diff --git a/projects/rocprofiler/src/core/rocprofiler.cpp b/projects/rocprofiler/src/core/rocprofiler.cpp
index 69bfbae644..e8901387f4 100644
--- a/projects/rocprofiler/src/core/rocprofiler.cpp
+++ b/projects/rocprofiler/src/core/rocprofiler.cpp
@@ -210,10 +210,6 @@ hsa_status_t GetExcStatus(const std::exception& e) {
 }
 
 rocprofiler_properties_t rocprofiler_properties;
-#if DEFERRED_HANDLERS
-Context::deferred_handler_list_t* Context::deferred_handler_list_ = NULL;
-Context::recur_mutex_t Context::mutex_static_;
-#endif
 uint32_t SqttProfile::output_buffer_size_ = 0x2000000;  // 32M
 bool SqttProfile::output_buffer_local_ = true;
 util::Logger::mutex_t util::Logger::mutex_;
diff --git a/projects/rocprofiler/test/tool/gfx_metrics.xml b/projects/rocprofiler/test/tool/gfx_metrics.xml
index 54dc50337c..9e4f24fc84 100644
--- a/projects/rocprofiler/test/tool/gfx_metrics.xml
+++ b/projects/rocprofiler/test/tool/gfx_metrics.xml
@@ -1,69 +1,69 @@
 <gfx8>
-  <metric name=GRBM_COUNT block=GRBM event=0 ></metric>
-  <metric name=GRBM_GUI_ACTIVE block=GRBM event=2 ></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=SQ_WAVES block=SQ event=4 ></metric>
-  <metric name=SQ_INSTS_VALU block=SQ event=26 ></metric>
-  <metric name=SQ_INSTS_VMEM_WR block=SQ event=27 ></metric>
-  <metric name=SQ_INSTS_VMEM_RD block=SQ event=28 ></metric>
-  <metric name=SQ_INSTS_SALU block=SQ event=30 ></metric>
-  <metric name=SQ_INSTS_SMEM block=SQ event=31 ></metric>
-  <metric name=SQ_INSTS_FLAT block=SQ event=32 ></metric>
-  <metric name=SQ_INSTS_FLAT_LDS_ONLY block=SQ event=33 ></metric>
-  <metric name=SQ_INSTS_LDS block=SQ event=34 ></metric>
-  <metric name=SQ_INSTS_GDS block=SQ event=35 ></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_INSTS_VALU" block=SQ event=26 descr="Number of VALU instructions issued. (per-simd, emulated)"></metric>
+  <metric name="SQ_INSTS_VMEM_WR" block=SQ event=27 descr="Number of VMEM write instructions issued (including FLAT). (per-simd, emulated)"></metric>
+  <metric name="SQ_INSTS_VMEM_RD" block=SQ event=28 descr="Number of VMEM read instructions issued (including FLAT). (per-simd, emulated)"></metric>
+  <metric name="SQ_INSTS_SALU" block=SQ event=30 descr="Number of SALU instructions issued. (per-simd, emulated)"></metric>
+  <metric name="SQ_INSTS_SMEM" block=SQ event=31 descr="Number of SMEM instructions issued. (per-simd, emulated)"></metric>
+  <metric name="SQ_INSTS_FLAT" block=SQ event=32 descr="Number of FLAT instructions issued. (per-simd, emulated)"></metric>
+  <metric name="SQ_INSTS_FLAT_LDS_ONLY" block=SQ event=33 descr="Number of FLAT instructions issued that read/wrote only from/to LDS (only works if EARLY_TA_DONE is enabled). (per-simd, emulated)"></metric>
+  <metric name="SQ_INSTS_LDS" block=SQ event=34 descr="Number of LDS instructions issued (including FLAT). (per-simd, emulated)"></metric>
+  <metric name="SQ_INSTS_GDS" block=SQ event=35 descr="Number of GDS instructions issued. (per-simd, emulated)"></metric>
 
-  <metric name=SQ_WAIT_INST_LDS block=SQ event=61 descr="Number of wave-cycles spent waiting for LDS instruction issue. In units of 4 cycles."></metric>
-  <metric name=SQ_ACTIVE_INST_VALU block=SQ event=69 descr="Number of cycles the SQ instruction arbiter is working on a VALU instruction."></metric>
-  <metric name=SQ_INST_CYCLES_SALU block=SQ event=86 descr="Number of cycles needed to execute non-memory read scalar operations."></metric>
-  <metric name=SQ_THREAD_CYCLES_VALU block=SQ event=89 descr="Number of thread-cycles used to execute VALU operations (similar to INST_CYCLES_VALU but multiplied by # of active threads)."></metric>
-  <metric name=SQ_LDS_BANK_CONFLICT block=SQ event=97 descr="Number of cycles LDS is stalled by bank conflicts."></metric>
+  <metric name="SQ_WAIT_INST_LDS" block=SQ event=61 descr="Number of wave-cycles spent waiting for LDS instruction issue. In units of 4 cycles. (per-simd, nondeterministic)"></metric>
+  <metric name="SQ_ACTIVE_INST_VALU" block=SQ event=69 descr="Number of cycles the SQ instruction arbiter is working on a VALU instruction. (per-simd, nondeterministic)"></metric>
+  <metric name="SQ_INST_CYCLES_SALU" block=SQ event=86 descr="Number of cycles needed to execute non-memory read scalar operations. (per-simd, emulated)"></metric>
+  <metric name="SQ_THREAD_CYCLES_VALU" block=SQ event=89 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_LDS_BANK_CONFLICT" block=SQ event=97 descr="Number of cycles LDS is stalled by bank conflicts. (emulated)"></metric>
 
