• October 2010
    M T W T F S S
    « Sep   Nov »
     123
    45678910
    11121314151617
    18192021222324
    25262728293031

Carnegie Mellon Researchers Break Speed Barrier in Solving Important Class of Linear Systems.

 Carnegie Mellon News (PA) (10/21/10) Byron Spice

Carnegie Mellon University (CMU) computer scientists have developed an algorithm that can solve systems of linear equations related to real-world problems in image processing, logistics and scheduling, and recommendation systems. The algorithm, developed by CMU professor Gary Miller, systems scientist Ioannis Koutis, and Ph.D. student Richard Peng, uses new tools from graph theory, randomized algorithms, and linear algebra to make solving real-world problems much faster. The algorithm applies to a class of problems called symmetric diagonally dominant (SSD) systems. “The fast SDD solvers developed by Koutis, Miller, and Peng represent a real breakthrough in this domain, and I expect them to have a major impact on the work that we do,” says Microsoft researcher Richard Szeliski. The CMU team’s approach to solving SDD systems is to first solve a simplified system that can be done rapidly and serve as a preconditioner to guide future steps to an ultimate solution.

-MORE-

Advertisements

How Energy-Efficient Is Cloud Computing?

PhysOrg.com (10/08/10) Lisa Zyga

University of Melbourne researchers have found that cloud computing is not always the most energy-efficient option. Although previous studies on energy consumption in cloud computing have focused only on the energy used in the data center, the Melbourne team found that transporting data between data centers and home computers can consume larger amounts of energy than storing it. “The most important conclusion in our analysis is that, when comparing the energy consumption of cloud-based services with that of a typical desktop PC, we must include the energy consumption required to transport the data from the user into the cloud resources and back,” says Melbourne researcher Rod Tucker. “Without careful consideration of the power consumption of cloud services, their growing popularity will become a significant contributor to greenhouse gas production.” The researchers found that power for transport can be as low as 10 percent and 25 percent at low usage levels for private and public storage services, respectively, and nearly 60 percent and 90 percent, respectively, at high usage levels. However, the researchers predict that cloud computing technology will continue to become more energy efficient.

Parallel Java Programming System Launched by University of Illinois.

eWeek (10/14/10) Darryl K. Taft

University of Illinois at Urbana-Champaign researchers, led by professor Vikram Adve and Ph.D. student Robert Bocchino, have launched a project to develop a Deterministic Parallel Java (DPJ) implementation. The researchers say the parallel implementation of Java would be the first to guarantee deterministic semantics without run-time checks for general-purpose, object-oriented programs. “The broad goal of our project is to provide deterministic-by-default semantics for an object-oriented, imperative parallel language, using primarily compile-time checking,” according to the DPJ website. The new system will help developers rewrite parts of parallel Java applications to simplify debugging, testing, and long-term maintenance. “It is our contention that parallel programming is much easier than concurrent programming; in particular, it is seldom necessary to use nondeterministic code,” according to the DPJ site. The researchers say they launched the project because they wanted to develop a language that supports programming styles developers find most familiar and productive, such as mainstream object-oriented programming languages.

-MORE-

Powerful Supercomputer Peers into the Origin of Life

Oak Ridge National Laboratory (10/04/10) Morgan McCorkle

Oak Ridge National Laboratory (ORNL) scientists are using supercomputer simulations to reveal how nucleic acids could have played a role in the origins of life. The research team, led by ORNL’s Jeremy Smith, used molecular dynamics simulations to investigate an organic chemical reaction that could have had an impact on the evolution of ribonucleic acids into early forms of life. “Computer simulations can provide insight into biological systems that you can’t get any other way,” Smith says. The research team found a theoretical explanation for why the Diels-Alder ribozyme requires magnesium to function. Computational simulations of the ribozyme’s internal movements permitted the scientists to capture and comprehend the reaction’s finer details. Smith says their calculations revealed that the ribozyme’s internal dynamics included an active site that opens and closes to control the reaction. The concentration of magnesium ions directly affects the ribozyme’s motions. “We found that magnesium ions bind to a special location on the ribozyme to keep the mouth open,” Smith says.

-MORE-