[PATCH] D101430: [AMDGPU] Refactor hazard recognition IsHazardFn and IsExpiredFn

[Carl Ritson via Phabricator via llvm-commits]

critson added a comment.

In D101430#2721935 <https://reviews.llvm.org/D101430#2721935>, @foad wrote:

> 



> I still hope there is a way to fix the early-out case, rather than removing it completely, but I have not worked through the details yet.

I don't think you can find the minimum wait count without a breath-first search?
Unless you are suggesting we allow selected searches to complete early?


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D101430/new/

https://reviews.llvm.org/D101430