[OpenCL] Add intel_reqd_sub_group_size attribute support
Summary:
Add intel_reqd_sub_group_size attribute support as intel extension cl_intel_required_subgroup_size from
https://www.khronos.org/registry/OpenCL/extensions/intel/cl_intel_required_subgroup_size.txt
Reviewers: Anastasia, bader, hfinkel, pxli168
Reviewed By: Anastasia, bader, pxli168
Subscribers: cfe-commits, yaxunl
Differential Revision: https://reviews.llvm.org/D30805
llvm-svn: 302125
diff --git a/clang/lib/CodeGen/CodeGenFunction.cpp b/clang/lib/CodeGen/CodeGenFunction.cpp
index 6e6eb7d..7b42850d 100644
--- a/clang/lib/CodeGen/CodeGenFunction.cpp
+++ b/clang/lib/CodeGen/CodeGenFunction.cpp
@@ -658,34 +658,42 @@
GenOpenCLArgMetadata(FD, Fn, CGM, Context, Builder, getContext());
if (const VecTypeHintAttr *A = FD->getAttr<VecTypeHintAttr>()) {
- QualType hintQTy = A->getTypeHint();
- const ExtVectorType *hintEltQTy = hintQTy->getAs<ExtVectorType>();
- bool isSignedInteger =
- hintQTy->isSignedIntegerType() ||
- (hintEltQTy && hintEltQTy->getElementType()->isSignedIntegerType());
- llvm::Metadata *attrMDArgs[] = {
+ QualType HintQTy = A->getTypeHint();
+ const ExtVectorType *HintEltQTy = HintQTy->getAs<ExtVectorType>();
+ bool IsSignedInteger =
+ HintQTy->isSignedIntegerType() ||
+ (HintEltQTy && HintEltQTy->getElementType()->isSignedIntegerType());
+ llvm::Metadata *AttrMDArgs[] = {
llvm::ConstantAsMetadata::get(llvm::UndefValue::get(
CGM.getTypes().ConvertType(A->getTypeHint()))),
llvm::ConstantAsMetadata::get(llvm::ConstantInt::get(
llvm::IntegerType::get(Context, 32),
- llvm::APInt(32, (uint64_t)(isSignedInteger ? 1 : 0))))};
- Fn->setMetadata("vec_type_hint", llvm::MDNode::get(Context, attrMDArgs));
+ llvm::APInt(32, (uint64_t)(IsSignedInteger ? 1 : 0))))};
+ Fn->setMetadata("vec_type_hint", llvm::MDNode::get(Context, AttrMDArgs));
}
if (const WorkGroupSizeHintAttr *A = FD->getAttr<WorkGroupSizeHintAttr>()) {
- llvm::Metadata *attrMDArgs[] = {
+ llvm::Metadata *AttrMDArgs[] = {
llvm::ConstantAsMetadata::get(Builder.getInt32(A->getXDim())),
llvm::ConstantAsMetadata::get(Builder.getInt32(A->getYDim())),
llvm::ConstantAsMetadata::get(Builder.getInt32(A->getZDim()))};
- Fn->setMetadata("work_group_size_hint", llvm::MDNode::get(Context, attrMDArgs));
+ Fn->setMetadata("work_group_size_hint", llvm::MDNode::get(Context, AttrMDArgs));
}
if (const ReqdWorkGroupSizeAttr *A = FD->getAttr<ReqdWorkGroupSizeAttr>()) {
- llvm::Metadata *attrMDArgs[] = {
+ llvm::Metadata *AttrMDArgs[] = {
llvm::ConstantAsMetadata::get(Builder.getInt32(A->getXDim())),
llvm::ConstantAsMetadata::get(Builder.getInt32(A->getYDim())),
llvm::ConstantAsMetadata::get(Builder.getInt32(A->getZDim()))};
- Fn->setMetadata("reqd_work_group_size", llvm::MDNode::get(Context, attrMDArgs));
+ Fn->setMetadata("reqd_work_group_size", llvm::MDNode::get(Context, AttrMDArgs));
+ }
+
+ if (const OpenCLIntelReqdSubGroupSizeAttr *A =
+ FD->getAttr<OpenCLIntelReqdSubGroupSizeAttr>()) {
+ llvm::Metadata *AttrMDArgs[] = {
+ llvm::ConstantAsMetadata::get(Builder.getInt32(A->getSubGroupSize()))};
+ Fn->setMetadata("intel_reqd_sub_group_size",
+ llvm::MDNode::get(Context, AttrMDArgs));
}
}
diff --git a/clang/lib/CodeGen/CodeGenFunction.h b/clang/lib/CodeGen/CodeGenFunction.h
index b696408..459841a 100644
--- a/clang/lib/CodeGen/CodeGenFunction.h
+++ b/clang/lib/CodeGen/CodeGenFunction.h
@@ -1413,16 +1413,8 @@
/// True if we need emit the life-time markers.
const bool ShouldEmitLifetimeMarkers;
- /// Add a kernel metadata node to the named metadata node 'opencl.kernels'.
- /// In the kernel metadata node, reference the kernel function and metadata
- /// nodes for its optional attribute qualifiers (OpenCL 1.1 6.7.2):
- /// - A node for the vec_type_hint(<type>) qualifier contains string
- /// "vec_type_hint", an undefined value of the <type> data type,
- /// and a Boolean that is true if the <type> is integer and signed.
- /// - A node for the work_group_size_hint(X,Y,Z) qualifier contains string
- /// "work_group_size_hint", and three 32-bit integers X, Y and Z.
- /// - A node for the reqd_work_group_size(X,Y,Z) qualifier contains string
- /// "reqd_work_group_size", and three 32-bit integers X, Y and Z.
+ /// Add OpenCL kernel arg metadata and the kernel attribute meatadata to
+ /// the function metadata.
void EmitOpenCLKernelMetadata(const FunctionDecl *FD,
llvm::Function *Fn);