[FFmpeg-devel] [PATCH] VP8 coeff decoding optimizations

[Jason Garrett-Glaser]

Attached are two mutually exclusive VP8 optimization patches.

Approach in #1 (test.diff): simplify addressing by eliminating vp8_coeff_band
Advantage: one less dereference, seems to be slightly faster, but
might depend on the mood of gcc
Disadvantage: more cache usage

Approach in #2 (test3.diff): simplify addressing by making the
probability table single-dimensional and merging the complex
addressing logic into vp8_coeff_band
Advantage: trivial addressing
Disadvantage: still has the dereference, and a bit ugly (probably fixable)

Thoughts?

Dark Shikari
-------------- next part --------------
A non-text attachment was scrubbed...
Name: test.diff
Type: application/octet-stream
Size: 4129 bytes
Desc: not available
URL: <http://lists.mplayerhq.hu/pipermail/ffmpeg-devel/attachments/20100802/ce4b64ee/attachment.obj>
-------------- next part --------------
A non-text attachment was scrubbed...
Name: test3.diff
Type: application/octet-stream
Size: 4116 bytes
Desc: not available
URL: <http://lists.mplayerhq.hu/pipermail/ffmpeg-devel/attachments/20100802/ce4b64ee/attachment-0001.obj>