[PATCH] D108835: [NVPTX] consider nvptx-nvidia-gpulibs triple to be compatible with other variants.

[Artem Belevich via Phabricator via llvm-commits]

tra added a comment.

How is `libomptarget-nvptx-sm_80.bc` built? Perhaps it should be changed to use a more detailed triple. Perhaps match libdevice's `nvptx64-nvidia-gpulibs` or have a distinct openmp-specific one?

Do we have to deal with the libomptarget-nvptx-sm_80.bc shipped with the current `nvptx64` triple or is it shipped with clang and we don't need to worry about the older versions in the wild?


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D108835/new/

https://reviews.llvm.org/D108835