| commit | 2d75e7dced65f82c5181cef163ff5bb49540dd94 | [log] [tgz] |
|---|---|---|
| author | Faith Ekstrand <faith.ekstrand@collabora.com> | Wed Mar 12 18:01:58 2025 -0500 |
| committer | Marge Bot <emma+marge@anholt.net> | Sat Mar 29 03:02:17 2025 +0000 |
| tree | e9a9aab86d8be228395b9a4c92acb39b5e640b7e | |
| parent | d826f82ffe62a8fb53f3b59df07b83d0c7c1093f [diff] |
nak/nir: Use correct rounding for fp64 -> fp16 conversions For up, down, and round towards zero, the rounding accumulates properly as long as you use the same rounding mode for both. For RTNE, however, we need to insert a two-instruction fixup in order to guarantee correct rounding. Reviewed-by: Mel Henning <mhenning@darkrefraction.com> Reviewed-by: Benjamin Lee <benjamin.lee@collabora.com> Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/34126>