[PATCH] D97922: [AMDGPU] Keep skip branch for ds instructions

[Sebastian Neubauer via Phabricator via llvm-commits]

sebastian-ne added a comment.

Yes, that’s also what Carl concluded. Taking a s_cbranch_execz should be about the same amount of cycles as a ds_ instruction.
If we more than a ds_ instruction, taking the branch should be cheaper.


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D97922/new/

https://reviews.llvm.org/D97922