[geeks] New Itanium machines from SGI

[Joshua D Boyd]

On Wed, Jan 08, 2003 at 07:58:15PM -0700, Chris Byrne wrote:

> > That is very non-trivial.  You might be able to get away with it on a
> > machine like the Onyx or Octane, assuming that you can figure out how
> > [0], but it is not easy for PC cards.
> > 
> > First, you need to figure out how to make the video card do a bunch of
> > work before reading it back or else you will severely saturate AGP on
> > readbacks.  So, you have so hope with pixel and vertex shaders, except
> > those are very limited as to program size.
> >  
> 
> I know this. What Im asking is WHY don't we design these things to
> either spread the loads out better, or effectively use them. Oh and I
> know for a fact you can do this with the high end SGI boxen because I've
> seen it done for cryptoprocessing. I couldn't tell you exactly how it
> was done, Im not much of a coder, but they said they got a 20-40% boost
> in their crunching.

SGIs are nice that way.

> Honestly a lot of them are getting more and more general purpose as they
> become more reprogrammable. Same thing applies to video cards with the
> programmable shaders etc...

Programable shaders are definately getting more powerfull.  Now if only
they had something better than AGP in between them and the ram.  I
really think it would have been nicer if Apple would have ignored AGP
and stuck with PCI for video cards.  But, perhaps nvidia and ATI were
just refusing to continue doing PCI 66/64 cards for them.
 
> I agree whole heartedly. Its not so much the core of the language but
> the programming practices that have been ingrained in our programmers.
> Theres really one basic problem. Ever since the 66 mhz level we have
> decided that machine time is far cheaper than developer time. So people
> arent coding the new libraries or making the older ones more efficient,
> they're just resuing the same old code. And as you point out even if
> they wanted to they have too many tasks to make them cross platform and
> it takes too much budget to be able to do separate implementations for
> each.

Well, my theory is that it is better to get your code written first,
then worry about speed later.  Mainly because if I don't, things won't
get done.  However, having libraries take care of things in a smart way
is always worth while.  

-- 
Joshua D. Boyd