[PATCH] D95672: [LV] Vectorize backward dependence

[Florian Hahn via Phabricator via llvm-commits]

fhahn added a comment.

Hi! Thanks for the patch. I won't have time to take a closer look until next week the earliest but I have a few high level questions/comments:

1. Can the initial patch be focused on initial support and only handle the case where only pairs of instructions need to be moved before/after another, not a list of instructions needs to be moved before/after another instruction?
2. Does the re-order map generation need to happen in LVL or could it be part of LoopAccessInfo, like the other memory checks? That way, other clients could also benefit.
3. Can we just use AliasAnalysis to check for instructions that block moving?
4. Why do we need to handle `EnableForwardingConflictDetection` again? Could LAI remember/mark those dependences, so we do not need to re-check them?


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D95672/new/

https://reviews.llvm.org/D95672