Advertisement

On Line Visualisation or Combining the Standard ORNL PVM with a Vendor PVM Implementation

  • Janusz Borkowski
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 1697)

Abstract

Vendor implementations of PVM provide optimum performance on multicomputers. However, such implementations may lack interoperability. Developing of a real time display for a LGA simulation on Hitachi SR2201 parallel computer required a connection between the calculating part running on SR2201 and GUI running on a graphics workstation. A native PVM could not provide it. We proposed to use ORNL PVM to facilitate the connection and at the same time to use the native PVM for effective internal communication. Performance evaluation of this approach and practical results are presented.

Keywords

Virtual Machine Parallel Application Message Size External Communication Communication Library 
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.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Janusz Borkowski.Google Scholar
  2. 2.
    T. Kimura and H. Takemiya: Local Area Metacomputing for Multidisciplinary Problems: A Case Study for Fluid/Structure Coupled Simulation, in Proceedings of International Conference of Supercomputing ICS 98 Melbourne, Australia, ACM 1998 0-89791-998-X pp 149–156.CrossRefGoogle Scholar
  3. 3.
    Graham Fagg and Jack Dongarra, PVMPI: An Integration of PVM and MPI Systems, Calculateurs Paralleles, Volume 8, Number 2, 1996, pp 151–166, Hermes, ISSN: 1260-3198.Google Scholar
  4. 4.
    T. Beisel, E. Gabriel and M. Resch, “An Extension of MPI for Distributed Computing on MPPs” in Recent Advances in Parallel Virtual Machine and Message Passing Interface, LNCS, Springer 1997, pp. 75–83.Google Scholar
  5. 5.
    http://www.isye.gatech.edu/chmsr/jPVM/ jPVM: A Native Methods Interface to PVM for the Java Platform.
  6. 6.
    H. Fujii, Y. Yasuda, H. Akashi, Y. Inagami, M. Koga, O. Ishihara, M. Kashiyama, H. Wada and T. Sumitomo, “Architecture and performance of the Hitachi SR2201 Massively Parallel Processor System” Proceedings of the 11th International Parallel Processing Symposium, Geneva 1997.Google Scholar
  7. 7.
    J. Hardy, Y. Polmeau & O. de Pazzis, “Time evolution od two-dimensional model system. I. Invariant states and time correletion functions.” J.Math. Phys 14 (1973) pp. 1746–1759.CrossRefGoogle Scholar
  8. 8.
    U. Frisch, B. Hasslacher & Y. Pomeau, “Lattice-gas automata for Navier-Stokes equation” Phys. Rev. Lett. 56 (1986) pp. 1505–1508.CrossRefGoogle Scholar
  9. 9.
    http://poseidon.ulb.ac.be/simulations/intro_en.html Introduction to lattice gas automata.
  10. 10.
    V.S. Sunderam “PVM: A Framework for Parallel Distributed Computing”, Journal of Concurrency: Practice and Experience” pp. 315–339, Dec 1990.Google Scholar
  11. 11.
    http://www.avs.com Home Page of Advance Visual Systems.

Copyright information

© Springer-Verlag Berlin Heidelberg 1999

Authors and Affiliations

  • Janusz Borkowski
    • 1
  1. 1.Polish-Japanese Institute for Information TechnologyWarsawPoland

Personalised recommendations