[PATCH v1 08/12] perf vendor events intel: Update meteorlake events from 1.21 to 1.22

[Chun-Tse Shao]

The updated events were published in:
https://github.com/intel/perfmon/commit/704ef43e4c0738065a0575622cf7d31867b8d48b

Signed-off-by: Chun-Tse Shao <ctshao@xxxxxxxxxx>
---
 tools/perf/pmu-events/arch/x86/mapfile.csv    |  2 +-
 .../pmu-events/arch/x86/meteorlake/cache.json | 11 ++-
 .../arch/x86/meteorlake/metricgroups.json     |  2 +-
 .../arch/x86/meteorlake/mtl-metrics.json      | 88 ++++++++++---------
 .../arch/x86/meteorlake/pipeline.json         |  4 +-
 .../arch/x86/meteorlake/uncore-memory.json    | 84 +++++++++++++++---
 6 files changed, 131 insertions(+), 60 deletions(-)

diff --git a/tools/perf/pmu-events/arch/x86/mapfile.csv b/tools/perf/pmu-events/arch/x86/mapfile.csv
index 68f1ae4c0aae..a15cd3280993 100644
--- a/tools/perf/pmu-events/arch/x86/mapfile.csv
+++ b/tools/perf/pmu-events/arch/x86/mapfile.csv
@@ -23,7 +23,7 @@ GenuineIntel-6-3E,v24,ivytown,core
 GenuineIntel-6-2D,v24,jaketown,core
 GenuineIntel-6-(57|85),v16,knightslanding,core
 GenuineIntel-6-BD,v1.26,lunarlake,core
-GenuineIntel-6-(AA|AC|B5),v1.21,meteorlake,core
+GenuineIntel-6-(AA|AC|B5),v1.22,meteorlake,core
 GenuineIntel-6-1[AEF],v4,nehalemep,core
 GenuineIntel-6-2E,v4,nehalemex,core
 GenuineIntel-6-(CC|D5),v1.06,pantherlake,core
diff --git a/tools/perf/pmu-events/arch/x86/meteorlake/cache.json b/tools/perf/pmu-events/arch/x86/meteorlake/cache.json
index 6419bc36f249..c2d351efa9d6 100644
--- a/tools/perf/pmu-events/arch/x86/meteorlake/cache.json
+++ b/tools/perf/pmu-events/arch/x86/meteorlake/cache.json
@@ -1,6 +1,6 @@
 [
     {
-        "BriefDescription": "Counts the number of request that were not accepted into the L2Q because the L2Q is FULL.",
+        "BriefDescription": "Counts the number of requests that were not accepted into the L2Q because the L2Q is FULL.",
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0x31",
         "EventName": "CORE_REJECT_L2Q.ANY",
@@ -631,6 +631,15 @@
         "UMask": "0x50",
         "Unit": "cpu_atom"
     },
+    {
+        "BriefDescription": "Counts the number of unhalted cycles when the core is stalled due to a demand load miss which missed all the caches, a snoop was required, and hits in other core or module on the same die. Another core provides the data with a FWD, NO_FWD, or HITM. If the core has access to an L3 cache, an LLC miss refers to an L3 cache miss, otherwise it is an L2 cache miss.",
+        "Counter": "0,1,2,3,4,5,6,7",
+        "EventCode": "0x34",
+        "EventName": "MEM_BOUND_STALLS_LOAD.LLC_MISS_OTHERMOD",
+        "SampleAfterValue": "1000003",
+        "UMask": "0x8",
+        "Unit": "cpu_atom"
+    },
     {
         "BriefDescription": "Counts the number of unhalted cycles when the core is stalled to a store buffer full condition",
         "Counter": "0,1,2,3,4,5,6,7",
diff --git a/tools/perf/pmu-events/arch/x86/meteorlake/metricgroups.json b/tools/perf/pmu-events/arch/x86/meteorlake/metricgroups.json
index 855585fe6fae..9acbda612c25 100644
--- a/tools/perf/pmu-events/arch/x86/meteorlake/metricgroups.json
+++ b/tools/perf/pmu-events/arch/x86/meteorlake/metricgroups.json
@@ -93,7 +93,6 @@
     "tma_code_stlb_miss_group": "Metrics contributing to tma_code_stlb_miss category",
     "tma_core_bound_group": "Metrics contributing to tma_core_bound category",
     "tma_divider_group": "Metrics contributing to tma_divider category",
-    "tma_dram_bound_group": "Metrics contributing to tma_dram_bound category",
     "tma_dtlb_load_group": "Metrics contributing to tma_dtlb_load category",
     "tma_dtlb_store_group": "Metrics contributing to tma_dtlb_store category",
     "tma_fetch_bandwidth_group": "Metrics contributing to tma_fetch_bandwidth category",
@@ -129,6 +128,7 @@
     "tma_l1_bound_group": "Metrics contributing to tma_l1_bound category",
     "tma_l2_bound_group": "Metrics contributing to tma_l2_bound category",
     "tma_l3_bound_group": "Metrics contributing to tma_l3_bound category",
+    "tma_l3_miss_bound_group": "Metrics contributing to tma_l3_miss_bound category",
     "tma_light_operations_group": "Metrics contributing to tma_light_operations category",
     "tma_load_op_utilization_group": "Metrics contributing to tma_load_op_utilization category",
     "tma_load_stlb_miss_group": "Metrics contributing to tma_load_stlb_miss category",
diff --git a/tools/perf/pmu-events/arch/x86/meteorlake/mtl-metrics.json b/tools/perf/pmu-events/arch/x86/meteorlake/mtl-metrics.json
index 948c16a1f95b..a23691052237 100644
--- a/tools/perf/pmu-events/arch/x86/meteorlake/mtl-metrics.json
+++ b/tools/perf/pmu-events/arch/x86/meteorlake/mtl-metrics.json
@@ -797,16 +797,16 @@
     },
     {
         "BriefDescription": "Total pipeline cost of external Memory- or Cache-Bandwidth related bottlenecks",
