[PATCH v1 04/22] perf vendor events: Update Broadwell events/metrics

[Ian Rogers]

Update events from v29 to v30.
Update TMA metrics from 4.8 to 5.01.

Bring in the event updates v30:
https://github.com/intel/perfmon/commit/9a1827b2ac3927a455ae7df5aa3d1e1b10e69f15

The TMA 5.01 update is from (with subsequent fixes):
https://github.com/intel/perfmon/commit/1d72913b2d938781fb28f3cc3507aaec5c22d782

Co-authored-by: Caleb Biggers <caleb.biggers@xxxxxxxxx>
Signed-off-by: Ian Rogers <irogers@xxxxxxxxxx>
---
 .../arch/x86/broadwell/bdw-metrics.json       | 312 ++++++++++--------
 .../pmu-events/arch/x86/broadwell/cache.json  |  10 +-
 .../arch/x86/broadwell/frontend.json          |   4 +-
 .../pmu-events/arch/x86/broadwell/memory.json |   8 +-
 .../arch/x86/broadwell/metricgroups.json      |   5 +
 .../arch/x86/broadwell/pipeline.json          |  10 +-
 tools/perf/pmu-events/arch/x86/mapfile.csv    |   2 +-
 7 files changed, 192 insertions(+), 159 deletions(-)

