• April 2014
    M T W T F S S
    « Mar   May »
     123456
    78910111213
    14151617181920
    21222324252627
    282930  

Big Data Reaches to the Stratosphere

HPC Wire (04/03/14) Tiffany Trader

A position paper by Berlin Technical University professor Volker Markl developed at the recent Big Data and Extreme-scale Computing workshop emphasizes the goals and challenges of big data analytics. “Today’s existing technologies have reached their limits due to big data requirements, which involve data volume, data rate and heterogeneity, and the complexity of the analysis algorithms, which go beyond relational algebra, employing complex user-defined functions, iterations, and distributed state,” Markl writes. To correct this requires deploying declarative language concepts for big data systems. However, the effort presents several challenges, including designing a programming language specification that does not demand systems programming skills; plotting out programs expressed in this language to a computing platform of their own choosing, and performing them in a scalable fashion. Markl says next-generation big data analytics frameworks such as Stratosphere can enable deeper data analysis. Stratosphere integrates the advantages of MapReduce/Hadoop with programming abstractions in Java and Scala and a high-performance runtime to facilitate massively parallel in-situ data analytics. Markl says Stratosphere is so far the only system for big data analytics featuring a query optimizer for advanced data analysis programs that transcend relational algebra, and the goal is to enable data scientists to concentrate on the main task without spending too much time on instilling scalability.

MORE

ETH Inaugurates Europe’s Most Powerful Supercomputer

Science Business (03/26/14) 

ETH Board president Fritz Schiesser recently inaugurated Piz Daint, a supercomputer housed at the Swiss National Supercomputing Center (CSCS) that is now ranked as the most powerful computer in Europe. Piz Daint is the result of the first phase of the national High-Performance Computing and Networking Strategy. Although Piz Daint has been at CSCS for about a year, only recently did it break the petaflop barrier following an upgrade from 12 computer cabinets to 28 and a hybrid expansion with graphics processing units (GPUs). In addition, the combination of GPUs and conventional processors, which together can process about 3.2 billion computer operations per watt, makes Piz Daint one of the world’s most energy-efficient supercomputers in the petaflop performance class. “Thanks to projects like [the Swiss Platform for High-Performance and High-Productivity Computing] and [the Platform for Advanced Scientific Computing (PASC)], [CSCS director] Thomas Schulthess and his team have also managed to position Swiss researchers at the cutting edge of algorithm and software development worldwide,” says PASC’s Ralph Eichler.

MORE

DARPA Looks to GPUs to Help Process Big Data in the Military

IT Pro (03/31/14) Clare Hopping 

The U.S. Defense Advanced Research Projects Agency (DARPA) wants to use graphics-processing units (GPUs) to help analyze big data in support of governmental and military efforts. Speaking at the recent GPU Technology Conference, DARPA project manager Chris White said the agency is looking for people to help them understand real-world battlefields using GPUs. White said DARPA needs expertise to help develop the XDATA cloud to process data from military sensors and communications systems, which will help soldiers make informed decisions quickly. Although GPUs can provide help to process the data, such a complex and specialized solution also needs investment to make it work more effectively, according to White. “Our goal is to apply the principles of big data analytics to identify and understand deep commonalities among the constantly evolving corpus of software drawn from the hundreds of billions of lines of open source code available today,” says DARPA program manager Suresh Jagannathan. “We’re aiming to treat programs–more precisely, facts about programs–as data, discovering new relationships among this ‘big code’ to build better, more robust software.”

MORE