[PATCH] D26855: New unsafe-fp-math implementation for X86 target

[Andrew V. Tischenko via Phabricator via llvm-commits]

avt77 added a comment.

Two more comments:

1. I did not update  the patch accordingly to the latest Gerolf comments: I'll do it asap
2. Gerolf asked: "Perhaps I missed it but I expected the optimization to kick in only under fast math. I saw 'fast' in the test cases, but didn't see a check in the code."

  I check fast-math in "static bool getFDIVPatterns"

  switch (TLI->getRecipEstimateDivEnabled(VT, *MF)) { // this line checks per-function option case TLI->ReciprocalEstimate::Disabled: return false; case TLI->ReciprocalEstimate::Unspecified: if (Root.getParent()->getParent()->getTarget().Options.UnsafeFPMath) // and here I check command line option if there is no per-function code


https://reviews.llvm.org/D26855