diff --git a/projects/rocprofiler/bin/rocprofv2 b/projects/rocprofiler/bin/rocprofv2
index 8d708317de..319e70833f 100755
--- a/projects/rocprofiler/bin/rocprofv2
+++ b/projects/rocprofiler/bin/rocprofv2
@@ -262,6 +262,7 @@ if [ -n "$COUNTERS_PATH" ]; then
   done < $input
 fi
 
+COUNTERS_PMC_DIRS=""
 if [ -n "$PMC_LINES" ]; then
   COUNTER=1
   for i in ${!PMC_LINES[@]}; do
@@ -269,6 +270,7 @@ if [ -n "$PMC_LINES" ]; then
     if [ -n "$OUTPUT_PATH" ]; then
       if [ ! -n "$ATT_ARGV" ]; then
         FINAL_PATH="$OUTPUT_PATH_INTERNAL/pmc_$COUNTER"
+        COUNTERS_PMC_DIRS="$COUNTERS_PMC_DIRS $FINAL_PATH"
       else
         FINAL_PATH="$OUTPUT_PATH"
       fi
@@ -292,6 +294,32 @@ elif [ ! -n "$ATT_ARGV" ]; then
   fi
 fi
 
+get_pmc_results_txt_path(){
+  for file_name in `ls $1` ; do
+    if [[ $file_name == *results.txt ]]; then
+      echo "$1/$file_name"
+    fi
+  done
+}
+
+if [ -n "$COUNTERS_PMC_DIRS" ]; then
+  COUNTERS_RESULTS_TXT=""
+  for PMC_DIR in $COUNTERS_PMC_DIRS; do
+    COUNTERS_RESULTS_TXT="$COUNTERS_RESULTS_TXT $(get_pmc_results_txt_path $PMC_DIR)"
+  done
+  CSV_RESULTS=$OUTPUT_PATH_INTERNAL/results.csv
+  if [ -n "$OUT_FILE_NAME" ]; then
+    CSV_RESULTS=$OUTPUT_PATH_INTERNAL/$OUT_FILE_NAME
+  fi
+  echo "csv results path: $CSV_RESULTS"
+  export ROCP_MERGE_PIDS=1 #required for tblextr.py to work correctly for counters
+  if [ $RUN_FROM_BUILD == 1 ]; then
+    eval "python3 $ROCM_DIR/bin/tblextr.py $CSV_RESULTS $COUNTERS_RESULTS_TXT"
+  else
+    eval "python3 $ROCPROFV2_DIR/../libexec/rocprofiler/tblextr.py $CSV_RESULTS $COUNTERS_RESULTS_TXT"
+  fi
+fi
+
 if [ -n "$ATT_PATH" ]; then
   if [ -n "$ATT_ARGV" ]; then
     eval "python3 $ATT_PATH $ATT_ARGV"
diff --git a/projects/rocprofiler/plugin/file/file.cpp b/projects/rocprofiler/plugin/file/file.cpp
index d3a643199b..b8fbaf4164 100644
--- a/projects/rocprofiler/plugin/file/file.cpp
+++ b/projects/rocprofiler/plugin/file/file.cpp
@@ -286,10 +286,10 @@ class file_plugin_t {
                                                       profiler_record->kernel_id, &kernel_name_c));
     }
     *output_file << std::string("dispatch[") << std::to_string(profiler_record->header.id.handle)
-                 << "], " << std::string("gpu_id(")
+                 << "], " << std::string("gpu-id(")
                  << std::to_string(profiler_record->gpu_id.handle) << "), "
-                 << std::string("queue_id(") << std::to_string(profiler_record->queue_id.handle)
-                 << "), " << std::string("queue_index(")
+                 << std::string("queue-id(") << std::to_string(profiler_record->queue_id.handle)
+                 << "), " << std::string("queue-index(")
                  << std::to_string(profiler_record->queue_idx.value) << "), " << std::string("pid(")
                  << std::to_string(GetPid()) << "), " << std::string("tid(")
                  << std::to_string(profiler_record->thread_id.value) << ")";
@@ -321,9 +321,9 @@ class file_plugin_t {
                  << std::to_string(profiler_record->kernel_id.handle) << "), "
                  << std::string("kernel-name(\"") << kernel_name << "\")"
                  << std::string(", start_time(")
-                 << std::to_string(profiler_record->timestamps.begin.value) << ")"
-                 << std::string(", end_time(")
-                 << std::to_string(profiler_record->timestamps.end.value) << ")";
+                 << std::string(", time(0,")
+                 << std::to_string(profiler_record->timestamps.begin.value) << ","
+                 << std::to_string(profiler_record->timestamps.end.value) << ",0)";
 
     // For Counters
     *output_file << std::endl;
@@ -339,7 +339,7 @@ class file_plugin_t {
             CHECK_ROCPROFILER(rocprofiler_query_counter_info(
                 session_id, ROCPROFILER_COUNTER_NAME, profiler_record->counters[i].counter_handler,
                 &name_c));
-            *output_file << ", " << name_c << " ("
+            *output_file << " " << name_c << " ("
                          << std::to_string(profiler_record->counters[i].value.value) << ")"
                          << std::endl;
           }
diff --git a/projects/rocprofiler/src/core/counters/metrics/basic_counters.xml b/projects/rocprofiler/src/core/counters/metrics/basic_counters.xml
index ba2275accf..6095e3f2eb 100755
--- a/projects/rocprofiler/src/core/counters/metrics/basic_counters.xml
+++ b/projects/rocprofiler/src/core/counters/metrics/basic_counters.xml
@@ -498,6 +498,7 @@
   <metric name="SQ_WAVES_RESTORED" block=SQ event=185 descr="Count number of context-restored waves sent to SQs. (per-simd, emulated, global)"></metric>
   <metric name="SQ_WAVES_SAVED" block=SQ event=186 descr="Count number of context-saved waves. (per-simd, emulated, global)"></metric>
   <metric name="SQ_INSTS_SMEM_NORM" block=SQ event=187 descr="Number of SMEM instructions issued normalized to match smem_level (*2 load/store; *2 atomic; *2 memtime; *4 wb/inv). (per-simd, emulated)"></metric>
+  <metric name="SQC_ICACHE_INPUT_VALID_READYB" block=SQ event=257 descr=" Input stalled by SQC (per-SQ, nondeterministic, unwindowed)"></metric>
   <metric name="SQC_DCACHE_INPUT_VALID_READYB" block=SQ event=260 descr="Input stalled by SQC (per-SQ, nondeterministic, unwindowed)"></metric>
   <metric name="SQC_TC_REQ" block=SQ event=262 descr="Total number of TC requests that were issued by instruction and constant caches. (No-Masking, nondeterministic)"></metric>
   <metric name="SQC_TC_INST_REQ" block=SQ event=263 descr="Number of insruction requests to the TC (No-Masking, nondeterministic)"></metric>
@@ -505,10 +506,12 @@
   <metric name="SQC_TC_DATA_WRITE_REQ" block=SQ event=265 descr="Number of data write requests to the TC (No-Masking, nondeterministic)"></metric>
   <metric name="SQC_TC_DATA_ATOMIC_REQ" block=SQ event=266 descr="Number of data atomic requests to the TC (No-Masking, nondeterministic)"></metric>
   <metric name="SQC_TC_STALL" block=SQ event=267 descr="Valid request stalled TC request interface (no-credits). (No-Masking, nondeterministic, unwindowed)"></metric>
+  <metric name="SQC_ICACHE_BUSY_CYCLES" block=SQ event=269 descr="Clock cycles while cache is reporting that it is busy. (No-Masking, nondeterministic, unwindowed)"></metric>
   <metric name="SQC_ICACHE_REQ" block=SQ event=270 descr="Number of requests. (per-SQ, per-Bank)"></metric>
   <metric name="SQC_ICACHE_HITS" block=SQ event=271 descr="Number of cache hits. (per-SQ, per-Bank, nondeterministic)"></metric>
   <metric name="SQC_ICACHE_MISSES" block=SQ event=272 descr="Number of cache misses, includes uncached requests. (per-SQ, per-Bank, nondeterministic)"></metric>
   <metric name="SQC_ICACHE_MISSES_DUPLICATE" block=SQ event=273 descr="Number of misses that were duplicates (access to a non-resident, miss pending CL). (per-SQ, per-Bank, nondeterministic)" ></metric>
+  <metric name="SQC_DCACHE_BUSY_CYCLES" block=SQ event=289 descr=" Clock cycles while cache is reporting that it is busy. (No-Masking, nondeterministic, unwindowed)"></metric>
   <metric name="SQC_DCACHE_REQ" block=SQ event=290 descr="Number of requests (post-bank-serialization). (per-SQ, per-Bank)"></metric>
   <metric name="SQC_DCACHE_HITS" block=SQ event=291 descr="Number of cache hits. (per-SQ, per-Bank, nondeterministic)"></metric>
   <metric name="SQC_DCACHE_MISSES" block=SQ event=292 descr="Number of cache misses, includes uncached requests. (per-SQ, per-Bank, nondeterministic)"></metric>
@@ -591,6 +594,7 @@
   <metric name="TCC_RW_REQ" block=TCC event=8 descr="The number of RW requests. This is measured at the tag block."></metric>
   <metric name="TCC_PROBE" block=TCC event=9 descr="Number of probe requests. Not windowable."></metric>
   <metric name="TCC_PROBE_ALL" block=TCC event=10 descr="Number of external probe requests with with EA_TCC_preq_all== 1. Not windowable."></metric>
+  <metric name="TCC_INTERNAL_PROBE" block=TCC event=11 descr="Number of self-probes spawned by TCC for CC writes/atomic operations. Not windowable."></metric>
   <metric name="TCC_READ" block=TCC event=12 descr="Number of read requests. Compressed reads are included in this, but metadata reads are not included."></metric>
   <metric name="TCC_WRITE" block=TCC event=13 descr="Number of write requests."></metric>
   <metric name="TCC_ATOMIC" block=TCC event=14 descr="Number of atomic requests of all types."></metric>
@@ -599,6 +603,7 @@
   <metric name="TCC_WRITEBACK" block=TCC event=22 descr="Number of lines written back to main memory. This includes writebacks of dirty lines and uncached write/atomic requests."></metric>
   <metric name="TCC_EA0_WRREQ" block=TCC event=26 descr="Number of transactions (either 32-byte or 64-byte) going over the TC_EA_wrreq interface. Atomics may travel over the same interface and are generally classified as write requests. This does not include probe commands."></metric>
   <metric name="TCC_EA0_WRREQ_64B" block=TCC event=27 descr="Number of 64-byte transactions going (64-byte write or CMPSWAP) over the TC_EA_wrreq interface."></metric>
+  <metric name="TCC_EA0_WRREQ_PROBE_COMMAND" block=TCC event=28 descr="Number of probe commands going over the TC_EA_wrreq interface."></metric>
   <metric name="TCC_EA0_WR_UNCACHED_32B" block=TCC event=29 descr="Number of 32-byte write/atomic going over the TC_EA_wrreq interface due to uncached traffic. Note that CC mtypes can produce uncached requests, and those are included in this. A 64-byte request will be counted as 2"></metric>
   <metric name="TCC_EA0_WRREQ_STALL" block=TCC event=30 descr="Number of cycles a write request was stalled."></metric>
   <metric name="TCC_EA0_WRREQ_IO_CREDIT_STALL" block=TCC event=31 descr="Number of cycles a EA write request was stalled because the interface was out of IO credits."></metric>
@@ -620,6 +625,7 @@
   <metric name="TCC_ALL_TC_OP_WB_WRITEBACK" block=TCC event=73 descr="Number of writebacks due to all TC_OP writeback requests."></metric>
   <metric name="TCC_NORMAL_EVICT" block=TCC event=74 descr="Number of evictions due to requests that are not invalidate or probe requests."></metric>
   <metric name="TCC_ALL_TC_OP_INV_EVICT" block=TCC event=80 descr="Number of evictions due to all TC_OP invalidate requests."></metric>
+  <metric name="TCC_PROBE_EVICT" block=TCC event=81 descr="Number of evictions/invalidations due to probes. Not windowable."></metric>
   <metric name="TCC_EA0_RDREQ_DRAM" block=TCC event=102 descr="Number of TCC/EA read requests (either 32-byte or 64-byte) destined for DRAM (MC)."></metric>
   <metric name="TCC_EA0_WRREQ_DRAM" block=TCC event=103 descr="Number of TCC/EA write requests (either 32-byte of 64-byte) destined for DRAM (MC)."></metric>
 </gfx940>
diff --git a/projects/rocprofiler/src/core/counters/metrics/derived_counters.xml b/projects/rocprofiler/src/core/counters/metrics/derived_counters.xml
index b32c950728..3119c4577d 100755
--- a/projects/rocprofiler/src/core/counters/metrics/derived_counters.xml
+++ b/projects/rocprofiler/src/core/counters/metrics/derived_counters.xml
@@ -49,8 +49,8 @@
   <metric name="TCC_EA_WRREQ_64B_sum" expr=sum(TCC_EA_WRREQ_64B,16) descr="Number of 64-byte transactions going (64-byte write or CMPSWAP) over the TC_EA_wrreq interface. Sum over TCC instances."></metric>
   <metric name="TCC_WRREQ_STALL_max" expr=max(TCC_EA_WRREQ_STALL,16) descr="Number of cycles a write request was stalled. Max over TCC instances."></metric>
 
-  <metric name="TCP_TCP_TA_DATA_STALL_CYCLES_sum" expr=sum(TCP_TCP_TA_DATA_STALL_CYCLES,16) decr="Total number of TCP stalls TA data interface."></metric>
-  <metric name="TCP_TCP_TA_DATA_STALL_CYCLES_max" expr=max(TCP_TCP_TA_DATA_STALL_CYCLES,16) decr="Maximum number of TCP stalls TA data interface."></metric>
+  <metric name="TCP_TCP_TA_DATA_STALL_CYCLES_sum" expr=sum(TCP_TCP_TA_DATA_STALL_CYCLES,16) descr="Total number of TCP stalls TA data interface."></metric>
+  <metric name="TCP_TCP_TA_DATA_STALL_CYCLES_max" expr=max(TCP_TCP_TA_DATA_STALL_CYCLES,16) descr="Maximum number of TCP stalls TA data interface."></metric>
 
   <metric name="FETCH_SIZE" expr=(TCC_EA_RDREQ_32B_sum*32+(TCC_EA_RDREQ_sum-TCC_EA_RDREQ_32B_sum)*64)/1024 descr="The total kilobytes fetched from the video memory. This is measured with all extra fetches and any cache or memory effects taken into account."></metric>
   <metric name="WRITE_SIZE" expr=((TCC_EA_WRREQ_sum-TCC_EA_WRREQ_64B_sum)*32+TCC_EA_WRREQ_64B_sum*64)/1024 descr="The total kilobytes written to the video memory. This is measured with all extra fetches and any cache or memory effects taken into account."></metric>
@@ -291,8 +291,8 @@
 </gfx90a_expr>
 
