NCSA Selects Dell for Supercomputing Cluster
Dell has been selected by the National Center for Supercomputing Applications (NCSA) at the University of Illinois, Urbana-Champaign to provide more than 1,450 servers that will perform computations and data analysis for researchers across the U.S. to better understand major scientific and engineering studies. Research conducted on NCSA systems includes: studying the evolution, size and structure of the universe, investigating theories on the lifecycle of stars like the Sun, modeling severe storms, studying the human genome and biological processes, advancing the drug design process and more.
The Dell PowerEdge servers will be linked to form a high-performance computing cluster (HPCC) with a theoretical peak performance of 17.7 trillion floating point operations per second (TFLOPS) that promises to rank among the world’s most powerful systems. Such performance capabilities would rank this cluster as the third most powerful system on the Top 500 List of supercomputers and will increase NCSA’s total computing power to close to 24 TFLOPS.
“NCSA’s reputation rests on being a leader in cutting-edge supercomputing for science and engineering research and in developing new computing technologies and infrastructure,” said Dan Reed, director of NCSA. “We are pioneering new performance capabilities for standards-based clusters and supercomputing applications. Dell was able to provide excellent performance and value through its products, programs and partnerships to further these efforts.”
“The new NCSA cluster shows Dell’s ability to deliver cutting-edge solutions at the highest-end of enterprise computing,” said John Mullen, vice president, Dell Higher Education. “Dell’s HPCC solutions offer high performance at significantly less cost than a proprietary platform – a value proposition that continues to be well-received in academia and government organizations, and in global corporations.”
NCSA’s main computational cluster uses 1,280 dual Intel Xeon 3.05 processor PowerEdge 1750 servers that will be networked with Myrinet 2000 high-speed interconnects and running Red Hat Linux. This will be supported with 106 PowerEdge servers providing I/O services with 120 TB of storage and 64-node Myrinet networked cluster for applications testing and development.
Platform Computing software will provide central management of the computing resources in the cluster, and manage the users’ job submissions and executions. Dell OpenManage software will monitor the health and the utilization of all the systems in the cluster.