“Creating more energy-efficient HPC is a continuous improvement process that requires the right tools for measuring, taking action, checking the results and iterating in a virtuous cycle. This is true for the infrastructure as well as all levels of the system; from components through applications. We haven’t had to think about energy efficiency, nor have we had the tools to measure it. Once the right tools are in place, we can start wrapping our heads around what are the contributing factors to better efficiency, and from that we can start influencing hardware designs.”
Archives for May 2014
Video: The e-Infrastructure Commons Marketplace
May 23, 2014 by
Helix Nebula has launched its new cloud-computing marketplace service during event held yesterday at CERN.
20 Years of Beowulf Workshop Issues Call for Papers
May 23, 2014 by
“The 20 Years of Beowulf workshop will mark the 20th anniversary of the introduction of commodity (AKA Beowulf) clusters, an architectural approach to creating parallel computers using entirely commodity components and open source system software. The initial target of the Beowulf cluster project was inexpensive, small to moderate parallel computing platforms. The Beowulf approach was extremely successful and adopted worldwide by teams ranging from high-school students to senior scientists. The Beowulf approach is now the basis of most of the world’s most powerful computers.”
This Week in HPC: IBM Edge Conference & A New Federated Cloud in Europe
May 23, 2014 by
In this episode of This Week in HPC, Michael Feldman and Addison Snell from Intersect360 Research discuss the the IBM Edge Conference and the new Federated Cloud for Science in Europe.
Podcast: Fabric Integration is Coming to Intel True Scale
May 23, 2014 by
“With Fabric Integration, you pick up five value vectors. One is an in increase in performance; so the closer you can drive the fabric to the CPU, the more things you can do to increase the overall performance of both the CPU, and the fabric together. Number two, you pick up density. Because now you’re not taking up any board space or PCIe slots and things like that. Number three, you pick up also the options for improved value, in terms of price per performance. Number four, you reduce power. And number five, by getting rid of things like the PCIe bus, you reduce componentry – which again reduces power – as well as improves reliability.”
Lorena Barba on Why She Pushes Python
May 22, 2014 by
“Using Python has improved the effectiveness of our computer science program for all students … More students leave the course with the ability to create meaningful programs and with the positive attitude toward the experience of programming that this engenders.”
Fujitsu HPC Powers Tofas Automotive
May 22, 2014 by
Today Fujitsu announced that Turkey’s largest automotive manufacturer has deployed the company’s HPC solutions.
Data Center Floor Space Utilization
May 22, 2014 by
You would probably not be surprised to learn that liquid submersion cooling of your servers can save you money on power and cooling costs. Yet, you might be surprised when you read this paper and find that liquid cooling also provides greater efficiency in terms of data center floor space.
Video: Cosmology on the GPU
May 22, 2014 by
“Numerical simulations represent one of the most effective tools to study and to solve astrophysical problems. Thanks to the enormous technological progress in the recent years, the available supercomputers allow now to study the details of complex processes, like galaxy formation or the evolution of the large scale structure of the universe. Sophisticated numerical codes can exploit the most advanced HPC architectures to simulate such phenomena and process and visualize their results. Enzo, Ramses and Splotch are prime examples of such codes. Work is ongoing to enable such codes to GPUs using the CUDA and OpenACC programming models. The accomplished refactoring work together with recent tests and results are presented.”
Cambridge Goes With Double Data Protection from OCF
May 21, 2014 by
OCF has teamed with IBM and DDN to provide a secure, offsite, replicated data archive for the University of Cambridge.