-        "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_mem_bandwidth / (tma_mem_bandwidth + tma_mem_latency)) + tma_memory_bound * (tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_sq_full / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_fb_full / (tma_dtlb_load + tma_fb_full + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)))",
+        "MetricExpr": "100 * (tma_memory_bound * (tma_l3_miss_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_l3_miss_bound + tma_store_bound)) * (tma_mem_bandwidth / (tma_mem_bandwidth + tma_mem_latency)) + tma_memory_bound * (tma_l3_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_l3_miss_bound + tma_store_bound)) * (tma_sq_full / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_memory_bound * (tma_l1_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_l3_miss_bound + tma_store_bound)) * (tma_fb_full / (tma_dtlb_load + tma_fb_full + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)))",
         "MetricGroup": "BvMB;Mem;MemoryBW;Offcore;tma_issueBW",
         "MetricName": "tma_bottleneck_data_cache_memory_bandwidth",
         "MetricThreshold": "tma_bottleneck_data_cache_memory_bandwidth > 20",
-        "PublicDescription": "Total pipeline cost of external Memory- or Cache-Bandwidth related bottlenecks. Related metrics: tma_fb_full, tma_info_system_dram_bw_use, tma_mem_bandwidth, tma_sq_full",
+        "PublicDescription": "Total pipeline cost of external Memory- or Cache-Bandwidth related bottlenecks. Related metrics: tma_fb_full, tma_info_system_dram_bw_use, tma_mem_bandwidth, tma_sq_full, tma_uc_bound",
         "Unit": "cpu_core"
     },
     {
         "BriefDescription": "Total pipeline cost of external Memory- or Cache-Latency related bottlenecks",
-        "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_mem_latency / (tma_mem_bandwidth + tma_mem_latency)) + tma_memory_bound * (tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_l3_hit_latency / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_memory_bound * tma_l2_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) + tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_l1_latency_dependency / (tma_dtlb_load + tma_fb_full + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_lock_latency / (tma_dtlb_load + tma_fb_full + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_split_loads / (tma_dtlb_load + tma_fb_full + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_memory_bound * (tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_split_stores / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency + tma_streaming_stores)) + tma_memory_bound * (tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_store_latency / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency + tma_streaming_stores)))",
+        "MetricExpr": "100 * (tma_memory_bound * (tma_l3_miss_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_l3_miss_bound + tma_store_bound)) * (tma_mem_latency / (tma_mem_bandwidth + tma_mem_latency)) + tma_memory_bound * (tma_l3_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_l3_miss_bound + tma_store_bound)) * (tma_l3_hit_latency / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_memory_bound * tma_l2_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_l3_miss_bound + tma_store_bound) + tma_memory_bound * (tma_l1_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_l3_miss_bound + tma_store_bound)) * (tma_l1_latency_dependency / (tma_dtlb_load + tma_fb_full + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_memory_bound * (tma_l1_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_l3_miss_bound + tma_store_bound)) * (tma_lock_latency / (tma_dtlb_load + tma_fb_full + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_memory_bound * (tma_l1_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_l3_miss_bound + tma_store_bound)) * (tma_split_loads / (tma_dtlb_load + tma_fb_full + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_memory_bound * (tma_store_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_l3_miss_bound + tma_store_bound)) * (tma_split_stores / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency + tma_streaming_stores)) + tma_memory_bound * (tma_store_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_l3_miss_bound + tma_store_bound)) * (tma_store_latency / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency + tma_streaming_stores)))",
         "MetricGroup": "BvML;Mem;MemoryLat;Offcore;tma_issueLat",
         "MetricName": "tma_bottleneck_data_cache_memory_latency",
         "MetricThreshold": "tma_bottleneck_data_cache_memory_latency > 20",
@@ -832,7 +832,7 @@
     },
     {
         "BriefDescription": "Total pipeline cost of Memory Address Translation related bottlenecks (data-side TLBs)",
-        "MetricExpr": "100 * (tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_dtlb_load / (tma_dtlb_load + tma_fb_full + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_memory_bound * (tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_dtlb_store / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency + tma_streaming_stores)))",
