maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity

[CUDA] Only allow NVIDIA offload-arch during CUDA compilation. 

Otherwise, if someone specifies a valid AMD arch, we may end up triggering an
assertion on unexpected arch later on.

Differential Revision: https://reviews.llvm.org/D105295
This commit is contained in:
Artem Belevich 2021-07-01 09:55:44 -07:00
parent 6245252d4c
commit 01d3a3dcab
2 changed files with 3 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
clang/lib/Driver/Driver.cpp
View File

@ -2785,7 +2785,7 @@ class OffloadingActionBuilder final {
StringRef getCanonicalOffloadArch(StringRef ArchStr) override {
CudaArch Arch = StringToCudaArch(ArchStr);
if (Arch == CudaArch::UNKNOWN) {
if (Arch == CudaArch::UNKNOWN || !IsNVIDIAGpuArch(Arch)) {
C.getDriver().Diag(clang::diag::err_drv_cuda_bad_gpu_arch) << ArchStr;
return StringRef();
}

2
clang/test/Driver/cuda-bad-arch.cu
View File

@ -10,6 +10,8 @@
// RUN: | FileCheck -check-prefix BAD %s
// RUN: %clang -### -target x86_64-linux-gnu --cuda-gpu-arch=sm_19 -c %s 2>&1 \
// RUN: | FileCheck -check-prefix BAD %s
// RUN: %clang -### -target x86_64-linux-gnu --cuda-gpu-arch=gfx900 -c %s 2>&1 \
// RUN: | FileCheck -check-prefix BAD %s
// BAD: error: Unsupported CUDA gpu architecture