October 16, 2012
Distributed computing stories in the tradition of volunteer grids (like SETI@home and World Community Grid) aren't terribly common, so I usually take notice of them. This week, an item in Digital Trends alerted me to the existence of a new cycle scavenging startup, CPUsage.
The company, based in Portland, Oregon, operates kind of like the volunteer grids, except it pays users for their "extra" compute power, then collects and reallocates the cycles. The loosely-coupled system is a good match for inherently-parallel workloads and the company is seeing demand for visualization-related jobs like video encoding.
"The idea is that there are so many computers around the world that sit idle most of the day," states co-founder Jeff Martens in the Digital Trends piece. "In the U.S. alone, there are 250 million PCs – and most of us let those computers sit idle most of the time. And even when we do use them, the average person is using about five percent or less of the CPU's capabilities."
"We harness that unused processing power and we repurpose it and sell it to companies with high through-put and high performance needs."
Martens and co-founder Matt Wallington, a 10-year veteran of Intel, explain that the concept of harnessing unused cycles over the Internet came out of NASA originally and was popularized by the SETI@home program – a Space Sciences Laboratory project that uses public computers to look for signs of intelligent life outside Earth. (SETI stands for the Search for Extraterrestrial Intelligence.) The impetus for CPUsage came when Martens, who was then working for an electronic design automation firm at the time, was listening to his friend, a Sun Microsystems employee, bemoan the amount of time required to run simulations.
Martens figured that if employees of a major HPC company were in this predicament, there had to be a better way. His thoughts soon turned to virtually-unlimited pools of idle compute cycles, and the idea for the company was born.
While the startup has already raised $1 million in seed funding thanks to Bay Area investors, the founders are managing the company's growth carefully. Nevertheless, the execs report that supply-side interest is already sky-high with a waiting list in the thousands. Louisiana State University is one high-profile partner and offers a good illustration of untapped computing power. Its computer labs are open and powered-on 20 hours a day, but only used for an average of three. CPusage will allow the university to recoup some of that wasted power and potential.
As with similar programs, the duo say the software is unobtrusive and all users have to do is download it, take care of a few settings, the rest happens automatically behind the scenes. The current release is limited to Windows clients, but Linux and OS X versions are being looked at.
Oct. 17, 2012 — Editor's note: This article has been updated since it was first published to correct facts and add information.
The ever-growing complexity of scientific and engineering problems continues to pose new computational challenges. Thus, we present a novel federation model that enables end-users with the ability to aggregate heterogeneous resource scale problems. The feasibility of this federation model has been proven, in the context of the UberCloud HPC Experiment, by gathering the most comprehensive information to date on the effects of pillars on microfluid channel flow.
Read more...
Large-scale, worldwide scientific initiatives rely on some cloud-based system to both coordinate efforts and manage computational efforts at peak times that cannot be contained within the combined in-house HPC resources. Last week at Google I/O, Brookhaven National Lab’s Sergey Panitkin discussed the role of the Google Compute Engine in providing computational support to ATLAS, a detector of high-energy particles at the Large Hadron Collider (LHC).
Read more...
Frank Ding, engineering analysis & technical computing manager at Simpson Strong-Tie, discussed the advantages of utilizing the cloud for occasional scientific computing, identified the obstacles to doing so, and proposed workarounds to some of those obstacles.
Read more...
05/10/2013 | Cleversafe, Cray, DDN, NetApp, & Panasas | From Wall Street to Hollywood, drug discovery to homeland security, companies and organizations of all sizes and stripes are coming face to face with the challenges – and opportunities – afforded by Big Data. Before anyone can utilize these extraordinary data repositories, however, they must first harness and manage their data stores, and do so utilizing technologies that underscore affordability, security, and scalability.
04/02/2012 | AMD | Developers today are just beginning to explore the potential of heterogeneous computing, but the potential for this new paradigm is huge. This brief article reviews how the technology might impact a range of application development areas, including client experiences and cloud-based data management. As platforms like OpenCL continue to evolve, the benefits of heterogeneous computing will become even more accessible. Use this quick article to jump-start your own thinking on heterogeneous computing.