+        "MetricExpr": "100 * (tma_memory_bound * (tma_l1_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_l3_miss_bound + tma_store_bound)) * (tma_dtlb_load / (tma_dtlb_load + tma_fb_full + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_memory_bound * (tma_store_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_l3_miss_bound + tma_store_bound)) * (tma_dtlb_store / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency + tma_streaming_stores)))",
         "MetricGroup": "BvMT;Mem;MemoryTLB;Offcore;tma_issueTLB",
         "MetricName": "tma_bottleneck_memory_data_tlbs",
         "MetricThreshold": "tma_bottleneck_memory_data_tlbs > 20",
@@ -841,7 +841,7 @@
     },
     {
         "BriefDescription": "Total pipeline cost of Memory Synchronization related bottlenecks (data transfers and coherency updates across processors)",
-        "MetricExpr": "100 * (tma_memory_bound * (tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_contested_accesses + tma_data_sharing) / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full) + tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * tma_false_sharing / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency + tma_streaming_stores - tma_store_latency)) + tma_machine_clears * (1 - tma_other_nukes / tma_other_nukes))",
+        "MetricExpr": "100 * (tma_memory_bound * (tma_l3_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_l3_miss_bound + tma_store_bound) * (tma_contested_accesses + tma_data_sharing) / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full) + tma_store_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_l3_miss_bound + tma_store_bound) * tma_false_sharing / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency + tma_streaming_stores - tma_store_latency)) + tma_machine_clears * (1 - tma_other_nukes / tma_other_nukes))",
         "MetricGroup": "BvMS;LockCont;Mem;Offcore;tma_issueSyncxn",
         "MetricName": "tma_bottleneck_memory_synchronization",
         "MetricThreshold": "tma_bottleneck_memory_synchronization > 10",
@@ -989,7 +989,7 @@
     },
     {
         "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to retired misprediction by non-taken conditional branches.",
-        "MetricExpr": "cpu_core@BR_MISP_RETIRED.COND_NTAKEN_COST@ * cpu_core@BR_MISP_RETIRED.COND_NTAKEN_COST@R / tma_info_thread_clks",
+        "MetricExpr": "cpu_core@BR_MISP_RETIRED.COND_NTAKEN@ / cpu_core@BR_MISP_RETIRED.ALL_BRANCHES@ * tma_branch_mispredicts",
         "MetricGroup": "BrMispredicts;TopdownL3;tma_L3_group;tma_branch_mispredicts_group",
         "MetricName": "tma_cond_nt_mispredicts",
         "MetricThreshold": "tma_cond_nt_mispredicts > 0.05 & (tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15)",
@@ -998,7 +998,7 @@
     },
     {
         "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to misprediction by taken conditional branches.",
-        "MetricExpr": "cpu_core@BR_MISP_RETIRED.COND_TAKEN_COST@ * cpu_core@BR_MISP_RETIRED.COND_TAKEN_COST@R / tma_info_thread_clks",
+        "MetricExpr": "cpu_core@BR_MISP_RETIRED.COND_TAKEN@ / cpu_core@BR_MISP_RETIRED.ALL_BRANCHES@ * tma_branch_mispredicts",
         "MetricGroup": "BrMispredicts;TopdownL3;tma_L3_group;tma_branch_mispredicts_group",
         "MetricName": "tma_cond_tk_mispredicts",
         "MetricThreshold": "tma_cond_tk_mispredicts > 0.05 & (tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15)",
@@ -1027,13 +1027,13 @@
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses",
+        "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to L3 data-sharing accesses",
         "MetricConstraint": "NO_GROUP_EVENTS",
         "MetricExpr": "(cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_NO_FWD@ * min(cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_NO_FWD@R, 24 * tma_info_system_core_frequency) + cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD@ * min(cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD@R, 24 * tma_info_system_core_frequency) * (1 - cpu_core@OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM@ / (cpu_core@OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM@ + cpu_core@OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD@))) * (1 + cpu_core@MEM_LOAD_RETIRED.FB_HIT@ / cpu_core@MEM_LOAD_RETIRED.L1_MISS@ / 2) / tma_info_thread_clks",
         "MetricGroup": "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_NO_FWD. Related metrics: tma_bottleneck_memory_synchronization, tma_contested_accesses, tma_false_sharing, tma_machine_clears, tma_remote_cache",
+        "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to L3 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_NO_FWD. Related metrics: tma_bottleneck_memory_synchronization, tma_contested_accesses, tma_false_sharing, tma_machine_clears, tma_remote_cache",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -1057,16 +1057,6 @@
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
-    {
-        "BriefDescription": "This metric estimates how often the CPU was stalled on accesses to external memory (DRAM) by loads",
