[PATCH] D97406: [Vectorizers]Improve emission of logical or/and reductions.

[Simon Pilgrim via Phabricator via llvm-commits]

RKSimon added a comment.

In D97406#2587071 <https://reviews.llvm.org/D97406#2587071>, @lebedev.ri wrote:

> Why can't we just do the costmodel change, and then canonicalize to the right variant (i.e. away from `@llvm.vector.reduce.?.v?i1`) in instcombine?

+1 I'd prefer to avoid yet more special cases in the vectorizers.


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D97406/new/

https://reviews.llvm.org/D97406