jhuber6 created this revision.
jhuber6 added reviewers: jdoerfert, JonChesterfield, ronlieb, yaxunl, arsenm.
Herald added subscribers: kosarev, guansong, t-tye, tpr, dstuttard, jvesely,
kzhuravl.
Herald added a project: All.
jhuber6 requested review of this revision.
Herald added subscribers: cfe-commits, sstefan1, wdng.
Herald added a project: clang.
The `cl-uniform-work-group` attribute asserts that the global work-size
be a multiple of the work-group specified work group size. This should
allow optimizations. It is already present by default in the AMD
compiler and for HIP kernels so it should be safe to allow this for
OpenMP kernels by default.
Repository:
rG LLVM Github Monorepo
https://reviews.llvm.org/D135374
Files:
clang/lib/CodeGen/TargetInfo.cpp
clang/test/OpenMP/amdgcn-attributes.cpp
Index: clang/test/OpenMP/amdgcn-attributes.cpp
===================================================================
--- clang/test/OpenMP/amdgcn-attributes.cpp
+++ clang/test/OpenMP/amdgcn-attributes.cpp
@@ -32,10 +32,10 @@
return x + 1;
}
- // DEFAULT: attributes #0 = { convergent noinline norecurse nounwind optnone
"frame-pointer"="none" "kernel" "min-legal-vector-width"="0"
"no-trapping-math"="true" "stack-protector-buffer-size"="8" }
- // CPU: attributes #0 = { convergent noinline norecurse nounwind optnone
"frame-pointer"="none" "kernel" "min-legal-vector-width"="0"
"no-trapping-math"="true" "stack-protector-buffer-size"="8"
"target-cpu"="gfx900"
"target-features"="+16-bit-insts,+ci-insts,+dpp,+flat-address-space,+gfx8-insts,+gfx9-insts,+s-memrealtime,+s-memtime-inst"
}
- // NOIEEE: attributes #0 = { convergent noinline norecurse nounwind optnone
"amdgpu-ieee"="false" "frame-pointer"="none" "kernel"
"min-legal-vector-width"="0" "no-nans-fp-math"="true" "no-trapping-math"="true"
"stack-protector-buffer-size"="8" }
- // UNSAFEATOMIC: attributes #0 = { convergent noinline norecurse nounwind
optnone "amdgpu-unsafe-fp-atomics"="true" "frame-pointer"="none" "kernel"
"min-legal-vector-width"="0" "no-trapping-math"="true"
"stack-protector-buffer-size"="8" }
+// DEFAULT: attributes #0 = { convergent noinline norecurse nounwind optnone
"frame-pointer"="none" "kernel" "min-legal-vector-width"="0"
"no-trapping-math"="true" "stack-protector-buffer-size"="8"
"uniform-work-group-size"="true" }
+// CPU: attributes #0 = { convergent noinline norecurse nounwind optnone
"frame-pointer"="none" "kernel" "min-legal-vector-width"="0"
"no-trapping-math"="true" "stack-protector-buffer-size"="8"
"target-cpu"="gfx900"
"target-features"="+16-bit-insts,+ci-insts,+dpp,+flat-address-space,+gfx8-insts,+gfx9-insts,+s-memrealtime,+s-memtime-inst"
"uniform-work-group-size"="true" }
+// NOIEEE: attributes #0 = { convergent noinline norecurse nounwind optnone
"amdgpu-ieee"="false" "frame-pointer"="none" "kernel"
"min-legal-vector-width"="0" "no-nans-fp-math"="true" "no-trapping-math"="true"
"stack-protector-buffer-size"="8" "uniform-work-group-size"="true" }
+// UNSAFEATOMIC: attributes #0 = { convergent noinline norecurse nounwind
optnone "amdgpu-unsafe-fp-atomics"="true" "frame-pointer"="none" "kernel"
"min-legal-vector-width"="0" "no-trapping-math"="true"
"stack-protector-buffer-size"="8" "uniform-work-group-size"="true" }
// DEFAULT: attributes #1 = { convergent mustprogress noinline nounwind
optnone "frame-pointer"="none" "min-legal-vector-width"="0"
"no-trapping-math"="true" "stack-protector-buffer-size"="8" }
// CPU: attributes #1 = { convergent mustprogress noinline nounwind optnone
"frame-pointer"="none" "min-legal-vector-width"="0" "no-trapping-math"="true"
"stack-protector-buffer-size"="8" "target-cpu"="gfx900"
"target-features"="+16-bit-insts,+ci-insts,+dpp,+flat-address-space,+gfx8-insts,+gfx9-insts,+s-memrealtime,+s-memtime-inst"
}
Index: clang/lib/CodeGen/TargetInfo.cpp
===================================================================
--- clang/lib/CodeGen/TargetInfo.cpp
