Indeed, PVM can also run a single parallel job across a heterogeneous
cluster. But I know that mpich can't do that for MPI parallel jobs
(http://bugs.debian.org/31779), and I don't believe lam can either.
On Wed, 2005-10-19 at 14:37 +0100, Dominik Kasprzyk wrote:
> As the previous poster said, if you can install nfs, nis and services like that, then the only thing preventing you is the job manager. Below is a link to condor which is designed to work on non-homogeneous clusters and may meet your needs.
> Dominik Kasprzyk.
> On Tue, 18 Oct 2005 17:12:31 -0400
> Blubaugh David A Civ AFRL/PRPG <David.Blubaugh@wpafb.af.mil> wrote:
> > To Whom It May Concern,
> > I was wondering if there is a way to combine old SGI machines, such as the
> > O2 and indy workstations, along with old pentium class computers into a
> > beowulf cluster supercomputer? Any help will be appreciated!!!
> > Sincerely,
> > David Blubaugh
GPG fingerprint: D54D 1AEE B11C CE9B A02B C5DD 526F 01E8 564E E4B6
Welcome to the best software in the world today cafe!
- Re: sgi
- From: Konstantinos P <firstname.lastname@example.org>
- From: Blubaugh David A Civ AFRL/PRPG <David.Blubaugh@wpafb.af.mil>
- Re: sgi
- From: Dominik Kasprzyk <email@example.com>