diff options
| author | Chandler Carruth <chandlerc@gmail.com> | 2015-02-27 12:13:14 +0000 |
|---|---|---|
| committer | Chandler Carruth <chandlerc@gmail.com> | 2015-02-27 12:13:14 +0000 |
| commit | 9ad2ffac23d9329432656c0dbc1bf69299b652d4 (patch) | |
| tree | a7a9a2ebce95232ff65a8765a0d57c44831d495d /llvm/lib/CodeGen/MachineBasicBlock.cpp | |
| parent | 66b705bc64ada9d8e6f5051f499256fb5f2749ff (diff) | |
| download | llvm-9ad2ffac23d9329432656c0dbc1bf69299b652d4.zip llvm-9ad2ffac23d9329432656c0dbc1bf69299b652d4.tar.gz llvm-9ad2ffac23d9329432656c0dbc1bf69299b652d4.tar.bz2 | |
[x86] Run most of the rest of the shuffle combining over non-128-bit
vectors. This lets us fix the rest of the v16 lowering problems when
pshufb is clearly better.
We might still be able to improve some of the lowerings by enabling the
other combine-based rewriting to fire for non-128-bit vectors, but this
at least should remove any regressions from using the fancy v16i16
lowering strategy.
llvm-svn: 230753
Diffstat (limited to 'llvm/lib/CodeGen/MachineBasicBlock.cpp')
0 files changed, 0 insertions, 0 deletions