache > 0.05 & tma_mem_latency > 0.1 & tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from remote cache in other sockets including synchronizations issues. This is caused often due to non-optimal NUMA allocations. Sample with: MEM_LOAD_L3_MISS_RETIRED.REMOTE_HITM, MEM_LOAD_L3_MISS_RETIRED.REMOTE_FWD. Related metrics: tma_bottleneck_memory_synchronization, tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_machine_clears",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from remote memory",
-        "MetricExpr": "127 * tma_info_system_core_frequency * MEM_LOAD_L3_MISS_RETIRED.REMOTE_DRAM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks",
+        "MetricExpr": "(147.5 * tma_info_system_core_frequency - 20.5 * tma_info_system_core_frequency) * MEM_LOAD_L3_MISS_RETIRED.REMOTE_DRAM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks",
         "MetricGroup": "Server;Snoop;TopdownL5;tma_L5_group;tma_mem_latency_group",
         "MetricName": "tma_remote_mem",
-        "MetricThreshold": "tma_remote_mem > 0.1 & (tma_mem_latency > 0.1 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))",
-        "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from remote memory. This is caused often due to non-optimal NUMA allocations. #link to NUMA article. Sample with: MEM_LOAD_L3_MISS_RETIRED.REMOTE_DRAM_PS",
+        "MetricThreshold": "tma_remote_mem > 0.1 & tma_mem_latency > 0.1 & tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from remote memory. This is caused often due to non-optimal NUMA allocations. Sample with: MEM_LOAD_L3_MISS_RETIRED.REMOTE_DRAM",
         "ScaleUnit": "100%"
     },
     {
@@ -1860,7 +1919,7 @@
         "MetricExpr": "PARTIAL_RAT_STALLS.SCOREBOARD / tma_info_thread_clks",
         "MetricGroup": "BvIO;PortsUtil;TopdownL3;tma_L3_group;tma_core_bound_group;tma_issueSO",
         "MetricName": "tma_serializing_operation",
-        "MetricThreshold": "tma_serializing_operation > 0.1 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)",
+        "MetricThreshold": "tma_serializing_operation > 0.1 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
         "PublicDescription": "This metric represents fraction of cycles the CPU issue-pipeline was stalled due to serializing operations. Instructions like CPUID; WRMSR or LFENCE serialize the out-of-order execution which may limit performance. Sample with: PARTIAL_RAT_STALLS.SCOREBOARD. Related metrics: tma_ms_switches",
         "ScaleUnit": "100%"
     },
@@ -1869,8 +1928,8 @@
         "MetricExpr": "40 * ROB_MISC_EVENTS.PAUSE_INST / tma_info_thread_clks",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_serializing_operation_group",
         "MetricName": "tma_slow_pause",
-        "MetricThreshold": "tma_slow_pause > 0.05 & (tma_serializing_operation > 0.1 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))",
-        "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to PAUSE Instructions. Sample with: MISC_RETIRED.PAUSE_INST",
+        "MetricThreshold": "tma_slow_pause > 0.05 & tma_serializing_operation > 0.1 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
+        "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to PAUSE Instructions. Sample with: ROB_MISC_EVENTS.PAUSE_INST",
         "ScaleUnit": "100%"
     },
     {
@@ -1879,8 +1938,8 @@
         "MetricExpr": "tma_info_memory_load_miss_real_latency * LD_BLOCKS.NO_SR / tma_info_thread_clks",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group",
         "MetricName": "tma_split_loads",
-        "MetricThreshold": "tma_split_loads > 0.2 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
-        "PublicDescription": "This metric estimates fraction of cycles handling memory load split accesses - load that cross 64-byte cache line boundary. Sample with: MEM_INST_RETIRED.SPLIT_LOADS_PS",
+        "MetricThreshold": "tma_split_loads > 0.3",
+        "PublicDescription": "This metric estimates fraction of cycles handling memory load split accesses - load that cross 64-byte cache line boundary. Sample with: MEM_INST_RETIRED.SPLIT_LOADS",
         "ScaleUnit": "100%"
     },
     {
@@ -1888,17 +1947,17 @@
         "MetricExpr": "MEM_INST_RETIRED.SPLIT_STORES / tma_info_core_core_clks",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_issueSpSt;tma_store_bound_group",
         "MetricName": "tma_split_stores",
-        "MetricThreshold": "tma_split_stores > 0.2 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
-        "PublicDescription": "This metric represents rate of split store accesses.  Consider aligning your data to the 64-byte cache line granularity. Sample with: MEM_INST_RETIRED.SPLIT_STORES_PS. Related metrics: tma_port_4",
+        "MetricThreshold": "tma_split_stores > 0.2 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "PublicDescription": "This metric represents rate of split store accesses.  Consider aligning your data to the 64-byte cache line granularity. Sample with: MEM_INST_RETIRED.SPLIT_STORES. Related metrics: tma_port_4",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors)",
         "MetricExpr": "(OFFCORE_REQUESTS_BUFFER.SQ_FULL / 2 if #SMT_on else OFFCORE_REQUESTS_BUFFER.SQ_FULL) / tma_info_core_core_clks",
-        "MetricGroup": "BvMS;MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_issueBW;tma_l3_bound_group",
+        "MetricGroup": "BvMB;MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_issueBW;tma_l3_bound_group",
         "MetricName": "tma_sq_full",
-        "MetricThreshold": "tma_sq_full > 0.3 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
-        "PublicDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors). Related metrics: tma_fb_full, tma_info_bottleneck_cache_memory_bandwidth, tma_info_system_dram_bw_use, tma_mem_bandwidth",
+        "MetricThreshold": "tma_sq_full > 0.3 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "PublicDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors). Related metrics: tma_bottleneck_cache_memory_bandwidth, tma_fb_full, tma_info_system_dram_bw_use, tma_mem_bandwidth",
         "ScaleUnit": "100%"
     },
     {
@@ -1906,8 +1965,8 @@
         "MetricExpr": "EXE_ACTIVITY.BOUND_ON_STORES / tma_info_thread_clks",
         "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group",
         "MetricName": "tma_store_bound",
-        "MetricThreshold": "tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)",
-        "PublicDescription": "This metric estimates how often CPU was stalled  due to RFO store memory accesses; RFO store issue a read-for-ownership request before the write. Even though store accesses do not typically stall out-of-order CPUs; there are few cases where stores can lead to actual stalls. This metric will be flagged should RFO stores be a bottleneck. Sample with: MEM_INST_RETIRED.ALL_STORES_PS",
+        "MetricThreshold": "tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "PublicDescription": "This metric estimates how often CPU was stalled  due to RFO store memory accesses; RFO store issue a read-for-ownership request before the write. Even though store accesses do not typically stall out-of-order CPUs; there are few cases where stores can lead to actual stalls. This metric will be flagged should RFO stores be a bottleneck. Sample with: MEM_INST_RETIRED.ALL_STORES",
         "ScaleUnit": "100%"
     },
     {
@@ -1915,18 +1974,18 @@
         "MetricExpr": "13 * LD_BLOCKS.STORE_FORWARD / tma_info_thread_clks",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group",
         "MetricName": "tma_store_fwd_blk",
-        "MetricThreshold": "tma_store_fwd_blk > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
-        "PublicDescription": "This metric roughly estimates fraction of cycles when the memory subsystem had loads blocked since they could not forward data from earlier (in program order) overlapping stores. To streamline memory operations in the pipeline; a load can avoid waiting for memory if a prior in-flight store is writing the data that the load wants to read (store forwarding process). However; in some cases the load may be blocked for a significant time pending the store forward. For example; when the prior store is writing a smaller region than the load is reading.",
+        "MetricThreshold": "tma_store_fwd_blk > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "PublicDescription": "This metric roughly estimates fraction of cycles when the memory subsystem had loads blocked since they could not forward data from earlier (in program order) overlapping stores. To streamline memory operations in the pipeline; a load can avoid waiting for memory if a prior in-flight store is writing the data that the load wants to read (store forwarding process). However; in some cases the load may be blocked for a significant time pending the store forward. For example; when the prior store is writing a smaller region than the load is reading",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "This metric estimates fraction of cycles the CPU spent handling L1D store misses",
         "MetricConstraint": "NO_GROUP_EVENTS_NMI",
         "MetricExpr": "(L2_RQSTS.RFO_HIT * 11 * (1 - MEM_INST_RETIRED.LOCK_LOADS / MEM_INST_RETIRED.ALL_STORES) + (1 - MEM_INST_RETIRED.LOCK_LOADS / MEM_INST_RETIRED.ALL_STORES) * min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO)) / tma_info_thread_clks",
-        "MetricGroup": "BvML;MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_issueSL;tma_store_bound_group",
+        "MetricGroup": "BvML;LockCont;MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_issueSL;tma_store_bound_group",
         "MetricName": "tma_store_latency",
-        "MetricThreshold": "tma_store_latency > 0.1 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
-        "PublicDescription": "This metric estimates fraction of cycles the CPU spent handling L1D store misses. Store accesses usually less impact out-of-order core performance; however; holding resources for longer time can lead into undesired implications (e.g. contention on L1D fill-buffer entries - see FB_Full). Related metrics: tma_fb_full, tma_lock_latency",
+        "MetricThreshold": "tma_store_latency > 0.1 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "PublicDescription": "This metric estimates fraction of cycles the CPU spent handling L1D store misses. Store accesses usually less impact out-of-order core performance; however; holding resources for longer time can lead into undesired implications (e.g. contention on L1D fill-buffer entries - see FB_Full). Related metrics: tma_branch_resteers, tma_fb_full, tma_l3_hit_latency, tma_lock_latency",
         "ScaleUnit": "100%"
     },
     {
@@ -1942,7 +2001,7 @@
         "MetricExpr": "tma_dtlb_store - tma_store_stlb_miss",
         "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_store_group",
         "MetricName": "tma_store_stlb_hit",
-        "MetricThreshold": "tma_store_stlb_hit > 0.05 & (tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))",
+        "MetricThreshold": "tma_store_stlb_hit > 0.05 & tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
         "ScaleUnit": "100%"
     },
     {
@@ -1950,7 +2009,31 @@
         "MetricExpr": "DTLB_STORE_MISSES.WALK_ACTIVE / tma_info_core_core_clks",
         "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_store_group",
         "MetricName": "tma_store_stlb_miss",
-        "MetricThreshold": "tma_store_stlb_miss > 0.05 & (tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))",
+        "MetricThreshold": "tma_store_stlb_miss > 0.05 & tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "ScaleUnit": "100%"
+    },
+    {
+        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 1 GB pages for data store accesses",
+        "MetricExpr": "tma_store_stlb_miss * DTLB_STORE_MISSES.WALK_COMPLETED_1G / (DTLB_STORE_MISSES.WALK_COMPLETED_4K + DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M + DTLB_STORE_MISSES.WALK_COMPLETED_1G)",
+        "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_store_stlb_miss_group",
+        "MetricName": "tma_store_stlb_miss_1g",
+        "MetricThreshold": "tma_store_stlb_miss_1g > 0.05 & tma_store_stlb_miss > 0.05 & tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "ScaleUnit": "100%"
+    },
+    {
+        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 2 or 4 MB pages for data store accesses",
+        "MetricExpr": "tma_store_stlb_miss * DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M / (DTLB_STORE_MISSES.WALK_COMPLETED_4K + DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M + DTLB_STORE_MISSES.WALK_COMPLETED_1G)",
+        "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_store_stlb_miss_group",
+        "MetricName": "tma_store_stlb_miss_2m",
+        "MetricThreshold": "tma_store_stlb_miss_2m > 0.05 & tma_store_stlb_miss > 0.05 & tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "ScaleUnit": "100%"
+    },
+    {
+        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 4 KB pages for data store accesses",
+        "MetricExpr": "tma_store_stlb_miss * DTLB_STORE_MISSES.WALK_COMPLETED_4K / (DTLB_STORE_MISSES.WALK_COMPLETED_4K + DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M + DTLB_STORE_MISSES.WALK_COMPLETED_1G)",
+        "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_store_stlb_miss_group",
+        "MetricName": "tma_store_stlb_miss_4k",
+        "MetricThreshold": "tma_store_stlb_miss_4k > 0.05 & tma_store_stlb_miss > 0.05 & tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
         "ScaleUnit": "100%"
     },
     {
@@ -1958,7 +2041,7 @@
         "MetricExpr": "9 * BACLEARS.ANY / tma_info_thread_clks",
         "MetricGroup": "BigFootprint;BvBC;FetchLat;TopdownL4;tma_L4_group;tma_branch_resteers_group",
         "MetricName": "tma_unknown_branches",
-        "MetricThreshold": "tma_unknown_branches > 0.05 & (tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))",
+        "MetricThreshold": "tma_unknown_branches > 0.05 & tma_branch_resteers > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
         "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to new branch address clears. These are fetched branches the Branch Prediction Unit was unable to recognize (e.g. first time the branch is fetched or hitting BTB capacity limit) hence called Unknown Branches. Sample with: BACLEARS.ANY",
         "ScaleUnit": "100%"
     },
@@ -1967,8 +2050,8 @@
         "MetricExpr": "tma_retiring * UOPS_EXECUTED.X87 / UOPS_EXECUTED.THREAD",
         "MetricGroup": "Compute;TopdownL4;tma_L4_group;tma_fp_arith_group",
         "MetricName": "tma_x87_use",
-        "MetricThreshold": "tma_x87_use > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6)",
-        "PublicDescription": "This metric serves as an approximation of legacy x87 usage. It accounts for instructions beyond X87 FP arithmetic operations; hence may be used as a thermometer to avoid X87 high usage and preferably upgrade to modern ISA. See Tip under Tuning Hint.",
+        "MetricThreshold": "tma_x87_use > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6",
+        "PublicDescription": "This metric serves as an approximation of legacy x87 usage. It accounts for instructions beyond X87 FP arithmetic operations; hence may be used as a thermometer to avoid X87 high usage and preferably upgrade to modern ISA. See Tip under Tuning Hint",
         "ScaleUnit": "100%"
     },
     {
tools/perf/pmu-events/arch/x86/cascadelakex/metricgroups.json +8 -1
index cccfcab3425e..a579603f720b 100644
@@ -38,6 +38,7 @@
     "IoBW": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
     "L2Evicts": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
     "LSD": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
+    "LockCont": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
     "MachineClears": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
     "Machine_Clears": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
     "Mem": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
@@ -84,7 +85,9 @@
     "tma_bad_speculation_group": "Metrics contributing to tma_bad_speculation category",
     "tma_branch_mispredicts_group": "Metrics contributing to tma_branch_mispredicts category",
     "tma_branch_resteers_group": "Metrics contributing to tma_branch_resteers category",
+    "tma_code_stlb_miss_group": "Metrics contributing to tma_code_stlb_miss category",
     "tma_core_bound_group": "Metrics contributing to tma_core_bound category",
+    "tma_divider_group": "Metrics contributing to tma_divider category",
     "tma_dram_bound_group": "Metrics contributing to tma_dram_bound category",
     "tma_dtlb_load_group": "Metrics contributing to tma_dtlb_load category",
     "tma_dtlb_store_group": "Metrics contributing to tma_dtlb_store category",
@@ -113,10 +116,13 @@
     "tma_issueSpSt": "Metrics related by the issue $issueSpSt",
     "tma_issueSyncxn": "Metrics related by the issue $issueSyncxn",
     "tma_issueTLB": "Metrics related by the issue $issueTLB",
+    "tma_itlb_misses_group": "Metrics contributing to tma_itlb_misses category",
     "tma_l1_bound_group": "Metrics contributing to tma_l1_bound category",
+    "tma_l2_bound_group": "Metrics contributing to tma_l2_bound category",
     "tma_l3_bound_group": "Metrics contributing to tma_l3_bound category",
     "tma_light_operations_group": "Metrics contributing to tma_light_operations category",
     "tma_load_op_utilization_group": "Metrics contributing to tma_load_op_utilization category",
+    "tma_load_stlb_miss_group": "Metrics contributing to tma_load_stlb_miss category",
     "tma_machine_clears_group": "Metrics contributing to tma_machine_clears category",
     "tma_mem_latency_group": "Metrics contributing to tma_mem_latency category",
     "tma_memory_bound_group": "Metrics contributing to tma_memory_bound category",
@@ -129,5 +135,6 @@
     "tma_retiring_group": "Metrics contributing to tma_retiring category",
     "tma_serializing_operation_group": "Metrics contributing to tma_serializing_operation category",
     "tma_store_bound_group": "Metrics contributing to tma_store_bound category",
-    "tma_store_op_utilization_group": "Metrics contributing to tma_store_op_utilization category"
+    "tma_store_op_utilization_group": "Metrics contributing to tma_store_op_utilization category",
+    "tma_store_stlb_miss_group": "Metrics contributing to tma_store_stlb_miss category"
 }
tools/perf/pmu-events/arch/x86/cascadelakex/uncore-cache.json +30 -30

240 lines not on this page · raw message

tools/perf/pmu-events/arch/x86/cascadelakex/uncore-interconnect.json +0 -11
index 91889e447bd1..4efbfeb338a6 100644
@@ -13855,16 +13855,5 @@
         "PerPkg": "1",
         "PublicDescription": "Number outstanding register requests within message channel tracker",
         "Unit": "UBOX"
-    },
-    {
-        "BriefDescription": "UPI interconnect send bandwidth for payload. Derived from unc_upi_txl_flits.all_data",
-        "Counter": "0,1,2,3",
-        "EventCode": "0x2",
-        "EventName": "UPI_DATA_BANDWIDTH_TX",
-        "PerPkg": "1",
-        "PublicDescription": "Counts valid data FLITs (80 bit FLow control unITs: 64bits of data) transmitted (TxL) via any of the 3 Intel(R) Ultra Path Interconnect (UPI) slots on this UPI unit.",
-        "ScaleUnit": "7.11E-06Bytes",
-        "UMask": "0xf",
-        "Unit": "UPI"
     }
 ]
tools/perf/pmu-events/arch/x86/mapfile.csv +1 -1
index 6405c7627e27..a1a3a8c1af02 100644
@@ -6,7 +6,7 @@ GenuineIntel-6-(1C|26|27|35|36),v5,bonnell,core
 GenuineIntel-6-(3D|47),v30,broadwell,core
 GenuineIntel-6-56,v12,broadwellde,core
 GenuineIntel-6-4F,v23,broadwellx,core
-GenuineIntel-6-55-[56789ABCDEF],v1.22,cascadelakex,core
+GenuineIntel-6-55-[56789ABCDEF],v1.23,cascadelakex,core
 GenuineIntel-6-9[6C],v1.05,elkhartlake,core
 GenuineIntel-6-CF,v1.09,emeraldrapids,core
 GenuineIntel-6-5[CF],v13,goldmont,core
Signature · 1 line
2.48.1.502.g6dc24dfdaf-goog
author reviewer
#8 lore raw

PATCH v8 8/24 perf vendor events: Add Clearwaterforest events

In reply to Ian Rogers

Add events v1.00.

Bring in the events from:
https://github.com/intel/perfmon/tree/main/CWF/events

---
 .../arch/x86/clearwaterforest/cache.json      | 144 ++++++++++++++++++
 .../arch/x86/clearwaterforest/counter.json    |   7 +
 .../arch/x86/clearwaterforest/frontend.json   |  18 +++
 .../arch/x86/clearwaterforest/memory.json     |  22 +++
 .../arch/x86/clearwaterforest/other.json      |  22 +++
 .../arch/x86/clearwaterforest/pipeline.json   | 113 ++++++++++++++
 .../x86/clearwaterforest/virtual-memory.json  |  29 ++++
 tools/perf/pmu-events/arch/x86/mapfile.csv    |   1 +
 8 files changed, 356 insertions(+)
 create mode 100644 tools/perf/pmu-events/arch/x86/clearwaterforest/cache.json
 create mode 100644 tools/perf/pmu-events/arch/x86/clearwaterforest/counter.json
 create mode 100644 tools/perf/pmu-events/arch/x86/clearwaterforest/frontend.json
 create mode 100644 tools/perf/pmu-events/arch/x86/clearwaterforest/memory.json
 create mode 100644 tools/perf/pmu-events/arch/x86/clearwaterforest/other.json
 create mode 100644 tools/perf/pmu-events/arch/x86/clearwaterforest/pipeline.json
 create mode 100644 tools/perf/pmu-events/arch/x86/clearwaterforest/virtual-memory.json
tools/perf/pmu-events/arch/x86/clearwaterforest/cache.json new file +144 -0
new file mode 100644
index 000000000000..875361b30f1d
@@ -0,0 +1,144 @@
+[
+    {
+        "BriefDescription": "Counts the number of cacheable memory requests that miss in the LLC. Counts on a per core basis.",
+        "Counter": "0,1,2,3,4,5,6,7",
+        "EventCode": "0x2e",
+        "EventName": "LONGEST_LAT_CACHE.MISS",
+        "PublicDescription": "Counts the number of cacheable memory requests that miss in the Last Level Cache (LLC). Requests include demand loads, reads for ownership (RFO), instruction fetches and L1 HW prefetches. If the core has access to an L3 cache, the LLC is the L3 cache, otherwise it is the L2 cache. Counts on a per core basis.",
+        "SampleAfterValue": "1000003",
+        "UMask": "0x41"
+    },
+    {
+        "BriefDescription": "Counts the number of cacheable memory requests that access the LLC. Counts on a per core basis.",
+        "Counter": "0,1,2,3,4,5,6,7",
+        "EventCode": "0x2e",
+        "EventName": "LONGEST_LAT_CACHE.REFERENCE",
+        "PublicDescription": "Counts the number of cacheable memory requests that access the Last Level Cache (LLC). Requests include demand loads, reads for ownership (RFO), instruction fetches and L1 HW prefetches. If the core has access to an L3 cache, the LLC is the L3 cache, otherwise it is the L2 cache. Counts on a per core basis.",
+        "SampleAfterValue": "1000003",
+        "UMask": "0x4f"
+    },
+    {
+        "BriefDescription": "Counts the number of load ops retired.",
+        "Counter": "0,1,2,3,4,5,6,7",
+        "EventCode": "0xd0",
+        "EventName": "MEM_UOPS_RETIRED.ALL_LOADS",
+        "SampleAfterValue": "1000003",
+        "UMask": "0x81"
+    },
+    {
+        "BriefDescription": "Counts the number of store ops retired.",
+        "Counter": "0,1,2,3,4,5,6,7",
+        "EventCode": "0xd0",
+        "EventName": "MEM_UOPS_RETIRED.ALL_STORES",
+        "SampleAfterValue": "1000003",
+        "UMask": "0x82"
+    },
+    {
+        "BriefDescription": "Counts the number of tagged load uops retired that exceed the latency threshold defined in MEC_CR_PEBS_LD_LAT_THRESHOLD - Only counts with PEBS enabled.",
+        "Counter": "0,1",
+        "EventCode": "0xd0",
+        "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_1024",
+        "MSRIndex": "0x3F6",
+        "MSRValue": "0x400",
+        "SampleAfterValue": "1000003",
+        "UMask": "0x5"
+    },
+    {
+        "BriefDescription": "Counts the number of tagged load uops retired that exceed the latency threshold defined in MEC_CR_PEBS_LD_LAT_THRESHOLD - Only counts with PEBS enabled.",
+        "Counter": "0,1",
+        "EventCode": "0xd0",
+        "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_128",
+        "MSRIndex": "0x3F6",
+        "MSRValue": "0x80",
+        "SampleAfterValue": "1000003",
+        "UMask": "0x5"
+    },
+    {
+        "BriefDescription": "Counts the number of tagged load uops retired that exceed the latency threshold defined in MEC_CR_PEBS_LD_LAT_THRESHOLD - Only counts with PEBS enabled.",
+        "Counter": "0,1",
+        "EventCode": "0xd0",
+        "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_16",
+        "MSRIndex": "0x3F6",
+        "MSRValue": "0x10",
+        "SampleAfterValue": "1000003",
+        "UMask": "0x5"
+    },
+    {
+        "BriefDescription": "Counts the number of tagged load uops retired that exceed the latency threshold defined in MEC_CR_PEBS_LD_LAT_THRESHOLD - Only counts with PEBS enabled.",
+        "Counter": "0,1",
+        "EventCode": "0xd0",
+        "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_2048",
+        "MSRIndex": "0x3F6",
+        "MSRValue": "0x800",
+        "SampleAfterValue": "1000003",
+        "UMask": "0x5"
+    },
+    {
+        "BriefDescription": "Counts the number of tagged load uops retired that exceed the latency threshold defined in MEC_CR_PEBS_LD_LAT_THRESHOLD - Only counts with PEBS enabled.",
+        "Counter": "0,1",
+        "EventCode": "0xd0",
+        "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_256",
+        "MSRIndex": "0x3F6",
+        "MSRValue": "0x100",
+        "SampleAfterValue": "1000003",
+        "UMask": "0x5"
+    },
+    {
+        "BriefDescription": "Counts the number of tagged load uops retired that exceed the latency threshold defined in MEC_CR_PEBS_LD_LAT_THRESHOLD - Only counts with PEBS enabled.",
+        "Counter": "0,1",
+        "EventCode": "0xd0",
+        "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_32",
+        "MSRIndex": "0x3F6",
+        "MSRValue": "0x20",
+        "SampleAfterValue": "1000003",
+        "UMask": "0x5"
+    },
+    {
+        "BriefDescription": "Counts the number of tagged load uops retired that exceed the latency threshold defined in MEC_CR_PEBS_LD_LAT_THRESHOLD - Only counts with PEBS enabled.",
+        "Counter": "0,1",
+        "EventCode": "0xd0",
+        "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_4",
+        "MSRIndex": "0x3F6",
+        "MSRValue": "0x4",
+        "SampleAfterValue": "1000003",
+        "UMask": "0x5"
+    },
+    {
+        "BriefDescription": "Counts the number of tagged load uops retired that exceed the latency threshold defined in MEC_CR_PEBS_LD_LAT_THRESHOLD - Only counts with PEBS enabled.",
+        "Counter": "0,1",
+        "EventCode": "0xd0",
+        "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_512",
+        "MSRIndex": "0x3F6",
+        "MSRValue": "0x200",
+        "SampleAfterValue": "1000003",
+        "UMask": "0x5"
+    },
+    {
+        "BriefDescription": "Counts the number of tagged load uops retired that exceed the latency threshold defined in MEC_CR_PEBS_LD_LAT_THRESHOLD - Only counts with PEBS enabled.",
+        "Counter": "0,1",
+        "EventCode": "0xd0",
+        "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_64",
+        "MSRIndex": "0x3F6",
+        "MSRValue": "0x40",
+        "SampleAfterValue": "1000003",
+        "UMask": "0x5"
+    },
+    {
+        "BriefDescription": "Counts the number of tagged load uops retired that exceed the latency threshold defined in MEC_CR_PEBS_LD_LAT_THRESHOLD - Only counts with PEBS enabled.",
+        "Counter": "0,1",
+        "EventCode": "0xd0",
+        "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_8",
+        "MSRIndex": "0x3F6",
+        "MSRValue": "0x8",
+        "SampleAfterValue": "1000003",
+        "UMask": "0x5"
+    },
+    {
+        "BriefDescription": "Counts the number of  stores uops retired same as MEM_UOPS_RETIRED.ALL_STORES",
+        "Counter": "0,1,2,3,4,5,6,7",
+        "EventCode": "0xd0",
+        "EventName": "MEM_UOPS_RETIRED.STORE_LATENCY",
+        "SampleAfterValue": "1000003",
+        "UMask": "0x6"
+    }
+]
tools/perf/pmu-events/arch/x86/clearwaterforest/counter.json new file +7 -0
new file mode 100644
index 000000000000..a0eaf5b6f2bc
@@ -0,0 +1,7 @@
+[
+    {
+        "Unit": "core",
+        "CountersNumFixed": "3",
+        "CountersNumGeneric": "39"
+    }
+]
\ No newline at end of file
tools/perf/pmu-events/arch/x86/clearwaterforest/frontend.json new file +18 -0
new file mode 100644
index 000000000000..7a9250e5c8f2
@@ -0,0 +1,18 @@
+[
+    {
+        "BriefDescription": "Counts every time the code stream enters into a new cache line by walking sequential from the previous line or being redirected by a jump.",
+        "Counter": "0,1,2,3,4,5,6,7",
+        "EventCode": "0x80",
+        "EventName": "ICACHE.ACCESSES",
+        "SampleAfterValue": "1000003",
+        "UMask": "0x3"
+    },
+    {
+        "BriefDescription": "Counts every time the code stream enters into a new cache line by walking sequential from the previous line or being redirected by a jump and the instruction cache registers bytes are not present. -",
+        "Counter": "0,1,2,3,4,5,6,7",
+        "EventCode": "0x80",
+        "EventName": "ICACHE.MISSES",
+        "SampleAfterValue": "1000003",
+        "UMask": "0x2"
+    }
+]
tools/perf/pmu-events/arch/x86/clearwaterforest/memory.json new file +22 -0
new file mode 100644
index 000000000000..f5007e56f39b
@@ -0,0 +1,22 @@
+[
+    {
+        "BriefDescription": "Counts demand data reads that were not supplied by the L3 cache.",
+        "Counter": "0,1,2,3,4,5,6,7",
+        "EventCode": "0xB7",
+        "EventName": "OCR.DEMAND_DATA_RD.L3_MISS",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x33FBFC00001",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts demand read for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that were not supplied by the L3 cache.",
+        "Counter": "0,1,2,3,4,5,6,7",
+        "EventCode": "0xB7",
+        "EventName": "OCR.DEMAND_RFO.L3_MISS",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x33FBFC00002",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    }
+]
tools/perf/pmu-events/arch/x86/clearwaterforest/other.json new file +22 -0
new file mode 100644
index 000000000000..80454e497f83
@@ -0,0 +1,22 @@
+[
+    {
+        "BriefDescription": "Counts demand data reads that have any type of response.",
+        "Counter": "0,1,2,3,4,5,6,7",
+        "EventCode": "0xB7",
+        "EventName": "OCR.DEMAND_DATA_RD.ANY_RESPONSE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x10001",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts demand read for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that have any type of response.",
+        "Counter": "0,1,2,3,4,5,6,7",
+        "EventCode": "0xB7",
+        "EventName": "OCR.DEMAND_RFO.ANY_RESPONSE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x10002",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    }
+]
tools/perf/pmu-events/arch/x86/clearwaterforest/pipeline.json new file +113 -0

113 lines not on this page · raw message

tools/perf/pmu-events/arch/x86/clearwaterforest/virtual-memory.json new file +29 -0
new file mode 100644
index 000000000000..78f2b835c1fa
@@ -0,0 +1,29 @@
+[
+    {
+        "BriefDescription": "Counts the number of page walks completed due to load DTLB misses to any page size.",
+        "Counter": "0,1,2,3,4,5,6,7",
+        "EventCode": "0x08",
+        "EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED",
+        "PublicDescription": "Counts the number of page walks completed due to loads (including SW prefetches) whose address translations missed in all Translation Lookaside Buffer (TLB) levels and were mapped to any page size. Includes page walks that page fault.",
+        "SampleAfterValue": "1000003",
+        "UMask": "0xe"
+    },
+    {
+        "BriefDescription": "Counts the number of page walks completed due to store DTLB misses to any page size.",
+        "Counter": "0,1,2,3,4,5,6,7",
+        "EventCode": "0x49",
+        "EventName": "DTLB_STORE_MISSES.WALK_COMPLETED",
+        "PublicDescription": "Counts the number of page walks completed due to stores whose address translations missed in all Translation Lookaside Buffer (TLB) levels and were mapped to any page size.  Includes page walks that page fault.",
+        "SampleAfterValue": "1000003",
+        "UMask": "0xe"
+    },
+    {
+        "BriefDescription": "Counts the number of page walks completed due to instruction fetch misses to any page size.",
+        "Counter": "0,1,2,3,4,5,6,7",
+        "EventCode": "0x85",
+        "EventName": "ITLB_MISSES.WALK_COMPLETED",
+        "PublicDescription": "Counts the number of page walks completed due to instruction fetches whose address translations missed in all Translation Lookaside Buffer (TLB) levels and were mapped to any page size.  Includes page walks that page fault.",
+        "SampleAfterValue": "1000003",
+        "UMask": "0xe"
+    }
+]
tools/perf/pmu-events/arch/x86/mapfile.csv +1 -0
index a1a3a8c1af02..68c33fa7328a 100644
@@ -7,6 +7,7 @@ GenuineIntel-6-(3D|47),v30,broadwell,core
 GenuineIntel-6-56,v12,broadwellde,core
 GenuineIntel-6-4F,v23,broadwellx,core
 GenuineIntel-6-55-[56789ABCDEF],v1.23,cascadelakex,core
+GenuineIntel-6-DD,v1.00,clearwaterforest,core
 GenuineIntel-6-9[6C],v1.05,elkhartlake,core
 GenuineIntel-6-CF,v1.09,emeraldrapids,core
 GenuineIntel-6-5[CF],v13,goldmont,core
Signature · 1 line
2.48.1.502.g6dc24dfdaf-goog
author reviewer
#9 lore raw

PATCH v8 9/24 perf vendor events: Update EmeraldRapids events/metrics

In reply to Ian Rogers

Update events from v1.09 to v1.11.
Update TMA metrics from 4.8 to 5.02.

Bring in the event updates v1.11:
https://github.com/intel/perfmon/commit/bffcec00a184bb93d505f182047cf889d124fbd5
https://github.com/intel/perfmon/commit/a63da6de48046c365ab91c5001bfd5d907d5a1d6

The TMA 5.02 update is from (with subsequent fixes):
https://github.com/intel/perfmon/commit/1d72913b2d938781fb28f3cc3507aaec5c22d782

Update uncore IIO events umask with the change:
https://github.com/intel/perfmon/commit/d78e8a166537c9ceab4f2e901dc96c53667a2174
which should address an issue originally raised by Michael Petlan:

---
 .../arch/x86/emeraldrapids/cache.json         |  28 +-
 .../arch/x86/emeraldrapids/emr-metrics.json   | 976 ++++++++++--------
 .../arch/x86/emeraldrapids/frontend.json      |  19 -
 .../arch/x86/emeraldrapids/memory.json        |  15 +-
 .../arch/x86/emeraldrapids/metricgroups.json  |  10 +-
 .../arch/x86/emeraldrapids/pipeline.json      |  23 -
 .../arch/x86/emeraldrapids/uncore-io.json     | 218 ++--
 tools/perf/pmu-events/arch/x86/mapfile.csv    |   2 +-
 8 files changed, 602 insertions(+), 689 deletions(-)
tools/perf/pmu-events/arch/x86/emeraldrapids/cache.json +2 -26
index 21d5d96b8a6d..3b0581151d63 100644
@@ -92,11 +92,11 @@
         "UMask": "0x2"
     },
     {
-        "BriefDescription": "Non-modified cache lines that are silently dropped by L2 cache when triggered by an L2 cache fill.",
+        "BriefDescription": "Non-modified cache lines that are silently dropped by L2 cache.",
         "Counter": "0,1,2,3",
         "EventCode": "0x26",
         "EventName": "L2_LINES_OUT.SILENT",
-        "PublicDescription": "Counts the number of lines that are silently dropped by L2 cache when triggered by an L2 cache fill. These lines are typically in Shared or Exclusive state. A non-threaded event.",
+        "PublicDescription": "Counts the number of lines that are silently dropped by L2 cache. These lines are typically in Shared or Exclusive state. A non-threaded event.",
         "SampleAfterValue": "200003",
         "UMask": "0x1"
     },
@@ -311,7 +311,6 @@
         "Data_LA": "1",
         "EventCode": "0xd0",
         "EventName": "MEM_INST_RETIRED.ALL_LOADS",
-        "PEBS": "1",
         "PublicDescription": "Counts all retired load instructions. This event accounts for SW prefetch instructions of PREFETCHNTA or PREFETCHT0/1/2 or PREFETCHW.",
         "SampleAfterValue": "1000003",
         "UMask": "0x81"
@@ -322,7 +321,6 @@
         "Data_LA": "1",
         "EventCode": "0xd0",
         "EventName": "MEM_INST_RETIRED.ALL_STORES",
-        "PEBS": "1",
         "PublicDescription": "Counts all retired store instructions.",
         "SampleAfterValue": "1000003",
         "UMask": "0x82"
@@ -333,7 +331,6 @@
         "Data_LA": "1",
         "EventCode": "0xd0",
         "EventName": "MEM_INST_RETIRED.ANY",
-        "PEBS": "1",
         "PublicDescription": "Counts all retired memory instructions - loads and stores.",
         "SampleAfterValue": "1000003",
         "UMask": "0x83"
@@ -344,7 +341,6 @@
         "Data_LA": "1",
         "EventCode": "0xd0",
         "EventName": "MEM_INST_RETIRED.LOCK_LOADS",
-        "PEBS": "1",
         "PublicDescription": "Counts retired load instructions with locked access.",
         "SampleAfterValue": "100007",
         "UMask": "0x21"
@@ -355,7 +351,6 @@
         "Data_LA": "1",
         "EventCode": "0xd0",
         "EventName": "MEM_INST_RETIRED.SPLIT_LOADS",
-        "PEBS": "1",
         "PublicDescription": "Counts retired load instructions that split across a cacheline boundary.",
         "SampleAfterValue": "100003",
         "UMask": "0x41"
@@ -366,7 +361,6 @@
         "Data_LA": "1",
         "EventCode": "0xd0",
         "EventName": "MEM_INST_RETIRED.SPLIT_STORES",
-        "PEBS": "1",
         "PublicDescription": "Counts retired store instructions that split across a cacheline boundary.",
         "SampleAfterValue": "100003",
         "UMask": "0x42"
@@ -377,7 +371,6 @@
         "Data_LA": "1",
         "EventCode": "0xd0",
         "EventName": "MEM_INST_RETIRED.STLB_MISS_LOADS",
-        "PEBS": "1",
         "PublicDescription": "Number of retired load instructions that (start a) miss in the 2nd-level TLB (STLB).",
         "SampleAfterValue": "100003",
         "UMask": "0x11"
@@ -388,7 +381,6 @@
         "Data_LA": "1",
         "EventCode": "0xd0",
         "EventName": "MEM_INST_RETIRED.STLB_MISS_STORES",
-        "PEBS": "1",
         "PublicDescription": "Number of retired store instructions that (start a) miss in the 2nd-level TLB (STLB).",
         "SampleAfterValue": "100003",
         "UMask": "0x12"
@@ -408,7 +400,6 @@
         "Data_LA": "1",
         "EventCode": "0xd2",
         "EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD",
-        "PEBS": "1",
         "PublicDescription": "Counts retired load instructions whose data sources were HitM responses from shared L3.",
         "SampleAfterValue": "20011",
         "UMask": "0x4"
@@ -419,7 +410,6 @@
         "Data_LA": "1",
         "EventCode": "0xd2",
         "EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS",
-        "PEBS": "1",
         "PublicDescription": "Counts the retired load instructions whose data sources were L3 hit and cross-core snoop missed in on-pkg core cache.",
         "SampleAfterValue": "20011",
         "UMask": "0x1"
@@ -430,7 +420,6 @@
         "Data_LA": "1",
         "EventCode": "0xd2",
         "EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_NONE",
-        "PEBS": "1",
         "PublicDescription": "Counts retired load instructions whose data sources were hits in L3 without snoops required.",
         "SampleAfterValue": "100003",
         "UMask": "0x8"
@@ -441,7 +430,6 @@
         "Data_LA": "1",
         "EventCode": "0xd2",
         "EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_NO_FWD",
-        "PEBS": "1",
         "PublicDescription": "Counts retired load instructions whose data sources were L3 and cross-core snoop hits in on-pkg core cache.",
         "SampleAfterValue": "20011",
         "UMask": "0x2"
@@ -452,7 +440,6 @@
         "Data_LA": "1",
         "EventCode": "0xd3",
         "EventName": "MEM_LOAD_L3_MISS_RETIRED.LOCAL_DRAM",
-        "PEBS": "1",
         "PublicDescription": "Retired load instructions which data sources missed L3 but serviced from local DRAM.",
         "SampleAfterValue": "100007",
         "UMask": "0x1"
@@ -463,7 +450,6 @@
         "Data_LA": "1",
         "EventCode": "0xd3",
         "EventName": "MEM_LOAD_L3_MISS_RETIRED.REMOTE_DRAM",
-        "PEBS": "1",
         "SampleAfterValue": "1000003",
         "UMask": "0x2"
     },
@@ -473,7 +459,6 @@
         "Data_LA": "1",
         "EventCode": "0xd3",
         "EventName": "MEM_LOAD_L3_MISS_RETIRED.REMOTE_FWD",
-        "PEBS": "1",
         "PublicDescription": "Retired load instructions whose data sources was forwarded from a remote cache.",
         "SampleAfterValue": "100007",
         "UMask": "0x8"
@@ -484,7 +469,6 @@
         "Data_LA": "1",
         "EventCode": "0xd3",
         "EventName": "MEM_LOAD_L3_MISS_RETIRED.REMOTE_HITM",
-        "PEBS": "1",
         "SampleAfterValue": "1000003",
         "UMask": "0x4"
     },
@@ -494,7 +478,6 @@
         "Data_LA": "1",
         "EventCode": "0xd4",
         "EventName": "MEM_LOAD_MISC_RETIRED.UC",
-        "PEBS": "1",
         "PublicDescription": "Retired instructions with at least one load to uncacheable memory-type, or at least one cache-line split locked access (Bus Lock).",
         "SampleAfterValue": "100007",
         "UMask": "0x4"
@@ -505,7 +488,6 @@
         "Data_LA": "1",
         "EventCode": "0xd1",
         "EventName": "MEM_LOAD_RETIRED.FB_HIT",
-        "PEBS": "1",
         "PublicDescription": "Counts retired load instructions with at least one uop was load missed in L1 but hit FB (Fill Buffers) due to preceding miss to the same cache line with data not ready.",
         "SampleAfterValue": "100007",
         "UMask": "0x40"
@@ -516,7 +498,6 @@
         "Data_LA": "1",
         "EventCode": "0xd1",
         "EventName": "MEM_LOAD_RETIRED.L1_HIT",
-        "PEBS": "1",
         "PublicDescription": "Counts retired load instructions with at least one uop that hit in the L1 data cache. This event includes all SW prefetches and lock instructions regardless of the data source.",
         "SampleAfterValue": "1000003",
         "UMask": "0x1"
@@ -527,7 +508,6 @@
         "Data_LA": "1",
         "EventCode": "0xd1",
         "EventName": "MEM_LOAD_RETIRED.L1_MISS",
-        "PEBS": "1",
         "PublicDescription": "Counts retired load instructions with at least one uop that missed in the L1 cache.",
         "SampleAfterValue": "200003",
         "UMask": "0x8"
@@ -538,7 +518,6 @@
         "Data_LA": "1",
         "EventCode": "0xd1",
         "EventName": "MEM_LOAD_RETIRED.L2_HIT",
-        "PEBS": "1",
         "PublicDescription": "Counts retired load instructions with L2 cache hits as data sources.",
         "SampleAfterValue": "200003",
         "UMask": "0x2"
@@ -549,7 +528,6 @@
         "Data_LA": "1",
         "EventCode": "0xd1",
         "EventName": "MEM_LOAD_RETIRED.L2_MISS",
-        "PEBS": "1",
         "PublicDescription": "Counts retired load instructions missed L2 cache as data sources.",
         "SampleAfterValue": "100021",
         "UMask": "0x10"
@@ -560,7 +538,6 @@
         "Data_LA": "1",
         "EventCode": "0xd1",
         "EventName": "MEM_LOAD_RETIRED.L3_HIT",
-        "PEBS": "1",
         "PublicDescription": "Counts retired load instructions with at least one uop that hit in the L3 cache.",
         "SampleAfterValue": "100021",
         "UMask": "0x4"
@@ -571,7 +548,6 @@
         "Data_LA": "1",
         "EventCode": "0xd1",
         "EventName": "MEM_LOAD_RETIRED.L3_MISS",
-        "PEBS": "1",
         "PublicDescription": "Counts retired load instructions with at least one uop that missed in the L3 cache.",
         "SampleAfterValue": "50021",
         "UMask": "0x20"
tools/perf/pmu-events/arch/x86/emeraldrapids/emr-metrics.json +520 -456

