[cuda][hip] Fix `RegisterVar` function prototype.
Summary:
- `RegisterVar` has `void` return type and `size_t` in its variable size
parameter in HIP or CUDA 9.0+.
Reviewers: tra, yaxunl
Subscribers: cfe-commits
Tags: #clang
Differential Revision: https://reviews.llvm.org/D77398
diff --git a/clang/lib/CodeGen/CGCUDANV.cpp b/clang/lib/CodeGen/CGCUDANV.cpp
index 6d92ef3..351c505 100644
--- a/clang/lib/CodeGen/CGCUDANV.cpp
+++ b/clang/lib/CodeGen/CGCUDANV.cpp
@@ -440,13 +440,19 @@
Builder.CreateCall(RegisterFunc, Args);
}
+ llvm::Type *VarSizeTy = IntTy;
+ // For HIP or CUDA 9.0+, device variable size is type of `size_t`.
+ if (CGM.getLangOpts().HIP ||
+ ToCudaVersion(CGM.getTarget().getSDKVersion()) >= CudaVersion::CUDA_90)
+ VarSizeTy = SizeTy;
+
// void __cudaRegisterVar(void **, char *, char *, const char *,
// int, int, int, int)
llvm::Type *RegisterVarParams[] = {VoidPtrPtrTy, CharPtrTy, CharPtrTy,
- CharPtrTy, IntTy, IntTy,
+ CharPtrTy, IntTy, VarSizeTy,
IntTy, IntTy};
llvm::FunctionCallee RegisterVar = CGM.CreateRuntimeFunction(
- llvm::FunctionType::get(IntTy, RegisterVarParams, false),
+ llvm::FunctionType::get(VoidTy, RegisterVarParams, false),
addUnderscoredPrefixToName("RegisterVar"));
// void __cudaRegisterSurface(void **, const struct surfaceReference *,
// const void **, const char *, int, int);
@@ -476,7 +482,7 @@
VarName,
VarName,
llvm::ConstantInt::get(IntTy, Info.Flags.isExtern()),
- llvm::ConstantInt::get(IntTy, VarSize),
+ llvm::ConstantInt::get(VarSizeTy, VarSize),
llvm::ConstantInt::get(IntTy, Info.Flags.isConstant()),
llvm::ConstantInt::get(IntTy, 0)};
Builder.CreateCall(RegisterVar, Args);