 <gfx940_expr>
-  <metric name="TCP_TCP_TA_DATA_STALL_CYCLES_sum" expr=sum(TCP_TCP_TA_DATA_STALL_CYCLES,16) decr="Total number of TCP stalls TA data interface."></metric>
-  <metric name="TCP_TCP_TA_DATA_STALL_CYCLES_max" expr=max(TCP_TCP_TA_DATA_STALL_CYCLES,16) decr="Maximum number of TCP stalls TA data interface."></metric>
+  <metric name="TCP_TCP_TA_DATA_STALL_CYCLES_sum" expr=sum(TCP_TCP_TA_DATA_STALL_CYCLES,16) descr="Total number of TCP stalls TA data interface."></metric>
+  <metric name="TCP_TCP_TA_DATA_STALL_CYCLES_max" expr=max(TCP_TCP_TA_DATA_STALL_CYCLES,16) descr="Maximum number of TCP stalls TA data interface."></metric>
 
   <metric name="VFetchInsts" expr=(SQ_INSTS_VMEM_RD-TA_FLAT_READ_WAVEFRONTS_sum)/SQ_WAVES descr="The average number of vector fetch instructions from the video memory executed per work-item (affected by flow control). Excludes FLAT instructions that fetch from video memory."></metric>
   <metric name="VWriteInsts" expr=(SQ_INSTS_VMEM_WR-TA_FLAT_WRITE_WAVEFRONTS_sum)/SQ_WAVES descr="The average number of vector write instructions to the video memory executed per work-item (affected by flow control). Excludes FLAT instructions that write to video memory."></metric>
@@ -369,7 +369,7 @@
   <metric name="TCA_CYCLE_sum"                                          expr=sum(TCA_CYCLE,16)  descr="Number of cycles. Sum over all TCA instances "></metric>
   <metric name="TCA_BUSY_sum"                                           expr=sum(TCA_BUSY,16)   descr="Number of cycles we have a request pending. Sum over all TCA instances."></metric>
   <metric name="TCC_BUSY_avr"                                           expr=avr(TCC_BUSY,32) descr="TCC_BUSY avr over all memory channels."></metric>
-  <metric name="TCC_WRREQ_STALL_max"                                    expr=max(TCC_EA_WRREQ_STALL,32) descr="Number of cycles a write request was stalled. Max over TCC instances."></metric>
+  <metric name="TCC_WRREQ_STALL_max"                                    expr=max(TCC_EA0_WRREQ_STALL,32) descr="Number of cycles a write request was stalled. Max over TCC instances."></metric>
   <metric name="TCC_CYCLE_sum"                                          expr=sum(TCC_CYCLE,32) descr="Number of cycles. Not windowable. Sum over TCC instances."></metric>
   <metric name="TCC_BUSY_sum"                                           expr=sum(TCC_BUSY,32) descr="Number of cycles we have a request pending. Not windowable. Sum over TCC instances."></metric>
   <metric name="TCC_REQ_sum"                                            expr=sum(TCC_REQ,32) descr="Number of requests of all types. This is measured at the tag block. This may be more than the number of requests arriving at the TCC, but it is a good indication of the total amount of work that needs to be performed. Sum over TCC instances."></metric>
@@ -411,9 +411,9 @@
   <metric name="TCC_ALL_TC_OP_INV_EVICT_sum"                            expr=sum(TCC_ALL_TC_OP_INV_EVICT,32) descr="Number of evictions due to all TC_OP invalidate requests. Sum over TCC instances."></metric>
   <metric name="TCC_EA0_RDREQ_DRAM_sum"                                  expr=sum(TCC_EA0_RDREQ_DRAM,32) descr="Number of TCC/EA read requests (either 32-byte or 64-byte) destined for DRAM (MC). Sum over TCC instances."></metric>
   <metric name="TCC_EA0_WRREQ_DRAM_sum"                                  expr=sum(TCC_EA0_WRREQ_DRAM,32) descr="Number of TCC/EA write requests (either 32-byte of 64-byte) destined for DRAM (MC). Sum over TCC instances."></metric>
-  <metric name="FETCH_SIZE"                                             expr=(TCC_EA0_RDREQ_32B_sum*32+(TCC_EA_RDREQ_sum-TCC_EA_RDREQ_32B_sum)*64)/1024 descr="The total kilobytes fetched from the video memory. This is measured with all extra fetches and any cache or memory effects taken into account."></metric>
-  <metric name="WRITE_SIZE"                                             expr=((TCC_EA0_WRREQ_sum-TCC_EA_WRREQ_64B_sum)*32+TCC_EA_WRREQ_64B_sum*64)/1024 descr="The total kilobytes written to the video memory. This is measured with all extra fetches and any cache or memory effects taken into account."></metric>
-  <metric name="WRITE_REQ_32B"                                          expr=TCC_EA0_WRREQ_64B_sum*2+(TCC_EA_WRREQ_sum-TCC_EA_WRREQ_64B_sum) descr="The total number of 32-byte effective memory writes."></metric>
+  <metric name="FETCH_SIZE"                                             expr=(TCC_EA0_RDREQ_32B_sum*32+(TCC_EA0_RDREQ_sum-TCC_EA0_RDREQ_32B_sum)*64)/1024 descr="The total kilobytes fetched from the video memory. This is measured with all extra fetches and any cache or memory effects taken into account."></metric>
+  <metric name="WRITE_SIZE"                                             expr=((TCC_EA0_WRREQ_sum-TCC_EA0_WRREQ_64B_sum)*32+TCC_EA0_WRREQ_64B_sum*64)/1024 descr="The total kilobytes written to the video memory. This is measured with all extra fetches and any cache or memory effects taken into account."></metric>
+  <metric name="WRITE_REQ_32B"                                          expr=TCC_EA0_WRREQ_64B_sum*2+(TCC_EA0_WRREQ_sum-TCC_EA0_WRREQ_64B_sum) descr="The total number of 32-byte effective memory writes."></metric>
   <metric name="CU_OCCUPANCY"                                           expr=(SQ_CYCLES/(SQ_WAVE_CYCLES*4))/MAX_WAVE_SIZE descr="The ratio of active waves on a CU to the maximum number of active waves supported by the CU"></metric>
   <metric name="CU_UTILIZATION"                                         expr=GRBM_GUI_ACTIVE/GRBM_COUNT descr="The total number of active cycles divided by total number of elapsed cycles"></metric>
   <metric name="TOTAL_16_OPS"                                           expr=(SQ_INSTS_VALU_FMA_F16*2+SQ_INSTS_VALU_ADD_F16+SQ_INSTS_VALU_MUL_F16+SQ_INSTS_VALU_TRANS_F16)*64+((SQ_INSTS_VALU_MFMA_MOPS_F16+SQ_INSTS_VALU_MFMA_MOPS_BF16)*512) descr="The number of 16 bits OPS executed"></metric>
@@ -503,6 +503,8 @@
 <gfx908 base="gfx908_expr"></gfx908>
 # Aldebaran
 <gfx90a base="gfx90a_expr"></gfx90a>
+#Mi300
+<gfx940 base="gfx940_expr"></gfx940>
 #Navi21
 <gfx1030 base="gfx1030_expr"></gfx1030>
 <gfx1031 base="gfx1031_expr"></gfx1031>
diff --git a/projects/rocprofiler/src/core/counters/metrics/metrics.h b/projects/rocprofiler/src/core/counters/metrics/metrics.h
index d33c2849be..062285d344 100755
--- a/projects/rocprofiler/src/core/counters/metrics/metrics.h
+++ b/projects/rocprofiler/src/core/counters/metrics/metrics.h
@@ -203,10 +203,14 @@ class MetricsDict {
       xml_->AddConst("top.const.metric", "SE_NUM", agent_info->getShaderEngineCount());
       ImportMetrics(agent_info, "const");
       agent_name_ = agent_info->getName();
+      if (agent_name_.substr(0, 6) == "gfx940")
+        agent_name_ =
+            "gfx940";  // To correct the agent_name from "gfx940:forcestoresc1+" -> "gfx940"
       if (std::string("gfx906") == agent_name_ || std::string("gfx908") == agent_name_ ||
-          std::string("gfx90a") == agent_name_ || std::string("gfx1032") == agent_name_ ||
-          std::string("gfx1031") == agent_name_ || std::string("gfx1030") == agent_name_ ||
-          std::string("gfx1100") == agent_name_ || std::string("gfx1101") == agent_name_) {
+          std::string("gfx90a") == agent_name_ || std::string("gfx940") == agent_name_ ||
+          std::string("gfx1032") == agent_name_ || std::string("gfx1031") == agent_name_ ||
+          std::string("gfx1030") == agent_name_ || std::string("gfx1100") == agent_name_ ||
+          std::string("gfx1101") == agent_name_) {
         ImportMetrics(agent_info, agent_name_);
       } else {
         agent_name_ = agent_info->getGfxip();
diff --git a/projects/rocprofiler/src/core/metrics.h b/projects/rocprofiler/src/core/metrics.h
index 9ce4489252..02c2c36714 100755
--- a/projects/rocprofiler/src/core/metrics.h
+++ b/projects/rocprofiler/src/core/metrics.h
@@ -136,7 +136,8 @@ class MetricsDict {
     const Metric* metric = NULL;
 
     auto it = cache_.find(name);
-    if (it != cache_.end()) metric = it->second;
+    if (it != cache_.end())
+      metric = it->second;
     else {
       const std::size_t pos = name.find(':');
       if (pos != std::string::npos) {
@@ -148,7 +149,8 @@ class MetricsDict {
         const std::size_t pos1 = block_name.find('[');
         if (pos1 != std::string::npos) {
           const std::size_t pos2 = block_name.find(']');
-          if (pos2 == std::string::npos) EXC_RAISING(HSA_STATUS_ERROR, "Malformed metric name '" << name << "'");
+          if (pos2 == std::string::npos)
+            EXC_RAISING(HSA_STATUS_ERROR, "Malformed metric name '" << name << "'");
           block_name = name.substr(0, pos1);
           const std::string block_index_str = name.substr(pos1 + 1, pos2 - (pos1 + 1));
           block_index = atol(block_index_str.c_str());
@@ -156,8 +158,10 @@ class MetricsDict {
         }
 
         const hsa_ven_amd_aqlprofile_id_query_t query = Translate(agent_info_, block_name);
-        const hsa_ven_amd_aqlprofile_block_name_t block_id = (hsa_ven_amd_aqlprofile_block_name_t)query.id;
-        if ((query.instance_count > 1) && (indexed == false)) EXC_RAISING(HSA_STATUS_ERROR, "Malformed indexed metric name '" << name << "'");
+        const hsa_ven_amd_aqlprofile_block_name_t block_id =
+            (hsa_ven_amd_aqlprofile_block_name_t)query.id;
+        if ((query.instance_count > 1) && (indexed == false))
+          EXC_RAISING(HSA_STATUS_ERROR, "Malformed indexed metric name '" << name << "'");
         const uint32_t event_id = atol(event_str.c_str());
         const counter_t counter = {name, {block_id, block_index, event_id}};
         metric = new BaseMetric(name, counter);
@@ -189,22 +193,23 @@ class MetricsDict {
     const char* xml_name = getenv("ROCP_METRICS");
     if (xml_name != NULL) {
       xml_ = xml::Xml::Create(xml_name);
-      if (xml_ == NULL) EXC_RAISING(HSA_STATUS_ERROR, "metrics .xml open error '" << xml_name << "'");
+      if (xml_ == NULL)
+        EXC_RAISING(HSA_STATUS_ERROR, "metrics .xml open error '" << xml_name << "'");
       xml_->AddConst("top.const.metric", "MAX_WAVE_SIZE", agent_info->max_wave_size);
       xml_->AddConst("top.const.metric", "CU_NUM", agent_info->cu_num);
       xml_->AddConst("top.const.metric", "SIMD_NUM", agent_info->simds_per_cu * agent_info->cu_num);
       xml_->AddConst("top.const.metric", "SE_NUM", agent_info->se_num);
       ImportMetrics(agent_info, "const");
       agent_name_ = agent_info->name;
-      if (std::string("gfx906") == agent_info->name ||
-          std::string("gfx908") == agent_info->name ||
-          std::string("gfx90a") == agent_info->name ||
-          std::string("gfx1032") == agent_info->name ||
-          std::string("gfx1031") == agent_info->name ||
-          std::string("gfx1030") == agent_info->name ||
-          std::string("gfx1100") == agent_info->name ||
-          std::string("gfx1101") == agent_info->name) {
-         ImportMetrics(agent_info, agent_info->name);
+      if (agent_name_.substr(0, 6) == "gfx940")
+        agent_name_ =
+            "gfx940";  // To correct the agent_name from "gfx940:forcestoresc1+" -> "gfx940"
+      if (std::string("gfx906") == agent_name_ || std::string("gfx908") == agent_name_ ||
+          std::string("gfx90a") == agent_name_ || std::string("gfx940") == agent_name_ ||
+          std::string("gfx1032") == agent_name_ || std::string("gfx1031") == agent_name_ ||
+          std::string("gfx1030") == agent_name_ || std::string("gfx1100") == agent_name_ ||
+          std::string("gfx1101") == agent_name_) {
+        ImportMetrics(agent_info, agent_name_);
       } else {
         agent_name_ = agent_info->gfxip;
         ImportMetrics(agent_info, agent_info->gfxip);
@@ -218,14 +223,16 @@ class MetricsDict {
     for (auto& entry : cache_) delete entry.second;
   }
 
-  static hsa_ven_amd_aqlprofile_id_query_t Translate(const util::AgentInfo* agent_info, const std::string& block_name) {
+  static hsa_ven_amd_aqlprofile_id_query_t Translate(const util::AgentInfo* agent_info,
+                                                     const std::string& block_name) {
     hsa_ven_amd_aqlprofile_profile_t profile{};
     profile.agent = agent_info->dev_id;
     hsa_ven_amd_aqlprofile_id_query_t query = {block_name.c_str(), 0, 0};
     hsa_status_t status =
         util::HsaRsrcFactory::Instance().AqlProfileApi()->hsa_ven_amd_aqlprofile_get_info(
             &profile, HSA_VEN_AMD_AQLPROFILE_INFO_BLOCK_ID, &query);
-    if (status != HSA_STATUS_SUCCESS) AQL_EXC_RAISING(HSA_STATUS_ERROR, "ImportMetrics: bad block name '" << block_name << "'");
+    if (status != HSA_STATUS_SUCCESS)
+      AQL_EXC_RAISING(HSA_STATUS_ERROR, "ImportMetrics: bad block name '" << block_name << "'");
     return query;
   }
 
