Management of PDE-software for supercomputing

  • J.-Fr. Hake
  • W. Homberg
Session 4B: Compilers And Restructuring Techniques II
Part of the Lecture Notes in Computer Science book series (LNCS, volume 297)


Many scientific processes can be modeled by a solution of partial differential equations. The increasing capabilities of modern computer systems strongly contribute to the computations of numerical solutions. Strategies for efficient problem solving in this field can be established with the concept of problem solving environments. A problem solving environment (pse) can be defined as a human interface to hardware and software to assist the user in the solution of a given class of problems.

The PDE pse developed at KFA Juelich/ZAM intends to support the user in the improvement and design of new components for the environment as well as in the accurate and efficient solution of partial differential equations. Predefined commands and several model problems lead to a more intensive concentration on the problem, because routine activities are reduced. The problem description becomes the central point of the work. Special emphasis is given to interactive pre- and postprocessing; i.e. syntactical check on the correctness of the formulated problems and support for the submission of jobs to the appropriate computer systems (IBM 3081 and CRAY X-MP). An interface to graphics software provides easy-to-use facilities for the representation of numerical results.


mathematical software problem solving environment partial differential equations numerical methods 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. [ 1]
    AERE Computer Science and Systems Division, Harwell Subroutine Library — A Catalogue of Subroutines, (AERE Harwell, UK, 1984).Google Scholar
  2. [ 2]
    J. Bechlars — R. Buhtz, GKS in der Praxis (Springer-Verlag, Berlin — New York, 1986).Google Scholar
  3. [ 3]
    R.F. Boisvert — R.A. Sweet, Mathematical Software for Elliptic Boundary Value Problems, in: W.R. Cowell, Ed., Sources and Development of Mathematical Software (Prentice-Hall, Englewood-Cliffs, 1984) 200–263.Google Scholar
  4. [ 4]
    C.A. Brebbia, Ed., Finite Element Systems — A Handbook (Springer-Verlag, Berlin — New York, 1983).Google Scholar
  5. [ 5]
    T.F. Chan — F. Saied, A Comparison of Elliptic Solvers for General Two-Dimensional Regions, SIAM J. Sci. Stat. Comput. 6 (1985) 742–760.Google Scholar
  6. [ 6]
    P.M. Dew — J.E. Walsh, A Set of Library Routines for Solving Parabolic Equations in One Space Variable, ACM TOMS 7 (1981) 295–314.Google Scholar
  7. [ 7]
    J.J. Dongarra — S.C. Eisenstat, Squeezing the Most out of an Algorithm in CRAY Fortran, ACM TOMS Vol. 10 (1984) 219–230.Google Scholar
  8. [ 8]
    B. Engquist — T. Smedsaas, Automatic Computer Code Generation for Hyperbolic and Parabolic Differential Equations, SIAM J. Sci. Stat. Comput. 1 (1980) 249–259.Google Scholar
  9. [ 9]
    B. Ford (Ed.), Problem Solving Environments for Scientific Computing, (North-Holland, Amsterdam, 1986).Google Scholar
  10. [10]
    L.O. Hertzberger, The Architecture of Fifth Generation Inference Computers, FGCS 1 (1984) 9–21.Google Scholar
  11. [11]
    F. Hoßfeld, Nonlinear Dynamics: A Challenge on High-Speed Computation, in: M. Feilmeier — J. Joubert — U. Schendel, Eds., Parallel Computing 83 (North-Holland, Amsterdam, 1984) 67–80.Google Scholar
  12. [12]
    C.E. Houstis — E.N. Houstis — J.R. Rice, Partitioning and Allocation of PDE Computations in Distributed Systems, in: B. Engquist — T. Smedsaas, Eds., PDE Software, Modules, Interfaces and Systems (North-Holland, Amsterdam, 1984).Google Scholar
  13. [13]
    E.N. Houstis — T.S. Papatheodorou, High-Order Fast Elliptic Equation Solver, ACM TOMS 5 (1979) 431–441.Google Scholar
  14. [14]
