kragen at pobox.com kragen at pobox.com
Mon Feb 26 19:42:10 PST 2001

"Robert G. Brown" <rgb at phy.duke.edu> writes:
> > On Mon, 19 Feb 2001, Alan Grimes wrote:
> > > Hey, I followed some links off the windoze $2000 site and came across
> > > some 32 way/64gb systems from Unisys! (Xenon)
> . . .
> Way easier to program is even more absurd.  In one sense it exactly as
> easy or difficult to program as it almost certainly is programmed using
> the same basic parallel environment and tools, for example, MPI.  MPI is
> MPI is MPI -- that't the whole POINT of MPI.  Cleanly written MPI code
> should both require about the same effort to develop for any parallel
> environment as the resulting code should in many cases be more or less
> transparently portable (again, that's the whole reason the interface
> library was created).

FWIW, big SMPs will tend to do shared-memory things more efficiently
than machines that actually have to pass messages to simulate shared
memory, and some people think writing a threaded program that scales
up to 32 threads is easier than writing an MPI program that scales up
to 32 nodes, or even 4 nodes, depending on the problem.

> Goodness, why does the beowulf concept exist at all, given that this
> [the availability of big expensive proprietary parallel systems] has
> >>always<< been true?

And that's really the point, isn't it?

More information about the Beowulf mailing list