@@ -251,7 +258,8 @@ class MetricsDict {
           const uint32_t event_id = atol(event_str.c_str());
 
           const hsa_ven_amd_aqlprofile_id_query_t query = Translate(agent_info, block_name);
-          const hsa_ven_amd_aqlprofile_block_name_t block_id = (hsa_ven_amd_aqlprofile_block_name_t)query.id;
+          const hsa_ven_amd_aqlprofile_block_name_t block_id =
+              (hsa_ven_amd_aqlprofile_block_name_t)query.id;
           if (query.instance_count > 1) {
             for (unsigned block_index = 0; block_index < query.instance_count; ++block_index) {
               std::ostringstream full_name;
@@ -272,9 +280,11 @@ class MetricsDict {
           xml::Expr* expr_obj = NULL;
           try {
             expr_obj = new xml::Expr(expr_str, new ExprCache(&cache_));
-          } catch(const xml::exception_t& exc) {
-              if (do_lookup) metrics_list.push_back(node);
-              else throw(exc);
+          } catch (const xml::exception_t& exc) {
+            if (do_lookup)
+              metrics_list.push_back(node);
+            else
+              throw(exc);
           }
           if (expr_obj) {
 #if 0
@@ -285,7 +295,8 @@ class MetricsDict {
             for (const std::string& var : expr_obj->GetVars()) {
               auto it = cache_.find(var);
               if (it == cache_.end()) {
-                EXC_RAISING(HSA_STATUS_ERROR, "Bad metric '" << name << "', var '" << var << "' is not found");
+                EXC_RAISING(HSA_STATUS_ERROR,
+                            "Bad metric '" << name << "', var '" << var << "' is not found");
               }
               it->second->GetCounters(counters_vec);
             }
@@ -309,23 +320,27 @@ class MetricsDict {
     }
   }
 
-  const Metric* AddMetric(const std::string& name, const std::string& /*alias*/, const counter_t& counter) {
+  const Metric* AddMetric(const std::string& name, const std::string& /*alias*/,
+                          const counter_t& counter) {
     const Metric* metric = NULL;
     const auto ret = cache_.insert({name, NULL});
     if (ret.second) {
       metric = new BaseMetric(name, counter);
       ret.first->second = metric;
-    } else EXC_RAISING(HSA_STATUS_ERROR, "metric redefined '" << name << "'");
+    } else
+      EXC_RAISING(HSA_STATUS_ERROR, "metric redefined '" << name << "'");
     return metric;
   }
 
-  const Metric* AddMetric(const std::string& name, const counters_vec_t& counters_vec, const xml::Expr* expr_obj) {
+  const Metric* AddMetric(const std::string& name, const counters_vec_t& counters_vec,
+                          const xml::Expr* expr_obj) {
     const Metric* metric = NULL;
     const auto ret = cache_.insert({name, NULL});
     if (ret.second) {
       metric = new ExprMetric(name, counters_vec, expr_obj);
       ret.first->second = metric;
-    } else EXC_RAISING(HSA_STATUS_ERROR, "expr-metric redefined '" << name << "'");
+    } else
+      EXC_RAISING(HSA_STATUS_ERROR, "expr-metric redefined '" << name << "'");
     return metric;
   }
 
@@ -336,7 +351,8 @@ class MetricsDict {
       printf("> Metric '%s'\n", metric->GetName().c_str());
       metric->GetCounters(counters_vec);
       for (auto c : counters_vec) {
-        printf("  counter %s, b(%u), i (%u), e (%u)\n", c->name.c_str(), c->event.block_name, c->event.block_index, c->event.counter_id);
+        printf("  counter %s, b(%u), i (%u), e (%u)\n", c->name.c_str(), c->event.block_name,
+               c->event.block_index, c->event.counter_id);
       }
     }
   }
diff --git a/projects/rocprofiler/test/tool/gfx_metrics.xml b/projects/rocprofiler/test/tool/gfx_metrics.xml
index a1ff2ea710..768b896c7e 100755
--- a/projects/rocprofiler/test/tool/gfx_metrics.xml
+++ b/projects/rocprofiler/test/tool/gfx_metrics.xml
@@ -105,7 +105,7 @@
 <gfx90a>
   <metric name="SQ_WAIT_INST_LDS" block=SQ event=91 descr="Number of wave-cycles spent waiting for LDS instruction issue. In units of 4 cycles. (per-simd, nondeterministic)"></metric>
   <metric name="TCP_TCP_TA_DATA_STALL_CYCLES" block=TCP event=6 descr="TCP stalls TA data interface. Now Windowed."></metric>
-  
+
   <metric name="GRBM_COUNT" block=GRBM event=0 descr="Tie High - Count Number of Clocks"></metric>
   <metric name="GRBM_GUI_ACTIVE" block=GRBM event=2 descr="The GUI is Active"></metric>
   <metric name="GRBM_CP_BUSY" block=GRBM event=3 descr="Any of the Command Processor (CPG/CPC/CPF) blocks are busy."></metric>
@@ -366,6 +366,271 @@
   <metric name="TCC_EA_WRREQ_DRAM" block=TCC event=103 descr="Number of TCC/EA write requests (either 32-byte of 64-byte) destined for DRAM (MC)."></metric>
 </gfx90a>
 