-  <metric name=TA_TA_BUSY block=TA event=15 ></metric>
-  <metric name=TA_FLAT_READ_WAVEFRONTS block=TA event=101 ></metric>
-  <metric name=TA_FLAT_WRITE_WAVEFRONTS block=TA event=102 ></metric>
+  <metric name="TA_TA_BUSY" block=TA event=15 descr="TA block is busy. Perf_Windowing not supported for this counter."></metric>
+  <metric name="TA_FLAT_READ_WAVEFRONTS" block=TA event=101 descr="Number of flat opcode reads processed by the TA."></metric>
+  <metric name="TA_FLAT_WRITE_WAVEFRONTS" block=TA event=102 descr="Number of flat opcode writes processed by the TA."></metric>
 
-  <metric name=TCC_HIT block=TCC event=18 ></metric>
-  <metric name=TCC_MISS block=TCC event=19 ></metric>
-  <metric name="TCC_MC_RDREQ" block=TCC event=35 ></metric>
-  <metric name="TCC_MC_WRREQ" block=TCC event=26 ></metric>
-  <metric name="TCC_MC_WRREQ_STALL" block=TCC event=28 ></metric>
+  <metric name="TCC_HIT" block=TCC event=18 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_MC_RDREQ" block=TCC event=35 descr="Number of 32-byte reads. The hardware actually does 64-byte reads but the number is adjusted to provide uniformity."></metric>
+  <metric name="TCC_MC_WRREQ" block=TCC event=26 descr="Number of 32-byte transactions going over the TC_MC_wrreq interface. Atomics may travel over the same interface and are generally classified as write requests."></metric>
+  <metric name="TCC_MC_WRREQ_STALL" block=TCC event=28 descr="Number of cycles a write request was stalled."></metric>
 
   <metric name="TCP_TA_DATA_STALL_CYCLES" block=TCP event=3 descr="TCP stalls TA data interface. Now Windowed."></metric>
 </gfx8>
 
 <gfx9>
-  <metric name=GRBM_COUNT block=GRBM event=0 ></metric>
-  <metric name=GRBM_GUI_ACTIVE block=GRBM event=2 ></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=SQ_WAVES block=SQ event=4 ></metric>
-  <metric name=SQ_INSTS_VALU block=SQ event=26 ></metric>
-  <metric name=SQ_INSTS_VMEM_WR block=SQ event=27 ></metric>
-  <metric name=SQ_INSTS_VMEM_RD block=SQ event=28 ></metric>
-  <metric name=SQ_INSTS_SALU block=SQ event=30 ></metric>
-  <metric name=SQ_INSTS_SMEM block=SQ event=31 ></metric>
-  <metric name=SQ_INSTS_FLAT block=SQ event=32 ></metric>
-  <metric name=SQ_INSTS_FLAT_LDS_ONLY block=SQ event=33 ></metric>
-  <metric name=SQ_INSTS_LDS block=SQ event=34 ></metric>
-  <metric name=SQ_INSTS_GDS block=SQ event=35 ></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_INSTS_VALU" block=SQ event=26 descr="Number of VALU instructions issued. (per-simd, emulated)"></metric>
+  <metric name="SQ_INSTS_VMEM_WR" block=SQ event=27 descr="Number of VMEM write instructions issued (including FLAT). (per-simd, emulated)"></metric>
+  <metric name="SQ_INSTS_VMEM_RD" block=SQ event=28 descr="Number of VMEM read instructions issued (including FLAT). (per-simd, emulated)"></metric>
+  <metric name="SQ_INSTS_SALU" block=SQ event=30 descr="Number of SALU instructions issued. (per-simd, emulated)"></metric>
+  <metric name="SQ_INSTS_SMEM" block=SQ event=31 descr="Number of SMEM instructions issued. (per-simd, emulated)"></metric>
+  <metric name="SQ_INSTS_FLAT" block=SQ event=32 descr="Number of FLAT instructions issued. (per-simd, emulated)"></metric>
+  <metric name="SQ_INSTS_FLAT_LDS_ONLY" block=SQ event=33 descr="Number of FLAT instructions issued that read/wrote only from/to LDS (only works if EARLY_TA_DONE is enabled). (per-simd, emulated)"></metric>
+  <metric name="SQ_INSTS_LDS" block=SQ event=34 descr="Number of LDS instructions issued (including FLAT). (per-simd, emulated)"></metric>
+  <metric name="SQ_INSTS_GDS" block=SQ event=35 descr="Number of GDS instructions issued. (per-simd, emulated)"></metric>
 
