Small cluster

[Joachim Worringen]

Garriss, Michael:
> I have a $5000 budget to build a sort of "proof of concept" cluster before
> a larger sum of money gets spent.  Any suggestions on getting the most bang
> for the buck.  The application is a simulation that would benefit from
> parallel computation and lots'o RAM.

Before spending any money, you should know what you want to prove (or are 
expected to do so): that it is possible to connect multiple computers to 
reduce the amount of time required to solve a given problem? Probably not.

I would rather spend $1000 to have someone run the application on their 
cluster, if you have none available. I could do this for you...

  Joachim

-- 
Joachim Worringen - NEC C&C research lab St.Augustin
fon +49-2241-9252.20 - fax .99 - http://www.ccrl-nece.de