diff options
| author | Craig Topper <craig.topper@intel.com> | 2018-03-15 20:30:54 +0000 |
|---|---|---|
| committer | Craig Topper <craig.topper@intel.com> | 2018-03-15 20:30:54 +0000 |
| commit | c3983c34cdf1655572aff3f12cfb77e629813dd4 (patch) | |
| tree | 2272e604ebbb2daab012ef3d9594c7e35af73ab0 /llvm/lib/Transforms/Utils/LoopUtils.cpp | |
| parent | 46502fa2efc29ca0bf64354a17701f677130a1a3 (diff) | |
| download | llvm-c3983c34cdf1655572aff3f12cfb77e629813dd4.zip llvm-c3983c34cdf1655572aff3f12cfb77e629813dd4.tar.gz llvm-c3983c34cdf1655572aff3f12cfb77e629813dd4.tar.bz2 | |
[X86] Make sure we use FSUB instruction as the reference for operand order in isAddSubOrSubAdd when recognizing subadd
The FADD part of the addsub/subadd pattern can have its operands commuted, but when checking for fsubadd we were using the fadd as reference and commuting the fsub node.
llvm-svn: 327660
Diffstat (limited to 'llvm/lib/Transforms/Utils/LoopUtils.cpp')
0 files changed, 0 insertions, 0 deletions