Idaho National Laboratory (INL)

Story Details

In 2002, U.S. Secretary of Energy Spencer Abraham designated the INL as the lead laboratory for nuclear energy research. INL needed significantly more compute resources to accommodate the increase in complexity of their scientific models and obtain more detailed results, faster. INL also needed high performance data management to improve performance and reliability. And, as part of the Generation IV nuclear energy systems initiative, secure collaboration was crucial. “Our research partners are international and commercial nuclear industrial partners. They are very sensitive about their data because it involves multi-billion dollar power plants,” explains Eric Greenwade, Chief IT Architect for INL.

Sun’s Solaris-based grid computing cluster solution dramatically improved compute power for the Idaho laboratory. “Sun’s grid computing cluster is a major component in advancing the large scale computing capability our researchers need for the design of the nuclear reactors,” says Greenwade. “The processors run anywhere from three to ten times faster than what we had before. That translates to substantial growth in work productivity. Now, we can work simultaneously on models, which are several thousand times larger than our previous ability. The end result is we can do problems that are up to 10 to 100 times bigger and get them done in as little as one-tenth the time, and our confidence in results also has vastly improved.”

Sun’s Grid Computing Solution also provides the security levels INL required. With Solaris Containers, CPUs, physical memory, and network bandwidth can be allocated and controlled on a fine-grained basis, helping simplify computing infrastructures and improving resource utilization. And moving to the Sun solution offers INL a fundamental improvement in data storage. INL uses Sun StorEdge SAM-FS software to manage data on the storage arrays. SAM-FS automatically backs up work in progress and creates file copies from the source that can be migrated to any storage media. By setting archiving policies that determine when, where, and how information is stored, large volumes of data can be managed cost-effectively.“We really needed fibre channel type speeds to access multiple terabyte data arrays,” explains Greenwade. “The Sun solution gives us the best of both worlds. We will still have fibre channel speeds and no single point failures in accessing high performance data.”