diff options
| author | Craig Topper <craig.topper@intel.com> | 2018-09-22 05:08:38 +0000 |
|---|---|---|
| committer | Craig Topper <craig.topper@intel.com> | 2018-09-22 05:08:38 +0000 |
| commit | 9995760df4a526cf086b286058ed93172481a8c3 (patch) | |
| tree | 65a044bc963fdfa55355901e7af7c1a8dc84cda7 /llvm/lib/MC/MCObjectFileInfo.cpp | |
| parent | 8d3fa39a0d8deaa99b2615b10f61a2ae85f7f119 (diff) | |
| download | llvm-9995760df4a526cf086b286058ed93172481a8c3.zip llvm-9995760df4a526cf086b286058ed93172481a8c3.tar.gz llvm-9995760df4a526cf086b286058ed93172481a8c3.tar.bz2 | |
[X86] Fold (movmsk (setne (and X, (1 << C)), 0)) -> (movmsk (X << C)) for vXi8 vectors.
We don't have a vXi8 shift left so we need to bitcast to a vXi16 vector to perform the shift. If we let lowering legalize the vXi8 shift we get an extra and that we don't need and fail to remove.
llvm-svn: 342795
Diffstat (limited to 'llvm/lib/MC/MCObjectFileInfo.cpp')
0 files changed, 0 insertions, 0 deletions