Press Release

University of Montreal Unveils New SGI Altix System, Largest Shared-Memory Supercomputer in Canada

Quebec Scientists and Researchers Count On SGI Solutions For Complex Data Analysis And Faster Results

SUNNYVALE, Calif. (February 15, 2007) — To allow Quebec research centers to remain competitive in a rapidly evolving technology environment and provide a diverse group of scientists with the ultimate in high performance, the Réseau Québécois de calcul de haute performance (RQCHP), has added an SGI® Altix® 4700 system, which is housed at the University of Montreal.

Over 350 scientists and researchers from five research institutions will now have access to the largest globally shared-memory supercomputer in Canada, the Altix 4700 system, giving them the capacity and performance to run complex computational simulations in days or weeks, instead of months or years. The RQCHP (which translates to Quebec Network for High Performance Computing) researchers cover a vast range of studies, including physics, chemistry, engineering, medicine, computer science, biochemistry, bioinformatics, automobile manufacturing, aeronautics, railroad transportation, and a host of business services. The Altix 4700 supercomputer is capable of 4.9 teraflops and features 1.5 terabytes of shared memory. The system represents approximately 30% of the total performance capacity of RQCHP.

"This installation exemplifies how SGI delivers solutions for the most demanding compute and data-intensive workflows," said Martin Pinard, president, SGI Canada. "The highly flexible, highly scalable and open architecture of the Altix system provides the optimum combination of compute, special purpose processing, memory and I/O elements, to match the needs of the customer's workflow, from fundamental to multi-disciplinary research."

For data-intensive environments such as the RQCHP, SGI's highly scalable shared-memory computing architecture provide researchers the tools to expand their analysis options, accelerate research and results, and lower total costs by freeing them to focus on science instead of system and data management. "What makes SGI's help so important — I can't stress this enough — is that it will allow many research centres in Quebec to be competitive in an environment where technology is changing very rapidly," said University of Montreal Rector Luc Vinet.

As part of the Canada Foundation for Innovation (CFI), an independent organization created by the Government of Canada to fund research infrastructure, and with a matching in-kind donation from SGI Canada, RQCHP was able to purchase the powerful new SGI Altix 4700. RQCHP is one of six computing grids for universities across the country, funded by CFI. RQCHP encompasses five institutions in Quebec: University of Montreal, University of Sherbrooke, Concordia University, École Polytechnique, and Bishop's University.

Applications in Medicine: The Virtual Heart
One example of the work that is now possible with the new SGI Altix is the research to better understand the effects of cardiac disease and pharmacological interventions on electrocardiograms (ECGs) of the human heart. Diseases that affect the heart disrupt its electrical currents. In some cases, for example in cardiac arrhythmia, these electrical disruptions may present a serious danger to the person affected. Physicians at present are able to analyze the impact of simple pathologies on their patients' ECGs. In cases of more complex pathology, a diagnosis is often much harder to establish, because the impact on the sequence of electrical events is more difficult to analyze.

Dr. Mark Potse and Dr. Alain Vinet at the University of Montreal and Sacré-Coeur Hospital and their research team will attempt to find answers to some of these diagnostic problems using a "virtual heart," which they will subject to various computer simulations. This model, the only one of its kind in the world, contains 60 million points, each representing a few hundred human heart cells.

"Using the recently acquired Altix 4700 our team will be able to calculate signals measured directly on the heart and not simply on the surface of the body," said Dr. Potse. "This will allow us to tackle a range of problems that have been impossible to model mathematically until now."

Applications in Computers and Operational Research: Statistical Learning
Some 20 University of Montreal researchers working under Professor Yoshua Bengio are seeking to raise the level of intelligence of computers, which could impact industries including insurance, translation, finance, pharmaceuticals, e-commerce, Internet, and marketing.

As Prof. Bengio explained, every day, computers deliver general conclusions based on data already available to them. These conclusions then help human beings make appropriate decisions and recommendations. Insurance companies, for example, use this type of computer-based prediction every day before they set premiums. But the ability of computers to generalize in varying contexts remains limited. In order to make the computer capable of analyzing more sophisticated concepts, Prof. Bengio's team is developing methods to allow machines to learn more abstract concepts. As part of their research, the team launches parallel simulations on hundreds of processors at a time. The resulting calculations produce examples for them to show the computer the level of learning it acquires, and monitor it.

"Our research team constantly tries to create more and more complex simulations, but they are often limited by the available computer power," said Prof. Bengio. "With the Altix 4700 supercomputer, we can now envision and initiate simulations that would previously have taken an entire year to compute and complete them in a single day. Most important of all, the acquisition of the Altix computer will allow us to remain competitive internationally."

SGI Solutions Tailored for Intensive Workloads
"Fueling advances in medicine to save lives, exploring the possibilities of artificial intelligence, seeking the proofs of physics theories or sequencing plant genomes to impact agricultural production — these are all applications that SGI Altix high-speed performance was made for and excels at," added Pinard. "With their selection of Altix 4700, the RQCHP researchers have joined the ranks of the top scientists at the most important government and industry labs around the world."

RQCHP's purchase includes a SGI Altix 4700 system with 384 Dual-Core Intel® Itanium® 2 processors and 1.5TB of RAM, an SGI InfiniteStorage 4500 system with 19 terabytes of capacity, SGI® CXFS™ Shared Filesystem and SGI Data Migration Facility (DMF) data management software, and two 32-port Silkworm Brocade switches 4Gbps 4900. The SGI Altix 4700 system joins existing RQCHP resources, which include an SGI® Altix® 3700 with 128 Intel Itanium 2 processors, and an SGI® Altix® 350 system, with 16 Intel Itanium 2 processors.

SGI - Innovation for Results™
SGI (NASDAQ: SGIC) is a leader in high-performance computing. SGI delivers a complete range of high-performance server and storage solutions along with industry-leading professional services and support that enable its customers to overcome the challenges of complex data-intensive workflows and accelerate breakthrough discoveries, innovation and information transformation. SGI solutions help customers solve their computing challenges whether it's enhancing the quality of life through drug research, designing and manufacturing safer and more efficient cars and airplanes, studying global climate, providing technologies for homeland security and defense, or helping enterprises manage large data. With offices worldwide, the company is headquartered in Sunnyvale, Calif., and can be found on the Web at www.sgi.com.

© 2007 SGI. All rights reserved. SGI, Altix, the SGI cube and the SGI logo are registered trademarks, and CXFS is a trademark of SGI in the United States and/or other countries worldwide. Intel and Itanium are trademarks or registered trademarks of Intel Corporation or its subsidiaries in the United States and other countries. All other trademarks mentioned herein are the property of their respective owners.

This news release contains forward-looking statements regarding SGI technologies and third-party technologies that are subject to risks and uncertainties. These risks and uncertainties could cause actual results to differ materially from those described in such statements. The reader is cautioned not to rely unduly on these forward-looking statements, which are not a guarantee of future or current performance. Such risks and uncertainties include long-term program commitments, the performance of third parties, the sustained performance of current and future products, financing risks, the ability to integrate and support a complex technology solution involving multiple providers and users, and other risks detailed from time to time in the company's most recent SEC reports, including its reports on Form 10-K and Form 10-Q.