+++ clang/lib/CodeGen/TargetInfo.cpp
@@ -9423,8 +9423,11 @@
const bool IsHIPKernel =
M.getLangOpts().HIP && FD && FD->hasAttr<CUDAGlobalAttr>();
+ const bool IsOpenMPkernel =
+ M.getLangOpts().OpenMPIsDevice &&
+ (F->getCallingConv() == llvm::CallingConv::AMDGPU_KERNEL);
- if (IsHIPKernel)
+ if (IsHIPKernel || IsOpenMPkernel)
F->addFnAttr("uniform-work-group-size", "true");
if (M.getContext().getTargetInfo().allowAMDGPUUnsafeFPAtomics())
Index: clang/test/OpenMP/amdgcn-attributes.cpp
===================================================================
--- clang/test/OpenMP/amdgcn-attributes.cpp
+++ clang/test/OpenMP/amdgcn-attributes.cpp
@@ -32,10 +32,10 @@
return x + 1;
}
- // DEFAULT: attributes #0 = { convergent noinline norecurse nounwind optnone "frame-pointer"="none" "kernel" "min-legal-vector-width"="0" "no-trapping-math"="true" "stack-protector-buffer-size"="8" }
- // CPU: attributes #0 = { convergent noinline norecurse nounwind optnone "frame-pointer"="none" "kernel" "min-legal-vector-width"="0" "no-trapping-math"="true" "stack-protector-buffer-size"="8" "target-cpu"="gfx900" "target-features"="+16-bit-insts,+ci-insts,+dpp,+flat-address-space,+gfx8-insts,+gfx9-insts,+s-memrealtime,+s-memtime-inst" }
- // NOIEEE: attributes #0 = { convergent noinline norecurse nounwind optnone "amdgpu-ieee"="false" "frame-pointer"="none" "kernel" "min-legal-vector-width"="0" "no-nans-fp-math"="true" "no-trapping-math"="true" "stack-protector-buffer-size"="8" }
- // UNSAFEATOMIC: attributes #0 = { convergent noinline norecurse nounwind optnone "amdgpu-unsafe-fp-atomics"="true" "frame-pointer"="none" "kernel" "min-legal-vector-width"="0" "no-trapping-math"="true" "stack-protector-buffer-size"="8" }
+// DEFAULT: attributes #0 = { convergent noinline norecurse nounwind optnone "frame-pointer"="none" "kernel" "min-legal-vector-width"="0" "no-trapping-math"="true" "stack-protector-buffer-size"="8" "uniform-work-group-size"="true" }
+// CPU: attributes #0 = { convergent noinline norecurse nounwind optnone "frame-pointer"="none" "kernel" "min-legal-vector-width"="0" "no-trapping-math"="true" "stack-protector-buffer-size"="8" "target-cpu"="gfx900" "target-features"="+16-bit-insts,+ci-insts,+dpp,+flat-address-space,+gfx8-insts,+gfx9-insts,+s-memrealtime,+s-memtime-inst" "uniform-work-group-size"="true" }
+// NOIEEE: attributes #0 = { convergent noinline norecurse nounwind optnone "amdgpu-ieee"="false" "frame-pointer"="none" "kernel" "min-legal-vector-width"="0" "no-nans-fp-math"="true" "no-trapping-math"="true" "stack-protector-buffer-size"="8" "uniform-work-group-size"="true" }
+// UNSAFEATOMIC: attributes #0 = { convergent noinline norecurse nounwind optnone "amdgpu-unsafe-fp-atomics"="true" "frame-pointer"="none" "kernel" "min-legal-vector-width"="0" "no-trapping-math"="true" "stack-protector-buffer-size"="8" "uniform-work-group-size"="true" }
// DEFAULT: attributes #1 = { convergent mustprogress noinline nounwind optnone "frame-pointer"="none" "min-legal-vector-width"="0" "no-trapping-math"="true" "stack-protector-buffer-size"="8" }
// CPU: attributes #1 = { convergent mustprogress noinline nounwind optnone "frame-pointer"="none" "min-legal-vector-width"="0" "no-trapping-math"="true" "stack-protector-buffer-size"="8" "target-cpu"="gfx900" "target-features"="+16-bit-insts,+ci-insts,+dpp,+flat-address-space,+gfx8-insts,+gfx9-insts,+s-memrealtime,+s-memtime-inst" }
Index: clang/lib/CodeGen/TargetInfo.cpp
===================================================================
--- clang/lib/CodeGen/TargetInfo.cpp
+++ clang/lib/CodeGen/TargetInfo.cpp
@@ -9423,8 +9423,11 @@
const bool IsHIPKernel =
M.getLangOpts().HIP && FD && FD->hasAttr<CUDAGlobalAttr>();
+ const bool IsOpenMPkernel =
+ M.getLangOpts().OpenMPIsDevice &&
+ (F->getCallingConv() == llvm::CallingConv::AMDGPU_KERNEL);
- if (IsHIPKernel)
+ if (IsHIPKernel || IsOpenMPkernel)
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
