INDUSTRY
Linux Networx Cluster System Climbs to Third Fastest Supercomputer
- Written by: Writer
- Category: INDUSTRY
SALT LAKE CITY -- A cluster supercomputer Linux Networx built for Lawrence Livermore National Laboratory (LLNL) in 2002, advanced two rankings to become the third fastest supercomputer in the world on the 21st TOP500 supercomputing list (www.top500.org). The Linux Networx Evolocity(R) system, called MCR by LLNL, can process 7.6 trillion calculations per second (teraflops) running the Linpack benchmark, and is also the fastest Linux cluster in the world. "This is another significant success for Linux Networx and the Linux community in general. In the top five supercomputers, Linux Networx has the third fastest system -- the highest rank for any Linux cluster ever. Only NEC and HP have recorded higher performances for their supercomputers," said Erich Strohmaier, computer scientist at NERSC/Lawrence Berkeley National Laboratory and co-founder of the TOP500 list. "Only a year and a half ago, MCR would have ranked as the fastest supercomputer in the world with this performance, which gives a good indication of the power of this machine." LLNL is using the cluster to conduct experiments in global climate modeling, material properties, earthquakes and other large-scale, high- performance simulations of physical phenomena. The lab was founded in 1952 as a nuclear weapons design lab and continues to conduct scientific research in the interests of national security. The Linux Networx system is also the fastest Intel-based and the fastest Linux machine ever built harnessing 2,304 Intel(R) 2.4 GHz Xeon(TM) processors and is connected using the Quadrics interconnect. LLNL uses the Linux Networx cluster appliance ICE Box(TM), for system management. "By building the world's third fastest supercomputer, we've proven our ability to design and build complex Linux cluster systems is world-class," said Stephen Hill, president of Linux Networx. "LLNL's MCR cluster continues to be a landmark computer system as it represents the future of high-end computing in Linux clustering." Cluster Overview: Each node within the cluster contains QsNet ELAN3 by Quadrics, 4 GB of DDR SDRAM memory and 120 GB Disk Space. Linux Networx ICE BoxTM management appliance is also used to help LLNL manage and maintain the cluster. Below is the breakdown of the Linux cluster system specs. -- 7.6 teraflops Linux cluster of Dual Intel(R) Xeon(TM) processors at 2.4 GHz -- 4.6 TB of aggregate memory -- 115.2 TB of aggregate local disk space -- 1154 total nodes plus separate hot spare cluster and development cluster -- 2,304 Intel Xeon processors at 2.4 GHz -- Sub 1U Evolocity node for 1116 compute nodes -- LinuxBIOS on all nodes -- Linux Networx ICE Box Management Appliance -- Blue Arc Si7500 Storage Systems with a combined storage capacity of 115 terabytes -- Cluster File Systems, Inc. supplied the Lustre Open Source cluster wide file system