SV: Capacity of the brain
Eric J. Korpela
korpela at albert.ssl.berkeley.edu
Fri Sep 17 12:02:14 EST 1999
In article <Q1tE3.16502$N77.1223152 at typ11.nn.bcandid.com>,
Kragen Sitaker <kragen at dnaco.net> wrote:
>On the other hand, some algorithms parallelize extremely well easily,
>even with quite minimal communication. There are a bunch of folks
>called genetic-programming.com who are running a 1000-Pentium cluster
>to try to invent algorithms so they can patent them.
Just say no to software patents.
Basically anything that requires large numbers of independent trials
will parallelize very well. Of course, now I just HAVE to mention the
project I'm involved in which is currently running on about 420,000
CPUs clicking over at about 7 to 10 teraFLOPs. Parallelizes to the extreme.
Follow the links if you can't figure out which one it is.
Eric Korpela | An object at rest can never be
korpela at ssl.berkeley.edu | stopped.
<a href="http://sag-www.ssl.berkeley.edu/~korpela">Click for home page.</a>
More information about the Neur-sci