December 06, 2011
Supercomputing luminary Larry Smarr is uniquely qualified to write about the future of networked computing. In an essay in today's New York Times, Smarr, the founding director of the California Institute for Telecommunications and Information Technology (Calit2), explores what he believes is a likely extension of today's increasingly-networked world. Smarr's theory begins with a simple premise: "Over the next 10 years, the physical world will become ever more overlaid with devices for sending and receiving information."
At the heart of this distributed communication system is an expanding network of low-power processors, nearly invisible in their embedded-state, yet ubiquitous in number. They're in the phones we use, in our automobiles' navigation systems. They're inside a growing number of appliances and even in our homes and office buildings. Other networked information collectors include real-time traffic monitoring systems and a variety of both government-sponsored and privately-run surveillance systems.
Smarr notes that all these tiny computers are constantly receiving input, which is then sent to remote datacenters, the "vast clouds" owned by the big Web-era players, such as Google, Amazon, Microsoft and Apple.
Smarr also points to the development of spatially-aware apps, which can take in all the data along with the associated geographical and time stamps to create real-time portraits of various systems. For example cell phones can "talk to each other," pinging the cloud as needed to provide commuters with up-to-the-second traffic information.
"Smart electric grids are measuring our homes' use of power; active people are tracking their heart rates; and hundreds of millions of us are uploading geo-tagged data to Flickr, Yelp, Facebook and Google Plus. As we look 10 years ahead, the fastest supercomputer (the "exascale" machine) will be composed of one billion processors, and the clouds will most likely grow to this scale as well, creating a distributed planetary computer of enormous power."
This unprecedented level of compute power, combined with the an equally vast storage system, will enable the analysis necessary for extracting meaningful intelligence from the torrent of incoming data. Research from the Institute for the Future shows that this global cloud computer will likely progress from simply collecting local data to being able to control it. "In this evolution," writes Smarr, "the world gradually becomes programmable."
There's an apocryphal ring to this tale, but it's a pretty straight-forward extrapolation of the current state of technology. Of course, any technological advance can be used for good or evil, a fact clearly illustrated by history. The good guys try to stay a step ahead of the bad guys; sometimes they fail, but for the most part it seems to work out. Smarr's academic home, Calit2, is exploring specific "programmable world" scenarios, such as using sensors to monitor electricity consumption, while no doubt remaining acutely aware of the potential for misuse.
Full story at New York Times
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.