+<gfx940>
+  <metric name="SQ_WAIT_INST_LDS" block=SQ event=96 descr="Number of wave-cycles spent waiting for LDS instruction issue. In units of 4 cycles. (per-simd, nondeterministic)"></metric>
+  <metric name="TCP_TCP_TA_DATA_STALL_CYCLES" block=TCP event=6 descr="TCP stalls TA data interface. Now Windowed."></metric>
+  <metric name="GRBM_COUNT" block=GRBM event=0 descr="Tie High - Count Number of Clocks"></metric>
+  <metric name="GRBM_GUI_ACTIVE" block=GRBM event=2 descr="The GUI is Active"></metric>
+  <metric name="GRBM_CP_BUSY" block=GRBM event=3 descr="Any of the Command Processor (CPG/CPC/CPF) blocks are busy."></metric>
+  <metric name="GRBM_SPI_BUSY" block=GRBM event=11 descr="Any of the Shader Pipe Interpolators (SPI) are busy in the shader engine(s)."></metric>
+  <metric name="GRBM_TA_BUSY" block=GRBM event=13 descr="Any of the Texture Pipes (TA) are busy in the shader engine(s)."></metric>
+  <metric name="GRBM_TC_BUSY" block=GRBM event=28 descr="Any of the Texture Cache Blocks (TCP/TCI/TCA/TCC) are busy."></metric>
+  <metric name="GRBM_CPC_BUSY" block=GRBM event=30 descr="The Command Processor Compute (CPC) is busy."></metric>
+  <metric name="GRBM_CPF_BUSY" block=GRBM event=31 descr="The Command Processor Fetchers (CPF) is busy."></metric>
+  <metric name="GRBM_UTCL2_BUSY" block=GRBM event=34 descr="The Unified Translation Cache Level-2 (UTCL2) block is busy."></metric>
+  <metric name="GRBM_EA_BUSY" block=GRBM event=35 descr="The Efficiency Arbiter (EA) block is busy."></metric>
+  <metric name="CPC_ME1_BUSY_FOR_PACKET_DECODE" block=CPC event=13 descr="Me1 busy for packet decode."></metric>
+  <metric name="CPC_UTCL1_STALL_ON_TRANSLATION" block=CPC event=24 descr="One of the UTCL1s is stalled waiting on translation, XNACK or PENDING response."></metric>
+  <metric name="CPC_CPC_STAT_BUSY" block=CPC event=25 descr="CPC Busy."></metric>
+  <metric name="CPC_CPC_STAT_IDLE" block=CPC event=26 descr="CPC Idle."></metric>
+  <metric name="CPC_CPC_STAT_STALL" block=CPC event=27 descr="CPC Stalled."></metric>
+  <metric name="CPC_CPC_TCIU_BUSY" block=CPC event=28 descr="CPC TCIU interface Busy."></metric>
+  <metric name="CPC_CPC_TCIU_IDLE" block=CPC event=29 descr="CPC TCIU interface Idle."></metric>
+  <metric name="CPC_CPC_UTCL2IU_BUSY" block=CPC event=30 descr="CPC UTCL2 interface Busy."></metric>
+  <metric name="CPC_CPC_UTCL2IU_IDLE" block=CPC event=31 descr="CPC UTCL2 interface Idle."></metric>
+  <metric name="CPC_CPC_UTCL2IU_STALL" block=CPC event=32 descr="CPC UTCL2 interface Stalled waiting on Free, Tags or Translation."></metric>
+  <metric name="CPC_ME1_DC0_SPI_BUSY" block=CPC event=33 descr="CPC Me1 Processor Busy."></metric>
+  <metric name="CPF_CMP_UTCL1_STALL_ON_TRANSLATION" block=CPF event=20 descr="One of the Compute UTCL1s is stalled waiting on translation, XNACK or PENDING response."></metric>
+  <metric name="CPF_CPF_STAT_BUSY" block=CPF event=23 descr="CPF Busy."></metric>
+  <metric name="CPF_CPF_STAT_IDLE" block=CPF event=24 descr="CPF Idle."></metric>
+  <metric name="CPF_CPF_STAT_STALL" block=CPF event=25 descr="CPF Stalled."></metric>
+  <metric name="CPF_CPF_TCIU_BUSY" block=CPF event=26 descr="CPF TCIU interface Busy."></metric>
+  <metric name="CPF_CPF_TCIU_IDLE" block=CPF event=27 descr="CPF TCIU interface Idle."></metric>
+  <metric name="CPF_CPF_TCIU_STALL" block=CPF event=28 descr="CPF TCIU interface Stalled waiting on Free, Tags."></metric>
+  <metric name="SPI_CSN_WINDOW_VALID" block=SPI event=47 descr="Clock count enabled by perfcounter_start event. Requires SPI_DEBUG_CNTL.DEBUG_PIPE_SEL to select source, DEBUG_PIPE_SEL = 1, source is CS1; DEBUG_PIPE_SEL = 2, source is CS2; DEBUG_PIPE_SEL = 3, source is CS3; default, source is CS0;"></metric>
+  <metric name="SPI_CSN_BUSY" block=SPI event=48 descr="Number of clocks with outstanding waves (SPI or SH). Requires SPI_DEBUG_CNTL.DEBUG_PIPE_SEL to select source, DEBUG_PIPE_SEL = 1, source is CS1; DEBUG_PIPE_SEL = 2, source is CS2; DEBUG_PIPE_SEL = 3, source is CS3; default, source is CS0;"></metric>
+  <metric name="SPI_CSN_NUM_THREADGROUPS" block=SPI event=49 descr="Number of threadgroups launched. Requires SPI_DEBUG_CNTL.DEBUG_PIPE_SEL to select source, DEBUG_PIPE_SEL = 1, source is CS1; DEBUG_PIPE_SEL = 2, source is CS2; DEBUG_PIPE_SEL = 3, source is CS3; default, source is CS0;"></metric>
+  <metric name="SPI_CSN_WAVE" block=SPI event=52 descr="Number of waves. Requires SPI_DEBUG_CNTL.DEBUG_PIPE_SEL to select source, DEBUG_PIPE_SEL = 1, source is CS1; DEBUG_PIPE_SEL = 2, source is CS2; DEBUG_PIPE_SEL = 3, source is CS3; default, source is CS0;"></metric>
+  <metric name="SPI_RA_REQ_NO_ALLOC" block=SPI event=79 descr="Arb cycles with requests but no allocation. Source is RA0"></metric>
+  <metric name="SPI_RA_REQ_NO_ALLOC_CSN" block=SPI event=85 descr="Arb cycles with CSn req and no CSn alloc. Source is RA0"></metric>
+  <metric name="SPI_RA_RES_STALL_CSN" block=SPI event=91 descr="Arb cycles with CSn req and no CSn fits. Source is RA0"></metric>
+  <metric name="SPI_RA_TMP_STALL_CSN" block=SPI event=97 descr="Cycles where csn wants to req but does not fit in temp space."></metric>
+  <metric name="SPI_RA_WAVE_SIMD_FULL_CSN" block=SPI event=103 descr="Sum of SIMD where WAVE can't take csn wave when !fits. Source is RA0"></metric>
+  <metric name="SPI_RA_VGPR_SIMD_FULL_CSN" block=SPI event=109 descr="Sum of SIMD where VGPR can't take csn wave when !fits. Source is RA0"></metric>
+  <metric name="SPI_RA_SGPR_SIMD_FULL_CSN" block=SPI event=115 descr="Sum of SIMD where SGPR can't take csn wave when !fits. Source is RA0"></metric>
+  <metric name="SPI_RA_LDS_CU_FULL_CSN" block=SPI event=120 descr="Sum of CU where LDS can't take csn wave when !fits. Source is RA0"></metric>
+  <metric name="SPI_RA_BAR_CU_FULL_CSN" block=SPI event=123 descr="Sum of CU where BARRIER can't take csn wave when !fits. Source is RA0"></metric>
+  <metric name="SPI_RA_BULKY_CU_FULL_CSN" block=SPI event=125 descr="Sum of CU where BULKY can't take csn wave when !fits. Source is RA0"></metric>
+  <metric name="SPI_RA_TGLIM_CU_FULL_CSN" block=SPI event=127 descr="Cycles where csn wants to req but all CU are at tg_limit"></metric>
+  <metric name="SPI_RA_WVLIM_STALL_CSN" block=SPI event=133 descr="Number of clocks csn is stalled due to WAVE LIMIT."></metric>
+  <metric name="SPI_SWC_CSC_WR" block=SPI event=189 descr="Number of clocks to write CSC waves to SGPRs (need to multiply this value by 4) Requires SPI_DEBUG_CNTL.DEBUG_PIPE_SEL to select source, DEBUG_PIPE_SEL = 1, source is CS1; DEBUG_PIPE_SEL = 2, source is CS2; DEBUG_PIPE_SEL = 3, source is CS3; default, source is CS0;"></metric>
+  <metric name="SPI_VWC_CSC_WR" block=SPI event=195 descr="Number of clocks to write CSC waves to VGPRs (need to multiply this value by 4) Requires SPI_DEBUG_CNTL.DEBUG_PIPE_SEL to select source, DEBUG_PIPE_SEL = 1, source is CS1; DEBUG_PIPE_SEL = 2, source is CS2; DEBUG_PIPE_SEL = 3, source is CS3; default, source is CS0;"></metric>
+  <metric name="SQ_ACCUM_PREV" block=SQ event=1 descr="For counter N, increment by the value of counter N-1. Only accumulates once every 4 cycles."></metric>
+  <metric name="SQ_CYCLES" block=SQ event=2 descr="Clock cycles. (nondeterministic, per-simd, global)"></metric>
+  <metric name="SQ_BUSY_CYCLES" block=SQ event=3 descr="Clock cycles while SQ is reporting that it is busy. (nondeterministic, per-simd, global)"></metric>
+  <metric name="SQ_WAVES" block=SQ event=4 descr="Count number of waves sent to SQs. (per-simd, emulated, global)"></metric>
+  <metric name="SQ_LEVEL_WAVES" block=SQ event=5 descr="Track the number of waves. Set ACCUM_PREV for the next counter to use this. (level, per-simd, global)"></metric>
+  <metric name="SQ_WAVES_EQ_64" block=SQ event=6 descr="Count number of waves with exactly 64 active threads sent to SQs. (per-simd, emulated, global)"></metric>
+  <metric name="SQ_WAVES_LT_64" block=SQ event=7 descr="Count number of waves with <64 active threads sent to SQs. (per-simd, emulated, global)"></metric>
+  <metric name="SQ_WAVES_LT_48" block=SQ event=8 descr="Count number of waves with <48 active threads sent to SQs. (per-simd, emulated, global)"></metric>
+  <metric name="SQ_WAVES_LT_32" block=SQ event=9 descr="Count number of waves sent <32 active threads sent to SQs. (per-simd, emulated, global)"></metric>
+  <metric name="SQ_WAVES_LT_16" block=SQ event=10 descr="Count number of waves sent <16 active threads sent to SQs. (per-simd, emulated, global)"></metric>
+  <metric name="SQ_BUSY_CU_CYCLES" block=SQ event=13 descr="Count quad-cycles each CU is busy. (nondeterministic, per-simd)"></metric>
+  <metric name="SQ_ITEMS" block=SQ event=14 descr="Number of valid items per wave. (per-simd, global)"></metric>
+  <metric name="SQ_INSTS" block=SQ event=25 descr="Number of instructions issued. (per-simd, emulated)"></metric>
+  <metric name="SQ_INSTS_VALU" block=SQ event=26 descr="Number of VALU instructions issued. (per-simd, emulated)"></metric>
+  <metric name="SQ_INSTS_VALU_ADD_F16" block=SQ event=27 descr="Number of VALU ADD/SUB instructions on float16. (per-simd, emulated)"></metric>
+  <metric name="SQ_INSTS_VALU_MUL_F16" block=SQ event=28 descr="Number of VALU MUL instructions on float16. (per-simd, emulated)"></metric>
+  <metric name="SQ_INSTS_VALU_FMA_F16" block=SQ event=29 descr="Number of VALU FMA/MAD instructions on float16. (per-simd, emulated)"></metric>
+  <metric name="SQ_INSTS_VALU_TRANS_F16" block=SQ event=30 descr="Number of VALU transcendental instructions on float16. (per-simd, emulated)"></metric>
+  <metric name="SQ_INSTS_VALU_ADD_F32" block=SQ event=31 descr="Number of VALU ADD/SUB instructions on float32. (per-simd, emulated)"></metric>
+  <metric name="SQ_INSTS_VALU_MUL_F32" block=SQ event=32 descr="Number of VALU MUL instructions on float32. (per-simd, emulated)"></metric>
+  <metric name="SQ_INSTS_VALU_FMA_F32" block=SQ event=33 descr="Number of VALU FMA/MAD instructions on float32. (per-simd, emulated)"></metric>
+  <metric name="SQ_INSTS_VALU_TRANS_F32" block=SQ event=34 descr="Number of VALU transcendental instructions on float32. (per-simd, emulated)"></metric>
+  <metric name="SQ_INSTS_VALU_ADD_F64" block=SQ event=35 descr="Number of VALU ADD/SUB instructions on float64. (per-simd, emulated)"></metric>
+  <metric name="SQ_INSTS_VALU_MUL_F64" block=SQ event=36 descr="Number of VALU MUL instructions on float64. (per-simd, emulated)"></metric>
+  <metric name="SQ_INSTS_VALU_FMA_F64" block=SQ event=37 descr="Number of VALU FMA/MAD instructions on float64. (per-simd, emulated)"></metric>
+  <metric name="SQ_INSTS_VALU_TRANS_F64" block=SQ event=38 descr="Number of VALU transcendental instructions on float64. (per-simd, emulated)"></metric>
+  <metric name="SQ_INSTS_VALU_INT32" block=SQ event=39 descr="Number of VALU 32-bit integer (signed or unsigned) instructions. (per-simd, emulated)"></metric>
+  <metric name="SQ_INSTS_VALU_INT64" block=SQ event=40 descr="Number of VALU 64-bit integer (signed or unsigned) instructions. (per-simd, emulated)"></metric>
+  <metric name="SQ_INSTS_VALU_CVT" block=SQ event=41 descr="Number of VALU data conversion instructions. (per-simd, emulated)"></metric>
+  <metric name="SQ_INSTS_VALU_MFMA_I8" block=SQ event=42 descr="Number of VALU V_MFMA_*_I8 instructions. (per-simd, emulated)"></metric>
+  <metric name="SQ_INSTS_VALU_MFMA_F16" block=SQ event=43 descr="Number of VALU V_MFMA_*_F16 instructions. (per-simd, emulated)"></metric>
+  <metric name="SQ_INSTS_VALU_MFMA_BF16" block=SQ event=44 descr="Number of VALU V_MFMA_*_BF16 instructions. (per-simd, emulated)"></metric>
+  <metric name="SQ_INSTS_VALU_MFMA_F32" block=SQ event=45 descr="Number of VALU V_MFMA_*_F32 instructions. (per-simd, emulated)"></metric>
+  <metric name="SQ_INSTS_VALU_MFMA_F64" block=SQ event=46 descr="Number of VALU V_MFMA_*_F64 instructions. (per-simd, emulated)"></metric>
+  <metric name="SQ_INSTS_VALU_MFMA_MOPS_I8" block=SQ event=49 descr="Number of VALU matrix math operations (add or mul) performed dividied by 512, assuming a full EXEC mask, of data type I8. (per-simd, emulated)"></metric>
+  <metric name="SQ_INSTS_VALU_MFMA_MOPS_F16" block=SQ event=50 descr="Number of VALU matrix math operations (add or mul) performed dividied by 512, assuming a full EXEC mask, of data type F16. (per-simd, emulated)"></metric>
+  <metric name="SQ_INSTS_VALU_MFMA_MOPS_BF16" block=SQ event=51 descr="Number of VALU matrix math operations (add or mul) performed dividied by 512, assuming a full EXEC mask, of data type BF16. (per-simd, emulated)"></metric>
+  <metric name="SQ_INSTS_VALU_MFMA_MOPS_F32" block=SQ event=52 descr="Number of VALU matrix math operations (add or mul) performed dividied by 512, assuming a full EXEC mask, of data type F32. (per-simd, emulated)"></metric>
+  <metric name="SQ_INSTS_VALU_MFMA_MOPS_F64" block=SQ event=53 descr="Number of VALU matrix math operations (add or mul) performed dividied by 512, assuming a full EXEC mask, of data type F64. (per-simd, emulated)"></metric>
+  <metric name="SQ_INSTS_MFMA" block=SQ event=56 descr="Number of MFMA instructions issued. (per-simd, emulated)"></metric>
+  <metric name="SQ_INSTS_VMEM_WR" block=SQ event=57 descr="Number of VMEM write instructions issued (including FLAT). (per-simd, emulated)"></metric>
+  <metric name="SQ_INSTS_VMEM_RD" block=SQ event=58 descr="Number of VMEM read instructions issued (including FLAT). (per-simd, emulated)"></metric>
+  <metric name="SQ_INSTS_VMEM" block=SQ event=59 descr="Number of VMEM instructions issued. (per-simd, emulated)"></metric>
+  <metric name="SQ_INSTS_SALU" block=SQ event=60 descr="Number of SALU instructions issued. (per-simd, emulated)"></metric>
