Matt Arsenault ed2f5f42ee AMDGPU: Skip last corrections in afn f64 reciprocal (#183696) ...

Device libs has a fast reciprocal macro that is close
to the fast division expansion, but skips the last terms
compared to the full division.

The basic reciprocal handling has identical output to this
macro. The negative reciprocal case has different fneg placement
and smaller code size, but I believe should be the same.

2026-04-22 21:59:45 +01:00

307 KiB

Raw Permalink Blame History

View Raw