<!DOCTYPE html PUBLIC "-//W3C//DTD HTML 4.01 Transitional//EN"> <html> <head> <meta content="text/html;charset=UTF-8" http-equiv="Content-Type"> <title></title> </head> <body bgcolor="#ffffff" text="#000000"> Michel Dänzer wrote: <blockquote cite="mid1164624572.5723.335.camel@thor.sulgenrain.local" type="cite"> <pre wrap="">On Sun, 2006-11-26 at 19:00 -0500, Ken Mandelberg wrote: </pre> <blockquote type="cite"> <pre wrap="">xine with -V xxmc PID USER PR NI VIRT RES SHR S %CPU %MEM TIME+ COMMAND 32291 km 15 0 223m 46m 28m S 53.6 6.1 0:25.60 xine 3954 root 16 0 197m 84m 46m R 28.3 11.1 7:37.75 Xorg With xv and xshm there is 0 idle. With xxmc there is about 15% idle, but in all three cases it drops frames (xshm is the worst). </pre> </blockquote> <pre wrap=""> The radeon driver doesn't support XvMC, so this is a little weird. Probably xine falls back to another output. </pre> </blockquote> Xine's xxmc driver falls back to Xv when it cannot use hardware decoding acceleration for a video stream, but it normally doesn't use as many frames in the frame queue as the Xv driver does, and may not enable the same deinterlacing. This could perhaps explain the difference. <blockquote cite="mid1164624572.5723.335.camel@thor.sulgenrain.local" type="cite"> <pre wrap=""></pre> <blockquote type="cite"> <pre wrap="">(II) RADEON(0): Will try to use DMA for Xv image transfers </pre> </blockquote> <pre wrap=""> Does Option "DMAForXv" "off" make any difference? </pre> <blockquote type="cite"> <pre wrap="">By the way I'm using your pre-downscale patch to get around the 1536 pixel scaling limitation (pink bar). The quality seems ok (at least on the notebook lcd), and I saw the HD performance problem without it. Also, I tried moving down to 16 bit depth from 24 and didn't see a difference. </pre> </blockquote> <pre wrap=""> This all makes sense, as the bottleneck is probably the transfer from system RAM to video RAM. Integrated chipsets actually have an advantage there. </pre> </blockquote> I agree. /Thomas </body> </html>