MOVIES

MOUNTAIN VIEW, Calif. -- SGI today announced it has begun delivery of scalable, open-source supercomputing clusters designed to meet the needs of scientific discovery researchers around the world and across disciplines. Universities in Austria, Australia, Germany, Japan, Poland and Spain, among other international sites, have already ordered the supercluster product, launched Jan. 7, for planned uses in such disciplines as biochemistry, bioinformatics, chemical computation, physics, mathematics, earthquake research and computational fluid dynamics. Closer to SGI's Silicon Valley home, Incyte Genomics, Inc., based in Palo Alto, Calif., is only one of many private-sector scientific companies worldwide that is investigating uses of the Linux(R) OS-based SGI(R) Altix(TM) 3000 server family to increase its research productivity. Incyte, which designs, develops and markets genomic information-based tools, has just completed benchmark testing of the product and found that it far exceeds the company's current cluster-based capabilities. "We were very impressed by the fact that the SGI Altix 3000 family server showed a 7x productivity improvement against our existing Intel Pentium-based Linux cluster," remarked Incyte's Ken Jacobsen, senior vice president, Information Services. "With the flexibility of being able to address large shared memory, researchers can now solve large problems in a much more timely, cost-effective manner. SGI is clearly hitting all the right marks with a product that's ideally suited for high-performance, high-productivity tasks in industries across the board and is particularly suited for researchers who want the portability of open-source environments combined with the best of SGI high-performance scalable shared memory architecture." The new Linux OS-based supercluster combines the compute power of Intel(R) Itanium(R) 2 processors with the unequalled scalability and high-speed memory access of SGI(R) NUMAflex(TM) shared-memory architecture. Using "brick" modules consisting of Itanium 2 microprocessors and up to 8GB of memory, researchers can scale up to 64 processors on a single SGI(R) shared-memory node. Among the universities that have ordered SGI Altix 3000 servers: -- The Computing Center at Johannes Kepler University Linz, located in Linz, Austria, has ordered a 128-processor system for basic science applications, including running Gaussian(R) for chemical computation problems -- The University of Tokyo's Earthquake Research Institute has purchased 64-, 32- and 12-processor systems, all to be used for a variety of earthquake research projects -- The Queensland Parallel Supercomputer Foundation has purchased 64- and 16-processor systems, both to be housed at the University of Queensland in Brisbane, Australia, for use by researchers at a consortium of six Queensland universities for applications ranging from bioinformatics to marine ecology -- The University of Tokyo's Institute of Industrial Science has ordered a 64-processor system for computational chemistry problems, including quantum biochemistry research projects -- The Universitat Politecnica de Valencia, located in Valencia, Spain, has purchased a 48-processor system to run various applications for chemistry, bioinformatics, physics and engineering computational needs -- The Institute of Structural Mechanics at Bauhaus-Universitet Weimar, located in Weimar, Germany, has purchased a 40-processor system for computational problems running on homegrown codes as well as on Ansys and Abaqus -- The Academic Supercomputing and Networking Center, located in Poznan, Poland, has ordered a small server for testing codes and software development in anticipation of a planned expansion, designed for a variety of scientific computation challenges Voicing a sentiment heard from universities and researchers around the world, Vicente Hernandez, vice chancellor of the Universitat Politecnica de Valencia, said of his university's buying decision, "SGI offered the best solution for our particular compute power and compatibility requirements, along with the most compelling roadmap for future product updates." "The SGI Altix 3000 supercluster series offers scientific researchers an industry-leading, high-productivity Linux OS-based solution," explained SGI's Dan Stevens, marketing manager, life sciences. "It can accelerate bioinformatics productivity with faster processors, high-speed access to shared memory and applications tuned by SGI applications engineers. These unique SGI capabilities can also enable productivity improvements for computational chemistry applications, such as Gaussian, to run at higher speed compared to other Linux cluster architectures." The SGI scalable Linux platform will also be highly effective in grid computing environments, providing increased computing capacity and development opportunities for Linux OS-based applications in a shared-memory, 64-bit environment. In medical imaging applications, where technologies such as computed tomography, MRI and cardiovascular applications are generating ever-growing data sets, the new SGI product line will fill the pressing need for high-productivity 64-bit computing. "Both the Linux-based and award-winning MIPS and IRIX platforms operate on our unique shared-memory architecture, and each offers specific advantages to the research community," said SGI's Chodi McReynolds, director, Industry Marketing, Sciences. "We're looking forward to working closely with the scientific community to continue providing researchers the computing tools they need to meet even greater discovery and applied science challenges in the years ahead." For further details about SGI and the sciences, visit www.sgi.com/go/sciences, and for information on SGI's involvement with universities and research labs around the world, visit www.sgi.com/go/research. Background on the SGI Altix 3000 family of superclusters is available at www.sgi.com/features/2003/jan/altix/.