+  <metric name="SQ_INSTS_SMEM" block=SQ event=61 descr="Number of SMEM instructions issued. (per-simd, emulated)"></metric>
+  <metric name="SQ_INSTS_FLAT" block=SQ event=62 descr="Number of FLAT instructions issued. (per-simd, emulated)"></metric>
+  <metric name="SQ_INSTS_LDS" block=SQ event=65 descr="Number of LDS instructions issued (including FLAT). (per-simd, emulated)"></metric>
+  <metric name="SQ_INSTS_GDS" block=SQ event=66 descr="Number of GDS instructions issued. (per-simd, emulated)"></metric>
+  <metric name="SQ_INSTS_EXP_GDS" block=SQ event=68 descr="Number of EXP and GDS instructions issued, excluding skipped export instructions. (per-simd, emulated)"></metric>
+  <metric name="SQ_INSTS_BRANCH" block=SQ event=69 descr="Number of Branch instructions issued. (per-simd, emulated)"></metric>
+  <metric name="SQ_INSTS_SENDMSG" block=SQ event=70 descr="Number of Sendmsg instructions issued. (per-simd, emulated)"></metric>
+  <metric name="SQ_INSTS_VSKIPPED" block=SQ event=71 descr="Number of vector instructions skipped. (per-simd, emulated)"></metric>
+  <metric name="SQ_INST_LEVEL_VMEM" block=SQ event=72 descr="Number of in-flight VMEM instructions. Set next counter to ACCUM_PREV and divide by INSTS_VMEM for average latency. Includes FLAT instructions. (per-simd, level, nondeterministic)"></metric>
+  <metric name="SQ_INST_LEVEL_SMEM" block=SQ event=73 descr="Number of in-flight SMEM instructions (*2 load/store; *2 atomic; *2 memtime; *4 wb/inv). Set next counter to ACCUM_PREV and divide by INSTS_SMEM for average latency per smem request. Falls slightly short of total request latency because some fetches are divided into two requests that may finish at different times and this counter collects the average latency of the two. (per-simd, level, nondeterministic)"></metric>
+  <metric name="SQ_INST_LEVEL_LDS" block=SQ event=74 descr="Number of in-flight LDS instructions. Set next counter to ACCUM_PREV and divide by INSTS_LDS for average latency. Includes FLAT instructions. (per-simd, level, nondeterministic)"></metric>
+  <metric name="SQ_VALU_MFMA_BUSY_CYCLES" block=SQ event=77 descr="Number of cycles the MFMA ALU is busy (per-simd, emulated)"></metric>
+  <metric name="SQ_WAVE_CYCLES" block=SQ event=79 descr="Number of wave-cycles spent by waves in the CUs (per-simd, nondeterministic). Units in quad-cycles(4 cycles)"></metric>
+  <metric name="SQ_WAIT_ANY" block=SQ event=90 descr="Number of wave-cycles spent waiting for anything (per-simd, nondeterministic). Units in quad-cycles(4 cycles)"></metric>
+  <metric name="SQ_WAIT_INST_ANY" block=SQ event=93 descr="Number of wave-cycles spent waiting for any instruction issue. In units of 4 cycles. (per-simd, nondeterministic)"></metric>
+  <metric name="SQ_ACTIVE_INST_ANY" block=SQ event=101 descr="Number of cycles each wave is working on an instruction. (per-simd, emulated). Units in quad-cycles(4 cycles)"></metric>
+  <metric name="SQ_ACTIVE_INST_VMEM" block=SQ event=102 descr="Number of cycles the SQ instruction arbiter is working on a VMEM instruction. (per-simd, emulated). Units in quad-cycles(4 cycles)"></metric>
+  <metric name="SQ_ACTIVE_INST_LDS" block=SQ event=103 descr="Number of cycles the SQ instruction arbiter is working on a LDS instruction. (per-simd, emulated). Units in quad-cycles(4 cycles)"></metric>
+  <metric name="SQ_ACTIVE_INST_VALU" block=SQ event=104 descr="Number of cycles the SQ instruction arbiter is working on a VALU instruction. (per-simd, emulated). Units in quad-cycles(4 cycles)"></metric>
+  <metric name="SQ_ACTIVE_INST_SCA" block=SQ event=105 descr="Number of cycles the SQ instruction arbiter is working on a SALU or SMEM instruction. (per-simd, emulated). Units in quad-cycles(4 cycles)"></metric>
+  <metric name="SQ_ACTIVE_INST_EXP_GDS" block=SQ event=106 descr="Number of cycles the SQ instruction arbiter is working on an EXPORT or GDS instruction. (per-simd, emulated). Units in quad-cycles(4 cycles)"></metric>
+  <metric name="SQ_ACTIVE_INST_MISC" block=SQ event=107 descr="Number of cycles the SQ instruction aribter is working on a BRANCH or SENDMSG instruction. (per-simd, emulated). Units in quad-cycles(4 cycles)"></metric>
+  <metric name="SQ_ACTIVE_INST_FLAT" block=SQ event=108 descr="Number of cycles the SQ instruction arbiter is working on a FLAT instruction. (per-simd, emulated). Units in quad-cycles(4 cycles)"></metric>
+  <metric name="SQ_INST_CYCLES_VMEM_WR" block=SQ event=109 descr="Number of cycles needed to send addr and cmd data for VMEM write instructions. (per-simd, emulated). Units in quad-cycles(4 cycles)"></metric>
+  <metric name="SQ_INST_CYCLES_VMEM_RD" block=SQ event=110 descr="Number of cycles needed to send addr and cmd data for VMEM read instructions. (per-simd, emulated). Units in quad-cycles(4 cycles)"></metric>
+  <metric name="SQ_INST_CYCLES_SMEM" block=SQ event=116 descr="Number of cycles needed to execute scalar memory reads. (per-simd, emulated)"></metric>
+  <metric name="SQ_INST_CYCLES_SALU" block=SQ event=117 descr="Number of cycles needed to execute non-memory read scalar operations. (per-simd, emulated). Units in quad-cycles(4 cycles)"></metric>
+  <metric name="SQ_THREAD_CYCLES_VALU" block=SQ event=118 descr="Number of thread-cycles used to execute VALU operations (similar to INST_CYCLES_VALU but multiplied by # of active threads). (per-simd)"></metric>
+  <metric name="SQ_IFETCH" block=SQ event=120 descr="Number of instruction fetch requests from cache. (per-simd, emulated)"></metric>
+  <metric name="SQ_IFETCH_LEVEL" block=SQ event=121 descr="Number of instruction fetch requests from cache. (per-simd, level)"></metric>
+  <metric name="SQ_LDS_BANK_CONFLICT" block=SQ event=126 descr="Number of cycles LDS is stalled by bank conflicts. (emulated)"></metric>
+  <metric name="SQ_LDS_ADDR_CONFLICT" block=SQ event=127 descr="Number of cycles LDS is stalled by address conflicts. (emulated,nondeterministic)"></metric>
+  <metric name="SQ_LDS_UNALIGNED_STALL" block=SQ event=128 descr="Number of cycles LDS is stalled processing flat unaligned load/store ops. (emulated)"></metric>
+  <metric name="SQ_LDS_MEM_VIOLATIONS" block=SQ event=129 descr="Number of threads that have a memory violation in the LDS.(emulated)"></metric>
+  <metric name="SQ_LDS_ATOMIC_RETURN" block=SQ event=130 descr="Number of atomic return cycles in LDS. (per-simd, emulated)"></metric>
+  <metric name="SQ_LDS_IDX_ACTIVE" block=SQ event=131 descr="Number of cycles LDS is used for indexed (non-direct,non-interpolation) operations. (per-simd, emulated)"></metric>
+  <metric name="SQ_ACCUM_PREV_HIRES" block=SQ event=184 descr="For counter N, increment by the value of counter N-1."></metric>
+  <metric name="SQ_WAVES_RESTORED" block=SQ event=185 descr="Count number of context-restored waves sent to SQs. (per-simd, emulated, global)"></metric>
+  <metric name="SQ_WAVES_SAVED" block=SQ event=186 descr="Count number of context-saved waves. (per-simd, emulated, global)"></metric>
+  <metric name="SQ_INSTS_SMEM_NORM" block=SQ event=187 descr="Number of SMEM instructions issued normalized to match smem_level (*2 load/store; *2 atomic; *2 memtime; *4 wb/inv). (per-simd, emulated)"></metric>
+  <metric name="SQC_ICACHE_INPUT_VALID_READYB" block=SQ event=257 descr=" Input stalled by SQC (per-SQ, nondeterministic, unwindowed)"></metric>
+  <metric name="SQC_DCACHE_INPUT_VALID_READYB" block=SQ event=260 descr="Input stalled by SQC (per-SQ, nondeterministic, unwindowed)"></metric>
+  <metric name="SQC_TC_REQ" block=SQ event=262 descr="Total number of TC requests that were issued by instruction and constant caches. (No-Masking, nondeterministic)"></metric>
+  <metric name="SQC_TC_INST_REQ" block=SQ event=263 descr="Number of insruction requests to the TC (No-Masking, nondeterministic)"></metric>
+  <metric name="SQC_TC_DATA_READ_REQ" block=SQ event=264 descr="Number of data read requests to the TC (No-Masking, nondeterministic)"></metric>
+  <metric name="SQC_TC_DATA_WRITE_REQ" block=SQ event=265 descr="Number of data write requests to the TC (No-Masking, nondeterministic)"></metric>
+  <metric name="SQC_TC_DATA_ATOMIC_REQ" block=SQ event=266 descr="Number of data atomic requests to the TC (No-Masking, nondeterministic)"></metric>
+  <metric name="SQC_TC_STALL" block=SQ event=267 descr="Valid request stalled TC request interface (no-credits). (No-Masking, nondeterministic, unwindowed)"></metric>
+  <metric name="SQC_ICACHE_BUSY_CYCLES" block=SQ event=269 descr="Clock cycles while cache is reporting that it is busy. (No-Masking, nondeterministic, unwindowed)"></metric>
+  <metric name="SQC_ICACHE_REQ" block=SQ event=270 descr="Number of requests. (per-SQ, per-Bank)"></metric>
+  <metric name="SQC_ICACHE_HITS" block=SQ event=271 descr="Number of cache hits. (per-SQ, per-Bank, nondeterministic)"></metric>
+  <metric name="SQC_ICACHE_MISSES" block=SQ event=272 descr="Number of cache misses, includes uncached requests. (per-SQ, per-Bank, nondeterministic)"></metric>
+  <metric name="SQC_ICACHE_MISSES_DUPLICATE" block=SQ event=273 descr="Number of misses that were duplicates (access to a non-resident, miss pending CL). (per-SQ, per-Bank, nondeterministic)" ></metric>
+  <metric name="SQC_DCACHE_BUSY_CYCLES" block=SQ event=289 descr=" Clock cycles while cache is reporting that it is busy. (No-Masking, nondeterministic, unwindowed)"></metric>
+  <metric name="SQC_DCACHE_REQ" block=SQ event=290 descr="Number of requests (post-bank-serialization). (per-SQ, per-Bank)"></metric>
+  <metric name="SQC_DCACHE_HITS" block=SQ event=291 descr="Number of cache hits. (per-SQ, per-Bank, nondeterministic)"></metric>
+  <metric name="SQC_DCACHE_MISSES" block=SQ event=292 descr="Number of cache misses, includes uncached requests. (per-SQ, per-Bank, nondeterministic)"></metric>
+  <metric name="SQC_DCACHE_MISSES_DUPLICATE" block=SQ event=293 descr="Number of misses that were duplicates (access to a non-resident, miss pending CL). (per-SQ, per-Bank, nondeterministic)" ></metric>
+  <metric name="SQC_DCACHE_ATOMIC" block=SQ event=298 descr="Number of atomic requests. (per-SQ, per-Bank)"></metric>
+  <metric name="SQC_DCACHE_REQ_READ_1" block=SQ event=323 descr="Number of constant cache 1 dw read requests. (per-SQ)"></metric>
+  <metric name="SQC_DCACHE_REQ_READ_2" block=SQ event=324 descr="Number of constant cache 2 dw read requests. (per-SQ)"></metric>
+  <metric name="SQC_DCACHE_REQ_READ_4" block=SQ event=325 descr="Number of constant cache 4 dw read requests. (per-SQ)"></metric>
+  <metric name="SQC_DCACHE_REQ_READ_8" block=SQ event=326 descr="Number of constant cache 8 dw read requests. (per-SQ)"></metric>
+  <metric name="SQC_DCACHE_REQ_READ_16" block=SQ event=327 descr="Number of constant cache 16 dw read requests. (per-SQ)"></metric>
+  <metric name="TA_TA_BUSY" block=TA event=13 descr="TA block is busy. Perf_Windowing not supported for this counter."></metric>
+  <metric name="TA_TOTAL_WAVEFRONTS" block=TA event=29 descr="Total number of wavefronts processed by TA."></metric>
+  <metric name="TA_BUFFER_WAVEFRONTS" block=TA event=32 descr="Number of buffer wavefronts processed by TA."></metric>
+  <metric name="TA_BUFFER_READ_WAVEFRONTS" block=TA event=33 descr="Number of buffer read wavefronts processed by TA."></metric>
+  <metric name="TA_BUFFER_WRITE_WAVEFRONTS" block=TA event=34 descr="Number of buffer write wavefronts processed by TA."></metric>
+  <metric name="TA_BUFFER_ATOMIC_WAVEFRONTS" block=TA event=35 descr="Number of buffer atomic wavefronts processed by TA."></metric>
+  <metric name="TA_BUFFER_TOTAL_CYCLES" block=TA event=37 descr="Number of buffer cycles issued to TC."></metric>
+  <metric name="TA_BUFFER_COALESCED_READ_CYCLES" block=TA event=40 descr="Number of buffer coalesced read cycles issued to TC."></metric>
+  <metric name="TA_BUFFER_COALESCED_WRITE_CYCLES" block=TA event=41 descr="Number of buffer coalesced write cycles issued to TC."></metric>
+  <metric name="TA_ADDR_STALLED_BY_TC_CYCLES" block=TA event=42 descr="Number of cycles addr path stalled by TC. Perf_Windowing not supported for this counter."></metric>
+  <metric name="TA_ADDR_STALLED_BY_TD_CYCLES" block=TA event=43 descr="Number of cycles addr path stalled by TD. Perf_Windowing not supported for this counter."></metric>
+  <metric name="TA_DATA_STALLED_BY_TC_CYCLES" block=TA event=44 descr="Number of cycles data path stalled by TC. Perf_Windowing not supported for this counter."></metric>
+  <metric name="TA_FLAT_WAVEFRONTS" block=TA event=51 descr="Number of flat opcode wavfronts processed by the TA."></metric>
+  <metric name="TA_FLAT_READ_WAVEFRONTS" block=TA event=52 descr="Number of flat opcode reads processed by the TA."></metric>
+  <metric name="TA_FLAT_WRITE_WAVEFRONTS" block=TA event=53 descr="Number of flat opcode writes processed by the TA."></metric>
+  <metric name="TA_FLAT_ATOMIC_WAVEFRONTS" block=TA event=54 descr="Number of flat opcode atomics processed by the TA."></metric>
+  <metric name="TD_TD_BUSY" block=TD event=1 descr="TD is processing or waiting for data. Perf_Windowing not supported for this counter."></metric>
+  <metric name="TD_TC_STALL" block=TD event=12 descr="TD is stalled waiting for TC data."></metric>
+  <metric name="TD_SPI_STALL" block=TD event=15 descr="TD is stalled SPI vinit"></metric>
+  <metric name="TD_LOAD_WAVEFRONT" block=TD event=16 descr="Count the wavefronts with opcode = load, include atomics and store."></metric>
+  <metric name="TD_ATOMIC_WAVEFRONT" block=TD event=17 descr="Count the wavefronts with opcode = atomic."></metric>
+  <metric name="TD_STORE_WAVEFRONT" block=TD event=18 descr="Count the wavefronts with opcode = store."></metric>
+  <metric name="TD_COALESCABLE_WAVEFRONT" block=TD event=21 descr="Count wavefronts that TA finds coalescable."></metric>
