With a little reorganization and forethought, you can even have your own mini-supercomputer using banks of GPU cards to crunch vectors and matrices. See Nvidia's CUDA development system, and their Tesla computer system.
- Ken > -----Original Message----- > From: [EMAIL PROTECTED] > [mailto:[EMAIL PROTECTED] On Behalf Of Jochen Fromm > Sent: Sunday, July 20, 2008 12:52 PM > To: The Friday Morning Applied Complexity Coffee Group > Subject: Re: [FRIAM] REPOST: The meaning of "inner". > > Yes, an impressive supercomputer. I think it is much more > difficult to use a supercomputer with a trillion operations > per second than a huge cluster of ordinary computers, as you > can find them in Google's data centers. > > -J. > > ----- Original Message ----- > From: "Marcus G. Daniels" <[EMAIL PROTECTED]> > To: "The Friday Morning Applied Complexity Coffee Group" > <[email protected]> > Sent: Sunday, July 20, 2008 7:49 PM > Subject: Re: [FRIAM] REPOST: The meaning of "inner". > > > > For comparison, LANL Roadrunner has about 5 trillion > transistors for the > > CPUs (~13000 PowerXCell 8i processors and ~6500 dual core > Opterons) and > > another 800 trillion for RAM (~100 TB). > > > > > ============================================================ > FRIAM Applied Complexity Group listserv > Meets Fridays 9a-11:30 at cafe at St. John's College > lectures, archives, unsubscribe, maps at http://www.friam.org ============================================================ FRIAM Applied Complexity Group listserv Meets Fridays 9a-11:30 at cafe at St. John's College lectures, archives, unsubscribe, maps at http://www.friam.org
