CNET también está disponible en español.

Ir a español

Don't show this again

HolidayBuyer's Guide
Desktops

AMD to power Utah supercomputer

The machine will use 1,000 of the chipmaker's Opteron processors and will help provide the University of Utah with the computational power it needs for biomedical research.

The University of Utah will set up a supercomputer that's based on the Opteron processor from Advanced Micro Devices.

The supercomputer, which was designed to use 1,000 Opteron processors, will be supplied by Angstrom Microsystems. The university expects the machine to provide it with the computational power it needs for biomedical research. The machine's clusters, a number of lower-end systems that are linked to form a single supercomputer, will be delivered next month.

According to the university, the supercomputer will cost $2 million.

Last month, Los Alamos National Laboratory chose Linux Networx to build two large computing clusters that are based on Opteron. "Lightning," the larger of the two clusters, will contain 2,816 Opteron processors. Clustered supercomputers are generally cheaper and can be built quickly, as they use commercially available processors.

AMD said the University of Utah supercomputer will be code-named Arches, named after Utah's Arches National Park. It will be built with Opteron-based Angstrom Titan64 Superblades that will offer researchers simultaneous 32- and 64-bit computing power. Arches will combine five clusters that are comprised of varying numbers of nodes and processors.

The Center for High Performance Computing at the University of Utah has received a grant from the National Institute of Health's National Center for Research Resources to develop the Arches cluster. The grant will be used for research that's expected to include identifying the causes of inherited cancers and other genetic diseases.

"The new system from Angstrom will help us to deeper analyze our extensive amount of biomedical data as well as perform even more complex and advanced simulations," Julio Facelli, director of the Center for High Performance Computing, said in a statement.