commit | faac86e5d6fe6ea2e357520cffaf839f1052314f | [log] [tgz] |
---|---|---|
author | Jeff Bolz <jbolz@nvidia.com> | Wed May 01 11:45:36 2019 -0500 |
committer | Jeff Bolz <jbolz@nvidia.com> | Wed May 01 11:45:51 2019 -0500 |
tree | 244da2b03ed8f7f308098b03d2576093e00a6f9c | |
parent | 86c72c9486a97da534f97e56b8f7ae06cd1b580b [diff] |
If a shader's only use of float16 is for FConvert, add the Float16 capability. When visiting instructions, check that there are no 16-bit storage capabilities and add the Float16 capability. Same for int8/int16.