1,999 lines not on this page · raw message

tools/perf/pmu-events/arch/x86/emeraldrapids/frontend.json +0 -19
index f6e3e40a3b20..bf68493d4509 100644
@@ -41,7 +41,6 @@
         "EventName": "FRONTEND_RETIRED.ANY_DSB_MISS",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x1",
-        "PEBS": "1",
         "PublicDescription": "Counts retired Instructions that experienced DSB (Decode stream buffer i.e. the decoded instruction-cache) miss.",
         "SampleAfterValue": "100007",
         "UMask": "0x1"
@@ -53,7 +52,6 @@
         "EventName": "FRONTEND_RETIRED.DSB_MISS",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x11",
-        "PEBS": "1",
         "PublicDescription": "Number of retired Instructions that experienced a critical DSB (Decode stream buffer i.e. the decoded instruction-cache) miss. Critical means stalls were exposed to the back-end as a result of the DSB miss.",
         "SampleAfterValue": "100007",
         "UMask": "0x1"
@@ -65,7 +63,6 @@
         "EventName": "FRONTEND_RETIRED.ITLB_MISS",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x14",
-        "PEBS": "1",
         "PublicDescription": "Counts retired Instructions that experienced iTLB (Instruction TLB) true miss.",
         "SampleAfterValue": "100007",
         "UMask": "0x1"
@@ -77,7 +74,6 @@
         "EventName": "FRONTEND_RETIRED.L1I_MISS",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x12",
-        "PEBS": "1",
         "PublicDescription": "Counts retired Instructions who experienced Instruction L1 Cache true miss.",
         "SampleAfterValue": "100007",
         "UMask": "0x1"
@@ -89,7 +85,6 @@
         "EventName": "FRONTEND_RETIRED.L2_MISS",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x13",
-        "PEBS": "1",
         "PublicDescription": "Counts retired Instructions who experienced Instruction L2 Cache true miss.",
         "SampleAfterValue": "100007",
         "UMask": "0x1"
@@ -101,7 +96,6 @@
         "EventName": "FRONTEND_RETIRED.LATENCY_GE_1",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x600106",
-        "PEBS": "1",
         "PublicDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of at least 1 cycle which was not interrupted by a back-end stall.",
         "SampleAfterValue": "100007",
         "UMask": "0x1"
@@ -113,7 +107,6 @@
         "EventName": "FRONTEND_RETIRED.LATENCY_GE_128",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x608006",
-        "PEBS": "1",
         "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 128 cycles which was not interrupted by a back-end stall.",
         "SampleAfterValue": "100007",
         "UMask": "0x1"
@@ -125,7 +118,6 @@
         "EventName": "FRONTEND_RETIRED.LATENCY_GE_16",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x601006",
-        "PEBS": "1",
         "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 16 cycles. During this period the front-end delivered no uops.",
         "SampleAfterValue": "100007",
         "UMask": "0x1"
@@ -137,7 +129,6 @@
         "EventName": "FRONTEND_RETIRED.LATENCY_GE_2",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x600206",
-        "PEBS": "1",
         "PublicDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of at least 2 cycles which was not interrupted by a back-end stall.",
         "SampleAfterValue": "100007",
         "UMask": "0x1"
@@ -149,7 +140,6 @@
         "EventName": "FRONTEND_RETIRED.LATENCY_GE_256",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x610006",
-        "PEBS": "1",
         "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 256 cycles which was not interrupted by a back-end stall.",
         "SampleAfterValue": "100007",
         "UMask": "0x1"
@@ -161,7 +151,6 @@
         "EventName": "FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x100206",
-        "PEBS": "1",
         "PublicDescription": "Counts retired instructions that are delivered to the back-end after the front-end had at least 1 bubble-slot for a period of 2 cycles. A bubble-slot is an empty issue-pipeline slot while there was no RAT stall.",
         "SampleAfterValue": "100007",
         "UMask": "0x1"
@@ -173,7 +162,6 @@
         "EventName": "FRONTEND_RETIRED.LATENCY_GE_32",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x602006",
-        "PEBS": "1",
         "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 32 cycles. During this period the front-end delivered no uops.",
         "SampleAfterValue": "100007",
         "UMask": "0x1"
@@ -185,7 +173,6 @@
         "EventName": "FRONTEND_RETIRED.LATENCY_GE_4",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x600406",
-        "PEBS": "1",
         "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 4 cycles which was not interrupted by a back-end stall.",
         "SampleAfterValue": "100007",
         "UMask": "0x1"
@@ -197,7 +184,6 @@
         "EventName": "FRONTEND_RETIRED.LATENCY_GE_512",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x620006",
-        "PEBS": "1",
         "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 512 cycles which was not interrupted by a back-end stall.",
         "SampleAfterValue": "100007",
         "UMask": "0x1"
@@ -209,7 +195,6 @@
         "EventName": "FRONTEND_RETIRED.LATENCY_GE_64",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x604006",
-        "PEBS": "1",
         "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 64 cycles which was not interrupted by a back-end stall.",
         "SampleAfterValue": "100007",
         "UMask": "0x1"
@@ -221,7 +206,6 @@
         "EventName": "FRONTEND_RETIRED.LATENCY_GE_8",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x600806",
-        "PEBS": "1",
         "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 8 cycles. During this period the front-end delivered no uops.",
         "SampleAfterValue": "100007",
         "UMask": "0x1"
@@ -233,7 +217,6 @@
         "EventName": "FRONTEND_RETIRED.MS_FLOWS",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x8",
-        "PEBS": "1",
         "SampleAfterValue": "100007",
         "UMask": "0x1"
     },
@@ -244,7 +227,6 @@
         "EventName": "FRONTEND_RETIRED.STLB_MISS",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x15",
-        "PEBS": "1",
         "PublicDescription": "Counts retired Instructions that experienced STLB (2nd level TLB) true miss.",
         "SampleAfterValue": "100007",
         "UMask": "0x1"
@@ -256,7 +238,6 @@
         "EventName": "FRONTEND_RETIRED.UNKNOWN_BRANCH",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x17",
-        "PEBS": "1",
         "SampleAfterValue": "100007",
         "UMask": "0x1"
     },
tools/perf/pmu-events/arch/x86/emeraldrapids/memory.json +2 -13
index 2ea19539291b..41d4120d4dae 100644
@@ -63,7 +63,6 @@
         "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_1024",
         "MSRIndex": "0x3F6",
         "MSRValue": "0x400",
-        "PEBS": "2",
         "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 1024 cycles.  Reported latency may be longer than just the memory latency.",
         "SampleAfterValue": "53",
         "UMask": "0x1"
@@ -76,7 +75,6 @@
         "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_128",
         "MSRIndex": "0x3F6",
         "MSRValue": "0x80",
-        "PEBS": "2",
         "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 128 cycles.  Reported latency may be longer than just the memory latency.",
         "SampleAfterValue": "1009",
         "UMask": "0x1"
@@ -89,7 +87,6 @@
         "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_16",
         "MSRIndex": "0x3F6",
         "MSRValue": "0x10",
-        "PEBS": "2",
         "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 16 cycles.  Reported latency may be longer than just the memory latency.",
         "SampleAfterValue": "20011",
         "UMask": "0x1"
@@ -102,7 +99,6 @@
         "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_256",
         "MSRIndex": "0x3F6",
         "MSRValue": "0x100",
-        "PEBS": "2",
         "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 256 cycles.  Reported latency may be longer than just the memory latency.",
         "SampleAfterValue": "503",
         "UMask": "0x1"
@@ -115,7 +111,6 @@
         "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_32",
         "MSRIndex": "0x3F6",
         "MSRValue": "0x20",
-        "PEBS": "2",
         "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 32 cycles.  Reported latency may be longer than just the memory latency.",
         "SampleAfterValue": "100007",
         "UMask": "0x1"
@@ -128,7 +123,6 @@
         "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_4",
         "MSRIndex": "0x3F6",
         "MSRValue": "0x4",
-        "PEBS": "2",
         "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 4 cycles.  Reported latency may be longer than just the memory latency.",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
@@ -141,7 +135,6 @@
         "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_512",
         "MSRIndex": "0x3F6",
         "MSRValue": "0x200",
-        "PEBS": "2",
         "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 512 cycles.  Reported latency may be longer than just the memory latency.",
         "SampleAfterValue": "101",
         "UMask": "0x1"
@@ -154,7 +147,6 @@
         "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_64",
         "MSRIndex": "0x3F6",
         "MSRValue": "0x40",
-        "PEBS": "2",
         "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 64 cycles.  Reported latency may be longer than just the memory latency.",
         "SampleAfterValue": "2003",
         "UMask": "0x1"
@@ -167,7 +159,6 @@
         "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_8",
         "MSRIndex": "0x3F6",
         "MSRValue": "0x8",
-        "PEBS": "2",
         "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 8 cycles.  Reported latency may be longer than just the memory latency.",
         "SampleAfterValue": "50021",
         "UMask": "0x1"
@@ -178,7 +169,6 @@
         "Data_LA": "1",
         "EventCode": "0xcd",
         "EventName": "MEM_TRANS_RETIRED.STORE_SAMPLE",
-        "PEBS": "2",
         "PublicDescription": "Counts Retired memory accesses with at least 1 store operation. This PEBS event is the precisely-distributed (PDist) trigger covering all stores uops for sampling by the PEBS Store Latency Facility. The facility is described in Intel SDM Volume 3 section 19.9.8",
         "SampleAfterValue": "1000003",
         "UMask": "0x2"
@@ -305,17 +295,16 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc9",
         "EventName": "RTM_RETIRED.ABORTED",
-        "PEBS": "1",
         "PublicDescription": "Counts the number of times RTM abort was triggered.",
         "SampleAfterValue": "100003",
         "UMask": "0x4"
     },
     {
-        "BriefDescription": "Number of times an RTM execution aborted due to none of the previous 4 categories (e.g. interrupt)",
+        "BriefDescription": "Number of times an RTM execution aborted due to none of the previous 3 categories (e.g. interrupt)",
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc9",
         "EventName": "RTM_RETIRED.ABORTED_EVENTS",
-        "PublicDescription": "Counts the number of times an RTM execution aborted due to none of the previous 4 categories (e.g. interrupt).",
+        "PublicDescription": "Counts the number of times an RTM execution aborted due to none of the previous 3 categories (e.g. interrupt).",
         "SampleAfterValue": "100003",
         "UMask": "0x80"
     },
tools/perf/pmu-events/arch/x86/emeraldrapids/metricgroups.json +9 -1
index e1de6c2675c4..9129fb7b7ce4 100644
@@ -40,6 +40,7 @@
     "IoBW": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
     "L2Evicts": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
     "LSD": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
+    "LockCont": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
     "MachineClears": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
     "Machine_Clears": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
     "Mem": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
@@ -86,7 +87,9 @@
     "tma_bad_speculation_group": "Metrics contributing to tma_bad_speculation category",
     "tma_branch_mispredicts_group": "Metrics contributing to tma_branch_mispredicts category",
     "tma_branch_resteers_group": "Metrics contributing to tma_branch_resteers category",
+    "tma_code_stlb_miss_group": "Metrics contributing to tma_code_stlb_miss category",
     "tma_core_bound_group": "Metrics contributing to tma_core_bound category",
+    "tma_divider_group": "Metrics contributing to tma_divider category",
     "tma_dram_bound_group": "Metrics contributing to tma_dram_bound category",
     "tma_dtlb_load_group": "Metrics contributing to tma_dtlb_load category",
     "tma_dtlb_store_group": "Metrics contributing to tma_dtlb_store category",
@@ -96,6 +99,7 @@
     "tma_fp_vector_group": "Metrics contributing to tma_fp_vector category",
     "tma_frontend_bound_group": "Metrics contributing to tma_frontend_bound category",
     "tma_heavy_operations_group": "Metrics contributing to tma_heavy_operations category",
+    "tma_icache_misses_group": "Metrics contributing to tma_icache_misses category",
     "tma_int_operations_group": "Metrics contributing to tma_int_operations category",
     "tma_issue2P": "Metrics related by the issue $issue2P",
     "tma_issueBM": "Metrics related by the issue $issueBM",
@@ -116,10 +120,13 @@
     "tma_issueSpSt": "Metrics related by the issue $issueSpSt",
     "tma_issueSyncxn": "Metrics related by the issue $issueSyncxn",
     "tma_issueTLB": "Metrics related by the issue $issueTLB",
+    "tma_itlb_misses_group": "Metrics contributing to tma_itlb_misses category",
     "tma_l1_bound_group": "Metrics contributing to tma_l1_bound category",
+    "tma_l2_bound_group": "Metrics contributing to tma_l2_bound category",
     "tma_l3_bound_group": "Metrics contributing to tma_l3_bound category",
     "tma_light_operations_group": "Metrics contributing to tma_light_operations category",
     "tma_load_op_utilization_group": "Metrics contributing to tma_load_op_utilization category",
+    "tma_load_stlb_miss_group": "Metrics contributing to tma_load_stlb_miss category",
     "tma_machine_clears_group": "Metrics contributing to tma_machine_clears category",
     "tma_mem_bandwidth_group": "Metrics contributing to tma_mem_bandwidth category",
     "tma_mem_latency_group": "Metrics contributing to tma_mem_latency category",
@@ -133,5 +140,6 @@
     "tma_retiring_group": "Metrics contributing to tma_retiring category",
     "tma_serializing_operation_group": "Metrics contributing to tma_serializing_operation category",
     "tma_store_bound_group": "Metrics contributing to tma_store_bound category",
-    "tma_store_op_utilization_group": "Metrics contributing to tma_store_op_utilization category"
+    "tma_store_op_utilization_group": "Metrics contributing to tma_store_op_utilization category",
+    "tma_store_stlb_miss_group": "Metrics contributing to tma_store_stlb_miss category"
 }
tools/perf/pmu-events/arch/x86/emeraldrapids/pipeline.json +0 -23
index 5d5811f26151..50cacfbbc7cf 100644
@@ -62,7 +62,6 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc4",
         "EventName": "BR_INST_RETIRED.ALL_BRANCHES",
-        "PEBS": "1",
         "PublicDescription": "Counts all branch instructions retired.",
         "SampleAfterValue": "400009"
     },
@@ -71,7 +70,6 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc4",
         "EventName": "BR_INST_RETIRED.COND",
-        "PEBS": "1",
         "PublicDescription": "Counts conditional branch instructions retired.",
         "SampleAfterValue": "400009",
         "UMask": "0x11"
@@ -81,7 +79,6 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc4",
         "EventName": "BR_INST_RETIRED.COND_NTAKEN",
-        "PEBS": "1",
         "PublicDescription": "Counts not taken branch instructions retired.",
         "SampleAfterValue": "400009",
         "UMask": "0x10"
@@ -91,7 +88,6 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc4",
         "EventName": "BR_INST_RETIRED.COND_TAKEN",
-        "PEBS": "1",
         "PublicDescription": "Counts taken conditional branch instructions retired.",
         "SampleAfterValue": "400009",
         "UMask": "0x1"
@@ -101,7 +97,6 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc4",
         "EventName": "BR_INST_RETIRED.FAR_BRANCH",
-        "PEBS": "1",
         "PublicDescription": "Counts far branch instructions retired.",
         "SampleAfterValue": "100007",
         "UMask": "0x40"
@@ -111,7 +106,6 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc4",
         "EventName": "BR_INST_RETIRED.INDIRECT",
-        "PEBS": "1",
         "PublicDescription": "Counts near indirect branch instructions retired excluding returns. TSX abort is an indirect branch.",
         "SampleAfterValue": "100003",
         "UMask": "0x80"
@@ -121,7 +115,6 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc4",
         "EventName": "BR_INST_RETIRED.NEAR_CALL",
-        "PEBS": "1",
         "PublicDescription": "Counts both direct and indirect near call instructions retired.",
         "SampleAfterValue": "100007",
         "UMask": "0x2"
@@ -131,7 +124,6 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc4",
         "EventName": "BR_INST_RETIRED.NEAR_RETURN",
-        "PEBS": "1",
         "PublicDescription": "Counts return instructions retired.",
         "SampleAfterValue": "100007",
         "UMask": "0x8"
@@ -141,7 +133,6 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc4",
         "EventName": "BR_INST_RETIRED.NEAR_TAKEN",
-        "PEBS": "1",
         "PublicDescription": "Counts taken branch instructions retired.",
         "SampleAfterValue": "400009",
         "UMask": "0x20"
@@ -151,7 +142,6 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc5",
         "EventName": "BR_MISP_RETIRED.ALL_BRANCHES",
-        "PEBS": "1",
         "PublicDescription": "Counts all the retired branch instructions that were mispredicted by the processor. A branch misprediction occurs when the processor incorrectly predicts the destination of the branch.  When the misprediction is discovered at execution, all the instructions executed in the wrong (speculative) path must be discarded, and the processor must start fetching from the correct path.",
         "SampleAfterValue": "400009"
     },
@@ -160,7 +150,6 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc5",
         "EventName": "BR_MISP_RETIRED.COND",
-        "PEBS": "1",
         "PublicDescription": "Counts mispredicted conditional branch instructions retired.",
         "SampleAfterValue": "400009",
         "UMask": "0x11"
@@ -170,7 +159,6 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc5",
         "EventName": "BR_MISP_RETIRED.COND_NTAKEN",
-        "PEBS": "1",
         "PublicDescription": "Counts the number of conditional branch instructions retired that were mispredicted and the branch direction was not taken.",
         "SampleAfterValue": "400009",
         "UMask": "0x10"
@@ -180,7 +168,6 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc5",
         "EventName": "BR_MISP_RETIRED.COND_TAKEN",
-        "PEBS": "1",
         "PublicDescription": "Counts taken conditional mispredicted branch instructions retired.",
         "SampleAfterValue": "400009",
         "UMask": "0x1"
@@ -190,7 +177,6 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc5",
         "EventName": "BR_MISP_RETIRED.INDIRECT",
-        "PEBS": "1",
         "PublicDescription": "Counts miss-predicted near indirect branch instructions retired excluding returns. TSX abort is an indirect branch.",
         "SampleAfterValue": "100003",
         "UMask": "0x80"
@@ -200,7 +186,6 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc5",
         "EventName": "BR_MISP_RETIRED.INDIRECT_CALL",
-        "PEBS": "1",
         "PublicDescription": "Counts retired mispredicted indirect (near taken) CALL instructions, including both register and memory indirect.",
         "SampleAfterValue": "400009",
         "UMask": "0x2"
@@ -210,7 +195,6 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc5",
         "EventName": "BR_MISP_RETIRED.NEAR_TAKEN",
-        "PEBS": "1",
         "PublicDescription": "Counts number of near branch instructions retired that were mispredicted and taken.",
         "SampleAfterValue": "400009",
         "UMask": "0x20"
@@ -220,7 +204,6 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc5",
         "EventName": "BR_MISP_RETIRED.RET",
-        "PEBS": "1",
         "PublicDescription": "This is a non-precise version (that is, does not use PEBS) of the event that counts mispredicted return instructions retired.",
         "SampleAfterValue": "100007",
         "UMask": "0x8"
@@ -469,7 +452,6 @@
         "BriefDescription": "Number of instructions retired. Fixed Counter - architectural event",
         "Counter": "Fixed counter 0",
         "EventName": "INST_RETIRED.ANY",
-        "PEBS": "1",
         "PublicDescription": "Counts the number of X86 instructions retired - an Architectural PerfMon event. Counting continues during hardware interrupts, traps, and inside interrupt handlers. Notes: INST_RETIRED.ANY is counted by a designated fixed counter freeing up programmable counters to count other events. INST_RETIRED.ANY_P is counted by a programmable counter.",
         "SampleAfterValue": "2000003",
         "UMask": "0x1"
@@ -479,7 +461,6 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc0",
         "EventName": "INST_RETIRED.ANY_P",
-        "PEBS": "1",
         "PublicDescription": "Counts the number of X86 instructions retired - an Architectural PerfMon event. Counting continues during hardware interrupts, traps, and inside interrupt handlers. Notes: INST_RETIRED.ANY is counted by a designated fixed counter freeing up programmable counters to count other events. INST_RETIRED.ANY_P is counted by a programmable counter.",
         "SampleAfterValue": "2000003"
     },
@@ -488,7 +469,6 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc0",
         "EventName": "INST_RETIRED.MACRO_FUSED",
-        "PEBS": "1",
         "SampleAfterValue": "2000003",
         "UMask": "0x10"
     },
@@ -497,7 +477,6 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc0",
         "EventName": "INST_RETIRED.NOP",
-        "PEBS": "1",
         "PublicDescription": "Counts all retired NOP or ENDBR32/64 instructions",
         "SampleAfterValue": "2000003",
         "UMask": "0x2"
@@ -506,7 +485,6 @@
         "BriefDescription": "Precise instruction retired with PEBS precise-distribution",
         "Counter": "Fixed counter 0",
         "EventName": "INST_RETIRED.PREC_DIST",
-        "PEBS": "1",
         "PublicDescription": "A version of INST_RETIRED that allows for a precise distribution of samples across instructions retired. It utilizes the Precise Distribution of Instructions Retired (PDIR++) feature to fix bias in how retired instructions get sampled. Use on Fixed Counter 0.",
         "SampleAfterValue": "2000003",
         "UMask": "0x1"
@@ -516,7 +494,6 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc0",
         "EventName": "INST_RETIRED.REP_ITERATION",
-        "PEBS": "1",
         "PublicDescription": "Number of iterations of Repeat (REP) string retired instructions such as MOVS, CMPS, and SCAS. Each has a byte, word, and doubleword version and string instructions can be repeated using a repetition prefix, REP, that allows their architectural execution to be repeated a number of times as specified by the RCX register. Note the number of iterations is implementation-dependent.",
         "SampleAfterValue": "2000003",
         "UMask": "0x8"
tools/perf/pmu-events/arch/x86/emeraldrapids/uncore-io.json +68 -150

394 lines not on this page · raw message

tools/perf/pmu-events/arch/x86/mapfile.csv +1 -1
index 68c33fa7328a..7260a2ac133a 100644

Lines of this file are not shown. View the raw message.

The rest of this diff is not shown. View the raw message.

Signature · 1 line
2.48.1.502.g6dc24dfdaf-goog

Part of the diff is not shown here. View the raw message.

author reviewer
#10 lore raw

PATCH v8 10/24 perf vendor events: Update GrandRidge events/metrics

In reply to Ian Rogers

Update events from v1.03 to v1.05.
Update TMA metrics from 4.8 to 5.02.

Bring in the event updates v1.05:
https://github.com/intel/perfmon/commit/3b2e3528fbfb5576f443607ac9d772de88aed72c
https://github.com/intel/perfmon/commit/9bc1815536ff1f6fe73693a19a410b6a711740c2

The TMA 5.02 update is from (with subsequent fixes):
https://github.com/intel/perfmon/commit/1d72913b2d938781fb28f3cc3507aaec5c22d782

Update uncore IIO events umask with the change:
https://github.com/intel/perfmon/commit/d78e8a166537c9ceab4f2e901dc96c53667a2174
which should address an issue originally raised by Michael Petlan:

---
 .../arch/x86/grandridge/grr-metrics.json      | 284 ++++++------------
 .../arch/x86/grandridge/pipeline.json         |   3 +-
 .../arch/x86/grandridge/uncore-cache.json     |   4 +-
 .../x86/grandridge/uncore-interconnect.json   |  60 ++++
 .../arch/x86/grandridge/uncore-io.json        | 214 ++++++-------
 .../arch/x86/grandridge/uncore-memory.json    |   2 +-
 tools/perf/pmu-events/arch/x86/mapfile.csv    |   2 +-
 7 files changed, 260 insertions(+), 309 deletions(-)
tools/perf/pmu-events/arch/x86/grandridge/grr-metrics.json +88 -196
index 07e542297e93..2f9959c61718 100644
@@ -1,4 +1,11 @@
 [
+    {
+        "BriefDescription": "C10 residency percent per package",
+        "MetricExpr": "cstate_pkg@c10\\-residency@ / TSC",
+        "MetricGroup": "Power",
+        "MetricName": "C10_Pkg_Residency",
+        "ScaleUnit": "100%"
+    },
     {
         "BriefDescription": "C1 residency percent per core",
         "MetricExpr": "cstate_core@c1\\-residency@ / TSC",
@@ -7,17 +14,24 @@
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "C6 residency percent per core",
-        "MetricExpr": "cstate_core@c6\\-residency@ / TSC",
+        "BriefDescription": "C2 residency percent per package",
+        "MetricExpr": "cstate_pkg@c2\\-residency@ / TSC",
         "MetricGroup": "Power",
-        "MetricName": "C6_Core_Residency",
+        "MetricName": "C2_Pkg_Residency",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "C6 residency percent per module",
-        "MetricExpr": "cstate_module@c6\\-residency@ / TSC",
+        "BriefDescription": "C3 residency percent per package",
+        "MetricExpr": "cstate_pkg@c3\\-residency@ / TSC",
         "MetricGroup": "Power",
-        "MetricName": "C6_Module_Residency",
+        "MetricName": "C3_Pkg_Residency",
+        "ScaleUnit": "100%"
+    },
+    {
+        "BriefDescription": "C6 residency percent per core",
+        "MetricExpr": "cstate_core@c6\\-residency@ / TSC",
+        "MetricGroup": "Power",
+        "MetricName": "C6_Core_Residency",
         "ScaleUnit": "100%"
     },
     {
@@ -28,7 +42,21 @@
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "Cycles per instruction retired; indicating how much time each executed instruction took; in units of cycles.",
+        "BriefDescription": "C7 residency percent per core",
+        "MetricExpr": "cstate_core@c7\\-residency@ / TSC",
+        "MetricGroup": "Power",
+        "MetricName": "C7_Core_Residency",
+        "ScaleUnit": "100%"
+    },
+    {
+        "BriefDescription": "C8 residency percent per package",
+        "MetricExpr": "cstate_pkg@c8\\-residency@ / TSC",
+        "MetricGroup": "Power",
+        "MetricName": "C8_Pkg_Residency",
+        "ScaleUnit": "100%"
+    },
+    {
+        "BriefDescription": "Cycles per instruction retired; indicating how much time each executed instruction took; in units of cycles",
         "MetricExpr": "CPU_CLK_UNHALTED.THREAD / INST_RETIRED.ANY",
         "MetricName": "cpi",
         "ScaleUnit": "1per_instr"
@@ -49,31 +77,31 @@
         "BriefDescription": "Ratio of number of completed page walks (for 2 megabyte page sizes) caused by demand data loads to the total number of completed instructions",
         "MetricExpr": "DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M / INST_RETIRED.ANY",
         "MetricName": "dtlb_2nd_level_2mb_large_page_load_mpi",
-        "PublicDescription": "Ratio of number of completed page walks (for 2 megabyte page sizes) caused by demand data loads to the total number of completed instructions. This implies it missed in the Data Translation Lookaside Buffer (DTLB) and further levels of TLB.",
+        "PublicDescription": "Ratio of number of completed page walks (for 2 megabyte page sizes) caused by demand data loads to the total number of completed instructions. This implies it missed in the Data Translation Lookaside Buffer (DTLB) and further levels of TLB",
         "ScaleUnit": "1per_instr"
     },
     {
         "BriefDescription": "Ratio of number of completed page walks (for all page sizes) caused by demand data loads to the total number of completed instructions",
         "MetricExpr": "DTLB_LOAD_MISSES.WALK_COMPLETED / INST_RETIRED.ANY",
         "MetricName": "dtlb_2nd_level_load_mpi",
-        "PublicDescription": "Ratio of number of completed page walks (for all page sizes) caused by demand data loads to the total number of completed instructions. This implies it missed in the DTLB and further levels of TLB.",
+        "PublicDescription": "Ratio of number of completed page walks (for all page sizes) caused by demand data loads to the total number of completed instructions. This implies it missed in the DTLB and further levels of TLB",
         "ScaleUnit": "1per_instr"
     },
     {
         "BriefDescription": "Ratio of number of completed page walks (for all page sizes) caused by demand data stores to the total number of completed instructions",
         "MetricExpr": "DTLB_STORE_MISSES.WALK_COMPLETED / INST_RETIRED.ANY",
         "MetricName": "dtlb_2nd_level_store_mpi",
-        "PublicDescription": "Ratio of number of completed page walks (for all page sizes) caused by demand data stores to the total number of completed instructions. This implies it missed in the DTLB and further levels of TLB.",
+        "PublicDescription": "Ratio of number of completed page walks (for all page sizes) caused by demand data stores to the total number of completed instructions. This implies it missed in the DTLB and further levels of TLB",
         "ScaleUnit": "1per_instr"
     },
     {
-        "BriefDescription": "Bandwidth of IO reads that are initiated by end device controllers that are requesting memory from the CPU.",
+        "BriefDescription": "Bandwidth of IO reads that are initiated by end device controllers that are requesting memory from the CPU",
         "MetricExpr": "UNC_CHA_TOR_INSERTS.IO_PCIRDCUR * 64 / 1e6 / duration_time",
         "MetricName": "io_bandwidth_read",
         "ScaleUnit": "1MB/s"
     },
     {
-        "BriefDescription": "Bandwidth of IO writes that are initiated by end device controllers that are writing memory to the CPU.",
+        "BriefDescription": "Bandwidth of IO writes that are initiated by end device controllers that are writing memory to the CPU",
         "MetricExpr": "(UNC_CHA_TOR_INSERTS.IO_ITOM + UNC_CHA_TOR_INSERTS.IO_ITOMCACHENEAR) * 64 / 1e6 / duration_time",
         "MetricName": "io_bandwidth_write",
         "ScaleUnit": "1MB/s"
@@ -82,14 +110,14 @@
         "BriefDescription": "Ratio of number of completed page walks (for 2 megabyte and 4 megabyte page sizes) caused by a code fetch to the total number of completed instructions",
         "MetricExpr": "ITLB_MISSES.WALK_COMPLETED_2M_4M / INST_RETIRED.ANY",
         "MetricName": "itlb_2nd_level_large_page_mpi",
-        "PublicDescription": "Ratio of number of completed page walks (for 2 megabyte and 4 megabyte page sizes) caused by a code fetch to the total number of completed instructions. This implies it missed in the Instruction Translation Lookaside Buffer (ITLB) and further levels of TLB.",
+        "PublicDescription": "Ratio of number of completed page walks (for 2 megabyte and 4 megabyte page sizes) caused by a code fetch to the total number of completed instructions. This implies it missed in the Instruction Translation Lookaside Buffer (ITLB) and further levels of TLB",
         "ScaleUnit": "1per_instr"
     },
     {
         "BriefDescription": "Ratio of number of completed page walks (for all page sizes) caused by a code fetch to the total number of completed instructions",
         "MetricExpr": "ITLB_MISSES.WALK_COMPLETED / INST_RETIRED.ANY",
         "MetricName": "itlb_2nd_level_mpi",
-        "PublicDescription": "Ratio of number of completed page walks (for all page sizes) caused by a code fetch to the total number of completed instructions. This implies it missed in the ITLB (Instruction TLB) and further levels of TLB.",
+        "PublicDescription": "Ratio of number of completed page walks (for all page sizes) caused by a code fetch to the total number of completed instructions. This implies it missed in the ITLB (Instruction TLB) and further levels of TLB",
         "ScaleUnit": "1per_instr"
     },
     {
@@ -188,17 +216,15 @@
     {
         "BriefDescription": "Counts the number of issue slots that were not consumed by the backend due to certain allocation restrictions",
         "MetricExpr": "tma_core_bound",
-        "MetricGroup": "TopdownL3;tma_L3_group;tma_core_bound_group",
+        "MetricGroup": "Slots;TopdownL3;tma_L3_group;tma_core_bound_group",
         "MetricName": "tma_allocation_restriction",
-        "MetricThreshold": "tma_allocation_restriction > 0.1 & (tma_core_bound > 0.1 & tma_backend_bound > 0.1)",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "Counts the total number of issue slots that were not consumed by the backend due to backend stalls",
         "MetricExpr": "TOPDOWN_BE_BOUND.ALL_P / (6 * CPU_CLK_UNHALTED.CORE)",
-        "MetricGroup": "TopdownL1;tma_L1_group",
+        "MetricGroup": "Slots;TopdownL1;tma_L1_group",
         "MetricName": "tma_backend_bound",
-        "MetricThreshold": "tma_backend_bound > 0.1",
         "MetricgroupNoGroup": "TopdownL1",
         "PublicDescription": "Counts the total number of issue slots that were not consumed by the backend due to backend stalls. Note that uops must be available for consumption in order for this event to count. If a uop is not available (IQ is empty), this event will not count",
         "ScaleUnit": "100%"
@@ -206,104 +232,92 @@
     {
         "BriefDescription": "Counts the total number of issue slots that were not consumed by the backend because allocation is stalled due to a mispredicted jump or a machine clear",
         "MetricExpr": "TOPDOWN_BAD_SPECULATION.ALL_P / (6 * CPU_CLK_UNHALTED.CORE)",
-        "MetricGroup": "TopdownL1;tma_L1_group",
+        "MetricGroup": "Slots;TopdownL1;tma_L1_group",
         "MetricName": "tma_bad_speculation",
-        "MetricThreshold": "tma_bad_speculation > 0.15",
         "MetricgroupNoGroup": "TopdownL1",
-        "PublicDescription": "Counts the total number of issue slots that were not consumed by the backend because allocation is stalled due to a mispredicted jump or a machine clear. Only issue slots wasted due to fast nukes such as memory ordering nukes are counted. Other nukes are not accounted for. Counts all issue slots blocked during this recovery window including relevant microcode flows and while uops are not yet available in the instruction queue (IQ). Also includes the issue slots that were consumed by the backend but were thrown away because they were younger than the mispredict or machine clear.",
+        "PublicDescription": "Counts the total number of issue slots that were not consumed by the backend because allocation is stalled due to a mispredicted jump or a machine clear. Only issue slots wasted due to fast nukes such as memory ordering nukes are counted. Other nukes are not accounted for. Counts all issue slots blocked during this recovery window including relevant microcode flows and while uops are not yet available in the instruction queue (IQ). Also includes the issue slots that were consumed by the backend but were thrown away because they were younger than the mispredict or machine clear",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to BACLEARS, which occurs when the Branch Target Buffer (BTB) prediction or lack thereof, was corrected by a later branch predictor in the frontend",
         "MetricExpr": "TOPDOWN_FE_BOUND.BRANCH_DETECT / (6 * CPU_CLK_UNHALTED.CORE)",
-        "MetricGroup": "TopdownL3;tma_L3_group;tma_ifetch_latency_group",
+        "MetricGroup": "Slots;TopdownL3;tma_L3_group;tma_ifetch_latency_group",
         "MetricName": "tma_branch_detect",
-        "MetricThreshold": "tma_branch_detect > 0.05 & (tma_ifetch_latency > 0.15 & tma_frontend_bound > 0.2)",
-        "PublicDescription": "Counts the number of issue slots that were not delivered by the frontend due to BACLEARS, which occurs when the Branch Target Buffer (BTB) prediction or lack thereof, was corrected by a later branch predictor in the frontend. Includes BACLEARS due to all branch types including conditional and unconditional jumps, returns, and indirect branches.",
+        "PublicDescription": "Counts the number of issue slots that were not delivered by the frontend due to BACLEARS, which occurs when the Branch Target Buffer (BTB) prediction or lack thereof, was corrected by a later branch predictor in the frontend. Includes BACLEARS due to all branch types including conditional and unconditional jumps, returns, and indirect branches",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "Counts the number of issue slots that were not consumed by the backend due to branch mispredicts",
         "MetricExpr": "TOPDOWN_BAD_SPECULATION.MISPREDICT / (6 * CPU_CLK_UNHALTED.CORE)",
-        "MetricGroup": "TopdownL2;tma_L2_group;tma_bad_speculation_group",
+        "MetricGroup": "Slots;TopdownL2;tma_L2_group;tma_bad_speculation_group",
         "MetricName": "tma_branch_mispredicts",
-        "MetricThreshold": "tma_branch_mispredicts > 0.05 & tma_bad_speculation > 0.15",
         "MetricgroupNoGroup": "TopdownL2",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to BTCLEARS, which occurs when the Branch Target Buffer (BTB) predicts a taken branch.",
+        "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to BTCLEARS, which occurs when the Branch Target Buffer (BTB) predicts a taken branch",
         "MetricExpr": "TOPDOWN_FE_BOUND.BRANCH_RESTEER / (6 * CPU_CLK_UNHALTED.CORE)",
-        "MetricGroup": "TopdownL3;tma_L3_group;tma_ifetch_latency_group",
+        "MetricGroup": "Slots;TopdownL3;tma_L3_group;tma_ifetch_latency_group",
         "MetricName": "tma_branch_resteer",
-        "MetricThreshold": "tma_branch_resteer > 0.05 & (tma_ifetch_latency > 0.15 & tma_frontend_bound > 0.2)",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to the microcode sequencer (MS).",
+        "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to the microcode sequencer (MS)",
         "MetricExpr": "TOPDOWN_FE_BOUND.CISC / (6 * CPU_CLK_UNHALTED.CORE)",
-        "MetricGroup": "TopdownL3;tma_L3_group;tma_ifetch_bandwidth_group",
+        "MetricGroup": "Slots;TopdownL3;tma_L3_group;tma_ifetch_bandwidth_group",
         "MetricName": "tma_cisc",
-        "MetricThreshold": "tma_cisc > 0.05 & (tma_ifetch_bandwidth > 0.1 & tma_frontend_bound > 0.2)",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "Counts the number of cycles due to backend bound stalls that are bounded by core restrictions and not attributed to an outstanding load or stores, or resource limitation",
         "MetricExpr": "TOPDOWN_BE_BOUND.ALLOC_RESTRICTIONS / (6 * CPU_CLK_UNHALTED.CORE)",
-        "MetricGroup": "TopdownL2;tma_L2_group;tma_backend_bound_group",
+        "MetricGroup": "Slots;TopdownL2;tma_L2_group;tma_backend_bound_group",
         "MetricName": "tma_core_bound",
-        "MetricThreshold": "tma_core_bound > 0.1 & tma_backend_bound > 0.1",
         "MetricgroupNoGroup": "TopdownL2",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to decode stalls.",
+        "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to decode stalls",
         "MetricExpr": "TOPDOWN_FE_BOUND.DECODE / (6 * CPU_CLK_UNHALTED.CORE)",
-        "MetricGroup": "TopdownL3;tma_L3_group;tma_ifetch_bandwidth_group",
+        "MetricGroup": "Slots;TopdownL3;tma_L3_group;tma_ifetch_bandwidth_group",
         "MetricName": "tma_decode",
-        "MetricThreshold": "tma_decode > 0.05 & (tma_ifetch_bandwidth > 0.1 & tma_frontend_bound > 0.2)",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "Counts the number of issue slots that were not consumed by the backend due to a machine clear that does not require the use of microcode, classified as a fast nuke, due to memory ordering, memory disambiguation and memory renaming",
         "MetricExpr": "TOPDOWN_BAD_SPECULATION.FASTNUKE / (6 * CPU_CLK_UNHALTED.CORE)",
-        "MetricGroup": "TopdownL3;tma_L3_group;tma_machine_clears_group",
+        "MetricGroup": "Slots;TopdownL3;tma_L3_group;tma_machine_clears_group",
         "MetricName": "tma_fast_nuke",
-        "MetricThreshold": "tma_fast_nuke > 0.05 & (tma_machine_clears > 0.05 & tma_bad_speculation > 0.15)",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "Counts the number of issue slots that were not consumed by the backend due to frontend stalls.",
+        "BriefDescription": "Counts the number of issue slots that were not consumed by the backend due to frontend stalls",
         "MetricExpr": "TOPDOWN_FE_BOUND.ALL_P / (6 * CPU_CLK_UNHALTED.CORE)",
-        "MetricGroup": "TopdownL1;tma_L1_group",
+        "MetricGroup": "Slots;TopdownL1;tma_L1_group",
         "MetricName": "tma_frontend_bound",
-        "MetricThreshold": "tma_frontend_bound > 0.2",
         "MetricgroupNoGroup": "TopdownL1",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to instruction cache misses.",
+        "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to instruction cache misses",
         "MetricExpr": "TOPDOWN_FE_BOUND.ICACHE / (6 * CPU_CLK_UNHALTED.CORE)",
-        "MetricGroup": "TopdownL3;tma_L3_group;tma_ifetch_latency_group",
+        "MetricGroup": "Slots;TopdownL3;tma_L3_group;tma_ifetch_latency_group",
         "MetricName": "tma_icache_misses",
-        "MetricThreshold": "tma_icache_misses > 0.05 & (tma_ifetch_latency > 0.15 & tma_frontend_bound > 0.2)",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to frontend bandwidth restrictions due to decode, predecode, cisc, and other limitations.",
+        "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to frontend bandwidth restrictions due to decode, predecode, cisc, and other limitations",
         "MetricExpr": "TOPDOWN_FE_BOUND.FRONTEND_BANDWIDTH / (6 * CPU_CLK_UNHALTED.CORE)",
-        "MetricGroup": "TopdownL2;tma_L2_group;tma_frontend_bound_group",
+        "MetricGroup": "Slots;TopdownL2;tma_L2_group;tma_frontend_bound_group",
         "MetricName": "tma_ifetch_bandwidth",
-        "MetricThreshold": "tma_ifetch_bandwidth > 0.1 & tma_frontend_bound > 0.2",
         "MetricgroupNoGroup": "TopdownL2",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to frontend latency restrictions due to icache misses, itlb misses, branch detection, and resteer limitations.",
+        "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to frontend latency restrictions due to icache misses, itlb misses, branch detection, and resteer limitations",
         "MetricExpr": "TOPDOWN_FE_BOUND.FRONTEND_LATENCY / (6 * CPU_CLK_UNHALTED.CORE)",
-        "MetricGroup": "TopdownL2;tma_L2_group;tma_frontend_bound_group",
+        "MetricGroup": "Slots;TopdownL2;tma_L2_group;tma_frontend_bound_group",
         "MetricName": "tma_ifetch_latency",
-        "MetricThreshold": "tma_ifetch_latency > 0.15 & tma_frontend_bound > 0.2",
         "MetricgroupNoGroup": "TopdownL2",
         "ScaleUnit": "100%"
     },
@@ -331,32 +345,6 @@
         "MetricGroup": "Flops",
         "MetricName": "tma_info_arith_inst_mix_ipfparith_scalar_sp"
     },
-    {
-        "BriefDescription": "Percentage of time that retirement is stalled due to a first level data TLB miss",
-        "MetricExpr": "tma_info_bottleneck_dtlb_miss_bound_cycles",
-        "MetricName": "tma_info_bottleneck_%_dtlb_miss_bound_cycles"
-    },
-    {
-        "BriefDescription": "Percentage of time that allocation and retirement is stalled by the Frontend Cluster due to an Ifetch Miss, either Icache or ITLB Miss",
-        "MetricExpr": "tma_info_bottleneck_ifetch_miss_bound_cycles",
-        "MetricGroup": "Ifetch",
-        "MetricName": "tma_info_bottleneck_%_ifetch_miss_bound_cycles",
-        "PublicDescription": "Percentage of time that allocation and retirement is stalled by the Frontend Cluster due to an Ifetch Miss, either Icache or ITLB Miss. See Info.Ifetch_Bound"
-    },
-    {
-        "BriefDescription": "Percentage of time that retirement is stalled due to an L1 miss",
-        "MetricExpr": "tma_info_bottleneck_load_miss_bound_cycles",
-        "MetricGroup": "Load_Store_Miss",
-        "MetricName": "tma_info_bottleneck_%_load_miss_bound_cycles",
-        "PublicDescription": "Percentage of time that retirement is stalled due to an L1 miss. See Info.Load_Miss_Bound"
-    },
-    {
-        "BriefDescription": "Percentage of time that retirement is stalled by the Memory Cluster due to a pipeline stall",
-        "MetricExpr": "tma_info_bottleneck_mem_exec_bound_cycles",
-        "MetricGroup": "Mem_Exec",
-        "MetricName": "tma_info_bottleneck_%_mem_exec_bound_cycles",
-        "PublicDescription": "Percentage of time that retirement is stalled by the Memory Cluster due to a pipeline stall. See Info.Mem_Exec_Bound"
-    },
     {
         "BriefDescription": "Percentage of time that retirement is stalled due to a first level data TLB miss",
         "MetricExpr": "100 * (LD_HEAD.DTLB_MISS_AT_RET + LD_HEAD.PGWALK_AT_RET) / CPU_CLK_UNHALTED.CORE",
@@ -438,21 +426,6 @@
         "MetricExpr": "BR_MISP_RETIRED.ALL_BRANCHES / BACLEARS.ANY",
         "MetricName": "tma_info_br_mispredict_bound_branch_mispredict_to_unknown_branch_ratio"
     },
-    {
-        "BriefDescription": "Percentage of time that allocation is stalled due to load buffer full",
-        "MetricExpr": "tma_info_buffer_stalls_load_buffer_stall_cycles",
-        "MetricName": "tma_info_buffer_stalls_%_load_buffer_stall_cycles"
-    },
-    {
-        "BriefDescription": "Percentage of time that allocation is stalled due to memory reservation stations full",
-        "MetricExpr": "tma_info_buffer_stalls_mem_rsv_stall_cycles",
-        "MetricName": "tma_info_buffer_stalls_%_mem_rsv_stall_cycles"
-    },
-    {
-        "BriefDescription": "Percentage of time that allocation is stalled due to store buffer full",
-        "MetricExpr": "tma_info_buffer_stalls_store_buffer_stall_cycles",
-        "MetricName": "tma_info_buffer_stalls_%_store_buffer_stall_cycles"
-    },
     {
         "BriefDescription": "Percentage of time that allocation is stalled due to load buffer full",
         "MetricExpr": "100 * MEM_SCHEDULER_BLOCK.LD_BUF / CPU_CLK_UNHALTED.CORE",
@@ -474,7 +447,8 @@
     {
         "BriefDescription": "Cycles Per Instruction",
         "MetricExpr": "CPU_CLK_UNHALTED.CORE / INST_RETIRED.ANY",
-        "MetricName": "tma_info_core_cpi"
+        "MetricName": "tma_info_core_cpi",
+        "ScaleUnit": "1per_instr"
     },
     {
         "BriefDescription": "Floating Point Operations Per Cycle",
@@ -492,21 +466,6 @@
         "MetricExpr": "TOPDOWN_RETIRING.ALL_P / INST_RETIRED.ANY",
         "MetricName": "tma_info_core_upi"
     },
-    {
-        "BriefDescription": "Percentage of ifetch miss bound stalls, where the ifetch miss hits in the L2",
-        "MetricExpr": "tma_info_ifetch_miss_bound_ifetchmissbound_with_l2hit",
-        "MetricName": "tma_info_ifetch_miss_bound_%_ifetchmissbound_with_l2hit"
-    },
-    {
-        "BriefDescription": "Percentage of ifetch miss bound stalls, where the ifetch miss hits in the L3",
-        "MetricExpr": "tma_info_ifetch_miss_bound_ifetchmissbound_with_l3hit",
-        "MetricName": "tma_info_ifetch_miss_bound_%_ifetchmissbound_with_l3hit"
-    },
-    {
-        "BriefDescription": "Percentage of ifetch miss bound stalls, where the ifetch miss subsequently misses in the L3",
-        "MetricExpr": "100 * MEM_BOUND_STALLS_IFETCH.LLC_MISS / MEM_BOUND_STALLS_IFETCH.ALL",
-        "MetricName": "tma_info_ifetch_miss_bound_%_ifetchmissbound_with_l3miss"
-    },
     {
         "BriefDescription": "Percentage of ifetch miss bound stalls, where the ifetch miss hits in the L2",
         "MetricExpr": "100 * MEM_BOUND_STALLS_IFETCH.L2_HIT / MEM_BOUND_STALLS_IFETCH.ALL",
@@ -519,24 +478,6 @@
         "MetricName": "tma_info_ifetch_miss_bound_ifetchmissbound_with_l3hit",
         "ScaleUnit": "100%"
     },
-    {
-        "BriefDescription": "Percentage of memory bound stalls where retirement is stalled due to an L1 miss that hit the L2",
-        "MetricExpr": "tma_info_load_miss_bound_loadmissbound_with_l2hit",
-        "MetricGroup": "load_store_bound",
-        "MetricName": "tma_info_load_miss_bound_%_loadmissbound_with_l2hit"
-    },
-    {
-        "BriefDescription": "Percentage of memory bound stalls where retirement is stalled due to an L1 miss that hit the L3",
-        "MetricExpr": "tma_info_load_miss_bound_loadmissbound_with_l3hit",
-        "MetricGroup": "load_store_bound",
-        "MetricName": "tma_info_load_miss_bound_%_loadmissbound_with_l3hit"
-    },
-    {
-        "BriefDescription": "Percentage of memory bound stalls where retirement is stalled due to an L1 miss that subsequently misses the L3",
-        "MetricExpr": "100 * MEM_BOUND_STALLS_LOAD.LLC_MISS / MEM_BOUND_STALLS_LOAD.ALL",
-        "MetricGroup": "load_store_bound",
-        "MetricName": "tma_info_load_miss_bound_%_loadmissbound_with_l3miss"
-    },
     {
         "BriefDescription": "Percentage of memory bound stalls where retirement is stalled due to an L1 miss that hit the L2",
         "MetricExpr": "100 * MEM_BOUND_STALLS_LOAD.L2_HIT / MEM_BOUND_STALLS_LOAD.ALL",
@@ -584,16 +525,6 @@
         "MetricExpr": "1e3 * MACHINE_CLEARS.SMC / INST_RETIRED.ANY",
         "MetricName": "tma_info_machine_clear_bound_machine_clears_smc_pki"
     },
-    {
-        "BriefDescription": "Percentage of total non-speculative loads with an address aliasing block",
-        "MetricExpr": "tma_info_mem_exec_blocks_loads_with_adressaliasing",
-        "MetricName": "tma_info_mem_exec_blocks_%_loads_with_adressaliasing"
-    },
-    {
-        "BriefDescription": "Percentage of total non-speculative loads with a store forward or unknown store address block",
-        "MetricExpr": "tma_info_mem_exec_blocks_loads_with_storefwdblk",
-        "MetricName": "tma_info_mem_exec_blocks_%_loads_with_storefwdblk"
-    },
     {
         "BriefDescription": "Percentage of total non-speculative loads with an address aliasing block",
         "MetricExpr": "100 * LD_BLOCKS.ADDRESS_ALIAS / MEM_UOPS_RETIRED.ALL_LOADS",
@@ -606,31 +537,6 @@
         "MetricName": "tma_info_mem_exec_blocks_loads_with_storefwdblk",
         "ScaleUnit": "100%"
     },
-    {
-        "BriefDescription": "Percentage of Memory Execution Bound due to a first level data cache miss",
-        "MetricExpr": "tma_info_mem_exec_bound_loadhead_with_l1miss",
-        "MetricName": "tma_info_mem_exec_bound_%_loadhead_with_l1miss"
-    },
-    {
-        "BriefDescription": "Percentage of Memory Execution Bound due to other block cases, such as pipeline conflicts, fences, etc",
-        "MetricExpr": "tma_info_mem_exec_bound_loadhead_with_otherpipelineblks",
-        "MetricName": "tma_info_mem_exec_bound_%_loadhead_with_otherpipelineblks"
-    },
-    {
-        "BriefDescription": "Percentage of Memory Execution Bound due to a pagewalk",
-        "MetricExpr": "tma_info_mem_exec_bound_loadhead_with_pagewalk",
-        "MetricName": "tma_info_mem_exec_bound_%_loadhead_with_pagewalk"
-    },
-    {
-        "BriefDescription": "Percentage of Memory Execution Bound due to a second level TLB miss",
-        "MetricExpr": "tma_info_mem_exec_bound_loadhead_with_stlbhit",
-        "MetricName": "tma_info_mem_exec_bound_%_loadhead_with_stlbhit"
-    },
-    {
-        "BriefDescription": "Percentage of Memory Execution Bound due to a store forward address match",
-        "MetricExpr": "tma_info_mem_exec_bound_loadhead_with_storefwding",
-        "MetricName": "tma_info_mem_exec_bound_%_loadhead_with_storefwding"
-    },
     {
         "BriefDescription": "Percentage of Memory Execution Bound due to a first level data cache miss",
         "MetricExpr": "100 * LD_HEAD.L1_MISS_AT_RET / LD_HEAD.ANY_AT_RET",
@@ -686,11 +592,6 @@
         "MetricExpr": "1e3 * MEM_UOPS_RETIRED.ALL_LOADS / TOPDOWN_RETIRING.ALL_P",
         "MetricName": "tma_info_mem_mix_memload_ratio"
     },
-    {
-        "BriefDescription": "Percentage of time that the core is stalled due to a TPAUSE or UMWAIT instruction",
-        "MetricExpr": "tma_info_serialization_tpause_cycles",
-        "MetricName": "tma_info_serialization _%_tpause_cycles"
-    },
     {
         "BriefDescription": "Percentage of time that the core is stalled due to a TPAUSE or UMWAIT instruction",
         "MetricExpr": "100 * SERIALIZATION.C01_MS_SCB / (6 * CPU_CLK_UNHALTED.CORE)",
@@ -711,14 +612,17 @@
     },
     {
         "BriefDescription": "Fraction of cycles spent in Kernel mode",
-        "MetricExpr": "cpu@CPU_CLK_UNHALTED.CORE_P@k / CPU_CLK_UNHALTED.CORE",
-        "MetricGroup": "Summary",
+        "MetricExpr": "CPU_CLK_UNHALTED.CORE_P:k / CPU_CLK_UNHALTED.CORE",
         "MetricName": "tma_info_system_kernel_utilization"
     },
+    {
+        "BriefDescription": "PerfMon Event Multiplexing accuracy indicator",
+        "MetricExpr": "CPU_CLK_UNHALTED.CORE_P / CPU_CLK_UNHALTED.CORE",
+        "MetricName": "tma_info_system_mux"
+    },
     {
         "BriefDescription": "Average Frequency Utilization relative nominal frequency",
         "MetricExpr": "CPU_CLK_UNHALTED.CORE / CPU_CLK_UNHALTED.REF_TSC",
-        "MetricGroup": "Power",
         "MetricName": "tma_info_system_turbo_utilization"
     },
     {
@@ -742,102 +646,90 @@
         "MetricName": "tma_info_uop_mix_x87_uop_ratio"
     },
     {
-        "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to Instruction Table Lookaside Buffer (ITLB) misses.",
+        "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to Instruction Table Lookaside Buffer (ITLB) misses",
         "MetricExpr": "TOPDOWN_FE_BOUND.ITLB_MISS / (6 * CPU_CLK_UNHALTED.CORE)",
-        "MetricGroup": "TopdownL3;tma_L3_group;tma_ifetch_latency_group",
+        "MetricGroup": "Slots;TopdownL3;tma_L3_group;tma_ifetch_latency_group",
         "MetricName": "tma_itlb_misses",
-        "MetricThreshold": "tma_itlb_misses > 0.05 & (tma_ifetch_latency > 0.15 & tma_frontend_bound > 0.2)",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "Counts the total number of issue slots that were not consumed by the backend because allocation is stalled due to a machine clear (nuke) of any kind including memory ordering and memory disambiguation",
         "MetricExpr": "TOPDOWN_BAD_SPECULATION.MACHINE_CLEARS / (6 * CPU_CLK_UNHALTED.CORE)",
-        "MetricGroup": "TopdownL2;tma_L2_group;tma_bad_speculation_group",
+        "MetricGroup": "Slots;TopdownL2;tma_L2_group;tma_bad_speculation_group",
         "MetricName": "tma_machine_clears",
-        "MetricThreshold": "tma_machine_clears > 0.05 & tma_bad_speculation > 0.15",
         "MetricgroupNoGroup": "TopdownL2",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "Counts the number of issue slots that were not consumed by the backend due to memory reservation stalls in which a scheduler is not able to accept uops",
         "MetricExpr": "TOPDOWN_BE_BOUND.MEM_SCHEDULER / (6 * CPU_CLK_UNHALTED.CORE)",
-        "MetricGroup": "TopdownL3;tma_L3_group;tma_resource_bound_group",
+        "MetricGroup": "Slots;TopdownL3;tma_L3_group;tma_resource_bound_group",
         "MetricName": "tma_mem_scheduler",
-        "MetricThreshold": "tma_mem_scheduler > 0.1 & (tma_resource_bound > 0.2 & tma_backend_bound > 0.1)",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "Counts the number of issue slots that were not consumed by the backend due to IEC or FPC RAT stalls, which can be due to FIQ or IEC reservation stalls in which the integer, floating point or SIMD scheduler is not able to accept uops",
         "MetricExpr": "TOPDOWN_BE_BOUND.NON_MEM_SCHEDULER / (6 * CPU_CLK_UNHALTED.CORE)",
-        "MetricGroup": "TopdownL3;tma_L3_group;tma_resource_bound_group",
+        "MetricGroup": "Slots;TopdownL3;tma_L3_group;tma_resource_bound_group",
         "MetricName": "tma_non_mem_scheduler",
-        "MetricThreshold": "tma_non_mem_scheduler > 0.1 & (tma_resource_bound > 0.2 & tma_backend_bound > 0.1)",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "Counts the number of issue slots that were not consumed by the backend due to a machine clear that requires the use of microcode (slow nuke)",
         "MetricExpr": "TOPDOWN_BAD_SPECULATION.NUKE / (6 * CPU_CLK_UNHALTED.CORE)",
-        "MetricGroup": "TopdownL3;tma_L3_group;tma_machine_clears_group",
+        "MetricGroup": "Slots;TopdownL3;tma_L3_group;tma_machine_clears_group",
         "MetricName": "tma_nuke",
-        "MetricThreshold": "tma_nuke > 0.05 & (tma_machine_clears > 0.05 & tma_bad_speculation > 0.15)",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to other common frontend stalls not categorized.",
+        "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to other common frontend stalls not categorized",
         "MetricExpr": "TOPDOWN_FE_BOUND.OTHER / (6 * CPU_CLK_UNHALTED.CORE)",
-        "MetricGroup": "TopdownL3;tma_L3_group;tma_ifetch_bandwidth_group",
+        "MetricGroup": "Slots;TopdownL3;tma_L3_group;tma_ifetch_bandwidth_group",
         "MetricName": "tma_other_fb",
-        "MetricThreshold": "tma_other_fb > 0.05 & (tma_ifetch_bandwidth > 0.1 & tma_frontend_bound > 0.2)",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to wrong predecodes.",
+        "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to wrong predecodes",
         "MetricExpr": "TOPDOWN_FE_BOUND.PREDECODE / (6 * CPU_CLK_UNHALTED.CORE)",
-        "MetricGroup": "TopdownL3;tma_L3_group;tma_ifetch_bandwidth_group",
+        "MetricGroup": "Slots;TopdownL3;tma_L3_group;tma_ifetch_bandwidth_group",
         "MetricName": "tma_predecode",
-        "MetricThreshold": "tma_predecode > 0.05 & (tma_ifetch_bandwidth > 0.1 & tma_frontend_bound > 0.2)",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "Counts the number of issue slots that were not consumed by the backend due to the physical register file unable to accept an entry (marble stalls)",
         "MetricExpr": "TOPDOWN_BE_BOUND.REGISTER / (6 * CPU_CLK_UNHALTED.CORE)",
-        "MetricGroup": "TopdownL3;tma_L3_group;tma_resource_bound_group",
+        "MetricGroup": "Slots;TopdownL3;tma_L3_group;tma_resource_bound_group",
         "MetricName": "tma_register",
-        "MetricThreshold": "tma_register > 0.1 & (tma_resource_bound > 0.2 & tma_backend_bound > 0.1)",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "Counts the number of issue slots that were not consumed by the backend due to the reorder buffer being full (ROB stalls)",
         "MetricExpr": "TOPDOWN_BE_BOUND.REORDER_BUFFER / (6 * CPU_CLK_UNHALTED.CORE)",
-        "MetricGroup": "TopdownL3;tma_L3_group;tma_resource_bound_group",
+        "MetricGroup": "Slots;TopdownL3;tma_L3_group;tma_resource_bound_group",
         "MetricName": "tma_reorder_buffer",
-        "MetricThreshold": "tma_reorder_buffer > 0.1 & (tma_resource_bound > 0.2 & tma_backend_bound > 0.1)",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "Counts the number of cycles the core is stalled due to a resource limitation",
         "MetricExpr": "tma_backend_bound - tma_core_bound",
-        "MetricGroup": "TopdownL2;tma_L2_group;tma_backend_bound_group",
+        "MetricGroup": "Slots;TopdownL2;tma_L2_group;tma_backend_bound_group",
         "MetricName": "tma_resource_bound",
-        "MetricThreshold": "tma_resource_bound > 0.2 & tma_backend_bound > 0.1",
         "MetricgroupNoGroup": "TopdownL2",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "Counts the number of issue slots that result in retirement slots",
         "MetricExpr": "TOPDOWN_RETIRING.ALL_P / (6 * CPU_CLK_UNHALTED.CORE)",
-        "MetricGroup": "TopdownL1;tma_L1_group",
+        "MetricGroup": "Slots;TopdownL1;tma_L1_group",
         "MetricName": "tma_retiring",
-        "MetricThreshold": "tma_retiring > 0.75",
         "MetricgroupNoGroup": "TopdownL1",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "Counts the number of issue slots that were not consumed by the backend due to scoreboards from the instruction queue (IQ), jump execution unit (JEU), or microcode sequencer (MS)",
         "MetricExpr": "TOPDOWN_BE_BOUND.SERIALIZATION / (6 * CPU_CLK_UNHALTED.CORE)",
-        "MetricGroup": "TopdownL3;tma_L3_group;tma_resource_bound_group",
+        "MetricGroup": "Slots;TopdownL3;tma_L3_group;tma_resource_bound_group",
         "MetricName": "tma_serialization",
-        "MetricThreshold": "tma_serialization > 0.1 & (tma_resource_bound > 0.2 & tma_backend_bound > 0.1)",
         "ScaleUnit": "100%"
     },
     {
tools/perf/pmu-events/arch/x86/grandridge/pipeline.json +1 -2
index b67c0c89054d..40fa4f5ae261 100644
@@ -1,6 +1,6 @@
 [
     {
-        "BriefDescription": "Counts the number of cycles when any of the dividers are active.",
+        "BriefDescription": "Counts the number of cycles when any of the floating point or integer dividers are active.",
         "Counter": "0,1,2,3,4,5,6,7",
         "CounterMask": "1",
         "EventCode": "0xcd",
@@ -185,7 +185,6 @@
         "BriefDescription": "Fixed Counter: Counts the number of instructions retired",
         "Counter": "Fixed counter 0",
         "EventName": "INST_RETIRED.ANY",
-        "PEBS": "1",
         "SampleAfterValue": "2000003",
         "UMask": "0x1"
     },
tools/perf/pmu-events/arch/x86/grandridge/uncore-cache.json +2 -2
index 1eaf796601b1..6a80cf6cbd36 100644
@@ -573,7 +573,7 @@
         "Unit": "CHA"
     },
     {
-        "BriefDescription": "Code read from local IA that miss the cache",
+        "BriefDescription": "Code read from local IA",
         "Counter": "0,1,2,3",
         "EventCode": "0x35",
         "EventName": "UNC_CHA_TOR_INSERTS.IA_CRD",
@@ -593,7 +593,7 @@
         "Unit": "CHA"
     },
     {
-        "BriefDescription": "Data read opt from local IA that miss the cache",
+        "BriefDescription": "Data read opt from local IA",
         "Counter": "0,1,2,3",
         "EventCode": "0x35",
         "EventName": "UNC_CHA_TOR_INSERTS.IA_DRD_OPT",
tools/perf/pmu-events/arch/x86/grandridge/uncore-interconnect.json +60 -0

72 lines not on this page · raw message

tools/perf/pmu-events/arch/x86/grandridge/uncore-io.json +107 -107

856 lines not on this page · raw message

tools/perf/pmu-events/arch/x86/grandridge/uncore-memory.json +1 -1
index 7e6e6764f181..e75b3050ccd5 100644
@@ -169,7 +169,7 @@
         "Unit": "IMC"
     },
     {
-        "BriefDescription": "Number of DRAM DCLK clock cycles while the event is enabled",
+        "BriefDescription": "Number of DRAM DCLK clock cycles while the event is enabled.  DCLK is 1/4 of DRAM data rate.",
         "Counter": "0,1,2,3",
         "EventCode": "0x01",
         "EventName": "UNC_M_CLOCKTICKS",
tools/perf/pmu-events/arch/x86/mapfile.csv +1 -1
index 7260a2ac133a..2cd9296f0f12 100644
@@ -12,7 +12,7 @@ GenuineIntel-6-9[6C],v1.05,elkhartlake,core
 GenuineIntel-6-CF,v1.11,emeraldrapids,core
 GenuineIntel-6-5[CF],v13,goldmont,core
 GenuineIntel-6-7A,v1.01,goldmontplus,core
-GenuineIntel-6-B6,v1.03,grandridge,core
+GenuineIntel-6-B6,v1.05,grandridge,core
 GenuineIntel-6-A[DE],v1.02,graniterapids,core
 GenuineIntel-6-(3C|45|46),v35,haswell,core
 GenuineIntel-6-3F,v28,haswellx,core
Signature · 1 line
2.48.1.502.g6dc24dfdaf-goog
author reviewer
#11 lore raw

PATCH v8 11/24 perf vendor events: Update/add Graniterapids events/metrics

In reply to Ian Rogers

Update events from v1.02 to v1.06.
Add TMA metrics 5.02.

Bring in the event updates v1.06:
https://github.com/intel/perfmon/commit/de5502e51a86b0cf42d0807d4e8ed3c6299b4e6c
https://github.com/intel/perfmon/commit/79b9e512eab58641941a0b8d10ffe75914a87e17
https://github.com/intel/perfmon/commit/bc74a895e461b5ac720559da667e83a8fedf7829

The TMA 5.02 addition is from (with subsequent fixes):
https://github.com/intel/perfmon/commit/1d72913b2d938781fb28f3cc3507aaec5c22d782

Update uncore IIO events umask with the change:
https://github.com/intel/perfmon/commit/d78e8a166537c9ceab4f2e901dc96c53667a2174
which should address an issue originally raised by Michael Petlan:

---
 .../arch/x86/graniterapids/cache.json         |  130 +-
 .../arch/x86/graniterapids/counter.json       |   24 +-
 .../arch/x86/graniterapids/frontend.json      |   24 +-
 .../arch/x86/graniterapids/gnr-metrics.json   | 2325 +++++++++++++++++
 .../arch/x86/graniterapids/memory.json        |  121 +-
 .../arch/x86/graniterapids/metricgroups.json  |  145 +
 .../arch/x86/graniterapids/other.json         |  109 +
 .../arch/x86/graniterapids/pipeline.json      |   40 +-
 .../arch/x86/graniterapids/uncore-cache.json  |   48 +-
 .../arch/x86/graniterapids/uncore-cxl.json    |    2 -
 .../graniterapids/uncore-interconnect.json    |   87 +
 .../arch/x86/graniterapids/uncore-io.json     |  280 +-
 .../arch/x86/graniterapids/uncore-memory.json |  122 +-
 .../arch/x86/graniterapids/uncore-power.json  |   98 +
 tools/perf/pmu-events/arch/x86/mapfile.csv    |    2 +-
 15 files changed, 3294 insertions(+), 263 deletions(-)
 create mode 100644 tools/perf/pmu-events/arch/x86/graniterapids/gnr-metrics.json
 create mode 100644 tools/perf/pmu-events/arch/x86/graniterapids/metricgroups.json
tools/perf/pmu-events/arch/x86/graniterapids/cache.json +102 -28
index b56066274813..d155da8610d8 100644
@@ -83,11 +83,11 @@
         "UMask": "0x2"
     },
     {
-        "BriefDescription": "Non-modified cache lines that are silently dropped by L2 cache when triggered by an L2 cache fill.",
+        "BriefDescription": "Non-modified cache lines that are silently dropped by L2 cache.",
         "Counter": "0,1,2,3",
         "EventCode": "0x26",
         "EventName": "L2_LINES_OUT.SILENT",
-        "PublicDescription": "Counts the number of lines that are silently dropped by L2 cache when triggered by an L2 cache fill. These lines are typically in Shared or Exclusive state. A non-threaded event.",
+        "PublicDescription": "Counts the number of lines that are silently dropped by L2 cache. These lines are typically in Shared or Exclusive state. A non-threaded event.",
         "SampleAfterValue": "200003",
         "UMask": "0x1"
     },
@@ -320,7 +320,6 @@
         "Data_LA": "1",
         "EventCode": "0xd0",
         "EventName": "MEM_INST_RETIRED.ALL_LOADS",
-        "PEBS": "1",
         "PublicDescription": "Counts all retired load instructions. This event accounts for SW prefetch instructions of PREFETCHNTA or PREFETCHT0/1/2 or PREFETCHW.",
         "SampleAfterValue": "1000003",
         "UMask": "0x81"
@@ -331,7 +330,6 @@
         "Data_LA": "1",
         "EventCode": "0xd0",
         "EventName": "MEM_INST_RETIRED.ALL_STORES",
-        "PEBS": "1",
         "PublicDescription": "Counts all retired store instructions.",
         "SampleAfterValue": "1000003",
         "UMask": "0x82"
@@ -342,7 +340,6 @@
         "Data_LA": "1",
         "EventCode": "0xd0",
         "EventName": "MEM_INST_RETIRED.ANY",
-        "PEBS": "1",
         "PublicDescription": "Counts all retired memory instructions - loads and stores.",
         "SampleAfterValue": "1000003",
         "UMask": "0x83"
@@ -353,7 +350,6 @@
         "Data_LA": "1",
         "EventCode": "0xd0",
         "EventName": "MEM_INST_RETIRED.LOCK_LOADS",
-        "PEBS": "1",
         "PublicDescription": "Counts retired load instructions with locked access.",
         "SampleAfterValue": "100007",
         "UMask": "0x21"
@@ -364,7 +360,6 @@
         "Data_LA": "1",
         "EventCode": "0xd0",
         "EventName": "MEM_INST_RETIRED.SPLIT_LOADS",
-        "PEBS": "1",
         "PublicDescription": "Counts retired load instructions that split across a cacheline boundary.",
         "SampleAfterValue": "100003",
         "UMask": "0x41"
@@ -375,7 +370,6 @@
         "Data_LA": "1",
         "EventCode": "0xd0",
         "EventName": "MEM_INST_RETIRED.SPLIT_STORES",
-        "PEBS": "1",
         "PublicDescription": "Counts retired store instructions that split across a cacheline boundary.",
         "SampleAfterValue": "100003",
         "UMask": "0x42"
@@ -386,7 +380,6 @@
         "Data_LA": "1",
         "EventCode": "0xd0",
         "EventName": "MEM_INST_RETIRED.STLB_HIT_LOADS",
-        "PEBS": "1",
         "PublicDescription": "Number of retired load instructions with a clean hit in the 2nd-level TLB (STLB).",
         "SampleAfterValue": "100003",
         "UMask": "0x9"
@@ -397,7 +390,6 @@
         "Data_LA": "1",
         "EventCode": "0xd0",
         "EventName": "MEM_INST_RETIRED.STLB_HIT_STORES",
-        "PEBS": "1",
         "PublicDescription": "Number of retired store instructions that hit in the 2nd-level TLB (STLB).",
         "SampleAfterValue": "100003",
         "UMask": "0xa"
@@ -408,7 +400,6 @@
         "Data_LA": "1",
         "EventCode": "0xd0",
         "EventName": "MEM_INST_RETIRED.STLB_MISS_LOADS",
-        "PEBS": "1",
         "PublicDescription": "Number of retired load instructions that (start a) miss in the 2nd-level TLB (STLB).",
         "SampleAfterValue": "100003",
         "UMask": "0x11"
@@ -419,7 +410,6 @@
         "Data_LA": "1",
         "EventCode": "0xd0",
         "EventName": "MEM_INST_RETIRED.STLB_MISS_STORES",
-        "PEBS": "1",
         "PublicDescription": "Number of retired store instructions that (start a) miss in the 2nd-level TLB (STLB).",
         "SampleAfterValue": "100003",
         "UMask": "0x12"
@@ -439,7 +429,6 @@
         "Data_LA": "1",
         "EventCode": "0xd2",
         "EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD",
-        "PEBS": "1",
         "PublicDescription": "Counts retired load instructions whose data sources were HitM responses from shared L3.",
         "SampleAfterValue": "20011",
         "UMask": "0x4"
@@ -450,7 +439,6 @@
         "Data_LA": "1",
         "EventCode": "0xd2",
         "EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS",
-        "PEBS": "1",
         "PublicDescription": "Counts the retired load instructions whose data sources were L3 hit and cross-core snoop missed in on-pkg core cache.",
         "SampleAfterValue": "20011",
         "UMask": "0x1"
@@ -461,7 +449,6 @@
         "Data_LA": "1",
         "EventCode": "0xd2",
         "EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_NONE",
-        "PEBS": "1",
         "PublicDescription": "Counts retired load instructions whose data sources were hits in L3 without snoops required.",
         "SampleAfterValue": "100003",
         "UMask": "0x8"
@@ -472,7 +459,6 @@
         "Data_LA": "1",
         "EventCode": "0xd2",
         "EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_NO_FWD",
-        "PEBS": "1",
         "PublicDescription": "Counts retired load instructions whose data sources were L3 and cross-core snoop hits in on-pkg core cache.",
         "SampleAfterValue": "20011",
         "UMask": "0x2"
@@ -483,7 +469,6 @@
         "Data_LA": "1",
         "EventCode": "0xd3",
         "EventName": "MEM_LOAD_L3_MISS_RETIRED.LOCAL_DRAM",
-        "PEBS": "1",
         "PublicDescription": "Retired load instructions which data sources missed L3 but serviced from local DRAM.",
         "SampleAfterValue": "100007",
         "UMask": "0x1"
@@ -494,7 +479,6 @@
         "Data_LA": "1",
         "EventCode": "0xd3",
         "EventName": "MEM_LOAD_L3_MISS_RETIRED.REMOTE_DRAM",
-        "PEBS": "1",
         "SampleAfterValue": "1000003",
         "UMask": "0x2"
     },
@@ -504,7 +488,6 @@
         "Data_LA": "1",
         "EventCode": "0xd3",
         "EventName": "MEM_LOAD_L3_MISS_RETIRED.REMOTE_FWD",
-        "PEBS": "1",
         "PublicDescription": "Retired load instructions whose data sources was forwarded from a remote cache.",
         "SampleAfterValue": "100007",
         "UMask": "0x8"
@@ -515,7 +498,6 @@
         "Data_LA": "1",
         "EventCode": "0xd3",
         "EventName": "MEM_LOAD_L3_MISS_RETIRED.REMOTE_HITM",
-        "PEBS": "1",
         "SampleAfterValue": "1000003",
         "UMask": "0x4"
     },
@@ -525,7 +507,6 @@
         "Data_LA": "1",
         "EventCode": "0xd4",
         "EventName": "MEM_LOAD_MISC_RETIRED.UC",
-        "PEBS": "1",
         "PublicDescription": "Retired instructions with at least one load to uncacheable memory-type, or at least one cache-line split locked access (Bus Lock).",
         "SampleAfterValue": "100007",
         "UMask": "0x4"
@@ -536,7 +517,6 @@
         "Data_LA": "1",
         "EventCode": "0xd1",
         "EventName": "MEM_LOAD_RETIRED.FB_HIT",
-        "PEBS": "1",
         "PublicDescription": "Counts retired load instructions with at least one uop was load missed in L1 but hit FB (Fill Buffers) due to preceding miss to the same cache line with data not ready.",
         "SampleAfterValue": "100007",
         "UMask": "0x40"
@@ -547,7 +527,6 @@
         "Data_LA": "1",
         "EventCode": "0xd1",
         "EventName": "MEM_LOAD_RETIRED.L1_HIT",
-        "PEBS": "1",
         "PublicDescription": "Counts retired load instructions with at least one uop that hit in the L1 data cache. This event includes all SW prefetches and lock instructions regardless of the data source.",
         "SampleAfterValue": "1000003",
         "UMask": "0x1"
@@ -558,7 +537,6 @@
         "Data_LA": "1",
         "EventCode": "0xd1",
         "EventName": "MEM_LOAD_RETIRED.L1_MISS",
-        "PEBS": "1",
         "PublicDescription": "Counts retired load instructions with at least one uop that missed in the L1 cache.",
         "SampleAfterValue": "200003",
         "UMask": "0x8"
@@ -569,7 +547,6 @@
         "Data_LA": "1",
         "EventCode": "0xd1",
         "EventName": "MEM_LOAD_RETIRED.L2_HIT",
-        "PEBS": "1",
         "PublicDescription": "Counts retired load instructions with L2 cache hits as data sources.",
         "SampleAfterValue": "200003",
         "UMask": "0x2"
@@ -580,7 +557,6 @@
         "Data_LA": "1",
         "EventCode": "0xd1",
         "EventName": "MEM_LOAD_RETIRED.L2_MISS",
-        "PEBS": "1",
         "PublicDescription": "Counts retired load instructions missed L2 cache as data sources.",
         "SampleAfterValue": "100021",
         "UMask": "0x10"
@@ -591,7 +567,6 @@
         "Data_LA": "1",
         "EventCode": "0xd1",
         "EventName": "MEM_LOAD_RETIRED.L3_HIT",
-        "PEBS": "1",
         "PublicDescription": "Counts retired load instructions with at least one uop that hit in the L3 cache.",
         "SampleAfterValue": "100021",
         "UMask": "0x4"
@@ -602,7 +577,6 @@
         "Data_LA": "1",
         "EventCode": "0xd1",
         "EventName": "MEM_LOAD_RETIRED.L3_MISS",
-        "PEBS": "1",
         "PublicDescription": "Counts retired load instructions with at least one uop that missed in the L3 cache.",
         "SampleAfterValue": "50021",
         "UMask": "0x20"
@@ -664,6 +638,16 @@
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
+    {
+        "BriefDescription": "Counts demand data reads that resulted in a snoop that hit in another core, which did not forward the data.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x2A,0x2B",
+        "EventName": "OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_NO_FWD",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x4003C0001",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
     {
         "BriefDescription": "Counts demand data reads that resulted in a snoop hit in another core's caches which forwarded the unmodified data to the requesting core.",
         "Counter": "0,1,2,3",
@@ -674,6 +658,26 @@
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
+    {
+        "BriefDescription": "Counts demand data reads that were supplied by a cache on a remote socket where a snoop hit a modified line in another core's caches which forwarded the data.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x2A,0x2B",
+        "EventName": "OCR.DEMAND_DATA_RD.REMOTE_CACHE.SNOOP_HITM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x1030000001",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts demand data reads that were supplied by a cache on a remote socket where a snoop hit in another core's caches which forwarded the unmodified data to the requesting core.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x2A,0x2B",
+        "EventName": "OCR.DEMAND_DATA_RD.REMOTE_CACHE.SNOOP_HIT_WITH_FWD",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x830000001",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
     {
         "BriefDescription": "Counts demand reads for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that hit in the L3 or were snooped from another core's caches on the same socket.",
         "Counter": "0,1,2,3",
@@ -704,6 +708,76 @@
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
+    {
+        "BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that resulted in a snoop hit a modified line in another core's caches which forwarded the data.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x2A,0x2B",
+        "EventName": "OCR.READS_TO_CORE.L3_HIT.SNOOP_HITM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x10003C4477",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by a cache on a remote socket where a snoop was sent and data was returned (Modified or Not Modified).",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x2A,0x2B",
+        "EventName": "OCR.READS_TO_CORE.REMOTE_CACHE.SNOOP_FWD",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x1830004477",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by a cache on a remote socket where a snoop hit a modified line in another core's caches which forwarded the data.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x2A,0x2B",
+        "EventName": "OCR.READS_TO_CORE.REMOTE_CACHE.SNOOP_HITM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x1030004477",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by a cache on a remote socket where a snoop hit in another core's caches which forwarded the unmodified data to the requesting core.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x2A,0x2B",
+        "EventName": "OCR.READS_TO_CORE.REMOTE_CACHE.SNOOP_HIT_WITH_FWD",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x830004477",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that hit a modified line in a distant L3 Cache or were snooped from a distant core's L1/L2 caches on this socket when the system is in SNC (sub-NUMA cluster) mode.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x2A,0x2B",
+        "EventName": "OCR.READS_TO_CORE.SNC_CACHE.HITM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x1008004477",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that either hit a non-modified line in a distant L3 Cache or were snooped from a distant core's L1/L2 caches on this socket when the system is in SNC (sub-NUMA cluster) mode.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x2A,0x2B",
+        "EventName": "OCR.READS_TO_CORE.SNC_CACHE.HIT_WITH_FWD",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x808004477",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts demand reads for ownership (RFO), hardware prefetch RFOs (which bring data to L2), and software prefetches for exclusive ownership (PREFETCHW) that hit to a (M)odified cacheline in the L3 or snoop filter.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x2A,0x2B",
+        "EventName": "OCR.RFO_TO_CORE.L3_HIT_M",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x1F80040022",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
     {
         "BriefDescription": "Any memory transaction that reached the SQ.",
         "Counter": "0,1,2,3",
tools/perf/pmu-events/arch/x86/graniterapids/counter.json +12 -12
index 250781a8ca64..137da7efa8b1 100644
@@ -19,6 +19,16 @@
         "CountersNumFixed": "0",
         "CountersNumGeneric": "4"
     },
+    {
+        "Unit": "CXLCM",
+        "CountersNumFixed": "0",
+        "CountersNumGeneric": 8
+    },
+    {
+        "Unit": "CXLDP",
+        "CountersNumFixed": "0",
+        "CountersNumGeneric": 4
+    },
     {
         "Unit": "B2HOT",
         "CountersNumFixed": "0",
@@ -52,26 +62,16 @@
     {
         "Unit": "PCU",
         "CountersNumFixed": "0",
-        "CountersNumGeneric": 4
+        "CountersNumGeneric": "4"
     },
     {
         "Unit": "CHACMS",
         "CountersNumFixed": "0",
-        "CountersNumGeneric": 4
+        "CountersNumGeneric": "4"
     },
     {
         "Unit": "MDF",
         "CountersNumFixed": "0",
         "CountersNumGeneric": "4"
-    },
-    {
-        "Unit": "CXLCM",
-        "CountersNumFixed": "0",
-        "CountersNumGeneric": 8
-    },
-    {
-        "Unit": "CXLDP",
-        "CountersNumFixed": "0",
-        "CountersNumGeneric": 4
     }
 ]
\ No newline at end of file
tools/perf/pmu-events/arch/x86/graniterapids/frontend.json +1 -23
index 663c1a0e55a2..dc81055941b1 100644
@@ -41,7 +41,6 @@
         "EventName": "FRONTEND_RETIRED.ANY_ANT",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x9",
-        "PEBS": "1",
         "PublicDescription": "Always Not Taken (ANT) conditional retired branches (no BTB entry and not mispredicted)",
         "SampleAfterValue": "100007",
         "UMask": "0x3"
@@ -53,7 +52,6 @@
         "EventName": "FRONTEND_RETIRED.ANY_DSB_MISS",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x1",
-        "PEBS": "1",
         "PublicDescription": "Counts retired Instructions that experienced DSB (Decode stream buffer i.e. the decoded instruction-cache) miss.",
         "SampleAfterValue": "100007",
         "UMask": "0x3"
@@ -65,7 +63,6 @@
         "EventName": "FRONTEND_RETIRED.DSB_MISS",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x11",
-        "PEBS": "1",
         "PublicDescription": "Number of retired Instructions that experienced a critical DSB (Decode stream buffer i.e. the decoded instruction-cache) miss. Critical means stalls were exposed to the back-end as a result of the DSB miss.",
         "SampleAfterValue": "100007",
         "UMask": "0x3"
@@ -77,7 +74,6 @@
         "EventName": "FRONTEND_RETIRED.ITLB_MISS",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x14",
-        "PEBS": "1",
         "PublicDescription": "Counts retired Instructions that experienced iTLB (Instruction TLB) true miss.",
         "SampleAfterValue": "100007",
         "UMask": "0x3"
@@ -89,7 +85,6 @@
         "EventName": "FRONTEND_RETIRED.L1I_MISS",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x12",
-        "PEBS": "1",
         "PublicDescription": "Counts retired Instructions who experienced Instruction L1 Cache true miss.",
         "SampleAfterValue": "100007",
         "UMask": "0x3"
@@ -101,7 +96,6 @@
         "EventName": "FRONTEND_RETIRED.L2_MISS",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x13",
-        "PEBS": "1",
         "PublicDescription": "Counts retired Instructions who experienced Instruction L2 Cache true miss.",
         "SampleAfterValue": "100007",
         "UMask": "0x3"
@@ -113,7 +107,6 @@
         "EventName": "FRONTEND_RETIRED.LATENCY_GE_1",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x600106",
-        "PEBS": "1",
         "PublicDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of at least 1 cycle which was not interrupted by a back-end stall.",
         "SampleAfterValue": "100007",
         "UMask": "0x3"
@@ -125,7 +118,6 @@
         "EventName": "FRONTEND_RETIRED.LATENCY_GE_128",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x608006",
-        "PEBS": "1",
         "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 128 cycles which was not interrupted by a back-end stall.",
         "SampleAfterValue": "100007",
         "UMask": "0x3"
@@ -137,7 +129,6 @@
         "EventName": "FRONTEND_RETIRED.LATENCY_GE_16",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x601006",
-        "PEBS": "1",
         "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 16 cycles. During this period the front-end delivered no uops.",
         "SampleAfterValue": "100007",
         "UMask": "0x3"
@@ -149,7 +140,6 @@
         "EventName": "FRONTEND_RETIRED.LATENCY_GE_2",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x600206",
-        "PEBS": "1",
         "PublicDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of at least 2 cycles which was not interrupted by a back-end stall.",
         "SampleAfterValue": "100007",
         "UMask": "0x3"
@@ -161,7 +151,6 @@
         "EventName": "FRONTEND_RETIRED.LATENCY_GE_256",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x610006",
-        "PEBS": "1",
         "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 256 cycles which was not interrupted by a back-end stall.",
         "SampleAfterValue": "100007",
         "UMask": "0x3"
@@ -173,7 +162,6 @@
         "EventName": "FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x100206",
-        "PEBS": "1",
         "PublicDescription": "Counts retired instructions that are delivered to the back-end after the front-end had at least 1 bubble-slot for a period of 2 cycles. A bubble-slot is an empty issue-pipeline slot while there was no RAT stall.",
         "SampleAfterValue": "100007",
         "UMask": "0x3"
@@ -185,7 +173,6 @@
         "EventName": "FRONTEND_RETIRED.LATENCY_GE_32",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x602006",
-        "PEBS": "1",
         "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 32 cycles. During this period the front-end delivered no uops.",
         "SampleAfterValue": "100007",
         "UMask": "0x3"
@@ -197,7 +184,6 @@
         "EventName": "FRONTEND_RETIRED.LATENCY_GE_4",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x600406",
-        "PEBS": "1",
         "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 4 cycles which was not interrupted by a back-end stall.",
         "SampleAfterValue": "100007",
         "UMask": "0x3"
@@ -209,7 +195,6 @@
         "EventName": "FRONTEND_RETIRED.LATENCY_GE_512",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x620006",
-        "PEBS": "1",
         "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 512 cycles which was not interrupted by a back-end stall.",
         "SampleAfterValue": "100007",
         "UMask": "0x3"
@@ -221,7 +206,6 @@
         "EventName": "FRONTEND_RETIRED.LATENCY_GE_64",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x604006",
-        "PEBS": "1",
         "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 64 cycles which was not interrupted by a back-end stall.",
         "SampleAfterValue": "100007",
         "UMask": "0x3"
@@ -233,7 +217,6 @@
         "EventName": "FRONTEND_RETIRED.LATENCY_GE_8",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x600806",
-        "PEBS": "1",
         "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 8 cycles. During this period the front-end delivered no uops.",
         "SampleAfterValue": "100007",
         "UMask": "0x3"
@@ -244,8 +227,7 @@
         "EventCode": "0xc6",
         "EventName": "FRONTEND_RETIRED.LATE_SWPF",
         "MSRIndex": "0x3F7",
-        "MSRValue": "0x9",
-        "PEBS": "1",
+        "MSRValue": "0xA",
         "PublicDescription": "Number of Instruction Cache demand miss in shadow of an on-going i-fetch cache-line triggered by PREFETCHIT0/1 instructions",
         "SampleAfterValue": "100007",
         "UMask": "0x3"
@@ -257,7 +239,6 @@
         "EventName": "FRONTEND_RETIRED.MISP_ANT",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x9",
-        "PEBS": "1",
         "PublicDescription": "ANT retired branches that got just mispredicted",
         "SampleAfterValue": "100007",
         "UMask": "0x2"
@@ -269,7 +250,6 @@
         "EventName": "FRONTEND_RETIRED.MS_FLOWS",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x8",
-        "PEBS": "1",
         "SampleAfterValue": "100007",
         "UMask": "0x3"
     },
@@ -280,7 +260,6 @@
         "EventName": "FRONTEND_RETIRED.STLB_MISS",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x15",
-        "PEBS": "1",
         "PublicDescription": "Counts retired Instructions that experienced STLB (2nd level TLB) true miss.",
         "SampleAfterValue": "100007",
         "UMask": "0x3"
@@ -292,7 +271,6 @@
         "EventName": "FRONTEND_RETIRED.UNKNOWN_BRANCH",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x17",
-        "PEBS": "1",
         "SampleAfterValue": "100007",
         "UMask": "0x3"
     },
tools/perf/pmu-events/arch/x86/graniterapids/gnr-metrics.json new file +2325 -0

