In this podcast, Dr. Peter Beckman, director of leadership computing at Argonne National Laboratory. talks about both cloud computing and green IT at the Lab.

Argonne National Laboratory (ANL) is one of the U.S. Department of Energy's (DOE) oldest and largest national laboratories for science and engineering research. ANL uses its annual $540 million operating budget to support 100's of research projects of interest to numerous federal agencies, and academic research institutions. ANL is one of DOE's two largest supercomputing centers. The other one is at the Oak Ridge National Laboratory.

In addition to supercomputing, ANL also offers its researchers some less expensive alternatives, namely, grid computing, and soon, cloud computing. Peter Beckman, the ANL's director of leadership computing, says that grid computing is best suited for running applications at multiple sites in cycles available to users in many locations. He says, "On the other hand, cloud computing will enable scientists to build their own solutions as they need them and run them in the cloud. It will also enable the consolidation and sharing of Linux clusters hosted on our cloud. For example, hosting will enable you to expand your 32-node cluster to a 200-node cluster for a few days. "

Opportunities for cloud computing at ANL include everything form studying the genome to looking at data from CERN's supercollider to understanding the smallest particles in the galaxy.

Cloud computing at ANL will eliminate the need for scientists to do their work on a $100 million supercomputer. Beckman says cloud computing is very appealing to some of ANL's researchers. He say, "Cloud computing's bursty, pay-as-you go for cycles model will lower the cost of getting some projects done. It will allow for demand-driven, large allocations of resources, such as a 1,000's of processors for the next couple of week, better than going to a supercomputer. It will also eliminate the need to upgrade equipment." Beckman adds that ANL would like to push some of its cloud capabilities to commercial service such as amazon.com.

In addition to cloud computing, ANL is saving money by optimizing data center technologies, such as water-size economizing, to keep the supercomputer cool and energy efficient. In fact, the chip architecture of ANL's supercomputer uses the least amount of power possible to do its scientific calculations. Beckman says, "Our data center is a factor of two less power data centers that have a different architecture." During some of the winter months, ANL uses water-side economizing to reduce energy costs. The process involves sending the water outside to be cooled by the cooling tower, and then piping the cooled water through heat exchangers in the machine room. He says, "We can cool the machine for free. We'd like to expand the number of months we can do this for."

Bio
Since 2008 Peter Beckman has been the director of leadership computing at Argonne National Laboratory, where he oversees its supercomputing facility. After receiving his Ph.D. in computer science from Indiana University, Beckman helped found the university's Extreme Computing Laboratory, which focused on parallel languages, portable run-time systems, and collaboration technology. In 1997 he joined the Advanced Computing Laboratory at Los Alamos National Laboratory, where he founded the ACL's Linux cluster team and launched the Extreme Linux series of workshops and activities, which helped catalyze the high-performance Linux computing cluster community. In 2000 he founded a Turbolinux-sponsored research laboratory in Santa Fe that developed the world's first dynamic provisioning system for cloud computing and HPC clusters. The following year, he became vice president of Turbolinux's worldwide engineering efforts, managing development offices in the US, Japan, China, Korea, and Slovenia. Beckman joined Argonne National Laboratory in 2002, as director of engineering, and later as chief architect for the TeraGrid. He designed and deployed the world's most powerful grid computing system for linking production HPC computing centers for the National Science Foundation.

Resources

Argonne's supercomputer named world's fastest for open science, third overall, Physorg.org
http://www.physorg.com/news133014256.html

Argonne Computer Goes Green, Power Management Design Line
http://www.powermanagementdesignline.com/news/212501723;jsessionid=1S14SOXKCF1QYQSNDLRCKHSCJUNN2JVN

Getting Control of the Cloud, Processor.com
http://www.processor.com/editorial/article.asp?article=articles%2Fp3114%2F69p14%2F69p14%2F69p14.asp

Production Credits
Elizabeth Ferrarini, Executive Producer
Tom Parish, Host and Audio Producer

Audio Editing by Doug Marcis