[TriLUG] Building a beowulf (or other) cluster

Phillip Rhodes motley.crue.fan at gmail.com
Sat Apr 2 20:50:04 EDT 2011


I think the previous answers hit all the high points... as you can see,
there
are a lot of different ways to solve this problem in a distributed fashion.
 I'll
just throw in this thought:  from what you've said, a full fledge Beowulf
cluster and MPI programming, etc. strikes me as overkill.  I have
a feeling that GNU Parallel would, indeed, work well for you.

I'll also point out two other area resources that might be of interest:

Triangle Hadoop User's Group:
http://www.trihug.org

RTP AI / Machine Learning / SemWeb / BigData Meetup:
http://www.meetup.com/RTP-AI-ML-SemWeb/

Also, a coupe of us at SplatSpace have been chewing on the idea of setting
up a cluster to experiment / play / learn distributed / parallel
development.
It's not definite yet, but if anyone is interested in getting involved with
that,
give us a shout.


Phil



More information about the TriLUG mailing list