November 22, 2002
Baltimore Convention Center, Baltimore, Maryland
10:30 a.m. - noon
Room 307/308
The 40 Tflop/s Earth Simulator System: Its Impact on the Future Development of Supercomputing
Moderator: Horst D. Simon, NERSC/LBNL
Panelists:
John Drake,
Oak Ridge National Laboratory
David Kahaner, Asian
Technology Information Program, Tokyo, Japan
Hisashi Nakamura,
Research Organization for Information Science & Technology, Tokyo, Japan
Tetsuya Sato,
Earth Simulator Center, Yokohama, Japan
Burton Smith, Cray,
Inc.
Questions that were addressed by the panel included:
Looking beyond the initial excitement about a 35 Tflop/s Linpack number, what is the lasting impact of the ESS on computational science in general, and on climate simulations in particular?
What intellectual and scientific advantage can be derived from
a supercomputer that makes a "quantum" leap in terms of performance?
What does the success of the ESS mean for the future of commodity, "off-the-shelf" clusters? for clusters of SMPs? For vector computing in the US?
What has been learned so far from the ESS experience? What steps should the
US take to strengthen supercomputing for basic science applications?
Are we in a supercomputing race or should we rather, as a community, build super
systems like the ESS, for example following a collaborative model practiced
by high-energy physicists? Can or should this be done as a science project in
the framework of an international collaboration? How could such a process get
started?
Presentations by the Panelists:
John Drake, "SC02
BOF on the Earth Simulator"
David Kahaner, "Earth Simulator's Impact"
Hisashi Nakamura
Tetsuya Sato
Burton Smith
An event.
Another event.
Lorem ipsum dolor sit amet, consectetuer adipiscing elit, sed diam nonummy nibh euismod tincidunt ut laoreet dolore magna aliquam erat volutpat. Ut wisi enim ad minim veniam, quis nostrud quid exercitation ulliam corper suscipit.
