 marfrit
|
b5fdb5e854
|
iter1 phase3: baseline measurements
C1-C6 measured for all 3 in-scope codecs on ampere RK3588 with the
hand-built libva backend over a clean v7.0-rc3 + ampere DTS kernel.
C1 (decode completes): PASS all 3 — 30-frame decodes produce
41 472 000 B NV12 exactly (30 × 1280 × 720 × 1.5).
C2 (HW engagement via strace ioctl trace): PASS all 3 —
VIDIOC_S_EXT_CTRLS + VIDIOC_QBUF/DQBUF + MEDIA_REQUEST_IOC_QUEUE
counts unambiguous. lsof poll lost race (script bug; non-fatal).
C3 (frame 0 byte-identical vs SW reference): PASS all 3 — same SHA
3214803d8be74416 across codecs (same source I-frame, both SW
and HW agree).
C4 (frame 720 / t=30s SSIM Y >= 0.99): split —
VP8 SSIM 1.000 (byte-identical), MPEG-2 SSIM 0.9997 (IEEE 1180),
H.264 SSIM 0.6676 (cumulative GOP drift, mirrors fresnel iter1).
Phase 4 must refine C4 to per-codec SSIM floors.
C5 (FPS N=3 with sigma): PASS all 3, tight sigma.
H.264 461±0.6 fps, VP8 217±0.6 fps, MPEG-2 199±0.7 fps.
C6 (clean dmesg): PASS — empty diff pre vs post sweep.
C7 (firefox-fourier vendor-defaults): NOT RUN — no Wayland session
on ampere (SDDM greeter only). Rig-blocked, documented.
Phase 1 hypothesis upheld: substrate is sound, codec works, no
backend regression. H.264 SSIM is decoder drift (per fresnel
precedent), needs C4 refinement, not loopback.
Scripts archived in phase3_scripts/ for reproducibility.
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
|
2026-05-16 07:24:19 +00:00 |
|