[PATCH] D31533: Do not translate rint into nearbyint, but truncate it like nearbyint

[Eli Friedman via Phabricator via llvm-commits]

efriedma added a comment.

If rint() is faster than nearbyint(), should we canonicalize nearbyint()->rint()?


Repository:
  rL LLVM

https://reviews.llvm.org/D31533