[HIP] Change default --gpu-max-threads-per-block value to 1024

[yaxunl]

Summary

This better matches CUDA behavior.

[b-sumner]

clang/lib/CodeGen/TargetInfo.cpp

8825

I'd like to see the word default, e.g. OpenCLDefaultMaxWorkGroupSize, used more since that is what this is about. Ideally the option would have been named gpu-default-max-threads-per-block, but I suppose I can see why it was shortened.

[yaxunl]

change variable names

[yaxunl]

clang/lib/CodeGen/TargetInfo.cpp

8825

changed variable names.

[b-sumner]

Thanks. This looks fine to me.

clang/include/clang/Basic/LangOptions.def

 LANGOPT(RenderScript      , 1, 0, "RenderScript")
 
 LANGOPT(CUDAIsDevice      , 1, 0, "compiling for CUDA device")
 LANGOPT(CUDAAllowVariadicFunctions, 1, 0, "allowing variadic functions in CUDA device code")
 LANGOPT(CUDAHostDeviceConstexpr, 1, 1, "treating unattributed constexpr functions as __host__ __device__")
 LANGOPT(CUDADeviceApproxTranscendentals, 1, 0, "using approximate transcendental functions")
 LANGOPT(GPURelocatableDeviceCode, 1, 0, "generate relocatable device code")
 LANGOPT(GPUAllowDeviceInit, 1, 0, "allowing device side global init functions for HIP")
-LANGOPT(GPUMaxThreadsPerBlock, 32, 256, "default max threads per block for kernel launch bounds for HIP")
+LANGOPT(GPUMaxThreadsPerBlock, 32, 1024, "default max threads per block for kernel launch bounds for HIP")
 
 LANGOPT(SYCL              , 1, 0, "SYCL")
 LANGOPT(SYCLIsDevice      , 1, 0, "Generate code for SYCL device")
 LANGOPT(SYCLVersion       , 32, 0, "Version of the SYCL standard used")
 
 LANGOPT(HIPUseNewLaunchAPI, 1, 0, "Use new kernel launching API for HIP")
 
 LANGOPT(SizedDeallocation , 1, 0, "sized deallocation")

clang/lib/CodeGen/TargetInfo.cpp

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 || IsHIPKernel) {
     // By default, restrict the maximum size to a value specified by
-    // --gpu-max-threads-per-block=n or its default value.
+    // --gpu-max-threads-per-block=n or its default value for HIP.
+    const unsigned OpenCLDefaultMaxWorkGroupSize = 256;
+    const unsigned DefaultMaxWorkGroupSize =
+        IsOpenCLKernel ? OpenCLDefaultMaxWorkGroupSize
+                       : M.getLangOpts().GPUMaxThreadsPerBlock;
     std::string AttrVal =
-        std::string("1,") + llvm::utostr(M.getLangOpts().GPUMaxThreadsPerBlock);
+        std::string("1,") + llvm::utostr(DefaultMaxWorkGroupSize);
     F->addFnAttr("amdgpu-flat-work-group-size", AttrVal);
   }
 
   if (const auto *Attr = FD->getAttr<AMDGPUWavesPerEUAttr>()) {
     unsigned Min =
         Attr->getMin()->EvaluateKnownConstInt(M.getContext()).getExtValue();
     unsigned Max = Attr->getMax() ? Attr->getMax()
                                         ->EvaluateKnownConstInt(M.getContext())
                                         .getExtValue()

clang/test/CodeGenCUDA/amdgpu-kernel-attrs.cu

 }
 
 // Make sure this is silently accepted on other targets.
 // NAMD-NOT: "amdgpu-flat-work-group-size"
 // NAMD-NOT: "amdgpu-waves-per-eu"
 // NAMD-NOT: "amdgpu-num-vgpr"
 // NAMD-NOT: "amdgpu-num-sgpr"
 
-// DEFAULT-DAG: attributes [[FLAT_WORK_GROUP_SIZE_DEFAULT]] = {{.*}}"amdgpu-flat-work-group-size"="1,256"{{.*}}"uniform-work-group-size"="true"
+// DEFAULT-DAG: attributes [[FLAT_WORK_GROUP_SIZE_DEFAULT]] = {{.*}}"amdgpu-flat-work-group-size"="1,1024"{{.*}}"uniform-work-group-size"="true"
 // MAX1024-DAG: attributes [[FLAT_WORK_GROUP_SIZE_DEFAULT]] = {{.*}}"amdgpu-flat-work-group-size"="1,1024"
 // CHECK-DAG: attributes [[FLAT_WORK_GROUP_SIZE_32_64]] = {{.*}}"amdgpu-flat-work-group-size"="32,64"
 // CHECK-DAG: attributes [[WAVES_PER_EU_2]] = {{.*}}"amdgpu-waves-per-eu"="2"
 // CHECK-DAG: attributes [[NUM_SGPR_32]] = {{.*}}"amdgpu-num-sgpr"="32"
 // CHECK-DAG: attributes [[NUM_VGPR_64]] = {{.*}}"amdgpu-num-vgpr"="64"

clang/test/CodeGenCUDA/kernel-amdgcn.cu

 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"
+// CHECK: attributes #[[ATTR]] = {{.*}}"amdgpu-flat-work-group-size"="1,1024"