Advertisement

Performance of Scientific Software

  • E. N. Houstis
  • J. R. Rice
  • C. C. Christara
  • E. A. Vavalis
Part of the The IMA Volumes in Mathematics and Its Applications book series (IMA, volume 14)

Abstract

We review performance methodologies used for the evaluation of scientific software in von Neumann architectures. A prototype evaluation facility for second order elliptic partial differential equation (PDE) solvers is described which realizes the main objectives of these methodologies. Finally, the results of an evaluation study for a new class of spline collocation solvers for elliptic PDEs are presented.

Keywords

Elliptic PDEs Performance Evaluation System Spline Collocation Method Smooth Spline Human Readable Form 
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]
    Boisvert, R.F., E.N. Houstis and J.R. Rice, A system for the performance evaluation of partial differential equations software, IEEE Trans. Softw. Eng., 5 (1979), pp. 418–425.CrossRefGoogle Scholar
  2. [2]
    Boisvert, R.F., Languages and software parts for elliptic boundary-value problems, The role of languages in problem solving 2 (J.C. Boudreaux, B.W. Hamill and R. Jernigan, eds. ), Elsevier Science Publishers (1987), pp. 411–431.Google Scholar
  3. [3]
    Bonomo, J., W.R. Dyksen and J.R. Rice, The ELLPACK performance evaluation system, Purdue University, Computer Science Department, Report CSD-TR 569 (1986), 23 pages.Google Scholar
  4. [4]
    Crowder, H., R.S. Dembo and J.M. Mulvey, On reporting computational experiments with mathematical software, ACM Trans. Math. Software, 5 (1979), pp. 193–203.CrossRefGoogle Scholar
  5. [5]
    ]Dyksen, W.R., E.N. Houstis, R.E. Lynch and J.R. Rice, The performance of the collocation and Galerkin methods with Hermite Bicubics, SIAM J. Numer. Anal., 21 (1984), pp. 695–715.Google Scholar
  6. [6]
    Hollander M. and D.A. Wolfe, Non parametric Statistics, Chap. 7, Wiley, New York (1973).Google Scholar
  7. [7]
    Houstis, E.N., C.C. Christara and J.R. Rice, Quadratic spline collocation methods for two point boundary value problems, Int. J. Numerical Methods Eng. to appear.Google Scholar
  8. [8]
    Houstis, C.E., E.N. Houstis and J.R. Rice, Partitioning PDE computations: Methods and performance evaluation, J. Parallel Comp., 4 (1987), pp. 141–163.MathSciNetCrossRefGoogle Scholar
  9. [9]
    Houstis, E.N. and M. Irodotou-Ellina, An 0(h6) quintic spline collocation method for fourth order two point boundary value problems, Purdue University, Computer Science Department, Report CSD-TR 616 (1986), 32 pages.Google Scholar
  10. [10]
    Houstis, E.N and J.R. Rice, High order methods for elliptic partial differential equations with singularities, Int. J. Numerical Methods Eng., 18 (1982), pp. 737–754.MathSciNetCrossRefMATHGoogle Scholar
  11. [11]
    Houstis, E.N. and J.R. Rice, An experimental design for the computational evaluation of partial differential equation solvers, The Production and Assessment of Numerical Software (M. Delves and M.A. Hennell, eds. ), Academic Press (1980), pp. 57–66.Google Scholar
  12. [12]
    Houstis, E.N., E.A. Vavalis and J.R. Rice, Convergence of an 0 (h 4 ) cubic spline collocation method for elliptic partial differential equations, SIAM J. Numer. Anal. to appear.Google Scholar
  13. [13]
    Lyness, J.N., Performance profiles and software evaluation, Performance Evaluation of Numerical Software, (L.D. Fosdick, ed. ), North-Holland (1979), pp. 51–58.Google Scholar
  14. [14]
    Rice, J.R., The algorithm selection problem, Advances in Computers, 15, (Rubicoff and Yovits, eds.), Academic Press (1976), pp. 65–118.Google Scholar
  15. [15]
    Rice, J.R, Methodology for the algorithm selection problem, Performance Evaluation of Numerical Software, (L. Fosdick, ed. ), Horth-Holland (1979), pp. 301–307.Google Scholar
  16. [16]
    Rice, J.R., Performance analysis of 13 methods to solve the Galerkin method equations, J. Lin. Algebra Applica., 52/53 (1983), pp. 533–546.Google Scholar
  17. [17]
    Rice, J.R., Design of a tensor product population of PDE problems, CSD-TR 628, Computer Science Department, Purdue University (1986), 12 pages.Google Scholar
  18. [18]
    Rice, J.R. and R.F. Boisvert, Solving Elliptic Problems with ELLPACK, Springer-Verlag, New York (1985).CrossRefGoogle Scholar
  19. [19]
    Rice, J.R, E.N. Houstis and W.R. Dyksen, A population of linear second order, elliptic partial differential equations on rectangular domains, Math. Comp., 36 (1981), pp. 475–484.MathSciNetMATHGoogle Scholar

Copyright information

© Springer-Verlag New York Inc. 1988

Authors and Affiliations

  • E. N. Houstis
    • 1
  • J. R. Rice
    • 1
  • C. C. Christara
    • 1
  • E. A. Vavalis
    • 1
  1. 1.Department of Computer SciencesPurdue UniversityUSA

Personalised recommendations