[FFmpeg-devel] [PATCH] move h264 loopfilter strength code to yasm

Ronald S. Bultje rsbultje
Fri Sep 24 18:04:11 CEST 2010


On Thu, Sep 23, 2010 at 6:13 PM, Ronald S. Bultje <rsbultje at gmail.com> wrote:
> $subj. This could likely be done in inline asm as well but I still

Attached patch #1:
1) unrolls loop (allows inlining of a lot more, saves registers/stack
after: 976 dezicycles in lf-strength, 4194102 runs, 202 skips
before: 1164 dezicycles in lf-strength, 4194083 runs, 221 skips

(the yasm version was ~86 cycles, which I hope to eventually reach by
eliminating the pand and the mask_dir variable, merging edge and
b_idx, etc.)

So removing pand (which doesn't do anything in the one case, and can
be replaced by a pxor in the other). With the attached patch #2, I get
register name `%%mm0'
register name `%%mm0'

What does that mean?

-------------- next part --------------
A non-text attachment was scrubbed...
Name: fix-lfstrength-inline-asm.patch
Type: application/octet-stream
Size: 2946 bytes
Desc: not available
URL: <http://lists.mplayerhq.hu/pipermail/ffmpeg-devel/attachments/20100924/ddb885c0/attachment.obj>
-------------- next part --------------
A non-text attachment was scrubbed...
Name: fix-lfstrength-inline-asm2.patch
Type: application/octet-stream
Size: 883 bytes
Desc: not available
URL: <http://lists.mplayerhq.hu/pipermail/ffmpeg-devel/attachments/20100924/ddb885c0/attachment-0001.obj>

More information about the ffmpeg-devel mailing list