2,325 lines not on this page · raw message

tools/perf/pmu-events/arch/x86/graniterapids/memory.json +110 -11

161 lines not on this page · raw message

tools/perf/pmu-events/arch/x86/graniterapids/metricgroups.json new file +145 -0

145 lines not on this page · raw message

tools/perf/pmu-events/arch/x86/graniterapids/other.json +109 -0

109 lines not on this page · raw message

tools/perf/pmu-events/arch/x86/graniterapids/pipeline.json +9 -31
index 0ef9daf64e2e..da6478607984 100644

Lines of this file are not shown. View the raw message.

tools/perf/pmu-events/arch/x86/graniterapids/uncore-cache.json +34 -14

48 lines not on this page · raw message

tools/perf/pmu-events/arch/x86/graniterapids/uncore-cxl.json +0 -2
index 383a5ba5a697..43e094c233cc 100644

Lines of this file are not shown. View the raw message.

tools/perf/pmu-events/arch/x86/graniterapids/uncore-interconnect.json +87 -0

87 lines not on this page · raw message

tools/perf/pmu-events/arch/x86/graniterapids/uncore-io.json +140 -140

280 lines not on this page · raw message

tools/perf/pmu-events/arch/x86/graniterapids/uncore-memory.json +121 -1

122 lines not on this page · raw message

tools/perf/pmu-events/arch/x86/graniterapids/uncore-power.json +98 -0

98 lines not on this page · raw message

tools/perf/pmu-events/arch/x86/mapfile.csv +1 -1
index 2cd9296f0f12..213f49e585bc 100644

Lines of this file are not shown. View the raw message.

The rest of this diff is not shown. View the raw message.

Signature · 1 line
2.48.1.502.g6dc24dfdaf-goog

Part of the diff is not shown here. View the raw message.

author reviewer
#12 lore raw

PATCH v8 12/24 perf vendor events: Update Haswell events/metrics

In reply to Ian Rogers

Update events from v35 to v36.
Update TMA metrics from 4.8 to 5.02.

Bring in the event updates v36:
https://github.com/intel/perfmon/commit/616ec6fc0315dac35c1bea0abc7f59e21a2d51c0

The TMA 5.02 update is from (with subsequent fixes):
https://github.com/intel/perfmon/commit/1d72913b2d938781fb28f3cc3507aaec5c22d782

Remove duplicate event UNC_CLOCK.SOCKET that was erroneously left in uncore-other.json.