-        "MetricExpr": "cpu_core@MEMORY_ACTIVITY.STALLS_L3_MISS@ / tma_info_thread_clks",
-        "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group",
-        "MetricName": "tma_dram_bound",
-        "MetricThreshold": "tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)",
-        "PublicDescription": "This metric estimates how often the CPU was stalled on accesses to external memory (DRAM) by loads. Better caching can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L3_MISS",
-        "ScaleUnit": "100%",
-        "Unit": "cpu_core"
-    },
     {
         "BriefDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to DSB (decoded uop cache) fetch pipeline",
         "MetricExpr": "(cpu_core@IDQ.DSB_CYCLES_ANY@ - cpu_core@IDQ.DSB_CYCLES_OK@) / tma_info_core_core_clks / 2",
@@ -1123,7 +1113,7 @@
         "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_bottleneck_data_cache_memory_bandwidth, tma_info_system_dram_bw_use, tma_mem_bandwidth, tma_sq_full, tma_store_latency, tma_streaming_stores",
+        "PublicDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed. The higher the metric value; the deeper the memory hierarchy level the misses are satisfied from (metric values >1 are valid). Often it hints on approaching bandwidth limits (to L2 cache; L3 cache or external memory). Related metrics: tma_bottleneck_data_cache_memory_bandwidth, tma_info_system_dram_bw_use, tma_mem_bandwidth, tma_sq_full, tma_store_latency, tma_streaming_stores, tma_uc_bound",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -1273,7 +1263,7 @@
     },
     {
         "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to retired misprediction by indirect CALL instructions.",
-        "MetricExpr": "cpu_core@BR_MISP_RETIRED.INDIRECT_CALL_COST@ * cpu_core@BR_MISP_RETIRED.INDIRECT_CALL_COST@R / tma_info_thread_clks",
+        "MetricExpr": "cpu_core@BR_MISP_RETIRED.INDIRECT_CALL@ / cpu_core@BR_MISP_RETIRED.ALL_BRANCHES@ * tma_branch_mispredicts",
         "MetricGroup": "BrMispredicts;TopdownL3;tma_L3_group;tma_branch_mispredicts_group",
         "MetricName": "tma_ind_call_mispredicts",
         "MetricThreshold": "tma_ind_call_mispredicts > 0.05 & (tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15)",
@@ -1282,7 +1272,7 @@
     },
     {
         "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to retired misprediction by indirect JMP instructions.",
-        "MetricExpr": "max((cpu_core@BR_MISP_RETIRED.INDIRECT_COST@ * cpu_core@BR_MISP_RETIRED.INDIRECT_COST@R - cpu_core@BR_MISP_RETIRED.INDIRECT_CALL_COST@ * cpu_core@BR_MISP_RETIRED.INDIRECT_CALL_COST@R) / tma_info_thread_clks, 0)",
+        "MetricExpr": "max((cpu_core@BR_MISP_RETIRED.INDIRECT@ - cpu_core@BR_MISP_RETIRED.INDIRECT_CALL@) / cpu_core@BR_MISP_RETIRED.ALL_BRANCHES@ * tma_branch_mispredicts, 0)",
         "MetricGroup": "BrMispredicts;TopdownL3;tma_L3_group;tma_branch_mispredicts_group",
         "MetricName": "tma_ind_jump_mispredicts",
         "MetricThreshold": "tma_ind_jump_mispredicts > 0.05 & (tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15)",
@@ -1459,7 +1449,7 @@
     },
     {
         "BriefDescription": "Fraction of Uops delivered by the DSB (aka Decoded ICache; or Uop Cache)",
-        "MetricExpr": "cpu_core@IDQ.DSB_UOPS@ / cpu_core@UOPS_ISSUED.ANY@",
+        "MetricExpr": "cpu_core@IDQ.DSB_UOPS@ / (cpu_core@IDQ.DSB_UOPS@ + cpu_core@xxxxxxxx@ + cpu_core@IDQ.MITE_UOPS@ + cpu_core@IDQ.MS_UOPS@)",
         "MetricGroup": "DSB;Fed;FetchBW;tma_issueFB",
         "MetricName": "tma_info_frontend_dsb_coverage",
         "MetricThreshold": "tma_info_frontend_dsb_coverage < 0.7 & tma_info_thread_ipc / 6 > 0.35",
@@ -1526,7 +1516,7 @@
     },
     {
         "BriefDescription": "Fraction of Uops delivered by the LSD (Loop Stream Detector; aka Loop Cache)",
-        "MetricExpr": "cpu_core@xxxxxxxx@ / cpu_core@UOPS_ISSUED.ANY@",
+        "MetricExpr": "cpu_core@xxxxxxxx@ / (cpu_core@IDQ.DSB_UOPS@ + cpu_core@xxxxxxxx@ + cpu_core@IDQ.MITE_UOPS@ + cpu_core@IDQ.MS_UOPS@)",
         "MetricGroup": "Fed;LSD",
         "MetricName": "tma_info_frontend_lsd_coverage",
         "Unit": "cpu_core"
@@ -1685,6 +1675,15 @@
         "PublicDescription": "Instructions per taken branch. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_lcp",
         "Unit": "cpu_core"
     },
+    {
+        "BriefDescription": "AVX preserve/restore assists per kilo instruction",
+        "MetricExpr": "1e3 * cpu_core@ASSISTS.SSE_AVX_MIX@ / cpu_core@INST_RETIRED.ANY@",
+        "MetricGroup": "tma_issueMV",
+        "MetricName": "tma_info_inst_mix_vectormixpki",
+        "MetricThreshold": "tma_info_inst_mix_vectormixpki > 0.05",
+        "PublicDescription": "AVX preserve/restore assists per kilo instruction. Related metrics: tma_mixing_vectors, tma_ms_switches",
+        "Unit": "cpu_core"
+    },
     {
         "BriefDescription": "Average per-core data fill bandwidth to the L1 data cache [GB / sec]",
         "MetricExpr": "tma_info_memory_l1d_cache_fill_bw",
