[PATCH] D48826: [AMDGPU] Add support for TFE/LWE in image intrinsics

[Nicolai Hähnle via Phabricator via llvm-commits]

nhaehnle added a comment.

Thanks for making the changes.

I think we got away with return type larger than dmask previously, because in the worst case we just over-conservatively allocate registers. But now that the number of registers actually matters because it's used to access the TFE/LWE return...


Repository:
  rL LLVM

https://reviews.llvm.org/D48826