[FFmpeg-devel] ZMBV Improved Motion Estimation

[Michael Niedermayer]

On Sun, May 11, 2008 at 11:45:31AM -0700, Jason Garrett-Glaser wrote:
> > probably its that histogram is uint8_t and thus 256==0
> 
> I'm not sure if uint16_t is going to be slower or faster than uint8_t
> or uint32_t.

uint16_t should be slower than uint8_t, it needs twice as long
to be set to 0.

if(histogram[0] || src[-stride]!=src2[-stride2])
    sum += 256*(bw*bh - histogram[0]);
return sum;

should achive the same without the larger memset()
(actually iam not sure if gcc memsets the array properly or does something
stupid, if uint16_t is not slower then a memset() instead of ={0} is likely
much faster)

[...]
-- 
Michael     GnuPG fingerprint: 9FF2128B147EF6730BADF133611EC787040B0FAB

Awnsering whenever a program halts or runs forever is
On a turing machine, in general impossible (turings halting problem).
On any real computer, always possible as a real computer has a finite number
of states N, and will either halt in less than N cycles or never halt.
-------------- next part --------------
A non-text attachment was scrubbed...
Name: not available
Type: application/pgp-signature
Size: 189 bytes
Desc: Digital signature
URL: <http://lists.mplayerhq.hu/pipermail/ffmpeg-devel/attachments/20080511/ce657272/attachment.pgp>