This revision was automatically updated to reflect the committed changes.
Closed by commit rGf90056767828: [OpenMP][AMDGPU] Refactor setting uniform work
group size attribute (authored by domada).
Repository:
rG LLVM Github Monorepo
CHANGES SINCE LAST ACTION
https://reviews.llvm.org/D148525/new/
https://reviews.llvm.org/D148525
Files:
clang/lib/CodeGen/TargetInfo.cpp
llvm/lib/Frontend/OpenMP/OMPIRBuilder.cpp
Index: llvm/lib/Frontend/OpenMP/OMPIRBuilder.cpp
===================================================================
--- llvm/lib/Frontend/OpenMP/OMPIRBuilder.cpp
+++ llvm/lib/Frontend/OpenMP/OMPIRBuilder.cpp
@@ -4892,6 +4892,8 @@
// Add a function attribute for the kernel.
Fn->addFnAttr(Attribute::get(Ctx, "kernel"));
+ if (Triple(M.getTargetTriple()).isAMDGCN())
+ Fn->addFnAttr("uniform-work-group-size", "true");
}
// We only generate metadata for function that contain target regions.
Index: clang/lib/CodeGen/TargetInfo.cpp
===================================================================
--- clang/lib/CodeGen/TargetInfo.cpp
+++ clang/lib/CodeGen/TargetInfo.cpp
@@ -9588,12 +9588,9 @@
const bool IsHIPKernel =
M.getLangOpts().HIP && FD && FD->hasAttr<CUDAGlobalAttr>();
- const bool IsOpenMPkernel =
- M.getLangOpts().OpenMPIsDevice &&
- (F->getCallingConv() == llvm::CallingConv::AMDGPU_KERNEL);
// TODO: This should be moved to language specific attributes instead.
- if (IsHIPKernel || IsOpenMPkernel)
+ if (IsHIPKernel)
F->addFnAttr("uniform-work-group-size", "true");
if (M.getContext().getTargetInfo().allowAMDGPUUnsafeFPAtomics())
Index: llvm/lib/Frontend/OpenMP/OMPIRBuilder.cpp
===================================================================
--- llvm/lib/Frontend/OpenMP/OMPIRBuilder.cpp
+++ llvm/lib/Frontend/OpenMP/OMPIRBuilder.cpp
@@ -4892,6 +4892,8 @@
// Add a function attribute for the kernel.
Fn->addFnAttr(Attribute::get(Ctx, "kernel"));
+ if (Triple(M.getTargetTriple()).isAMDGCN())
+ Fn->addFnAttr("uniform-work-group-size", "true");
}
// We only generate metadata for function that contain target regions.
Index: clang/lib/CodeGen/TargetInfo.cpp
===================================================================
--- clang/lib/CodeGen/TargetInfo.cpp
+++ clang/lib/CodeGen/TargetInfo.cpp
@@ -9588,12 +9588,9 @@
const bool IsHIPKernel =
M.getLangOpts().HIP && FD && FD->hasAttr<CUDAGlobalAttr>();
- const bool IsOpenMPkernel =
- M.getLangOpts().OpenMPIsDevice &&
- (F->getCallingConv() == llvm::CallingConv::AMDGPU_KERNEL);
// TODO: This should be moved to language specific attributes instead.
- if (IsHIPKernel || IsOpenMPkernel)
+ if (IsHIPKernel)
F->addFnAttr("uniform-work-group-size", "true");
if (M.getContext().getTargetInfo().allowAMDGPUUnsafeFPAtomics())
_______________________________________________
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits
