[llvm] [Offload] Guard HSA implicit arguments if they aren't created (PR #133073)

[Joseph Huber via llvm-commits]

https://github.com/jhuber6 updated https://github.com/llvm/llvm-project/pull/133073

>From 2928db43d064dfce992120f8fb207c94ee0c2f4a Mon Sep 17 00:00:00 2001
From: Joseph Huber <huberjn at outlook.com>
Date: Wed, 26 Mar 2025 08:05:43 -0500
Subject: [PATCH] [Offload] Guard HSA implicit arguments if they aren't created

Summary:
We conditionally allocate the implicit arguments, so they possibly are
null. The flang compiler seems to hit this case, even though it
shouldn't when it's supposed to conform to the HSA code object. For now
guard this to fix the regression and cover a case in the future where
someone rolls a fully custom implementatation.

Fixes: https://github.com/llvm/llvm-project/issues/132982
---
 offload/plugins-nextgen/amdgpu/src/rtl.cpp | 39 ++++++++++------------
 1 file changed, 18 insertions(+), 21 deletions(-)

diff --git a/offload/plugins-nextgen/amdgpu/src/rtl.cpp b/offload/plugins-nextgen/amdgpu/src/rtl.cpp
index b2ede888b542d..ed575f2213f28 100644
--- a/offload/plugins-nextgen/amdgpu/src/rtl.cpp
+++ b/offload/plugins-nextgen/amdgpu/src/rtl.cpp
@@ -3363,16 +3363,6 @@ Error AMDGPUKernelTy::launchImpl(GenericDeviceTy &GenericDevice,
   if (auto Err = GenericDevice.getDeviceStackSize(StackSize))
     return Err;
 
-  hsa_utils::AMDGPUImplicitArgsTy *ImplArgs = nullptr;
-  if (ArgsSize == LaunchParams.Size + getImplicitArgsSize()) {
-    // Initialize implicit arguments.
-    ImplArgs = reinterpret_cast<hsa_utils::AMDGPUImplicitArgsTy *>(
-        utils::advancePtr(AllArgs, LaunchParams.Size));
-
-    // Initialize the implicit arguments to zero.
-    std::memset(ImplArgs, 0, getImplicitArgsSize());
-  }
-
   // Copy the explicit arguments.
   // TODO: We should expose the args memory manager alloc to the common part as
   // 	   alternative to copying them twice.
@@ -3385,17 +3375,24 @@ Error AMDGPUKernelTy::launchImpl(GenericDeviceTy &GenericDevice,
   if (auto Err = AMDGPUDevice.getStream(AsyncInfoWrapper, Stream))
     return Err;
 
-  // Set the COV5+ implicit arguments to the appropriate values.
-  ImplArgs->BlockCountX = NumBlocks[0];
-  ImplArgs->BlockCountY = NumBlocks[1];
-  ImplArgs->BlockCountZ = NumBlocks[2];
-  ImplArgs->GroupSizeX = NumThreads[0];
-  ImplArgs->GroupSizeY = NumThreads[1];
-  ImplArgs->GroupSizeZ = NumThreads[2];
-  ImplArgs->GridDims = NumBlocks[2] * NumThreads[2] > 1
-                           ? 3
-                           : 1 + (NumBlocks[1] * NumThreads[1] != 1);
-  ImplArgs->DynamicLdsSize = KernelArgs.DynCGroupMem;
+  hsa_utils::AMDGPUImplicitArgsTy *ImplArgs = nullptr;
+  if (ArgsSize == LaunchParams.Size + getImplicitArgsSize()) {
+    ImplArgs = reinterpret_cast<hsa_utils::AMDGPUImplicitArgsTy *>(
+        utils::advancePtr(AllArgs, LaunchParams.Size));
+
+    // Set the COV5+ implicit arguments to the appropriate values.
+    std::memset(ImplArgs, 0, getImplicitArgsSize());
+    ImplArgs->BlockCountX = NumBlocks[0];
+    ImplArgs->BlockCountY = NumBlocks[1];
+    ImplArgs->BlockCountZ = NumBlocks[2];
+    ImplArgs->GroupSizeX = NumThreads[0];
+    ImplArgs->GroupSizeY = NumThreads[1];
+    ImplArgs->GroupSizeZ = NumThreads[2];
+    ImplArgs->GridDims = NumBlocks[2] * NumThreads[2] > 1
+                             ? 3
+                             : 1 + (NumBlocks[1] * NumThreads[1] != 1);
+    ImplArgs->DynamicLdsSize = KernelArgs.DynCGroupMem;
+  }
 
   // Push the kernel launch into the stream.
   return Stream->pushKernelLaunch(*this, AllArgs, NumThreads, NumBlocks,