Strange speed differences on composite

[Alex Deucher]

On 2/15/06, Dennis Jacobfeuerborn <d.jacobfeuerborn at conversis.de> wrote:
>
>
> Tomasz Torcz wrote:
> > On Tue, Feb 14, 2006 at 12:07:59PM -0500, Adam Jackson wrote:
> >> On Saturday 11 February 2006 14:13, Tomasz Torcz wrote:
> >>> On Fri, Feb 10, 2006 at 07:00:03AM -0500, Owen Taylor wrote:
> >>>> On Thu, 2006-02-09 at 18:55 +0100, Tomasz Torcz wrote:
> >>>>>   The question: how it comes that software-only Xephyr is _faster_ at
> >>>>> drawing shadows than fully hw accelerated X server with mga driver?
> >>>> If you ever have to read data from the frame buffer, that's *slow* -
> >>>> you lose far more than you gain from any hardware acceleration you
> >>>> might be getting.
> >>>   But why read data? Shouldn't it be composed by graphic card in VRAM?
> >>> Isn't that what acceleration is for?
> >> "Acceleration" isn't an all-or-nothing thing.  Almost all the drivers we have
> >> are accelerated to one degree or another.  The issue is that very few of them
> >> accelerate the image composition operations that Render exposes.
> >>
> >> When you do an Over blend in Render, you're computing values for each pixel:
> >
> >  [ .. cut .. ]
> >
> >  Thanks for your profound explanation!
> >
> >> Phrased another way, your assertion above:
> >>
> >>>>> drawing shadows than fully hw accelerated X server with mga driver?
> >> is that the mga driver is fully hardware accelerated.  It's not, it doesn't
> >> accelerate Render in hardware.
> >
> >   Now, this is something that surprised me. I lived under impression
> > that mga actually accelerates everything. Few years back I bought this
> > costly (ati and nvidia cards were 2-3 times cheaper) card _because_ it
> > had open source driver including 3D part. And it was sufficient to play
> > quake3. Somehow I thought 3d == full acceleration. I was wrong all those
> > years :(
> >   Apparently, now I have to wait until Xgl comes to more compilable
> > shape. Or until it will be shipped by my distro (Slackware).
> >
>
> That's actually something that I wondered about recently. How is a user
> supposed to make a decision when he intends to go out and buy a videocard
> for his machine running Xorg? It seems there exists no recommendation from
> Xorg for such a case and given the statements above it doesn't even seem to
> be possible to give one.

Once Xgl is ready, any card with a 3D driver and the appropriate
OpenGL extensions should be able to provide fast rendering.  Right now
is sort of a transitional period and the only xorg driver that
accelerates render (via EXA) is radeon.

Alex

>
> Regards,
>    Dennis