+  <metric name="TCP_GATE_EN1" block=TCP event=0 descr="TCP interface clocks are turned on. Not Windowed."></metric>
+  <metric name="TCP_GATE_EN2" block=TCP event=1 descr="TCP core clocks are turned on. Not Windowed."></metric>
+  <metric name="TCP_TD_TCP_STALL_CYCLES" block=TCP event=7 descr="TD stalls TCP"></metric>
+  <metric name="TCP_TCR_TCP_STALL_CYCLES" block=TCP event=8 descr="TCR stalls TCP_TCR_req interface"></metric>
+  <metric name="TCP_READ_TAGCONFLICT_STALL_CYCLES" block=TCP event=10 descr="Tagram conflict stall on a read"></metric>
+  <metric name="TCP_WRITE_TAGCONFLICT_STALL_CYCLES" block=TCP event=11 descr="Tagram conflict stall on a write"></metric>
+  <metric name="TCP_ATOMIC_TAGCONFLICT_STALL_CYCLES" block=TCP event=12 descr="Tagram conflict stall on an atomic"></metric>
+  <metric name="TCP_PENDING_STALL_CYCLES" block=TCP event=21 descr="Stall due to data pending from L2"></metric>
+  <metric name="TCP_TA_TCP_STATE_READ" block=TCP event=25 descr="Number of state reads"></metric>
+  <metric name="TCP_VOLATILE" block=TCP event=26 descr="Total number of L1 volatile pixels/buffers from TA"></metric>
+  <metric name="TCP_TOTAL_ACCESSES" block=TCP event=27 descr="Total number of pixels/buffers from TA. Equals TCP_PERF_SEL_TOTAL_READ+TCP_PERF_SEL_TOTAL_NONREAD"></metric>
+  <metric name="TCP_TOTAL_READ" block=TCP event=28 descr="Total number of read pixels/buffers from TA. Equals TCP_PERF_SEL_TOTAL_HIT_LRU_READ + TCP_PERF_SEL_TOTAL_MISS_LRU_READ + TCP_PERF_SEL_TOTAL_MISS_EVICT_READ"></metric>
+  <metric name="TCP_TOTAL_WRITE" block=TCP event=30 descr="Total number of local write pixels/buffers from TA. Equals TCP_PERF_SEL_TOTAL_MISS_LRU_WRITE+ TCP_PERF_SEL_TOTAL_MISS_EVICT_WRITE"></metric>
+  <metric name="TCP_TOTAL_ATOMIC_WITH_RET" block=TCP event=36 descr="Total number of atomic with return pixels/buffers from TA"></metric>
+  <metric name="TCP_TOTAL_ATOMIC_WITHOUT_RET" block=TCP event=37 descr="Total number of atomic without return pixels/buffers from TA"></metric>
+  <metric name="TCP_TOTAL_WRITEBACK_INVALIDATES" block=TCP event=43 descr="Total number of cache invalidates. Equals TCP_PERF_SEL_TOTAL_WBINVL1+ TCP_PERF_SEL_TOTAL_WBINVL1_VOL+ TCP_PERF_SEL_CP_TCP_INVALIDATE+ TCP_PERF_SEL_SQ_TCP_INVALIDATE_VOL. Not Windowed."></metric>
+  <metric name="TCP_UTCL1_REQUEST" block=TCP event=45 descr="Total CLIENT_UTCL1 NORMAL requests"></metric>
+  <metric name="TCP_UTCL1_TRANSLATION_MISS" block=TCP event=47 descr="Total utcl1 translation misses"></metric>
+  <metric name="TCP_UTCL1_TRANSLATION_HIT" block=TCP event=48 descr="Total utcl1 translation hits"></metric>
+  <metric name="TCP_UTCL1_PERMISSION_MISS" block=TCP event=49 descr="Total utcl1 permission misses"></metric>
+  <metric name="TCP_TOTAL_CACHE_ACCESSES" block=TCP event=60 descr="Count of total cache line (tag) accesses (includes hits and misses)."></metric>
+  <metric name="TCP_TCC_READ_REQ" block=TCP event=65 descr="Total read requests from TCP to all TCCs"></metric>
+  <metric name="TCP_TCC_WRITE_REQ" block=TCP event=66 descr="Total write requests from TCP to all TCCs"></metric>
+  <metric name="TCP_TCC_ATOMIC_WITH_RET_REQ" block=TCP event=67 descr="Total atomic with return requests from TCP to all TCCs"></metric>
+  <metric name="TCP_TCC_ATOMIC_WITHOUT_RET_REQ" block=TCP event=68 descr="Total atomic without return requests from TCP to all TCCs"></metric>
+  <metric name="TCP_TCC_NC_READ_REQ" block=TCP event=71 descr="Total read requests with NC mtype from this TCP to all TCCs"></metric>
+  <metric name="TCP_TCC_NC_WRITE_REQ" block=TCP event=72 descr="Total write requests with NC mtype from this TCP to all TCCs"></metric>
+  <metric name="TCP_TCC_NC_ATOMIC_REQ" block=TCP event=73 descr="Total atomic requests with NC mtype from this TCP to all TCCs"></metric>
+  <metric name="TCP_TCC_UC_READ_REQ" block=TCP event=74 descr="Total read requests with UC mtype from this TCP to all TCCs"></metric>
+  <metric name="TCP_TCC_UC_WRITE_REQ" block=TCP event=75 descr="Total write requests with UC mtype from this TCP to all TCCs"></metric>
+  <metric name="TCP_TCC_UC_ATOMIC_REQ" block=TCP event=76 descr="Total atomic requests with UC mtype from this TCP to all TCCs"></metric>
+  <metric name="TCP_TCC_CC_READ_REQ" block=TCP event=77 descr="Total write requests with CC mtype from this TCP to all TCCs"></metric>
+  <metric name="TCP_TCC_CC_WRITE_REQ" block=TCP event=78 descr="Total write requests with CC mtype from this TCP to all TCCs"></metric>
+  <metric name="TCP_TCC_CC_ATOMIC_REQ" block=TCP event=79 descr="Total atomic requests with CC mtype from this TCP to all TCCs"></metric>
+  <metric name="TCP_TCC_RW_READ_REQ" block=TCP event=80 descr="Total write requests with RW mtype from this TCP to all TCCs"></metric>
+  <metric name="TCP_TCC_RW_WRITE_REQ" block=TCP event=81 descr="Total write requests with RW mtype from this TCP to all TCCs"></metric>
+  <metric name="TCP_TCC_RW_ATOMIC_REQ" block=TCP event=82 descr="Total atomic requests with RW mtype from this TCP to all TCCs"></metric>
+  <metric name="TCA_CYCLE" block=TCA event=1 descr="Number of cycles. Not windowable."></metric>
+  <metric name="TCA_BUSY" block=TCA event=2 descr="Number of cycles we have a request pending. Not windowable."></metric>
+  <metric name="TCC_CYCLE" block=TCC event=1 descr="Number of cycles. Not windowable."></metric>
+  <metric name="TCC_BUSY" block=TCC event=2 descr="Number of cycles we have a request pending. Not windowable."></metric>
+  <metric name="TCC_REQ" block=TCC event=3 descr="Number of requests of all types. This is measured at the tag block. This may be more than the number of requests arriving at the TCC, but it is a good indication of the total amount of work that needs to be performed."></metric>
+  <metric name="TCC_STREAMING_REQ" block=TCC event=4 descr="Number of streaming requests. This is measured at the tag block."></metric>
+  <metric name="TCC_NC_REQ" block=TCC event=5 descr="The number of noncoherently cached requests. This is measured at the tag block."></metric>
+  <metric name="TCC_UC_REQ" block=TCC event=6 descr="The number of uncached requests. This is measured at the tag block."></metric>
+  <metric name="TCC_CC_REQ" block=TCC event=7 descr="The number of coherently cached requests. This is measured at the tag block."></metric>
+  <metric name="TCC_RW_REQ" block=TCC event=8 descr="The number of RW requests. This is measured at the tag block."></metric>
+  <metric name="TCC_PROBE" block=TCC event=9 descr="Number of probe requests. Not windowable."></metric>
+  <metric name="TCC_PROBE_ALL" block=TCC event=10 descr="Number of external probe requests with with EA_TCC_preq_all== 1. Not windowable."></metric>
+  <metric name="TCC_INTERNAL_PROBE" block=TCC event=11 descr="Number of self-probes spawned by TCC for CC writes/atomic operations. Not windowable."></metric>
+  <metric name="TCC_READ" block=TCC event=12 descr="Number of read requests. Compressed reads are included in this, but metadata reads are not included."></metric>
+  <metric name="TCC_WRITE" block=TCC event=13 descr="Number of write requests."></metric>
+  <metric name="TCC_ATOMIC" block=TCC event=14 descr="Number of atomic requests of all types."></metric>
+  <metric name="TCC_HIT" block=TCC event=17 descr="Number of cache hits."></metric>
+  <metric name="TCC_MISS" block=TCC event=19 descr="Number of cache misses. UC reads count as misses."></metric>
+  <metric name="TCC_WRITEBACK" block=TCC event=22 descr="Number of lines written back to main memory. This includes writebacks of dirty lines and uncached write/atomic requests."></metric>
+  <metric name="TCC_EA0_WRREQ" block=TCC event=26 descr="Number of transactions (either 32-byte or 64-byte) going over the TC_EA_wrreq interface. Atomics may travel over the same interface and are generally classified as write requests. This does not include probe commands."></metric>
+  <metric name="TCC_EA0_WRREQ_64B" block=TCC event=27 descr="Number of 64-byte transactions going (64-byte write or CMPSWAP) over the TC_EA_wrreq interface."></metric>
+  <metric name="TCC_EA0_WRREQ_PROBE_COMMAND" block=TCC event=28 descr="Number of probe commands going over the TC_EA_wrreq interface."></metric>
+  <metric name="TCC_EA0_WR_UNCACHED_32B" block=TCC event=29 descr="Number of 32-byte write/atomic going over the TC_EA_wrreq interface due to uncached traffic. Note that CC mtypes can produce uncached requests, and those are included in this. A 64-byte request will be counted as 2"></metric>
+  <metric name="TCC_EA0_WRREQ_STALL" block=TCC event=30 descr="Number of cycles a write request was stalled."></metric>
+  <metric name="TCC_EA0_WRREQ_IO_CREDIT_STALL" block=TCC event=31 descr="Number of cycles a EA write request was stalled because the interface was out of IO credits."></metric>
+  <metric name="TCC_EA0_WRREQ_GMI_CREDIT_STALL" block=TCC event=32 descr="Number of cycles a EA write request was stalled because the interface was out of GMI credits."></metric>
+  <metric name="TCC_EA0_WRREQ_DRAM_CREDIT_STALL" block=TCC event=33 descr="Number of cycles a EA write request was stalled because the interface was out of DRAM credits."></metric>
+  <metric name="TCC_TOO_MANY_EA_WRREQS_STALL" block=TCC event=34 descr="Number of cycles the TCC could not send a EA write request because it already reached its maximum number of pending EA write requests."></metric>
+  <metric name="TCC_EA0_WRREQ_LEVEL" block=TCC event=35 descr="The sum of the number of EA write requests in flight. This is primarily meant for measure average EA write latency. Average write latency = TCC_PERF_SEL_EA_WRREQ_LEVEL/TCC_PERF_SEL_EA_WRREQ."></metric>
+  <metric name="TCC_EA0_ATOMIC" block=TCC event=36 descr="Number of transactions going over the TC_EA_wrreq interface that are actually atomic requests."></metric>
+  <metric name="TCC_EA0_ATOMIC_LEVEL" block=TCC event=37 descr="The sum of the number of EA atomics in flight. This is primarily meant for measure average EA atomic latency. Average atomic latency = TCC_PERF_SEL_EA_WRREQ_ATOMIC_LEVEL/TCC_PERF_SEL_EA_WRREQ_ATOMIC."></metric>
+  <metric name="TCC_EA0_RDREQ" block=TCC event=38 descr="Number of TCC/EA read requests (either 32-byte or 64-byte)"></metric>
+  <metric name="TCC_EA0_RDREQ_32B" block=TCC event=39 descr="Number of 32-byte TCC/EA read requests"></metric>
+  <metric name="TCC_EA0_RD_UNCACHED_32B" block=TCC event=40 descr="Number of 32-byte TCC/EA read due to uncached traffic. A 64-byte request will be counted as 2"></metric>
+  <metric name="TCC_EA0_RDREQ_IO_CREDIT_STALL" block=TCC event=41 descr="Number of cycles there was a stall because the read request interface was out of IO credits. Stalls occur regardless of whether a read needed to be performed or not."></metric>
+  <metric name="TCC_EA0_RDREQ_GMI_CREDIT_STALL" block=TCC event=42 descr="Number of cycles there was a stall because the read request interface was out of GMI credits. Stalls occur regardless of whether a read needed to be performed or not."></metric>
+  <metric name="TCC_EA0_RDREQ_DRAM_CREDIT_STALL" block=TCC event=43 descr="Number of cycles there was a stall because the read request interface was out of DRAM credits. Stalls occur regardless of whether a read needed to be performed or not."></metric>
+  <metric name="TCC_EA0_RDREQ_LEVEL" block=TCC event=44 descr="The sum of the number of TCC/EA read requests in flight. This is primarily meant for measure average EA read latency. Average read latency = TCC_PERF_SEL_EA_RDREQ_LEVEL/TCC_PERF_SEL_EA_RDREQ."></metric>
+  <metric name="TCC_TAG_STALL" block=TCC event=45 descr="Number of cycles the normal request pipeline in the tag was stalled for any reason. Normally, stalls of this nature are measured exactly from one point the pipeline, but that is not the case for this counter. Probes can stall the pipeline at a variety of places, and there is no single point that can reasonably measure the total stalls accurately."></metric>
+  <metric name="TCC_NORMAL_WRITEBACK" block=TCC event=68 descr="Number of writebacks due to requests that are not writeback requests."></metric>
+  <metric name="TCC_ALL_TC_OP_WB_WRITEBACK" block=TCC event=73 descr="Number of writebacks due to all TC_OP writeback requests."></metric>
+  <metric name="TCC_NORMAL_EVICT" block=TCC event=74 descr="Number of evictions due to requests that are not invalidate or probe requests."></metric>
+  <metric name="TCC_ALL_TC_OP_INV_EVICT" block=TCC event=80 descr="Number of evictions due to all TC_OP invalidate requests."></metric>
+  <metric name="TCC_PROBE_EVICT" block=TCC event=81 descr="Number of evictions/invalidations due to probes. Not windowable."></metric>
+  <metric name="TCC_EA0_RDREQ_DRAM" block=TCC event=102 descr="Number of TCC/EA read requests (either 32-byte or 64-byte) destined for DRAM (MC)."></metric>
+  <metric name="TCC_EA0_WRREQ_DRAM" block=TCC event=103 descr="Number of TCC/EA write requests (either 32-byte of 64-byte) destined for DRAM (MC)."></metric>
+</gfx940>
+
 <gfx10>
   <metric name="GRBM_COUNT" block=GRBM event=0 descr="Tie High - Count Number of Clocks"></metric>
   <metric name="GRBM_GUI_ACTIVE" block=GRBM event=2 descr="The GUI is Active"></metric>
diff --git a/projects/rocprofiler/test/tool/metrics.xml b/projects/rocprofiler/test/tool/metrics.xml
index f3f7b7eac6..47ce197a95 100755
--- a/projects/rocprofiler/test/tool/metrics.xml
+++ b/projects/rocprofiler/test/tool/metrics.xml
@@ -49,6 +49,9 @@
   <metric name="TCC_EA_WRREQ_64B_sum" expr=sum(TCC_EA_WRREQ_64B,16) descr="Number of 64-byte transactions going (64-byte write or CMPSWAP) over the TC_EA_wrreq interface. Sum over TCC instances."></metric>
   <metric name="TCC_WRREQ_STALL_max" expr=max(TCC_EA_WRREQ_STALL,16) descr="Number of cycles a write request was stalled. Max over TCC instances."></metric>
 
