[PATCH] D148215: [SLP] Compute min/max scalar reduction costs using min/max intrinsics instead of expanded cmp+sel

Thu Apr 13 05:05:08 PDT 2023

nikic added a comment.

> I was considering updating all the LoopUtils minmax reduction helpers to work with the intrinsics directly (createMinMaxOp in particular), but I'm concerned that we don't guarantee minnum/maxnum handling on all backends. I could still do this for the integer cases at least?

For integers using the intrinsics definitely makes sense. For FP, that depends on whether non-nnan reductions are supported. If these are always nnan then minnum/maxnum should be fine (at least I think we consider those to be the canonical form).

Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D148215/new/

https://reviews.llvm.org/D148215