[PATCH] D130618: [AArch64][LoopVectorize] Enable tail-folding of simple loops on neoverse-v1

[Dave Green via Phabricator via llvm-commits]

dmgreen added a comment.

Those number do not match what I see. The second version is 25% slower without interleaving in the example I tried. It can be dependant on the trip count though, or there could be something else going on. I will try to contact you to see where the discrepancy might lie.


CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D130618/new/

https://reviews.llvm.org/D130618