Alex 3a9da568fe fix(shader): round v_fma_mixlo_f16 and v_fma_mixhi_f16 once to f16 ... The f16 forms of v_fma_mix computed an f32 FMA and converted it to f16, so a result that lands on an f16 tie after the f32 rounding was rounded twice. RDNA2 rounds the exact product-sum once. They now use the exact f64 path of v_interp_p2_f16 and flush f32 sources like v_fma_mix_f32. They follow the f16 round and denormal fields on hardware, so another f16 mode throws, as packed f16 does. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>		2026-10-10 08:33:43 +02:00
..
recompiler	fix(shader): round v_fma_mixlo_f16 and v_fma_mixhi_f16 once to f16	2026-10-10 08:33:43 +02:00