From 4df3e0bd9ae6e5982b43fd2fc3867cf5f0b87a53 Mon Sep 17 00:00:00 2001
From: AMD <amd@node-bp126-r03c.amd.com>
Date: Wed, 16 Jun 2021 18:33:58 -0500
Subject: [PATCH] Add support for gfx90a

Merge gfx90a support from the 'amd-npi' branch.

Change-Id: I9b51711ed4a1d2f1ed42ba9b83cb12136be228b8
---
 src/core/metrics.h        |  6 +++---
 test/tool/gfx_metrics.xml | 17 +++++++++++++++++
 test/tool/metrics.xml     |  8 ++++++--
 3 files changed, 26 insertions(+), 5 deletions(-)

diff --git a/src/core/metrics.h b/src/core/metrics.h
index a221168a..6eeebee3 100644
--- a/src/core/metrics.h
+++ b/src/core/metrics.h
@@ -196,9 +196,9 @@ class MetricsDict {
       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) {
-        ImportMetrics(agent_info, agent_info->name);
-      } else if (std::string("gfx908") == agent_info->name) {
+      if (std::string("gfx906") == agent_info->name ||
+          std::string("gfx908") == agent_info->name ||
+          std::string("gfx90a") == agent_info->name) {
         ImportMetrics(agent_info, agent_info->name);
       } else {
         agent_name_ = agent_info->gfxip;
diff --git a/test/tool/gfx_metrics.xml b/test/tool/gfx_metrics.xml
index 698826c6..c2a79af2 100644
--- a/test/tool/gfx_metrics.xml
+++ b/test/tool/gfx_metrics.xml
@@ -101,3 +101,20 @@
   <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>
 </gfx908>
+
+<gfx90a base="gfx908">
+  <metric name="SQ_INSTS_VMEM_WR" block=SQ event=53 descr="Number of VMEM write instructions issued (including FLAT). (per-simd, emulated)"></metric>
+  <metric name="SQ_INSTS_VMEM_RD" block=SQ event=54 descr="Number of VMEM read instructions issued (including FLAT). (per-simd, emulated)"></metric>
+  <metric name="SQ_INSTS_SALU" block=SQ event=56 descr="Number of SALU instructions issued. (per-simd, emulated)"></metric>
+  <metric name="SQ_INSTS_SMEM" block=SQ event=57 descr="Number of SMEM instructions issued. (per-simd, emulated)"></metric>
+  <metric name="SQ_INSTS_FLAT" block=SQ event=58 descr="Number of FLAT instructions issued. (per-simd, emulated)"></metric>
+  <metric name="SQ_INSTS_FLAT_LDS_ONLY" block=SQ event=59 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=60 descr="Number of LDS instructions issued (including FLAT). (per-simd, emulated)"></metric>
+  <metric name="SQ_INSTS_GDS" block=SQ event=61 descr="Number of GDS instructions issued. (per-simd, emulated)"></metric>
+
+  <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="SQ_ACTIVE_INST_VALU" block=SQ event=99 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=112 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=113 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=121 descr="Number of cycles LDS is stalled by bank conflicts. (emulated)"></metric>
+</gfx90a>
diff --git a/test/tool/metrics.xml b/test/tool/metrics.xml
index c340a439..a920ff04 100644
--- a/test/tool/metrics.xml
+++ b/test/tool/metrics.xml
@@ -65,12 +65,16 @@
   <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>
 </gfx908_expr>
 
+<gfx90a_expr base="gfx908_expr"></gfx90a_expr>
+
 <gfx8 base="gfx8_expr"></gfx8>
 <gfx9 base="gfx9_expr"></gfx9>
-# VG20
+# Vega20
 <gfx906 base="gfx906_expr"></gfx906>
-# MI100
+# Arcturus
 <gfx908 base="gfx908_expr"></gfx908>
+# Aldebaran
+<gfx90a base="gfx90a_expr"></gfx90a>
 
 <global>
   # GPUBusy         The percentage of time GPU was busy.