December 18, 2008
Here's a collection of highlights, selected totally subjectively, from this week's HPC news stream as reported at insideHPC.com and HPCwire.
10 words and a link
Kogge on Spectrum Radio, DARPA's gloomy predictions for exascale computing
Guide to building a PS3 cluster
HPC info graphic in the NYT
Irish researchers work with IBM optical networks in next-gen supers
Intel: three things you must teach in parallel programming
Google U: intro to parallel programming and MapReduce
PRACE Winter Petascale Computing School
Berkeley developing patterns for parallel programmingHow to stand out in HPC
Acceleware ditches hardware, goes software only
Tour of NASA's Pleiades (with video)
Serial semantics with Cilk++
NCSA's HPC coloring book...genius
This in from NCSA's newsfeed, an item that warms the cockles of my heart:
Looking for a stocking stuffer this holiday season? Check out NCSA's supercomputing coloring book! Learn more about the resources NCSA provides and how this computing power helps scientists, engineers, and major companies.
This is fantastic. Makes me want to go ahead and finish up my "What is HPC" movie. Kudos to you, NCSA, for trying to broaden the reach of HPC down several age brackets.
Distributed computing with NVIDIA Cuda
NVIDIA cut a press release this week highlighting its participation (as a vendor) in various distributed computing projects. Using the Berkeley Open Infrastructure for Network Computing (BOINC), researchers are tapping into the computational power sitting on the desks of every Dick and Jane NVIDIA user.
"NVIDIA CUDA technology opens up processing power for scientific research that was previously unavailable and impossible for researchers to afford," said Dr. David Anderson, Research Scientist U.C. Berkeley Space Sciences Laboratory and founder of BOINC. "CUDA technology makes it easy for scientists and researchers to optimize BOINC projects for NVIDIA GPUs and they are already using it for applications in molecular dynamics, protein structure prediction, climate and weather modeling, medical imaging, and many other areas."
For a list of projects, check out the post at insideHPC.
UC and P&G Create Simulation Center
The University of Cincinnati and Proctor & Gamble have announced a collaborative effort to develop a center of expertise in computer simulation. The UC Simulation Center will provide P&G with cost-effective, high-value virtual modeling and simulation capacity and capability not currently found within the halls of P&G. It will also serve as a pipeline for future technical talent.
"The more virtual engineering we can do, the more we can save in terms of costs, time, engineering resources, etc. We can do far more parametric studies applying virtual models -- such as different sizes and shapes -- because there is no retooling of fabrication machines," Professor Teik C. Lim, head of UC's Mechanical Engineering Department, points out. "For example, this practice has been gaining popularity amongst major automotive companies like Ford, Mercedes and Toyota because they cannot afford to build several variations of the same car."
For more info on the new collaboration, read the full release.
10/30/2013 | Cray, DDN, Mellanox, NetApp, ScaleMP, Supermicro, Xyratex | Creating data is easy… the challenge is getting it to the right place to make use of it. This paper discusses fresh solutions that can directly increase I/O efficiency, and the applications of these solutions to current, and new technology infrastructures.
10/01/2013 | IBM | A new trend is developing in the HPC space that is also affecting enterprise computing productivity with the arrival of “ultra-dense” hyper-scale servers.
Ken Claffey, SVP and General Manager at Xyratex, presents ClusterStor at the Vendor Showdown at ISC13 in Leipzig, Germany.
Join HPCwire Editor Nicole Hemsoth and Dr. David Bader from Georgia Tech as they take center stage on opening night at Atlanta's first Big Data Kick Off Week, filmed in front of a live audience. Nicole and David look at the evolution of HPC, today's big data challenges, discuss real world solutions, and reveal their predictions. Exactly what does the future holds for HPC?