| commit | 7287fcb5d580e8ac0b860ddd4da03dc395795fa0 | [log] [tgz] |
|---|---|---|
| author | Matt Arsenault <Matthew.Arsenault@amd.com> | Wed Sep 20 20:28:39 2017 +0000 |
| committer | Matt Arsenault <Matthew.Arsenault@amd.com> | Wed Sep 20 20:28:39 2017 +0000 |
| tree | 2bc96b63df047d02af7a782e78dd0537e1212b1e | |
| parent | d3762c4675cbe5178acef79f01c813bcbfc58cf5 [diff] |
AMDGPU: Start selecting v_mad_mixlo_f16 Also add some tests that should be able to use v_mad_mixhi_f16, but do not yet. This is trickier because we don't really model the partial update of the register done by 16-bit instructions. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@313806 91177308-0d34-0410-b5e6-96231b3b80d8