On Wed, Nov 21, 2001 at 03:51:17AM -0500, Mike A. Harris wrote: > On Wed, 21 Nov 2001, Sprague, IT3 wrote: > > >Date: Wed, 21 Nov 2001 07:24:27 -0000 > >From: "Sprague, IT3" <[EMAIL PROTECTED]> > >To: 'Mike A. Harris' <[EMAIL PROTECTED]> > >Cc: "'[EMAIL PROTECTED]'" <[EMAIL PROTECTED]> > >Content-Type: text/plain > >Subject: RE: [Xpert]Radeon 2D accel very slow when DRI is enabled. > > > >No MTRR? That could be a significant percentage of it. I've got a > >semi-similar setup (32MB DDR Radeon, 768MB PC133 system RAM, 1.2GHz Athlon, > >KT133 chipset, AGP 4x, 256MB aperture), and while I do notice a few XAA > >items being disabled, I don't see the dragging slowness that you mention, > >DRI or no. > > MTRR makes no difference, because it is non-functional in both > cases. So, that doesn't explain why when DRI is enabled, 2D > takes a dive, and seems to run like it is done unaccelerated. > Again, note that I said 2D is fast with DRI disabled, but slow > with it enabled. > > 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" Alan. _______________________________________________ Xpert mailing list [EMAIL PROTECTED] http://XFree86.Org/mailman/listinfo/xpert
