[Beowulf] Beowulf Application in the Sciences

Robert G. Brown rgb at phy.duke.edu
Thu Sep 23 12:38:02 PDT 2004


On Thu, 23 Sep 2004, Michael Will wrote:

> I would love to read something about currently available fast interconnects
> from different vendors. (i.e. Infiniband from Infinicon, Mellanox, Voltaire, ...) 
> and how they are supported by the various beowulf distributions (Rocks, Scyld, ...)
> together with a backgrounder on OpenIB and on which applications require a 
> lot of interprocess communication. (FFT...).
> 
> Sounds like a ressource intensive research task though ;-)

Not at all.  If all of those vendors will generously give me free
samples of all their interfaces and switches, I will make the heroic
sacrifice of putting them into my various toy clusters and testing them
against various distributions and then writing them up.  If they include
free tee shirts and a small wad of unmarked bills, I'll even give them a
GOOD writeup, guaranteed!

See, I'm easy.  I can be bought.

Alas, nobody ever wants to buy, though...;-)

   rgb

> 
> Michael Will
> 
> 
> On Thursday 23 September 2004 06:21 am, Robert G. Brown wrote:
> > On Thu, 23 Sep 2004, Jeff Layton wrote:
> > 
> > > Robert G. Brown wrote:
> > > 
> > > >(Damn, I need to just put these replies straight into my CWM column.
> > > >Kill two birds with one stone, so to speak;-).
> > > >
> > > 
> > > Hey! That's my job! I'm forming a union to protect myself from the
> > > original posters!
> > 
> > Sigh.  Fine, fine, back to the salt mines.  Wonder what to write about
> > for December (already slightly overdue:-).  More networking benchmark
> > tools?  Benchmark tools in general?  wulfware (saving that one for a
> > rainy day;-)?
> > 
> > Work, work, work.  And there is a big grid project in the proposal
> > writing stage here that I'm helping on, and it too is amazingly
> > demanding as we try to wheedle resources from the university to make the
> > NSF happy while utilizing NSF-purchased resources within the university
> > in some way that makes them equally happy strategic-vision-wise.  Happy,
> > happy, happy.
> > 
> > Maybe I'll write about that.  Naaa, that's too depressing and sad a
> > topic and would leave the readers weeping...
> > 
> >    rgb
> > 
> > > 
> > > Jeff
> > > 
> > > -- 
> > > Dr. Jeff Layton
> > > Aerodynamics and CFD
> > > Lockheed-Martin Aeronautical Company - Marietta
> > > 
> > > 
> > 
> > Robert G. Brown                        http://www.phy.duke.edu/~rgb/
> > Duke University Dept. of Physics, Box 90305
> > Durham, N.C. 27708-0305
> > Phone: 1-919-660-2567  Fax: 919-660-2525     email:rgb at phy.duke.edu
> > 
> > 
> > _______________________________________________
> > Beowulf mailing list, Beowulf at beowulf.org
> > To change your subscription (digest mode or unsubscribe) visit http://www.beowulf.org/mailman/listinfo/beowulf
> > 
> 
> -- 
> Michael Will, Linux Sales Engineer
> NEWS: We have moved to a larger iceberg :-)
> NEWS: 300 California St., San Francisco, CA.
> Tel:  415-954-2822  Toll Free:  888-PENGUIN
> Fax:  415-954-2899 
> www.penguincomputing.com
> 

Robert G. Brown	                       http://www.phy.duke.edu/~rgb/
Duke University Dept. of Physics, Box 90305
Durham, N.C. 27708-0305
Phone: 1-919-660-2567  Fax: 919-660-2525     email:rgb at phy.duke.edu





More information about the Beowulf mailing list