APPLICATIONS

ALBUQUERQUE, NM and SEATTLE, WA - The Department of Energy's Sandia National Laboratories and Cray Inc. announced that they have finalized a multiyear contract, valued at approximately $90 million, under which Cray will collaborate with Sandia to develop and deliver a new massively parallel processing (MPP) supercomputer called Red Storm. In June 2002, Sandia reported that Cray had been selected for the award, subject to successful contract negotiations. Cray will deliver a system with theoretical peak performance of 40 trillion calculations per second (teraOPS) using two calculations/clock cycle, or 20 teraops using one calculation/clock cycle. Red Storm is expected to become operational in fiscal year 2004, and will use the upcoming Advanced Micro Devices Inc. Opteron™ processors connected via a low-latency, high-bandwidth, three-dimensional mesh interconnect network based on HyperTransport™ technology. This system is expected to be at least seven times more powerful than Sandia's current ASCI Red supercomputer on actual weapons problems. ASCI Red was the first supercomputer delivered under the ASCI program. "This computer will allow modeling and simulation of complex problems that were only recently thought impractical, if not impossible," said Tom Hunter, Sandia Senior Vice President for Nuclear Weapons Programs. "Calculations that would have taken months only a dozen years ago will now be done in a matter of minutes. This investment by Sandia and the NNSA represents a clear commitment to provide the essential capabilities to support the nation's nuclear weapons program. It is a major step toward establishing computing as the key enabler of science and engineering in the 21st century and reemphasizes our role as one of the world's leaders in that transformation." Dr. William Reed, Acting Director of ASCI, considers Red Storm a crucial initiative in developing and deploying scalable, cost-effective supercomputers to meet the demanding simulation needs of nuclear weapons stockpile stewardship. "We are excited to have the new Cray Inc. as an industrial partner in the ASCI program," said Dr. Reed. Cray Chairman and CEO Jim Rottsolk said Red Storm reflects Cray's strategy to deliver high-efficiency, high bandwidth supercomputer systems. "Red Storm embodies the same design philosophy as our new Cray X1™ vector-based product in a highly cost-effective superscalar architecture and will be a key initiative for Cray. With X1 and Red Storm Cray is demonstrating its comprehensive capabilities in the high-performance scientific and technical marketplace," he said. "We are excited about winning this significant contract, and eager to begin collaborating with Sandia in the ASCI program." "AMD has forged a credible reputation in the high performance computing arena with its current generation of processors," said Marty Seyer, vice president of server business at AMD. "We are proud that a supercomputing leader like Cray selected our upcoming AMD Opteron™ processor for the new Red Storm system. This is an important validation of the performance and stability of AMD Opteron™ processors." "Sandia selected Cray to build this design because of their commitment to engineering, building, and delivering efficient, cost-effective and reliable large-scale MPP systems," said Sandia's Bill Camp, Director of Computers, Computation, Information and Mathematics. Camp also said that Cray's commitment to developing balanced and cost-effective architectures, together with its focus on the scientific computing market, were key factors. MPP supercomputers, designed as single machines, are more efficient than "clustered" systems that more loosely link together multiple servers or PCs. "We expect to get substantially more real work done, at a lower overall cost, on a highly balanced system like Red Storm than on a large-scale cluster," Camp said. Jim Tomkins, a Distinguished Member of Technical Staff at Sandia, and Camp architected the Red Storm design. Sandia's design was strongly influenced by the successes of the Cray T3E and ASCI Red MPP supercomputers. According to Tomkins, "The Red Storm contract contains an option to upgrade to 60 teraOPS. The Red Storm system architecture is designed to scale to hundreds of teraOPS."