Beowulf in a Box

[Robert G. Brown]

On Mon, 28 Sep 1998, Douglas Eadline wrote:

> While I encourage such efforts, I have my reservations as to
> the economic success of such an approach.  Let me explain a bit.
> Please consider me the "devils advocate" so that I can make your idea
> stronger by providing my reservations based on my experience.

   <text deleted>

> Well there are some things to consider.  I tried to give
> some objective experience that may help you "fine tune" your strategy. 
> It is not my goal to say "this will not work (because I have no
> idea if it will or not)", but rather, "push your idea a little".

Well said, Doug!  It encapsulates a considerable portion of the
motivation of the beowulf project and its reliance on commodity
hardware.  This also points the "right" (read: scalable and
extensible) direction for designers who don't want to become a niche.

Define your problem carefully, make sure that your proposed solution
solves an important and common problem (and not one of interest only in
a narrow niche) and is within the capabilities of your commodity
hardware base (e.g. the motherboard, the PCI or memory channels
themselves).  Develop your solution openly with open standards -- earn
your market dominance by your contributions to the idea and head start,
not by keeping it all to yourself via patent or copyright.  Finally,
when you finally go to market, sell it cheap!  View it as a loss leader
-- the real money comes when your product becomes a standard, not from
selling to a small, specialized market that one day is overtaken by
commodity items via Moore's Law, if nothing else.

   rgb

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@phy.duke.edu