Parallel HPC Reaches for the Stars

High-performance parallel computing is taking off – literally. NASA and the U.S. Air Force have begun development of the Next Generation Space Processor (NGSP). The brain behind future space missions, NGSP will provide a minimum of 24 processor cores to support both highly parallel applications and precise power management, fault tolerance and program unit distribution, the agencies say.

(Read my complete blog on the topic at GoParallel)

Best, Bightest Parallel Students Work for "Betterment of Life on Earth"

Who will help create the next-generation of faster, higher resolution parallel computing models to help counter climate change, global warming and ozone layer damage? A good bet is one of the 11 student standouts recently chosen for prestigious summer internships in parallel computational science by the National Center for Atmospheric Research (NCAR). The University of Wyoming claimed three spots – the only college or university to claim multiple honors, according to NCAR.

(Read my complete blog on the topic at GoParallel)

Mixing Code Can Draw Penalty Flags

Parallel processing performance penalties can be pretty painful. Any developer that has tried to mix code in the single-precision and double-precision pipelines in the coprocessor knows this first hand. For good advice on how to avoid such mistakes, check out the recently published  “Intel Xeon Phi Coprocessor Vector Architecture”.  The report will help you better understand how SP instructions can come to your rescue, enabling good performance results.

(Read my complete blog on the topic at GoParallel)

Parallel Success Starts With Proper Planning

"Measure twice; cut once.” That maxim of carpentry is also good advice for parallel programming, according to a recent technical paper from Intel. Taking maximum advantage of a Many Integrated Core (MIC) coprocessor requires careful design of algorithm, data structure and architecture, warns “Intel Xeon Phi Application Design and Implementation Considerations.”

(Read my complete blog on the topic at GoParallel)

M2M: Rise of the Machines? Not Yet

In the 1970 science fiction thriller Colossus: The Forbin Project, two giant supercomputers from the United States and Soviet Union secretly join forces to take control of the collective nuclear might of the two countries. In the film, the two machines discover each other's existence, communicate back-and-forth, share their collective data, and cut their human creators out of the process. It is the ultimate example of machine-to-machine communications, or M2M.

(See my complete blog on the topic at InternetEvolution)

Wanted: Energy-Efficient Supercomputers

Who says super-fast computing has to be energy-wasting computing? That challenging question is at the core of a discussion workshop on large-scale parallel processing at the IEEE International Parallel and Distributed Processing Symposium in Boston May 20-24.

(Read my complete blog on the topic at goparallel.sourceforge.net)

Data Deluge Bottlenecking Breakthroughs

Data complexity and lack of scalability of underlying algorithms is bottlenecking the nation’s ability to analyze and apply massive amounts of science and engineering data for new breakthroughs, according to the U.S. Department of Energy. The DOE says translating the unprecedented flow of data from experiments and simulations – much of it generated by massively parallel computers – requires  “fundamentally different techniques, tools, and approaches.”

(See my complete blog on the topic at goparallel.sourceforge.net)