[Mplayer-users] i586 vs. i686

Christoph Lampert lampert at math.chalmers.se
Thu Jun 14 17:04:19 CEST 2001


great benchmark option. Can you put the 1800.avi to some download space on the 
ftp-server? Then the benchmark can be make a "standard". Or is it already?

What other file formats are useful for benchmarking? MPEG1/2 is native codec, so 
it might be interesting? Testing with the Win-DLLs does not show much?

What about that "video output" benchmark that you talked about some time ago, 
just printing out (empty? random?) pictures at maximum possible speed to test 
performance of different -vo's ?

Cool, in the end mplayer could get a "genetic algorithm", that determines best 
setting for compile and play based on real performance, not on religion. :-))) 
Compiling and configuring takes 2 weeks, but after that your system is really at 
it's limit. Is there an "genetic autoconf"? 


P.S. I know the answer already: "Send a patch, if you want all that..."

>Ok. I've just did this benchmark, using teh brand-new -benchmark option:
>-rw-rw-rw-   1 root     root      2087466 Jan 30 10:21 1800.avi
>mplayer -osdlevel 0 -nosound -benchmark 1800.avi -vo null -pp 15
>VIDEO:  [divx]  640x352  24bpp  23.98 fps  1865.1 kbps (227.7 kbyte/s)
>[V] filefmt:3  fourcc:0x78766964  size:640x352  fps:23.98  ftime:=0.0417
>Found video codec: [odivx] drv:3 (OpenDivX (MPEG-4 v2))
>VO: [null] 640x352 => 640x352  YV12

Mplayer-users mailing list
Mplayer-users at lists.sourceforge.net

More information about the MPlayer-users mailing list