squiid/llvm
1
0
Fork 0
Code Issues Pull requests Activity

[CUDA][SPIRV] Use OpenCLKernel CC for CUDA -> SPIRV

Browse source 
Select the OpenCLKernel calling convention for kernels when compiling
CUDA targeting SPIR-V.

In this way the generated LLVM IR will have a spir_kernel calling
convention that will be translated to an OpEntryPoint when converting
to SPIRV.

Reviewed By: jlebar, tra

Differential Revision: https://reviews.llvm.org/D114407
This commit is contained in:
Daniele Castagna 2021-12-06 15:06:29 -08:00 committed by Artem Belevich
parent cc3bb85580
commit abbdc13e68
2 changed files with 23 additions and 0 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

14
clang/lib/Sema/SemaType.cpp
View file

@ -3940,6 +3940,20 @@ static CallingConv getCCForDeclaratorChunk(
break;
}
}
} else if (S.getLangOpts().CUDA) {
// If we're compiling CUDA/HIP code and targeting SPIR-V we need to make
// sure the kernels will be marked with the right calling convention so that
// they will be visible by the APIs that ingest SPIR-V.
llvm::Triple Triple = S.Context.getTargetInfo().getTriple();
if (Triple.getArch() == llvm::Triple::spirv32 ||
Triple.getArch() == llvm::Triple::spirv64) {
for (const ParsedAttr &AL : D.getDeclSpec().getAttributes()) {
if (AL.getKind() == ParsedAttr::AT_CUDAGlobal) {
CC = CC_OpenCLKernel;
break;
}
}
}
}
return CC;

9
clang/test/CodeGenCUDASPIRV/kernel-cc.cu Normal file
View file

@ -0,0 +1,9 @@
// RUN: %clang_cc1 -fcuda-is-device -triple spirv32 -o - -emit-llvm -x cuda %s | FileCheck %s
// RUN: %clang_cc1 -fcuda-is-device -triple spirv64 -o - -emit-llvm -x cuda %s | FileCheck %s
// Verifies that building CUDA targeting SPIR-V {32,64} generates LLVM IR with
// spir_kernel attributes for kernel functions.
// CHECK: define spir_kernel void @_Z6kernelv()
__attribute__((global)) void kernel() { return; }