August 07, 2012
The news media has been abuzz over NASA's recent achievement. The big risk, big reward operation costing 2.5 billion dollars, which included safely landing a mini cooper-sized robot on Mars, paid off. Behind the scenes, the agency has relied on cloud services to keep people informed and will most likely continue to use similar application to assist the rover as it explores the red planet.
Animation of the Mars rover Curiosity communicating
Just before the landing took place, GigaOm posted an article detailing the preparations NASA put into their live stream. The agency knew Curiosity's entry sequence was going to be a big event, so they had to prepare for high amounts of Web traffic aimed at their live stream.
They partnered with SOASTA, a service that tests how much load applications can handle on the web. The company uses cloud resources to flood servers, emulating high amounts of traffic. It's a method of testing the stamina of a given infrastructure and was used to determine the resiliency of the 2012 Olympic website.
In NASA's case, a Mac Pro at the Jet Propulsion Laboratory (JPL) shipped four streams of various bitrates to a flash server. The flash server then pushed the streams to a "tier 1" server, which was replicated by 40 load balanced "tier 2" servers on Amazon's EC2.
When SOASTA tested the stream, they generated 25 Gbps of traffic for 40 minutes. In addition, they terminated 10 instances and then 20 instances from NASA's stream to make sure Amazon's load balancing service would automatically bring them back up. During the 40-minute test, SOASTA downloaded over 6 terabytes of data. Needless to say, NASA's stream worked without a hitch.
Looking ahead, it appears the agency will continue to use cloud applications during the Curiosity's mission. HPC in the Cloud reported on NASA's use of Windows Azure to power a new cloud-based application called the "Be a Martian" program. The project uploaded 250,000 images of Mars onto Microsoft's cloud platform and served more than 2.5 million data queries. Given that the new rover is equipped with 17 onboard cameras, there is a good chance a number of images captured by Curiosity will make their way to the application.
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.
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).
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.
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.