Lawrence Livermore National Laboratory - Largest Computers

Largest Computers

Throughout its history, LLNL has been a leader in computers and scientific computing. Even before the Livermore Lab opened its doors, E.O. Lawrence and Edward Teller recognized the importance of computing and the potential of computational simulation. Their purchase of one of the first UNIVAC computers, set the precedent for LLNL’s history of acquiring and exploiting the fastest and most capable supercomputers in the world. A succession of increasingly powerful and fast computers have been used at the Lab over the years:

  • 1953 Remington-Rand UNIVAC 1 (Universal Automatic Computer)
  • 1954 IBM 701
  • 1956 IBM 704
  • 1958 IBM 709
  • 1960 IBM 7090
  • 1960 Remington-Rand LARC (Livermore Advanced Research Computer)
  • 1961 IBM 7030 (Stretch)
  • 1963 IBM 7094
  • 1963 CDC 1604
  • 1963 CDC 3600
  • 1964 CDC 6600
  • 1969 CDC 7600
  • 1974 CDC STAR 100
  • 1978 Cray-1
  • 1984 Cray X-MP
  • 1985 Cray-2
  • 1989 Cray Y-MP
  • 1992 BBN Butterfly
  • 1994 Meiko CS-2
  • 1995 Cray C90
  • 1995 Cray T3D
  • 1998 IBM ASCI Blue Pacific
  • 2000 IBM ASCI White
  • 2004 Thunder
  • 2005 IBM Blue Gene/L
  • 2005 ASC Purple
  • 2006 Zeus
  • 2006 Rhea
  • 2006 Atlas
  • 2007 Minos
  • 2012 IBM Sequoia

The November 2007 release of the 30th TOP500 list of the 500 most powerful computer systems in the world, has LLNL’s Blue Gene/L computer in first place for the seventh consecutive time. Five other LLNL computers are in the top 100. However, the November 2008 release of the TOP500 list places the Blue Gene/L supercomputer behind the Pleiades supercomputer in NASA/Ames Research Center, the Jaguar supercomputer in Oak Ridge National Laboratory, and the IBM Roadrunner supercomputer in Los Alamos National Laboratory. Currently, the Blue Gene/L computer can sustain 478.2 trillion operations per second, with a peak of 596.4 trillion operations per second.

On June 22, 2006, researchers at LLNL announced that they had devised a scientific software application that sustained 207.3 trillion operations per second. The record performance was made at LLNL on Blue Gene/L, the world's fastest supercomputer with 131,072 processors. The record was a milestone in the evolution of predictive science, a field in which researchers use supercomputers to answer questions about such subjects as: materials science simulations, global warming, and reactions to natural disasters.

LLNL has a long history of developing computing software and systems. Initially, there was no commercially available software, and computer manufacturers considered it the customer’s responsibility to develop their own. Users of the early computers had to write not only the codes to solve their technical problems, but also the routines to run the machines themselves. Today, LLNL computer scientists focus on creating the highly complex physics models, visualization codes, and other unique applications tailored to specific research requirements. A great deal of software also has been written by LLNL personnel to optimize the operation and management of the computer systems, including operating system extensions such as CHAOS (Linux Clustering) and resource management packages such as SLURM. The Peloton procurements in late 2006 (Atlas and other computers) were the first in which a commercial resource management package, Moab, was used to manage the clusters.

Read more about this topic:  Lawrence Livermore National Laboratory

Famous quotes containing the word largest:

    Given for one instant an intelligence which could comprehend all the forces by which nature is animated and the respective positions of the beings which compose it, if moreover this intelligence were vast enough to submit these data to analysis, it would embrace in the same formula both the movements of the largest bodies in the universe and those of the lightest atom; to it nothing would be uncertain, and the future as the past would be present to its eyes.
    Pierre Simon De Laplace (1749–1827)