diff --git a/tools/perf/pmu-events/arch/x86/broadwell/bdw-metrics.json b/tools/perf/pmu-events/arch/x86/broadwell/bdw-metrics.json
index af620553f958..40970fa5566c 100644
--- a/tools/perf/pmu-events/arch/x86/broadwell/bdw-metrics.json
+++ b/tools/perf/pmu-events/arch/x86/broadwell/bdw-metrics.json
@@ -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. Related metrics: tma_mispredicts_resteers",
         "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%"
     },
     {
@@ -143,8 +143,8 @@
         "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%"
     },
     {
@@ -152,7 +152,7 @@
         "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%"
     },
@@ -160,10 +160,10 @@
         "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_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%"
     },
     {
@@ -174,7 +174,7 @@
         "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%"
     },
     {
@@ -183,8 +183,8 @@
         "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%"
     },
     {
@@ -192,8 +192,8 @@
         "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%"
     },
     {
@@ -202,8 +202,8 @@
         "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%"
     },
     {
@@ -212,7 +212,7 @@
         "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%"
     },
     {
@@ -220,45 +220,45 @@
         "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": "60 * OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.SNOOP_HITM / 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.SNOOP_HITM. 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.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%"
     },
     {
@@ -287,7 +287,7 @@
         "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%"
     },
     {
@@ -295,8 +295,8 @@
         "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%"
     },
     {
@@ -304,8 +304,8 @@
         "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%"
     },
     {
@@ -313,8 +313,8 @@
         "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%"
     },
     {
@@ -322,8 +322,8 @@
         "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%"
     },
     {
@@ -333,33 +333,33 @@
         "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)",
@@ -370,7 +370,7 @@
     },
     {
         "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"
     },
@@ -391,11 +391,11 @@
         "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"
     },
@@ -414,7 +414,13 @@
         "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"
@@ -432,7 +438,7 @@
         "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)",
@@ -440,7 +446,7 @@
         "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)",
@@ -448,7 +454,7 @@
         "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)",
@@ -456,7 +462,7 @@
         "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)",
@@ -464,7 +470,7 @@
         "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)",
@@ -506,7 +512,7 @@
         "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"
     },
     {
@@ -529,7 +535,7 @@
     },
     {
         "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"
     },
@@ -541,7 +547,7 @@
     },
     {
         "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"
     },
@@ -583,7 +589,7 @@
     },
     {
         "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"
     },
@@ -602,7 +608,7 @@
     {
         "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"
     },
     {
@@ -628,26 +634,26 @@
     },
     {
         "BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses",
-        "MetricExpr": "(cpu@ITLB_MISSES.WALK_DURATION\\,cmask\\=1@ + cpu@DTLB_LOAD_MISSES.WALK_DURATION\\,cmask\\=1@ + cpu@DTLB_STORE_MISSES.WALK_DURATION\\,cmask\\=1@ + 7 * (DTLB_STORE_MISSES.WALK_COMPLETED + DTLB_LOAD_MISSES.WALK_COMPLETED + ITLB_MISSES.WALK_COMPLETED)) / tma_info_core_core_clks",
+        "MetricExpr": "(cpu@ITLB_MISSES.WALK_DURATION\\,cmask\\=0x1@ + cpu@DTLB_LOAD_MISSES.WALK_DURATION\\,cmask\\=0x1@ + cpu@DTLB_STORE_MISSES.WALK_DURATION\\,cmask\\=0x1@ + 7 * (DTLB_STORE_MISSES.WALK_COMPLETED + DTLB_LOAD_MISSES.WALK_COMPLETED + ITLB_MISSES.WALK_COMPLETED)) / tma_info_core_core_clks",
         "MetricGroup": "Mem;MemoryTLB",
         "MetricName": "tma_info_memory_tlb_page_walks_utilization",
         "MetricThreshold": "tma_info_memory_tlb_page_walks_utilization > 0.5"
     },
     {
         "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"
     },
@@ -665,14 +671,14 @@
     },
     {
         "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"
     },
     {
         "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"
@@ -682,13 +688,14 @@
         "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",
@@ -697,6 +704,19 @@
         "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)",
@@ -709,6 +729,13 @@
         "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",
@@ -716,7 +743,7 @@
         "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"
@@ -725,14 +752,15 @@
         "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)",
@@ -758,24 +786,24 @@
         "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%"
     },
     {
@@ -783,8 +811,8 @@
         "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%"
     },
     {
@@ -793,8 +821,8 @@
         "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%"
     },
     {
@@ -803,8 +831,8 @@
         "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%"
     },
     {
@@ -812,18 +840,18 @@
         "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%"
     },
     {
@@ -840,10 +868,10 @@
         "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%"
     },
     {
@@ -854,15 +882,15 @@
         "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_clears_resteers, 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\\=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%"
     },
@@ -871,7 +899,7 @@
         "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%"
     },
@@ -883,7 +911,7 @@
         "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%"
     },
     {
@@ -900,8 +928,8 @@
         "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%"
     },
     {
@@ -910,7 +938,7 @@
         "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%"
     },
     {
@@ -918,8 +946,8 @@
         "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%"
     },
     {
@@ -928,7 +956,7 @@
         "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%"
     },
     {
@@ -937,7 +965,7 @@
         "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%"
     },
     {
@@ -973,7 +1001,7 @@
         "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%"
     },
     {
@@ -982,7 +1010,7 @@
         "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%"
     },
     {
@@ -1000,43 +1028,43 @@
         "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%"
     },
     {
@@ -1055,8 +1083,8 @@
         "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%"
     },
     {
@@ -1064,16 +1092,16 @@
         "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%"
     },
@@ -1082,8 +1110,8 @@
         "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%"
     },
     {
@@ -1091,18 +1119,18 @@
         "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%"
     },
     {
@@ -1118,7 +1146,7 @@
         "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%"
     },
@@ -1127,8 +1155,8 @@
         "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%"
     }
 ]
diff --git a/tools/perf/pmu-events/arch/x86/broadwell/cache.json b/tools/perf/pmu-events/arch/x86/broadwell/cache.json
index 063ec8c2b2a1..fd3df87318c5 100644
--- a/tools/perf/pmu-events/arch/x86/broadwell/cache.json
+++ b/tools/perf/pmu-events/arch/x86/broadwell/cache.json
@@ -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"
     },
@@ -401,7 +401,7 @@
         "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"
     },
@@ -412,7 +412,7 @@
         "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"
     },
@@ -601,7 +601,7 @@
         "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"
     },
@@ -664,7 +664,7 @@
         "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"
     },
diff --git a/tools/perf/pmu-events/arch/x86/broadwell/frontend.json b/tools/perf/pmu-events/arch/x86/broadwell/frontend.json
index db3488abf9fc..018020a51436 100644
--- a/tools/perf/pmu-events/arch/x86/broadwell/frontend.json
+++ b/tools/perf/pmu-events/arch/x86/broadwell/frontend.json
@@ -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"
     },
diff --git a/tools/perf/pmu-events/arch/x86/broadwell/memory.json b/tools/perf/pmu-events/arch/x86/broadwell/memory.json
index 77fbfe99a522..bbc5d7deea6b 100644
--- a/tools/perf/pmu-events/arch/x86/broadwell/memory.json
+++ b/tools/perf/pmu-events/arch/x86/broadwell/memory.json
@@ -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"
     },
@@ -2226,7 +2226,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0xc9",
         "EventName": "RTM_RETIRED.ABORTED",
-        "PEBS": "2",
+        "PEBS": "1",
         "PublicDescription": "Number of times RTM abort was triggered .",
         "SampleAfterValue": "2000003",
         "UMask": "0x4"
@@ -2290,7 +2290,7 @@
         "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"
     },
diff --git a/tools/perf/pmu-events/arch/x86/broadwell/metricgroups.json b/tools/perf/pmu-events/arch/x86/broadwell/metricgroups.json
index 4193c90c3459..0863375bdead 100644
--- a/tools/perf/pmu-events/arch/x86/broadwell/metricgroups.json
+++ b/tools/perf/pmu-events/arch/x86/broadwell/metricgroups.json
@@ -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",
diff --git a/tools/perf/pmu-events/arch/x86/broadwell/pipeline.json b/tools/perf/pmu-events/arch/x86/broadwell/pipeline.json
index c03f77539362..962cd07eb307 100644
--- a/tools/perf/pmu-events/arch/x86/broadwell/pipeline.json
+++ b/tools/perf/pmu-events/arch/x86/broadwell/pipeline.json
@@ -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"
     },
diff --git a/tools/perf/pmu-events/arch/x86/mapfile.csv b/tools/perf/pmu-events/arch/x86/mapfile.csv
index 154402fa1d39..01f6a4a82ed2 100644
--- a/tools/perf/pmu-events/arch/x86/mapfile.csv
+++ b/tools/perf/pmu-events/arch/x86/mapfile.csv
@@ -3,7 +3,7 @@ GenuineIntel-6-(97|9A|B7|BA|BF),v1.28,alderlake,core
 GenuineIntel-6-BE,v1.28,alderlaken,core
 GenuineIntel-6-C[56],v1.05,arrowlake,core
 GenuineIntel-6-(1C|26|27|35|36),v5,bonnell,core
-GenuineIntel-6-(3D|47),v29,broadwell,core
+GenuineIntel-6-(3D|47),v30,broadwell,core
 GenuineIntel-6-56,v11,broadwellde,core
 GenuineIntel-6-4F,v22,broadwellx,core
 GenuineIntel-6-55-[56789ABCDEF],v1.22,cascadelakex,core
-- 
2.47.1.545.g3c1d2e2a6a-goog