AlexandClaude Sonnet 5.5 de54527a8b fix(shader): keep f32 denormals in compares when denormals are kept ...

With the f32 denormal field of FLOAT_MODE set to keep, v_cmp_X_f32 and
v_cmpx_X_f32 read a denormal operand as zero: NVIDIA, RADV and lavapipe
all flush denormals in their float compares. Compare the operands as
sign-magnitude integers instead, with NaN handled apart. Compares with
flushed denormals are unchanged. This matches RDNA2 (gfx1036) on 256
operand pairs per opcode, with f32 denormals kept and flushed.

Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>

2026-10-11 18:51:37 -04:00

..

ARCHITECTURE.md

Merge pull request #419 from MichonGoddijn231849/feat/msaa-targets

2026-10-12 00:01:37 +02:00

BUILD.md

Merge pull request #3836 from nyavana/docs/libs-build-testing-refresh-20261011

2026-10-12 00:09:13 +02:00

CONVENTIONS.md

refactor(docs): separated user and dev in docs + compatibility file

2026-09-28 22:58:17 +03:00

HW_ORACLE.md

feat(shader): follow FP16_OVFL in every f16 result

2026-10-10 04:32:38 -03:00

PROGRESS.md

fix(progress): match stub calls across whitespace

2026-10-11 15:06:06 +03:00

TechnicalDebt.md

fix(shader): keep f32 denormals in compares when denormals are kept

2026-10-11 18:51:37 -04:00