Communications of the ACM
ncovering Results in the Magellan Testbed
"The difference in performance is visible even when running fairly modest-sized applications across different cloud environments," says Kathy Yelick, director of The National Energy Research Scientific Computing Centers.
Credit: University of California, Berkeley
The Magellan cloud computing testbed funded by the U.S. Department of Energy (DOE) is dedicated to studying the advantages and disadvantages, in terms of cost and energy, of the cloud computing model as it applies to scientists working on government-funded initiatives. "What we're exploring is the question of whether the DOE or other government agencies should be buying their own clusters . . . or whether those kinds of purchases should be done in a more consolidated way," says the National Energy Research Scientific Computing Centers' Kathy Yelick. She says the testbed's areas of concentration in addition to genomics research will include applied mathematics, high-energy physics, and climate data analysis.
In terms of the usefulness of the cloud to scientific computation, Yelick contends that "there's a part of the workload in scientific computing that's well-suited to the cloud, but it's not the [high-performance computing] end, it's really the bulk aggregate serial workload that often comes up in scientific computing that is not really the traditional arena of high-performance computing."
One of the findings Magellan has uncovered in its experiments is the fact that performance differences are evident even when operating fairly modest-sized applications across different cloud environments, Yelick says.
From HPC Wire
View Full Article
Abstracts Copyright © 2010 Information Inc., Bethesda, Maryland, USA 
No entries found