---
 .../arch/x86/haswell/hsw-metrics.json         | 260 ++++++++++--------
 .../pmu-events/arch/x86/haswell/memory.json   |   2 +-
 .../arch/x86/haswell/metricgroups.json        |   5 +
 .../arch/x86/haswell/uncore-other.json        |  10 -
 tools/perf/pmu-events/arch/x86/mapfile.csv    |   2 +-
 5 files changed, 151 insertions(+), 128 deletions(-)
 delete mode 100644 tools/perf/pmu-events/arch/x86/haswell/uncore-other.json
tools/perf/pmu-events/arch/x86/haswell/hsw-metrics.json +144 -116
index b693c0b0cafe..0c1040b7e38c 100644
@@ -74,12 +74,12 @@
         "MetricExpr": "LD_BLOCKS_PARTIAL.ADDRESS_ALIAS / tma_info_thread_clks",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group",
         "MetricName": "tma_4k_aliasing",
-        "MetricThreshold": "tma_4k_aliasing > 0.2 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
-        "PublicDescription": "This metric estimates how often memory load accesses were aliased by preceding stores (in program order) with a 4K address offset. False match is possible; which incur a few cycles load re-issue. However; the short re-issue duration is often hidden by the out-of-order core and HW optimizations; hence a user may safely ignore a high value of this metric unless it manages to propagate up into parent nodes of the hierarchy (e.g. to L1_Bound).",
+        "MetricThreshold": "tma_4k_aliasing > 0.2 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "PublicDescription": "This metric estimates how often memory load accesses were aliased by preceding stores (in program order) with a 4K address offset. False match is possible; which incur a few cycles load re-issue. However; the short re-issue duration is often hidden by the out-of-order core and HW optimizations; hence a user may safely ignore a high value of this metric unless it manages to propagate up into parent nodes of the hierarchy (e.g. to L1_Bound)",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution ports for ALU operations.",
+        "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution ports for ALU operations",
         "MetricConstraint": "NO_GROUP_EVENTS_NMI",
         "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",
@@ -92,8 +92,8 @@
         "MetricExpr": "66 * OTHER_ASSISTS.ANY_WB_ASSIST / tma_info_thread_slots",
         "MetricGroup": "BvIO;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)",
-        "PublicDescription": "This metric estimates fraction of slots the CPU retired uops delivered by the Microcode_Sequencer as a result of Assists. Assists are long sequences of uops that are required in certain corner-cases for operations that cannot be handled natively by the execution pipeline. For example; when working with very small floating point values (so-called Denormals); the FP units are not set up to perform these operations natively. Instead; a sequence of instructions to perform the computation on the Denormals is injected into the pipeline. Since these microcode sequences might be dozens of uops long; Assists can be extremely deleterious to performance and they can be avoided in many cases. Sample with: OTHER_ASSISTS.ANY",
+        "MetricThreshold": "tma_assists > 0.1 & tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1",
+        "PublicDescription": "This metric estimates fraction of slots the CPU retired uops delivered by the Microcode_Sequencer as a result of Assists. Assists are long sequences of uops that are required in certain corner-cases for operations that cannot be handled natively by the execution pipeline. For example; when working with very small floating point values (so-called Denormals); the FP units are not set up to perform these operations natively. Instead; a sequence of instructions to perform the computation on the Denormals is injected into the pipeline. Since these microcode sequences might be dozens of uops long; Assists can be extremely deleterious to performance and they can be avoided in many cases. Sample with: OTHER_ASSISTS.ANY_WB_ASSIST",
         "ScaleUnit": "100%"
     },
     {
@@ -104,7 +104,7 @@
         "MetricName": "tma_backend_bound",
         "MetricThreshold": "tma_backend_bound > 0.2",
         "MetricgroupNoGroup": "TopdownL1",
-        "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound.",
+        "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound",
         "ScaleUnit": "100%"
     },
     {
@@ -114,7 +114,7 @@
         "MetricName": "tma_bad_speculation",
         "MetricThreshold": "tma_bad_speculation > 0.15",
         "MetricgroupNoGroup": "TopdownL1",
-        "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.",
+        "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example",
         "ScaleUnit": "100%"
     },
     {
@@ -125,7 +125,7 @@
         "MetricName": "tma_branch_mispredicts",
         "MetricThreshold": "tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15",
         "MetricgroupNoGroup": "TopdownL2",
-        "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction.  These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_info_bad_spec_branch_misprediction_cost, tma_mispredicts_resteers",
+        "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction.  These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: BR_MISP_RETIRED.ALL_BRANCHES",
         "ScaleUnit": "100%"
     },
     {
@@ -133,8 +133,8 @@
         "MetricExpr": "12 * (BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT + BACLEARS.ANY) / tma_info_thread_clks",
         "MetricGroup": "FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group",
         "MetricName": "tma_branch_resteers",
-        "MetricThreshold": "tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)",
-        "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers. Branch Resteers estimates the Frontend delay in fetching operations from corrected path; following all sorts of miss-predicted branches. For example; branchy code with lots of miss-predictions might get categorized under Branch Resteers. Note the value of this node may overlap with its siblings. Sample with: BR_MISP_RETIRED.ALL_BRANCHES",
+        "MetricThreshold": "tma_branch_resteers > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+        "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers. Branch Resteers estimates the Frontend delay in fetching operations from corrected path; following all sorts of miss-predicted branches. For example; branchy code with lots of miss-predictions might get categorized under Branch Resteers. Note the value of this node may overlap with its siblings. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_l3_hit_latency, tma_store_latency",
         "ScaleUnit": "100%"
     },
     {
@@ -143,18 +143,18 @@
         "MetricExpr": "max(0, tma_microcode_sequencer - tma_assists)",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_microcode_sequencer_group",
         "MetricName": "tma_cisc",
-        "MetricThreshold": "tma_cisc > 0.1 & (tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1)",
-        "PublicDescription": "This metric estimates fraction of cycles the CPU retired uops originated from CISC (complex instruction set computer) instruction. A CISC instruction has multiple uops that are required to perform the instruction's functionality as in the case of read-modify-write as an example. Since these instructions require multiple uops they may or may not imply sub-optimal use of machine resources.",
+        "MetricThreshold": "tma_cisc > 0.1 & tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1",
+        "PublicDescription": "This metric estimates fraction of cycles the CPU retired uops originated from CISC (complex instruction set computer) instruction. A CISC instruction has multiple uops that are required to perform the instruction's functionality as in the case of read-modify-write as an example. Since these instructions require multiple uops they may or may not imply sub-optimal use of machine resources",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses",
         "MetricConstraint": "NO_GROUP_EVENTS",
         "MetricExpr": "(60 * (MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.L3_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_RETIRED.L3_MISS))) + 43 * (MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.L3_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_RETIRED.L3_MISS)))) / tma_info_thread_clks",
-        "MetricGroup": "BvMS;DataSharing;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group",
+        "MetricGroup": "BvMS;DataSharing;LockCont;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))",
-        "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses. Contested accesses occur when data written by one Logical Processor are read by another Logical Processor on a different Physical Core. Examples of contested accesses include synchronizations such as locks; true data sharing such as modified locked variables; and false sharing. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM_PS;MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS_PS. Related metrics: tma_data_sharing, tma_false_sharing, tma_machine_clears, tma_remote_cache",
+        "MetricThreshold": "tma_contested_accesses > 0.05 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses. Contested accesses occur when data written by one Logical Processor are read by another Logical Processor on a different Physical Core. Examples of contested accesses include synchronizations such as locks; true data sharing such as modified locked variables; and false sharing. Sample with: MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM, MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS. Related metrics: tma_data_sharing, tma_false_sharing, tma_machine_clears",
         "ScaleUnit": "100%"
     },
     {
@@ -165,7 +165,7 @@
         "MetricName": "tma_core_bound",
         "MetricThreshold": "tma_core_bound > 0.1 & tma_backend_bound > 0.2",
         "MetricgroupNoGroup": "TopdownL2",
-        "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck.  Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations).",
+        "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck.  Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations)",
         "ScaleUnit": "100%"
     },
     {
@@ -174,8 +174,8 @@
         "MetricExpr": "43 * (MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.L3_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_RETIRED.L3_MISS))) / tma_info_thread_clks",
         "MetricGroup": "BvMS;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))",
-        "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses. Data shared by multiple Logical Processors (even just read shared) may cause increased access latency due to cache coherency. Excessive data sharing can drastically harm multithreaded performance. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_HIT_PS. Related metrics: tma_contested_accesses, tma_false_sharing, tma_machine_clears, tma_remote_cache",
+        "MetricThreshold": "tma_data_sharing > 0.05 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses. Data shared by multiple Logical Processors (even just read shared) may cause increased access latency due to cache coherency. Excessive data sharing can drastically harm multithreaded performance. Sample with: MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT. Related metrics: tma_contested_accesses, tma_false_sharing, tma_machine_clears",
         "ScaleUnit": "100%"
     },
     {
@@ -183,7 +183,7 @@
         "MetricExpr": "10 * ARITH.DIVIDER_UOPS / tma_info_core_core_clks",
         "MetricGroup": "BvCB;TopdownL3;tma_L3_group;tma_core_bound_group",
         "MetricName": "tma_divider",
-        "MetricThreshold": "tma_divider > 0.2 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)",
+        "MetricThreshold": "tma_divider > 0.2 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
         "PublicDescription": "This metric represents fraction of cycles where the Divider unit was active. Divide and square root instructions are performed by the Divider unit and can take considerably longer latency than integer or Floating Point addition; subtraction; or multiplication. Sample with: ARITH.DIVIDER_UOPS",
         "ScaleUnit": "100%"
     },
@@ -193,8 +193,8 @@
         "MetricExpr": "(1 - MEM_LOAD_UOPS_RETIRED.L3_HIT / (MEM_LOAD_UOPS_RETIRED.L3_HIT + 7 * MEM_LOAD_UOPS_RETIRED.L3_MISS)) * CYCLE_ACTIVITY.STALLS_L2_PENDING / tma_info_thread_clks",
         "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group",
         "MetricName": "tma_dram_bound",
-        "MetricThreshold": "tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)",
-        "PublicDescription": "This metric estimates how often the CPU was stalled on accesses to external memory (DRAM) by loads. Better caching can improve the latency and increase performance. Sample with: MEM_LOAD_UOPS_RETIRED.L3_MISS_PS",
+        "MetricThreshold": "tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "PublicDescription": "This metric estimates how often the CPU was stalled on accesses to external memory (DRAM) by loads. Better caching can improve the latency and increase performance. Sample with: MEM_LOAD_UOPS_RETIRED.L3_MISS",
         "ScaleUnit": "100%"
     },
     {
@@ -203,7 +203,7 @@
         "MetricGroup": "DSB;FetchBW;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group",
         "MetricName": "tma_dsb",
         "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.",
+        "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%"
     },
     {
@@ -211,7 +211,7 @@
         "MetricExpr": "DSB2MITE_SWITCHES.PENALTY_CYCLES / tma_info_thread_clks",
         "MetricGroup": "DSBmiss;FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueFB",
         "MetricName": "tma_dsb_switches",
-        "MetricThreshold": "tma_dsb_switches > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)",
+        "MetricThreshold": "tma_dsb_switches > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
         "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines. The DSB (decoded i-cache) is a Uop Cache where the front-end directly delivers Uops (micro operations) avoiding heavy x86 decoding. The DSB pipeline has shorter latency and delivered higher bandwidth than the MITE (legacy instruction decode pipeline). Switching between the two pipelines can cause penalties hence this metric measures the exposed penalty. Related metrics: tma_fetch_bandwidth, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp",
         "ScaleUnit": "100%"
     },
@@ -220,8 +220,8 @@
         "MetricExpr": "(8 * DTLB_LOAD_MISSES.STLB_HIT + DTLB_LOAD_MISSES.WALK_DURATION) / tma_info_thread_clks",
         "MetricGroup": "BvMT;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_UOPS_RETIRED.STLB_MISS_LOADS_PS. Related metrics: tma_dtlb_store",
+        "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_UOPS_RETIRED.STLB_MISS_LOADS. Related metrics: tma_dtlb_store",
         "ScaleUnit": "100%"
     },
     {
@@ -229,27 +229,27 @@
         "MetricExpr": "(8 * DTLB_STORE_MISSES.STLB_HIT + DTLB_STORE_MISSES.WALK_DURATION) / tma_info_thread_clks",
         "MetricGroup": "BvMT;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_UOPS_RETIRED.STLB_MISS_STORES_PS. Related metrics: tma_dtlb_load",
+        "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_UOPS_RETIRED.STLB_MISS_STORES. Related metrics: tma_dtlb_load",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "This metric roughly estimates how often CPU was handling synchronizations due to False Sharing",
         "MetricExpr": "60 * OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.HITM_OTHER_CORE / tma_info_thread_clks",
-        "MetricGroup": "BvMS;DataSharing;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_store_bound_group",
+        "MetricGroup": "BvMS;DataSharing;LockCont;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))",
-        "PublicDescription": "This metric roughly estimates how often CPU was handling synchronizations due to False Sharing. False Sharing is a multithreading hiccup; where multiple Logical Processors contend on different data-elements mapped into the same cache line. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM_PS;OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.SNOOP_HITM. Related metrics: tma_contested_accesses, tma_data_sharing, tma_machine_clears, tma_remote_cache",
+        "MetricThreshold": "tma_false_sharing > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "PublicDescription": "This metric roughly estimates how often CPU was handling synchronizations due to False Sharing. False Sharing is a multithreading hiccup; where multiple Logical Processors contend on different data-elements mapped into the same cache line. Sample with: MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM, OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.HITM_OTHER_CORE. Related metrics: tma_contested_accesses, tma_data_sharing, tma_machine_clears",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed",
         "MetricConstraint": "NO_GROUP_EVENTS",
-        "MetricExpr": "tma_info_memory_load_miss_real_latency * cpu@L1D_PEND_MISS.REQUEST_FB_FULL\\,cmask\\=1@ / tma_info_thread_clks",
-        "MetricGroup": "BvMS;MemoryBW;TopdownL4;tma_L4_group;tma_issueBW;tma_issueSL;tma_issueSmSt;tma_l1_bound_group",
+        "MetricExpr": "tma_info_memory_load_miss_real_latency * cpu@L1D_PEND_MISS.REQUEST_FB_FULL\\,cmask\\=0x1@ / tma_info_thread_clks",
+        "MetricGroup": "BvMB;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_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_system_dram_bw_use, tma_mem_bandwidth, tma_sq_full, tma_store_latency",
         "ScaleUnit": "100%"
     },
     {
@@ -279,33 +279,33 @@
         "MetricName": "tma_frontend_bound",
         "MetricThreshold": "tma_frontend_bound > 0.15",
         "MetricgroupNoGroup": "TopdownL1",
-        "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound.",
+        "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences",
+        "BriefDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations , instructions that require two or more uops or micro-coded sequences",
         "MetricExpr": "tma_microcode_sequencer",
         "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group",
         "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. ([ICL+] Note this may overcount due to approximation using indirect events; [ADL+] .)",
+        "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.",
+        "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to instruction cache misses",
         "MetricExpr": "ICACHE.IFDATA_STALL / tma_info_thread_clks",
         "MetricGroup": "BigFootprint;BvBC;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)",
+        "MetricThreshold": "tma_icache_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "Instructions per retired mispredicts for indirect CALL or JMP branches (lower number means higher occurrence rate).",
+        "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 * BR_MISP_EXEC.INDIRECT)",
         "MetricGroup": "Bad;BrMispredicts",
         "MetricName": "tma_info_bad_spec_ipmisp_indirect",
-        "MetricThreshold": "tma_info_bad_spec_ipmisp_indirect < 1e3"
+        "MetricThreshold": "tma_info_bad_spec_ipmisp_indirect < 1000"
     },
     {
         "BriefDescription": "Number of Instructions per non-speculative Branch Misprediction (JEClear) (lower number means higher occurrence rate)",
@@ -316,7 +316,7 @@
     },
     {
         "BriefDescription": "Core actual clocks when any Logical Processor is active on the Physical Core",
-        "MetricExpr": "(CPU_CLK_UNHALTED.THREAD / 2 * (1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK) if #core_wide < 1 else (CPU_CLK_UNHALTED.THREAD_ANY / 2 if #SMT_on else tma_info_thread_clks))",
+        "MetricExpr": "(CPU_CLK_UNHALTED.THREAD_ANY / 2 if #SMT_on else tma_info_thread_clks)",
         "MetricGroup": "SMT",
         "MetricName": "tma_info_core_core_clks"
     },
@@ -328,7 +328,7 @@
     },
     {
         "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is execution) per thread (logical-processor)",
-        "MetricExpr": "(UOPS_EXECUTED.CORE / 2 / (cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ / 2 if #SMT_on else cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@) if #SMT_on else UOPS_EXECUTED.CORE / (cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ / 2 if #SMT_on else cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@))",
+        "MetricExpr": "(UOPS_EXECUTED.CORE / 2 / (cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x1@ / 2 if #SMT_on else cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x1@) if #SMT_on else UOPS_EXECUTED.CORE / (cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x1@ / 2 if #SMT_on else cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x1@))",
         "MetricGroup": "Backend;Cor;Pipeline;PortsUtil",
         "MetricName": "tma_info_core_ilp"
     },
@@ -347,7 +347,13 @@
         "MetricName": "tma_info_frontend_ipunknown_branch"
     },
     {
-        "BriefDescription": "Branch instructions per taken branch.",
+        "BriefDescription": "Taken Branches retired Per Cycle",
+        "MetricExpr": "BR_INST_RETIRED.NEAR_TAKEN / tma_info_thread_clks",
+        "MetricGroup": "Branches;FetchBW",
+        "MetricName": "tma_info_frontend_tbpc"
+    },
+    {
+        "BriefDescription": "Branch instructions per taken branch",
         "MetricExpr": "BR_INST_RETIRED.ALL_BRANCHES / BR_INST_RETIRED.NEAR_TAKEN",
         "MetricGroup": "Branches;Fed;PGO",
         "MetricName": "tma_info_inst_mix_bptkbranch"
@@ -392,7 +398,7 @@
         "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_TAKEN",
         "MetricGroup": "Branches;Fed;FetchBW;Frontend;PGO;tma_issueFB",
         "MetricName": "tma_info_inst_mix_iptb",
-        "MetricThreshold": "tma_info_inst_mix_iptb < 9",
+        "MetricThreshold": "tma_info_inst_mix_iptb < 4 * 2 + 1",
         "PublicDescription": "Instructions per taken branch. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_frontend_dsb_coverage, tma_lcp"
     },
     {
@@ -415,7 +421,7 @@
     },
     {
         "BriefDescription": "Average per-thread data fill bandwidth to the L1 data cache [GB / sec]",
-        "MetricExpr": "64 * L1D.REPLACEMENT / 1e9 / duration_time",
+        "MetricExpr": "64 * L1D.REPLACEMENT / 1e9 / tma_info_system_time",
         "MetricGroup": "Mem;MemoryBW",
         "MetricName": "tma_info_memory_l1d_cache_fill_bw"
     },
@@ -427,7 +433,7 @@
     },
     {
         "BriefDescription": "Average per-thread data fill bandwidth to the L2 cache [GB / sec]",
-        "MetricExpr": "64 * L2_LINES_IN.ALL / 1e9 / duration_time",
+        "MetricExpr": "64 * L2_LINES_IN.ALL / 1e9 / tma_info_system_time",
         "MetricGroup": "Mem;MemoryBW",
         "MetricName": "tma_info_memory_l2_cache_fill_bw"
     },
@@ -445,7 +451,7 @@
     },
     {
         "BriefDescription": "Average per-thread data fill bandwidth to the L3 cache [GB / sec]",
-        "MetricExpr": "64 * LONGEST_LAT_CACHE.MISS / 1e9 / duration_time",
+        "MetricExpr": "64 * LONGEST_LAT_CACHE.MISS / 1e9 / tma_info_system_time",
         "MetricGroup": "Mem;MemoryBW",
         "MetricName": "tma_info_memory_l3_cache_fill_bw"
     },
@@ -464,7 +470,7 @@
     {
         "BriefDescription": "Average Latency for L2 cache miss demand Loads",
         "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD / OFFCORE_REQUESTS.DEMAND_DATA_RD",
-        "MetricGroup": "Memory_Lat;Offcore",
+        "MetricGroup": "LockCont;Memory_Lat;Offcore",
         "MetricName": "tma_info_memory_latency_load_l2_miss_latency"
     },
     {
@@ -496,14 +502,14 @@
         "MetricThreshold": "tma_info_memory_tlb_page_walks_utilization > 0.5"
     },
     {
-        "BriefDescription": "Average number of Uops retired in cycles where at least one uop has retired.",
-        "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / cpu@UOPS_RETIRED.RETIRE_SLOTS\\,cmask\\=1@",
+        "BriefDescription": "Average number of Uops retired in cycles where at least one uop has retired",
+        "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / cpu@UOPS_RETIRED.RETIRE_SLOTS\\,cmask\\=0x1@",
         "MetricGroup": "Pipeline;Ret",
         "MetricName": "tma_info_pipeline_retire"
     },
     {
         "BriefDescription": "Measured Average Core Frequency for unhalted processors [GHz]",
-        "MetricExpr": "tma_info_system_turbo_utilization * TSC / 1e9 / duration_time",
+        "MetricExpr": "tma_info_system_turbo_utilization * TSC / 1e9 / tma_info_system_time",
         "MetricGroup": "Power;Summary",
         "MetricName": "tma_info_system_core_frequency"
     },
@@ -521,7 +527,7 @@
     },
     {
         "BriefDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]",
-        "MetricExpr": "64 * (UNC_ARB_TRK_REQUESTS.ALL + UNC_ARB_COH_TRK_REQUESTS.ALL) / 1e6 / duration_time / 1e3",
+        "MetricExpr": "64 * (UNC_ARB_TRK_REQUESTS.ALL + UNC_ARB_COH_TRK_REQUESTS.ALL) / 1e6 / tma_info_system_time / 1e3",
         "MetricGroup": "HPC;MemOffcore;MemoryBW;SoC;tma_issueBW",
         "MetricName": "tma_info_system_dram_bw_use",
         "PublicDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]. Related metrics: tma_fb_full, tma_mem_bandwidth, tma_sq_full"
@@ -531,13 +537,14 @@
         "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.FAR_BRANCH:u",
         "MetricGroup": "Branches;OS",
         "MetricName": "tma_info_system_ipfarbranch",
-        "MetricThreshold": "tma_info_system_ipfarbranch < 1e6"
+        "MetricThreshold": "tma_info_system_ipfarbranch < 1000000"
     },
     {
         "BriefDescription": "Cycles Per Instruction for the Operating System (OS) Kernel mode",
         "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P:k / INST_RETIRED.ANY_P:k",
         "MetricGroup": "OS",
-        "MetricName": "tma_info_system_kernel_cpi"
+        "MetricName": "tma_info_system_kernel_cpi",
+        "ScaleUnit": "1per_instr"
     },
     {
         "BriefDescription": "Fraction of cycles spent in the Operating System (OS) Kernel mode",
@@ -546,6 +553,19 @@
         "MetricName": "tma_info_system_kernel_utilization",
         "MetricThreshold": "tma_info_system_kernel_utilization > 0.05"
     },
+    {
+        "BriefDescription": "PerfMon Event Multiplexing accuracy indicator",
+        "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P / CPU_CLK_UNHALTED.THREAD",
+        "MetricGroup": "Summary",
+        "MetricName": "tma_info_system_mux",
+        "MetricThreshold": "tma_info_system_mux > 1.1 | tma_info_system_mux < 0.9"
+    },
+    {
+        "BriefDescription": "Total package Power in Watts",
+        "MetricExpr": "power@energy\\-pkg@ * 61 / (tma_info_system_time * 1e6)",
+        "MetricGroup": "Power;SoC",
+        "MetricName": "tma_info_system_power"
+    },
     {
         "BriefDescription": "Fraction of cycles where both hardware Logical Processors were active",
         "MetricExpr": "(1 - CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / (CPU_CLK_UNHALTED.REF_XCLK_ANY / 2) if #SMT_on else 0)",
@@ -558,6 +578,13 @@
         "MetricGroup": "SoC",
         "MetricName": "tma_info_system_socket_clks"
     },
+    {
+        "BriefDescription": "Run duration time in seconds",
+        "MetricExpr": "duration_time",
+        "MetricGroup": "Summary",
+        "MetricName": "tma_info_system_time",
+        "MetricThreshold": "tma_info_system_time < 1"
+    },
     {
         "BriefDescription": "Average Frequency Utilization relative nominal frequency",
         "MetricExpr": "tma_info_thread_clks / CPU_CLK_UNHALTED.REF_TSC",
@@ -565,7 +592,7 @@
         "MetricName": "tma_info_system_turbo_utilization"
     },
     {
-        "BriefDescription": "Per-Logical Processor actual clocks when the Logical Processor is active.",
+        "BriefDescription": "Per-Logical Processor actual clocks when the Logical Processor is active",
         "MetricExpr": "CPU_CLK_UNHALTED.THREAD",
         "MetricGroup": "Pipeline",
         "MetricName": "tma_info_thread_clks"
@@ -574,7 +601,8 @@
         "BriefDescription": "Cycles Per Instruction (per Logical Processor)",
         "MetricExpr": "1 / tma_info_thread_ipc",
         "MetricGroup": "Mem;Pipeline",
-        "MetricName": "tma_info_thread_cpi"
+        "MetricName": "tma_info_thread_cpi",
+        "ScaleUnit": "1per_instr"
     },
     {
         "BriefDescription": "Instructions Per Cycle (per Logical Processor)",
@@ -600,24 +628,24 @@
         "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / BR_INST_RETIRED.NEAR_TAKEN",
         "MetricGroup": "Branches;Fed;FetchBW",
         "MetricName": "tma_info_thread_uptb",
-        "MetricThreshold": "tma_info_thread_uptb < 6"
+        "MetricThreshold": "tma_info_thread_uptb < 4 * 1.5"
     },
     {
         "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to Instruction TLB (ITLB) misses",
         "MetricExpr": "(14 * ITLB_MISSES.STLB_HIT + ITLB_MISSES.WALK_DURATION) / tma_info_thread_clks",
         "MetricGroup": "BigFootprint;BvBC;FetchLat;MemoryTLB;TopdownL3;tma_L3_group;tma_fetch_latency_group",
         "MetricName": "tma_itlb_misses",
-        "MetricThreshold": "tma_itlb_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)",
+        "MetricThreshold": "tma_itlb_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 TLB (ITLB) misses. Sample with: ITLB_MISSES.WALK_COMPLETED",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric estimates how often the CPU was stalled without loads missing the L1 data cache",
+        "BriefDescription": "This metric estimates how often the CPU was stalled without loads missing the L1 Data (L1D) cache",
         "MetricExpr": "max((min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.STALLS_LDM_PENDING) - CYCLE_ACTIVITY.STALLS_L1D_PENDING) / tma_info_thread_clks, 0)",
         "MetricGroup": "CacheHits;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_issueL1;tma_issueMC;tma_memory_bound_group",
         "MetricName": "tma_l1_bound",
-        "MetricThreshold": "tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)",
-        "PublicDescription": "This metric estimates how often the CPU was stalled without loads missing the L1 data cache.  The L1 data cache typically has the shortest latency.  However; in certain cases like loads blocked on older stores; a load might suffer due to high latency even though it is being satisfied by the L1. Another example is loads who miss in the TLB. These cases are characterized by execution unit stalls; while some non-completed demand load lives in the machine without having that demand load missing the L1 cache. Sample with: MEM_LOAD_UOPS_RETIRED.L1_HIT_PS;MEM_LOAD_UOPS_RETIRED.HIT_LFB_PS. Related metrics: tma_clears_resteers, tma_machine_clears, tma_microcode_sequencer, tma_ms_switches, tma_ports_utilized_1",
+        "MetricThreshold": "tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "PublicDescription": "This metric estimates how often the CPU was stalled without loads missing the L1 Data (L1D) cache.  The L1D cache typically has the shortest latency.  However; in certain cases like loads blocked on older stores; a load might suffer due to high latency even though it is being satisfied by the L1D. Another example is loads who miss in the TLB. These cases are characterized by execution unit stalls; while some non-completed demand load lives in the machine without having that demand load missing the L1 cache. Sample with: MEM_LOAD_UOPS_RETIRED.L1_HIT. Related metrics: tma_machine_clears, tma_microcode_sequencer, tma_ms_switches, tma_ports_utilized_1",
         "ScaleUnit": "100%"
     },
     {
@@ -625,8 +653,8 @@
         "MetricExpr": "(CYCLE_ACTIVITY.STALLS_L1D_PENDING - CYCLE_ACTIVITY.STALLS_L2_PENDING) / tma_info_thread_clks",
         "MetricGroup": "BvML;CacheHits;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group",
         "MetricName": "tma_l2_bound",
-        "MetricThreshold": "tma_l2_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)",
-        "PublicDescription": "This metric estimates how often the CPU was stalled due to L2 cache accesses by loads.  Avoiding cache misses (i.e. L1 misses/L2 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_UOPS_RETIRED.L2_HIT_PS",
+        "MetricThreshold": "tma_l2_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "PublicDescription": "This metric estimates how often the CPU was stalled due to L2 cache accesses by loads.  Avoiding cache misses (i.e. L1 misses/L2 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_UOPS_RETIRED.L2_HIT",
         "ScaleUnit": "100%"
     },
     {
@@ -635,8 +663,8 @@
         "MetricExpr": "MEM_LOAD_UOPS_RETIRED.L3_HIT / (MEM_LOAD_UOPS_RETIRED.L3_HIT + 7 * MEM_LOAD_UOPS_RETIRED.L3_MISS) * CYCLE_ACTIVITY.STALLS_L2_PENDING / tma_info_thread_clks",
         "MetricGroup": "CacheHits;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group",
         "MetricName": "tma_l3_bound",
-        "MetricThreshold": "tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)",
-        "PublicDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core.  Avoiding cache misses (i.e. L2 misses/L3 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_UOPS_RETIRED.L3_HIT_PS",
+        "MetricThreshold": "tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "PublicDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core.  Avoiding cache misses (i.e. L2 misses/L3 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_UOPS_RETIRED.L3_HIT",
         "ScaleUnit": "100%"
     },
     {
@@ -645,8 +673,8 @@
         "MetricExpr": "29 * (MEM_LOAD_UOPS_RETIRED.L3_HIT * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.L3_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_RETIRED.L3_MISS))) / tma_info_thread_clks",
         "MetricGroup": "BvML;MemoryLat;TopdownL4;tma_L4_group;tma_issueLat;tma_l3_bound_group",
         "MetricName": "tma_l3_hit_latency",
-        "MetricThreshold": "tma_l3_hit_latency > 0.1 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
-        "PublicDescription": "This metric estimates fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited).  Avoiding private cache misses (i.e. L2 misses/L3 hits) will improve the latency; reduce contention with sibling physical cores and increase performance.  Note the value of this node may overlap with its siblings. Sample with: MEM_LOAD_UOPS_RETIRED.L3_HIT_PS. Related metrics: tma_mem_latency",
+        "MetricThreshold": "tma_l3_hit_latency > 0.1 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "PublicDescription": "This metric estimates fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited).  Avoiding private cache misses (i.e. L2 misses/L3 hits) will improve the latency; reduce contention with sibling physical cores and increase performance.  Note the value of this node may overlap with its siblings. Sample with: MEM_LOAD_UOPS_RETIRED.L3_HIT. Related metrics: tma_branch_resteers, tma_mem_latency, tma_store_latency",
         "ScaleUnit": "100%"
     },
     {
@@ -654,18 +682,18 @@
         "MetricExpr": "ILD_STALL.LCP / tma_info_thread_clks",
         "MetricGroup": "FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueFB",
         "MetricName": "tma_lcp",
-        "MetricThreshold": "tma_lcp > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)",
-        "PublicDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs). Using proper compiler flags or Intel Compiler by default will certainly avoid this. #Link: Optimization Guide about LCP BKMs. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb",
+        "MetricThreshold": "tma_lcp > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+        "PublicDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs). Using proper compiler flags or Intel Compiler by default will certainly avoid this. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation)",
+        "BriefDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations , instructions that require no more than one uop (micro-operation)",
         "MetricExpr": "tma_retiring - tma_heavy_operations",
         "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group",
         "MetricName": "tma_light_operations",
         "MetricThreshold": "tma_light_operations > 0.6",
         "MetricgroupNoGroup": "TopdownL2",
-        "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized code running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. ([ICL+] Note this may undercount due to approximation using indirect events; [ADL+] .). Sample with: INST_RETIRED.PREC_DIST",
+        "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations , instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized code running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. ([ICL+] Note this may undercount due to approximation using indirect events; [ADL+] .). Sample with: INST_RETIRED.PREC_DIST",
         "ScaleUnit": "100%"
     },
     {
@@ -682,10 +710,10 @@
         "BriefDescription": "This metric represents fraction of cycles the CPU spent handling cache misses due to lock operations",
         "MetricConstraint": "NO_GROUP_EVENTS",
         "MetricExpr": "MEM_UOPS_RETIRED.LOCK_LOADS / MEM_UOPS_RETIRED.ALL_STORES * min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO) / tma_info_thread_clks",
-        "MetricGroup": "Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_l1_bound_group",
+        "MetricGroup": "LockCont;Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_l1_bound_group",
         "MetricName": "tma_lock_latency",
-        "MetricThreshold": "tma_lock_latency > 0.2 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
-        "PublicDescription": "This metric represents fraction of cycles the CPU spent handling cache misses due to lock operations. Due to the microarchitecture handling of locks; they are classified as L1_Bound regardless of what memory source satisfied them. Sample with: MEM_UOPS_RETIRED.LOCK_LOADS_PS. Related metrics: tma_store_latency",
+        "MetricThreshold": "tma_lock_latency > 0.2 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "PublicDescription": "This metric represents fraction of cycles the CPU spent handling cache misses due to lock operations. Due to the microarchitecture handling of locks; they are classified as L1_Bound regardless of what memory source satisfied them. Sample with: MEM_UOPS_RETIRED.LOCK_LOADS. Related metrics: tma_store_latency",
         "ScaleUnit": "100%"
     },
     {
@@ -696,15 +724,15 @@
         "MetricName": "tma_machine_clears",
         "MetricThreshold": "tma_machine_clears > 0.1 & tma_bad_speculation > 0.15",
         "MetricgroupNoGroup": "TopdownL2",
-        "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears.  These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT. Related metrics: tma_clears_resteers, tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_l1_bound, tma_microcode_sequencer, tma_ms_switches, tma_remote_cache",
+        "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears.  These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT. Related metrics: tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_l1_bound, tma_microcode_sequencer, tma_ms_switches",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory - DRAM ([SPR-HBM] and/or HBM)",
-        "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, cpu@OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD\\,cmask\\=6@) / tma_info_thread_clks",
-        "MetricGroup": "BvMS;MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueBW",
+        "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, cpu@OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD\\,cmask\\=0x6@) / tma_info_thread_clks",
+        "MetricGroup": "BvMB;MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueBW",
         "MetricName": "tma_mem_bandwidth",
-        "MetricThreshold": "tma_mem_bandwidth > 0.2 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+        "MetricThreshold": "tma_mem_bandwidth > 0.2 & tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
         "PublicDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory - DRAM ([SPR-HBM] and/or HBM).  The underlying heuristic assumes that a similar off-core traffic is generated by all IA cores. This metric does not aggregate non-data-read requests by this logical processor; requests from other IA Logical Processors/Physical Cores/sockets; or other non-IA devices like GPU; hence the maximum external memory bandwidth limits may or may not be approached when this metric is flagged (see Uncore counters for that). Related metrics: tma_fb_full, tma_info_system_dram_bw_use, tma_sq_full",
         "ScaleUnit": "100%"
     },
@@ -713,19 +741,19 @@
         "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD) / tma_info_thread_clks - tma_mem_bandwidth",
         "MetricGroup": "BvML;MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueLat",
         "MetricName": "tma_mem_latency",
-        "MetricThreshold": "tma_mem_latency > 0.1 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+        "MetricThreshold": "tma_mem_latency > 0.1 & tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
         "PublicDescription": "This metric estimates fraction of cycles where the performance was likely hurt due to latency from external memory - DRAM ([SPR-HBM] and/or HBM).  This metric does not aggregate requests from other Logical Processors/Physical Cores/sockets (see Uncore counters for that). Related metrics: tma_l3_hit_latency",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck",
         "MetricConstraint": "NO_GROUP_EVENTS",
-        "MetricExpr": "((min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.STALLS_LDM_PENDING) + RESOURCE_STALLS.SB) / (min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.CYCLES_NO_EXECUTE) + (cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ - (cpu@UOPS_EXECUTED.CORE\\,cmask\\=3@ if tma_info_thread_ipc > 1.8 else cpu@UOPS_EXECUTED.CORE\\,cmask\\=2@)) / 2 - (RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else 0) + RESOURCE_STALLS.SB) if #SMT_on else min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.CYCLES_NO_EXECUTE) + cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ - (cpu@UOPS_EXECUTED.CORE\\,cmask\\=3@ if tma_info_thread_ipc > 1.8 else cpu@UOPS_EXECUTED.CORE\\,cmask\\=2@) - (RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else 0) + RESOURCE_STALLS.SB) * tma_backend_bound",
+        "MetricExpr": "(min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.STALLS_LDM_PENDING) + RESOURCE_STALLS.SB) / (min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.CYCLES_NO_EXECUTE) + (cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x1@ - (cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x3@ if tma_info_thread_ipc > 1.8 else cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x2@)) / 2 - (RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else 0) + RESOURCE_STALLS.SB if #SMT_on else min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.CYCLES_NO_EXECUTE) + cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x1@ - (cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x3@ if tma_info_thread_ipc > 1.8 else cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x2@) - (RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else 0) + RESOURCE_STALLS.SB) * tma_backend_bound",
         "MetricGroup": "Backend;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group",
         "MetricName": "tma_memory_bound",
         "MetricThreshold": "tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
         "MetricgroupNoGroup": "TopdownL2",
-        "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck.  Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two).",
+        "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck.  Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two)",
         "ScaleUnit": "100%"
     },
     {
@@ -734,7 +762,7 @@
         "MetricGroup": "MicroSeq;TopdownL3;tma_L3_group;tma_heavy_operations_group;tma_issueMC;tma_issueMS",
         "MetricName": "tma_microcode_sequencer",
         "MetricThreshold": "tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1",
-        "PublicDescription": "This metric represents fraction of slots the CPU was retiring uops fetched by the Microcode Sequencer (MS) unit.  The MS is used for CISC instructions not supported by the default decoders (like repeat move strings; or CPUID); or by microcode assists used to address some operation modes (like in Floating Point assists). These cases can often be avoided. Sample with: IDQ.MS_UOPS. Related metrics: tma_clears_resteers, tma_l1_bound, tma_machine_clears, tma_ms_switches",
+        "PublicDescription": "This metric represents fraction of slots the CPU was retiring uops fetched by the Microcode Sequencer (MS) unit.  The MS is used for CISC instructions not supported by the default decoders (like repeat move strings; or CPUID); or by microcode assists used to address some operation modes (like in Floating Point assists). These cases can often be avoided. Sample with: IDQ.MS_UOPS. Related metrics: tma_l1_bound, tma_machine_clears, tma_ms_switches",
         "ScaleUnit": "100%"
     },
     {
@@ -743,7 +771,7 @@
         "MetricGroup": "DSBmiss;FetchBW;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group",
         "MetricName": "tma_mite",
         "MetricThreshold": "tma_mite > 0.1 & tma_fetch_bandwidth > 0.2",
-        "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to the MITE pipeline (the legacy decode pipeline). This pipeline is used for code that was not pre-cached in the DSB or LSD. For example; inefficiencies due to asymmetric decoders; use of long immediate or LCP can manifest as MITE fetch bandwidth bottleneck.",
+        "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to the MITE pipeline (the legacy decode pipeline). This pipeline is used for code that was not pre-cached in the DSB or LSD. For example; inefficiencies due to asymmetric decoders; use of long immediate or LCP can manifest as MITE fetch bandwidth bottleneck",
         "ScaleUnit": "100%"
     },
     {
@@ -751,8 +779,8 @@
         "MetricExpr": "2 * IDQ.MS_SWITCHES / tma_info_thread_clks",
         "MetricGroup": "FetchLat;MicroSeq;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueMC;tma_issueMS;tma_issueMV;tma_issueSO",
         "MetricName": "tma_ms_switches",
-        "MetricThreshold": "tma_ms_switches > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)",
-        "PublicDescription": "This metric estimates the fraction of cycles when the CPU was stalled due to switches of uop delivery to the Microcode Sequencer (MS). Commonly used instructions are optimized for delivery by the DSB (decoded i-cache) or MITE (legacy instruction decode) pipelines. Certain operations cannot be handled natively by the execution pipeline; and must be performed by microcode (small programs injected into the execution stream). Switching to the MS too often can negatively impact performance. The MS is designated to deliver long uop flows required by CISC instructions like CPUID; or uncommon conditions like Floating Point Assists when dealing with Denormals. Sample with: IDQ.MS_SWITCHES. Related metrics: tma_clears_resteers, tma_l1_bound, tma_machine_clears, tma_microcode_sequencer, tma_mixing_vectors, tma_serializing_operation",
+        "MetricThreshold": "tma_ms_switches > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+        "PublicDescription": "This metric estimates the fraction of cycles when the CPU was stalled due to switches of uop delivery to the Microcode Sequencer (MS). Commonly used instructions are optimized for delivery by the DSB (decoded i-cache) or MITE (legacy instruction decode) pipelines. Certain operations cannot be handled natively by the execution pipeline; and must be performed by microcode (small programs injected into the execution stream). Switching to the MS too often can negatively impact performance. The MS is designated to deliver long uop flows required by CISC instructions like CPUID; or uncommon conditions like Floating Point Assists when dealing with Denormals. Sample with: IDQ.MS_SWITCHES. Related metrics: tma_l1_bound, tma_machine_clears, tma_microcode_sequencer",
         "ScaleUnit": "100%"
     },
     {
@@ -761,7 +789,7 @@
         "MetricGroup": "Compute;TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P",
         "MetricName": "tma_port_0",
         "MetricThreshold": "tma_port_0 > 0.6",
-        "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 0 ([SNB+] ALU; [HSW+] ALU and 2nd branch). Sample with: UOPS_DISPATCHED_PORT.PORT_0. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2",
+        "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 0 ([SNB+] ALU; [HSW+] ALU and 2nd branch). Sample with: UOPS_DISPATCHED_PORT.PORT_0. Related metrics: tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2",
         "ScaleUnit": "100%"
     },
     {
@@ -770,7 +798,7 @@
         "MetricGroup": "TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P",
         "MetricName": "tma_port_1",
         "MetricThreshold": "tma_port_1 > 0.6",
-        "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 1 (ALU). Sample with: UOPS_DISPATCHED_PORT.PORT_1. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_5, tma_port_6, tma_ports_utilized_2",
+        "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 1 (ALU). Sample with: UOPS_DISPATCHED_PORT.PORT_1. Related metrics: tma_port_0, tma_port_5, tma_port_6, tma_ports_utilized_2",
         "ScaleUnit": "100%"
     },
     {
@@ -806,7 +834,7 @@
         "MetricGroup": "TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P",
         "MetricName": "tma_port_5",
         "MetricThreshold": "tma_port_5 > 0.6",
-        "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 5 ([SNB+] Branches and ALU; [HSW+] ALU). Sample with: UOPS_DISPATCHED.PORT_5. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_6, tma_ports_utilized_2",
+        "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 5 ([SNB+] Branches and ALU; [HSW+] ALU). Sample with: UOPS_DISPATCHED_PORT.PORT_5. Related metrics: tma_port_0, tma_port_1, tma_port_6, tma_ports_utilized_2",
         "ScaleUnit": "100%"
     },
     {
@@ -815,7 +843,7 @@
         "MetricGroup": "TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P",
         "MetricName": "tma_port_6",
         "MetricThreshold": "tma_port_6 > 0.6",
-        "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 6 ([HSW+] Primary Branch and simple ALU). Sample with: UOPS_DISPATCHED_PORT.PORT_6. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_ports_utilized_2",
+        "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 6 ([HSW+] Primary Branch and simple ALU). Sample with: UOPS_DISPATCHED_PORT.PORT_1. Related metrics: tma_port_0, tma_port_1, tma_port_5, tma_ports_utilized_2",
         "ScaleUnit": "100%"
     },
     {
@@ -830,46 +858,46 @@
     {
         "BriefDescription": "This metric estimates fraction of cycles the CPU performance was potentially limited due to Core computation issues (non divider-related)",
         "MetricConstraint": "NO_GROUP_EVENTS",
-        "MetricExpr": "(min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.CYCLES_NO_EXECUTE) + (cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ - (cpu@UOPS_EXECUTED.CORE\\,cmask\\=3@ if tma_info_thread_ipc > 1.8 else cpu@UOPS_EXECUTED.CORE\\,cmask\\=2@)) / 2 - (RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else 0) + RESOURCE_STALLS.SB if #SMT_on else min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.CYCLES_NO_EXECUTE) + cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ - (cpu@UOPS_EXECUTED.CORE\\,cmask\\=3@ if tma_info_thread_ipc > 1.8 else cpu@UOPS_EXECUTED.CORE\\,cmask\\=2@) - (RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else 0) + RESOURCE_STALLS.SB - RESOURCE_STALLS.SB - min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.STALLS_LDM_PENDING)) / tma_info_thread_clks",
+        "MetricExpr": "((min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.CYCLES_NO_EXECUTE) + (cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x1@ - (cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x3@ if tma_info_thread_ipc > 1.8 else cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x2@)) / 2 - (RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else 0) + RESOURCE_STALLS.SB if #SMT_on else min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.CYCLES_NO_EXECUTE) + cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x1@ - (cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x3@ if tma_info_thread_ipc > 1.8 else cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x2@) - (RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else 0) + RESOURCE_STALLS.SB) - RESOURCE_STALLS.SB - min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.STALLS_LDM_PENDING)) / tma_info_thread_clks",
         "MetricGroup": "PortsUtil;TopdownL3;tma_L3_group;tma_core_bound_group",
         "MetricName": "tma_ports_utilization",
-        "MetricThreshold": "tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)",
-        "PublicDescription": "This metric estimates fraction of cycles the CPU performance was potentially limited due to Core computation issues (non divider-related).  Two distinct categories can be attributed into this metric: (1) heavy data-dependency among contiguous instructions would manifest in this metric - such cases are often referred to as low Instruction Level Parallelism (ILP). (2) Contention on some hardware execution unit other than Divider. For example; when there are too many multiply operations.",
+        "MetricThreshold": "tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
+        "PublicDescription": "This metric estimates fraction of cycles the CPU performance was potentially limited due to Core computation issues (non divider-related).  Two distinct categories can be attributed into this metric: (1) heavy data-dependency among contiguous instructions would manifest in this metric - such cases are often referred to as low Instruction Level Parallelism (ILP). (2) Contention on some hardware execution unit other than Divider. For example; when there are too many multiply operations",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "This metric represents fraction of cycles CPU executed no uops on any execution port (Logical Processor cycles since ICL, Physical Core cycles otherwise)",
-        "MetricExpr": "(cpu@UOPS_EXECUTED.CORE\\,inv\\,cmask\\=1@ / 2 if #SMT_on else (min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.CYCLES_NO_EXECUTE) - (RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else 0)) / tma_info_core_core_clks)",
+        "MetricExpr": "(cpu@UOPS_EXECUTED.CORE\\,inv\\=0x1\\,cmask\\=0x1@ / 2 if #SMT_on else min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.CYCLES_NO_EXECUTE) - (RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else 0)) / tma_info_core_core_clks",
         "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group",
         "MetricName": "tma_ports_utilized_0",
-        "MetricThreshold": "tma_ports_utilized_0 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))",
-        "PublicDescription": "This metric represents fraction of cycles CPU executed no uops on any execution port (Logical Processor cycles since ICL, Physical Core cycles otherwise). Long-latency instructions like divides may contribute to this metric.",
+        "MetricThreshold": "tma_ports_utilized_0 > 0.2 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
+        "PublicDescription": "This metric represents fraction of cycles CPU executed no uops on any execution port (Logical Processor cycles since ICL, Physical Core cycles otherwise). Long-latency instructions like divides may contribute to this metric",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "This metric represents fraction of cycles where the CPU executed total of 1 uop per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise)",
-        "MetricExpr": "((cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ - cpu@UOPS_EXECUTED.CORE\\,cmask\\=2@) / 2 if #SMT_on else (cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ - cpu@UOPS_EXECUTED.CORE\\,cmask\\=2@) / tma_info_core_core_clks)",
+        "MetricExpr": "((cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x1@ - cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x2@) / 2 if #SMT_on else cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x1@ - cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x2@) / tma_info_core_core_clks",
         "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_issueL1;tma_ports_utilization_group",
         "MetricName": "tma_ports_utilized_1",
-        "MetricThreshold": "tma_ports_utilized_1 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))",
+        "MetricThreshold": "tma_ports_utilized_1 > 0.2 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
         "PublicDescription": "This metric represents fraction of cycles where the CPU executed total of 1 uop per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise). This can be due to heavy data-dependency among software instructions; or over oversubscribing a particular hardware resource. In some other cases with high 1_Port_Utilized and L1_Bound; this metric can point to L1 data-cache latency bottleneck that may not necessarily manifest with complete execution starvation (due to the short L1 latency e.g. walking a linked list) - looking at the assembly can be helpful. Related metrics: tma_l1_bound",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "This metric represents fraction of cycles CPU executed total of 2 uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise)",
-        "MetricExpr": "((cpu@UOPS_EXECUTED.CORE\\,cmask\\=2@ - cpu@UOPS_EXECUTED.CORE\\,cmask\\=3@) / 2 if #SMT_on else (cpu@UOPS_EXECUTED.CORE\\,cmask\\=2@ - cpu@UOPS_EXECUTED.CORE\\,cmask\\=3@) / tma_info_core_core_clks)",
+        "MetricExpr": "((cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x2@ - cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x3@) / 2 if #SMT_on else cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x2@ - cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x3@) / tma_info_core_core_clks",
         "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_issue2P;tma_ports_utilization_group",
         "MetricName": "tma_ports_utilized_2",
-        "MetricThreshold": "tma_ports_utilized_2 > 0.15 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))",
-        "PublicDescription": "This metric represents fraction of cycles CPU executed total of 2 uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise).  Loop Vectorization -most compilers feature auto-Vectorization options today- reduces pressure on the execution ports as multiple elements are calculated with same uop. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6",
+        "MetricThreshold": "tma_ports_utilized_2 > 0.15 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
+        "PublicDescription": "This metric represents fraction of cycles CPU executed total of 2 uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise).  Loop Vectorization -most compilers feature auto-Vectorization options today- reduces pressure on the execution ports as multiple elements are calculated with same uop. Related metrics: tma_port_0, tma_port_1, tma_port_5, tma_port_6",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric represents fraction of cycles CPU executed total of 3 or more uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise).",
-        "MetricExpr": "(cpu@UOPS_EXECUTED.CORE\\,cmask\\=3@ / 2 if #SMT_on else cpu@UOPS_EXECUTED.CORE\\,cmask\\=3@) / tma_info_core_core_clks",
+        "BriefDescription": "This metric represents fraction of cycles CPU executed total of 3 or more uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise)",
+        "MetricExpr": "(cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x3@ / 2 if #SMT_on else cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x3@) / tma_info_core_core_clks",
         "MetricGroup": "BvCB;PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group",
         "MetricName": "tma_ports_utilized_3m",
-        "MetricThreshold": "tma_ports_utilized_3m > 0.4 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))",
+        "MetricThreshold": "tma_ports_utilized_3m > 0.4 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
         "ScaleUnit": "100%"
     },
     {
@@ -888,8 +916,8 @@
         "MetricExpr": "tma_info_memory_load_miss_real_latency * LD_BLOCKS.NO_SR / tma_info_thread_clks",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group",
         "MetricName": "tma_split_loads",
-        "MetricThreshold": "tma_split_loads > 0.2 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
-        "PublicDescription": "This metric estimates fraction of cycles handling memory load split accesses - load that cross 64-byte cache line boundary. Sample with: MEM_UOPS_RETIRED.SPLIT_LOADS_PS",
+        "MetricThreshold": "tma_split_loads > 0.3",
+        "PublicDescription": "This metric estimates fraction of cycles handling memory load split accesses - load that cross 64-byte cache line boundary. Sample with: MEM_UOPS_RETIRED.SPLIT_LOADS",
         "ScaleUnit": "100%"
     },
     {
@@ -897,16 +925,16 @@
         "MetricExpr": "2 * MEM_UOPS_RETIRED.SPLIT_STORES / tma_info_core_core_clks",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_issueSpSt;tma_store_bound_group",
         "MetricName": "tma_split_stores",
-        "MetricThreshold": "tma_split_stores > 0.2 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
-        "PublicDescription": "This metric represents rate of split store accesses.  Consider aligning your data to the 64-byte cache line granularity. Sample with: MEM_UOPS_RETIRED.SPLIT_STORES_PS. Related metrics: tma_port_4",
+        "MetricThreshold": "tma_split_stores > 0.2 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "PublicDescription": "This metric represents rate of split store accesses.  Consider aligning your data to the 64-byte cache line granularity. Sample with: MEM_UOPS_RETIRED.SPLIT_STORES. Related metrics: tma_port_4",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors)",
         "MetricExpr": "(OFFCORE_REQUESTS_BUFFER.SQ_FULL / 2 if #SMT_on else OFFCORE_REQUESTS_BUFFER.SQ_FULL) / tma_info_core_core_clks",
-        "MetricGroup": "BvMS;MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_issueBW;tma_l3_bound_group",
+        "MetricGroup": "BvMB;MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_issueBW;tma_l3_bound_group",
         "MetricName": "tma_sq_full",
-        "MetricThreshold": "tma_sq_full > 0.3 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+        "MetricThreshold": "tma_sq_full > 0.3 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
         "PublicDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors). Related metrics: tma_fb_full, tma_info_system_dram_bw_use, tma_mem_bandwidth",
         "ScaleUnit": "100%"
     },
@@ -915,8 +943,8 @@
         "MetricExpr": "RESOURCE_STALLS.SB / tma_info_thread_clks",
         "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group",
         "MetricName": "tma_store_bound",
-        "MetricThreshold": "tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)",
-        "PublicDescription": "This metric estimates how often CPU was stalled  due to RFO store memory accesses; RFO store issue a read-for-ownership request before the write. Even though store accesses do not typically stall out-of-order CPUs; there are few cases where stores can lead to actual stalls. This metric will be flagged should RFO stores be a bottleneck. Sample with: MEM_UOPS_RETIRED.ALL_STORES_PS",
+        "MetricThreshold": "tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "PublicDescription": "This metric estimates how often CPU was stalled  due to RFO store memory accesses; RFO store issue a read-for-ownership request before the write. Even though store accesses do not typically stall out-of-order CPUs; there are few cases where stores can lead to actual stalls. This metric will be flagged should RFO stores be a bottleneck. Sample with: MEM_UOPS_RETIRED.ALL_STORES",
         "ScaleUnit": "100%"
     },
     {
@@ -924,18 +952,18 @@
         "MetricExpr": "13 * LD_BLOCKS.STORE_FORWARD / tma_info_thread_clks",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group",
         "MetricName": "tma_store_fwd_blk",
-        "MetricThreshold": "tma_store_fwd_blk > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
-        "PublicDescription": "This metric roughly estimates fraction of cycles when the memory subsystem had loads blocked since they could not forward data from earlier (in program order) overlapping stores. To streamline memory operations in the pipeline; a load can avoid waiting for memory if a prior in-flight store is writing the data that the load wants to read (store forwarding process). However; in some cases the load may be blocked for a significant time pending the store forward. For example; when the prior store is writing a smaller region than the load is reading.",
+        "MetricThreshold": "tma_store_fwd_blk > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "PublicDescription": "This metric roughly estimates fraction of cycles when the memory subsystem had loads blocked since they could not forward data from earlier (in program order) overlapping stores. To streamline memory operations in the pipeline; a load can avoid waiting for memory if a prior in-flight store is writing the data that the load wants to read (store forwarding process). However; in some cases the load may be blocked for a significant time pending the store forward. For example; when the prior store is writing a smaller region than the load is reading",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "This metric estimates fraction of cycles the CPU spent handling L1D store misses",
         "MetricConstraint": "NO_GROUP_EVENTS",
         "MetricExpr": "(L2_RQSTS.RFO_HIT * 9 * (1 - MEM_UOPS_RETIRED.LOCK_LOADS / MEM_UOPS_RETIRED.ALL_STORES) + (1 - MEM_UOPS_RETIRED.LOCK_LOADS / MEM_UOPS_RETIRED.ALL_STORES) * min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO)) / tma_info_thread_clks",
-        "MetricGroup": "BvML;MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_issueSL;tma_store_bound_group",
+        "MetricGroup": "BvML;LockCont;MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_issueSL;tma_store_bound_group",
         "MetricName": "tma_store_latency",
-        "MetricThreshold": "tma_store_latency > 0.1 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
-        "PublicDescription": "This metric estimates fraction of cycles the CPU spent handling L1D store misses. Store accesses usually less impact out-of-order core performance; however; holding resources for longer time can lead into undesired implications (e.g. contention on L1D fill-buffer entries - see FB_Full). Related metrics: tma_fb_full, tma_lock_latency",
+        "MetricThreshold": "tma_store_latency > 0.1 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "PublicDescription": "This metric estimates fraction of cycles the CPU spent handling L1D store misses. Store accesses usually less impact out-of-order core performance; however; holding resources for longer time can lead into undesired implications (e.g. contention on L1D fill-buffer entries - see FB_Full). Related metrics: tma_branch_resteers, tma_fb_full, tma_l3_hit_latency, tma_lock_latency",
         "ScaleUnit": "100%"
     },
     {
tools/perf/pmu-events/arch/x86/haswell/memory.json +1 -1
index edb1b5b9f553..a76f1862e5ea 100644
@@ -412,7 +412,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0xc9",
         "EventName": "RTM_RETIRED.ABORTED",
-        "PEBS": "2",
+        "PEBS": "1",
         "SampleAfterValue": "2000003",
         "UMask": "0x4"
     },
tools/perf/pmu-events/arch/x86/haswell/metricgroups.json +5 -0
index 4193c90c3459..0863375bdead 100644
@@ -9,6 +9,7 @@
     "BvCB": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
     "BvFB": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
     "BvIO": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
+    "BvMB": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
     "BvML": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
     "BvMP": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
     "BvMS": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
@@ -34,6 +35,7 @@
     "InsType": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
     "L2Evicts": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
     "LSD": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
+    "LockCont": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
     "MachineClears": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
     "Machine_Clears": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
     "Mem": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
@@ -51,6 +53,7 @@
     "Pipeline": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
     "PortsUtil": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
     "Power": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
+    "Prefetches": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
     "Ret": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
     "Retire": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
     "SMT": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
@@ -78,6 +81,7 @@
     "tma_bad_speculation_group": "Metrics contributing to tma_bad_speculation category",
     "tma_branch_resteers_group": "Metrics contributing to tma_branch_resteers category",
     "tma_core_bound_group": "Metrics contributing to tma_core_bound category",
+    "tma_divider_group": "Metrics contributing to tma_divider category",
     "tma_dram_bound_group": "Metrics contributing to tma_dram_bound category",
     "tma_dtlb_load_group": "Metrics contributing to tma_dtlb_load category",
     "tma_dtlb_store_group": "Metrics contributing to tma_dtlb_store category",
@@ -103,6 +107,7 @@
     "tma_issueSpSt": "Metrics related by the issue $issueSpSt",
     "tma_issueSyncxn": "Metrics related by the issue $issueSyncxn",
     "tma_issueTLB": "Metrics related by the issue $issueTLB",
+    "tma_itlb_misses_group": "Metrics contributing to tma_itlb_misses category",
     "tma_l1_bound_group": "Metrics contributing to tma_l1_bound category",
     "tma_l3_bound_group": "Metrics contributing to tma_l3_bound category",
     "tma_light_operations_group": "Metrics contributing to tma_light_operations category",
tools/perf/pmu-events/arch/x86/haswell/uncore-other.json deleted +0 -10
deleted file mode 100644
index 1ac5b5ef8094..000000000000
@@ -1,10 +0,0 @@
-[
-    {
-        "BriefDescription": "This 48-bit fixed counter counts the UCLK cycles.",
-        "Counter": "FIXED",
-        "EventCode": "0xff",
-        "EventName": "UNC_CLOCK.SOCKET",
-        "PerPkg": "1",
-        "Unit": "CLOCK"
-    }
-]
tools/perf/pmu-events/arch/x86/mapfile.csv +1 -1
index 213f49e585bc..bd87a41a1de7 100644
@@ -14,7 +14,7 @@ GenuineIntel-6-5[CF],v13,goldmont,core
 GenuineIntel-6-7A,v1.01,goldmontplus,core
 GenuineIntel-6-B6,v1.05,grandridge,core
 GenuineIntel-6-A[DE],v1.06,graniterapids,core
-GenuineIntel-6-(3C|45|46),v35,haswell,core
+GenuineIntel-6-(3C|45|46),v36,haswell,core
 GenuineIntel-6-3F,v28,haswellx,core
 GenuineIntel-6-7[DE],v1.22,icelake,core
 GenuineIntel-6-6[AC],v1.26,icelakex,core
Signature · 1 line
2.48.1.502.g6dc24dfdaf-goog
author reviewer
#13 lore raw

PATCH v8 13/24 perf vendor events: Update HaswellX events/metrics

In reply to Ian Rogers

Update events from v28 to v29.
Update TMA metrics from 4.8 to 5.02.

Bring in the event updates v29:
https://github.com/intel/perfmon/commit/71dbf03aba964f79fb096c9ded385c8a486a99b3

The TMA 5.02 update is from (with subsequent fixes):
https://github.com/intel/perfmon/commit/1d72913b2d938781fb28f3cc3507aaec5c22d782

