[PATCH] D50575: [AMDGPU] Add support for a16 modifier for gfx9

[Nicolai Hähnle via Phabricator via llvm-commits]

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

Thanks for the changes.

Sorry to be a stickler about this, but the formatting of the odd gradients check in `lowerImage` is still wrong, please adjust this according to clang-format-diff before you commit.

No need to re-upload here, the rest of the changes looks good to me.


Repository:
  rL LLVM

https://reviews.llvm.org/D50575