[libc-commits] [PATCH] D152486: [libc] Begin implementing a 'libmgpu.a' for math on the GPU

[Matt Arsenault via Phabricator via libc-commits]

arsenm added a comment.

In D152486#4408610 <https://reviews.llvm.org/D152486#4408610>, @JonChesterfield wrote:

> @Matt good news on ocml, thanks. I think we should add a wave size intrinsic, unconditionally expand it somewhere in clang and the backend and replace the current magic variable in ocml with it.

We used to do that, and it doesn't work. We can't codegen different subtargets within the same function like that. Really having wave32 and wave64 coexist in the same module leads to a variety of untenable situations


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D152486/new/

https://reviews.llvm.org/D152486