Shengyu Wu aee03ffbb2 feat(rvv-hal): optimize FAST pre-screen with deferred u8mf2 widening ...

Defer the u8→i16 widening (vzext) in the pre-screen phase until after
the quick-reject check passes. This avoids 5 unnecessary widen
operations per pixel-strip when the pre-screen rejects (which happens
~70-80% of the time at the default threshold=20).

The approach uses u8mf2 (same VL as i16m1) for the pre-screen
comparison with vssubu/vsaddu for bounds and vmsgtu for unsigned
comparison. When the pre-screen passes, the already-loaded u8mf2
variables are widened to i16m1 for the score computation, reusing
the same data without redundant memory loads.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

2026-05-31 20:49:30 +08:00

..

include

Merge pull request #28887 from milllemonman:4.x

2026-05-06 16:05:28 +03:00

src

feat(rvv-hal): optimize FAST pre-screen with deferred u8mf2 widening

2026-05-31 20:49:30 +08:00

CMakeLists.txt

Merge pull request #27391 from Haosonn:pr-rvv-hal-fast

2025-08-11 13:03:34 +03:00

rvv_hal.hpp

Merge pull request #27391 from Haosonn:pr-rvv-hal-fast

2025-08-11 13:03:34 +03:00