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

[CUDA] Improve clang's ability to detect recent CUDA versions. 

CUDA-11.1 does not carry version.txt which causes clang to assume that it's
CUDA-7.0, which used to be the only CUDA version w/o version.txt.

In order to tell CUDA-7.0 apart from the new versions, clang now probes for the
presence of libdevice.10.bc which is not present in the old CUDA versions.

This should keep Clang working for CUDA-11.1.

PR47332: https://bugs.llvm.org/show_bug.cgi?id=47332

Differential Revision: https://reviews.llvm.org/D89752
This commit is contained in:
Artem Belevich 2020-10-19 16:41:51 -07:00
parent de346cf2ac
commit 65d206484c
7 changed files with 14 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

11
clang/lib/Driver/ToolChains/Cuda.cpp
View File

@ -155,9 +155,14 @@ CudaInstallationDetector::CudaInstallationDetector(
llvm::ErrorOr<std::unique_ptr<llvm::MemoryBuffer>> VersionFile =
FS.getBufferForFile(InstallPath + "/version.txt");
if (!VersionFile) {
// CUDA 7.0 doesn't have a version.txt, so guess that's our version if
// version.txt isn't present.
Version = CudaVersion::CUDA_70;
// CUDA 7.0 and CUDA 11.1+ do not have version.txt file.
// Use libdevice file to distinguish 7.0 from the new versions.
if (FS.exists(LibDevicePath + "/libdevice.10.bc")) {
Version = CudaVersion::LATEST;
DetectedVersionIsNotSupported = Version > CudaVersion::LATEST_SUPPORTED;
} else {
Version = CudaVersion::CUDA_70;
}
} else {
ParseCudaVersionFile((*VersionFile)->getBuffer());
}

0
clang/test/Driver/Inputs/CUDA_111/usr/local/cuda/bin/.keep Normal file
View File

0
clang/test/Driver/Inputs/CUDA_111/usr/local/cuda/include/.keep Normal file
View File

0
clang/test/Driver/Inputs/CUDA_111/usr/local/cuda/lib/.keep Normal file
View File

0
clang/test/Driver/Inputs/CUDA_111/usr/local/cuda/lib64/.keep Normal file
View File

0
clang/test/Driver/Inputs/CUDA_111/usr/local/cuda/nvvm/libdevice/libdevice.10.bc Normal file
View File

7
clang/test/Driver/cuda-version-check.cu
View File

@ -10,6 +10,11 @@
// RUN: FileCheck %s --check-prefix=OK
// RUN: %clang --target=x86_64-linux -v -### --cuda-gpu-arch=sm_60 --cuda-path=%S/Inputs/CUDA-unknown/usr/local/cuda 2>&1 %s | \
// RUN: FileCheck %s --check-prefix=UNKNOWN_VERSION
// CUDA versions after 11.0 (update 1) do not carry version.txt file. Make sure
// we still detect them as a new version and handle them the same as we handle
// other new CUDA versions.
// RUN: %clang --target=x86_64-linux -v -### --cuda-gpu-arch=sm_60 --cuda-path=%S/Inputs/CUDA_111/usr/local/cuda 2>&1 %s | \
// RUN: FileCheck %s --check-prefix=UNKNOWN_VERSION
// Make sure that we don't warn about CUDA version during C++ compilation.
// RUN: %clang --target=x86_64-linux -v -### -x c++ --cuda-gpu-arch=sm_60 \
// RUN: --cuda-path=%S/Inputs/CUDA-unknown/usr/local/cuda 2>&1 %s | \
@ -65,5 +70,5 @@
// ERR_SM61: error: GPU arch sm_61 {{.*}}
// ERR_SM61-NOT: error: GPU arch sm_61
// UNKNOWN_VERSION: Unknown CUDA version 999.999. Assuming the latest supported version
// UNKNOWN_VERSION: Unknown CUDA version {{.*}}. Assuming the latest supported version
// UNKNOWN_VERSION_CXX-NOT: Unknown CUDA version