Xvideo performance on Radeon 7500 vs Intel 915

Ken Mandelberg km at mathcs.emory.edu
Sun Dec 3 09:29:57 PST 2006


I tried out the final patch. Didn't see any bug.

It seems like it might have helped performance a bit. I ran a before and 
after on a 4 minute 1080i clip on my Radeon 7500 Penitum 4 (2GHZ)

    mplayer: user: 125sec sys:  4 secs real:198
    Xorg:    user:  50sec sys: 33secs

    mplayer: user: 124sec sys:  3secs  real:198
    Xorg:    user:  34sec sys: 32secs

So unless there is a statistical anomaly here, it seems to have reduced 
the user space cpu time of Xorg by about 30%.

Still it doesn't perform well enough to use except in a pinch because of 
frame drops (about 30%) . I guess the hardware is just not up to the 
task for HD, especially 1080i.

For comparison with my Intel 915-Pentium M (2GHZ) on the same clip

    mplayer: user: 116sec sys:  3secs  real:249
    Xorg:    user:  2sec sys:   0secs

Roland Scheidegger wrote:
> Roland Scheidegger wrote:
>> Ok, here's a newer version which applies cleanly to git head. It has
>> most problems ironed out, with the exception that moving a video window
>> beyond the screen border still causes ugly things (bogus video if moved
>> to the left, bogus video and segfaults if moved to top). I'm wondering
>> why and how that can work for the other formats...
> Here's my final word on this. Declared 100% bug-free :-). Someone wants
> to test it on big-endian (I don't think there should be a problem but
> you never know...) or with odd-shaped, err, odd-sized videos?
> Roland

More information about the xorg mailing list