[PATCH] D83981: [x86] split FMA with fast-math-flags to avoid libcall

Cameron McInally via Phabricator via llvm-commits llvm-commits at lists.llvm.org
Fri Jul 17 13:28:46 PDT 2020

Previous message: [PATCH] D83981: [x86] split FMA with fast-math-flags to avoid libcall
Next message: [PATCH] D83981: [x86] split FMA with fast-math-flags to avoid libcall
Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]

cameron.mcinally added a comment.

This looks good besides the Piledriver checks.

Regarding StrictFP: an FMA is not the same as a MUL+ADD in that context. So going to a libcall is the right move.


CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D83981/new/

https://reviews.llvm.org/D83981

Previous message: [PATCH] D83981: [x86] split FMA with fast-math-flags to avoid libcall
Next message: [PATCH] D83981: [x86] split FMA with fast-math-flags to avoid libcall
Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]

More information about the llvm-commits mailing list