+  <metric name="TCP_TCP_TA_DATA_STALL_CYCLES_sum" expr=sum(TCP_TCP_TA_DATA_STALL_CYCLES,16) descr="Total number of TCP stalls TA data interface."></metric>
+  <metric name="TCP_TCP_TA_DATA_STALL_CYCLES_max" expr=max(TCP_TCP_TA_DATA_STALL_CYCLES,16) descr="Maximum number of TCP stalls TA data interface."></metric>
+
   <metric name="FETCH_SIZE" expr=(TCC_EA_RDREQ_32B_sum*32+(TCC_EA_RDREQ_sum-TCC_EA_RDREQ_32B_sum)*64)/1024 descr="The total kilobytes fetched from the video memory. This is measured with all extra fetches and any cache or memory effects taken into account."></metric>
   <metric name="WRITE_SIZE" expr=((TCC_EA_WRREQ_sum-TCC_EA_WRREQ_64B_sum)*32+TCC_EA_WRREQ_64B_sum*64)/1024 descr="The total kilobytes written to the video memory. This is measured with all extra fetches and any cache or memory effects taken into account."></metric>
   <metric name="WRITE_REQ_32B" expr=TCC_EA_WRREQ_64B_sum*2+(TCC_EA_WRREQ_sum-TCC_EA_WRREQ_64B_sum) descr="The total number of 32-byte effective memory writes."></metric>
@@ -112,7 +115,7 @@
   <metric name="TA_BUFFER_ATOMIC_WAVEFRONTS_sum"                        expr=sum(TA_BUFFER_ATOMIC_WAVEFRONTS,16) descr="Number of buffer atomic wavefronts processed by TA. Sum over TA instances."></metric>
   <metric name="TA_BUFFER_TOTAL_CYCLES_sum"                             expr=sum(TA_BUFFER_TOTAL_CYCLES,16) descr="Number of buffer cycles issued to TC. Sum over TA instances."></metric>
   <metric name="TA_BUFFER_COALESCED_READ_CYCLES_sum"                    expr=sum(TA_BUFFER_COALESCED_READ_CYCLES,16) descr="Number of buffer coalesced read cycles issued to TC. Sum over TA instances."></metric>
-  <metric name="TA_BUFFER_COALESCED_WRITE_CYCLES_sum"                   expr=sum(TA_BUFFER_COALESCED_WRITE_CYCLES,16) descr="Number of buffer coalesced write cycles issued to TC. Sum over TA instances."></metric> 
+  <metric name="TA_BUFFER_COALESCED_WRITE_CYCLES_sum"                   expr=sum(TA_BUFFER_COALESCED_WRITE_CYCLES,16) descr="Number of buffer coalesced write cycles issued to TC. Sum over TA instances."></metric>
   <metric name="TD_TD_BUSY_sum"                                         expr=sum(TD_TD_BUSY,16) descr="TD is processing or waiting for data. Perf_Windowing not supported for this counter. Sum over TD instances."></metric>
   <metric name="TD_TC_STALL_sum"                                        expr=sum(TD_TC_STALL,16) descr="TD is stalled waiting for TC data. Sum over TD instances."></metric>
   <metric name="TD_LOAD_WAVEFRONT_sum"                                  expr=sum(TD_LOAD_WAVEFRONT,16) descr="Count the wavefronts with opcode = load, include atomics and store. Sum over TD instances."></metric>
@@ -207,6 +210,137 @@
   <metric name="TCC_EA_WRREQ_DRAM_sum"                                  expr=sum(TCC_EA_WRREQ_DRAM,32) descr="Number of TCC/EA write requests (either 32-byte of 64-byte) destined for DRAM (MC). Sum over TCC instances."></metric>
 </gfx90a_expr>
 
