diff options
| author | Sanjay Patel <spatel@rotateright.com> | 2019-05-07 18:58:07 +0000 |
|---|---|---|
| committer | Sanjay Patel <spatel@rotateright.com> | 2019-05-07 18:58:07 +0000 |
| commit | 6a281a75450a23346bb24077c7e019183fe1d498 (patch) | |
| tree | adc01ea1e2969656c7e366366b64d639f02be27d /llvm/lib/Transforms/Utils/BasicBlockUtils.cpp | |
| parent | 102ec0977d17069812c505c4b1faae0266a34625 (diff) | |
| download | llvm-6a281a75450a23346bb24077c7e019183fe1d498.zip llvm-6a281a75450a23346bb24077c7e019183fe1d498.tar.gz llvm-6a281a75450a23346bb24077c7e019183fe1d498.tar.bz2 | |
[InstCombine] allow sinking fneg operands through an FP min/max
Fundamentally/generally, we should not have to rely on bailouts/crippling of
folds. In this particular case, I think we always recognize the inverted
predicate min/max pattern, so there should not be any loss of optimization.
Codegen looks better because we are eliminating an fneg.
llvm-svn: 360180
Diffstat (limited to 'llvm/lib/Transforms/Utils/BasicBlockUtils.cpp')
0 files changed, 0 insertions, 0 deletions