[PATCH] D81085: [AMDGPU/MemOpsCluster] Implement new heuristic for computing max mem ops cluster size

[Mahesha S via Phabricator via llvm-commits]

hsmhsm added a comment.

Unit test failures in the latest Harbormaster build are spurious - `llvm.amdgcn.image.nsa.ll` actually passes in my local repo build, and other three failures are `unsupported`  cases.


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D81085/new/

https://reviews.llvm.org/D81085