MSI Deploys Koronis

The University of Minnesota Supercomputing Institute for Advanced Computational Research (MSI) has purchased a new high-performance computing system based on the SGI Altix UV 1000 supercomputer. This new system was made possible by a National Institutes of Health (NIH) grant. The system is being installed and undergoing acceptance testing during October and November 2010. It is scheduled to be available to users by the end of November.

The new system will meet the needs of research groups at MSI in the fields of multi-scale modeling, chemical dynamics, bioinformatics and computational biology, and biomedical imaging. The new system will aid the groups in the interpretation of experimental data and will make possible predictions that facilitate the rational design of new therapeutics or biomedical technology. The new supercomputer, named Koronis after one of Minnesota’s lakes, will include a powerful shared-memory system, ultrafast disk storage/access, and high-end visualization capabilities that can keep pace simultaneously with compute and memory-intensive applications.

Koronis will feature a 1,152-core UV 1000 server with shared-memory architecture in which each core can access all 3.1 terabytes of memory directly. Also, Koronis will include high-performance visualization workstations to handle large-size biomedical data and high-performance/-fidelity data storage to ensure adequate data analysis and processing.

Koronis will be a unique, state-of the-art system built on “green” computing technology for minimal environmental impact. It should also create a wealth of research job opportunities at the University of Minnesota. Ultimately, it is hoped the system will facilitate breakthroughs in biomedical research and have a significant impact on human health.

Because Koronis was purchased with funds from an NIH grant award, only NIH grant recipients will be able to use it. These MSI researchers are already busy planning their research for when Koronis is installed and ready to be used. Professor Darrin York (Chemistry), author of the NIH grant proposal, intends to continue working on a multi-scale model of mechanical heart valves. In addition to Professor York, the research groups of Jiali Gao (Chemistry), Donald Truhlar (Chemistry), George Karypis (Computer Science and Engineering), David Largaspaeda (Genetics, Cell Biology and Development), Kelvin Lim (Psychiatry), and Bin He (Biomedical Engineering) will also be continuing their work on the new supercomputer, as well as other NIH-funded MSI researchers.

Taking the place of the recently retired Altix computer system, Koronis will join the other supercomputer resources MSI housed in Walter Library. These other systems—Itasca, Calhoun, Blade, and Elmo—are available to all researchers at institutions of higher education in the State of Minnesota. More than 4,000 active users across a wide range of disciplines utilize MSI’s diverse computational resources, making MSI a focal point of collaborative research at the University of Minnesota. MSI currently supports almost 500 active research groups by providing complete high-performance computing environments including systems, software, storage, support, and services. MSI resources have helped these researchers obtain nearly $150 million in external funding in the past academic year.