From df4739929d063c8aa78b29d5912a13e9bcbbee76 Mon Sep 17 00:00:00 2001
From: Matthew Poremba <matthew.poremba@amd.com>
Date: Fri, 28 Jul 2023 11:51:11 -0500
Subject: [PATCH] gpu-compute: Change kernel-based exit location

The previous exit event occurs when the dispatcher sends a completion
signal for a kernel, but gem5 does some kernel-based stats updates after
the signal is sent. Therefore, if these exit events are used as a way to
dump per-kernel stats, some of the stats for the kernel that just ended
will be in the next kernel's stat dump which is misleading.

This patch moves the exit event to where the stats are updated and only
exits if the dispatcher has requested a stat dump to prevent situations
where stats are updated mid-kernel.

Change-Id: I74dc1cad5fc90382a2a80564764b3e7c9fb65521
---
 src/gpu-compute/dispatcher.cc |  2 +-
 src/gpu-compute/shader.cc     |  8 +++++++-
 src/gpu-compute/shader.hh     | 10 ++++++++++
 3 files changed, 18 insertions(+), 2 deletions(-)

diff --git a/src/gpu-compute/dispatcher.cc b/src/gpu-compute/dispatcher.cc
index 7b36bce591..babc938489 100644
--- a/src/gpu-compute/dispatcher.cc
+++ b/src/gpu-compute/dispatcher.cc
@@ -334,7 +334,7 @@ GPUDispatcher::notifyWgCompl(Wavefront *wf)
         DPRINTF(GPUKernelInfo, "Completed kernel %d\n", kern_id);
 
         if (kernelExitEvents) {
-            exitSimLoop("GPU Kernel Completed");
+            shader->requestKernelExitEvent();
         }
     }
 
diff --git a/src/gpu-compute/shader.cc b/src/gpu-compute/shader.cc
index 73d2366b74..620d0152c1 100644
--- a/src/gpu-compute/shader.cc
+++ b/src/gpu-compute/shader.cc
@@ -519,8 +519,14 @@ Shader::notifyCuSleep() {
     panic_if(_activeCus <= 0 || _activeCus > cuList.size(),
              "Invalid activeCu size\n");
     _activeCus--;
-    if (!_activeCus)
+    if (!_activeCus) {
         stats.shaderActiveTicks += curTick() - _lastInactiveTick;
+
+        if (kernelExitRequested) {
+            kernelExitRequested = false;
+            exitSimLoop("GPU Kernel Completed");
+        }
+    }
 }
 
 /**
diff --git a/src/gpu-compute/shader.hh b/src/gpu-compute/shader.hh
index 08dfd24b76..32ddf3d15b 100644
--- a/src/gpu-compute/shader.hh
+++ b/src/gpu-compute/shader.hh
@@ -97,6 +97,10 @@ class Shader : public ClockedObject
     // Last tick that all CUs attached to this shader were inactive
     Tick _lastInactiveTick;
 
+    // If a kernel-based exit event was requested, wait for all CUs in the
+    // shader to complete before actually exiting so that stats are updated.
+    bool kernelExitRequested = false;
+
   public:
     typedef ShaderParams Params;
     enum hsail_mode_e {SIMT,VECTOR_SCALAR};
@@ -314,6 +318,12 @@ class Shader : public ClockedObject
         stats.vectorInstDstOperand[num_operands]++;
     }
 
+    void
+    requestKernelExitEvent()
+    {
+        kernelExitRequested = true;
+    }
+
   protected:
     struct ShaderStats : public statistics::Group
     {