| commit | 4dc43963efbeaf320e45f65b0ed7cf10b03b4b11 | [log] [tgz] |
|---|---|---|
| author | Matt Arsenault <Matthew.Arsenault@amd.com> | Wed Jan 25 04:25:02 2017 +0000 |
| committer | Matt Arsenault <Matthew.Arsenault@amd.com> | Wed Jan 25 04:25:02 2017 +0000 |
| tree | e6bdd6c70bce8ecd7b33cb849d0b21d97c79af69 | |
| parent | 6e6c6de33b7e944c80bf72549e6fa5d085f9d285 [diff] |
AMDGPU: Implement early ifcvt target hooks. Leave early ifcvt disabled for now since there are some shader-db regressions. This causes some immediate improvements, but could be better. The cost checking that the pass does is based on critical path length for out of order CPUs which we do not want so it skips out on many cases we want. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@293016 91177308-0d34-0410-b5e6-96231b3b80d8