Summary Photograph of NERSC in Oakland, taken by me. Licensing PD self date October 2006 Copy to Wikimedia Commons bot Fbot Orphan image ... more details
File NERSC Hopper.jpg thumb NERSC Hopper The http www.nersc.gov National Energy Research Scientific Computing Center , or NERSC for short, is a designated user facility operated by Lawrence Berkeley National Laboratory and the United States Department of Energy Department of Energy . It contains several Cluster computing cluster supercomputer s, the largest of which is Hopper, which is ranked 5th on the TOP500 list of world s fastest supercomputers as of November 2010. It is located in Oakland, California . History NERSC was founded in 1974 at Lawrence Livermore National Laboratory , then called the Controlled Thermonuclear Research Computer Center or CTRCC and consisting of a Control Data Corporation 6600 computer. Over time, it expanded to contain a CDC 7600, then a Cray 1 SN 6 which was called the c machine, and in 1985 the world s first Cray 2 SN 1 which was the b machine, nicknamed bubbles because of the bubbles visible in the fluid of its unique direct liquid cooling system. In the early eighties, CTRCC s name was changed to the National Magnetic Fusion Energy Computer Center or NMFECC. The name was again changed in the early nineties to National Energy Research Supercomputer Center. In 1996 NERSC moved from LLNL to LBNL . In 2000, it was moved to its current location in Oakland . Computers and projects NERSC s fastest computer, Hopper, a Cray XE6 named in honor of Grace Hopper , a pioneer in the field of software development and programming languages and the creator of the first compiler. It has 153,308 Opteron processor cores and runs the Suse Linux operating system. Other systems at NERSC are named Franklin, Carver, Magellan, Dirac, Euclid, Tesla, Turing, and PDSF ... High Performance Storage System HPSS installation. NERSC facilities are accessible through the Energy Sciences Network or ESnet, which was created and is managed by NERSC. External links http www.nersc.gov NERSC main website http www.nersc.gov about history.php NERSC history http www.es.net ESnet ... more details
ViVA Vi rtual V ector A rchitecture is a technology from IBM for coupling together multiple Scalar computing scalar floating point unit s to act as a single vector processor . Certain computing tasks are more efficiently handled through vector computations where an instruction can be applied to multiple elements simultaneously, rather than the scalar approach where one instruction is applied to one piece of data at a time. This kind of technology is highly sought after for scientific computing and is IBM s answer to the vector based supercomputer s pioneered by Cray and that was the basis for NEC s Earth Simulator which was the fastest supercomputer in the world 2002 2004. ViVA was developed and implemented by IBM together with National Energy Research Scientific Computing Center inside the Blue Planet project where they had 8 dual core POWER5 processors made into one vector processor capable of approximately 60 80 FLOPS GFLOPS of computing power. ViVA technology is in use in the ASC Purple supercomputer. Where ViVA was a software implementation in high end POWER5 based systems, the second generation, ViVA 2 , is directly supported by hardware in the POWER6 processor. References http news.com.com IBM supercomputing goes retro 2100 1010 3 5425551.html IBM supercomputing goes retro CNet http www.nersc.gov news reports blueplanetmore.php Blue Planet Extending IBM Power Technology and Virtual Vector Processing NERSC http www.es.jamstec.go.jp esc images jes vol.2 pdf JES2 1Horst 20Simon.pdf Science Driven System Architecture A New Process for Leadership Class Computing NERSC http www.realworldtech.com page.cfm?ArticleID RWT121905001634 An eCLipz Looms on the Horizon Real World Technologies Category Power Architecture ViVA ja IBM ViVA ... more details
research through the National Energy Research Scientific Computing Center NERSC at Lawrence ... of the resources at NERSC were allocated to INCITE awardees. However, demand for supercomputing resources ... more details
to support intensive robust data movement between BNL to NERSC at a rate of about 10,000 files about ... by several facilities including BNL, NERSC, FNAL, CERN, TJNAF, ORNL and NCAR, and other facilities ... Project to provide transparent access from multiple remote storage systems at NERSC, NCAR, ORNL, LLNL ... more details
