New acceleration architecture

[Jon Smirl]

On 6/27/05, Jim Gettys <Jim.Gettys at hp.com> wrote:
> > > Will Xglx run on glide? Have you tried xtank on Xglx? If it is close
> > > to working DaveR will probably fix it. It would be interesting to
> > > compare if everything is working.
> >
> > Irrelevant.  Core X lines have a pixel-precise spec.  GL lines do not.  If you
> > implement X lines with GL lines you will not conform.  Which means they'll be
> > done in software in xgl, so they'll be roughly as fast as in kdrive and exa.
> 
> Huh?  0 width core X lines have a specification so wide that you can
> drive a truck through it.  Any thing that goes from one end to the other
> qualifies; its problem is the spec is useless.
> 
> It is only wide lines that have a (broken) pixel precise specification,
> that generates ugly results, and therefore wide lines are almost
> entirely unused.

Can we all make a promise never to write specs again that require
pixel precise drawing algorithms? The hardware is never going to match
the spec and multiple vendors will probably implement things
differently. I just love the concept of buying a $400 highly
accelerated graphics card and then ignoring it because it's drawing
algorithms don't match the spec. We need to figure out how to live
with these cards, they are not going away.

BTW, there have been articles stating that both NVidia/ATI are looking
at removing the 2D core from their chips in the next generation or
two. If you look at a floor plan for their current chips the 2D core
take up way less than 5% of the transistors. Removal of the 2D core
can be dealt with in the VBIOS on Windows.

-- 
Jon Smirl
jonsmirl at gmail.com