For US federal government agencies, the rule is “cloud first” when looking to make new IT acquisitions. However, cloud isn’t always the best choice. The economics of cloud computing may be compelling for many front-line and transactional applications, but the costs and performance issues in applying cloud to specialized, deep analytical, or scientific environments may still be too prohibitive in many cases.
That’s the conclusion drawn in a recently issued report from the U.S. Department of Energy‘s Magellan project (“a cloud for science”), initiated two years ago to investigate the potential role of cloud computing in addressing the data-intensive computing needs of the DOE’s Office of Science.
The Magellan team sought to measure the returns for cloud computing — versus existing on-premises systems — from performance, usability, and cost standpoints. The researchers observed cloud models such as Infrastructure as a Service (IaaS) and Platform as a Service(PaaS), virtual software stacks, MapReduce and Hadoop in action. (Thanks toInformationWeek’s John Foley for surfacing this report.)
