diff options
| author | Raul Tambre <raul@tambre.ee> | 2020-09-05 16:40:02 (GMT) |
|---|---|---|
| committer | Brad King <brad.king@kitware.com> | 2020-09-24 19:19:54 (GMT) |
| commit | c63fe018353cf6afb30980c4cac7493be7cd0a82 (patch) | |
| tree | 68d2daf0cd8ab91a9feaa49392607c6cfecd2ac4 /Source/cmLocalGenerator.cxx | |
| parent | c98ec731f90eb0180c89108b7d2e42263b66d1ed (diff) | |
| download | CMake-c63fe018353cf6afb30980c4cac7493be7cd0a82.zip CMake-c63fe018353cf6afb30980c4cac7493be7cd0a82.tar.gz CMake-c63fe018353cf6afb30980c4cac7493be7cd0a82.tar.bz2 | |
CUDA: Clang separable compilation
For NVCC the compiler takes care of device linking when passed the "-dlink"
flag.
Clang doesn't support such magic and requires the buildsystem to do the work
that NVCC does behind the scenes.
The implementation is based on Bazel's device linking documentation:
https://github.com/tensorflow/tensorflow/blob/7cabcdf073abad8c46e9dda62bb8fa4682d2061e/third_party/nccl/build_defs.bzl.tpl#L259
Closes: #20726
Diffstat (limited to 'Source/cmLocalGenerator.cxx')
| -rw-r--r-- | Source/cmLocalGenerator.cxx | 11 |
1 files changed, 0 insertions, 11 deletions
diff --git a/Source/cmLocalGenerator.cxx b/Source/cmLocalGenerator.cxx index 47931b0..4e6010c 100644 --- a/Source/cmLocalGenerator.cxx +++ b/Source/cmLocalGenerator.cxx @@ -1955,17 +1955,6 @@ void cmLocalGenerator::AddLanguageFlags(std::string& flags, } else if (lang == "CUDA") { target->AddCUDAArchitectureFlags(flags); target->AddCUDAToolkitFlags(flags); - - if (compiler == "Clang") { - bool separable = target->GetPropertyAsBool("CUDA_SEPARABLE_COMPILATION"); - - if (separable) { - this->Makefile->IssueMessage( - MessageType::FATAL_ERROR, - "CUDA_SEPARABLE_COMPILATION isn't supported on Clang. " - "See CMake issue #20726."); - } - } } else if (lang == "ISPC") { target->AddISPCTargetFlags(flags); } |