[PATCH] D112317: [AMDGPU] Fix latency for implicit vcc_lo operands on GFX10 wave32

[Jay Foad via Phabricator via llvm-commits]

foad added a comment.

In D112317#3080805 <https://reviews.llvm.org/D112317#3080805>, @arsenm wrote:

> Really we should have wave32 variants of all instructions

I agree, but I'd still like to be able to fix minor scheduling problems without tackling that fundamental issue.


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D112317/new/

https://reviews.llvm.org/D112317