new to the game ( Jörg Kaduk)

[Christopher Dickson]

hi joerg,

Here are some sites that have some general introductions to cluster
computing:

http://www.spade.com/linux/howto/Parallel-Processing-HOWTO.html
http://yara.ecn.purdue.edu/~pplinux/ppcluster.html

>   Where should I look to get info about the problems involved and
>   to research the questions. Is PVM the only way for this kind of
>   problem?

There are two main packages that support shared memory and distributed
shared memory, MPI and PVM -         

MPI sites

http://www-unix.mcs.anl.gov/mpi/index.html
http://www.mpi-forum.org/

PVM sites

http://www.epm.ornl.gov/pvm/

Since i'm not really using these i can't tell you such about them. thou
IBM is the one of the main supports of MPI with the SP project.  Both MPI
and PVM work on a heterogenous cluster.

Currently i'm doing datamining using a cluster of nondedicated
Workstations connected by basic ethernet.  This is a cluster of linux
boxes, NT boxes and even G3 macs for parallel processing.  

For this i'm using a client/server architecture built in python using
sockets (TCP/IP).  On the datamining side of things i'm using C.

A couple of questions, what are planning on using this cluster for? and
are the computer nodes dedicated or nondedicated i.e. is some else using
them as well.


Anyway have fun,

chris.

Free software is artificial life, but better.