Voltaire Switches Accelerate Top 4 Supercomputers on Green500 List Demonstrating Performance and Efficiency Leadership

 

Voltaire Ltd’s switches are connecting the world’s most energy efficient supercomputers, according to the findings of the latest Green500 list announced by Green500.org. Voltaire switches serve as the high-performance interconnect for the top 4 and 26 of the top 100 most energy efficient supercomputers on the list.

“Voltaire is known for delivering performance as evidenced by our InfiniBand leadership position on the TOP500 list of the world’s most powerful supercomputers, said Asaf Somekh, vice president of marketing, Voltaire. “This new Green500 list showcases Voltaire’s strength in delivering energy efficient fabrics for high performance systems. Voltaire’s unique combination of performance and efficiency is important for commercial data centers that need to reduce costs and energy usage without compromising on performance.”

Voltaire Grid Director InfiniBand switches deliver 20 or 40 Gb/s bandwidths and low latency with less than 5 watts per port power consumption.

“Insufficient power and cooling continue to dominate as the greatest data center facility problems,” said John Phelps, Research VP, Gartner. “In a recent poll of infrastructure and operations managers, combined power and cooling deficiencies were identified as the greatest data center facility problem for 67% of users.”

The Green500 (www.green500.org) is a list ranking the most energy-efficient supercomputers in the world and serves as a complementary view to the Top500 (www.top500.org) list of the most powerful supercomputers.

More information about Voltaire’s Grid Director InfiniBand switches is available at http://www.voltaire.com/Products/InfiniBand/Grid_Director_Switches and a free whitepaper, “Reducing Data Center Energy Costs Up to 50% by Consolidating and Virtualizing Your Network” is available at http://www.voltaire.com/unifiedfabric.

Are you a hipster, surfer or biker? What is your urban tribe? Your computer may soon be able to tell. Computer scientists at the University of California, San Diego, are developing an algorithm that uses group pictures to determine to which of these groups, or urban tribes, you belong. So far, the algorithm is 48 percent accurate on average. That's better than chance--which gets answers right only nine percent of the time--but researchers would like the algorithm perform at least as well as humans would.

An algorithm able to identify people's urban tribes would have a wide range of applications, from generating more relevant search results and ads, to allowing social networks to provide better recommendations and content. There also is a growing interest in analyzing footage from cameras installed in public spaces to identify groups rather than individuals.

Computer scientists presented their findings at the British Machine Vision Conference in the United Kingdom this fall.

"This is a first step," said Serge Belongie, a computer science professor at the Jacobs School of Engineering at the University of California, San Diego, and co-author of the study. "We are scratching the surface to figure out what the signals are."

This is an extremely difficult problem, Belongie explained, and a 48 percent accuracy rate is actually a very good result. One of the researchers' insights was to look at group pictures rather than pictures of individuals. They hoped that this would make it easier to pick up social cues, such as clothing and hairdos, to determine people's tribes based on visuals featuring more than one person. 

While humans can recognize urban tribes at a glance, computers cannot. So the algorithm segments each person in six sections—face, head, top of the head (where a hat would be), neck, torso and arms. This method is an example of what's better known as a "parts and attributes" approach. Computer scientists designed the algorithm to analyze the picture as the sum of its parts and attributes—in this case haircuts, hair color, make up, jewelry and tattoos, for example. The algorithm also analyzes the boxes for color, texture and other factors.

Researchers then let data do the work, feeding the algorithm pictures labeled for the urban tribes they represent—hipsters, surfers, bikers, Goth, etc.—a common machine learning technique. Finally, they fed the algorithm pictures without labels. The computer vision program accurately determined to which urban tribe the pictures belonged 48 percent of the time—better than random. The researcher's next step is to run the same set of pictures by human users and see how they perform.

In addition, the UC San Diego researchers are working with Lubomir Bourdev, a fomer Ph.D. computer science student at UC Berkeley, and Peter Belhumeur from the Department of Computer Science at Columbia University to improve the analysis of facial features and other attributes within the system.

To define urban tribes in the study, computer scientists turned to Wikipedia and selected the eight most popular categories in the encyclopedia's list of subcultures: biker, country, Goth, heavy metal, hip hop, hipster, raver and surfer. They also included photographs from three common categories for social venues: formal events, dance clubs and casual pubs.

A by-product of their research was the development of an extensive dataset of urban tribe pictures, including hundreds of images, which they plan to make available to other research groups.

The U.S. Army Tank Automotive Research, Development and Engineering Center's (TARDEC) National Automotive Center (NAC) today announced that the Army's new Mobile Parts Hospital (MPH), a mini- manufacturing center, is operational and producing vehicle replacement parts at Camp Arifjan, Kuwait, in support of American forces in Iraq. The announcement was made at the Association of the U.S. Army (AUSA) Annual Meeting and Conference in Washington, D.C.

Wheat Ridge, Colorado -- Aspen Systems, Inc., a leader in the custom design, manufacture and service of a wide array of Linux(R)-based high-performance computing solutions, is named to Deloitte & Touche’s prestigious Technology Fast 50 Program for Colorado, a ranking of the 50 fastest growing technology companies in the area by Deloitte & Touche LLP. Rankings are based on the percentage of growth in fiscal year revenues over five years, from 1998-2002.

WARRENDALE, Pa. -- AVL North America, a Plymouth, Michigan-based powertrain engineering, instrumentation and simulation software supplier will sponsor the popular Technology Theater at the SAE 2004 World Congress at Cobo Hall in Detroit March 8-11. The Technology Theater hosts high level executives and panels that discuss pressing issues affecting engineering, technology, and design in the global automotive industry. The Technology Theater concept was launched last year at the annual SAE World Congress event.

Page 2 of 43