+<gfx940_expr>
+  <metric name="TCP_TCP_TA_DATA_STALL_CYCLES_sum" expr=sum(TCP_TCP_TA_DATA_STALL_CYCLES,16) descr="Total number of TCP stalls TA data interface."></metric>
+  <metric name="TCP_TCP_TA_DATA_STALL_CYCLES_max" expr=max(TCP_TCP_TA_DATA_STALL_CYCLES,16) descr="Maximum number of TCP stalls TA data interface."></metric>
+
+  <metric name="VFetchInsts" expr=(SQ_INSTS_VMEM_RD-TA_FLAT_READ_WAVEFRONTS_sum)/SQ_WAVES descr="The average number of vector fetch instructions from the video memory executed per work-item (affected by flow control). Excludes FLAT instructions that fetch from video memory."></metric>
+  <metric name="VWriteInsts" expr=(SQ_INSTS_VMEM_WR-TA_FLAT_WRITE_WAVEFRONTS_sum)/SQ_WAVES descr="The average number of vector write instructions to the video memory executed per work-item (affected by flow control). Excludes FLAT instructions that write to video memory."></metric>
+  <metric name="VALUUtilization" expr=100*SQ_THREAD_CYCLES_VALU/(SQ_ACTIVE_INST_VALU*MAX_WAVE_SIZE) descr="The percentage of active vector ALU threads in a wave. A lower number can mean either more thread divergence in a wave or that the work-group size is not a multiple of 64. Value range: 0% (bad), 100% (ideal - no thread divergence)."></metric>
+  <metric name="VALUBusy" expr=100*SQ_ACTIVE_INST_VALU*4/SIMD_NUM/GRBM_GUI_ACTIVE descr="The percentage of GPUTime vector ALU instructions are processed. Value range: 0% (bad) to 100% (optimal)."></metric>
+  <metric name="SALUBusy" expr=100*SQ_INST_CYCLES_SALU*4/SIMD_NUM/GRBM_GUI_ACTIVE descr="The percentage of GPUTime scalar ALU instructions are processed. Value range: 0% (bad) to 100% (optimal)."></metric>
+  <metric name="FetchSize" expr=FETCH_SIZE descr="The total kilobytes fetched from the video memory. This is measured with all extra fetches and any cache or memory effects taken into account."></metric>
+  <metric name="WriteSize" expr=WRITE_SIZE descr="The total kilobytes written to the video memory. This is measured with all extra fetches and any cache or memory effects taken into account."></metric>
+  <metric name="MemWrites32B" expr=WRITE_REQ_32B descr="The total number of effective 32B write transactions to the memory"></metric>
+  <metric name="MemUnitStalled" expr=100*TCP_TCP_TA_DATA_STALL_CYCLES_max/GRBM_GUI_ACTIVE/SE_NUM descr="The percentage of GPUTime the memory unit is stalled. Try reducing the number or size of fetches and writes if possible. Value range: 0% (optimal) to 100% (bad)."></metric>
+  <metric name="TA_BUSY_avr"                                            expr=avr(TA_TA_BUSY,16) descr="TA block is busy. Average over TA instances."></metric>
+  <metric name="TA_BUSY_max"                                            expr=max(TA_TA_BUSY,16) descr="TA block is busy. Max over TA instances."></metric>
+  <metric name="TA_BUSY_min"                                            expr=min(TA_TA_BUSY,16) descr="TA block is busy. Min over TA instances."></metric>
+  <metric name="TA_TA_BUSY_sum"                                         expr=sum(TA_TA_BUSY,16) descr="TA block is busy. Perf_Windowing not supported for this counter. Sum over TA instances."></metric>
+  <metric name="TA_TOTAL_WAVEFRONTS_sum"                                expr=sum(TA_TOTAL_WAVEFRONTS,16) descr="Total number of wavefronts processed by TA. Sum over TA instances."></metric>
+  <metric name="TA_ADDR_STALLED_BY_TC_CYCLES_sum"                       expr=sum(TA_ADDR_STALLED_BY_TC_CYCLES,16) descr="Number of cycles addr path stalled by TC. Perf_Windowing not supported for this counter. Sum over TA instances."></metric>
+  <metric name="TA_ADDR_STALLED_BY_TD_CYCLES_sum"                       expr=sum(TA_ADDR_STALLED_BY_TD_CYCLES,16) descr="Number of cycles addr path stalled by TD. Perf_Windowing not supported for this counter. Sum over TA instances."></metric>
+  <metric name="TA_DATA_STALLED_BY_TC_CYCLES_sum"                       expr=sum(TA_DATA_STALLED_BY_TC_CYCLES,16) descr="Number of cycles data path stalled by TC. Perf_Windowing not supported for this counter. Sum over TA instances."></metric>
+  <metric name="TA_FLAT_WAVEFRONTS_sum"                                 expr=sum(TA_FLAT_WAVEFRONTS,16) descr="Number of flat opcode wavfronts processed by the TA. Sum over TA instances."></metric>
+  <metric name="TA_FLAT_READ_WAVEFRONTS_sum"                            expr=sum(TA_FLAT_READ_WAVEFRONTS,16) descr="Number of flat opcode reads processed by the TA. Sum over TA instances."></metric>
+  <metric name="TA_FLAT_WRITE_WAVEFRONTS_sum"                           expr=sum(TA_FLAT_WRITE_WAVEFRONTS,16) descr="Number of flat opcode writes processed by the TA. Sum over TA instances."></metric>
+  <metric name="TA_FLAT_ATOMIC_WAVEFRONTS_sum"                          expr=sum(TA_FLAT_ATOMIC_WAVEFRONTS,16) descr="Number of flat opcode atomics processed by the TA. Sum over TA instances."></metric>
+  <metric name="TA_BUFFER_WAVEFRONTS_sum"                               expr=sum(TA_BUFFER_WAVEFRONTS,16) descr="Number of buffer wavefronts processed by TA. Sum over TA instances."></metric>
+  <metric name="TA_BUFFER_READ_WAVEFRONTS_sum"                          expr=sum(TA_BUFFER_READ_WAVEFRONTS,16) descr="Number of buffer read wavefronts processed by TA. Sum over TA instances."></metric>
+  <metric name="TA_BUFFER_WRITE_WAVEFRONTS_sum"                         expr=sum(TA_BUFFER_WRITE_WAVEFRONTS,16) descr="Number of buffer write wavefronts processed by TA. Sum over TA instances."></metric>
+  <metric name="TA_BUFFER_ATOMIC_WAVEFRONTS_sum"                        expr=sum(TA_BUFFER_ATOMIC_WAVEFRONTS,16) descr="Number of buffer atomic wavefronts processed by TA. Sum over TA instances."></metric>
+  <metric name="TA_BUFFER_TOTAL_CYCLES_sum"                             expr=sum(TA_BUFFER_TOTAL_CYCLES,16) descr="Number of buffer cycles issued to TC. Sum over TA instances."></metric>
+  <metric name="TA_BUFFER_COALESCED_READ_CYCLES_sum"                    expr=sum(TA_BUFFER_COALESCED_READ_CYCLES,16) descr="Number of buffer coalesced read cycles issued to TC. Sum over TA instances."></metric>
+  <metric name="TA_BUFFER_COALESCED_WRITE_CYCLES_sum"                   expr=sum(TA_BUFFER_COALESCED_WRITE_CYCLES,16) descr="Number of buffer coalesced write cycles issued to TC. Sum over TA instances."></metric> 
+  <metric name="TD_TD_BUSY_sum"                                         expr=sum(TD_TD_BUSY,16) descr="TD is processing or waiting for data. Perf_Windowing not supported for this counter. Sum over TD instances."></metric>
+  <metric name="TD_TC_STALL_sum"                                        expr=sum(TD_TC_STALL,16) descr="TD is stalled waiting for TC data. Sum over TD instances."></metric>
+  <metric name="TD_LOAD_WAVEFRONT_sum"                                  expr=sum(TD_LOAD_WAVEFRONT,16) descr="Count the wavefronts with opcode = load, include atomics and store. Sum over TD instances."></metric>
+  <metric name="TD_ATOMIC_WAVEFRONT_sum"                                expr=sum(TD_ATOMIC_WAVEFRONT,16) descr="Count the wavefronts with opcode = atomic. Sum over TD instances."></metric>
+  <metric name="TD_STORE_WAVEFRONT_sum"                                 expr=sum(TD_STORE_WAVEFRONT,16) descr="Count the wavefronts with opcode = store. Sum over TD instances."></metric>
+  <metric name="TD_COALESCABLE_WAVEFRONT_sum"                           expr=sum(TD_COALESCABLE_WAVEFRONT,16) descr="Count wavefronts that TA finds coalescable. Sum over TD instances."></metric>
+  <metric name="TD_SPI_STALL_sum"                                       expr=sum(TD_SPI_STALL,16) descr="TD is stalled SPI vinit, sum of TCP instances"></metric>
+  <metric name="TCP_GATE_EN1_sum"                                       expr=sum(TCP_GATE_EN1,16) descr="TCP interface clocks are turned on. Not Windowed. Sum over TCP instances."></metric>
+  <metric name="TCP_GATE_EN2_sum"                                       expr=sum(TCP_GATE_EN2,16) descr="TCP core clocks are turned on. Not Windowed. Sum over TCP instances."></metric>
+  <metric name="TCP_TD_TCP_STALL_CYCLES_sum"                            expr=sum(TCP_TD_TCP_STALL_CYCLES,16) descr="TD stalls TCP. Sum over TCP instances."></metric>
+  <metric name="TCP_TCR_TCP_STALL_CYCLES_sum"                           expr=sum(TCP_TCR_TCP_STALL_CYCLES,16) descr="TCR stalls TCP_TCR_req interface. Sum over TCP instances."></metric>
+  <metric name="TCP_READ_TAGCONFLICT_STALL_CYCLES_sum"                  expr=sum(TCP_READ_TAGCONFLICT_STALL_CYCLES,16) descr="Tagram conflict stall on a read. Sum over TCP instances."></metric>
+  <metric name="TCP_WRITE_TAGCONFLICT_STALL_CYCLES_sum"                 expr=sum(TCP_WRITE_TAGCONFLICT_STALL_CYCLES,16) descr="Tagram conflict stall on a write. Sum over TCP instances."></metric>
+  <metric name="TCP_ATOMIC_TAGCONFLICT_STALL_CYCLES_sum"                expr=sum(TCP_ATOMIC_TAGCONFLICT_STALL_CYCLES,16) descr="Tagram conflict stall on an atomic. Sum over TCP instances."></metric>
+  <metric name="TCP_VOLATILE_sum"                                       expr=sum(TCP_VOLATILE,16) descr="Total number of L1 volatile pixels/buffers from TA. Sum over TCP instances."></metric>
+  <metric name="TCP_TOTAL_ACCESSES_sum"                                 expr=sum(TCP_TOTAL_ACCESSES,16) descr="Total number of pixels/buffers from TA. Equals TCP_PERF_SEL_TOTAL_READ+TCP_PERF_SEL_TOTAL_NONREAD. Sum over TCP instances."></metric>
+  <metric name="TCP_TOTAL_READ_sum"                                     expr=sum(TCP_TOTAL_READ,16) descr="Total number of read pixels/buffers from TA. Equals TCP_PERF_SEL_TOTAL_HIT_LRU_READ + TCP_PERF_SEL_TOTAL_MISS_LRU_READ + TCP_PERF_SEL_TOTAL_MISS_EVICT_READ. Sum over TCP instances."></metric>
+  <metric name="TCP_TOTAL_WRITE_sum"                                    expr=sum(TCP_TOTAL_WRITE,16) descr="Total number of local write pixels/buffers from TA. Equals TCP_PERF_SEL_TOTAL_MISS_LRU_WRITE+ TCP_PERF_SEL_TOTAL_MISS_EVICT_WRITE. Sum over TCP instances."></metric>
+  <metric name="TCP_TOTAL_ATOMIC_WITH_RET_sum"                          expr=sum(TCP_TOTAL_ATOMIC_WITH_RET,16) descr="Total number of atomic with return pixels/buffers from TA. Sum over TCP instances."></metric>
+  <metric name="TCP_TOTAL_ATOMIC_WITHOUT_RET_sum"                       expr=sum(TCP_TOTAL_ATOMIC_WITHOUT_RET,16) descr="Total number of atomic without return pixels/buffers from TA Sum over TCP instances."></metric>
+  <metric name="TCP_TOTAL_WRITEBACK_INVALIDATES_sum"                    expr=sum(TCP_TOTAL_WRITEBACK_INVALIDATES,16) descr="Total number of cache invalidates. Equals TCP_PERF_SEL_TOTAL_WBINVL1+ TCP_PERF_SEL_TOTAL_WBINVL1_VOL+ TCP_PERF_SEL_CP_TCP_INVALIDATE+ TCP_PERF_SEL_SQ_TCP_INVALIDATE_VOL. Not Windowed. Sum over TCP instances."></metric>
+  <metric name="TCP_UTCL1_REQUEST_sum"                                  expr=sum(TCP_UTCL1_REQUEST,16) descr="Total CLIENT_UTCL1 NORMAL requests Sum over TCP instances."></metric>
+  <metric name="TCP_UTCL1_TRANSLATION_MISS_sum"                         expr=sum(TCP_UTCL1_TRANSLATION_MISS,16) descr="Total utcl1 translation misses Sum over TCP instances."></metric>
+  <metric name="TCP_UTCL1_TRANSLATION_HIT_sum"                          expr=sum(TCP_UTCL1_TRANSLATION_HIT,16) descr="Total utcl1 translation hits Sum over TCP instances."></metric>
+  <metric name="TCP_UTCL1_PERMISSION_MISS_sum"                          expr=sum(TCP_UTCL1_PERMISSION_MISS,16) descr="Total utcl1 permission misses Sum over TCP instances."></metric>
+  <metric name="TCP_TOTAL_CACHE_ACCESSES_sum"                           expr=sum(TCP_TOTAL_CACHE_ACCESSES,16) descr="Count of total cache line (tag) accesses (includes hits and misses). Sum over TCP instances."></metric>
+  <metric name="TCP_TA_TCP_STATE_READ_sum"                              expr=sum(TCP_TA_TCP_STATE_READ,16) descr="Number of state reads Sum over TCP instances."></metric>
+  <metric name="TCP_TCC_READ_REQ_sum"                                   expr=sum(TCP_TCC_READ_REQ,16) descr="Total read requests from TCP to all TCCs Sum over TCP instances."></metric>
+  <metric name="TCP_TCC_WRITE_REQ_sum"                                  expr=sum(TCP_TCC_WRITE_REQ,16) descr="Total write requests from TCP to all TCCs Sum over TCP instances."></metric>
+  <metric name="TCP_TCC_ATOMIC_WITH_RET_REQ_sum"                        expr=sum(TCP_TCC_ATOMIC_WITH_RET_REQ,16) descr="Total atomic with return requests from TCP to all TCCs Sum over TCP instances."></metric>
+  <metric name="TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum"                     expr=sum(TCP_TCC_ATOMIC_WITHOUT_RET_REQ,16) descr="Total atomic without return requests from TCP to all TCCs Sum over TCP instances."></metric>
+  <metric name="TCP_TCC_NC_READ_REQ_sum"                                expr=sum(TCP_TCC_NC_READ_REQ,16) descr="Total read requests with NC mtype from this TCP to all TCCs Sum over TCP instances."></metric>
+  <metric name="TCP_TCC_NC_WRITE_REQ_sum"                               expr=sum(TCP_TCC_NC_WRITE_REQ,16) descr="Total write requests with NC mtype from this TCP to all TCCs Sum over TCP instances."></metric>
+  <metric name="TCP_TCC_NC_ATOMIC_REQ_sum"                              expr=sum(TCP_TCC_NC_ATOMIC_REQ,16) descr="Total atomic requests with NC mtype from this TCP to all TCCs Sum over TCP instances."></metric>
+  <metric name="TCP_TCC_UC_READ_REQ_sum"                                expr=sum(TCP_TCC_UC_READ_REQ,16) descr="Total read requests with UC mtype from this TCP to all TCCs Sum over TCP instances."></metric>
+  <metric name="TCP_TCC_UC_WRITE_REQ_sum"                               expr=sum(TCP_TCC_UC_WRITE_REQ,16) descr="Total write requests with UC mtype from this TCP to all TCCs Sum over TCP instances."></metric>
+  <metric name="TCP_TCC_UC_ATOMIC_REQ_sum"                              expr=sum(TCP_TCC_UC_ATOMIC_REQ,16) descr="Total atomic requests with UC mtype from this TCP to all TCCs Sum over TCP instances."></metric>
+  <metric name="TCP_TCC_CC_READ_REQ_sum"                                expr=sum(TCP_TCC_CC_READ_REQ,16) descr="Total write requests with CC mtype from this TCP to all TCCs Sum over TCP instances."></metric>
+  <metric name="TCP_TCC_CC_WRITE_REQ_sum"                               expr=sum(TCP_TCC_CC_WRITE_REQ,16) descr="Total write requests with CC mtype from this TCP to all TCCs Sum over TCP instances."></metric>
+  <metric name="TCP_TCC_CC_ATOMIC_REQ_sum"                              expr=sum(TCP_TCC_CC_ATOMIC_REQ,16) descr="Total atomic requests with CC mtype from this TCP to all TCCs Sum over TCP instances."></metric>
+  <metric name="TCP_TCC_RW_READ_REQ_sum"                                expr=sum(TCP_TCC_RW_READ_REQ,16) descr="Total write requests with RW mtype from this TCP to all TCCs. Sum over TCP instances."></metric>
+  <metric name="TCP_TCC_RW_WRITE_REQ_sum"                               expr=sum(TCP_TCC_RW_WRITE_REQ,16) descr="Total write requests with RW mtype from this TCP to all TCCs. Sum over TCP instances."></metric>
+  <metric name="TCP_TCC_RW_ATOMIC_REQ_sum"                              expr=sum(TCP_TCC_RW_ATOMIC_REQ,16) descr="Total atomic requests with RW mtype from this TCP to all TCCs. Sum over TCP instances."></metric>
+  <metric name="TCP_PENDING_STALL_CYCLES_sum"                           expr=sum(TCP_PENDING_STALL_CYCLES,16) descr="Stall due to data pending from L2. Sum over TCP instances."></metric>
+  <metric name="TCA_CYCLE_sum"                                          expr=sum(TCA_CYCLE,16)  descr="Number of cycles. Sum over all TCA instances "></metric>
+  <metric name="TCA_BUSY_sum"                                           expr=sum(TCA_BUSY,16)   descr="Number of cycles we have a request pending. Sum over all TCA instances."></metric>
+  <metric name="TCC_BUSY_avr"                                           expr=avr(TCC_BUSY,32) descr="TCC_BUSY avr over all memory channels."></metric>
+  <metric name="TCC_WRREQ_STALL_max"                                    expr=max(TCC_EA0_WRREQ_STALL,32) descr="Number of cycles a write request was stalled. Max over TCC instances."></metric>
+  <metric name="TCC_CYCLE_sum"                                          expr=sum(TCC_CYCLE,32) descr="Number of cycles. Not windowable. Sum over TCC instances."></metric>
+  <metric name="TCC_BUSY_sum"                                           expr=sum(TCC_BUSY,32) descr="Number of cycles we have a request pending. Not windowable. Sum over TCC instances."></metric>
+  <metric name="TCC_REQ_sum"                                            expr=sum(TCC_REQ,32) descr="Number of requests of all types. This is measured at the tag block. This may be more than the number of requests arriving at the TCC, but it is a good indication of the total amount of work that needs to be performed. Sum over TCC instances."></metric>
+  <metric name="TCC_STREAMING_REQ_sum"                                  expr=sum(TCC_STREAMING_REQ,32) descr="Number of streaming requests. This is measured at the tag block. Sum over TCC instances."></metric>
+  <metric name="TCC_NC_REQ_sum"                                         expr=sum(TCC_NC_REQ,32) descr="The number of noncoherently cached requests. This is measured at the tag block. Sum over TCC instances."></metric>
+  <metric name="TCC_UC_REQ_sum"                                         expr=sum(TCC_UC_REQ,32) descr="The number of uncached requests. This is measured at the tag block. Sum over TCC instances."></metric>
+  <metric name="TCC_CC_REQ_sum"                                         expr=sum(TCC_CC_REQ,32) descr="The number of coherently cached requests. This is measured at the tag block. Sum over TCC instances."></metric>
+  <metric name="TCC_RW_REQ_sum"                                         expr=sum(TCC_RW_REQ,32) descr="The number of RW requests. This is measured at the tag block. Sum over TCC instances."></metric>
+  <metric name="TCC_PROBE_sum"                                          expr=sum(TCC_PROBE,32) descr="Number of probe requests. Not windowable. Sum over TCC instances."></metric>
+  <metric name="TCC_PROBE_ALL_sum"                                      expr=sum(TCC_PROBE_ALL,32) descr="Number of external probe requests with with EA_TCC_preq_all== 1. Not windowable. Sum over TCC instances."></metric>
+  <metric name="TCC_READ_sum"                                           expr=sum(TCC_READ,32) descr="Number of read requests. Compressed reads are included in this, but metadata reads are not included. Sum over TCC instances."></metric>
+  <metric name="TCC_WRITE_sum"                                          expr=sum(TCC_WRITE,32) descr="Number of write requests. Sum over TCC instances."></metric>
+  <metric name="TCC_ATOMIC_sum"                                         expr=sum(TCC_ATOMIC,32) descr="Number of atomic requests of all types. Sum over TCC instances."></metric>
+  <metric name="TCC_HIT_sum"                                            expr=sum(TCC_HIT,32) descr="Number of cache hits. Sum over TCC instances."></metric>
+  <metric name="TCC_MISS_sum"                                           expr=sum(TCC_MISS,32) descr="Number of cache misses. UC reads count as misses. Sum over TCC instances."></metric>
+  <metric name="TCC_WRITEBACK_sum"                                      expr=sum(TCC_WRITEBACK,32) descr="Number of lines written back to main memory. This includes writebacks of dirty lines and uncached write/atomic requests. Sum over TCC instances."></metric>
+  <metric name="TCC_EA0_WRREQ_sum"                                       expr=sum(TCC_EA0_WRREQ,32) descr="Number of transactions (either 32-byte or 64-byte) going over the TC_EA_wrreq interface. Atomics may travel over the same interface and are generally classified as write requests. This does not include probe commands. Sum over TCC instances."></metric>
+  <metric name="TCC_EA0_WRREQ_64B_sum"                                   expr=sum(TCC_EA0_WRREQ_64B,32) descr="Number of 64-byte transactions going (64-byte write or CMPSWAP) over the TC_EA_wrreq interface. Sum over TCC instances."></metric>
+  <metric name="TCC_EA0_WR_UNCACHED_32B_sum"                             expr=sum(TCC_EA0_WR_UNCACHED_32B,32) descr="Number of 32-byte write/atomic going over the TC_EA_wrreq interface due to uncached traffic. Note that CC mtypes can produce uncached requests, and those are included in this. A 64-byte request will be counted as 2. Sum over TCC instances."></metric>
+  <metric name="TCC_EA0_WRREQ_STALL_sum"                                 expr=sum(TCC_EA0_WRREQ_STALL,32) descr="Number of cycles a write request was stalled. Sum over TCC instances."></metric>
+  <metric name="TCC_EA0_WRREQ_IO_CREDIT_STALL_sum"                       expr=sum(TCC_EA0_WRREQ_IO_CREDIT_STALL,32) descr="Number of cycles a EA write request was stalled because the interface was out of IO credits. Sum over TCC instances."></metric>
+  <metric name="TCC_EA0_WRREQ_GMI_CREDIT_STALL_sum"                      expr=sum(TCC_EA0_WRREQ_GMI_CREDIT_STALL,32) descr="Number of cycles a EA write request was stalled because the interface was out of GMI credits. Sum over TCC instances."></metric>
+  <metric name="TCC_EA0_WRREQ_DRAM_CREDIT_STALL_sum"                     expr=sum(TCC_EA0_WRREQ_DRAM_CREDIT_STALL,32) descr="Number of cycles a EA write request was stalled because the interface was out of DRAM credits. Sum over TCC instances."></metric>
+  <metric name="TCC_TOO_MANY_EA_WRREQS_STALL_sum"                       expr=sum(TCC_TOO_MANY_EA_WRREQS_STALL,32) descr="Number of cycles the TCC could not send a EA write request because it already reached its maximum number of pending EA write requests. Sum over TCC instances."></metric>
+  <metric name="TCC_EA0_WRREQ_LEVEL_sum"                                 expr=sum(TCC_EA0_WRREQ_LEVEL,32) descr="The sum of the number of EA write requests in flight. This is primarily meant for measure average EA write latency. Average write latency = TCC_PERF_SEL_EA_WRREQ_LEVEL/TCC_PERF_SEL_EA_WRREQ. Sum over TCC instances."></metric>
+  <metric name="TCC_EA0_RDREQ_LEVEL_sum"                                 expr=sum(TCC_EA0_RDREQ_LEVEL,32) descr="The sum of the number of TCC/EA read requests in flight. This is primarily meant for measure average EA read latency. Average read latency = TCC_PERF_SEL_EA_RDREQ_LEVEL/TCC_PERF_SEL_EA_RDREQ. Sum over TCC instances."></metric>
+  <metric name="TCC_EA0_ATOMIC_sum"                                      expr=sum(TCC_EA0_ATOMIC,32) descr="Number of transactions going over the TC_EA_wrreq interface that are actually atomic requests. Sum over TCC instances."></metric>
+  <metric name="TCC_EA0_ATOMIC_LEVEL_sum"                                expr=sum(TCC_EA0_ATOMIC_LEVEL,32) descr="The sum of the number of EA atomics in flight. This is primarily meant for measure average EA atomic latency. Average atomic latency = TCC_PERF_SEL_EA_WRREQ_ATOMIC_LEVEL/TCC_PERF_SEL_EA_WRREQ_ATOMIC. Sum over TCC instances."></metric>
+  <metric name="TCC_EA0_RDREQ_sum"                                       expr=sum(TCC_EA0_RDREQ,32) descr="Number of TCC/EA read requests (either 32-byte or 64-byte) Sum over TCC instances."></metric>
+  <metric name="TCC_EA0_RDREQ_32B_sum"                                   expr=sum(TCC_EA0_RDREQ_32B,32) descr="Number of 32-byte TCC/EA read requests Sum over TCC instances."></metric>
+  <metric name="TCC_EA0_RD_UNCACHED_32B_sum"                             expr=sum(TCC_EA0_RD_UNCACHED_32B,32) descr="Number of 32-byte TCC/EA read due to uncached traffic. A 64-byte request will be counted as 2 Sum over TCC instances."></metric>
+  <metric name="TCC_EA0_RDREQ_IO_CREDIT_STALL_sum"                       expr=sum(TCC_EA0_RDREQ_IO_CREDIT_STALL,32) descr="Number of cycles there was a stall because the read request interface was out of IO credits. Stalls occur regardless of whether a read needed to be performed or not. Sum over TCC instances."></metric>
+  <metric name="TCC_EA0_RDREQ_GMI_CREDIT_STALL_sum"                      expr=sum(TCC_EA0_RDREQ_GMI_CREDIT_STALL,32) descr="Number of cycles there was a stall because the read request interface was out of GMI credits. Stalls occur regardless of whether a read needed to be performed or not. Sum over TCC instances."></metric>
+  <metric name="TCC_EA0_RDREQ_DRAM_CREDIT_STALL_sum"                     expr=sum(TCC_EA0_RDREQ_DRAM_CREDIT_STALL,32) descr="Number of cycles there was a stall because the read request interface was out of DRAM credits. Stalls occur regardless of whether a read needed to be performed or not. Sum over TCC instances."></metric>
+  <metric name="TCC_TAG_STALL_sum"                                      expr=sum(TCC_TAG_STALL,32) descr="."></metric>
+  <metric name="TCC_NORMAL_WRITEBACK_sum"                               expr=sum(TCC_NORMAL_WRITEBACK,32) descr="Number of writebacks due to requests that are not writeback requests. Sum over TCC instances."></metric>
+  <metric name="TCC_ALL_TC_OP_WB_WRITEBACK_sum"                         expr=sum(TCC_ALL_TC_OP_WB_WRITEBACK,32) descr="Number of writebacks due to all TC_OP writeback requests. Sum over TCC instances."></metric>
+  <metric name="TCC_NORMAL_EVICT_sum"                                   expr=sum(TCC_NORMAL_EVICT,32) descr="Number of evictions due to requests that are not invalidate or probe requests. Sum over TCC instances."></metric>
+  <metric name="TCC_ALL_TC_OP_INV_EVICT_sum"                            expr=sum(TCC_ALL_TC_OP_INV_EVICT,32) descr="Number of evictions due to all TC_OP invalidate requests. Sum over TCC instances."></metric>
+  <metric name="TCC_EA0_RDREQ_DRAM_sum"                                  expr=sum(TCC_EA0_RDREQ_DRAM,32) descr="Number of TCC/EA read requests (either 32-byte or 64-byte) destined for DRAM (MC). Sum over TCC instances."></metric>
+  <metric name="TCC_EA0_WRREQ_DRAM_sum"                                  expr=sum(TCC_EA0_WRREQ_DRAM,32) descr="Number of TCC/EA write requests (either 32-byte of 64-byte) destined for DRAM (MC). Sum over TCC instances."></metric>
+  <metric name="FETCH_SIZE"                                             expr=(TCC_EA0_RDREQ_32B_sum*32+(TCC_EA0_RDREQ_sum-TCC_EA0_RDREQ_32B_sum)*64)/1024 descr="The total kilobytes fetched from the video memory. This is measured with all extra fetches and any cache or memory effects taken into account."></metric>
+  <metric name="WRITE_SIZE"                                             expr=((TCC_EA0_WRREQ_sum-TCC_EA0_WRREQ_64B_sum)*32+TCC_EA0_WRREQ_64B_sum*64)/1024 descr="The total kilobytes written to the video memory. This is measured with all extra fetches and any cache or memory effects taken into account."></metric>
+  <metric name="WRITE_REQ_32B"                                          expr=TCC_EA0_WRREQ_64B_sum*2+(TCC_EA0_WRREQ_sum-TCC_EA0_WRREQ_64B_sum) descr="The total number of 32-byte effective memory writes."></metric>
+  <metric name="CU_OCCUPANCY"                                           expr=(SQ_CYCLES/(SQ_WAVE_CYCLES*4))/MAX_WAVE_SIZE descr="The ratio of active waves on a CU to the maximum number of active waves supported by the CU"></metric>
+  <metric name="CU_UTILIZATION"                                         expr=GRBM_GUI_ACTIVE/GRBM_COUNT descr="The total number of active cycles divided by total number of elapsed cycles"></metric>
+  <metric name="TOTAL_16_OPS"                                           expr=(SQ_INSTS_VALU_FMA_F16*2+SQ_INSTS_VALU_ADD_F16+SQ_INSTS_VALU_MUL_F16+SQ_INSTS_VALU_TRANS_F16)*64+((SQ_INSTS_VALU_MFMA_MOPS_F16+SQ_INSTS_VALU_MFMA_MOPS_BF16)*512) descr="The number of 16 bits OPS executed"></metric>
+  <metric name="TOTAL_32_OPS"                                           expr=(SQ_INSTS_VALU_FMA_F32*2+SQ_INSTS_VALU_INT32+SQ_INSTS_VALU_ADD_F32+SQ_INSTS_VALU_MUL_F32+SQ_INSTS_VALU_TRANS_F32)*64+(SQ_INSTS_VALU_MFMA_MOPS_F32*512) descr="The number of 32 bits OPS executed"></metric>
+  <metric name="TOTAL_64_OPS"                                           expr=(SQ_INSTS_VALU_FMA_F64*2+SQ_INSTS_VALU_INT64+SQ_INSTS_VALU_ADD_F64+SQ_INSTS_VALU_MUL_F64)*64+(SQ_INSTS_VALU_MFMA_MOPS_F64*512) descr="The number of 64 bits OPS executed"></metric>
+</gfx940_expr>
+
 <gfx10_expr>
   <metric name="GPU_UTIL" expr=100*GRBM_GUI_ACTIVE/GRBM_COUNT descr="Percentage of the time that GUI is active"></metric>
   <metric name="CP_UTIL" expr=100*GRBM_CP_BUSY/GRBM_GUI_ACTIVE descr="Percentage of the GRBM_GUI_ACTIVE time that any of the Command Processor (CPG/CPC/CPF) blocks are busy"></metric>
@@ -290,6 +424,8 @@
 <gfx908 base="gfx908_expr"></gfx908>
 # Aldebaran
 <gfx90a base="gfx90a_expr"></gfx90a>
+#Mi300
+<gfx940 base="gfx940_expr"></gfx940>
 #Navi21
 <gfx1030 base="gfx1030_expr"></gfx1030>