| commit | 901f036353d328ad89969eb84eaa83aaefe49eed | [log] [tgz] |
|---|---|---|
| author | Quentin Colombet <qcolombet@apple.com> | Fri Dec 04 01:53:14 2015 +0000 |
| committer | Quentin Colombet <qcolombet@apple.com> | Fri Dec 04 01:53:14 2015 +0000 |
| tree | 405cc9966604fc21fd33b0ad2e8cf13142257b87 | |
| parent | 97d0ffbe0647c4ec49ed4c1e58c9067963f57f95 [diff] |
[ARM] When a bitcast is about to be turned into a VMOVDRR, try to combine it with its source instead of forcing the values on GPRs. This improves the lowering of vector code when such bitcasts happen in the middle of vector computations. rdar://problem/23691584 llvm-svn: 254684