Advertisement

Parallel Access to Persistent Multidimensional Arrays from HPF Applications Using Panda

  • Peter Brezany
  • Przemysław Czerwiński
  • Artur Świetanowski
  • Marianne Winslett
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 1823)

Abstract

A critical performance issue for a number of scientific and engineering applications is the efficient transfer of data to secondary storage. Languages such as High Performance Fortran (HPF) have been introduced to allow programming distributed-memory systems at a relatively high level of abstraction. However, the present version of HPF does not provide appropriate constructs for controlling the parallel I/O capabilities of these systems. In this paper, constructs to specify parallel I/O operations on multidimensional arrays in the context of HPF are proposed. The paper also presents implementation concepts that are based on the HPF compiler developed at the University of Vienna and the parallel I/O runtime system Panda developed at the University of Illinois. Experimental performance results are discussed in the context of financial management and traffic simulation applications.

Keywords

Pension Fund Language Construct Simulation Application Secondary Storage Application Case Study 
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.
    F. Bassow. IBM AIX Parallel I/O File System: Installation, Administration, and Use, IBM, May 1995. Document Number SH34-6065-00.Google Scholar
  2. 2.
    S. Benkner et al. “VFC-The Vienna HPF+ Compiler”, Proc. of the Int. Conf. on Compilers for Parallel Computers, Linkoping, Sweden, June 29–July 1, 1998.Google Scholar
  3. 3.
    R. R. Bordawekar and A. N. Choudhary. Language and compiler support for parallel I/O. In IFIP Working Conference on Programming Environments for Massively Parallel Distributed Systems. Swiss, April 1994.Google Scholar
  4. 4.
    P. Brezany, M. Gerndt, P. Mehrotra, and H. Zima. Concurrent file operations in a High Performance FORTRAN. In Proceedings of Supercomputing’ 92, pages 230–237, 1992.Google Scholar
  5. 5.
    P. Brezany and M. Winslett. Advanced Data Repository Support for Java Scientific Programming. HPCN Europe 1999, Springer-Verlag, LNCS 1593, pp. 1127–1136.Google Scholar
  6. 6.
    P. Ciaccia and A. Veronesi. Dynamic Declustering Methods for Parallel Grid Files. Proc. of the Conference “Parallel Computation”, Klagenfurt, September 1996, Springer-Verlag, LNCS 1127, pp. 110–123.Google Scholar
  7. 7.
    Nils Nieuwejaar and David Kotz. The Galley parallel file system. In Proceedings of the 10th ACM International Conference on Supercomputing, May 1996.Google Scholar
  8. 8.
    K. E. Seamons and M. Winslett. Multidimensional Array I/O in Panda 1.0. Journal of Supercomputing, Vol. 10, No. 2, pages 191–211.Google Scholar
  9. 9.
    M. Snir. Proposal for I/O. Posted to HPFF I/O Forum, July 1992.Google Scholar
  10. 10.
    E. Dockner, H. Moritsch, G.Ch. Pflug, and A. Swiętanowski. The Aurora financial management system. Techn. rep. Aurora TR1998-08, Vienna University, 1998.Google Scholar
  11. 11.
    G.Ch. Pflug and A. Świetanowski. Dynamic asset allocation under uncertainty for pension fund management. To appear in Control and Cybernetics.Google Scholar
  12. 12.
    E. Schikuta, T. Fuerle and Helmut Wanek. ViPIOS: The Vienna Parallel Input/Output System. In Proc. Euro-Par’98, Southampton, England, Springer-Verlag, LNCS.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2000

Authors and Affiliations

  • Peter Brezany
    • 1
  • Przemysław Czerwiński
    • 1
  • Artur Świetanowski
    • 2
  • Marianne Winslett
    • 3
  1. 1.Institute for Software ScienceUniversity of ViennaViennaAustria
  2. 2.Department of Statistics, Operations Research and Computer MethodsUniversity of ViennaViennaAustria
  3. 3.Database Research Laboratory, Department of Computer ScienceUniversity of IllinoisUrbanaUSA

Personalised recommendations