---
 .../arch/x86/haswellx/hsx-metrics.json        | 296 ++++++++++--------
 .../arch/x86/haswellx/metricgroups.json       |   5 +
 .../arch/x86/haswellx/uncore-cache.json       |  28 +-
 .../x86/haswellx/uncore-interconnect.json     |  38 +--
 tools/perf/pmu-events/arch/x86/mapfile.csv    |   2 +-
 5 files changed, 191 insertions(+), 178 deletions(-)
tools/perf/pmu-events/arch/x86/haswellx/hsx-metrics.json +162 -134
index 8f2ba3391e35..1a05b74be575 100644
@@ -55,7 +55,7 @@
         "MetricName": "UNCORE_FREQ"
     },
     {
-        "BriefDescription": "Cycles per instruction retired; indicating how much time each executed instruction took; in units of cycles.",
+        "BriefDescription": "Cycles per instruction retired; indicating how much time each executed instruction took; in units of cycles",
         "MetricExpr": "CPU_CLK_UNHALTED.THREAD / INST_RETIRED.ANY",
         "MetricName": "cpi",
         "ScaleUnit": "1per_instr"
@@ -76,24 +76,24 @@
         "BriefDescription": "Ratio of number of completed page walks (for all page sizes) caused by demand data loads to the total number of completed instructions",
         "MetricExpr": "DTLB_LOAD_MISSES.WALK_COMPLETED / INST_RETIRED.ANY",
         "MetricName": "dtlb_load_mpi",
-        "PublicDescription": "Ratio of number of completed page walks (for all page sizes) caused by demand data loads to the total number of completed instructions. This implies it missed in the DTLB and further levels of TLB.",
+        "PublicDescription": "Ratio of number of completed page walks (for all page sizes) caused by demand data loads to the total number of completed instructions. This implies it missed in the DTLB and further levels of TLB",
         "ScaleUnit": "1per_instr"
     },
     {
         "BriefDescription": "Ratio of number of completed page walks (for all page sizes) caused by demand data stores to the total number of completed instructions",
         "MetricExpr": "DTLB_STORE_MISSES.WALK_COMPLETED / INST_RETIRED.ANY",
         "MetricName": "dtlb_store_mpi",
-        "PublicDescription": "Ratio of number of completed page walks (for all page sizes) caused by demand data stores to the total number of completed instructions. This implies it missed in the DTLB and further levels of TLB.",
+        "PublicDescription": "Ratio of number of completed page walks (for all page sizes) caused by demand data stores to the total number of completed instructions. This implies it missed in the DTLB and further levels of TLB",
         "ScaleUnit": "1per_instr"
     },
     {
-        "BriefDescription": "Bandwidth of IO reads that are initiated by end device controllers that are requesting memory from the CPU.",
+        "BriefDescription": "Bandwidth of IO reads that are initiated by end device controllers that are requesting memory from the CPU",
         "MetricExpr": "cbox@UNC_C_TOR_INSERTS.OPCODE\\,filter_opc\\=0x19e@ * 64 / 1e6 / duration_time",
         "MetricName": "io_bandwidth_read",
         "ScaleUnit": "1MB/s"
     },
     {
-        "BriefDescription": "Bandwidth of IO writes that are initiated by end device controllers that are writing memory to the CPU.",
+        "BriefDescription": "Bandwidth of IO writes that are initiated by end device controllers that are writing memory to the CPU",
         "MetricExpr": "cbox@UNC_C_TOR_INSERTS.OPCODE\\,filter_opc\\=0x1c8\\,filter_tid\\=0x3e@ * 64 / 1e6 / duration_time",
         "MetricName": "io_bandwidth_write",
         "ScaleUnit": "1MB/s"
@@ -102,14 +102,14 @@
         "BriefDescription": "Ratio of number of completed page walks (for 2 megabyte and 4 megabyte page sizes) caused by a code fetch to the total number of completed instructions",
         "MetricExpr": "ITLB_MISSES.WALK_COMPLETED_2M_4M / INST_RETIRED.ANY",
         "MetricName": "itlb_large_page_mpi",
-        "PublicDescription": "Ratio of number of completed page walks (for 2 megabyte and 4 megabyte page sizes) caused by a code fetch to the total number of completed instructions. This implies it missed in the Instruction Translation Lookaside Buffer (ITLB) and further levels of TLB.",
+        "PublicDescription": "Ratio of number of completed page walks (for 2 megabyte and 4 megabyte page sizes) caused by a code fetch to the total number of completed instructions. This implies it missed in the Instruction Translation Lookaside Buffer (ITLB) and further levels of TLB",
         "ScaleUnit": "1per_instr"
     },
     {
         "BriefDescription": "Ratio of number of completed page walks (for all page sizes) caused by a code fetch to the total number of completed instructions",
         "MetricExpr": "ITLB_MISSES.WALK_COMPLETED / INST_RETIRED.ANY",
         "MetricName": "itlb_mpi",
-        "PublicDescription": "Ratio of number of completed page walks (for all page sizes) caused by a code fetch to the total number of completed instructions. This implies it missed in the ITLB (Instruction TLB) and further levels of TLB.",
+        "PublicDescription": "Ratio of number of completed page walks (for all page sizes) caused by a code fetch to the total number of completed instructions. This implies it missed in the ITLB (Instruction TLB) and further levels of TLB",
         "ScaleUnit": "1per_instr"
     },
     {
@@ -209,13 +209,13 @@
         "ScaleUnit": "1MB/s"
     },
     {
-        "BriefDescription": "Memory read that miss the last level cache (LLC) addressed to local DRAM as a percentage of total memory read accesses, does not include LLC prefetches.",
+        "BriefDescription": "Memory read that miss the last level cache (LLC) addressed to local DRAM as a percentage of total memory read accesses, does not include LLC prefetches",
         "MetricExpr": "cbox@UNC_C_TOR_INSERTS.MISS_LOCAL_OPCODE\\,filter_opc\\=0x182@ / (cbox@UNC_C_TOR_INSERTS.MISS_LOCAL_OPCODE\\,filter_opc\\=0x182@ + cbox@UNC_C_TOR_INSERTS.MISS_REMOTE_OPCODE\\,filter_opc\\=0x182@)",
         "MetricName": "numa_reads_addressed_to_local_dram",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "Memory reads that miss the last level cache (LLC) addressed to remote DRAM as a percentage of total memory read accesses, does not include LLC prefetches.",
+        "BriefDescription": "Memory reads that miss the last level cache (LLC) addressed to remote DRAM as a percentage of total memory read accesses, does not include LLC prefetches",
         "MetricExpr": "cbox@UNC_C_TOR_INSERTS.MISS_REMOTE_OPCODE\\,filter_opc\\=0x182@ / (cbox@UNC_C_TOR_INSERTS.MISS_LOCAL_OPCODE\\,filter_opc\\=0x182@ + cbox@UNC_C_TOR_INSERTS.MISS_REMOTE_OPCODE\\,filter_opc\\=0x182@)",
         "MetricName": "numa_reads_addressed_to_remote_dram",
         "ScaleUnit": "100%"
@@ -276,12 +276,12 @@
         "MetricExpr": "LD_BLOCKS_PARTIAL.ADDRESS_ALIAS / tma_info_thread_clks",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group",
         "MetricName": "tma_4k_aliasing",
-        "MetricThreshold": "tma_4k_aliasing > 0.2 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
-        "PublicDescription": "This metric estimates how often memory load accesses were aliased by preceding stores (in program order) with a 4K address offset. False match is possible; which incur a few cycles load re-issue. However; the short re-issue duration is often hidden by the out-of-order core and HW optimizations; hence a user may safely ignore a high value of this metric unless it manages to propagate up into parent nodes of the hierarchy (e.g. to L1_Bound).",
+        "MetricThreshold": "tma_4k_aliasing > 0.2 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "PublicDescription": "This metric estimates how often memory load accesses were aliased by preceding stores (in program order) with a 4K address offset. False match is possible; which incur a few cycles load re-issue. However; the short re-issue duration is often hidden by the out-of-order core and HW optimizations; hence a user may safely ignore a high value of this metric unless it manages to propagate up into parent nodes of the hierarchy (e.g. to L1_Bound)",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution ports for ALU operations.",
+        "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution ports for ALU operations",
         "MetricConstraint": "NO_GROUP_EVENTS_NMI",
         "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",
@@ -294,8 +294,8 @@
         "MetricExpr": "66 * OTHER_ASSISTS.ANY_WB_ASSIST / tma_info_thread_slots",
         "MetricGroup": "BvIO;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)",
-        "PublicDescription": "This metric estimates fraction of slots the CPU retired uops delivered by the Microcode_Sequencer as a result of Assists. Assists are long sequences of uops that are required in certain corner-cases for operations that cannot be handled natively by the execution pipeline. For example; when working with very small floating point values (so-called Denormals); the FP units are not set up to perform these operations natively. Instead; a sequence of instructions to perform the computation on the Denormals is injected into the pipeline. Since these microcode sequences might be dozens of uops long; Assists can be extremely deleterious to performance and they can be avoided in many cases. Sample with: OTHER_ASSISTS.ANY",
+        "MetricThreshold": "tma_assists > 0.1 & tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1",
+        "PublicDescription": "This metric estimates fraction of slots the CPU retired uops delivered by the Microcode_Sequencer as a result of Assists. Assists are long sequences of uops that are required in certain corner-cases for operations that cannot be handled natively by the execution pipeline. For example; when working with very small floating point values (so-called Denormals); the FP units are not set up to perform these operations natively. Instead; a sequence of instructions to perform the computation on the Denormals is injected into the pipeline. Since these microcode sequences might be dozens of uops long; Assists can be extremely deleterious to performance and they can be avoided in many cases. Sample with: OTHER_ASSISTS.ANY_WB_ASSIST",
         "ScaleUnit": "100%"
     },
     {
@@ -306,7 +306,7 @@
         "MetricName": "tma_backend_bound",
         "MetricThreshold": "tma_backend_bound > 0.2",
         "MetricgroupNoGroup": "TopdownL1",
-        "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound.",
+        "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound",
         "ScaleUnit": "100%"
     },
     {
@@ -316,7 +316,7 @@
         "MetricName": "tma_bad_speculation",
         "MetricThreshold": "tma_bad_speculation > 0.15",
         "MetricgroupNoGroup": "TopdownL1",
-        "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.",
+        "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example",
         "ScaleUnit": "100%"
     },
     {
@@ -327,7 +327,7 @@
         "MetricName": "tma_branch_mispredicts",
         "MetricThreshold": "tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15",
         "MetricgroupNoGroup": "TopdownL2",
-        "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction.  These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_info_bad_spec_branch_misprediction_cost, tma_mispredicts_resteers",
+        "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction.  These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: BR_MISP_RETIRED.ALL_BRANCHES",
         "ScaleUnit": "100%"
     },
     {
@@ -335,8 +335,8 @@
         "MetricExpr": "12 * (BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT + BACLEARS.ANY) / tma_info_thread_clks",
         "MetricGroup": "FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group",
         "MetricName": "tma_branch_resteers",
-        "MetricThreshold": "tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)",
-        "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers. Branch Resteers estimates the Frontend delay in fetching operations from corrected path; following all sorts of miss-predicted branches. For example; branchy code with lots of miss-predictions might get categorized under Branch Resteers. Note the value of this node may overlap with its siblings. Sample with: BR_MISP_RETIRED.ALL_BRANCHES",
+        "MetricThreshold": "tma_branch_resteers > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+        "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers. Branch Resteers estimates the Frontend delay in fetching operations from corrected path; following all sorts of miss-predicted branches. For example; branchy code with lots of miss-predictions might get categorized under Branch Resteers. Note the value of this node may overlap with its siblings. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_l3_hit_latency, tma_store_latency",
         "ScaleUnit": "100%"
     },
     {
@@ -345,18 +345,18 @@
         "MetricExpr": "max(0, tma_microcode_sequencer - tma_assists)",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_microcode_sequencer_group",
         "MetricName": "tma_cisc",
-        "MetricThreshold": "tma_cisc > 0.1 & (tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1)",
-        "PublicDescription": "This metric estimates fraction of cycles the CPU retired uops originated from CISC (complex instruction set computer) instruction. A CISC instruction has multiple uops that are required to perform the instruction's functionality as in the case of read-modify-write as an example. Since these instructions require multiple uops they may or may not imply sub-optimal use of machine resources.",
+        "MetricThreshold": "tma_cisc > 0.1 & tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1",
+        "PublicDescription": "This metric estimates fraction of cycles the CPU retired uops originated from CISC (complex instruction set computer) instruction. A CISC instruction has multiple uops that are required to perform the instruction's functionality as in the case of read-modify-write as an example. Since these instructions require multiple uops they may or may not imply sub-optimal use of machine resources",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses",
         "MetricConstraint": "NO_GROUP_EVENTS",
         "MetricExpr": "(60 * (MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.L3_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_L3_MISS_RETIRED.LOCAL_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_HITM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_FWD))) + 43 * (MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.L3_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_L3_MISS_RETIRED.LOCAL_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_HITM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_FWD)))) / tma_info_thread_clks",
-        "MetricGroup": "BvMS;DataSharing;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group",
+        "MetricGroup": "BvMS;DataSharing;LockCont;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))",
-        "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses. Contested accesses occur when data written by one Logical Processor are read by another Logical Processor on a different Physical Core. Examples of contested accesses include synchronizations such as locks; true data sharing such as modified locked variables; and false sharing. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM_PS;MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS_PS. Related metrics: tma_data_sharing, tma_false_sharing, tma_machine_clears, tma_remote_cache",
+        "MetricThreshold": "tma_contested_accesses > 0.05 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses. Contested accesses occur when data written by one Logical Processor are read by another Logical Processor on a different Physical Core. Examples of contested accesses include synchronizations such as locks; true data sharing such as modified locked variables; and false sharing. Sample with: MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM, MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS. Related metrics: tma_data_sharing, tma_false_sharing, tma_machine_clears, tma_remote_cache",
         "ScaleUnit": "100%"
     },
     {
@@ -367,7 +367,7 @@
         "MetricName": "tma_core_bound",
         "MetricThreshold": "tma_core_bound > 0.1 & tma_backend_bound > 0.2",
         "MetricgroupNoGroup": "TopdownL2",
-        "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck.  Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations).",
+        "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck.  Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations)",
         "ScaleUnit": "100%"
     },
     {
@@ -376,8 +376,8 @@
         "MetricExpr": "43 * (MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.L3_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_L3_MISS_RETIRED.LOCAL_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_HITM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_FWD))) / tma_info_thread_clks",
         "MetricGroup": "BvMS;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))",
-        "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses. Data shared by multiple Logical Processors (even just read shared) may cause increased access latency due to cache coherency. Excessive data sharing can drastically harm multithreaded performance. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_HIT_PS. Related metrics: tma_contested_accesses, tma_false_sharing, tma_machine_clears, tma_remote_cache",
+        "MetricThreshold": "tma_data_sharing > 0.05 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses. Data shared by multiple Logical Processors (even just read shared) may cause increased access latency due to cache coherency. Excessive data sharing can drastically harm multithreaded performance. Sample with: MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT. Related metrics: tma_contested_accesses, tma_false_sharing, tma_machine_clears, tma_remote_cache",
         "ScaleUnit": "100%"
     },
     {
@@ -385,7 +385,7 @@
         "MetricExpr": "10 * ARITH.DIVIDER_UOPS / tma_info_core_core_clks",
         "MetricGroup": "BvCB;TopdownL3;tma_L3_group;tma_core_bound_group",
         "MetricName": "tma_divider",
-        "MetricThreshold": "tma_divider > 0.2 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)",
+        "MetricThreshold": "tma_divider > 0.2 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
         "PublicDescription": "This metric represents fraction of cycles where the Divider unit was active. Divide and square root instructions are performed by the Divider unit and can take considerably longer latency than integer or Floating Point addition; subtraction; or multiplication. Sample with: ARITH.DIVIDER_UOPS",
         "ScaleUnit": "100%"
     },
@@ -395,8 +395,8 @@
         "MetricExpr": "(1 - MEM_LOAD_UOPS_RETIRED.L3_HIT / (MEM_LOAD_UOPS_RETIRED.L3_HIT + 7 * MEM_LOAD_UOPS_RETIRED.L3_MISS)) * CYCLE_ACTIVITY.STALLS_L2_PENDING / tma_info_thread_clks",
         "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group",
         "MetricName": "tma_dram_bound",
-        "MetricThreshold": "tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)",
-        "PublicDescription": "This metric estimates how often the CPU was stalled on accesses to external memory (DRAM) by loads. Better caching can improve the latency and increase performance. Sample with: MEM_LOAD_UOPS_RETIRED.L3_MISS_PS",
+        "MetricThreshold": "tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "PublicDescription": "This metric estimates how often the CPU was stalled on accesses to external memory (DRAM) by loads. Better caching can improve the latency and increase performance. Sample with: MEM_LOAD_UOPS_RETIRED.L3_MISS",
         "ScaleUnit": "100%"
     },
     {
@@ -405,7 +405,7 @@
         "MetricGroup": "DSB;FetchBW;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group",
         "MetricName": "tma_dsb",
         "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.",
+        "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%"
     },
     {
@@ -413,7 +413,7 @@
         "MetricExpr": "DSB2MITE_SWITCHES.PENALTY_CYCLES / tma_info_thread_clks",
         "MetricGroup": "DSBmiss;FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueFB",
         "MetricName": "tma_dsb_switches",
-        "MetricThreshold": "tma_dsb_switches > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)",
+        "MetricThreshold": "tma_dsb_switches > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
         "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines. The DSB (decoded i-cache) is a Uop Cache where the front-end directly delivers Uops (micro operations) avoiding heavy x86 decoding. The DSB pipeline has shorter latency and delivered higher bandwidth than the MITE (legacy instruction decode pipeline). Switching between the two pipelines can cause penalties hence this metric measures the exposed penalty. Related metrics: tma_fetch_bandwidth, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp",
         "ScaleUnit": "100%"
     },
@@ -422,8 +422,8 @@
         "MetricExpr": "(8 * DTLB_LOAD_MISSES.STLB_HIT + DTLB_LOAD_MISSES.WALK_DURATION) / tma_info_thread_clks",
         "MetricGroup": "BvMT;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_UOPS_RETIRED.STLB_MISS_LOADS_PS. Related metrics: tma_dtlb_store",
+        "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_UOPS_RETIRED.STLB_MISS_LOADS. Related metrics: tma_dtlb_store",
         "ScaleUnit": "100%"
     },
     {
@@ -431,27 +431,27 @@
         "MetricExpr": "(8 * DTLB_STORE_MISSES.STLB_HIT + DTLB_STORE_MISSES.WALK_DURATION) / tma_info_thread_clks",
         "MetricGroup": "BvMT;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_UOPS_RETIRED.STLB_MISS_STORES_PS. Related metrics: tma_dtlb_load",
+        "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_UOPS_RETIRED.STLB_MISS_STORES. Related metrics: tma_dtlb_load",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "This metric roughly estimates how often CPU was handling synchronizations due to False Sharing",
         "MetricExpr": "(200 * OFFCORE_RESPONSE.DEMAND_RFO.LLC_MISS.REMOTE_HITM + 60 * OFFCORE_RESPONSE.DEMAND_RFO.LLC_HIT.HITM_OTHER_CORE) / tma_info_thread_clks",
-        "MetricGroup": "BvMS;DataSharing;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_store_bound_group",
+        "MetricGroup": "BvMS;DataSharing;LockCont;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))",
-        "PublicDescription": "This metric roughly estimates how often CPU was handling synchronizations due to False Sharing. False Sharing is a multithreading hiccup; where multiple Logical Processors contend on different data-elements mapped into the same cache line. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM_PS;OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.SNOOP_HITM. Related metrics: tma_contested_accesses, tma_data_sharing, tma_machine_clears, tma_remote_cache",
+        "MetricThreshold": "tma_false_sharing > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "PublicDescription": "This metric roughly estimates how often CPU was handling synchronizations due to False Sharing. False Sharing is a multithreading hiccup; where multiple Logical Processors contend on different data-elements mapped into the same cache line. Sample with: MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM, MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_HITM, OFFCORE_RESPONSE.DEMAND_RFO.LLC_HIT.HITM_OTHER_CORE, OFFCORE_RESPONSE.DEMAND_RFO.LLC_MISS.REMOTE_HITM. Related metrics: tma_contested_accesses, tma_data_sharing, tma_machine_clears, tma_remote_cache",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed",
         "MetricConstraint": "NO_GROUP_EVENTS",
-        "MetricExpr": "tma_info_memory_load_miss_real_latency * cpu@L1D_PEND_MISS.REQUEST_FB_FULL\\,cmask\\=1@ / tma_info_thread_clks",
-        "MetricGroup": "BvMS;MemoryBW;TopdownL4;tma_L4_group;tma_issueBW;tma_issueSL;tma_issueSmSt;tma_l1_bound_group",
+        "MetricExpr": "tma_info_memory_load_miss_real_latency * cpu@L1D_PEND_MISS.REQUEST_FB_FULL\\,cmask\\=0x1@ / tma_info_thread_clks",
+        "MetricGroup": "BvMB;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_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_system_dram_bw_use, tma_mem_bandwidth, tma_sq_full, tma_store_latency",
         "ScaleUnit": "100%"
     },
     {
@@ -481,33 +481,33 @@
         "MetricName": "tma_frontend_bound",
         "MetricThreshold": "tma_frontend_bound > 0.15",
         "MetricgroupNoGroup": "TopdownL1",
-        "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound.",
+        "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences",
+        "BriefDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations , instructions that require two or more uops or micro-coded sequences",
         "MetricExpr": "tma_microcode_sequencer",
         "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group",
         "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. ([ICL+] Note this may overcount due to approximation using indirect events; [ADL+] .)",
+        "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.",
+        "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to instruction cache misses",
         "MetricExpr": "ICACHE.IFDATA_STALL / tma_info_thread_clks",
         "MetricGroup": "BigFootprint;BvBC;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)",
+        "MetricThreshold": "tma_icache_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "Instructions per retired mispredicts for indirect CALL or JMP branches (lower number means higher occurrence rate).",
+        "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 * BR_MISP_EXEC.INDIRECT)",
         "MetricGroup": "Bad;BrMispredicts",
         "MetricName": "tma_info_bad_spec_ipmisp_indirect",
-        "MetricThreshold": "tma_info_bad_spec_ipmisp_indirect < 1e3"
+        "MetricThreshold": "tma_info_bad_spec_ipmisp_indirect < 1000"
     },
     {
         "BriefDescription": "Number of Instructions per non-speculative Branch Misprediction (JEClear) (lower number means higher occurrence rate)",
@@ -518,7 +518,7 @@
     },
     {
         "BriefDescription": "Core actual clocks when any Logical Processor is active on the Physical Core",
-        "MetricExpr": "(CPU_CLK_UNHALTED.THREAD / 2 * (1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK) if #core_wide < 1 else (CPU_CLK_UNHALTED.THREAD_ANY / 2 if #SMT_on else tma_info_thread_clks))",
+        "MetricExpr": "(CPU_CLK_UNHALTED.THREAD_ANY / 2 if #SMT_on else tma_info_thread_clks)",
         "MetricGroup": "SMT",
         "MetricName": "tma_info_core_core_clks"
     },
@@ -530,7 +530,7 @@
     },
     {
         "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is execution) per thread (logical-processor)",
-        "MetricExpr": "(UOPS_EXECUTED.CORE / 2 / (cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ / 2 if #SMT_on else cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@) if #SMT_on else UOPS_EXECUTED.CORE / (cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ / 2 if #SMT_on else cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@))",
+        "MetricExpr": "(UOPS_EXECUTED.CORE / 2 / (cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x1@ / 2 if #SMT_on else cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x1@) if #SMT_on else UOPS_EXECUTED.CORE / (cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x1@ / 2 if #SMT_on else cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x1@))",
         "MetricGroup": "Backend;Cor;Pipeline;PortsUtil",
         "MetricName": "tma_info_core_ilp"
     },
@@ -549,7 +549,13 @@
         "MetricName": "tma_info_frontend_ipunknown_branch"
     },
     {
-        "BriefDescription": "Branch instructions per taken branch.",
+        "BriefDescription": "Taken Branches retired Per Cycle",
+        "MetricExpr": "BR_INST_RETIRED.NEAR_TAKEN / tma_info_thread_clks",
+        "MetricGroup": "Branches;FetchBW",
+        "MetricName": "tma_info_frontend_tbpc"
+    },
+    {
+        "BriefDescription": "Branch instructions per taken branch",
         "MetricExpr": "BR_INST_RETIRED.ALL_BRANCHES / BR_INST_RETIRED.NEAR_TAKEN",
         "MetricGroup": "Branches;Fed;PGO",
         "MetricName": "tma_info_inst_mix_bptkbranch"
@@ -594,7 +600,7 @@
         "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_TAKEN",
         "MetricGroup": "Branches;Fed;FetchBW;Frontend;PGO;tma_issueFB",
         "MetricName": "tma_info_inst_mix_iptb",
-        "MetricThreshold": "tma_info_inst_mix_iptb < 9",
+        "MetricThreshold": "tma_info_inst_mix_iptb < 4 * 2 + 1",
         "PublicDescription": "Instructions per taken branch. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_frontend_dsb_coverage, tma_lcp"
     },
     {
@@ -617,7 +623,7 @@
     },
     {
         "BriefDescription": "Average per-thread data fill bandwidth to the L1 data cache [GB / sec]",
-        "MetricExpr": "64 * L1D.REPLACEMENT / 1e9 / duration_time",
+        "MetricExpr": "64 * L1D.REPLACEMENT / 1e9 / tma_info_system_time",
         "MetricGroup": "Mem;MemoryBW",
         "MetricName": "tma_info_memory_l1d_cache_fill_bw"
     },
@@ -629,7 +635,7 @@
     },
     {
         "BriefDescription": "Average per-thread data fill bandwidth to the L2 cache [GB / sec]",
-        "MetricExpr": "64 * L2_LINES_IN.ALL / 1e9 / duration_time",
+        "MetricExpr": "64 * L2_LINES_IN.ALL / 1e9 / tma_info_system_time",
         "MetricGroup": "Mem;MemoryBW",
         "MetricName": "tma_info_memory_l2_cache_fill_bw"
     },
@@ -647,7 +653,7 @@
     },
     {
         "BriefDescription": "Average per-thread data fill bandwidth to the L3 cache [GB / sec]",
-        "MetricExpr": "64 * LONGEST_LAT_CACHE.MISS / 1e9 / duration_time",
+        "MetricExpr": "64 * LONGEST_LAT_CACHE.MISS / 1e9 / tma_info_system_time",
         "MetricGroup": "Mem;MemoryBW",
         "MetricName": "tma_info_memory_l3_cache_fill_bw"
     },
@@ -666,7 +672,7 @@
     {
         "BriefDescription": "Average Latency for L2 cache miss demand Loads",
         "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD / OFFCORE_REQUESTS.DEMAND_DATA_RD",
-        "MetricGroup": "Memory_Lat;Offcore",
+        "MetricGroup": "LockCont;Memory_Lat;Offcore",
         "MetricName": "tma_info_memory_latency_load_l2_miss_latency"
     },
     {
@@ -698,14 +704,14 @@
         "MetricThreshold": "tma_info_memory_tlb_page_walks_utilization > 0.5"
     },
     {
-        "BriefDescription": "Average number of Uops retired in cycles where at least one uop has retired.",
-        "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / cpu@UOPS_RETIRED.RETIRE_SLOTS\\,cmask\\=1@",
+        "BriefDescription": "Average number of Uops retired in cycles where at least one uop has retired",
+        "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / cpu@UOPS_RETIRED.RETIRE_SLOTS\\,cmask\\=0x1@",
         "MetricGroup": "Pipeline;Ret",
         "MetricName": "tma_info_pipeline_retire"
     },
     {
         "BriefDescription": "Measured Average Core Frequency for unhalted processors [GHz]",
-        "MetricExpr": "tma_info_system_turbo_utilization * TSC / 1e9 / duration_time",
+        "MetricExpr": "tma_info_system_turbo_utilization * TSC / 1e9 / tma_info_system_time",
         "MetricGroup": "Power;Summary",
         "MetricName": "tma_info_system_core_frequency"
     },
@@ -723,7 +729,7 @@
     },
     {
         "BriefDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]",
-        "MetricExpr": "64 * (UNC_M_CAS_COUNT.RD + UNC_M_CAS_COUNT.WR) / 1e9 / duration_time",
+        "MetricExpr": "64 * (UNC_M_CAS_COUNT.RD + UNC_M_CAS_COUNT.WR) / 1e9 / tma_info_system_time",
         "MetricGroup": "HPC;MemOffcore;MemoryBW;SoC;tma_issueBW",
         "MetricName": "tma_info_system_dram_bw_use",
         "PublicDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]. Related metrics: tma_fb_full, tma_mem_bandwidth, tma_sq_full"
@@ -733,13 +739,14 @@
         "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.FAR_BRANCH:u",
         "MetricGroup": "Branches;OS",
         "MetricName": "tma_info_system_ipfarbranch",
-        "MetricThreshold": "tma_info_system_ipfarbranch < 1e6"
+        "MetricThreshold": "tma_info_system_ipfarbranch < 1000000"
     },
     {
         "BriefDescription": "Cycles Per Instruction for the Operating System (OS) Kernel mode",
         "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P:k / INST_RETIRED.ANY_P:k",
         "MetricGroup": "OS",
-        "MetricName": "tma_info_system_kernel_cpi"
+        "MetricName": "tma_info_system_kernel_cpi",
+        "ScaleUnit": "1per_instr"
     },
     {
         "BriefDescription": "Fraction of cycles spent in the Operating System (OS) Kernel mode",
@@ -750,18 +757,31 @@
     },
     {
         "BriefDescription": "Average number of parallel data read requests to external memory",
-        "MetricExpr": "UNC_C_TOR_OCCUPANCY.MISS_OPCODE@filter_opc\\=0x182@ / UNC_C_TOR_OCCUPANCY.MISS_OPCODE@filter_opc\\=0x182\\,thresh\\=1@",
+        "MetricExpr": "cbox@UNC_C_TOR_OCCUPANCY.MISS_OPCODE\\,filter_opc\\=0x182@ / cbox@UNC_C_TOR_OCCUPANCY.MISS_OPCODE\\,filter_opc\\=0x182@",
         "MetricGroup": "Mem;MemoryBW;SoC",
         "MetricName": "tma_info_system_mem_parallel_reads",
         "PublicDescription": "Average number of parallel data read requests to external memory. Accounts for demand loads and L1/L2 prefetches"
     },
     {
         "BriefDescription": "Average latency of data read request to external memory (in nanoseconds)",
-        "MetricExpr": "1e9 * (UNC_C_TOR_OCCUPANCY.MISS_OPCODE@filter_opc\\=0x182@ / UNC_C_TOR_INSERTS.MISS_OPCODE@filter_opc\\=0x182@) / (tma_info_system_socket_clks / duration_time)",
+        "MetricExpr": "1e9 * (cbox@UNC_C_TOR_OCCUPANCY.MISS_OPCODE\\,filter_opc\\=0x182@ / cbox@UNC_C_TOR_INSERTS.MISS_OPCODE\\,filter_opc\\=0x182@) / (tma_info_system_socket_clks / tma_info_system_time)",
         "MetricGroup": "Mem;MemoryLat;SoC",
         "MetricName": "tma_info_system_mem_read_latency",
         "PublicDescription": "Average latency of data read request to external memory (in nanoseconds). Accounts for demand loads and L1/L2 prefetches. ([RKL+]memory-controller only)"
     },
+    {
+        "BriefDescription": "PerfMon Event Multiplexing accuracy indicator",
+        "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P / CPU_CLK_UNHALTED.THREAD",
+        "MetricGroup": "Summary",
+        "MetricName": "tma_info_system_mux",
+        "MetricThreshold": "tma_info_system_mux > 1.1 | tma_info_system_mux < 0.9"
+    },
+    {
+        "BriefDescription": "Total package Power in Watts",
+        "MetricExpr": "(power@energy\\-pkg@ * 61 + 15.6 * power@energy\\-ram@) / (duration_time * 1e6)",
+        "MetricGroup": "Power;SoC",
+        "MetricName": "tma_info_system_power"
+    },
     {
         "BriefDescription": "Fraction of cycles where both hardware Logical Processors were active",
         "MetricExpr": "(1 - CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / (CPU_CLK_UNHALTED.REF_XCLK_ANY / 2) if #SMT_on else 0)",
@@ -774,6 +794,13 @@
         "MetricGroup": "SoC",
         "MetricName": "tma_info_system_socket_clks"
     },
+    {
+        "BriefDescription": "Run duration time in seconds",
+        "MetricExpr": "duration_time",
+        "MetricGroup": "Summary",
+        "MetricName": "tma_info_system_time",
+        "MetricThreshold": "tma_info_system_time < 1"
+    },
     {
         "BriefDescription": "Average Frequency Utilization relative nominal frequency",
         "MetricExpr": "tma_info_thread_clks / CPU_CLK_UNHALTED.REF_TSC",
@@ -782,12 +809,12 @@
     },
     {
         "BriefDescription": "Measured Average Uncore Frequency for the SoC [GHz]",
-        "MetricExpr": "tma_info_system_socket_clks / 1e9 / duration_time",
+        "MetricExpr": "tma_info_system_socket_clks / 1e9 / tma_info_system_time",
         "MetricGroup": "SoC",
         "MetricName": "tma_info_system_uncore_frequency"
     },
     {
-        "BriefDescription": "Per-Logical Processor actual clocks when the Logical Processor is active.",
+        "BriefDescription": "Per-Logical Processor actual clocks when the Logical Processor is active",
         "MetricExpr": "CPU_CLK_UNHALTED.THREAD",
         "MetricGroup": "Pipeline",
         "MetricName": "tma_info_thread_clks"
@@ -796,7 +823,8 @@
         "BriefDescription": "Cycles Per Instruction (per Logical Processor)",
         "MetricExpr": "1 / tma_info_thread_ipc",
         "MetricGroup": "Mem;Pipeline",
-        "MetricName": "tma_info_thread_cpi"
+        "MetricName": "tma_info_thread_cpi",
+        "ScaleUnit": "1per_instr"
     },
     {
         "BriefDescription": "Instructions Per Cycle (per Logical Processor)",
@@ -822,24 +850,24 @@
         "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / BR_INST_RETIRED.NEAR_TAKEN",
         "MetricGroup": "Branches;Fed;FetchBW",
         "MetricName": "tma_info_thread_uptb",
-        "MetricThreshold": "tma_info_thread_uptb < 6"
+        "MetricThreshold": "tma_info_thread_uptb < 4 * 1.5"
     },
     {
         "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to Instruction TLB (ITLB) misses",
         "MetricExpr": "(14 * ITLB_MISSES.STLB_HIT + ITLB_MISSES.WALK_DURATION) / tma_info_thread_clks",
         "MetricGroup": "BigFootprint;BvBC;FetchLat;MemoryTLB;TopdownL3;tma_L3_group;tma_fetch_latency_group",
         "MetricName": "tma_itlb_misses",
-        "MetricThreshold": "tma_itlb_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)",
+        "MetricThreshold": "tma_itlb_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 TLB (ITLB) misses. Sample with: ITLB_MISSES.WALK_COMPLETED",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric estimates how often the CPU was stalled without loads missing the L1 data cache",
+        "BriefDescription": "This metric estimates how often the CPU was stalled without loads missing the L1 Data (L1D) cache",
         "MetricExpr": "max((min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.STALLS_LDM_PENDING) - CYCLE_ACTIVITY.STALLS_L1D_PENDING) / tma_info_thread_clks, 0)",
         "MetricGroup": "CacheHits;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_issueL1;tma_issueMC;tma_memory_bound_group",
         "MetricName": "tma_l1_bound",
-        "MetricThreshold": "tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)",
-        "PublicDescription": "This metric estimates how often the CPU was stalled without loads missing the L1 data cache.  The L1 data cache typically has the shortest latency.  However; in certain cases like loads blocked on older stores; a load might suffer due to high latency even though it is being satisfied by the L1. Another example is loads who miss in the TLB. These cases are characterized by execution unit stalls; while some non-completed demand load lives in the machine without having that demand load missing the L1 cache. Sample with: MEM_LOAD_UOPS_RETIRED.L1_HIT_PS;MEM_LOAD_UOPS_RETIRED.HIT_LFB_PS. Related metrics: tma_clears_resteers, tma_machine_clears, tma_microcode_sequencer, tma_ms_switches, tma_ports_utilized_1",
+        "MetricThreshold": "tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "PublicDescription": "This metric estimates how often the CPU was stalled without loads missing the L1 Data (L1D) cache.  The L1D cache typically has the shortest latency.  However; in certain cases like loads blocked on older stores; a load might suffer due to high latency even though it is being satisfied by the L1D. Another example is loads who miss in the TLB. These cases are characterized by execution unit stalls; while some non-completed demand load lives in the machine without having that demand load missing the L1 cache. Sample with: MEM_LOAD_UOPS_RETIRED.L1_HIT. Related metrics: tma_machine_clears, tma_microcode_sequencer, tma_ms_switches, tma_ports_utilized_1",
         "ScaleUnit": "100%"
     },
     {
@@ -847,8 +875,8 @@
         "MetricExpr": "(CYCLE_ACTIVITY.STALLS_L1D_PENDING - CYCLE_ACTIVITY.STALLS_L2_PENDING) / tma_info_thread_clks",
         "MetricGroup": "BvML;CacheHits;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group",
         "MetricName": "tma_l2_bound",
-        "MetricThreshold": "tma_l2_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)",
-        "PublicDescription": "This metric estimates how often the CPU was stalled due to L2 cache accesses by loads.  Avoiding cache misses (i.e. L1 misses/L2 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_UOPS_RETIRED.L2_HIT_PS",
+        "MetricThreshold": "tma_l2_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "PublicDescription": "This metric estimates how often the CPU was stalled due to L2 cache accesses by loads.  Avoiding cache misses (i.e. L1 misses/L2 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_UOPS_RETIRED.L2_HIT",
         "ScaleUnit": "100%"
     },
     {
@@ -857,8 +885,8 @@
         "MetricExpr": "MEM_LOAD_UOPS_RETIRED.L3_HIT / (MEM_LOAD_UOPS_RETIRED.L3_HIT + 7 * MEM_LOAD_UOPS_RETIRED.L3_MISS) * CYCLE_ACTIVITY.STALLS_L2_PENDING / tma_info_thread_clks",
         "MetricGroup": "CacheHits;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group",
         "MetricName": "tma_l3_bound",
-        "MetricThreshold": "tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)",
-        "PublicDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core.  Avoiding cache misses (i.e. L2 misses/L3 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_UOPS_RETIRED.L3_HIT_PS",
+        "MetricThreshold": "tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "PublicDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core.  Avoiding cache misses (i.e. L2 misses/L3 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_UOPS_RETIRED.L3_HIT",
         "ScaleUnit": "100%"
     },
     {
@@ -867,8 +895,8 @@
         "MetricExpr": "41 * (MEM_LOAD_UOPS_RETIRED.L3_HIT * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.L3_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_L3_MISS_RETIRED.LOCAL_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_HITM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_FWD))) / tma_info_thread_clks",
         "MetricGroup": "BvML;MemoryLat;TopdownL4;tma_L4_group;tma_issueLat;tma_l3_bound_group",
         "MetricName": "tma_l3_hit_latency",
-        "MetricThreshold": "tma_l3_hit_latency > 0.1 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
-        "PublicDescription": "This metric estimates fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited).  Avoiding private cache misses (i.e. L2 misses/L3 hits) will improve the latency; reduce contention with sibling physical cores and increase performance.  Note the value of this node may overlap with its siblings. Sample with: MEM_LOAD_UOPS_RETIRED.L3_HIT_PS. Related metrics: tma_mem_latency",
+        "MetricThreshold": "tma_l3_hit_latency > 0.1 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "PublicDescription": "This metric estimates fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited).  Avoiding private cache misses (i.e. L2 misses/L3 hits) will improve the latency; reduce contention with sibling physical cores and increase performance.  Note the value of this node may overlap with its siblings. Sample with: MEM_LOAD_UOPS_RETIRED.L3_HIT. Related metrics: tma_branch_resteers, tma_mem_latency, tma_store_latency",
         "ScaleUnit": "100%"
     },
     {
@@ -876,18 +904,18 @@
         "MetricExpr": "ILD_STALL.LCP / tma_info_thread_clks",
         "MetricGroup": "FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueFB",
         "MetricName": "tma_lcp",
-        "MetricThreshold": "tma_lcp > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)",
-        "PublicDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs). Using proper compiler flags or Intel Compiler by default will certainly avoid this. #Link: Optimization Guide about LCP BKMs. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb",
+        "MetricThreshold": "tma_lcp > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+        "PublicDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs). Using proper compiler flags or Intel Compiler by default will certainly avoid this. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation)",
+        "BriefDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations , instructions that require no more than one uop (micro-operation)",
         "MetricExpr": "tma_retiring - tma_heavy_operations",
         "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group",
         "MetricName": "tma_light_operations",
         "MetricThreshold": "tma_light_operations > 0.6",
         "MetricgroupNoGroup": "TopdownL2",
-        "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized code running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. ([ICL+] Note this may undercount due to approximation using indirect events; [ADL+] .). Sample with: INST_RETIRED.PREC_DIST",
+        "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations , instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized code running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. ([ICL+] Note this may undercount due to approximation using indirect events; [ADL+] .). Sample with: INST_RETIRED.PREC_DIST",
         "ScaleUnit": "100%"
     },
     {
@@ -905,18 +933,18 @@
         "MetricExpr": "200 * (MEM_LOAD_UOPS_L3_MISS_RETIRED.LOCAL_DRAM * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.L3_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_L3_MISS_RETIRED.LOCAL_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_HITM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_FWD))) / tma_info_thread_clks",
         "MetricGroup": "Server;TopdownL5;tma_L5_group;tma_mem_latency_group",
         "MetricName": "tma_local_mem",
-        "MetricThreshold": "tma_local_mem > 0.1 & (tma_mem_latency > 0.1 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))",
-        "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from local memory. Caching will improve the latency and increase performance. Sample with: MEM_LOAD_UOPS_L3_MISS_RETIRED.LOCAL_DRAM_PS",
+        "MetricThreshold": "tma_local_mem > 0.1 & tma_mem_latency > 0.1 & tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from local memory. Caching will improve the latency and increase performance. Sample with: MEM_LOAD_UOPS_L3_MISS_RETIRED.LOCAL_DRAM",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "This metric represents fraction of cycles the CPU spent handling cache misses due to lock operations",
         "MetricConstraint": "NO_GROUP_EVENTS",
         "MetricExpr": "MEM_UOPS_RETIRED.LOCK_LOADS / MEM_UOPS_RETIRED.ALL_STORES * min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO) / tma_info_thread_clks",
-        "MetricGroup": "Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_l1_bound_group",
+        "MetricGroup": "LockCont;Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_l1_bound_group",
         "MetricName": "tma_lock_latency",
-        "MetricThreshold": "tma_lock_latency > 0.2 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
-        "PublicDescription": "This metric represents fraction of cycles the CPU spent handling cache misses due to lock operations. Due to the microarchitecture handling of locks; they are classified as L1_Bound regardless of what memory source satisfied them. Sample with: MEM_UOPS_RETIRED.LOCK_LOADS_PS. Related metrics: tma_store_latency",
+        "MetricThreshold": "tma_lock_latency > 0.2 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "PublicDescription": "This metric represents fraction of cycles the CPU spent handling cache misses due to lock operations. Due to the microarchitecture handling of locks; they are classified as L1_Bound regardless of what memory source satisfied them. Sample with: MEM_UOPS_RETIRED.LOCK_LOADS. Related metrics: tma_store_latency",
         "ScaleUnit": "100%"
     },
     {
@@ -927,15 +955,15 @@
         "MetricName": "tma_machine_clears",
         "MetricThreshold": "tma_machine_clears > 0.1 & tma_bad_speculation > 0.15",
         "MetricgroupNoGroup": "TopdownL2",
-        "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears.  These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT. Related metrics: tma_clears_resteers, tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_l1_bound, tma_microcode_sequencer, tma_ms_switches, tma_remote_cache",
+        "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears.  These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT. Related metrics: tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_l1_bound, tma_microcode_sequencer, tma_ms_switches, tma_remote_cache",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory - DRAM ([SPR-HBM] and/or HBM)",
-        "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, cpu@OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD\\,cmask\\=6@) / tma_info_thread_clks",
-        "MetricGroup": "BvMS;MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueBW",
+        "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, cpu@OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD\\,cmask\\=0x6@) / tma_info_thread_clks",
+        "MetricGroup": "BvMB;MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueBW",
         "MetricName": "tma_mem_bandwidth",
-        "MetricThreshold": "tma_mem_bandwidth > 0.2 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+        "MetricThreshold": "tma_mem_bandwidth > 0.2 & tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
         "PublicDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory - DRAM ([SPR-HBM] and/or HBM).  The underlying heuristic assumes that a similar off-core traffic is generated by all IA cores. This metric does not aggregate non-data-read requests by this logical processor; requests from other IA Logical Processors/Physical Cores/sockets; or other non-IA devices like GPU; hence the maximum external memory bandwidth limits may or may not be approached when this metric is flagged (see Uncore counters for that). Related metrics: tma_fb_full, tma_info_system_dram_bw_use, tma_sq_full",
         "ScaleUnit": "100%"
     },
@@ -944,19 +972,19 @@
         "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD) / tma_info_thread_clks - tma_mem_bandwidth",
         "MetricGroup": "BvML;MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueLat",
         "MetricName": "tma_mem_latency",
-        "MetricThreshold": "tma_mem_latency > 0.1 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+        "MetricThreshold": "tma_mem_latency > 0.1 & tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
         "PublicDescription": "This metric estimates fraction of cycles where the performance was likely hurt due to latency from external memory - DRAM ([SPR-HBM] and/or HBM).  This metric does not aggregate requests from other Logical Processors/Physical Cores/sockets (see Uncore counters for that). Related metrics: tma_l3_hit_latency",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck",
         "MetricConstraint": "NO_GROUP_EVENTS",
-        "MetricExpr": "((min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.STALLS_LDM_PENDING) + RESOURCE_STALLS.SB) / (min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.CYCLES_NO_EXECUTE) + (cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ - (cpu@UOPS_EXECUTED.CORE\\,cmask\\=3@ if tma_info_thread_ipc > 1.8 else cpu@UOPS_EXECUTED.CORE\\,cmask\\=2@)) / 2 - (RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else 0) + RESOURCE_STALLS.SB) if #SMT_on else min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.CYCLES_NO_EXECUTE) + cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ - (cpu@UOPS_EXECUTED.CORE\\,cmask\\=3@ if tma_info_thread_ipc > 1.8 else cpu@UOPS_EXECUTED.CORE\\,cmask\\=2@) - (RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else 0) + RESOURCE_STALLS.SB) * tma_backend_bound",
+        "MetricExpr": "(min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.STALLS_LDM_PENDING) + RESOURCE_STALLS.SB) / (min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.CYCLES_NO_EXECUTE) + (cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x1@ - (cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x3@ if tma_info_thread_ipc > 1.8 else cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x2@)) / 2 - (RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else 0) + RESOURCE_STALLS.SB if #SMT_on else min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.CYCLES_NO_EXECUTE) + cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x1@ - (cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x3@ if tma_info_thread_ipc > 1.8 else cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x2@) - (RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else 0) + RESOURCE_STALLS.SB) * tma_backend_bound",
         "MetricGroup": "Backend;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group",
         "MetricName": "tma_memory_bound",
         "MetricThreshold": "tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
         "MetricgroupNoGroup": "TopdownL2",
-        "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck.  Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two).",
+        "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck.  Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two)",
         "ScaleUnit": "100%"
     },
     {
@@ -965,7 +993,7 @@
         "MetricGroup": "MicroSeq;TopdownL3;tma_L3_group;tma_heavy_operations_group;tma_issueMC;tma_issueMS",
         "MetricName": "tma_microcode_sequencer",
         "MetricThreshold": "tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1",
-        "PublicDescription": "This metric represents fraction of slots the CPU was retiring uops fetched by the Microcode Sequencer (MS) unit.  The MS is used for CISC instructions not supported by the default decoders (like repeat move strings; or CPUID); or by microcode assists used to address some operation modes (like in Floating Point assists). These cases can often be avoided. Sample with: IDQ.MS_UOPS. Related metrics: tma_clears_resteers, tma_l1_bound, tma_machine_clears, tma_ms_switches",
+        "PublicDescription": "This metric represents fraction of slots the CPU was retiring uops fetched by the Microcode Sequencer (MS) unit.  The MS is used for CISC instructions not supported by the default decoders (like repeat move strings; or CPUID); or by microcode assists used to address some operation modes (like in Floating Point assists). These cases can often be avoided. Sample with: IDQ.MS_UOPS. Related metrics: tma_l1_bound, tma_machine_clears, tma_ms_switches",
         "ScaleUnit": "100%"
     },
     {
@@ -974,7 +1002,7 @@
         "MetricGroup": "DSBmiss;FetchBW;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group",
         "MetricName": "tma_mite",
         "MetricThreshold": "tma_mite > 0.1 & tma_fetch_bandwidth > 0.2",
-        "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to the MITE pipeline (the legacy decode pipeline). This pipeline is used for code that was not pre-cached in the DSB or LSD. For example; inefficiencies due to asymmetric decoders; use of long immediate or LCP can manifest as MITE fetch bandwidth bottleneck.",
+        "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to the MITE pipeline (the legacy decode pipeline). This pipeline is used for code that was not pre-cached in the DSB or LSD. For example; inefficiencies due to asymmetric decoders; use of long immediate or LCP can manifest as MITE fetch bandwidth bottleneck",
         "ScaleUnit": "100%"
     },
     {
@@ -982,8 +1010,8 @@
         "MetricExpr": "2 * IDQ.MS_SWITCHES / tma_info_thread_clks",
         "MetricGroup": "FetchLat;MicroSeq;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueMC;tma_issueMS;tma_issueMV;tma_issueSO",
         "MetricName": "tma_ms_switches",
-        "MetricThreshold": "tma_ms_switches > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)",
-        "PublicDescription": "This metric estimates the fraction of cycles when the CPU was stalled due to switches of uop delivery to the Microcode Sequencer (MS). Commonly used instructions are optimized for delivery by the DSB (decoded i-cache) or MITE (legacy instruction decode) pipelines. Certain operations cannot be handled natively by the execution pipeline; and must be performed by microcode (small programs injected into the execution stream). Switching to the MS too often can negatively impact performance. The MS is designated to deliver long uop flows required by CISC instructions like CPUID; or uncommon conditions like Floating Point Assists when dealing with Denormals. Sample with: IDQ.MS_SWITCHES. Related metrics: tma_clears_resteers, tma_l1_bound, tma_machine_clears, tma_microcode_sequencer, tma_mixing_vectors, tma_serializing_operation",
