October 01, 2007
With this week’s issue containing the second half of GRIDtoday’s look at some of the incarnations of utility computing currently available, I wanted to spend a little time discussing utility computing – something I have covered numerous times over the past 18 months, or so, but something that nonetheless deserves the attention.
To begin, it’s important to note that the four approaches we have detailed in this feature are by no means the only options customers have for utility computing. In fact, they aren’t even the majority (although they are among the most unique). HP, for example, has a handful of utility computing solutions focusing on Instant Capacity, Metered Capacity and Managed Capacity, and IBM, for its part, offers off-site Deep Computing Capacity on Demand, as well as Capacity on Demand capabilities in many of its servers. In addition, if we are to consider capacity on-demand as a key component of a utility platform (how could we not?), there are a good number of application virtualization (e.g., Appistry EAF and DataSynapse FabricServer) and more-traditional grid solutions that certainly meet this standard, even if they are lacking somewhat in the metering and analytics departments. And, while I’m at it, I would be remiss to omit the new breed of utility/grid hosting services from providers like Layered Technologies and ServePath. As you might have read in our recent article on the aforementioned providers and services, the hosting market is really onto something with their new flexible, on-demand offerings – some of which are pay-per-use just like their big brothers.
Then, of course, there is the question of adoption, which everyone (but Amazon) seems to believe is coming along at about they pace they expected. (Amazon, for its part, says the current demand for EC2’s beta release far exceeds the Web giant’s current allocation of resources.) And while that pace might be slow-but-steady, most everyone with whom I have spoken on the issue believes that it will continue to pick up speed, eventually leading to utility computing being commonplace within mainstream organizations. The conventional wisdom here is that datacenters are becoming more complex and more costly to run with every passing day, and it’s just a matter of time until companies get fed up. Also, as Amazon’s Werner Vogels likes to say, companies who do decide to outsource their computing in a utility model not only save themselves the hassle of buying and managing their own resources, they also have more money to spend on innovation in their core businesses.
These notions also hold true for the new breed of in-house utility solutions, which give businesses that absolutely cannot outsource a way to maximize their IT dollars. As the guys at Cassatt are quick to point out, it is a lot simpler and a lot more cost-effective to manage your datacenter as one big utility than it is to manage each component, application and set of resources as its own individual entity. And did I mention the high availability, high resource utilization and on-demand access to those resources?
Personally, I’ve always been a proponent of the utility model and, barring some major turn of events, I always will be. This stance has only been bolstered by speaking with the companies I have over the past couple of months, as the new spins they are incorporating are adding both shine and substance to utility computing. Plus, it is now easier than ever for companies to -- as the cliché goes -- get their feet wet with this method of doing things. With little to no re-writing and, in some outsourced models, zero commitment, companies have every opportunity to test it out before fully immersing themselves in the utility waters.
Of course, life goes on outside of the utility computing world, and we’ve got the news to prove it. Among the big announcements of the week are: Société Générale expanding its financial grid with Platform’s Symphony product; the Department of Defense solidifying its patient care systems with Egenera BladeFrame systems; the BEinGRID project looking for new business-related experiments on which to spend its grant monies; and HP revamping its Adaptive Infrastructure offerings. Also, be sure to check out Tiffany Trader’s recap of last week’s Objectivity webinar detailing the complementary nature of grids and distributed databases.
Comments about GRIDtoday are welcomed and encouraged. Write to me, Derrick Harris, at email@example.com.
Posted by Derrick Harris - October 01, 2007 @ 11:28 AM, Pacific Daylight Time
Derrick Harris is the Editor of On-Demand Enterprise
No Recent Blog Comments
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.
May 23, 2013 |
The study of climate change is one of those scientific problems where it is almost essential to model the entire Earth to attain accurate results and make worthwhile predictions. In an attempt to make climate science more accessible to smaller research facilities, NASA introduced what they call ‘Climate in a Box,’ a system they note acts as a desktop supercomputer.
May 16, 2013 |
When it comes to cloud, long distances mean unacceptably high latencies. Researchers from the University of Bonn in Germany examined those latency issues of doing CFD modeling in the cloud by utilizing a common CFD and its utilization in HPC instance types including both CPU and GPU cores of Amazon EC2.
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.