| commit | aac82e218f96f1bbafe8265baaf4b28f4bdb85bb | [log] [tgz] |
|---|---|---|
| author | Matt Arsenault <Matthew.Arsenault@amd.com> | Tue Feb 21 23:35:48 2017 +0000 |
| committer | Matt Arsenault <Matthew.Arsenault@amd.com> | Tue Feb 21 23:35:48 2017 +0000 |
| tree | 1caf5134f4140fff689362b40d1757f9dce26a74 | |
| parent | b1a24afa7a2c317de4da7e25ca003a918e45ac74 [diff] |
AMDGPU: Redefine clamp node as clamp 0.0-1.0 Change implementation to use max instead of add. min/max/med3 do not flush denormals regardless of the mode, so it is OK to use it whether or not they are enabled. Also allow using clamp with f16, and use knowledge of dx10_clamp. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@295788 91177308-0d34-0410-b5e6-96231b3b80d8