[Clang][OpenCL][AMDGPU] Use byref for OpenCL kernel arguments

Due to a previous workaround allowing kernels to be called from other functions,
Clang currently doesn't use the `byref` attribute for aggregate kernel
arguments. The issue was recently resolved in
#115821. With that fix, we can now
enable the use of `byref` consistently across all languages.

Co-authored-by: Matt Arsenault <[email protected]>

Author: shiltian

clang/lib/CodeGen/Targets/AMDGPU.cpp

@@ -198,14 +198,10 @@ ABIArgInfo AMDGPUABIInfo::classifyKernelArgumentType(QualType Ty) const {
         /*ToAS=*/getContext().getTargetAddressSpace(LangAS::cuda_device));
   }
 
-  // FIXME: Should also use this for OpenCL, but it requires addressing the
-  // problem of kernels being called.
-  //
   // FIXME: This doesn't apply the optimization of coercing pointers in structs
   // to global address space when using byref. This would require implementing a
   // new kind of coercion of the in-memory type when for indirect arguments.
-  if (!getContext().getLangOpts().OpenCL && LTy == OrigLTy &&
-      isAggregateTypeForABI(Ty)) {
+  if (LTy == OrigLTy && isAggregateTypeForABI(Ty)) {
     return ABIArgInfo::getIndirectAliased(
         getContext().getTypeAlignInChars(Ty),
         getContext().getTargetAddressSpace(LangAS::opencl_constant),