[all-commits] [llvm/llvm-project] 3530c3: [OpenMP] Use CUDA's non-RDC mode when LTO has whol...

Joseph Huber via All-commits all-commits at lists.llvm.org
Sat Apr 23 09:43:03 PDT 2022

  Branch: refs/heads/main
  Home:   https://github.com/llvm/llvm-project
  Commit: 3530c35c660919b9367f1ac598abfb9a569e7606
  Author: Joseph Huber <jhuber6 at vols.utk.edu>
  Date:   2022-04-23 (Sat, 23 Apr 2022)

  Changed paths:
    M clang/test/Driver/linker-wrapper.c
    M clang/tools/clang-linker-wrapper/ClangLinkerWrapper.cpp

  Log Message:
  [OpenMP] Use CUDA's non-RDC mode when LTO has whole program visibility

When we do LTO we consider ourselves to have whole program visibility if
every single input file we have contains LLVM bitcode. If we have whole
program visibliity then we can create a single image and utilize CUDA's
non-RDC mode by not passing `-c` to `ptxas` and ignoring the `nvlink`
job. This should be faster for some situations and also saves us the
time executing `nvlink`.

Reviewed By: tra

Differential Revision: https://reviews.llvm.org/D124292

More information about the All-commits mailing list