[Beowulf] Differenz between a Grid and a Cluster???

Mark Hahn hahn at physics.mcmaster.ca
Wed Sep 21 11:16:27 PDT 2005

> > grids are based on the absolutely mistaken premise that computing 
> > is commodified and generic.  you just arrange the plumbing and the 
> > flops will flow to whereever they're needed.  I've never quite been
> > clear on whether gridophiles believe this, and understand that there
> > are different instruction sets, different cache sizes, different clocks,
> > different sizes and speeds of memory, etc.  maybe they're simply 
> > comfortable working with the least common denominator - a portable 
> > language like java/perl/etc and nothing but embarassingly parallel codes.
> A nice use case is to use grid stuff to get a uniform way to access
> preinstalled applications, locally tuned according to the
> idiosyncrasies of the local systems.

oh, absolutely.  in this case, a "grid" is just an application farm.
and I'm sure there's lots of demand for that.  but it assumes that your
apps change very slowly or you have a _horde_ of very effective admins
who can make all the grid nodes look basically identical to the app.

I guess I should have mentioned that my own context is academic/research
HPC, where nearly every job runs a unique executable, and for the most part,
the only "applications" installed are compilers ;)

that's not entirely true - we have some users who run Gaussian, but they
tend to be fairly limited in number.  our focus is actually to get
researchers to think bigger, which usually means they can't use some 
off-the-shelf app.

in that way of thinking, grids make a lot of sense as a shrink-wrap-app farm.

regards, mark hahn.

More information about the Beowulf mailing list