MarcelineVQ 61ee4f48e1 bone_sse: f32 callFtol, fastMod conditional subtract for looping anims ...

callFtol: use f32 multiply instead of f64 intermediate. Parity holds --
the delta*scale product is well within f32 precision range.

fastMod: replace integer modulo (idiv, ~25 cycles) with conditional
subtract (~2 cycles) for looping animation frame computation. Falls
back to real modulo for large time skips (alt-tab, etc).

3609 cycles (-14% vs 4176 baseline), parity PASS.

2026-03-16 17:06:20 -07:00

..

decompiled

bone_sse: replace IsParticleBufferEmpty with pure Zig — 1 game call remains (atexit)

2026-03-16 10:45:06 -07:00

ASM_DIVERGENCES.md

bone_sse_ref: fix world entry crash — 6 bugs found via full asm stepthrough

2026-03-15 17:38:14 -07:00

bone_sse_baseline.zig

bench: dual BASELINE/SSE with parity check — 2177 vs 2112 cycles, PASS

2026-03-16 12:10:51 -07:00

BONE_SSE_PROGRESS.md

bone_sse: assembly-verified reimplementation of transformMatrix4x4

2026-03-14 17:34:37 -07:00

bone_sse_reference.zig

bone_sse_ref: fix world entry crash — 6 bugs found via full asm stepthrough

2026-03-15 17:38:14 -07:00

bone_sse.zig

bone_sse: f32 callFtol, fastMod conditional subtract for looping anims

2026-03-16 17:06:20 -07:00

clip_sse.zig

Add SSE multiplyMatrix4x4 hook (0x7bc6a0) with A/B benchmark — 4.3x speedup

2026-03-12 18:44:02 -07:00

OPTIMIZATION_RESEARCH.md

bench: 2M iterations, baseline 4176 cycles, SSE 3841 (-8%), parity PASS

2026-03-16 15:25:00 -07:00

RESEARCH.md

Add ReleaseFast SSE build unit, weather override Lua API, and research notes

2026-03-12 18:46:54 -07:00

SCENEOBJECT_OFFSETS.md

WIP: bone_sse SSE reimplementation of transformMatrix4x4 + OnWorldUpdate frame counter

2026-03-14 00:22:36 -07:00

timer_fix.zig

Move file cache to standalone module, add timer fix, fix refcount crashes

2026-03-14 14:57:58 -07:00

transform44.zig

bone_sse: clean A/B testing, remove diagnostic comparison code

2026-03-16 10:18:35 -07:00