[MPlayer-users] mplayer benchmark interpretation

[Carl Eugen Hoyos]

Umar Qureshey <umar <at> janteq.com> writes:

> I run mplayer with:
> DISPLAY=:0 ./mplayer -nosound -benchmark 
> -lavdopts threads=4  ./1080p30_low_latency.ts

(Complete, uncut console output missing.)

> And I get:
> [h264  <at>  0x75be98]Missing reference picture, default is 0
> [h264  <at>  0x75be98]decode_slice_header error
> [h264  <at>  0x75be98]mmco: unref short failure
> Movie-Aspect is 1.78:1 - prescaling to correct movie aspect.

> VO: [x11] 1920x1080 => 1920x1080 Planar YV12

x11 is typically not very useful, or are you 
on a system where nothing else is useful?
(useful are xv, gl_nosw and vdpau)

> [swscaler  <at>  0x82d278]No accelerated colorspace 
> conversion found from yuv420p to rgb565le.

(Did Reimar and I guess correctly that you are on arm?)

> BENCHMARKs: VC:   1.590s VO:  48.035s A:   0.000s 
> Sys:   0.567s =   50.193s
> BENCHMARK%: VC:  3.1679% VO: 95.7016% A:  0.0000% 
> Sys:  1.1304% = 100.0000%
> 
> It looks like VO is taking 95% of the processing.
> Would it be correct to assume that colorspace 
> conversion is taking most of these cycles since 
> it's being done in software?

Reimar will hopefully correct me but I thought that 
x11 (when fed with rgb16) does not need additional 
colourspace conversion, but the filtering may be 
part of the "VO:" in this statistic.

And yes, in theory opengl would accept yuv420p and 
convert using shaders.

Carl Eugen