[PATCH] D57748: AMDGPU: Add inverse ballot intrinsic

[Matt Arsenault via Phabricator via llvm-commits]

arsenm added a comment.

In D57748#1389109 <https://reviews.llvm.org/D57748#1389109>, @arsenm wrote:

> In D57748#1389105 <https://reviews.llvm.org/D57748#1389105>, @nhaehnle wrote:
>
> > Why can't we recognize this as a pattern? Basically, it's just `(src & (1 << thread_idx))`, and `thread_idx` can be matched as a sequence of `mbcnt` intrinsics.
> >
> > Hmm, except the SelectionDAG is only per-basic block. Ugh.
>
>
> We could always make CodeGenPrepare always sink these


I think this would be cleaner since then we wouldn't have to worry about the conceptually disturbing readfirstlane case


Repository:
  rL LLVM

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D57748/new/

https://reviews.llvm.org/D57748