[PATCH] D98512: [LoopVectorize] Simplify scalar cost calculation in getInstructionCost

[Dave Green via Phabricator via llvm-commits]

dmgreen added a comment.

I agree that the IV update in the test should have a cost of 1. (It seems strange it doesn't already, I suspect it isn't matched the same as an increment 1).

Would it always be true for the addresses of scalarized loads/stores? They do need to calculate N addresses.

This didn't show any change in the tests I ran on it, but there is potentially not a lot in there that would scalarize memops.


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D98512/new/

https://reviews.llvm.org/D98512