replica
/
hanchenye-llvm-project
2
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

[HIP] Mark kernels with uniform-work-group-size=true 

Differential Revision: https://reviews.llvm.org/D76076
This commit is contained in:
Yaxun (Sam) Liu 2020-03-12 12:49:26 -04:00
parent 2e77f0cf76
commit 0ffb12ca67
2 changed files with 5 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
clang/lib/CodeGen/TargetInfo.cpp
View File

@ -8091,6 +8091,10 @@ void AMDGPUTargetCodeGenInfo::setTargetAttributes(
(M.getTriple().getOS() == llvm::Triple::AMDHSA))
F->addFnAttr("amdgpu-implicitarg-num-bytes", "56");
if (IsHIPKernel)
F->addFnAttr("uniform-work-group-size", "true");
const auto *FlatWGS = FD->getAttr<AMDGPUFlatWorkGroupSizeAttr>();
if (ReqdWGS || FlatWGS) {
unsigned Min = 0;

2
clang/test/CodeGenCUDA/amdgpu-kernel-attrs.cu
View File

@ -39,7 +39,7 @@ __global__ void num_vgpr_64() {
// 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"
// DEFAULT-DAG: attributes [[FLAT_WORK_GROUP_SIZE_DEFAULT]] = {{.*}}"amdgpu-flat-work-group-size"="1,256"{{.*}}"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"