[PATCH] D44401: [AMDGPU] Always use IDX for load/store format intrinsics.

Nicolai Hähnle via Phabricator via llvm-commits llvm-commits at lists.llvm.org
Sat Mar 17 05:34:45 PDT 2018


nhaehnle accepted this revision.
nhaehnle added a comment.
This revision is now accepted and ready to land.

In https://reviews.llvm.org/D44401#1040539, @mareko wrote:

> In https://reviews.llvm.org/D44401#1040175, @arsenm wrote:
>
> > I think the unit change is a hint we should use different intrinsics for this
>
>
> The current intrinsic is unusable on GFX9 though. Why should we keep it as-is if it's unusable? This patch is reasonable because it picks the most expected behavior for GFX9 while it disallows the least expected and problematic behavior.


I agree. We don't have a use for "format" instructions without stride, and we don't have a use for "non-format" instructions with stride, so this change is pragmatic. Arguably, we should remove the "index" parameter from the "non-format" intrinsics, but that's a change requiring a flag-day.


Repository:
  rL LLVM

https://reviews.llvm.org/D44401





More information about the llvm-commits mailing list