was between two observations . There are 7 of them Global MFC Mercator Ocean Arctic MFC NERSC Baltic ... the main parties INGV, Met Office, NERSC, DMI, Ifremer, CLS and Mercator Ocean The Chairmen of the Advisory ... more details
Image Cray2.jpeg thumb A Cray 2 operated by NASA Image Cray2.jpg thumb A Cray 2 and its Fluorinert cooling waterfall , formerly serial number 2101, the only 8 processor system ever made, for NERSC File Cray 2 1985.jpg thumb Front view of 1985 Supercomputer Cray 2, Mus e des Arts et M tiers , Paris File 1985 Cray 2 side view.jpg thumb Side view of 1985 Supercomputer Cray 2, Mus e des Arts et M tiers , Paris Image EPFL CRAY II 1.jpg thumb Detail of the upper part of the Cray 2 Image EPFL CRAY II 2.jpg thumb Inside of the Cray 2 Unreferenced date January 2008 The Cray 2 was a four processor ECL vector processor vector supercomputer made by Cray Cray Research starting in 1985 . It was the fastest machine in the world when it was released, replacing the Cray Cray Research Cray X MP X MP designed by Steve Chen computer engineer Steve Chen in that spot. The Cray 2 was capable of 1.9 FLOPS GFLOPS peak performance and was only bumped off of the top spot by the ETA10 ETA 10G in 1990 . Initial design With the successful launch of his famed Cray 1 , Seymour Cray turned to the design of its successor. By 1979 he had become fed up with management interruptions in what was now a large company, and as he had done in the past, decided to resign his management post and move to form a new lab. As with his original move to Chippewa Falls, Wisconsin from Control Data HQ in Minneapolis, MN , Cray management understood his needs and supported his move to a new lab in Boulder, Colorado . Working as an independent consultant at these new Cray Labs, he put together a team and started on a completely new design. This Lab would later close, and a decade later a new facility in Colorado Springs would open. Cray had previously attacked the problem of increased speed with three simultaneous advances more functional units to give the system higher parallelism, tighter packaging to decrease signal delays, and faster components to allow for a higher clock speed. The classic example of this design is ... more details
File Top500.svg thumb 300px right Total computational power of the 500 most powerful computer systems in the world, 1993 2010. Note the logarithmic scale . The TOP500 project ranks and details the 500 non distributed computing distributed most powerful known computer systems in the world. The project was started in 1993 and publishes an updated list of the supercomputers twice a year. The first of these updates always coincides with the International Supercomputing Conference in June, the second one is presented in November at the Supercomputing Conference ACM IEEE Supercomputing Conference . The project aims to provide a reliable basis for tracking and detecting trends in high performance computing and bases rankings on http www.netlib.org benchmark hpl HPL , a portable implementation of the High Performance LINPACK Benchmark computing benchmark written in Fortran for distributed memory computers. The TOP500 list is compiled by Hans Meuer of the University of Mannheim , Germany , Jack Dongarra of the University of Tennessee , Knoxville, and Erich Strohmaier and Horst Simon of NERSC Lawrence Berkeley National Laboratory . Project history In the early 1990s, a new definition of supercomputer was needed to produce meaningful statistics. After experimenting with metrics based on processor count in 1992, the idea was born at the University of Mannheim to use a detailed listing of installed systems as the basis. Early 1993 Jack Dongarra was persuaded to join the project with his Linpack benchmark. A first test version was produced in May 1993, partially based on data available on the Internet, including the following sources ref http www.hpcwire.com archives 10219.html AN INTERVIEW WITH JACK DONGARRA by Alan Beck, editor in chief HPCwire Bot generated title ref ref http www.netlib.org benchmark top500 reports report93 section2 16 4.html Statistics on Manufacturers and Continents Bot generated title ref http www.hoise.com primeur PL 96 pl top500 ES PL 11 96 4.html List of ... more details
Encyclopedia
top
