Internetworkers: http://www.ibiblio.org/internetworkers/

[Roger Austin <raustin3 AT nc.rr.com>]

zman wrote:
> On Wed, 28 Jan 2004, Jeffrey Gordon wrote:
>
> > Actually, these folks are wasting a LOT of money.  I am glad I'm not a VT
> > student or alum being asked to foot the bill.
>
>
> Actually no they're not. Apple is taking the other machines back. The 
> decrease in power use will save money. And there will also be an increase 
> in performance. So do a little research before you spout off.

Question: Why did they build this machine? Was there some other reason 
than to build the largest clustered Mac or was there a business reason. 
I think that Jeffrey could be right if it wasn't used for something of 
value. I'm sure a ton of resources went into the project whether Apple 
took the machines back or not. Was this a publicity stunt or did it add 
value to the world's research? The research needed here is the project
balance sheet and sales data.

 Looking at the VT site it notes;
  "Virginia Tech will have one of the top ranked supercomputing
   facilities in the world, supporting significant 'big science'
   research. It is anticipated that Virginia Tech will realize at
   least a five to one return on this investment in terms of
   annual research grant and contract activity," says Glenda
   Scales, assistant dean of computing and distance learning at
   Virginia Tech."

 I didn't see anything on the site about what work was done on the
systems. Big science projects need big systems, but I don't remember
that SCNC really pushed out much of value other than getting in the
paper a lot. I tried to get people interested in using it, but we had
all kinds of roadblocks. I couldn't find anyone or anything to help get
us started. Suddenly, when the money ran out, people over there wanted
us to use it, but by then you could then do a lot of work with better
software on a couple of linked machines so it wasn't cost effective
to spend money on a supercomputer.

 Has this system done anything of value so far other than be really big
and really fast? I'm not against it just for being big, but I would need
a lot more explanation before dismissing whether it is a waste of money
or not. SCNC didn't leave a lot of people saying that North Carolina
should invest in more supercomputing power.