From c3ce5684a8b408220eed983d065edba0e6ed5016 Mon Sep 17 00:00:00 2001
From: Aniket Lal <lalaniket8@gmail.com>
Date: Wed, 7 May 2025 15:42:23 +0530
Subject: [Clang][OpenCL][AMDGPU]  OpenCL Kernel stubs should be assigned
 alwaysinline attribute (#137769)

OpenCL Kernels body is emitted as stubs and the kernel is emitted as
call to respective stub.
(https://github.com/llvm/llvm-project/pull/115821).
The stub function should be alwaysinlined, since call to stub can cause
performance drop.

Co-authored-by: anikelal <anikelal@amd.com>
---
 clang/lib/CodeGen/CodeGenModule.cpp | 16 ++++++++++++++++
 1 file changed, 16 insertions(+)

(limited to 'clang/lib/CodeGen/CodeGenModule.cpp')

diff --git a/clang/lib/CodeGen/CodeGenModule.cpp b/clang/lib/CodeGen/CodeGenModule.cpp
index b36e078..c278176 100644
--- a/clang/lib/CodeGen/CodeGenModule.cpp
+++ b/clang/lib/CodeGen/CodeGenModule.cpp
@@ -6172,6 +6172,22 @@ void CodeGenModule::EmitGlobalFunctionDefinition(GlobalDecl GD,
   CodeGenFunction(*this).GenerateCode(GD, Fn, FI);
 
   setNonAliasAttributes(GD, Fn);
+
+  bool ShouldAddOptNone = !CodeGenOpts.DisableO0ImplyOptNone &&
+                          (CodeGenOpts.OptimizationLevel == 0) &&
+                          !D->hasAttr<MinSizeAttr>();
+
+  if (D->hasAttr<OpenCLKernelAttr>()) {
+    if (GD.getKernelReferenceKind() == KernelReferenceKind::Stub &&
+        !D->hasAttr<NoInlineAttr>() &&
+        !Fn->hasFnAttribute(llvm::Attribute::NoInline) &&
+        !D->hasAttr<OptimizeNoneAttr>() &&
+        !Fn->hasFnAttribute(llvm::Attribute::OptimizeNone) &&
+        !ShouldAddOptNone) {
+      Fn->addFnAttr(llvm::Attribute::AlwaysInline);
+    }
+  }
+
   SetLLVMFunctionAttributesForDefinition(D, Fn);
 
   if (const ConstructorAttr *CA = D->getAttr<ConstructorAttr>())
-- 
cgit v1.1