[PATCH] D110076: [AMDGPU][GlobalISel] Code quality: Combine V_RSQ

[Jay Foad via Phabricator via llvm-commits]

foad added a comment.

Do we also need to handle:

- sqrt(rcp(x)) as well as rcp(sqrt(x)) ?
- 1.0 / x as well as llvm.amdgcn.rcp(x) ?


CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D110076/new/

https://reviews.llvm.org/D110076