Skip to main content
SpringerLink
Log in

Communication cost reduction for Krylov methods on parallel computers

  • Numerical Algorithms for Engineering
  • Conference paper
  • First Online:
Book cover High-Performance Computing and Networking (HPCN-Europe 1994)

Part of the book series: Lecture Notes in Computer Science ((LNCS,volume 797))

Included in the following conference series:

Abstract

On large distributed memory parallel computers the global communication cost of inner products seriously limits the performance of Krylov subspace methods [3]. We consider improved algorithms to reduce this communication overhead, and we analyze the performance by experiments on a 400-processor parallel computer and with a simple performance model.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Log in via an institution

Institutional subscriptions

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. Z. Bai, D. Hu, and L. Reichel. A Newton basis GMRES implementation. Technical Report 91-03, University of Kentucky, 1991.

    Google Scholar 

  2. J. W. Demmel, M. T. Heath, and H.A. van der Vorst. Parallel numerical linear algebra. Acta Numerica Vol 2, Cambridge Press, New York, 1993

    Google Scholar 

  3. E. De Sturler. A parallel restructured version of GMRES(m). Technical Report 91-85, Delft University of Technology, Delft, 1991.

    Google Scholar 

  4. E. De Sturler. A parallel variant of GMRES(m). In R. Vichnevetsky, J. H. H. Miller, editors, Proc. of the 13th IMACS World Congress on Computation and Applied Mathematics, IMACS, Criterion Press Dublin 1991, pp 682–683.

    Google Scholar 

  5. E. De Sturler and H. A. Van der Vorst. Reducing the effect of global communication in GMRES (m) and CG on Parallel Distributed Memory Computers. Technical Report 832, Mathematical Institute, University of Utrecht, Utrecht, 1993

    Google Scholar 

  6. M. R. Hestenes and E. Stiefel. Methods of conjugate gradients for solving linear systems. J. Res. Natl. Bur. Stand., 49:409–436, 1954.

    Google Scholar 

  7. Y. Saad and M. H. Schultz. GMRES: a generalized minimal residual algorithm for solving nonsymmetric linear systems. SIAM J. Sci. Statist. Comput., 7:856–869, 1986.

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Swiss Scientific Computing Center CSCS-ETHZ, Via Cantonale, CH-6928, Manno, Switzerland

    E. de Sturler

  2. Mathematical Institute, Utrecht University, Budapestlaan 6, Utrecht, The Netherlands

    H. A. van der Vorst

Authors
  1. E. de Sturler
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. H. A. van der Vorst
    View author publications

    You can also search for this author in PubMed Google Scholar

Editor information

Wolfgang Gentzsch Uwe Harms

Rights and permissions

Reprints and permissions

Copyright information

© 1994 Springer-Verlag Berlin Heidelberg

About this paper

Cite this paper

de Sturler, E., van der Vorst, H.A. (1994). Communication cost reduction for Krylov methods on parallel computers. In: Gentzsch, W., Harms, U. (eds) High-Performance Computing and Networking. HPCN-Europe 1994. Lecture Notes in Computer Science, vol 797. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-57981-8_115

Download citation

  • DOI: https://doi.org/10.1007/3-540-57981-8_115

  • Published:

  • Publisher Name: Springer, Berlin, Heidelberg

  • Print ISBN: 978-3-540-57981-6

  • Online ISBN: 978-3-540-48408-0

  • eBook Packages: Springer Book Archive

Publish with us

Policies and ethics

Search

Navigation