| commit | 372d796ab165a6d488fb8968e754d3cb22247054 | [log] [tgz] |
|---|---|---|
| author | Matt Arsenault <Matthew.Arsenault@amd.com> | Fri May 18 21:35:00 2018 +0000 |
| committer | Matt Arsenault <Matthew.Arsenault@amd.com> | Fri May 18 21:35:00 2018 +0000 |
| tree | cfa96823b953d3220f560eab8122a25b2f82d27f | |
| parent | 0198b73769e4ff37cc122a11c3fdea575d1a2e08 [diff] |
AMDGPU: Add pass to optimize reqd_work_group_size Eliminate loads from the dispatch packet when they will have a known value. Also pattern match the code used by the library to handle partial workgroup dispatches, which isn't necessary if reqd_work_group_size is used. llvm-svn: 332771