+        "MetricThreshold": "tma_ms_switches > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+        "PublicDescription": "This metric estimates the fraction of cycles when the CPU was stalled due to switches of uop delivery to the Microcode Sequencer (MS). Commonly used instructions are optimized for delivery by the DSB (decoded i-cache) or MITE (legacy instruction decode) pipelines. Certain operations cannot be handled natively by the execution pipeline; and must be performed by microcode (small programs injected into the execution stream). Switching to the MS too often can negatively impact performance. The MS is designated to deliver long uop flows required by CISC instructions like CPUID; or uncommon conditions like Floating Point Assists when dealing with Denormals. Sample with: IDQ.MS_SWITCHES. Related metrics: tma_l1_bound, tma_machine_clears, tma_microcode_sequencer",
         "ScaleUnit": "100%"
     },
     {
@@ -992,7 +1020,7 @@
         "MetricGroup": "Compute;TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P",
         "MetricName": "tma_port_0",
         "MetricThreshold": "tma_port_0 > 0.6",
-        "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 0 ([SNB+] ALU; [HSW+] ALU and 2nd branch). Sample with: UOPS_DISPATCHED_PORT.PORT_0. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2",
+        "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 0 ([SNB+] ALU; [HSW+] ALU and 2nd branch). Sample with: UOPS_DISPATCHED_PORT.PORT_0. Related metrics: tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2",
         "ScaleUnit": "100%"
     },
     {
@@ -1001,7 +1029,7 @@
         "MetricGroup": "TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P",
         "MetricName": "tma_port_1",
         "MetricThreshold": "tma_port_1 > 0.6",
-        "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 1 (ALU). Sample with: UOPS_DISPATCHED_PORT.PORT_1. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_5, tma_port_6, tma_ports_utilized_2",
+        "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 1 (ALU). Sample with: UOPS_DISPATCHED_PORT.PORT_1. Related metrics: tma_port_0, tma_port_5, tma_port_6, tma_ports_utilized_2",
         "ScaleUnit": "100%"
     },
     {
@@ -1037,7 +1065,7 @@
         "MetricGroup": "TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P",
         "MetricName": "tma_port_5",
         "MetricThreshold": "tma_port_5 > 0.6",
-        "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 5 ([SNB+] Branches and ALU; [HSW+] ALU). Sample with: UOPS_DISPATCHED.PORT_5. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_6, tma_ports_utilized_2",
+        "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 5 ([SNB+] Branches and ALU; [HSW+] ALU). Sample with: UOPS_DISPATCHED_PORT.PORT_5. Related metrics: tma_port_0, tma_port_1, tma_port_6, tma_ports_utilized_2",
         "ScaleUnit": "100%"
     },
     {
@@ -1046,7 +1074,7 @@
         "MetricGroup": "TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P",
         "MetricName": "tma_port_6",
         "MetricThreshold": "tma_port_6 > 0.6",
-        "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 6 ([HSW+] Primary Branch and simple ALU). Sample with: UOPS_DISPATCHED_PORT.PORT_6. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_ports_utilized_2",
+        "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 6 ([HSW+] Primary Branch and simple ALU). Sample with: UOPS_DISPATCHED_PORT.PORT_1. Related metrics: tma_port_0, tma_port_1, tma_port_5, tma_ports_utilized_2",
         "ScaleUnit": "100%"
     },
     {
@@ -1061,46 +1089,46 @@
     {
         "BriefDescription": "This metric estimates fraction of cycles the CPU performance was potentially limited due to Core computation issues (non divider-related)",
         "MetricConstraint": "NO_GROUP_EVENTS",
-        "MetricExpr": "(min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.CYCLES_NO_EXECUTE) + (cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ - (cpu@UOPS_EXECUTED.CORE\\,cmask\\=3@ if tma_info_thread_ipc > 1.8 else cpu@UOPS_EXECUTED.CORE\\,cmask\\=2@)) / 2 - (RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else 0) + RESOURCE_STALLS.SB if #SMT_on else min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.CYCLES_NO_EXECUTE) + cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ - (cpu@UOPS_EXECUTED.CORE\\,cmask\\=3@ if tma_info_thread_ipc > 1.8 else cpu@UOPS_EXECUTED.CORE\\,cmask\\=2@) - (RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else 0) + RESOURCE_STALLS.SB - RESOURCE_STALLS.SB - min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.STALLS_LDM_PENDING)) / tma_info_thread_clks",
+        "MetricExpr": "((min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.CYCLES_NO_EXECUTE) + (cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x1@ - (cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x3@ if tma_info_thread_ipc > 1.8 else cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x2@)) / 2 - (RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else 0) + RESOURCE_STALLS.SB if #SMT_on else min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.CYCLES_NO_EXECUTE) + cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x1@ - (cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x3@ if tma_info_thread_ipc > 1.8 else cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x2@) - (RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else 0) + RESOURCE_STALLS.SB) - RESOURCE_STALLS.SB - min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.STALLS_LDM_PENDING)) / tma_info_thread_clks",
         "MetricGroup": "PortsUtil;TopdownL3;tma_L3_group;tma_core_bound_group",
         "MetricName": "tma_ports_utilization",
-        "MetricThreshold": "tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)",
-        "PublicDescription": "This metric estimates fraction of cycles the CPU performance was potentially limited due to Core computation issues (non divider-related).  Two distinct categories can be attributed into this metric: (1) heavy data-dependency among contiguous instructions would manifest in this metric - such cases are often referred to as low Instruction Level Parallelism (ILP). (2) Contention on some hardware execution unit other than Divider. For example; when there are too many multiply operations.",
+        "MetricThreshold": "tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
+        "PublicDescription": "This metric estimates fraction of cycles the CPU performance was potentially limited due to Core computation issues (non divider-related).  Two distinct categories can be attributed into this metric: (1) heavy data-dependency among contiguous instructions would manifest in this metric - such cases are often referred to as low Instruction Level Parallelism (ILP). (2) Contention on some hardware execution unit other than Divider. For example; when there are too many multiply operations",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "This metric represents fraction of cycles CPU executed no uops on any execution port (Logical Processor cycles since ICL, Physical Core cycles otherwise)",
-        "MetricExpr": "(cpu@UOPS_EXECUTED.CORE\\,inv\\,cmask\\=1@ / 2 if #SMT_on else (min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.CYCLES_NO_EXECUTE) - (RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else 0)) / tma_info_core_core_clks)",
+        "MetricExpr": "(cpu@UOPS_EXECUTED.CORE\\,inv\\=0x1\\,cmask\\=0x1@ / 2 if #SMT_on else min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.CYCLES_NO_EXECUTE) - (RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else 0)) / tma_info_core_core_clks",
         "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group",
         "MetricName": "tma_ports_utilized_0",
-        "MetricThreshold": "tma_ports_utilized_0 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))",
-        "PublicDescription": "This metric represents fraction of cycles CPU executed no uops on any execution port (Logical Processor cycles since ICL, Physical Core cycles otherwise). Long-latency instructions like divides may contribute to this metric.",
+        "MetricThreshold": "tma_ports_utilized_0 > 0.2 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
+        "PublicDescription": "This metric represents fraction of cycles CPU executed no uops on any execution port (Logical Processor cycles since ICL, Physical Core cycles otherwise). Long-latency instructions like divides may contribute to this metric",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "This metric represents fraction of cycles where the CPU executed total of 1 uop per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise)",
-        "MetricExpr": "((cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ - cpu@UOPS_EXECUTED.CORE\\,cmask\\=2@) / 2 if #SMT_on else (cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ - cpu@UOPS_EXECUTED.CORE\\,cmask\\=2@) / tma_info_core_core_clks)",
+        "MetricExpr": "((cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x1@ - cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x2@) / 2 if #SMT_on else cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x1@ - cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x2@) / tma_info_core_core_clks",
         "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_issueL1;tma_ports_utilization_group",
         "MetricName": "tma_ports_utilized_1",
-        "MetricThreshold": "tma_ports_utilized_1 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))",
+        "MetricThreshold": "tma_ports_utilized_1 > 0.2 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
         "PublicDescription": "This metric represents fraction of cycles where the CPU executed total of 1 uop per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise). This can be due to heavy data-dependency among software instructions; or over oversubscribing a particular hardware resource. In some other cases with high 1_Port_Utilized and L1_Bound; this metric can point to L1 data-cache latency bottleneck that may not necessarily manifest with complete execution starvation (due to the short L1 latency e.g. walking a linked list) - looking at the assembly can be helpful. Related metrics: tma_l1_bound",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "This metric represents fraction of cycles CPU executed total of 2 uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise)",
-        "MetricExpr": "((cpu@UOPS_EXECUTED.CORE\\,cmask\\=2@ - cpu@UOPS_EXECUTED.CORE\\,cmask\\=3@) / 2 if #SMT_on else (cpu@UOPS_EXECUTED.CORE\\,cmask\\=2@ - cpu@UOPS_EXECUTED.CORE\\,cmask\\=3@) / tma_info_core_core_clks)",
+        "MetricExpr": "((cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x2@ - cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x3@) / 2 if #SMT_on else cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x2@ - cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x3@) / tma_info_core_core_clks",
         "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_issue2P;tma_ports_utilization_group",
         "MetricName": "tma_ports_utilized_2",
-        "MetricThreshold": "tma_ports_utilized_2 > 0.15 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))",
-        "PublicDescription": "This metric represents fraction of cycles CPU executed total of 2 uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise).  Loop Vectorization -most compilers feature auto-Vectorization options today- reduces pressure on the execution ports as multiple elements are calculated with same uop. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6",
+        "MetricThreshold": "tma_ports_utilized_2 > 0.15 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
+        "PublicDescription": "This metric represents fraction of cycles CPU executed total of 2 uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise).  Loop Vectorization -most compilers feature auto-Vectorization options today- reduces pressure on the execution ports as multiple elements are calculated with same uop. Related metrics: tma_port_0, tma_port_1, tma_port_5, tma_port_6",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric represents fraction of cycles CPU executed total of 3 or more uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise).",
-        "MetricExpr": "(cpu@UOPS_EXECUTED.CORE\\,cmask\\=3@ / 2 if #SMT_on else cpu@UOPS_EXECUTED.CORE\\,cmask\\=3@) / tma_info_core_core_clks",
+        "BriefDescription": "This metric represents fraction of cycles CPU executed total of 3 or more uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise)",
+        "MetricExpr": "(cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x3@ / 2 if #SMT_on else cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x3@) / tma_info_core_core_clks",
         "MetricGroup": "BvCB;PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group",
         "MetricName": "tma_ports_utilized_3m",
-        "MetricThreshold": "tma_ports_utilized_3m > 0.4 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))",
+        "MetricThreshold": "tma_ports_utilized_3m > 0.4 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
         "ScaleUnit": "100%"
     },
     {
@@ -1109,8 +1137,8 @@
         "MetricExpr": "(200 * (MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_HITM * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.L3_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_L3_MISS_RETIRED.LOCAL_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_HITM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_FWD))) + 180 * (MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_FWD * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.L3_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_L3_MISS_RETIRED.LOCAL_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_HITM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_FWD)))) / tma_info_thread_clks",
         "MetricGroup": "Offcore;Server;Snoop;TopdownL5;tma_L5_group;tma_issueSyncxn;tma_mem_latency_group",
         "MetricName": "tma_remote_cache",
-        "MetricThreshold": "tma_remote_cache > 0.05 & (tma_mem_latency > 0.1 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))",
-        "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from remote cache in other sockets including synchronizations issues. This is caused often due to non-optimal NUMA allocations. #link to NUMA article. Sample with: MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_HITM_PS;MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_FWD_PS. Related metrics: tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_machine_clears",
+        "MetricThreshold": "tma_remote_cache > 0.05 & tma_mem_latency > 0.1 & tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from remote cache in other sockets including synchronizations issues. This is caused often due to non-optimal NUMA allocations. Sample with: MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_HITM, MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_FWD. Related metrics: tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_machine_clears",
         "ScaleUnit": "100%"
     },
     {
@@ -1118,8 +1146,8 @@
         "MetricExpr": "310 * (MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_DRAM * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.L3_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_L3_MISS_RETIRED.LOCAL_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_HITM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_FWD))) / tma_info_thread_clks",
         "MetricGroup": "Server;Snoop;TopdownL5;tma_L5_group;tma_mem_latency_group",
         "MetricName": "tma_remote_mem",
-        "MetricThreshold": "tma_remote_mem > 0.1 & (tma_mem_latency > 0.1 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))",
-        "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from remote memory. This is caused often due to non-optimal NUMA allocations. #link to NUMA article. Sample with: MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_DRAM_PS",
+        "MetricThreshold": "tma_remote_mem > 0.1 & tma_mem_latency > 0.1 & tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from remote memory. This is caused often due to non-optimal NUMA allocations. Sample with: MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_DRAM",
         "ScaleUnit": "100%"
     },
     {
@@ -1138,8 +1166,8 @@
         "MetricExpr": "tma_info_memory_load_miss_real_latency * LD_BLOCKS.NO_SR / tma_info_thread_clks",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group",
         "MetricName": "tma_split_loads",
-        "MetricThreshold": "tma_split_loads > 0.2 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
-        "PublicDescription": "This metric estimates fraction of cycles handling memory load split accesses - load that cross 64-byte cache line boundary. Sample with: MEM_UOPS_RETIRED.SPLIT_LOADS_PS",
+        "MetricThreshold": "tma_split_loads > 0.3",
+        "PublicDescription": "This metric estimates fraction of cycles handling memory load split accesses - load that cross 64-byte cache line boundary. Sample with: MEM_UOPS_RETIRED.SPLIT_LOADS",
         "ScaleUnit": "100%"
     },
     {
@@ -1147,16 +1175,16 @@
         "MetricExpr": "2 * MEM_UOPS_RETIRED.SPLIT_STORES / tma_info_core_core_clks",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_issueSpSt;tma_store_bound_group",
         "MetricName": "tma_split_stores",
-        "MetricThreshold": "tma_split_stores > 0.2 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
-        "PublicDescription": "This metric represents rate of split store accesses.  Consider aligning your data to the 64-byte cache line granularity. Sample with: MEM_UOPS_RETIRED.SPLIT_STORES_PS. Related metrics: tma_port_4",
+        "MetricThreshold": "tma_split_stores > 0.2 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "PublicDescription": "This metric represents rate of split store accesses.  Consider aligning your data to the 64-byte cache line granularity. Sample with: MEM_UOPS_RETIRED.SPLIT_STORES. Related metrics: tma_port_4",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors)",
         "MetricExpr": "(OFFCORE_REQUESTS_BUFFER.SQ_FULL / 2 if #SMT_on else OFFCORE_REQUESTS_BUFFER.SQ_FULL) / tma_info_core_core_clks",
-        "MetricGroup": "BvMS;MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_issueBW;tma_l3_bound_group",
+        "MetricGroup": "BvMB;MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_issueBW;tma_l3_bound_group",
         "MetricName": "tma_sq_full",
-        "MetricThreshold": "tma_sq_full > 0.3 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+        "MetricThreshold": "tma_sq_full > 0.3 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
         "PublicDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors). Related metrics: tma_fb_full, tma_info_system_dram_bw_use, tma_mem_bandwidth",
         "ScaleUnit": "100%"
     },
@@ -1165,8 +1193,8 @@
         "MetricExpr": "RESOURCE_STALLS.SB / tma_info_thread_clks",
         "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group",
         "MetricName": "tma_store_bound",
-        "MetricThreshold": "tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)",
-        "PublicDescription": "This metric estimates how often CPU was stalled  due to RFO store memory accesses; RFO store issue a read-for-ownership request before the write. Even though store accesses do not typically stall out-of-order CPUs; there are few cases where stores can lead to actual stalls. This metric will be flagged should RFO stores be a bottleneck. Sample with: MEM_UOPS_RETIRED.ALL_STORES_PS",
+        "MetricThreshold": "tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "PublicDescription": "This metric estimates how often CPU was stalled  due to RFO store memory accesses; RFO store issue a read-for-ownership request before the write. Even though store accesses do not typically stall out-of-order CPUs; there are few cases where stores can lead to actual stalls. This metric will be flagged should RFO stores be a bottleneck. Sample with: MEM_UOPS_RETIRED.ALL_STORES",
         "ScaleUnit": "100%"
     },
     {
@@ -1174,18 +1202,18 @@
         "MetricExpr": "13 * LD_BLOCKS.STORE_FORWARD / tma_info_thread_clks",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group",
         "MetricName": "tma_store_fwd_blk",
-        "MetricThreshold": "tma_store_fwd_blk > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
-        "PublicDescription": "This metric roughly estimates fraction of cycles when the memory subsystem had loads blocked since they could not forward data from earlier (in program order) overlapping stores. To streamline memory operations in the pipeline; a load can avoid waiting for memory if a prior in-flight store is writing the data that the load wants to read (store forwarding process). However; in some cases the load may be blocked for a significant time pending the store forward. For example; when the prior store is writing a smaller region than the load is reading.",
+        "MetricThreshold": "tma_store_fwd_blk > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "PublicDescription": "This metric roughly estimates fraction of cycles when the memory subsystem had loads blocked since they could not forward data from earlier (in program order) overlapping stores. To streamline memory operations in the pipeline; a load can avoid waiting for memory if a prior in-flight store is writing the data that the load wants to read (store forwarding process). However; in some cases the load may be blocked for a significant time pending the store forward. For example; when the prior store is writing a smaller region than the load is reading",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "This metric estimates fraction of cycles the CPU spent handling L1D store misses",
         "MetricConstraint": "NO_GROUP_EVENTS",
         "MetricExpr": "(L2_RQSTS.RFO_HIT * 9 * (1 - MEM_UOPS_RETIRED.LOCK_LOADS / MEM_UOPS_RETIRED.ALL_STORES) + (1 - MEM_UOPS_RETIRED.LOCK_LOADS / MEM_UOPS_RETIRED.ALL_STORES) * min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO)) / tma_info_thread_clks",
-        "MetricGroup": "BvML;MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_issueSL;tma_store_bound_group",
+        "MetricGroup": "BvML;LockCont;MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_issueSL;tma_store_bound_group",
         "MetricName": "tma_store_latency",
-        "MetricThreshold": "tma_store_latency > 0.1 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
-        "PublicDescription": "This metric estimates fraction of cycles the CPU spent handling L1D store misses. Store accesses usually less impact out-of-order core performance; however; holding resources for longer time can lead into undesired implications (e.g. contention on L1D fill-buffer entries - see FB_Full). Related metrics: tma_fb_full, tma_lock_latency",
+        "MetricThreshold": "tma_store_latency > 0.1 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "PublicDescription": "This metric estimates fraction of cycles the CPU spent handling L1D store misses. Store accesses usually less impact out-of-order core performance; however; holding resources for longer time can lead into undesired implications (e.g. contention on L1D fill-buffer entries - see FB_Full). Related metrics: tma_branch_resteers, tma_fb_full, tma_l3_hit_latency, tma_lock_latency",
         "ScaleUnit": "100%"
     },
     {
tools/perf/pmu-events/arch/x86/haswellx/metricgroups.json +5 -0
index 4193c90c3459..0863375bdead 100644
@@ -9,6 +9,7 @@
     "BvCB": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
     "BvFB": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
     "BvIO": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
+    "BvMB": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
     "BvML": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
     "BvMP": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
     "BvMS": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
@@ -34,6 +35,7 @@
     "InsType": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
     "L2Evicts": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
     "LSD": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
+    "LockCont": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
     "MachineClears": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
     "Machine_Clears": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
     "Mem": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
@@ -51,6 +53,7 @@
     "Pipeline": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
     "PortsUtil": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
     "Power": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
+    "Prefetches": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
     "Ret": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
     "Retire": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
     "SMT": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
@@ -78,6 +81,7 @@
     "tma_bad_speculation_group": "Metrics contributing to tma_bad_speculation category",
     "tma_branch_resteers_group": "Metrics contributing to tma_branch_resteers category",
     "tma_core_bound_group": "Metrics contributing to tma_core_bound category",
+    "tma_divider_group": "Metrics contributing to tma_divider category",
     "tma_dram_bound_group": "Metrics contributing to tma_dram_bound category",
     "tma_dtlb_load_group": "Metrics contributing to tma_dtlb_load category",
     "tma_dtlb_store_group": "Metrics contributing to tma_dtlb_store category",
@@ -103,6 +107,7 @@
     "tma_issueSpSt": "Metrics related by the issue $issueSpSt",
     "tma_issueSyncxn": "Metrics related by the issue $issueSyncxn",
     "tma_issueTLB": "Metrics related by the issue $issueTLB",
+    "tma_itlb_misses_group": "Metrics contributing to tma_itlb_misses category",
     "tma_l1_bound_group": "Metrics contributing to tma_l1_bound category",
     "tma_l3_bound_group": "Metrics contributing to tma_l3_bound category",
     "tma_light_operations_group": "Metrics contributing to tma_light_operations category",
tools/perf/pmu-events/arch/x86/haswellx/uncore-cache.json +14 -14
index 3c23bafcba28..d664af16c1db 100644
@@ -812,7 +812,7 @@
         "EventCode": "0x12",
         "EventName": "UNC_C_RxR_EXT_STARVED.IPQ",
         "PerPkg": "1",
-        "PublicDescription": "Counts cycles in external starvation.  This occurs when one of the ingress queues is being starved by the other queues.; IPQ is externally startved and therefore we are blocking the IRQ.",
+        "PublicDescription": "Counts cycles in external starvation.  This occurs when one of the ingress queues is being starved by the other queues.; IPQ is externally starved and therefore we are blocking the IRQ.",
         "UMask": "0x2",
         "Unit": "CBOX"
     },
@@ -1869,7 +1869,7 @@
         "EventCode": "0x14",
         "EventName": "UNC_H_BYPASS_IMC.NOT_TAKEN",
         "PerPkg": "1",
-        "PublicDescription": "Counts the number of times when the HA was able to bypass was attempted.  This is a latency optimization for situations when there is light loadings on the memory subsystem.  This can be filted by when the bypass was taken and when it was not.; Filter for transactions that could not take the bypass.",
+        "PublicDescription": "Counts the number of times when the HA was able to bypass was attempted.  This is a latency optimization for situations when there is light loadings on the memory subsystem.  This can be filtered by when the bypass was taken and when it was not.; Filter for transactions that could not take the bypass.",
         "UMask": "0x2",
         "Unit": "HA"
     },
@@ -1879,7 +1879,7 @@
         "EventCode": "0x14",
         "EventName": "UNC_H_BYPASS_IMC.TAKEN",
         "PerPkg": "1",
-        "PublicDescription": "Counts the number of times when the HA was able to bypass was attempted.  This is a latency optimization for situations when there is light loadings on the memory subsystem.  This can be filted by when the bypass was taken and when it was not.; Filter for transactions that succeeded in taking the bypass.",
+        "PublicDescription": "Counts the number of times when the HA was able to bypass was attempted.  This is a latency optimization for situations when there is light loadings on the memory subsystem.  This can be filtered by when the bypass was taken and when it was not.; Filter for transactions that succeeded in taking the bypass.",
         "UMask": "0x1",
         "Unit": "HA"
     },
@@ -2874,7 +2874,7 @@
         "EventCode": "0x15",
         "EventName": "UNC_H_RPQ_CYCLES_NO_REG_CREDITS.CHN0",
         "PerPkg": "1",
-        "PublicDescription": "Counts the number of cycles when there are no regular credits available for posting reads from the HA into the iMC.  In order to send reads into the memory controller, the HA must first acquire a credit for the iMC's RPQ (read pending queue).  This queue is broken into regular credits/buffers that are used by general reads, and special requests such as ISOCH reads.  This count only tracks the regular credits  Common high banwidth workloads should be able to make use of all of the regular buffers, but it will be difficult (and uncommon) to make use of both the regular and special buffers at the same time.  One can filter based on the memory controller channel.  One or more channels can be tracked at a given time.; Filter for memory controller channel 0 only.",
+        "PublicDescription": "Counts the number of cycles when there are no regular credits available for posting reads from the HA into the iMC.  In order to send reads into the memory controller, the HA must first acquire a credit for the iMC's RPQ (read pending queue).  This queue is broken into regular credits/buffers that are used by general reads, and special requests such as ISOCH reads.  This count only tracks the regular credits  Common high bandwidth workloads should be able to make use of all of the regular buffers, but it will be difficult (and uncommon) to make use of both the regular and special buffers at the same time.  One can filter based on the memory controller channel.  One or more channels can be tracked at a given time.; Filter for memory controller channel 0 only.",
         "UMask": "0x1",
         "Unit": "HA"
     },
@@ -2884,7 +2884,7 @@
         "EventCode": "0x15",
         "EventName": "UNC_H_RPQ_CYCLES_NO_REG_CREDITS.CHN1",
         "PerPkg": "1",
-        "PublicDescription": "Counts the number of cycles when there are no regular credits available for posting reads from the HA into the iMC.  In order to send reads into the memory controller, the HA must first acquire a credit for the iMC's RPQ (read pending queue).  This queue is broken into regular credits/buffers that are used by general reads, and special requests such as ISOCH reads.  This count only tracks the regular credits  Common high banwidth workloads should be able to make use of all of the regular buffers, but it will be difficult (and uncommon) to make use of both the regular and special buffers at the same time.  One can filter based on the memory controller channel.  One or more channels can be tracked at a given time.; Filter for memory controller channel 1 only.",
+        "PublicDescription": "Counts the number of cycles when there are no regular credits available for posting reads from the HA into the iMC.  In order to send reads into the memory controller, the HA must first acquire a credit for the iMC's RPQ (read pending queue).  This queue is broken into regular credits/buffers that are used by general reads, and special requests such as ISOCH reads.  This count only tracks the regular credits  Common high bandwidth workloads should be able to make use of all of the regular buffers, but it will be difficult (and uncommon) to make use of both the regular and special buffers at the same time.  One can filter based on the memory controller channel.  One or more channels can be tracked at a given time.; Filter for memory controller channel 1 only.",
         "UMask": "0x2",
         "Unit": "HA"
     },
@@ -2894,7 +2894,7 @@
         "EventCode": "0x15",
         "EventName": "UNC_H_RPQ_CYCLES_NO_REG_CREDITS.CHN2",
         "PerPkg": "1",
-        "PublicDescription": "Counts the number of cycles when there are no regular credits available for posting reads from the HA into the iMC.  In order to send reads into the memory controller, the HA must first acquire a credit for the iMC's RPQ (read pending queue).  This queue is broken into regular credits/buffers that are used by general reads, and special requests such as ISOCH reads.  This count only tracks the regular credits  Common high banwidth workloads should be able to make use of all of the regular buffers, but it will be difficult (and uncommon) to make use of both the regular and special buffers at the same time.  One can filter based on the memory controller channel.  One or more channels can be tracked at a given time.; Filter for memory controller channel 2 only.",
+        "PublicDescription": "Counts the number of cycles when there are no regular credits available for posting reads from the HA into the iMC.  In order to send reads into the memory controller, the HA must first acquire a credit for the iMC's RPQ (read pending queue).  This queue is broken into regular credits/buffers that are used by general reads, and special requests such as ISOCH reads.  This count only tracks the regular credits  Common high bandwidth workloads should be able to make use of all of the regular buffers, but it will be difficult (and uncommon) to make use of both the regular and special buffers at the same time.  One can filter based on the memory controller channel.  One or more channels can be tracked at a given time.; Filter for memory controller channel 2 only.",
         "UMask": "0x4",
         "Unit": "HA"
     },
@@ -2904,7 +2904,7 @@
         "EventCode": "0x15",
         "EventName": "UNC_H_RPQ_CYCLES_NO_REG_CREDITS.CHN3",
         "PerPkg": "1",
-        "PublicDescription": "Counts the number of cycles when there are no regular credits available for posting reads from the HA into the iMC.  In order to send reads into the memory controller, the HA must first acquire a credit for the iMC's RPQ (read pending queue).  This queue is broken into regular credits/buffers that are used by general reads, and special requests such as ISOCH reads.  This count only tracks the regular credits  Common high banwidth workloads should be able to make use of all of the regular buffers, but it will be difficult (and uncommon) to make use of both the regular and special buffers at the same time.  One can filter based on the memory controller channel.  One or more channels can be tracked at a given time.; Filter for memory controller channel 3 only.",
+        "PublicDescription": "Counts the number of cycles when there are no regular credits available for posting reads from the HA into the iMC.  In order to send reads into the memory controller, the HA must first acquire a credit for the iMC's RPQ (read pending queue).  This queue is broken into regular credits/buffers that are used by general reads, and special requests such as ISOCH reads.  This count only tracks the regular credits  Common high bandwidth workloads should be able to make use of all of the regular buffers, but it will be difficult (and uncommon) to make use of both the regular and special buffers at the same time.  One can filter based on the memory controller channel.  One or more channels can be tracked at a given time.; Filter for memory controller channel 3 only.",
         "UMask": "0x8",
         "Unit": "HA"
     },
@@ -3438,7 +3438,7 @@
         "EventCode": "0x3",
         "EventName": "UNC_H_TRACKER_CYCLES_NE.ALL",
         "PerPkg": "1",
-        "PublicDescription": "Counts the number of cycles when the local HA tracker pool is not empty.  This can be used with edge detect to identify the number of situations when the pool became empty.  This should not be confused with RTID credit usage -- which must be tracked inside each cbo individually -- but represents the actual tracker buffer structure.  In other words, this buffer could be completely empty, but there may still be credits in use by the CBos.  This stat can be used in conjunction with the occupancy accumulation stat in order to calculate average queue occpancy.  HA trackers are allocated as soon as a request enters the HA if an HT (Home Tracker) entry is available and is released after the snoop response and data return (or post in the case of a write) and the response is returned on the ring.; Requests coming from both local and remote sockets.",
+        "PublicDescription": "Counts the number of cycles when the local HA tracker pool is not empty.  This can be used with edge detect to identify the number of situations when the pool became empty.  This should not be confused with RTID credit usage -- which must be tracked inside each cbo individually -- but represents the actual tracker buffer structure.  In other words, this buffer could be completely empty, but there may still be credits in use by the CBos.  This stat can be used in conjunction with the occupancy accumulation stat in order to calculate average queue occupancy.  HA trackers are allocated as soon as a request enters the HA if an HT (Home Tracker) entry is available and is released after the snoop response and data return (or post in the case of a write) and the response is returned on the ring.; Requests coming from both local and remote sockets.",
         "UMask": "0x3",
         "Unit": "HA"
     },
@@ -3448,7 +3448,7 @@
         "EventCode": "0x3",
         "EventName": "UNC_H_TRACKER_CYCLES_NE.LOCAL",
         "PerPkg": "1",
-        "PublicDescription": "Counts the number of cycles when the local HA tracker pool is not empty.  This can be used with edge detect to identify the number of situations when the pool became empty.  This should not be confused with RTID credit usage -- which must be tracked inside each cbo individually -- but represents the actual tracker buffer structure.  In other words, this buffer could be completely empty, but there may still be credits in use by the CBos.  This stat can be used in conjunction with the occupancy accumulation stat in order to calculate average queue occpancy.  HA trackers are allocated as soon as a request enters the HA if an HT (Home Tracker) entry is available and is released after the snoop response and data return (or post in the case of a write) and the response is returned on the ring.; This filter includes only requests coming from the local socket.",
+        "PublicDescription": "Counts the number of cycles when the local HA tracker pool is not empty.  This can be used with edge detect to identify the number of situations when the pool became empty.  This should not be confused with RTID credit usage -- which must be tracked inside each cbo individually -- but represents the actual tracker buffer structure.  In other words, this buffer could be completely empty, but there may still be credits in use by the CBos.  This stat can be used in conjunction with the occupancy accumulation stat in order to calculate average queue occupancy.  HA trackers are allocated as soon as a request enters the HA if an HT (Home Tracker) entry is available and is released after the snoop response and data return (or post in the case of a write) and the response is returned on the ring.; This filter includes only requests coming from the local socket.",
         "UMask": "0x1",
         "Unit": "HA"
     },
@@ -3458,7 +3458,7 @@
         "EventCode": "0x3",
         "EventName": "UNC_H_TRACKER_CYCLES_NE.REMOTE",
         "PerPkg": "1",
-        "PublicDescription": "Counts the number of cycles when the local HA tracker pool is not empty.  This can be used with edge detect to identify the number of situations when the pool became empty.  This should not be confused with RTID credit usage -- which must be tracked inside each cbo individually -- but represents the actual tracker buffer structure.  In other words, this buffer could be completely empty, but there may still be credits in use by the CBos.  This stat can be used in conjunction with the occupancy accumulation stat in order to calculate average queue occpancy.  HA trackers are allocated as soon as a request enters the HA if an HT (Home Tracker) entry is available and is released after the snoop response and data return (or post in the case of a write) and the response is returned on the ring.; This filter includes only requests coming from remote sockets.",
+        "PublicDescription": "Counts the number of cycles when the local HA tracker pool is not empty.  This can be used with edge detect to identify the number of situations when the pool became empty.  This should not be confused with RTID credit usage -- which must be tracked inside each cbo individually -- but represents the actual tracker buffer structure.  In other words, this buffer could be completely empty, but there may still be credits in use by the CBos.  This stat can be used in conjunction with the occupancy accumulation stat in order to calculate average queue occupancy.  HA trackers are allocated as soon as a request enters the HA if an HT (Home Tracker) entry is available and is released after the snoop response and data return (or post in the case of a write) and the response is returned on the ring.; This filter includes only requests coming from remote sockets.",
         "UMask": "0x2",
         "Unit": "HA"
     },
@@ -3878,7 +3878,7 @@
         "EventCode": "0x18",
         "EventName": "UNC_H_WPQ_CYCLES_NO_REG_CREDITS.CHN0",
         "PerPkg": "1",
-        "PublicDescription": "Counts the number of cycles when there are no regular credits available for posting writes from the HA into the iMC.  In order to send writes into the memory controller, the HA must first acquire a credit for the iMC's WPQ (write pending queue).  This queue is broken into regular credits/buffers that are used by general writes, and special requests such as ISOCH writes.  This count only tracks the regular credits  Common high banwidth workloads should be able to make use of all of the regular buffers, but it will be difficult (and uncommon) to make use of both the regular and special buffers at the same time.  One can filter based on the memory controller channel.  One or more channels can be tracked at a given time.; Filter for memory controller channel 0 only.",
+        "PublicDescription": "Counts the number of cycles when there are no regular credits available for posting writes from the HA into the iMC.  In order to send writes into the memory controller, the HA must first acquire a credit for the iMC's WPQ (write pending queue).  This queue is broken into regular credits/buffers that are used by general writes, and special requests such as ISOCH writes.  This count only tracks the regular credits  Common high bandwidth workloads should be able to make use of all of the regular buffers, but it will be difficult (and uncommon) to make use of both the regular and special buffers at the same time.  One can filter based on the memory controller channel.  One or more channels can be tracked at a given time.; Filter for memory controller channel 0 only.",
         "UMask": "0x1",
         "Unit": "HA"
     },
@@ -3888,7 +3888,7 @@
         "EventCode": "0x18",
         "EventName": "UNC_H_WPQ_CYCLES_NO_REG_CREDITS.CHN1",
         "PerPkg": "1",
-        "PublicDescription": "Counts the number of cycles when there are no regular credits available for posting writes from the HA into the iMC.  In order to send writes into the memory controller, the HA must first acquire a credit for the iMC's WPQ (write pending queue).  This queue is broken into regular credits/buffers that are used by general writes, and special requests such as ISOCH writes.  This count only tracks the regular credits  Common high banwidth workloads should be able to make use of all of the regular buffers, but it will be difficult (and uncommon) to make use of both the regular and special buffers at the same time.  One can filter based on the memory controller channel.  One or more channels can be tracked at a given time.; Filter for memory controller channel 1 only.",
+        "PublicDescription": "Counts the number of cycles when there are no regular credits available for posting writes from the HA into the iMC.  In order to send writes into the memory controller, the HA must first acquire a credit for the iMC's WPQ (write pending queue).  This queue is broken into regular credits/buffers that are used by general writes, and special requests such as ISOCH writes.  This count only tracks the regular credits  Common high bandwidth workloads should be able to make use of all of the regular buffers, but it will be difficult (and uncommon) to make use of both the regular and special buffers at the same time.  One can filter based on the memory controller channel.  One or more channels can be tracked at a given time.; Filter for memory controller channel 1 only.",
         "UMask": "0x2",
         "Unit": "HA"
     },
@@ -3898,7 +3898,7 @@
         "EventCode": "0x18",
         "EventName": "UNC_H_WPQ_CYCLES_NO_REG_CREDITS.CHN2",
         "PerPkg": "1",
-        "PublicDescription": "Counts the number of cycles when there are no regular credits available for posting writes from the HA into the iMC.  In order to send writes into the memory controller, the HA must first acquire a credit for the iMC's WPQ (write pending queue).  This queue is broken into regular credits/buffers that are used by general writes, and special requests such as ISOCH writes.  This count only tracks the regular credits  Common high banwidth workloads should be able to make use of all of the regular buffers, but it will be difficult (and uncommon) to make use of both the regular and special buffers at the same time.  One can filter based on the memory controller channel.  One or more channels can be tracked at a given time.; Filter for memory controller channel 2 only.",
+        "PublicDescription": "Counts the number of cycles when there are no regular credits available for posting writes from the HA into the iMC.  In order to send writes into the memory controller, the HA must first acquire a credit for the iMC's WPQ (write pending queue).  This queue is broken into regular credits/buffers that are used by general writes, and special requests such as ISOCH writes.  This count only tracks the regular credits  Common high bandwidth workloads should be able to make use of all of the regular buffers, but it will be difficult (and uncommon) to make use of both the regular and special buffers at the same time.  One can filter based on the memory controller channel.  One or more channels can be tracked at a given time.; Filter for memory controller channel 2 only.",
         "UMask": "0x4",
         "Unit": "HA"
     },
@@ -3908,7 +3908,7 @@
         "EventCode": "0x18",
         "EventName": "UNC_H_WPQ_CYCLES_NO_REG_CREDITS.CHN3",
         "PerPkg": "1",
-        "PublicDescription": "Counts the number of cycles when there are no regular credits available for posting writes from the HA into the iMC.  In order to send writes into the memory controller, the HA must first acquire a credit for the iMC's WPQ (write pending queue).  This queue is broken into regular credits/buffers that are used by general writes, and special requests such as ISOCH writes.  This count only tracks the regular credits  Common high banwidth workloads should be able to make use of all of the regular buffers, but it will be difficult (and uncommon) to make use of both the regular and special buffers at the same time.  One can filter based on the memory controller channel.  One or more channels can be tracked at a given time.; Filter for memory controller channel 3 only.",
+        "PublicDescription": "Counts the number of cycles when there are no regular credits available for posting writes from the HA into the iMC.  In order to send writes into the memory controller, the HA must first acquire a credit for the iMC's WPQ (write pending queue).  This queue is broken into regular credits/buffers that are used by general writes, and special requests such as ISOCH writes.  This count only tracks the regular credits  Common high bandwidth workloads should be able to make use of all of the regular buffers, but it will be difficult (and uncommon) to make use of both the regular and special buffers at the same time.  One can filter based on the memory controller channel.  One or more channels can be tracked at a given time.; Filter for memory controller channel 3 only.",
         "UMask": "0x8",
         "Unit": "HA"
     },
tools/perf/pmu-events/arch/x86/haswellx/uncore-interconnect.json +9 -29
index 121de411d312..8f73a8649b39 100644
@@ -1,24 +1,4 @@
 [
-    {
-        "BriefDescription": "Number of non data (control) flits transmitted . Derived from unc_q_txl_flits_g0.non_data",
-        "Counter": "0,1,2,3",
-        "EventName": "QPI_CTL_BANDWIDTH_TX",
-        "PerPkg": "1",
-        "PublicDescription": "Counts the number of flits transmitted across the QPI Link.  It includes filters for Idle, protocol, and Data Flits.  Each flit is made up of 80 bits of information (in addition to some ECC data).  In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data).   In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit.  When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits.  Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed.  One can calculate the bandwidth of the link by taking: flits*80b/time.  Note that this is not the same as data bandwidth.  For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information.  To calculate data bandwidth, one should therefore do: data flits * 8B / time (for L0) or 4B instead of 8B for L0p.; Number of non-NULL non-data flits transmitted across QPI.  This basically tracks the protocol overhead on the QPI link.  One can get a good picture of the QPI-link characteristics by evaluating the protocol flits, data flits, and idle/null flits.  This includes the header flits for data packets.",
-        "ScaleUnit": "8Bytes",
-        "UMask": "0x4",
-        "Unit": "QPI"
-    },
-    {
-        "BriefDescription": "Number of data flits transmitted . Derived from unc_q_txl_flits_g0.data",
-        "Counter": "0,1,2,3",
-        "EventName": "QPI_DATA_BANDWIDTH_TX",
-        "PerPkg": "1",
-        "PublicDescription": "Counts the number of flits transmitted across the QPI Link.  It includes filters for Idle, protocol, and Data Flits.  Each flit is made up of 80 bits of information (in addition to some ECC data).  In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data).   In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit.  When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits.  Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed.  One can calculate the bandwidth of the link by taking: flits*80b/time.  Note that this is not the same as data bandwidth.  For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information.  To calculate data bandwidth, one should therefore do: data flits * 8B / time (for L0) or 4B instead of 8B for L0p.; Number of data flits transmitted over QPI.  Each flit contains 64b of data.  This includes both DRS and NCB data flits (coherent and non-coherent).  This can be used to calculate the data bandwidth of the QPI link.  One can get a good picture of the QPI-link characteristics by evaluating the protocol flits, data flits, and idle/null flits.  This does not include the header flits that go in data packets.",
-        "ScaleUnit": "8Bytes",
-        "UMask": "0x2",
-        "Unit": "QPI"
-    },
     {
         "BriefDescription": "Total Write Cache Occupancy; Any Source",
         "Counter": "0,1",
@@ -53,7 +33,7 @@
         "EventCode": "0x13",
         "EventName": "UNC_I_COHERENT_OPS.CLFLUSH",
         "PerPkg": "1",
-        "PublicDescription": "Counts the number of coherency related operations servied by the IRP",
+        "PublicDescription": "Counts the number of coherency related operations serviced by the IRP",
         "UMask": "0x80",
         "Unit": "IRP"
     },
@@ -63,7 +43,7 @@
         "EventCode": "0x13",
         "EventName": "UNC_I_COHERENT_OPS.CRD",
         "PerPkg": "1",
-        "PublicDescription": "Counts the number of coherency related operations servied by the IRP",
+        "PublicDescription": "Counts the number of coherency related operations serviced by the IRP",
         "UMask": "0x2",
         "Unit": "IRP"
     },
@@ -73,7 +53,7 @@
         "EventCode": "0x13",
         "EventName": "UNC_I_COHERENT_OPS.DRD",
         "PerPkg": "1",
-        "PublicDescription": "Counts the number of coherency related operations servied by the IRP",
+        "PublicDescription": "Counts the number of coherency related operations serviced by the IRP",
         "UMask": "0x4",
         "Unit": "IRP"
     },
@@ -83,7 +63,7 @@
         "EventCode": "0x13",
         "EventName": "UNC_I_COHERENT_OPS.PCIDCAHINT",
         "PerPkg": "1",
-        "PublicDescription": "Counts the number of coherency related operations servied by the IRP",
+        "PublicDescription": "Counts the number of coherency related operations serviced by the IRP",
         "UMask": "0x20",
         "Unit": "IRP"
     },
@@ -93,7 +73,7 @@
         "EventCode": "0x13",
         "EventName": "UNC_I_COHERENT_OPS.PCIRDCUR",
         "PerPkg": "1",
-        "PublicDescription": "Counts the number of coherency related operations servied by the IRP",
+        "PublicDescription": "Counts the number of coherency related operations serviced by the IRP",
         "UMask": "0x1",
         "Unit": "IRP"
     },
@@ -103,7 +83,7 @@
         "EventCode": "0x13",
         "EventName": "UNC_I_COHERENT_OPS.PCITOM",
         "PerPkg": "1",
-        "PublicDescription": "Counts the number of coherency related operations servied by the IRP",
+        "PublicDescription": "Counts the number of coherency related operations serviced by the IRP",
         "UMask": "0x10",
         "Unit": "IRP"
     },
@@ -113,7 +93,7 @@
         "EventCode": "0x13",
         "EventName": "UNC_I_COHERENT_OPS.RFO",
         "PerPkg": "1",
-        "PublicDescription": "Counts the number of coherency related operations servied by the IRP",
+        "PublicDescription": "Counts the number of coherency related operations serviced by the IRP",
         "UMask": "0x8",
         "Unit": "IRP"
     },
@@ -123,7 +103,7 @@
         "EventCode": "0x13",
         "EventName": "UNC_I_COHERENT_OPS.WBMTOI",
         "PerPkg": "1",
-        "PublicDescription": "Counts the number of coherency related operations servied by the IRP",
+        "PublicDescription": "Counts the number of coherency related operations serviced by the IRP",
         "UMask": "0x40",
         "Unit": "IRP"
     },
@@ -493,7 +473,7 @@
         "EventCode": "0x16",
         "EventName": "UNC_I_TRANSACTIONS.WRITES",
         "PerPkg": "1",
-        "PublicDescription": "Counts the number of Inbound transactions from the IRP to the Uncore.  This can be filtered based on request type in addition to the source queue.  Note the special filtering equation.  We do OR-reduction on the request type.  If the SOURCE bit is set, then we also do AND qualification based on the source portID.; Trackes only write requests.  Each write request should have a prefetch, so there is no need to explicitly track these requests.  For writes that are tickled and have to retry, the counter will be incremented for each retry.",
+        "PublicDescription": "Counts the number of Inbound transactions from the IRP to the Uncore.  This can be filtered based on request type in addition to the source queue.  Note the special filtering equation.  We do OR-reduction on the request type.  If the SOURCE bit is set, then we also do AND qualification based on the source portID.; Tracks only write requests.  Each write request should have a prefetch, so there is no need to explicitly track these requests.  For writes that are tickled and have to retry, the counter will be incremented for each retry.",
         "UMask": "0x2",
         "Unit": "IRP"
     },
tools/perf/pmu-events/arch/x86/mapfile.csv +1 -1
index bd87a41a1de7..ab55929df484 100644
@@ -15,7 +15,7 @@ GenuineIntel-6-7A,v1.01,goldmontplus,core
 GenuineIntel-6-B6,v1.05,grandridge,core
 GenuineIntel-6-A[DE],v1.06,graniterapids,core
 GenuineIntel-6-(3C|45|46),v36,haswell,core
-GenuineIntel-6-3F,v28,haswellx,core
+GenuineIntel-6-3F,v29,haswellx,core
 GenuineIntel-6-7[DE],v1.22,icelake,core
 GenuineIntel-6-6[AC],v1.26,icelakex,core
 GenuineIntel-6-3A,v24,ivybridge,core
Signature · 1 line
2.48.1.502.g6dc24dfdaf-goog
author reviewer
#14 lore raw

