DOE Facility Plan Sees Major Role for Computing

In a speech at the National Press Club on November 10, 2003, U.S. Energy Secretary Spencer Abraham outlined the Department of Energy’s Office of Science 20-year science facility plan, a roadmap for future scientific facilities to support the department’s basic science and research missions. The plan prioritizes new, major scientific facilities and upgrades to current facilities.

“This plan will be the cornerstone for the future of critical fields of science in America. These facilities will revolutionize science—and society,” said Abraham. “With this plan our goal is to keep the United States at the scientific forefront.”

Priority 2 in the plan is an UltraScale Scientific Computing Capability (USSCC), to be located at multiple sites, which would increase by a factor of 100 the computing capability available to support open scientific research. Most existing supercomputers have been designed with the consumer market in mind; USSCC’s new configurations will develop computing capability specifically designed for science and industrial applications. These facilities will operate like Office of Science light sources: available to all, subject to proposal peer review.

The USSCC will involve long-term relationships with U.S. computer vendors and an integrated program of hardware and software investments designed to optimize computer performance for scientific and commercial problems by creating a better balance of memory size, processor speed, and interconnection rates. A very similar strategy was spelled out in the white paper that NERSC together with seven other DOE labs submitted to the High End Computing Revitalization Task Force in June 2003 (see http://www.nersc.gov/news/reports/HECRTF-V4-2003.pdf).

An upgrade of the NERSC facility is tied for Priority 7. This upgrade will ensure that NERSC, DOE’s premier scientific computing facility for unclassified research, continues to provide high-performance computing resources to support the requirements of scientific discovery.

NERSC will continue to provide the core scientific computing needed by the research community, and will complement the “grand challenge” approach pursued under the USSCC, according to the facility plan. Reaffirming the goals of the NERSC Strategic Proposal for 2002–2006, the plan describes the NERSC upgrade as using Grid technology to deploy a capability designed to meet the needs of an integrated science environment combining experiment, simulation, and theory by facilitating access to computing and data resources, as well as to large DOE experimental instruments. NERSC will concentrate its resources on supporting scientific challenge teams, with the goal of bridging the software gap between currently achievable and peak performance on the new terascale platforms.

Top