@@ -1922,7 +1921,7 @@
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "Mem;Backend;CacheHits",
+        "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is execution) per physical core",
         "MetricExpr": "cpu_core@UOPS_EXECUTED.THREAD@ / (cpu_core@UOPS_EXECUTED.CORE_CYCLES_GE_1@ / 2 if #SMT_on else cpu_core@UOPS_EXECUTED.THREAD\\,cmask\\=1@)",
         "MetricGroup": "Cor;Pipeline;PortsUtil;SMT",
         "MetricName": "tma_info_pipeline_execute",
@@ -2004,10 +2003,10 @@
     },
     {
         "BriefDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]",
-        "MetricExpr": "64 * (UNC_HAC_ARB_TRK_REQUESTS.ALL + UNC_HAC_ARB_COH_TRK_REQUESTS.ALL) / 1e9 / tma_info_system_time",
+        "MetricExpr": "32 * UNC_M_TOTAL_DATA / 1e9 / tma_info_system_time",
         "MetricGroup": "HPC;MemOffcore;MemoryBW;SoC;tma_issueBW",
         "MetricName": "tma_info_system_dram_bw_use",
-        "PublicDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]. Related metrics: tma_bottleneck_data_cache_memory_bandwidth, tma_fb_full, tma_mem_bandwidth, tma_sq_full",
+        "PublicDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]. Related metrics: tma_bottleneck_data_cache_memory_bandwidth, tma_fb_full, tma_mem_bandwidth, tma_sq_full, tma_uc_bound",
         "Unit": "cpu_core"
     },
     {
@@ -2093,13 +2092,6 @@
         "MetricName": "tma_info_system_turbo_utilization",
         "Unit": "cpu_core"
     },
-    {
-        "BriefDescription": "Measured Average Uncore Frequency for the SoC [GHz]",
-        "MetricExpr": "tma_info_system_socket_clks / 1e9 / tma_info_system_time",
-        "MetricGroup": "SoC",
-        "MetricName": "tma_info_system_uncore_frequency",
-        "Unit": "cpu_core"
-    },
     {
         "BriefDescription": "Per-Logical Processor actual clocks when the Logical Processor is active.",
         "MetricExpr": "cpu_core@CPU_CLK_UNHALTED.THREAD@",
@@ -2268,6 +2260,16 @@
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
+    {
+        "BriefDescription": "This metric estimates how often the CPU was stalled on accesses to external memory (DRAM) by loads",
+        "MetricExpr": "cpu_core@MEMORY_ACTIVITY.STALLS_L3_MISS@ / tma_info_thread_clks",
+        "MetricGroup": "MemoryBound;Offcore;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group",
+        "MetricName": "tma_l3_miss_bound",
+        "MetricThreshold": "tma_l3_miss_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)",
+        "PublicDescription": "This metric estimates how often the CPU was stalled on accesses to external memory (DRAM) by loads. Better caching can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L3_MISS",
+        "ScaleUnit": "100%",
+        "Unit": "cpu_core"
+    },
     {
         "BriefDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs)",
         "MetricExpr": "cpu_core@xxxxxxxxxx@ / tma_info_thread_clks",
@@ -2379,19 +2381,19 @@
     {
         "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_core@CPU_CLK_UNHALTED.THREAD@, cpu_core@OFFCORE_REQUESTS_OUTSTANDING.DATA_RD\\,cmask\\=4@) / tma_info_thread_clks",
-        "MetricGroup": "BvMB;MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueBW",
+        "MetricGroup": "BvMB;MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_issueBW;tma_l3_miss_bound_group",
         "MetricName": "tma_mem_bandwidth",
-        "MetricThreshold": "tma_mem_bandwidth > 0.2 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
-        "PublicDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory - DRAM ([SPR-HBM] and/or HBM).  The underlying heuristic assumes that a similar off-core traffic is generated by all IA cores. This metric does not aggregate non-data-read requests by this logical processor; requests from other IA Logical Processors/Physical Cores/sockets; or other non-IA devices like GPU; hence the maximum external memory bandwidth limits may or may not be approached when this metric is flagged (see Uncore counters for that). Related metrics: tma_bottleneck_data_cache_memory_bandwidth, tma_fb_full, tma_info_system_dram_bw_use, tma_sq_full",
+        "MetricThreshold": "tma_mem_bandwidth > 0.2 & (tma_l3_miss_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory - DRAM ([SPR-HBM] and/or HBM).  The underlying heuristic assumes that a similar off-core traffic is generated by all IA cores. This metric does not aggregate non-data-read requests by this logical processor; requests from other IA Logical Processors/Physical Cores/sockets; or other non-IA devices like GPU; hence the maximum external memory bandwidth limits may or may not be approached when this metric is flagged (see Uncore counters for that). Related metrics: tma_bottleneck_data_cache_memory_bandwidth, tma_fb_full, tma_info_system_dram_bw_use, tma_sq_full, tma_uc_bound",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
         "BriefDescription": "This metric estimates fraction of cycles where the performance was likely hurt due to latency from external memory - DRAM ([SPR-HBM] and/or HBM)",
