A Compact, Thread-Safe Communication Library for Efficient Cluster Computing

  • M. Danelutto
  • C. Pucci
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 1823)

Abstract

We describe a compact, thread-safe communication library for cluster computing. The library provides the most used communication functions, such as point-to-point send/receives and broadcast, scatter and gather collective operations. In addition, our library allows processes running on different processing elements of a cluster to share portions of memory. We show experimental results that demonstrate the library outperforms classical implementations of MPI (mpich) in collective operations and achieves comparable performance in point-to-point communications on Beowulf class workstation clusters.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    M. Baker and R. Buyya. Cluster Computing at a Glance. In Rajkumar Buyya, editor, High Performance Cluster Computing, pages 3–47. Prentice Hall, 1999.Google Scholar
  2. 2.
    W. Gropp and E. Lusk. The MPI communication library: its design and a portable implementation. In Proceedings of the Scalable Parallel Libraries Conference, pages 160–165. IEEE Computer Society Press, October 1993. Mississippi.Google Scholar
  3. 3.
    Al Geist, Adam Beguelin, Jack Dongarra, Weicheng Jiang, Robert Manchek, and Vaidy Sunderam. PVM 3 Users Guide and Reference Manual. Technical report, Oak Ridge National Laboratory, September 1994.Google Scholar
  4. 4.
    William D. Gropp and Ewing Lusk. User’s Guide mpich, a Portable Implementation of MPI. Technical Report ANL-96/6, Mathematics and Computer Science Division, Argonne National Laboratory, 1996.Google Scholar
  5. 5.
    A. Beguelin, J. Dongarra, A. Geist, R. Manchek, and V. Sunderam. A User’s Guide to PVM (Parallel Virtual Machine). Technical Report TM-11826, Oak Ridge National Laboratory, June 1991.Google Scholar
  6. 6.
    W. Richard Stevens. UNIX Network Programming. Prentice Hall, 1999. Second Edition, Vol. 1 and 2.Google Scholar
  7. 7.
    S._J. Norton and M. D. DiPasquale. THREADTIME The multithreaded programming guide. Prentice Hall, 1997.Google Scholar
  8. 8.
    R. Rabenseifner, P. Gottshling, W. E. Nagel, and S. Seidl. Effective performance problem detection of MPI programs on MPP systems: From the global view to the detail. In Proceedings of the ParCo’99 Conference — Parallel Computing, 1999.Google Scholar
  9. 9.
    Andrews S. Tanenbaum. Computer Networks. Prentice Hall, 1997.Google Scholar
  10. 10.
    Cray Resarch Inc. Cray C/C++ Reference Manual. Technical Report SR-2196, Cray Research Inc., 1998.Google Scholar
  11. 11.
    W.D. Gropp, E. Lusk, N. Doss, and A. Skjellum. An high-performance, portable implementation of the MPI message passing interface standard. Parallel Computing, September 1996.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2000

Authors and Affiliations

  • M. Danelutto
    • 1
  • C. Pucci
    • 1
  1. 1.Dept. Computer ScienceUniversity of PisaItaly

Personalised recommendations