[Mplayer-users] mp3 downsampling/mixing? (again)

Christoph Lampert lampert at math.chalmers.se
Wed Aug 15 13:45:45 CEST 2001

>> Why is audio decoding faster with -hardframedrop? Audio is not skiped, is it?
>it is not faster/slower. (no audio skipped)
>but all CPU usage times are compared to video times, so if A-V is out of
>sync (video playback is slower than realtime), they will show false results!
>Btw not so false, but they mean "how many % of cpu required for playback
>without A-V desync". this way you can get >100% values, it means that you
>need xx% more cpu to get synced playback.

Nope, I did not mean audio %age, I meant absolute values in seconds!

noframedrop:  V:  27.369s VO:   0.002s A:   2.341s Sys:   3.787s =   33.498s
hardframedrop V:  25.736s VO:   0.008s A:   2.107s Sys:   5.510s =   33.360s

noframedrop:  V:  27.210s VO:   0.003s A:   1.648s Sys:   4.784s =   33.646s
hardfraemdrop V:  25.852s VO:   0.014s A:   1.501s Sys:   5.963s =   33.330s

It's not much, but the effect is stable. Audio goes down a little, also if I 
rerun. Maybe it's a cache effect or just timing problem...


Dipl. math. Christoph Lampert (complex analysis, integral formulae)
Email: gruel at gmx.de                |     Email: lampert at math.chalmers.se

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

More information about the MPlayer-users mailing list