         "MetricExpr": "min(cpu_core@CPU_CLK_UNHALTED.THREAD@, cpu_core@OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD@) / tma_info_thread_clks - tma_mem_bandwidth",
-        "MetricGroup": "BvML;MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueLat",
+        "MetricGroup": "BvML;MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_issueLat;tma_l3_miss_bound_group",
         "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_l3_miss_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
         "PublicDescription": "This metric estimates fraction of cycles where the performance was likely hurt due to latency from external memory - DRAM ([SPR-HBM] and/or HBM).  This metric does not aggregate requests from other Logical Processors/Physical Cores/sockets (see Uncore counters for that). Related metrics: tma_bottleneck_data_cache_memory_latency, tma_l3_hit_latency",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
@@ -2461,7 +2463,7 @@
         "MetricGroup": "TopdownL5;tma_L5_group;tma_issueMV;tma_ports_utilized_0_group",
         "MetricName": "tma_mixing_vectors",
         "MetricThreshold": "tma_mixing_vectors > 0.05",
-        "PublicDescription": "This metric estimates penalty in terms of percentage of([SKL+] injected blend uops out of all Uops Issued -- the Count Domain; [ADL+] cycles). Usually a Mixing_Vectors over 5% is worth investigating. Read more in Appendix B1 of the Optimizations Guide for this topic. Related metrics: tma_ms_switches",
+        "PublicDescription": "This metric estimates penalty in terms of percentage of([SKL+] injected blend uops out of all Uops Issued -- the Count Domain; [ADL+] cycles). Usually a Mixing_Vectors over 5% is worth investigating. Read more in Appendix B1 of the Optimizations Guide for this topic. Related metrics: tma_info_inst_mix_vectormixpki, tma_ms_switches",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -2480,7 +2482,7 @@
         "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: FRONTEND_RETIRED.MS_FLOWS. Related metrics: tma_bottleneck_irregular_overhead, tma_clears_resteers, tma_l1_bound, tma_machine_clears, tma_microcode_sequencer, tma_mixing_vectors, tma_serializing_operation",
+        "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: FRONTEND_RETIRED.MS_FLOWS. Related metrics: tma_bottleneck_irregular_overhead, tma_clears_resteers, tma_info_inst_mix_vectormixpki, tma_l1_bound, tma_machine_clears, tma_microcode_sequencer, tma_mixing_vectors, tma_serializing_operation",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -2628,7 +2630,7 @@
     },
     {
         "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to retired misprediction by (indirect) RET instructions.",
-        "MetricExpr": "cpu_core@BR_MISP_RETIRED.RET_COST@ * cpu_core@BR_MISP_RETIRED.RET_COST@R / tma_info_thread_clks",
+        "MetricExpr": "cpu_core@BR_MISP_RETIRED.RET@ / cpu_core@BR_MISP_RETIRED.ALL_BRANCHES@ * tma_branch_mispredicts",
         "MetricGroup": "BrMispredicts;TopdownL3;tma_L3_group;tma_branch_mispredicts_group",
         "MetricName": "tma_ret_mispredicts",
         "MetricThreshold": "tma_ret_mispredicts > 0.05 & (tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15)",
@@ -2703,7 +2705,7 @@
         "MetricGroup": "BvMB;MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_issueBW;tma_l3_bound_group",
         "MetricName": "tma_sq_full",
         "MetricThreshold": "tma_sq_full > 0.3 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
-        "PublicDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors). Related metrics: tma_bottleneck_data_cache_memory_bandwidth, tma_fb_full, tma_info_system_dram_bw_use, tma_mem_bandwidth",
+        "PublicDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors). Related metrics: tma_bottleneck_data_cache_memory_bandwidth, tma_fb_full, tma_info_system_dram_bw_use, tma_mem_bandwidth, tma_uc_bound",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
diff --git a/tools/perf/pmu-events/arch/x86/meteorlake/pipeline.json b/tools/perf/pmu-events/arch/x86/meteorlake/pipeline.json
index 09e1147c4733..6cd1b1659ec7 100644
--- a/tools/perf/pmu-events/arch/x86/meteorlake/pipeline.json
+++ b/tools/perf/pmu-events/arch/x86/meteorlake/pipeline.json
@@ -909,7 +909,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc0",
         "EventName": "INST_RETIRED.REP_ITERATION",
-        "PublicDescription": "Number of iterations of Repeat (REP) string retired instructions such as MOVS, CMPS, and SCAS. Each has a byte, word, and doubleword version and string instructions can be repeated using a repetition prefix, REP, that allows their architectural execution to be repeated a number of times as specified by the RCX register. Note the number of iterations is implementation-dependent.",
