diff options
| author | Craig Topper <craig.topper@intel.com> | 2018-07-28 18:21:46 +0000 |
|---|---|---|
| committer | Craig Topper <craig.topper@intel.com> | 2018-07-28 18:21:46 +0000 |
| commit | 5daa03254637225408c1220e8788125a569872d1 (patch) | |
| tree | c81026f9eb02e3544239c598b078b9dd697237a2 /llvm/lib/Transforms/Vectorize/LoopVectorizationLegality.cpp | |
| parent | ba208b07b64efba4045e3cc08d404e1038bcc480 (diff) | |
| download | bcm5719-llvm-5daa03254637225408c1220e8788125a569872d1.tar.gz bcm5719-llvm-5daa03254637225408c1220e8788125a569872d1.zip | |
[X86] Correct the immediate cost for 'add/sub i64 %x, 0x80000000'.
X86 normally requires immediates to be a signed 32-bit value which would exclude i64 0x80000000. But for add/sub we can negate the constant and use the opposite instruction.
llvm-svn: 338204
Diffstat (limited to 'llvm/lib/Transforms/Vectorize/LoopVectorizationLegality.cpp')
0 files changed, 0 insertions, 0 deletions
