[PATCH] D108443: [MCA] Fixing bug causing LSUnit to not be notified when a 0 latency instruction finishes executing.

[Andrea Di Biagio via Phabricator via llvm-commits]

andreadb accepted this revision.
andreadb added a comment.
This revision is now accepted and ready to land.

LGTM

Presumably this bug was found while experimenting with your downstream target.
That would explain why you don't provide a test case for it. If my assumption is correct, then it is fine to commit this patch If so, then fine, Ship this patch anyway, because it is clearly good.

That being said, I am not entirely sure how you end up in a situation like this in general. It doesn't feel right for a load/store like instruction to have zero latency.
Was the instruction somehow eliminated? I wouldn't expect it to happen for memory operations. But the, I don't know your target.


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D108443/new/

https://reviews.llvm.org/D108443