+        "PublicDescription": "Number of iterations of Repeat (REP) string retired instructions such as MOVS, CMPS, and SCAS. Each has a byte, word, and doubleword version and string instructions can be repeated using a repetition prefix, REP, that allows their architectural execution to be repeated a number of times as specified by the RCX register. Note: Since the number of iterations within a REP instruction can be significantly affected by fast strings, this event may vary run to run and not match the architectural number of iterations (specified by RCX)",
         "SampleAfterValue": "2000003",
         "UMask": "0x8",
         "Unit": "cpu_core"
@@ -1443,7 +1443,7 @@
         "Unit": "cpu_atom"
     },
     {
-        "BriefDescription": "Counts the number issue slots not consumed  due to a  color request for an FCW or MXCSR control register when all 4 colors (copies) are already in use.",
+        "BriefDescription": "Counts the number of issue slots not consumed due to a color request for an FCW or MXCSR control register when all 4 colors (copies) are already in use.",
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0x75",
         "EventName": "SERIALIZATION.COLOR_STALLS",
diff --git a/tools/perf/pmu-events/arch/x86/meteorlake/uncore-memory.json b/tools/perf/pmu-events/arch/x86/meteorlake/uncore-memory.json
index ceb8839f0767..60bf390198d6 100644
--- a/tools/perf/pmu-events/arch/x86/meteorlake/uncore-memory.json
+++ b/tools/perf/pmu-events/arch/x86/meteorlake/uncore-memory.json
@@ -1,61 +1,61 @@
 [
     {
-        "BriefDescription": "Counts every CAS read command sent from the Memory Controller 0 to DRAM (sum of all channels).",
+        "BriefDescription": "This event is deprecated. [This event is alias to UNC_M_MC0_RDCAS_COUNT_FREERUN]",
         "Counter": "0",
+        "Deprecated": "1",
         "EventCode": "0xff",
         "EventName": "UNC_MC0_RDCAS_COUNT_FREERUN",
         "PerPkg": "1",
-        "PublicDescription": "Counts every CAS read command sent from the Memory Controller 0 to DRAM (sum of all channels). Each CAS commands can be for 32B or 64B of data.",
         "UMask": "0x20",
         "Unit": "imc_free_running_0"
     },
     {
-        "BriefDescription": "Counts every read and write request entering the Memory Controller 0.",
+        "BriefDescription": "This event is deprecated. [This event is alias to UNC_M_MC0_TOTAL_REQCOUNT_FREERUN]",
         "Counter": "2",
+        "Deprecated": "1",
         "EventCode": "0xff",
         "EventName": "UNC_MC0_TOTAL_REQCOUNT_FREERUN",
         "PerPkg": "1",
-        "PublicDescription": "Counts every read and write request entering the Memory Controller 0 (sum of all channels). All requests are counted as one, whether they are 32B or 64B Read/Write or partial/full line writes. Some write requests to the same address may merge to a single write command to DRAM. Therefore, the total request count may be higher than total DRAM BW.",
         "UMask": "0x10",
         "Unit": "imc_free_running_0"
     },
     {
-        "BriefDescription": "Counts every CAS write command sent from the Memory Controller 0 to DRAM (sum of all channels).",
+        "BriefDescription": "This event is deprecated. [This event is alias to UNC_M_MC0_WRCAS_COUNT_FREERUN]",
         "Counter": "1",
+        "Deprecated": "1",
         "EventCode": "0xff",
         "EventName": "UNC_MC0_WRCAS_COUNT_FREERUN",
         "PerPkg": "1",
-        "PublicDescription": "Counts every CAS write command sent from the Memory Controller 0 to DRAM (sum of all channels).  Each CAS commands can be for 32B or 64B of data.",
         "UMask": "0x30",
         "Unit": "imc_free_running_0"
     },
     {
-        "BriefDescription": "Counts every CAS read command sent from the Memory Controller 1 to DRAM (sum of all channels).",
+        "BriefDescription": "This event is deprecated. [This event is alias to UNC_M_MC1_RDCAS_COUNT_FREERUN]",
         "Counter": "3",
+        "Deprecated": "1",
         "EventCode": "0xff",
         "EventName": "UNC_MC1_RDCAS_COUNT_FREERUN",
         "PerPkg": "1",
-        "PublicDescription": "Counts every CAS read command sent from the Memory Controller 1 to DRAM (sum of all channels). Each CAS commands can be for 32B or 64B of data.",
         "UMask": "0x20",
         "Unit": "imc_free_running_1"
     },
     {
-        "BriefDescription": "Counts every read and write request entering the Memory Controller 1.",
+        "BriefDescription": "This event is deprecated. [This event is alias to UNC_M_MC1_TOTAL_REQCOUNT_FREERUN]",
         "Counter": "5",
+        "Deprecated": "1",
         "EventCode": "0xff",
         "EventName": "UNC_MC1_TOTAL_REQCOUNT_FREERUN",
         "PerPkg": "1",
-        "PublicDescription": "Counts every read and write request entering the Memory Controller 1 (sum of all channels). All requests are counted as one, whether they are 32B or 64B Read/Write or partial/full line writes. Some write requests to the same address may merge to a single write command to DRAM. Therefore, the total request count may be higher than total DRAM BW.",
         "UMask": "0x10",
         "Unit": "imc_free_running_1"
     },
     {
