[clang] 1495210 - [OpenCL] Always add nounwind attribute for OpenCL

[Sven van Haastregt via cfe-commits]

Author: Sven van Haastregt
Date: 2023-01-20T12:01:22Z
New Revision: 1495210914997bcd0ca6937be0ae3cd6809b5ef5

URL: https://github.com/llvm/llvm-project/commit/1495210914997bcd0ca6937be0ae3cd6809b5ef5
DIFF: https://github.com/llvm/llvm-project/commit/1495210914997bcd0ca6937be0ae3cd6809b5ef5.diff

LOG: [OpenCL] Always add nounwind attribute for OpenCL

Neither OpenCL nor C++ for OpenCL support exceptions, so add the
`nounwind` attribute unconditionally for those languages.

Differential Revision: https://reviews.llvm.org/D142033

Added: 
    

Modified: 
    clang/lib/CodeGen/CGCall.cpp
    clang/test/CodeGenOpenCL/amdgpu-enqueue-kernel.cl
    clang/test/CodeGenOpenCL/convergent.cl

Removed: 
    


################################################################################
diff  --git a/clang/lib/CodeGen/CGCall.cpp b/clang/lib/CodeGen/CGCall.cpp
index 276d91fa2758d..dfa552161d7ca 100644
--- a/clang/lib/CodeGen/CGCall.cpp
+++ b/clang/lib/CodeGen/CGCall.cpp
@@ -1969,11 +1969,11 @@ void CodeGenModule::getDefaultFunctionAttributes(StringRef Name,
     FuncAttrs.addAttribute(llvm::Attribute::Convergent);
   }
 
-  // TODO: NoUnwind attribute should be added for other GPU modes OpenCL, HIP,
+  // TODO: NoUnwind attribute should be added for other GPU modes HIP,
   // SYCL, OpenMP offload. AFAIK, none of them support exceptions in device
   // code.
-  if (getLangOpts().CUDA && getLangOpts().CUDAIsDevice) {
-    // Exceptions aren't supported in CUDA device code.
+  if ((getLangOpts().CUDA && getLangOpts().CUDAIsDevice) ||
+      getLangOpts().OpenCL) {
     FuncAttrs.addAttribute(llvm::Attribute::NoUnwind);
   }
 

diff  --git a/clang/test/CodeGenOpenCL/amdgpu-enqueue-kernel.cl b/clang/test/CodeGenOpenCL/amdgpu-enqueue-kernel.cl
index 210014d14c086..4277dbbc20530 100644
--- a/clang/test/CodeGenOpenCL/amdgpu-enqueue-kernel.cl
+++ b/clang/test/CodeGenOpenCL/amdgpu-enqueue-kernel.cl
@@ -298,7 +298,7 @@ kernel void test(global char *a, char b, global long *c, long d) {
 // CHECK: attributes #2 = { nocallback nofree nounwind willreturn memory(argmem: readwrite) }
 // CHECK: attributes #3 = { convergent noinline nounwind optnone "no-trapping-math"="true" "stack-protector-buffer-size"="8" "target-cpu"="gfx900" "target-features"="+16-bit-insts,+ci-insts,+dpp,+gfx8-insts,+gfx9-insts,+s-memrealtime,+s-memtime-inst,+wavefrontsize64" }
 // CHECK: attributes #4 = { nounwind "enqueued-block" }
-// CHECK: attributes #5 = { convergent }
+// CHECK: attributes #5 = { convergent nounwind }
 //.
 // CHECK: !0 = !{i32 1, !"amdgpu_code_object_version", i32 400}
 // CHECK: !1 = !{i32 1, !"wchar_size", i32 4}

diff  --git a/clang/test/CodeGenOpenCL/convergent.cl b/clang/test/CodeGenOpenCL/convergent.cl
index f764cf0fc782d..123adba7b40d2 100644
--- a/clang/test/CodeGenOpenCL/convergent.cl
+++ b/clang/test/CodeGenOpenCL/convergent.cl
@@ -139,4 +139,5 @@ kernel void assume_convergent_asm()
 // CHECK: attributes #3 = { {{[^}]*}}convergent noduplicate{{[^}]*}} }
 // CHECK: attributes #4 = { {{[^}]*}}convergent{{[^}]*}} }
 // CHECK: attributes #5 = { {{[^}]*}}convergent{{[^}]*}} }
-// CHECK: attributes #6 = { {{[^}]*}}convergent noduplicate{{[^}]*}} }
+// CHECK: attributes #6 = { {{[^}]*}}nounwind{{[^}]*}} }
+// CHECK: attributes #7 = { {{[^}]*}}convergent noduplicate nounwind{{[^}]*}} }