• June 2010
    M T W T F S S

Social Supercomputing Is Now.

ETH Zurich (05/28/10)

ETH Zurich scientists working on the FuturIcT project plan to use the world’s largest supercomputers to simulate life on Earth, including the financial system, economies, and whole societies. The ETH researchers, working under the Competence Center for Coping with Crises in Complex Socio-Economic Systems, are analyzing huge amounts of financial data to detect dangerous bubbles in stock and housing markets, potential bankruptcy cascades in networks of companies, or similar vulnerabilities in other complex networks such as communication networks or the Internet. The FutureIcT project aims to bring different kinds of research together to simulate the entire globe, including the diverse interactions of social systems and of the economy with the environment. The FutureIcT project also aims to analyze data on social, economic, and environmental processes by augmenting the results of field studies and laboratory experiments. “Such observatories would detect advance warning signs of many different kinds of emerging problems, including large-scale congestion, financial instabilities, the spreading of diseases, environmental change, resource shortages, and social conflicts,” says ETH’s Dirk Helbing.


Customizing Supercomputers From the Ground Up.

Pacific Northwest National Laboratory (05/26/10) Beckman, Mary

The Pacific Northwest National Laboratory (PNNL) computer scientist Adolfy Hoisie will lead a group of scientists that will design supercomputers and their software applications simultaneously, so all the components of a supercomputer can be optimized and focused on one kind of problem. The PNNL team plans on solving the kinds of problems specific to various scientific fields, from studying biological systems to understanding the electrical power grid. The data-intensive problems the PNNL team wants to solve requires a different emphasis in computational resources, which is why they will design supercomputers and their applications simultaneously. “The science of systems and applications designed for optimal performance is a grand challenge for high performance computing research,” says PNNL researcher Moe Khaleel. The team also will examine how performance and power relate, and how they trade off against one another on extreme-scale systems and workloads.


Tokyo Tech Announces Plans for 2.4 Petaflop Supercomputer.

Tokyo Institute of Technology (05/26/10)

The Tokyo Institute of Technology (TIT) announced that the TSUBAME 2.0 supercomputer, a green, cloud-based supercomputer system with a top speed of 2.4 petaflops, will begin operation this fall. TSUBAME 2.0 will be built by Hewlett-Packard and NEC using GPGPU computing and will feature a large solid-state drive. TSUBAME 2.0, dubbed Petakon, will be 12 times faster than Japan’s current fastest supercomputer and is expected to achieve a top ranking on the TOP500 list. It also is expected to score high on the DARPA HPC Challenge benchmark and the Green 500 list. TSUBAME 2.0 will feature Intel Westmere-EP and Nehalem-EX processors with scalar operation, and will employ approximately 4,200 NVIDIA Fermi graphics processing units. Petakon also will have more than 1,400 computer nodes and use Voltaire’s QDR InfiniBand network. The operating system will be a combination of Linux and Microsoft Windows HPC, and will use virtual machine technology to provide cloud-hosting services.


Chinese Supercomputer Is Ranked World’s Second-Fastest, Challenging U.S. Dominance.

New York Times (05/31/10) Markoff, John

China’s Dawning Nebulae supercomputer, based at the National Supercomputing Center in Shenzhen, has been ranked as the world’s second-fastest machine, passing European and Japanese systems. Dawning Nebulae achieved a sustained computing speed of 1.27 petaflops, which makes it the world’s fastest in terms of theoretical peak performance, but that is considered a less significant measure than the actual computing speed achieved on a standardized computing test. The Cray Jaguar, based at the Oak Ridge National Laboratory in Tennessee, remains the world’s fastest supercomputer, according to the latest semiannual supercomputer ranking. Dawning Nebulae is based on chips from Intel and NVIDIA. China also is developing a new system based on a microprocessor designed and manufactured in China, which is expected to be complete later this year. “I wouldn’t be surprised if by the end of this year they surpass the scientific computing power of the [European Union] countries combined and have a computer system with an achieved performance to reach the No. 1 position on the Top500,” says University of Tennessee computer scientist Jack Dongarra.