-        "BriefDescription": "Counts every CAS write command sent from the Memory Controller 1 to DRAM (sum of all channels).",
+        "BriefDescription": "This event is deprecated. [This event is alias to UNC_M_MC1_WRCAS_COUNT_FREERUN]",
         "Counter": "4",
+        "Deprecated": "1",
         "EventCode": "0xff",
         "EventName": "UNC_MC1_WRCAS_COUNT_FREERUN",
         "PerPkg": "1",
-        "PublicDescription": "Counts every CAS write command sent from the Memory Controller 1 to DRAM (sum of all channels).  Each CAS commands can be for 32B or 64B of data.",
         "UMask": "0x30",
         "Unit": "imc_free_running_1"
     },
@@ -117,6 +117,66 @@
         "PerPkg": "1",
         "Unit": "iMC"
     },
+    {
+        "BriefDescription": "Counts every CAS read command sent from the Memory Controller 0 to DRAM (sum of all channels). [This event is alias to UNC_MC0_RDCAS_COUNT_FREERUN]",
+        "Counter": "0",
+        "EventCode": "0xff",
+        "EventName": "UNC_M_MC0_RDCAS_COUNT_FREERUN",
+        "PerPkg": "1",
+        "PublicDescription": "Counts every CAS read command sent from the Memory Controller 0 to DRAM (sum of all channels). Each CAS commands can be for 32B or 64B of data. [This event is alias to UNC_MC0_RDCAS_COUNT_FREERUN]",
+        "UMask": "0x20",
+        "Unit": "imc_free_running_0"
+    },
+    {
+        "BriefDescription": "Counts every read and write request entering the Memory Controller 0. [This event is alias to UNC_MC0_TOTAL_REQCOUNT_FREERUN]",
+        "Counter": "2",
+        "EventCode": "0xff",
+        "EventName": "UNC_M_MC0_TOTAL_REQCOUNT_FREERUN",
+        "PerPkg": "1",
+        "PublicDescription": "Counts every read and write request entering the Memory Controller 0 (sum of all channels). All requests are counted as one, whether they are 32B or 64B Read/Write or partial/full line writes. Some write requests to the same address may merge to a single write command to DRAM. Therefore, the total request count may be higher than total DRAM BW. [This event is alias to UNC_MC0_TOTAL_REQCOUNT_FREERUN]",
+        "UMask": "0x10",
+        "Unit": "imc_free_running_0"
+    },
+    {
+        "BriefDescription": "Counts every CAS write command sent from the Memory Controller 0 to DRAM (sum of all channels). [This event is alias to UNC_MC0_WRCAS_COUNT_FREERUN]",
+        "Counter": "1",
+        "EventCode": "0xff",
+        "EventName": "UNC_M_MC0_WRCAS_COUNT_FREERUN",
+        "PerPkg": "1",
+        "PublicDescription": "Counts every CAS write command sent from the Memory Controller 0 to DRAM (sum of all channels).  Each CAS commands can be for 32B or 64B of data. [This event is alias to UNC_MC0_WRCAS_COUNT_FREERUN]",
+        "UMask": "0x30",
+        "Unit": "imc_free_running_0"
+    },
+    {
+        "BriefDescription": "Counts every CAS read command sent from the Memory Controller 1 to DRAM (sum of all channels). [This event is alias to UNC_MC1_RDCAS_COUNT_FREERUN]",
+        "Counter": "3",
+        "EventCode": "0xff",
+        "EventName": "UNC_M_MC1_RDCAS_COUNT_FREERUN",
+        "PerPkg": "1",
+        "PublicDescription": "Counts every CAS read command sent from the Memory Controller 1 to DRAM (sum of all channels). Each CAS commands can be for 32B or 64B of data. [This event is alias to UNC_MC1_RDCAS_COUNT_FREERUN]",
+        "UMask": "0x20",
+        "Unit": "imc_free_running_1"
+    },
+    {
+        "BriefDescription": "Counts every read and write request entering the Memory Controller 1. [This event is alias to UNC_MC1_TOTAL_REQCOUNT_FREERUN]",
+        "Counter": "5",
+        "EventCode": "0xff",
+        "EventName": "UNC_M_MC1_TOTAL_REQCOUNT_FREERUN",
+        "PerPkg": "1",
+        "PublicDescription": "Counts every read and write request entering the Memory Controller 1 (sum of all channels). All requests are counted as one, whether they are 32B or 64B Read/Write or partial/full line writes. Some write requests to the same address may merge to a single write command to DRAM. Therefore, the total request count may be higher than total DRAM BW. [This event is alias to UNC_MC1_TOTAL_REQCOUNT_FREERUN]",
+        "UMask": "0x10",
+        "Unit": "imc_free_running_1"
+    },
+    {
+        "BriefDescription": "Counts every CAS write command sent from the Memory Controller 1 to DRAM (sum of all channels). [This event is alias to UNC_MC1_WRCAS_COUNT_FREERUN]",
+        "Counter": "4",
+        "EventCode": "0xff",
+        "EventName": "UNC_M_MC1_WRCAS_COUNT_FREERUN",
+        "PerPkg": "1",
+        "PublicDescription": "Counts every CAS write command sent from the Memory Controller 1 to DRAM (sum of all channels).  Each CAS commands can be for 32B or 64B of data. [This event is alias to UNC_MC1_WRCAS_COUNT_FREERUN]",
+        "UMask": "0x30",
+        "Unit": "imc_free_running_1"
+    },
     {
         "BriefDescription": "PRE command sent to DRAM due to page table idle timer expiration",
         "Counter": "0,1,2,3,4",
-- 
2.55.0.795.g602f6c329a-goog