[AMDGPU] Set default flat work group size to (1,256) for HIP

[yaxunl]

add test

[arsenm]

LGTM

lib/CodeGen/TargetInfo.cpp

void AMDGPUTargetCodeGenInfo::setTargetAttributes(
   llvm::Function *F = cast<llvm::Function>(GV);
 
   const auto *ReqdWGS = M.getLangOpts().OpenCL ?
     FD->getAttr<ReqdWorkGroupSizeAttr>() : nullptr;
 
 
   const bool IsOpenCLKernel = M.getLangOpts().OpenCL &&
                               FD->hasAttr<OpenCLKernelAttr>();
-  if ((IsOpenCLKernel ||
-       (M.getLangOpts().HIP && FD->hasAttr<CUDAGlobalAttr>())) &&
+  const bool IsHIPKernel = M.getLangOpts().HIP &&
+                           FD->hasAttr<CUDAGlobalAttr>();
+  if ((IsOpenCLKernel || IsHIPKernel) &&
       (M.getTriple().getOS() == llvm::Triple::AMDHSA))
     F->addFnAttr("amdgpu-implicitarg-num-bytes", "56");
 
   const auto *FlatWGS = FD->getAttr<AMDGPUFlatWorkGroupSizeAttr>();
   if (ReqdWGS || FlatWGS) {
     unsigned Min = 0;
     unsigned Max = 0;
     if (FlatWGS) {
if (ReqdWGS || FlatWGS) {
 
     if (Min != 0) {
       assert(Min <= Max && "Min must be less than or equal Max");
 
       std::string AttrVal = llvm::utostr(Min) + "," + llvm::utostr(Max);
       F->addFnAttr("amdgpu-flat-work-group-size", AttrVal);
     } else
       assert(Max == 0 && "Max must be zero");
-  } else if (IsOpenCLKernel) {
+  } else if (IsOpenCLKernel || IsHIPKernel) {
     // By default, restrict the maximum size to 256.
     F->addFnAttr("amdgpu-flat-work-group-size", "1,256");
   }
 
   if (const auto *Attr = FD->getAttr<AMDGPUWavesPerEUAttr>()) {
     unsigned Min =
         Attr->getMin()->EvaluateKnownConstInt(M.getContext()).getExtValue();
     unsigned Max = Attr->getMax() ? Attr->getMax()

test/CodeGenCUDA/kernel-amdgcn.cu

-// RUN: %clang_cc1 -triple amdgcn -fcuda-is-device -emit-llvm %s -o - | FileCheck %s
+// RUN: %clang_cc1 -triple amdgcn -fcuda-is-device -emit-llvm -x hip %s -o - | FileCheck %s
 #include "Inputs/cuda.h"
 
 // CHECK: define amdgpu_kernel void @_ZN1A6kernelEv
 class A {
 public:
   static __global__ void kernel(){}
 };
 

 __global__ void EmptyKernel(void) {}
 
 struct Dummy {
   /// Type definition of the EmptyKernel kernel entry point
   typedef void (*EmptyKernelPtr)();
   EmptyKernelPtr Empty() { return EmptyKernel<void>; } 
 };
 
-// CHECK: define amdgpu_kernel void @_Z15template_kernelI1AEvT_
+// CHECK: define amdgpu_kernel void @_Z15template_kernelI1AEvT_{{.*}} #[[ATTR:[0-9][0-9]*]]
 template<class T>
 __global__ void template_kernel(T x) {}
 
 void launch(void *f);
 
 int main() {
   Dummy D;
   launch((void*)A::kernel);
   launch((void*)kernel);
   launch((void*)template_kernel<A>);
   launch((void*)D.Empty());
   return 0;
 }
+// CHECK: attributes #[[ATTR]] = {{.*}}"amdgpu-flat-work-group-size"="1,256"