Implementing iterative solvers for irregular sparse matrix problems in high performance Fortran

  • E. de Sturler
  • D. Loher
VI Application
Part of the Lecture Notes in Computer Science book series (LNCS, volume 1336)


Writing efficient iterative solvers for irregular, sparse matrices in HPF is hard. The locality in the computations is unclear, and for efficiency we use storage schemes that obscure any structure in the matrix. Moreover, the limited capabilities of HPF to distribute and align data structures make it hard to implement the desired distributions, or to indicate these such that the compiler recognizes the efficient implementation.

We propose techniques to handle these problems. We combine strategies that have become popular in message-passing parallel programming, like mesh partitioning and splitting the matrix in local submatrices, with the functionality of HPF and HPF compilers, like the implicit handling of communication and distribution. The implementation of these techniques in HPF is not trivial, and we describe in detail how we propose to solve the problems. Our results demonstrate that efficient implementations are possible. We indicate how some of the ‘approved extensions’ of HPF-2.0 can be used, but they do not solve all problems. For comparison we show results for regular, sparse matrices.


High Performance Fortran Irregular Sparse Matrices Iterative Solvers 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    S. T. Barnard and H. D. Simon. A fast multilevel implementation of recursive spectral bisection for partitioning unstructured problems. Technical Report RNR92-033, NASA Ames Research Center, Mail Stop T045-1, Moffet Field, CA 94035, USA, 1992.Google Scholar
  2. 2.
    E. De Sturler. Iterative Methods on, Distributed Memory Computers. PhD thesis, Delft University of Technology, Delft, The Netherlands, October 1994.Google Scholar
  3. 3.
    E. De Sturler. Incomplete Block LU preconditioners on slightly overlapping subdomains for a massively parallel computer. Applied Numerical Mathematics (IMACS), 19:129–146, 1995.CrossRefGoogle Scholar
  4. 4.
    E. De Sturler and H. A. Van der Vorst. Communication cost reduction for Krylov methods on parallel computers. In W. Gentzsch and U. Harms, editors, HighPerformance Computing and Networking, Lecture Notes in Computer Science 797, pages 190–195, Berlin, Heidelberg, Germany, 1994. Springer-Verlag.Google Scholar
  5. 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. Applied Numerical Mathematics (IMACS), 18:441–459, 1995.CrossRefGoogle Scholar
  6. 6.
    F. Nataf, F. Rogier, and E. De Sturler. Domain decomposition methods for fluid dynamics. In A. Sequeira, editor, Navier-Stokes Equations and Related Nonlinear Problems, New York, 1995. Plenum Press.Google Scholar
  7. 7.
    High Performance Fortran Forum. High Performance Fortran Language Specification, version 2.0 Rice University, 1997Google Scholar
  8. 8.
    A. Pothen, H. D. Simon, and K.-P. Lion. Partitioning sparse matrices with eigenvectors of graphs. SIAM T. Matrix Anal. Appl., 11:430–452, 1990.CrossRefGoogle Scholar
  9. 9.
    Y. Saad and M. Schultz. GMRES: A generalized minimal residual algorithm for solving nonsymmetric linear systems. SIAM J. Sci. Statist. Comput., 7:856–869, 1986.CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1997

Authors and Affiliations

  • E. de Sturler
    • 1
  • D. Loher
    • 1
  1. 1.Swiss Center for Scientific Computing (SCSC-ETHZ)Swiss Federal Institute of Technology Zurich, ETH Zentrum (RZ F-11)ZurichSwitzerland

Personalised recommendations