marfrit/fresnel-fourier
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

iter33: MPEG-2 closed (libva==kdirect bit-exact) — 5/5 codecs PASS

Browse Source 
After VP8 fix landed, ran 5-codec libva-vs-kdirect anchor sweep.
All 5 codecs produce byte-identical libva and kdirect output:
  h264   sha=dd4f5f2d552c07bc
  hevc   sha=108f925bb6cbb6c9
  vp9    sha=cf35908ae0f9ab60
  vp8    sha=d3231e5b6c0ee10b
  mpeg2  sha=95c5905890c937d4

MPEG-2 HW output (libva and kdirect agree) differs from libavcodec
SW MPEG-2 by ~1 LSB per ~67 pixels — hantro IDCT precision artifact,
not a libva bug. Effectively 5/5 PASS for libva correctness contract.
This commit is contained in:
Markus Fritsche
2026-05-14 16:40:05 +00:00
parent 51eee192b8
commit cd2d077cb6
1 changed files with 8 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files
phase8_iteration33_close.md
+8 -4
View File
@@ -14,9 +14,11 @@ Unblock VP8 through libva backend → hantro. Pre-existing libva single-device p
| HEVC 10F | PASS | 108f925bb6cbb6c9 |
| VP9 10F | PASS | cf35908ae0f9ab60 |
| **VP8 10F** | **PASS** (iter33 α-30) | d3231e5b6c0ee10b |
| MPEG-2 10F | FAIL (separate bug) | libva=95c5905890c937d4 sw=933b744134e47ba4 |
| MPEG-2 10F | PASS (libva==kdirect bit-exact) | libva=95c5905890c937d4 kdirect=95c5905890c937d4 |
4 of 5 codecs PASS byte-equal SW.
**5 of 5 codecs PASS** for the libva-correctness contract (libva backend output bit-equal to kdirect reference path).
4 of 5 also bit-equal to SW reference. MPEG-2's HW decoder (hantro) differs from libavcodec SW MPEG-2 by ≤1 LSB per ~67 pixels (mean=0.01, max=1) — IDCT precision artifact, not a libva bug. Both libva and kdirect HW paths produce identical bytes through hantro.
### Root cause for VP8
@@ -66,9 +68,11 @@ VAAPI's `pic_fields.bits.key_frame` is INVERTED (0 = keyframe per VP8 spec conve
Source: backend commit `7e0848d`.
### MPEG-2 (surfaced, deferred to iter34)
### MPEG-2 (closed in same iteration)
Same libva → hantro path. Decodes to non-zero output but byte-different from SW for all 10 frames. Likely a similar ffmpeg-vaapi-strip / OUTPUT-mismatch as VP8, possibly with different offset semantics for MPEG-2. To investigate in next iteration.
Surfaced as "fail" against SW, but libva-vs-kdirect comparison showed both HW paths produce BIT-EXACT EQUAL output (sha=95c5905890c937d4). MPEG-2 decode through libva works correctly. The HW-vs-SW byte divergence is a hantro IDCT precision difference vs libavcodec's exact IDCT (mean diff = 0.01 byte, max = 1 byte, ~1.5% of bytes nonzero). Not a libva bug, not a fixable bug at this level.
No iter34 needed for MPEG-2.
### Substrate state at iter33 close