Advertisement

Building the Teraflops/Petabytes Production Supercomputing Center

  • HorstD. Simon
  • William T. C. Kramer
  • RobertF. Lucas
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 1685)

Abstract

In just one decade, the 1990s, supercomputer centers have undergone two fundamental transitions which require rethinking their operation and their role in high performance computing. The first transition in the early to mid-1990s resulted from a technology change in high performance computing architecture. Highly parallel distributed memory machines built from commodity parts increased the operational complexity of the supercomputer center, and required the introduction of intellectual services as equally important components of the center. The second transition is happening in the late 1990s as centers are introducing loosely coupled clusters of SMPs as their premier high performance computing platforms, while dealing with an everincreasing volume of data. In addition, increasing network bandwidth enables new modes of use of a supercomputer center, in particular, computational grid applications. In this paper we describe what steps NERSC is taking to address these issues and stay at the leading edge of supercomputing centers.

Keywords

Large Hadron Collider High Performance Computing Distribute Memory Machine Supercomputer Center Stanford Linear Accelerator Center 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

References

  1. 1.
  2. 2.
    Horst D. Simon: High Performance Computing in the U.S. in 1994. Supercomputer 11 (1995) 21–31Google Scholar
  3. 3.
    Horst D. Simon: Site Report: Reinventing the Supercomputer Center at NERSC. IEEE Computational Science and Engineering Vol. 4 No. 3 (1997)Google Scholar
  4. 4.
  5. 5.
    B. Ujfalussy, X. Wang, X. Zhang, D.M.C. Nicholson, W.A. Shelton, G.M. Stocks, A. Canning, Y. Wang, and B.L. Gyorffy: High Performance First Principles Method for Complex Magnetic Properties. IEEE Proceedings of SC98, Orlando, Florida (1998)Google Scholar
  6. 6.
  7. 7.
  8. 8.
    Jon Bashor: NERSC First to Reach Goal of Seamless Shutdown, Restart of Supercomputer. http://www.lbl.gov/Science-Articles/Archive/Craycheckpointing.html (1997)
  9. 9.
    Jon Bashor: NERSC Achieves Breakthrough 93% Utilization on Cray T3E. http://www.nersc.gov/news/t3e-utilization4-19-99.html (1999)
  10. 10.
    Paul Messina: The 30Tflops Procurement at Los Alamos. Presentation (January 1999Google Scholar
  11. 11.
    David H. Bailey et al.: System Utilization Performance Effectiveness Rating (SUPER) (in preparation, 1999)Google Scholar
  12. 12.
  13. 13.
  14. 14.
  15. 15.
  16. 16.
    Keith Fitzgerald et al.: http://www.nersc.gov/groups/FSG/
  17. 17.
    Sylvia Spengler and Manfred Zorn: http://www.nersc.gov/cbcg/
  18. 18.
    Arie Shoshani et al.: http://gizmo.lbl.gov/DM.html
  19. 19.
    Ian Foster and Carl Kesselman (eds.): The Grid: Blueprint for a New Computing Infrastructure. Morgan-Kauffman (1998)Google Scholar
  20. 20.
    Ian Foster: Large-Scale Data Grids. DOE Conference on High Speed Computing, Salishan Lodge, OR (1999)Google Scholar
  21. 21.
    Brian Tierney et al.: http://www-itg.lbl.gov/DPSS/
  22. 22.
    William Johnston et al.: http://www-itg.lbl.gov/Clipper/
  23. 23.
    Jon Bashor: New Technology Demonstrates Priority Service for Internet Traffic Between Lawrence Berkeley and Argonne National Laboratories. http://www.lbl.gov/CS/Archive/headlines4-14-98.html (1998)

Copyright information

© Springer-Verlag Berlin Heidelberg 1999

Authors and Affiliations

  • HorstD. Simon
    • 1
  • William T. C. Kramer
    • 1
  • RobertF. Lucas
    • 1
  1. 1.Lawrence Berkeley National LaboratoryNational Energy Research Scientific Computing Center (NERSC)BerkeleyUSA

Personalised recommendations