[PATCH] D84743: [Clang][AMDGCN] Universal device offloading macros header

[Joseph Huber via Phabricator via cfe-commits]

jhuber6 added a comment.

This might be useful in the context of generating multi-architecture libraries when we start writing `libc` and `libc++` functionality. Although I can't name any use-cases for certain right now. However, shouldn't we just be able to define these in `clang` along similar to the `__NVPTX__` and `__AMDGPU___`? We already have `__CUDA_ARCH__` don't we?


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D84743/new/

https://reviews.llvm.org/D84743