[PATCH] D97342: [AMDGPU] Skip unclusterd rescheduling w/o ld/st

[Valery Pykhtin via Phabricator via llvm-commits]

vpykhtin added a comment.

Looks good, but should we use just a single dedicated pass over SUs to check if there're clustered ops after first scheduling to make the logic slightly easier?


CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D97342/new/

https://reviews.llvm.org/D97342