PATCH v8 14/24 perf vendor events: Update Icelake events/metrics

In reply to Ian Rogers

Update events from v1.22 to v1.24.
Update TMA metrics from 4.8 to 5.02.

Bring in the event updates v1.24:
https://github.com/intel/perfmon/commit/d4f10746cf549466723d17cd214e1ee9cb7bac11

The TMA 5.02 update is from (with subsequent fixes):
https://github.com/intel/perfmon/commit/1d72913b2d938781fb28f3cc3507aaec5c22d782

---
 .../pmu-events/arch/x86/icelake/cache.json    |  34 +-
 .../pmu-events/arch/x86/icelake/frontend.json |  17 -
 .../arch/x86/icelake/icl-metrics.json         | 849 +++++++++---------
 .../pmu-events/arch/x86/icelake/memory.json   |  13 +-
 .../arch/x86/icelake/metricgroups.json        |  10 +-
 .../pmu-events/arch/x86/icelake/pipeline.json |  30 +-
 .../arch/x86/icelake/uncore-interconnect.json |  76 --
 .../arch/x86/icelake/uncore-other.json        |   2 +-
 .../arch/x86/icelake/virtual-memory.json      |  18 +
 tools/perf/pmu-events/arch/x86/mapfile.csv    |   2 +-
 10 files changed, 500 insertions(+), 551 deletions(-)
tools/perf/pmu-events/arch/x86/icelake/cache.json +12 -22
index 3508340acd0e..015f70f157d1 100644
@@ -75,11 +75,11 @@
         "UMask": "0x2"
     },
     {
-        "BriefDescription": "Non-modified cache lines that are silently dropped by L2 cache when triggered by an L2 cache fill.",
+        "BriefDescription": "Non-modified cache lines that are silently dropped by L2 cache.",
         "Counter": "0,1,2,3",
         "EventCode": "0xF2",
         "EventName": "L2_LINES_OUT.SILENT",
-        "PublicDescription": "Counts the number of lines that are silently dropped by L2 cache when triggered by an L2 cache fill. These lines are typically in Shared or Exclusive state. A non-threaded event.",
+        "PublicDescription": "Counts the number of lines that are silently dropped by L2 cache. These lines are typically in Shared or Exclusive state. A non-threaded event.",
         "SampleAfterValue": "200003",
         "UMask": "0x1"
     },
@@ -251,7 +251,6 @@
         "Data_LA": "1",
         "EventCode": "0xd0",
         "EventName": "MEM_INST_RETIRED.ALL_LOADS",
-        "PEBS": "1",
         "PublicDescription": "Counts all retired load instructions. This event accounts for SW prefetch instructions of PREFETCHNTA or PREFETCHT0/1/2 or PREFETCHW.",
         "SampleAfterValue": "1000003",
         "UMask": "0x81"
@@ -262,7 +261,6 @@
         "Data_LA": "1",
         "EventCode": "0xd0",
         "EventName": "MEM_INST_RETIRED.ALL_STORES",
-        "PEBS": "1",
         "PublicDescription": "Counts all retired store instructions.",
         "SampleAfterValue": "1000003",
         "UMask": "0x82"
@@ -273,7 +271,6 @@
         "Data_LA": "1",
         "EventCode": "0xd0",
         "EventName": "MEM_INST_RETIRED.ANY",
-        "PEBS": "1",
         "PublicDescription": "Counts all retired memory instructions - loads and stores.",
         "SampleAfterValue": "1000003",
         "UMask": "0x83"
@@ -284,7 +281,6 @@
         "Data_LA": "1",
         "EventCode": "0xd0",
         "EventName": "MEM_INST_RETIRED.LOCK_LOADS",
-        "PEBS": "1",
         "PublicDescription": "Counts retired load instructions with locked access.",
         "SampleAfterValue": "100007",
         "UMask": "0x21"
@@ -295,7 +291,6 @@
         "Data_LA": "1",
         "EventCode": "0xd0",
         "EventName": "MEM_INST_RETIRED.SPLIT_LOADS",
-        "PEBS": "1",
         "PublicDescription": "Counts retired load instructions that split across a cacheline boundary.",
         "SampleAfterValue": "100003",
         "UMask": "0x41"
@@ -306,7 +301,6 @@
         "Data_LA": "1",
         "EventCode": "0xd0",
         "EventName": "MEM_INST_RETIRED.SPLIT_STORES",
-        "PEBS": "1",
         "PublicDescription": "Counts retired store instructions that split across a cacheline boundary.",
         "SampleAfterValue": "100003",
         "UMask": "0x42"
@@ -317,7 +311,6 @@
         "Data_LA": "1",
         "EventCode": "0xd0",
         "EventName": "MEM_INST_RETIRED.STLB_MISS_LOADS",
-        "PEBS": "1",
         "PublicDescription": "Number of retired load instructions that (start a) miss in the 2nd-level TLB (STLB).",
         "SampleAfterValue": "100003",
         "UMask": "0x11"
@@ -328,7 +321,6 @@
         "Data_LA": "1",
         "EventCode": "0xd0",
         "EventName": "MEM_INST_RETIRED.STLB_MISS_STORES",
-        "PEBS": "1",
         "PublicDescription": "Number of retired store instructions that (start a) miss in the 2nd-level TLB (STLB).",
         "SampleAfterValue": "100003",
         "UMask": "0x12"
@@ -339,7 +331,6 @@
         "Data_LA": "1",
         "EventCode": "0xd2",
         "EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_HIT",
-        "PEBS": "1",
         "PublicDescription": "Counts retired load instructions whose data sources were L3 and cross-core snoop hits in on-pkg core cache.",
         "SampleAfterValue": "20011",
         "UMask": "0x2"
@@ -350,7 +341,6 @@
         "Data_LA": "1",
         "EventCode": "0xd2",
         "EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM",
-        "PEBS": "1",
         "PublicDescription": "Counts retired load instructions whose data sources were HitM responses from shared L3.",
         "SampleAfterValue": "20011",
         "UMask": "0x4"
@@ -361,7 +351,6 @@
         "Data_LA": "1",
         "EventCode": "0xd2",
         "EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS",
-        "PEBS": "1",
         "PublicDescription": "Counts the retired load instructions whose data sources were L3 hit and cross-core snoop missed in on-pkg core cache.",
         "SampleAfterValue": "20011",
         "UMask": "0x1"
@@ -372,7 +361,6 @@
         "Data_LA": "1",
         "EventCode": "0xd2",
         "EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_NONE",
-        "PEBS": "1",
         "PublicDescription": "Counts retired load instructions whose data sources were hits in L3 without snoops required.",
         "SampleAfterValue": "100003",
         "UMask": "0x8"
@@ -383,7 +371,6 @@
         "Data_LA": "1",
         "EventCode": "0xd4",
         "EventName": "MEM_LOAD_MISC_RETIRED.UC",
-        "PEBS": "1",
         "PublicDescription": "Retired instructions with at least one load to uncacheable memory-type, or at least one cache-line split locked access (Bus Lock).",
         "SampleAfterValue": "100007",
         "UMask": "0x4"
@@ -394,7 +381,6 @@
         "Data_LA": "1",
         "EventCode": "0xd1",
         "EventName": "MEM_LOAD_RETIRED.FB_HIT",
-        "PEBS": "1",
         "PublicDescription": "Counts retired load instructions with at least one uop was load missed in L1 but hit FB (Fill Buffers) due to preceding miss to the same cache line with data not ready.",
         "SampleAfterValue": "100007",
         "UMask": "0x40"
@@ -405,7 +391,6 @@
         "Data_LA": "1",
         "EventCode": "0xd1",
         "EventName": "MEM_LOAD_RETIRED.L1_HIT",
-        "PEBS": "1",
         "PublicDescription": "Counts retired load instructions with at least one uop that hit in the L1 data cache. This event includes all SW prefetches and lock instructions regardless of the data source.",
         "SampleAfterValue": "1000003",
         "UMask": "0x1"
@@ -416,7 +401,6 @@
         "Data_LA": "1",
         "EventCode": "0xd1",
         "EventName": "MEM_LOAD_RETIRED.L1_MISS",
-        "PEBS": "1",
         "PublicDescription": "Counts retired load instructions with at least one uop that missed in the L1 cache.",
         "SampleAfterValue": "200003",
         "UMask": "0x8"
@@ -427,7 +411,6 @@
         "Data_LA": "1",
         "EventCode": "0xd1",
         "EventName": "MEM_LOAD_RETIRED.L2_HIT",
-        "PEBS": "1",
         "PublicDescription": "Counts retired load instructions with L2 cache hits as data sources.",
         "SampleAfterValue": "200003",
         "UMask": "0x2"
@@ -438,7 +421,6 @@
         "Data_LA": "1",
         "EventCode": "0xd1",
         "EventName": "MEM_LOAD_RETIRED.L2_MISS",
-        "PEBS": "1",
         "PublicDescription": "Counts retired load instructions missed L2 cache as data sources.",
         "SampleAfterValue": "100021",
         "UMask": "0x10"
@@ -449,7 +431,6 @@
         "Data_LA": "1",
         "EventCode": "0xd1",
         "EventName": "MEM_LOAD_RETIRED.L3_HIT",
-        "PEBS": "1",
         "PublicDescription": "Counts retired load instructions with at least one uop that hit in the L3 cache.",
         "SampleAfterValue": "100021",
         "UMask": "0x4"
@@ -460,7 +441,6 @@
         "Data_LA": "1",
         "EventCode": "0xd1",
         "EventName": "MEM_LOAD_RETIRED.L3_MISS",
-        "PEBS": "1",
         "PublicDescription": "Counts retired load instructions with at least one uop that missed in the L3 cache.",
         "SampleAfterValue": "50021",
         "UMask": "0x20"
@@ -910,6 +890,16 @@
         "SampleAfterValue": "1000003",
         "UMask": "0x8"
     },
+    {
+        "BriefDescription": "Cycles with outstanding code read requests pending.",
+        "Counter": "0,1,2,3",
+        "CounterMask": "1",
+        "EventCode": "0x60",
+        "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_CODE_RD",
+        "PublicDescription": "Cycles with outstanding code read requests pending.  Code Read requests include both cacheable and non-cacheable Code Reads.  Requests are considered outstanding from the time they miss the core's L2 cache until the transaction completion message is sent to the requestor.",
+        "SampleAfterValue": "1000003",
+        "UMask": "0x2"
+    },
     {
         "BriefDescription": "Cycles where at least 1 outstanding Demand RFO request is pending.",
         "Counter": "0,1,2,3",
tools/perf/pmu-events/arch/x86/icelake/frontend.json +0 -17
index e7c7d4d4152d..7afa2436d584 100644
@@ -44,7 +44,6 @@
         "EventName": "FRONTEND_RETIRED.ANY_DSB_MISS",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x1",
-        "PEBS": "1",
         "PublicDescription": "Counts retired Instructions that experienced DSB (Decode stream buffer i.e. the decoded instruction-cache) miss.",
         "SampleAfterValue": "100007",
         "UMask": "0x1"
@@ -56,7 +55,6 @@
         "EventName": "FRONTEND_RETIRED.DSB_MISS",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x11",
-        "PEBS": "1",
         "PublicDescription": "Number of retired Instructions that experienced a critical DSB (Decode stream buffer i.e. the decoded instruction-cache) miss. Critical means stalls were exposed to the back-end as a result of the DSB miss.",
         "SampleAfterValue": "100007",
         "UMask": "0x1"
@@ -68,7 +66,6 @@
         "EventName": "FRONTEND_RETIRED.ITLB_MISS",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x14",
-        "PEBS": "1",
         "PublicDescription": "Counts retired Instructions that experienced iTLB (Instruction TLB) true miss.",
         "SampleAfterValue": "100007",
         "UMask": "0x1"
@@ -80,7 +77,6 @@
         "EventName": "FRONTEND_RETIRED.L1I_MISS",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x12",
-        "PEBS": "1",
         "PublicDescription": "Counts retired Instructions who experienced Instruction L1 Cache true miss.",
         "SampleAfterValue": "100007",
         "UMask": "0x1"
@@ -92,7 +88,6 @@
         "EventName": "FRONTEND_RETIRED.L2_MISS",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x13",
-        "PEBS": "1",
         "PublicDescription": "Counts retired Instructions who experienced Instruction L2 Cache true miss.",
         "SampleAfterValue": "100007",
         "UMask": "0x1"
@@ -104,7 +99,6 @@
         "EventName": "FRONTEND_RETIRED.LATENCY_GE_1",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x500106",
-        "PEBS": "1",
         "PublicDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of at least 1 cycle which was not interrupted by a back-end stall.",
         "SampleAfterValue": "100007",
         "UMask": "0x1"
@@ -116,7 +110,6 @@
         "EventName": "FRONTEND_RETIRED.LATENCY_GE_128",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x508006",
-        "PEBS": "1",
         "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 128 cycles which was not interrupted by a back-end stall.",
         "SampleAfterValue": "100007",
         "UMask": "0x1"
@@ -128,7 +121,6 @@
         "EventName": "FRONTEND_RETIRED.LATENCY_GE_16",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x501006",
-        "PEBS": "1",
         "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 16 cycles. During this period the front-end delivered no uops.",
         "SampleAfterValue": "100007",
         "UMask": "0x1"
@@ -140,7 +132,6 @@
         "EventName": "FRONTEND_RETIRED.LATENCY_GE_2",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x500206",
-        "PEBS": "1",
         "PublicDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of at least 2 cycles which was not interrupted by a back-end stall.",
         "SampleAfterValue": "100007",
         "UMask": "0x1"
@@ -152,7 +143,6 @@
         "EventName": "FRONTEND_RETIRED.LATENCY_GE_256",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x510006",
-        "PEBS": "1",
         "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 256 cycles which was not interrupted by a back-end stall.",
         "SampleAfterValue": "100007",
         "UMask": "0x1"
@@ -164,7 +154,6 @@
         "EventName": "FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x100206",
-        "PEBS": "1",
         "PublicDescription": "Counts retired instructions that are delivered to the back-end after the front-end had at least 1 bubble-slot for a period of 2 cycles. A bubble-slot is an empty issue-pipeline slot while there was no RAT stall.",
         "SampleAfterValue": "100007",
         "UMask": "0x1"
@@ -176,7 +165,6 @@
         "EventName": "FRONTEND_RETIRED.LATENCY_GE_32",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x502006",
-        "PEBS": "1",
         "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 32 cycles. During this period the front-end delivered no uops.",
         "SampleAfterValue": "100007",
         "UMask": "0x1"
@@ -188,7 +176,6 @@
         "EventName": "FRONTEND_RETIRED.LATENCY_GE_4",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x500406",
-        "PEBS": "1",
         "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 4 cycles which was not interrupted by a back-end stall.",
         "SampleAfterValue": "100007",
         "UMask": "0x1"
@@ -200,7 +187,6 @@
         "EventName": "FRONTEND_RETIRED.LATENCY_GE_512",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x520006",
-        "PEBS": "1",
         "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 512 cycles which was not interrupted by a back-end stall.",
         "SampleAfterValue": "100007",
         "UMask": "0x1"
@@ -212,7 +198,6 @@
         "EventName": "FRONTEND_RETIRED.LATENCY_GE_64",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x504006",
-        "PEBS": "1",
         "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 64 cycles which was not interrupted by a back-end stall.",
         "SampleAfterValue": "100007",
         "UMask": "0x1"
@@ -224,7 +209,6 @@
         "EventName": "FRONTEND_RETIRED.LATENCY_GE_8",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x500806",
-        "PEBS": "1",
         "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 8 cycles. During this period the front-end delivered no uops.",
         "SampleAfterValue": "100007",
         "UMask": "0x1"
@@ -236,7 +220,6 @@
         "EventName": "FRONTEND_RETIRED.STLB_MISS",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x15",
-        "PEBS": "1",
         "PublicDescription": "Counts retired Instructions that experienced STLB (2nd level TLB) true miss.",
         "SampleAfterValue": "100007",
         "UMask": "0x1"
tools/perf/pmu-events/arch/x86/icelake/icl-metrics.json +448 -401

1,639 lines not on this page · raw message

tools/perf/pmu-events/arch/x86/icelake/memory.json +2 -11
index f73035f44330..abaf3f4f9d63 100644
@@ -88,7 +88,6 @@
         "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_128",
         "MSRIndex": "0x3F6",
         "MSRValue": "0x80",
-        "PEBS": "2",
         "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 128 cycles.  Reported latency may be longer than just the memory latency.",
         "SampleAfterValue": "1009",
         "UMask": "0x1"
@@ -101,7 +100,6 @@
         "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_16",
         "MSRIndex": "0x3F6",
         "MSRValue": "0x10",
-        "PEBS": "2",
         "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 16 cycles.  Reported latency may be longer than just the memory latency.",
         "SampleAfterValue": "20011",
         "UMask": "0x1"
@@ -114,7 +112,6 @@
         "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_256",
         "MSRIndex": "0x3F6",
         "MSRValue": "0x100",
-        "PEBS": "2",
         "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 256 cycles.  Reported latency may be longer than just the memory latency.",
         "SampleAfterValue": "503",
         "UMask": "0x1"
@@ -127,7 +124,6 @@
         "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_32",
         "MSRIndex": "0x3F6",
         "MSRValue": "0x20",
-        "PEBS": "2",
         "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 32 cycles.  Reported latency may be longer than just the memory latency.",
         "SampleAfterValue": "100007",
         "UMask": "0x1"
@@ -140,7 +136,6 @@
         "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_4",
         "MSRIndex": "0x3F6",
         "MSRValue": "0x4",
-        "PEBS": "2",
         "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 4 cycles.  Reported latency may be longer than just the memory latency.",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
@@ -153,7 +148,6 @@
         "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_512",
         "MSRIndex": "0x3F6",
         "MSRValue": "0x200",
-        "PEBS": "2",
         "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 512 cycles.  Reported latency may be longer than just the memory latency.",
         "SampleAfterValue": "101",
         "UMask": "0x1"
@@ -166,7 +160,6 @@
         "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_64",
         "MSRIndex": "0x3F6",
         "MSRValue": "0x40",
-        "PEBS": "2",
         "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 64 cycles.  Reported latency may be longer than just the memory latency.",
         "SampleAfterValue": "2003",
         "UMask": "0x1"
@@ -179,7 +172,6 @@
         "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_8",
         "MSRIndex": "0x3F6",
         "MSRValue": "0x8",
-        "PEBS": "2",
         "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 8 cycles.  Reported latency may be longer than just the memory latency.",
         "SampleAfterValue": "50021",
         "UMask": "0x1"
@@ -287,17 +279,16 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc9",
         "EventName": "RTM_RETIRED.ABORTED",
-        "PEBS": "1",
         "PublicDescription": "Counts the number of times RTM abort was triggered.",
         "SampleAfterValue": "100003",
         "UMask": "0x4"
     },
     {
-        "BriefDescription": "Number of times an RTM execution aborted due to none of the previous 4 categories (e.g. interrupt)",
+        "BriefDescription": "Number of times an RTM execution aborted due to none of the previous 3 categories (e.g. interrupt)",
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc9",
         "EventName": "RTM_RETIRED.ABORTED_EVENTS",
-        "PublicDescription": "Counts the number of times an RTM execution aborted due to none of the previous 4 categories (e.g. interrupt).",
+        "PublicDescription": "Counts the number of times an RTM execution aborted due to none of the previous 3 categories (e.g. interrupt).",
         "SampleAfterValue": "100003",
         "UMask": "0x80"
     },
tools/perf/pmu-events/arch/x86/icelake/metricgroups.json +9 -1
index 3a88260194d1..80ca8021f2de 100644
@@ -37,6 +37,7 @@
     "InsType": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
     "L2Evicts": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
     "LSD": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
+    "LockCont": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
     "MachineClears": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
     "Machine_Clears": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
     "Mem": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
@@ -83,7 +84,9 @@
     "tma_bad_speculation_group": "Metrics contributing to tma_bad_speculation category",
     "tma_branch_mispredicts_group": "Metrics contributing to tma_branch_mispredicts category",
     "tma_branch_resteers_group": "Metrics contributing to tma_branch_resteers category",
+    "tma_code_stlb_miss_group": "Metrics contributing to tma_code_stlb_miss category",
     "tma_core_bound_group": "Metrics contributing to tma_core_bound category",
+    "tma_divider_group": "Metrics contributing to tma_divider category",
     "tma_dram_bound_group": "Metrics contributing to tma_dram_bound category",
     "tma_dtlb_load_group": "Metrics contributing to tma_dtlb_load category",
     "tma_dtlb_store_group": "Metrics contributing to tma_dtlb_store category",
@@ -93,6 +96,7 @@
     "tma_fp_vector_group": "Metrics contributing to tma_fp_vector category",
     "tma_frontend_bound_group": "Metrics contributing to tma_frontend_bound category",
     "tma_heavy_operations_group": "Metrics contributing to tma_heavy_operations category",
+    "tma_icache_misses_group": "Metrics contributing to tma_icache_misses category",
     "tma_issue2P": "Metrics related by the issue $issue2P",
     "tma_issueBM": "Metrics related by the issue $issueBM",
     "tma_issueBW": "Metrics related by the issue $issueBW",
@@ -112,10 +116,13 @@
     "tma_issueSpSt": "Metrics related by the issue $issueSpSt",
     "tma_issueSyncxn": "Metrics related by the issue $issueSyncxn",
     "tma_issueTLB": "Metrics related by the issue $issueTLB",
+    "tma_itlb_misses_group": "Metrics contributing to tma_itlb_misses category",
     "tma_l1_bound_group": "Metrics contributing to tma_l1_bound category",
+    "tma_l2_bound_group": "Metrics contributing to tma_l2_bound category",
     "tma_l3_bound_group": "Metrics contributing to tma_l3_bound category",
     "tma_light_operations_group": "Metrics contributing to tma_light_operations category",
     "tma_load_op_utilization_group": "Metrics contributing to tma_load_op_utilization category",
+    "tma_load_stlb_miss_group": "Metrics contributing to tma_load_stlb_miss category",
     "tma_machine_clears_group": "Metrics contributing to tma_machine_clears category",
     "tma_mem_latency_group": "Metrics contributing to tma_mem_latency category",
     "tma_memory_bound_group": "Metrics contributing to tma_memory_bound category",
@@ -128,5 +135,6 @@
     "tma_retiring_group": "Metrics contributing to tma_retiring category",
     "tma_serializing_operation_group": "Metrics contributing to tma_serializing_operation category",
     "tma_store_bound_group": "Metrics contributing to tma_store_bound category",
-    "tma_store_op_utilization_group": "Metrics contributing to tma_store_op_utilization category"
+    "tma_store_op_utilization_group": "Metrics contributing to tma_store_op_utilization category",
+    "tma_store_stlb_miss_group": "Metrics contributing to tma_store_stlb_miss category"
 }
tools/perf/pmu-events/arch/x86/icelake/pipeline.json +9 -21
index 4fdf07c7beb7..44659f26cbab 100644
@@ -9,6 +9,15 @@
         "SampleAfterValue": "1000003",
         "UMask": "0x9"
     },
+    {
+        "BriefDescription": "ARITH.FP_DIVIDER_ACTIVE",
+        "Counter": "0,1,2,3,4,5,6,7",
+        "CounterMask": "1",
+        "EventCode": "0x14",
+        "EventName": "ARITH.FP_DIVIDER_ACTIVE",
+        "SampleAfterValue": "1000003",
+        "UMask": "0x1"
+    },
     {
         "BriefDescription": "Number of occurrences where a microcode assist is invoked by hardware.",
         "Counter": "0,1,2,3,4,5,6,7",
@@ -23,7 +32,6 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc4",
         "EventName": "BR_INST_RETIRED.ALL_BRANCHES",
-        "PEBS": "1",
         "PublicDescription": "Counts all branch instructions retired.",
         "SampleAfterValue": "400009"
     },
@@ -32,7 +40,6 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc4",
         "EventName": "BR_INST_RETIRED.COND",
-        "PEBS": "1",
         "PublicDescription": "Counts conditional branch instructions retired.",
         "SampleAfterValue": "400009",
         "UMask": "0x11"
@@ -42,7 +49,6 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc4",
         "EventName": "BR_INST_RETIRED.COND_NTAKEN",
-        "PEBS": "1",
         "PublicDescription": "Counts not taken branch instructions retired.",
         "SampleAfterValue": "400009",
         "UMask": "0x10"
@@ -52,7 +58,6 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc4",
         "EventName": "BR_INST_RETIRED.COND_TAKEN",
-        "PEBS": "1",
         "PublicDescription": "Counts taken conditional branch instructions retired.",
         "SampleAfterValue": "400009",
         "UMask": "0x1"
@@ -62,7 +67,6 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc4",
         "EventName": "BR_INST_RETIRED.FAR_BRANCH",
-        "PEBS": "1",
         "PublicDescription": "Counts far branch instructions retired.",
         "SampleAfterValue": "100007",
         "UMask": "0x40"
@@ -72,7 +76,6 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc4",
         "EventName": "BR_INST_RETIRED.INDIRECT",
-        "PEBS": "1",
         "PublicDescription": "Counts near indirect branch instructions retired excluding returns. TSX abort is an indirect branch.",
         "SampleAfterValue": "100003",
         "UMask": "0x80"
@@ -82,7 +85,6 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc4",
         "EventName": "BR_INST_RETIRED.NEAR_CALL",
-        "PEBS": "1",
         "PublicDescription": "Counts both direct and indirect near call instructions retired.",
         "SampleAfterValue": "100007",
         "UMask": "0x2"
@@ -92,7 +94,6 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc4",
         "EventName": "BR_INST_RETIRED.NEAR_RETURN",
-        "PEBS": "1",
         "PublicDescription": "Counts return instructions retired.",
         "SampleAfterValue": "100007",
         "UMask": "0x8"
@@ -102,7 +103,6 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc4",
         "EventName": "BR_INST_RETIRED.NEAR_TAKEN",
-        "PEBS": "1",
         "PublicDescription": "Counts taken branch instructions retired.",
         "SampleAfterValue": "400009",
         "UMask": "0x20"
@@ -112,7 +112,6 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc5",
         "EventName": "BR_MISP_RETIRED.ALL_BRANCHES",
-        "PEBS": "1",
         "PublicDescription": "Counts all the retired branch instructions that were mispredicted by the processor. A branch misprediction occurs when the processor incorrectly predicts the destination of the branch.  When the misprediction is discovered at execution, all the instructions executed in the wrong (speculative) path must be discarded, and the processor must start fetching from the correct path.",
         "SampleAfterValue": "50021"
     },
@@ -121,7 +120,6 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc5",
         "EventName": "BR_MISP_RETIRED.COND",
-        "PEBS": "1",
         "PublicDescription": "Counts mispredicted conditional branch instructions retired.",
         "SampleAfterValue": "50021",
         "UMask": "0x11"
@@ -131,7 +129,6 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc5",
         "EventName": "BR_MISP_RETIRED.COND_NTAKEN",
-        "PEBS": "1",
         "PublicDescription": "Counts the number of conditional branch instructions retired that were mispredicted and the branch direction was not taken.",
         "SampleAfterValue": "50021",
         "UMask": "0x10"
@@ -141,7 +138,6 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc5",
         "EventName": "BR_MISP_RETIRED.COND_TAKEN",
-        "PEBS": "1",
         "PublicDescription": "Counts taken conditional mispredicted branch instructions retired.",
         "SampleAfterValue": "50021",
         "UMask": "0x1"
@@ -151,7 +147,6 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc5",
         "EventName": "BR_MISP_RETIRED.INDIRECT",
-        "PEBS": "1",
         "PublicDescription": "Counts all miss-predicted indirect branch instructions retired (excluding RETs. TSX aborts is considered indirect branch).",
         "SampleAfterValue": "50021",
         "UMask": "0x80"
@@ -161,7 +156,6 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc5",
         "EventName": "BR_MISP_RETIRED.INDIRECT_CALL",
-        "PEBS": "1",
         "PublicDescription": "Counts retired mispredicted indirect (near taken) CALL instructions, including both register and memory indirect.",
         "SampleAfterValue": "50021",
         "UMask": "0x2"
@@ -171,7 +165,6 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc5",
         "EventName": "BR_MISP_RETIRED.NEAR_TAKEN",
-        "PEBS": "1",
         "PublicDescription": "Counts number of near branch instructions retired that were mispredicted and taken.",
         "SampleAfterValue": "50021",
         "UMask": "0x20"
@@ -181,7 +174,6 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc5",
         "EventName": "BR_MISP_RETIRED.RET",
-        "PEBS": "1",
         "PublicDescription": "This is a non-precise version (that is, does not use PEBS) of the event that counts mispredicted return instructions retired.",
         "SampleAfterValue": "50021",
         "UMask": "0x8"
@@ -377,7 +369,6 @@
         "BriefDescription": "Number of instructions retired. Fixed Counter - architectural event",
         "Counter": "Fixed counter 0",
         "EventName": "INST_RETIRED.ANY",
-        "PEBS": "1",
         "PublicDescription": "Counts the number of instructions retired - an Architectural PerfMon event. Counting continues during hardware interrupts, traps, and inside interrupt handlers. Notes: INST_RETIRED.ANY is counted by a designated fixed counter freeing up programmable counters to count other events. INST_RETIRED.ANY_P is counted by a programmable counter.",
         "SampleAfterValue": "2000003",
         "UMask": "0x1"
@@ -387,7 +378,6 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc0",
         "EventName": "INST_RETIRED.ANY_P",
-        "PEBS": "1",
         "PublicDescription": "Counts the number of instructions retired - an Architectural PerfMon event. Counting continues during hardware interrupts, traps, and inside interrupt handlers. Notes: INST_RETIRED.ANY is counted by a designated fixed counter freeing up programmable counters to count other events. INST_RETIRED.ANY_P is counted by a programmable counter.",
         "SampleAfterValue": "2000003"
     },
@@ -396,7 +386,6 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc0",
         "EventName": "INST_RETIRED.NOP",
-        "PEBS": "1",
         "SampleAfterValue": "2000003",
         "UMask": "0x2"
     },
@@ -404,7 +393,6 @@
         "BriefDescription": "Precise instruction retired event with a reduced effect of PEBS shadow in IP distribution",
         "Counter": "Fixed counter 0",
         "EventName": "INST_RETIRED.PREC_DIST",
-        "PEBS": "1",
         "PublicDescription": "A version of INST_RETIRED that allows for a more unbiased distribution of samples across instructions retired. It utilizes the Precise Distribution of Instructions Retired (PDIR) feature to mitigate some bias in how retired instructions get sampled. Use on Fixed Counter 0.",
         "SampleAfterValue": "2000003",
         "UMask": "0x1"
tools/perf/pmu-events/arch/x86/icelake/uncore-interconnect.json +0 -76

87 lines not on this page · raw message

tools/perf/pmu-events/arch/x86/icelake/uncore-other.json +1 -1
index cc8110ac020c..1ac5b5ef8094 100644
@@ -1,6 +1,6 @@
 [
     {
-        "BriefDescription": "UNC_CLOCK.SOCKET",
+        "BriefDescription": "This 48-bit fixed counter counts the UCLK cycles.",
         "Counter": "FIXED",
         "EventCode": "0xff",
         "EventName": "UNC_CLOCK.SOCKET",
tools/perf/pmu-events/arch/x86/icelake/virtual-memory.json +18 -0
index 3ff51040f84f..9df790d4361f 100644
@@ -27,6 +27,15 @@
         "SampleAfterValue": "100003",
         "UMask": "0xe"
     },
+    {
+        "BriefDescription": "Page walks completed due to a demand data load to a 1G page.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x08",
+        "EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED_1G",
+        "PublicDescription": "Counts completed page walks  (1G sizes) caused by demand data loads. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.",
+        "SampleAfterValue": "100003",
+        "UMask": "0x8"
+    },
     {
         "BriefDescription": "Page walks completed due to a demand data load to a 2M/4M page.",
         "Counter": "0,1,2,3",
@@ -82,6 +91,15 @@
         "SampleAfterValue": "100003",
         "UMask": "0xe"
     },
+    {
+        "BriefDescription": "Page walks completed due to a demand data store to a 1G page.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x49",
+        "EventName": "DTLB_STORE_MISSES.WALK_COMPLETED_1G",
+        "PublicDescription": "Counts completed page walks  (1G sizes) caused by demand data stores. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.",
+        "SampleAfterValue": "100003",
+        "UMask": "0x8"
+    },
     {
         "BriefDescription": "Page walks completed due to a demand data store to a 2M/4M page.",
         "Counter": "0,1,2,3",
tools/perf/pmu-events/arch/x86/mapfile.csv +1 -1
index ab55929df484..f416ab2a4eea 100644
@@ -16,7 +16,7 @@ GenuineIntel-6-B6,v1.05,grandridge,core
 GenuineIntel-6-A[DE],v1.06,graniterapids,core
 GenuineIntel-6-(3C|45|46),v36,haswell,core
 GenuineIntel-6-3F,v29,haswellx,core
-GenuineIntel-6-7[DE],v1.22,icelake,core
+GenuineIntel-6-7[DE],v1.24,icelake,core
 GenuineIntel-6-6[AC],v1.26,icelakex,core
 GenuineIntel-6-3A,v24,ivybridge,core
 GenuineIntel-6-3E,v24,ivytown,core
Signature · 1 line
2.48.1.502.g6dc24dfdaf-goog