Top 500 trends

Trent Piepho xyzzy at speakeasy.org
Tue Nov 26 17:51:05 PST 2002


On Wed, 27 Nov 2002, Toon Moene wrote:
> Robert G. Brown wrote:
> 
> > I were told "sorry, we can do your Monte Carlo computations now at a
> > cost of $50K/year for eight years or wait until year seven and complete
> > them in year eight for $100K total, and you'll just have to wait".

You just have to wait for the pipeline to fill.  You may do nothing for those
first 7 years, but then in year 9 you can work on the CFD problem that would
have taken nine years at $70k/year, and the year after work on protein folding
that would have taken ten years and pretty soon in year 14 you're ready to
start the next version of the monte carlo simulation.

> 
> Heh :-)  That's why I'm in weather forecasting :-) :-)

But doesn't forecasting tomorrow's weather get even easier if you wait until
tomorrow to start?




More information about the Beowulf mailing list