OPENMP: fix kernel attributes for fixed blocksize

Change-Id: I121f6c8a1cf219c9561318b45272df4072b230c1

Author: gregrodgers

clang/lib/CodeGen/CGOpenMPRuntimeGPU.cpp

@@ -1097,10 +1097,9 @@ void CGOpenMPRuntimeGPU::GenerateMetaData(CodeGenModule &CGM,
       if (IsGeneric)
         compileTimeThreadLimit =
             ComputeGenericWorkgroupSize(CGM, compileTimeThreadLimit);
-      std::string AttrVal = llvm::utostr(compileTimeThreadLimit);
       FlatAttr = compileTimeThreadLimit;
       OutlinedFn->addFnAttr("amdgpu-flat-work-group-size",
-                            AttrVal + "," + AttrVal);
+                            "1," + llvm::utostr(compileTimeThreadLimit));
       flatAttrEmitted = true;
     } // end   > 0
   }   // end of amdgcn teams or parallel directive
@@ -1114,10 +1113,9 @@ void CGOpenMPRuntimeGPU::GenerateMetaData(CodeGenModule &CGM,
       GenericModeWorkgroupSize =
           ComputeGenericWorkgroupSize(CGM, CmdLineWorkGroupSz);
 
-    std::string FlatAttrVal = llvm::utostr(GenericModeWorkgroupSize);
     FlatAttr = GenericModeWorkgroupSize;
     OutlinedFn->addFnAttr("amdgpu-flat-work-group-size",
-                            FlatAttrVal + "," + FlatAttrVal);
+                          "1," + llvm::utostr(GenericModeWorkgroupSize));
   }
   // Emit a kernel descriptor for runtime.
   setPropertyWorkGroupSize(CGM, OutlinedFn->getName(), FlatAttr);

clang/lib/CodeGen/TargetInfo.cpp

@@ -9418,7 +9418,7 @@ void AMDGPUTargetCodeGenInfo::setTargetAttributes(
   const bool IsHIPKernel =
       M.getLangOpts().HIP && FD && FD->hasAttr<CUDAGlobalAttr>();
 
-  if (IsHIPKernel)
+  if (IsHIPKernel || M.getLangOpts().OpenMPIsDevice)
     F->addFnAttr("uniform-work-group-size", "true");
 
   if (M.getContext().getTargetInfo().allowAMDGPUUnsafeFPAtomics())

clang/test/OpenMP/amdgcn-attributes.cpp

@@ -32,12 +32,12 @@ int callable(int x) {
   return x + 1;
 }
 
-  // DEFAULT: attributes #0 = { convergent noinline norecurse nounwind optnone "amdgpu-flat-work-group-size"="257,257" "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 "amdgpu-flat-work-group-size"="257,257" "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-flat-work-group-size"="257,257" "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-flat-work-group-size"="257,257" "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 #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" }
-// NOIEEE: attributes #1 = { convergent mustprogress noinline nounwind optnone "amdgpu-ieee"="false" "frame-pointer"="none" "min-legal-vector-width"="0" "no-nans-fp-math"="true" "no-trapping-math"="true" "stack-protector-buffer-size"="8" }
-// UNSAFEATOMIC: attributes #1 = { convergent mustprogress noinline nounwind optnone "amdgpu-unsafe-fp-atomics"="true" "frame-pointer"="none" "min-legal-vector-width"="0" "no-trapping-math"="true" "stack-protector-buffer-size"="8" }
+  // DEFAULT: attributes #0 = { convergent noinline norecurse nounwind optnone "amdgpu-flat-work-group-size"="1,257" "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 "amdgpu-flat-work-group-size"="1,257" "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-flat-work-group-size"="1,257" "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-flat-work-group-size"="1,257" "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" "uniform-work-group-size"="true" }
+// 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" "uniform-work-group-size"="true" }
+// NOIEEE: attributes #1 = { convergent mustprogress noinline nounwind optnone "amdgpu-ieee"="false" "frame-pointer"="none" "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 #1 = { convergent mustprogress noinline nounwind optnone "amdgpu-unsafe-fp-atomics"="true" "frame-pointer"="none" "min-legal-vector-width"="0" "no-trapping-math"="true" "stack-protector-buffer-size"="8" "uniform-work-group-size"="true" }