Beowulfs can compete with Supercomputers

[Kragen Sitaker]

Greg Lindahl writes:
> > Also, speaking of weather prediction, des anyone know of any recent
> > advances in getting the shallow-water model to perform well on
> > a cluster?  I was always under the impression that this was a big
> > sticking point for some of the more complex models.
> 
> I may reveal my ignorance here, but:
> 
> Shallow water models are not cache friendly, so the usual problem is that
> they run only as fast as main memory does. Vector machines mostly have
> relatively good main memory systems, so there's a strike against non-vector
> systems. Shallow water models are nicely MPI-friendly, but since they're
> shallow, they often don't have very much data, which is a strike against
> slower interconnects.
> 
> Most clusters have both strikes. They're cost effective, but the absolute
> performance level may not be what you want.

Vector machines and the MTA are going to survive Beowulf, I think; they
are good at some things Beowulfs are not good at, and they are easier
to program.

Massively parallel machines like the T3E (which is a bunch of Alphas!)
are going down.  They're slightly better at Beowulf stuff than
Beowulfs, but they cost too much, and they suck at the same things
Beowulfs suck at.

Keep in mind that all of the above is based on hearsay: reading
marketing littrachaw and convussations on this list, not actual
experience of my own.  :)

-- 
<kragen at pobox.com>       Kragen Sitaker     <http://www.pobox.com/~kragen/>
The Internet stock bubble didn't burst on 1999-11-08.  Hurrah!
<URL:http://www.pobox.com/~kragen/bubble.html>
The power didn't go out on 2000-01-01 either.  :)