From 55680ff541e9d2d8fbcb30baad0916f2a9976bb0 Mon Sep 17 00:00:00 2001
From: Evgeny <evgeny.shcherbakov@amd.com>
Date: Wed, 7 Aug 2019 19:44:31 -0500
Subject: [PATCH] gfx908 events update

Change-Id: Ieb7c72f66b7e5e5dfc29d97650a29722a6276a31


[ROCm/rocprofiler commit: 09eed4f35b63d7b1fa0277feb423cd1818ecdc40]
---
 .../rocprofiler/test/tool/gfx_metrics.xml     | 36 +++++++++++++++++++
 projects/rocprofiler/test/tool/metrics.xml    |  7 ++--
 2 files changed, 40 insertions(+), 3 deletions(-)

diff --git a/projects/rocprofiler/test/tool/gfx_metrics.xml b/projects/rocprofiler/test/tool/gfx_metrics.xml
index c44576f1a8..2df7d53197 100644
--- a/projects/rocprofiler/test/tool/gfx_metrics.xml
+++ b/projects/rocprofiler/test/tool/gfx_metrics.xml
@@ -76,3 +76,39 @@
   <metric name="TCC_EA1_RDREQ" block=TCC event=267 descr="Number of TCC/EA read requests (either 32-byte or 64-byte)"></metric>
   <metric name="TCC_EA1_RDREQ_32B" block=TCC event=268 descr="Number of 32-byte TCC/EA read requests"></metric>
 </gfx906>
+
+<gfx908>
+  <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 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=28 descr="Number of VMEM write instructions issued (including FLAT). (per-simd, emulated)"></metric>
+  <metric name="SQ_INSTS_VMEM_RD" block=SQ event=29 descr="Number of VMEM read instructions issued (including FLAT). (per-simd, emulated)"></metric>
+  <metric name="SQ_INSTS_SALU" block=SQ event=31 descr="Number of SALU instructions issued. (per-simd, emulated)"></metric>
+  <metric name="SQ_INSTS_SMEM" block=SQ event=32 descr="Number of SMEM instructions issued. (per-simd, emulated)"></metric>
+  <metric name="SQ_INSTS_FLAT" block=SQ event=33 descr="Number of FLAT instructions issued. (per-simd, emulated)"></metric>
+  <metric name="SQ_INSTS_FLAT_LDS_ONLY" block=SQ event=34 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=35 descr="Number of LDS instructions issued (including FLAT). (per-simd, emulated)"></metric>
+  <metric name="SQ_INSTS_GDS" block=SQ event=36 descr="Number of GDS instructions issued. (per-simd, emulated)"></metric>
+
+  <metric name="SQ_WAIT_INST_LDS" block=SQ event=64 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=72 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=85 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=86 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=94 descr="Number of cycles LDS is stalled by bank conflicts. (emulated)"></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=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_EA_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_EA_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_EA_WRREQ_STALL" block=TCC event=30 descr="Number of cycles a write request was stalled."></metric>
+  <metric name="TCC_EA_RDREQ" block=TCC event=38 descr="Number of TCC/EA read requests (either 32-byte or 64-byte)"></metric>
+  <metric name="TCC_EA_RDREQ_32B" block=TCC event=39 descr="Number of 32-byte TCC/EA read requests"></metric>
+
+  <metric name="TCP_TCP_TA_DATA_STALL_CYCLES" block=TCP event=6 descr="TCP stalls TA data interface. Now Windowed."></metric>
+</gfx908>
diff --git a/projects/rocprofiler/test/tool/metrics.xml b/projects/rocprofiler/test/tool/metrics.xml
index 74d2ac62d5..fe87069642 100644
--- a/projects/rocprofiler/test/tool/metrics.xml
+++ b/projects/rocprofiler/test/tool/metrics.xml
@@ -33,11 +33,11 @@
   <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>
 </gfx9_base>
 
-<gfx9 base="gfx9_base">
+<gfx9_common base="gfx9_base">
   <metric name="TCC_MC_WRREQ_sum" expr=TCC_EA_WRREQ_64B_sum*2+(TCC_EA_WRREQ_sum-TCC_EA_WRREQ_64B_sum) descr="Number of 32-byte effective writes. Sum over TCC instaces."></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>
-</gfx9>
+</gfx9_common>
 
 <gfx906 base="gfx9_base">
   # EA1
@@ -55,7 +55,8 @@
   <metric name="WRITE_SIZE" expr=((TCC_EA_WRREQ_sum-TCC_EA_WRREQ_64B_sum)*32+TCC_EA_WRREQ_64B_sum*64+WDATA1_SIZE)/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>
 </gfx906>
 
-<gfx908 base="gfx9"></gfx908>
+<gfx908 base="gfx9_common"></gfx908>
+<gfx9 base="gfx9_common"></gfx9>
 
 <global>
   # GPUBusy         The percentage of time GPU was busy.