Rice Building Fastest Academic Supercomputer in Texas
 |
Rice’s first supercomputer, the R1, was built in 1959. Billed
in the press as “the world’s fastest brain,” the
room-sized R1 was fast for its time, but by today’s standards,
it only matches up to a programmable hand-held calculator. Now
Rice is again building Texas’s fastest academic supercomputer,
but it will take a warehouse full of calculators to match the power
of the Rice Terascale Cluster.
When fully operational next year, the Rice Terascale Cluster (RTC) will rank
among the world’s fastest computers and will be the first university computer
in Texas with a peak performance of one teraflop, or one trillion floating-point
operations per second (FLOPs), the standard measure of supercomputer performance.
That makes it approximately three times faster than any other university computer
in Texas. The power comes from a cluster of at least 70 interconnected servers,
each containing four 900-megahertz Intel Itanium 2 processors. The cluster will
have more than 500 gigabytes of RAM and will be linked to a one-terabyte array
of dedicated hard drives.
Were it operational today, the RTC would rank among the 10 fastest academic supercomputers
in the country and the top 25 university computers worldwide, according to www.top500.org,
a semiannual ranking of the world’s top supercomputers that is compiled
by researchers at the University of Tennessee and the University of Mannheim,
Germany. According to the list, the fastest supercomputer currently in Texas
is the IBM Regatta-HPC Cluster at the University of Texas–Austin, which
has a peak performance of one-third of a teraflop. Most of the fastest supercomputers,
including the fastest in the world—the 35.9-teraflop NEC Earth Simulator
in Japan—and the fastest in the United States—the 7.2-teraflop ASCI
White-Pacific at Lawrence Livermore National Laboratory in California—are
operated by private or government-run research laboratories.
The RTC will be housed at Rice’s Computer and Information Technology Institute
(CITI). “Rice faculty from disciplines as diverse as biochemistry, earth
science, economics, neuroscience, computer science, and political science will
use RTC in their research,” says Moshe Vardi, RTC principal investigator
and CITI director. “It will also be a vital tool for basic computational
research aimed at better designing software that can run on hundreds or even
thousands of processors simultaneously.”
Complex research already slated for the RTC includes simulations of biomolecular
interactions, the physics of heavy ion collisions, simulations of Internet-based
computer applications running on hundreds of computers, and simulations that
aim to better understand and predict international conflicts.
The total cost for the RTC is undetermined, but funding includes a $1.15-million
grant from the National Science Foundation (NSF) and a grant from the Intel Corporation.
Rice’s proposal for NSF funding for the RTC faced stiff competition in
a process that saw awards for just one in three applicants. Rice won based on
independent evaluations by reviewers who praised CITI’s expertise in high-performance
computing, the interdisciplinary nature of CITI research, and the caliber of
the faculty involved.
—Jade Boyd
|
