The project reached a milestone this week when the university submitted a research paper for publication in the Journal Of Physical Oceanography, an American Meteorological Society publication.
This research couldn't be done without the right IT platform, says Thomas Haine, assistant professor in the department of earth and planetary sciences. "Simulating the North Atlantic is a computationally complex job," Haine says. The ocean's ability to absorb gases, particularly carbon dioxide, can have a profound effect on global warming and climate patterns across landmasses nearest the ocean, he says. To simulate the temperature, saliency, and pressure of the North Atlantic, Haine relies on real data collected from satellites and ships and sent to the university via the Internet.
Haine's Dell cluster consists of eight Dell 2450 PowerEdge servers with two P3 CPUs, 18 Gbytes of hard drive, and 1 Gbyte of memory each. Data is stored on each server within the cluster, and the cluster is interconnected via two networks. The Dell servers have a Fast Ethernet connection that handles the copying of files and other general system-administration jobs. The cluster also has a faster Myrinet connection from Myricom Inc. that's used for high-speed computations.
Johns Hopkins considered systems from SGI Inc. and Sun Microsystems but ultimately chose Dell because of pricing. "The cluster was about $50,000, but we were never really presented with a like-for-like comparison" with Sun or SGI, Haine says. "We could have done this with Unix but wouldn't have gotten as much for our money. I suspect we would have been looking at twice that from Sun and SGI."