On Sun, 10 Aug 2003 14:07:16 -0700 (PDT) Mark Vojkovich <[EMAIL PROTECTED]>
babbled:
> On Sun, 10 Aug 2003, Carsten Haitzler wrote:
>
> > On Sun, 10 Aug 2003 05:59:54 +0100 Alan Hourihane
> > <[EMAIL PROTECTED]> babbled:
> >
> > > On Sun, Aug 10, 2003 at 02:27:13PM +1000, Carsten Haitzler wrote:
> > > > Would I be correct in the assumption that the only accelerated path for
> > > > xrender is the identity transform (1:1 scale)? all other transforms are
> > > > done in software? (my initial tests here with xfree86 4.3.0 & nvidia's
> > > > latest drivers(as of about a month ago) seem to indicate as much...)
> > > > (and yes... my drivers are using acceleration... GL definitely is). ?
> > >
> > > No. About 99% of the drivers don't have any xrender acceleration. I think
> > > only the mga driver does. Although looking furthur the sis has some, but
> > > it seems disabled, and the vmware driver has it too. But that's it.
> > >
> > > I guess nvidia do some acceleration in their binary drivers though, as
> > > you've probably found. But it's bad to assume other drivers have xrender
> > > acceleration.
> > >
> > > I think the thing that's holding other drivers up in getting furthur
> > > xrender acceleration is that there's no test suite to check that the
> > > driver is doing the right thing. I think Keith Packard mentioned he had
> > > intern's working on a test suite a while ago, but nothing has materialized
> > > as far as I know.
> >
> > hmmm - well i could write a performance suite here... if that helps. so far
> > as in my other e-mail, the "hardware acceleration" provides by the nvidia
> > drivers so far manages to be 1/35th the speed of my own mmx asm blending
> > routines... this is blending with 1:1 scaling (no transform).
>
> You're not hitting hardware paths. If you want to see this stuff
> in hardware there's going to need to be a correctness test suite. I'm
> already accelerating more than I can test. That worries me, and is
> why render acceleration is off by default in recent NVIDIA drivers.
ooooh! it's OFF! i understood i'ts on - 1:1 blending of 32it ARGB onto a 24bpp
RGB destination i s the most obvious (and easy) case so of all of them i'd
assume that hits hardware... but since it's disabled... no wonder! now that
begins to explain thins.
> > i just tested a quick scaling test and the software routines i have are 41
> > times faster than xrender... there is something suspicious here...
> >
> > a quick rundown:
> > my software routines are in imlib2.
> > machine is amd 1.7ghz
> > gfx is nvidia gf4 4400ti 128mb
> >
> > NVAGP is set to 0 cause it manages to lock up my kernel regularly :(
> >
> > this is xfree 4.3.0
> > nvidia drivers:
> >
> > NVIDIA_kernel-1.0-4191
> > NVIDIA_GLX-1.0-4191
>
> I thought you said you were using recent drivers. There's been
> two releases since then. There are known render bugs in 4191.
well recent as in i updated only month or 2 ago... :)
> > well there goes my plans for
> > a project to do an xrender display engine... opengl still is the big winner
> > :)
> >
>
> OpenGL reflects what the hardware can do, and has a compliance test
> suite. RENDER doesn't reflect hardware capabilities very well (it
> reflects what end users wanted to see in an API) and there's no
> compliance tests. Stick with OpenGL.
well opengl is next on my hit-list. i just wanted to try xrender first, but it
doesn't look like it's a worthwhile pursuit. opengl for me has other major
benefits, like portability :)
though i've said it before, xrender really should be an easily accessible 2d
subset of opengl and pixel-exact rendering as it defines limits the ability to
accelerate it - either with tricks in software (by losing 1 bit of precision you
can double the speed in some cases), or with hardware. what people want to see
IMHO is fast redraw of blended/scaled objects on things like the desktop or
within web browsers etc. but if it isn't fast there's going to be a big
resistance in migrating to use it.
--
--------------- Codito, ergo sum - "I code, therefore I am" --------------------
The Rasterman (Carsten Haitzler) [EMAIL PROTECTED]
熊耳 - 車君 [EMAIL PROTECTED]
Mobile Phone: +61 (0)413 451 899 Home Phone: 02 9698 8615
_______________________________________________
Devel mailing list
[EMAIL PROTECTED]
http://XFree86.Org/mailman/listinfo/devel
