FEATURES & COMMENTARY
New York, N.Y. — A clustered supercomputer at the Cornell Theory Center (CTC) at Cornell University is helping scientists understand how to prevent airplanes from failing, develop new and better drugs, and treat hereditary diseases like Alzheimer’s and Cystic Fibrosis.
Technology scientists and industry thought leaders will meet here tomorrow at the World Trade Center to discuss the next generation of computers and how linking ultra-powerful machines into clusters will help advance science and commerce. The Advanced Cluster Computing Consortium (AC3), an organization founded to help businesses, academic institutions, and government agencies understand super-clustered computing and how to build and use these systems, is hosting the event. Speakers at the symposium will include executives and experts from the Cornell Theory Center, Dell(tm), Intel(R), Microsoft(R), and Merrill Lynch.
“Super-clustered computers are helping us accelerate new discoveries and solve complex problems that, in some cases, were previously impossible or at the very least would have taken decades,” said Thomas F. Coleman, director, Cornell Theory Center, Cornell University.
For example, the average length of service for a commercial jetliner is greater than 15 years and, over time, the stress of flight causes small cracks in the jet’s body, wings and engine. The materials community is using the Cornell computer (known as Velocity) to create models that determine when stress cracks will render those planes unfit to fly. These models, which simulate years of aircraft pressurization, will help the aerospace and airline industry and government safety agencies design maintenance and retirement plans for aircraft with the potential for structural failure.
Velocity is also helping scientists understand how proteins “fold” into their functional shape, a critical component for the development of new drugs and for treatment of diseases such as Alzheimer’s and Cystic Fibrosis. Scientists at Cornell recently used the computer to uncover a connection between the gene that causes very large tomatoes and the gene that proliferates cancer in humans. They speculate that this linkage might have implications for future cancer treatments.
“Airplane safety and medical breakthroughs are only a few areas that will see miraculous discoveries resulting from using this new technology,” said Coleman. “Thursday’s meeting should provide additional insights into the power of high-performance computing with Dell, Intell, Microsoft, and CTC.”
Super computers have been fueling discoveries for the past two to three decades and have become more powerful over the years. In fact, experts at the University of Manheim in Germany and the University of Tennessee annually unveil a ranking of the world’s 500 most powerful computers and count Velocity as a member of that list. However, Velocity isn’t a computer at all. Instead, it is a group of commonly available Dell PowerEdge(tm) servers linked together by ultra-fast networking technology that behaves like one large computer.
This method for building super computers, known as clustering, uses industry-standard computer equipment like Dell servers, Intel Pentium Processors, Windows 2000 from Microsoft, and networking technology from Giganet as building blocks to group computers into clusters for increased power, performance, and reliability of the individual systems. The advantage of this industry standard approach is that it ends up significantly less expensive than building one large, custom-engineered system. Another benefit is that owners of these newer clustered systems can increase their power simply by adding another computer to the cluster.
“This approach to building high-end computing systems is known as scaling out and will make it possible for more organizations to develop these systems and possibly accelerate new breakthroughs,” added Coleman.