On Wed, 21 Nov 2001, Alan Hourihane wrote: >> I've hypothesized the reason for the slowdown, as being lack of >> proper 2D acceleration being implemented when DRI is enabled, >> checked the sources out to find that that did in fact seem to >> be the case, and now had that confirmed. >> >> Getting MTRR working would be an overall improvement on top of >> that, but if it was working now, it would just make for >> slightly faster unaccelerated 2D, and not accelerated 2D. >> >> Getting the 2D CP stuff implemented that is not implemented right >> now is the next step. I'm at least 30% happy that I know what is >> wrong now. ;o) >> >Mike, you can check this.... > >Use the XAA options to turn off color expansion in the non-DRI case to >see if it proves what your seeing. > >Option "XaaNoScanlineCPUToScreenColorExpandFill"
Ok, I just tried that, and the result was a slowdown duplicated with DRI disabled. I disabled DRI by commenting out the dri and GLcore modules, then restarted X. 2D worked fast as expected. I then added XaaNoScanlineCPUToScreenColorExpandFill as you have suggested above, and restarted again, and indeed, the incredible slowdown returned. So it seems that at least this one 2D accel feature needs to be implemented. Any other recommendations? What applications are used for benchmarking XAA performance, etc? -- ---------------------------------------------------------------------- Mike A. Harris Shipping/mailing address: OS Systems Engineer 190 Pittsburgh Ave., Sault Ste. Marie, XFree86 maintainer Ontario, Canada, P6C 5B3 Red Hat Inc. Phone: (705)949-2136 http://www.redhat.com ftp://people.redhat.com/mharris Red Hat XFree86 mailing list: [EMAIL PROTECTED] General open IRC discussion: #xfree86 on irc.openprojects.net ---------------------------------------------------------------------- _______________________________________________ Xpert mailing list [EMAIL PROTECTED] http://XFree86.Org/mailman/listinfo/xpert
