diff options
| author | Matt Arsenault <Matthew.Arsenault@amd.com> | 2017-05-17 20:00:00 +0000 |
|---|---|---|
| committer | Matt Arsenault <Matthew.Arsenault@amd.com> | 2017-05-17 20:00:00 +0000 |
| commit | 572b72726d6359153df8c9c11364f66764c4ad17 (patch) | |
| tree | bb67b2e5f3509e09bf7459b866a3b3ead462c357 /test/CodeGen/NVPTX | |
| parent | ace0d94c1392c27a0300b98b642fcd246f7abd03 (diff) | |
AMDGPU: Try to use op_sel when selecting packed instructions
Avoids instructions to pack a vector when the source is really
a scalar being broadcast.
Also be smarter and look for per-component fneg.
Doesn't yet handle scalar from upper half of register
or other swizzles.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@303291 91177308-0d34-0410-b5e6-96231b3b80d8
Diffstat (limited to 'test/CodeGen/NVPTX')
0 files changed, 0 insertions, 0 deletions