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/cmRulePlaceholderExpander.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/cmRulePlaceholderExpander.cxx')
-rw-r--r-- | Source/cmRulePlaceholderExpander.cxx | 10 |
1 files changed, 10 insertions, 0 deletions
diff --git a/Source/cmRulePlaceholderExpander.cxx b/Source/cmRulePlaceholderExpander.cxx index 6f40ec6..f5f9c67 100644 --- a/Source/cmRulePlaceholderExpander.cxx +++ b/Source/cmRulePlaceholderExpander.cxx @@ -141,6 +141,16 @@ std::string cmRulePlaceholderExpander::ExpandRuleVariable( return replaceValues.DependencyFile; } } + if (replaceValues.Fatbinary) { + if (variable == "FATBINARY") { + return replaceValues.Fatbinary; + } + } + if (replaceValues.RegisterFile) { + if (variable == "REGISTER_FILE") { + return replaceValues.RegisterFile; + } + } if (replaceValues.Target) { if (variable == "TARGET_QUOTED") { |