Mountain View, CALIF. — SGI, recognized worldwide for providing industry-leading advanced graphics and high-performance computing solutions, announced significant gains in the supercomputing industry with the widespread acceptance of its SGI Origin 3000 series servers and SGI Onyx AE 3000 series visualization systems, launched in July 2000. To date, SGI has shipped in excess of 4,000 processors within SGI Origin 3000 series and SGI Onyx 3000 series systems of varying configurations. The systems, totaling more than 100, have been shipped to organizations in Europe, North America, Asia and Australia.
The SGI Origin 3000 series and SGI Onyx 3000 series systems use SGI NUMAflex modular technology to create some of the world’s largest supercomputing solutions. These solutions can be configured to the specific needs of individual customers and break through many previous limits in CPU, memory, I/O and graphics performance. SGI modular supercomputing solutions are being deployed across industries for applications such as automobile design and crash-test analysis, oil and gas exploration, financial services, health care and weather forecasting.
“Whether our customers are modeling the world’s financial markets or designing safer automobiles, the SGI Origin 3000 series and SGI Onyx 3000 series systems are able to take research and development and other core business functions to unprecedented levels, processing enormous amounts of data more quickly and more efficiently than any other solution,” said Jan Silverman, vice president, Advanced Systems Marketing, SGI. “The modular supercomputing architecture gives our new and existing customers much-needed reliability, scalability, flexibility and performance for their computationally intensive needs.”
SGI will be showcasing its developments in modular supercomputing, including recent and upcoming implementations of the SGI Origin series and SGI Onyx series systems, at Supercomputing 2000 (SC2000) in Dallas, Texas, November 6-10. Additionally, SGI and its partners are scheduled to pres= ent case studies about their joint solutions. Presentations are to include representatives from:
* University of Manchester
* NASA Ames
* Ohio Supercomputing Center
* BMW and ESI Group
* Computational Engineering International
* Porsche and Vircinity IT Consulting
Dr. Goh Eng Lim, chief technology officer at SGI and a specialist in high-performance computing architectures and computer graphics algorithms, will also give a presentation. Recent and upcoming implementations of the SGI Origin 3000 series and SGI Onyx 3000 series include the following:
ESI Group and BMW Announced this week, SGI and the ESI Group achieved unprecedented computing power using an SGI Origin 3000 series server and ESI Group PAM-CRASH 2000 software to assist BMW in creating a crash-simulation engine. The SGI and ESI Group team achieved sustained performance of more than 12 GFLOPS using SGI Origin 3000 series servers with 96 MIPS=AE R12000 processors. This marks the highest level of performance ever achieved in a computerized crash simulation.
Using this system rather than conventional design-analysis technology, BMW was able to significantly shorten the design cycle time, delivering future owners an even safer BMW Series 5 in a shorter period of time.
“The key to our success for superior solutions in engineering is utilizing the best compute resources,” said Touraj Gholami, head of the crash simulation department at BMW. “The SGI Origin 3000 series servers coupled with the MPP version of PAM-CRASH 2000 from ESI Group enable extremely fast simulations at very reasonable costs.”
Representatives from the ESI Group and SGI presented the solution developed for BMW at SC2000. NASA and SGI are currently building one of the most powerful supercomputers in the world-a 1,024-processor SGI Origin 3000 series server designed for NASA’s work in computational physics, including global climate modeling, nanotechnology and aeronautics. Additionally, NASA will utilize this system as it enters into biological simulation research with the National Cancer Institute. The system is targeted for full operation by April 2001.
“The SGI architecture enables us to extract greater performance from a single address space system-a multiprocessor supercomputer that performs like one computer,” said Bill Feiereisen, division chief, Numerical Aerospace System Division, NASA. “Together SGI and NASA have surged ahead of the pack to truly harness the power of large multiprocessor systems.”
Prior to the development of the SGI modular architecture, engineers were challenged with harnessing the full power of a large multiprocessor supercomputer, often breaking the system into a set of subsystems or not being able to extract the full compute power.
Feiereisen will present and demonstrate representative samples of the results achieved at NASA Ames using SGI solutions, and SGIrepresentatives will be at SC2000 to explain the technologies behind NASA research and supercomputing solutions.
SGI was recently selected to supply the National Oceanic and Atmospheric Administration’s (NOAA) Geophysical Fluid Dynamics Laboratory (GFDL) with 10 SGI Origin 3800 supercomputers, with a total of 1,152 processors that will be on-site at the time of system acceptance. The total performance of the systems to be installed is 922 GFLOPS.
The SGI systems will be used for the computationally intensive modeling and simulating of the Earth separated into large interacting regions. The NOAA will use the models for analyzing and forecasting weather phenomena such as hurricanes and climatic trends such as global warming. The SGI modular supercomputers will be able to perform simulations four times faster than the older machines, giving the NOAA a key advantage in its research.
SGI Origin 3000 series servers and SGI Onyx 3000 series visualization systems utilize the unique NUMAflex modular technology, a brick-style system for constructing small to very large systems from a common set of building blocks. NUMAflex modular technology allows users to build the optimum configuration one component at a time and adopt new technologies that map to their specific business or research needs. In contrast, traditional high-performance computers may need to be replaced all at once as often as once a year to keep up with competitive demands and technological changes-a costly and cumbersome process.
SGI Origin 3000 series servers enable “capability computing” — the ability to analyze and solve complex problems that were previously unsolvable. For existing projects or applications, SGI Origin 3000 series servers provide greater precision, quicker results and breakthroughs in price and performance.
SGI Onyx 3000 series visualization systems offer users a unique combination of graphics capability and compute power. This combination allows for visualization of large, complex volumetric data (e.g., brainmapping); allows interactivity and realism (e.g., pilot training simulation); provides bandwidth and image quality for real-time, high-definition special effects (e.g., broadcast); and has the visual accuracy and compute power that enable interactive design (e.g., photo-realistic automotive modeling).
SGI Origin 3000 and SGI Onyx 3000 series systems utilize the SGI IRIXAE operating system, the world’s premier 64-bit UNIX AE operating system for high-performance computing, advanced visualization and production supercomputing. SGI IRIX is renowned for its leadership in scalable computation; high-performance data movement, sharing and management; real-time applications support; and media streaming capabilities Technical applications that currently run on the SGI 2000 series and Silicon Graphics=AE Onyx2=AE systems will run on SGI 3000 family systems with as much as twice the previous performance without the need for recompilation. All technical applications currently available on SGI 2000 series and Silicon Graphics Onyx2 systems can run on the new systems.
With NUMAflex technology, each drawer-like module in a system has a specific function and can be linked, through the patented SGI high-speed system interconnect, to many other bricks of varying types to create a fully customized configuration. The same bricks, depending on their number or configuration, can be used for a continually expanding range of high-performance computing needs: C-brick (CPU module), P-brick (PCI expansion), D-brick (disk storage), R-brick (system/memory interconnect), I-brick (base I/O module), X-brick (XIO expansion) and G-brick (InfiniteReality=AE graphics). New brick types will be added to the NUMAflex modular offering for specialized configurations (e.g., broadband data streaming) and as new technologies, such as PCI-X and Infiniband, enter the market. The systems can also be deployed in clusters or as large shared-memory systems, depending on users’ needs.
SGI provides a broad range of high-performance computing and advanced graphics solutions that enable customers to understand and conquer their toughest computing problems. Headquartered in Mountain View, Calif., with offices worldwide, the company is located on the Web at http://www.sgi.com .