-  <metric name=SQ_WAIT_INST_LDS block=SQ event=63 descr="Number of wave-cycles spent waiting for LDS instruction issue. In units of 4 cycles."></metric>
-  <metric name=SQ_ACTIVE_INST_VALU block=SQ event=71 descr="regspec 71? Number of cycles the SQ instruction arbiter is working on a VALU instruction."></metric>
-  <metric name=SQ_INST_CYCLES_SALU block=SQ event=84 descr="Number of cycles needed to execute non-memory read scalar operations."></metric>
-  <metric name=SQ_THREAD_CYCLES_VALU block=SQ event=85 descr="Number of thread-cycles used to execute VALU operations (similar to INST_CYCLES_VALU but multiplied by # of active threads)."></metric>
-  <metric name=SQ_LDS_BANK_CONFLICT block=SQ event=93 descr="Number of cycles LDS is stalled by bank conflicts."></metric>
+  <metric name="SQ_WAIT_INST_LDS" block=SQ event=63 descr="Number of wave-cycles spent waiting for LDS instruction issue. In units of 4 cycles. (per-simd, nondeterministic)"></metric>
+  <metric name="SQ_ACTIVE_INST_VALU" block=SQ event=71 descr="regspec 71? Number of cycles the SQ instruction arbiter is working on a VALU instruction. (per-simd, nondeterministic)"></metric>
+  <metric name="SQ_INST_CYCLES_SALU" block=SQ event=84 descr="Number of cycles needed to execute non-memory read scalar operations. (per-simd, emulated)"></metric>
+  <metric name="SQ_THREAD_CYCLES_VALU" block=SQ event=85 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_LDS_BANK_CONFLICT" block=SQ event=93 descr="Number of cycles LDS is stalled by bank conflicts. (emulated)"></metric>
 
-  <metric name=TA_TA_BUSY block=TA event=15 ></metric>
-  <metric name=TA_FLAT_READ_WAVEFRONTS block=TA event=101 ></metric>
-  <metric name=TA_FLAT_WRITE_WAVEFRONTS block=TA event=102 ></metric>
+  <metric name="TA_TA_BUSY" block=TA event=15 descr="TA block is busy. Perf_Windowing not supported for this counter."></metric>
+  <metric name="TA_FLAT_READ_WAVEFRONTS" block=TA event=101 descr="Number of flat opcode reads processed by the TA."></metric>
+  <metric name="TA_FLAT_WRITE_WAVEFRONTS" block=TA event=102 descr="Number of flat opcode writes processed by the TA."></metric>
 
-  <metric name=TCC_HIT block=TCC event=20 ></metric>
-  <metric name=TCC_MISS block=TCC event=22 ></metric>
-  <metric name=TCC_EA_WRREQ block=TCC event=29 ></metric>
-  <metric name=TCC_EA_WRREQ_64B block=TCC event=30 ></metric>
-  <metric name=TCC_EA_WRREQ_STALL block=TCC event=33 ></metric>
-  <metric name=TCC_EA_RDREQ block=TCC event=41 ></metric>
-  <metric name=TCC_EA_RDREQ_32B block=TCC event=42 ></metric>
+  <metric name="TCC_HIT" block=TCC event=20 descr="Number of cache hits."></metric>
+  <metric name="TCC_MISS" block=TCC event=22 descr="Number of cache misses. UC reads count as misses."></metric>
+  <metric name="TCC_EA_WRREQ" block=TCC event=29 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_EA_WRREQ_64B" block=TCC event=30 descr="Number of 64-byte transactions going (64-byte write or CMPSWAP) over the TC_EA_wrreq interface."></metric>
+  <metric name="TCC_EA_WRREQ_STALL" block=TCC event=33 descr="Number of cycles a write request was stalled."></metric>
+  <metric name="TCC_EA_RDREQ" block=TCC event=41 descr="Number of TCC/EA read requests (either 32-byte or 64-byte)"></metric>
+  <metric name="TCC_EA_RDREQ_32B" block=TCC event=42 descr="Number of 32-byte TCC/EA read requests"></metric>
 
   <metric name="TCP_TA_DATA_STALL_CYCLES" block=TCP event=6 descr="TCP stalls TA data interface. Now Windowed."></metric>
 </gfx9>
diff --git a/projects/rocprofiler/test/tool/metrics.xml b/projects/rocprofiler/test/tool/metrics.xml
index a346eee933..6ee5c1d679 100644
--- a/projects/rocprofiler/test/tool/metrics.xml
+++ b/projects/rocprofiler/test/tool/metrics.xml
@@ -47,15 +47,14 @@
 </gfx9>
 
 <global>
-  # GPUBusy, percentage
-  # The percentage of time GPU was busy.
+  # GPUBusy         The percentage of time GPU was busy.
   <metric
     name="GPUBusy"
     descr="The percentage of time GPU was busy."
     expr=100*GRBM_GUI_ACTIVE/GRBM_COUNT
   ></metric>
 
-  # Wavefronts      Total wavefronts.,
+  # Wavefronts      Total wavefronts.
   <metric
     name="Wavefronts"
     descr="Total wavefronts."