[PATCH] D79164: [CostModel] getCFInstrCost

[Sam Parker via Phabricator via llvm-commits]

samparker added a comment.

I suspect that the getCFInstr maybe used in an odd way by the vectorizer for these changes to make such a difference. I'm suspect that the vectorizer is multiplying the cost of it, where 0 or 1 would make quite a difference, but where it just shouldn't be... hopefully the cost of a branch and phi doesn't change that much after vectorization / scalarization.


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D79164/new/

https://reviews.llvm.org/D79164