    E.N. Houstis — W.F. Mitchell — J.R. Rice, Collocation Software for Second-Order Elliptical Partial Differential Equations, ACM TOMS 11 (1985) 379–412.Google Scholar
  15. [15]
    IBM VM/SP System Product: System Product Interpreter Reference, SC24-5239.Google Scholar
  16. [16]
    C.L. Lawson — R.J. Hanson — D.R. Kincaid — F.T. Krogh, Basic Linear Algebra Subprograms for Fortran Usage, ACM TOMS 5 (1979) 308–323.Google Scholar
  17. [17]
    M. Machura — R.A. Sweet, A Survey of Software for Partial Differential Equations, ACM TOMS 6 (1980) 461–488.Google Scholar
  18. [18]
    M. Machura, Problem Solving Environment for Partial Differential Equations: The User Perspective, in: B. Engquist — T. Smedsaas, Eds., PDE Software, Modules, Interfaces and Systems (North-Holland, Amsterdam, 1984).Google Scholar
  19. [19]
    J. Mackerle — T. Andersson, Boundary Element Software in Engineering, Adv. Eng. Software 6 (1983) 66–102.Google Scholar
  20. [20]
    N.K. Madsen — R.F. Sincovec, PDECOL, General Collocation Software for Partial Differential Equations, ACM TOMS 5 (1979) 326–351.Google Scholar
  21. [21]
    D.K. Melgaard — R.F. Sincovec, General Software for Two-Dimensional Nonlinear Partial Differential Equations, ACM TOMS 7 (1981) 106–125.Google Scholar
  22. [22]
    G. Meurant, The Conjugate Gradient Method on Supercomputers, Supercomputer Vol. 13 (1986) 9–17.Google Scholar
  23. [23]
    D.P. O'Leary — O. Widlund, Solution of the Helmholtz Equation for the Dirichlet Problem on General Bounded Three-Dimensional Regions, ACM TOMS 7 (1981) 239–246.Google Scholar
  24. [24]
    J.M. Ortega — R.G. Voigt, Solution of Partial Differential Equations on Vector and Parallel Computers, SIAM Review 27 (1985) 149–240.Google Scholar
  25. [25]
    W. Proskurowski, Numerical Solution of Helmholtz's Equation by Implicit Capacitance Matrix Methods, ACM TOMS 5 (1979) 36–49.Google Scholar
  26. [26]
    J.R. Rice, Software Parts for Elliptic PDE Software, in: B. Engquist — T. Smedsaas, Eds., PDE Software, Modules, Interfaces and Systems (North-Holland, Amsterdam, 1984).Google Scholar
  27. [27]
    J.R. Rice — R.F. Boisvert, Elliptic Problem Solving with ELLPACK (Springer-Verlag, Berlin — New York, 1985).Google Scholar
  28. [28]
    J.R. Rice — E.N. Houstis — W.R. Dyksen, A Population of Linear, Second Order Elliptic Partial Differential Equations on Rectangular Domains, Math. Comp. 36 (1981) 475–484.Google Scholar
  29. [29]
    M.K. Seager, Parallelizing Conjugate Gradient for the CRAY X-MP, Parallel Computing Vol. 3 (1986) 35–47.Google Scholar
  30. [30]
    G. Sewell, Analysis of a Finite Element Method. PDE/PROTRAN. (Springer-Verlag, Berlin — New York, 1985).Google Scholar
  31. [31]
    R.F. Sincovec — N.K. Madsen, Software for Nonlinear Partial Differential Equations, ACM TOMS 1 (1975) 232–260.Google Scholar
  32. [32]
    B.P. Sommeijer — P.J. van der Houwen, Software with Low Storage Requirements for Two-Dimensional Parabolic Differential Equations, ACM TOMS 10 (1984) 378–396.Google Scholar
  33. [33]
    P.N. Swartztrauber — R.A. Sweet, Efficient FORTRAN Subprograms for the Solution of Separable Elliptic Partial Differential Equations, ACM TOMS 5 (1979) 352–364.Google Scholar
  34. [34]
    A. van der Steen, Results on the Livermore Loops on some new Supercomputers, Supercomputer Vol. 12 (1986) 13–14.Google Scholar
  35. [35]
    H.A. van der Vorst, The Performance of Fortran Implementations for Preconditioned Conjugate Gradients on Vector Computers, Parallel Computing Vol. 3 (1986) 49–58.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1988

Authors and Affiliations

  • J.-Fr. Hake
    • 1
  • W. Homberg
    • 1
  1. 1.Zentralinstitut fuer Angewandte Mathematik (ZAM) Kernforschungsanlage Juelich GmbH (KFA)JuelichFed. Rep. of Germany

Personalised recommendations