Re: Where's lam's mpirun?
Greetings!
Yusuke Tanimura <tanisuke@mikilab.doshisha.ac.jp> writes:
> Hello,
>
> > I'm trying to move the new PETSc package from mpich to lam,
>
> Why?
> The reason is
>
> * a problem for the PETSc itself?
> * you can only use the LAM environments?
> * LAM is superior to MPICH? for PETSc?
> * or other...?
>
About 1.5 years ago, I did some crude benchmarking of lam vs. mpich.
They were about equal for big problems. Lam did significantly better
where latency was an issue, i.e. on small problems. I'm sure the
situation has changed now -- I just have no more recent information.
By the way, did you see all that update-alternatives bug-fix stuff?
Do our alternatives work right now?
> I'm interested in the performance and usability of LAM and MPICH.
> Is the description of the following paper applied to the latest LAM and MPICH?
>
> Nick Nevin, "The Performance of LAM 6.0 and MPICH 1.0.12 on a Workstation
> Cluster", Ohio Supercomputer Center Technical Report OSC-TR-1996-4
>
> # My question is suitable for this ML...?
>
>
> Y.Tanimura
> University of Doshisha
>
>
> --
> To UNSUBSCRIBE, email to debian-beowulf-request@lists.debian.org
> with a subject of "unsubscribe". Trouble? Contact listmaster@lists.debian.org
>
>
>
--
Camm Maguire camm@enhanced.com
==========================================================================
"The earth is but one country, and mankind its citizens." -- Baha'u'llah
Reply to: