Parallel calculations on the wind-driven oceanic circulation using Fourier pseudospectral methods

ABSTRACT

The shallow-water equations for the wind-driven oceanic circulation were solved in parallel, using Fourier pseudospectral methods. A domain decomposition approach was used to perform two-dimensional Fast Fourier Transforms (2-D FFTs), as part of a computational scheme for the parallel solution of the time dependent partial differential equations. The algorithm was implemented using a shared memory approach, and tested on the ACE experimental multiprocessor workstation. The performance of the parallel code, including timings for execution, processor intercommunication and synchronization is discussed. It was found that the parallel efficiency of the method is satisfactory for reasonable problem sizes.

REFERENCES

• 1: D. Bernstein, K. So. "PREFACE- A Fortran Preprocessor for Parallel Workstation Systems". IBM Research Report RC. 13600, 1988.
• 2: Christidis, Z. D. and V. Sonnad. Parallel Implementation of a Pseudospc(:t.r~l Method on Loosely Coupled Array of Processors, Pro(:ccdings of the Third International Conference on Supercomputing (ICS88, Boston), May 1988.
• 3: Christidis, Z. D., V. Sonnad, and D. Logan. Parallel Implementation of a 2-D Fast Fourier Transform on a Loosely Coupled Array of Processors. iBM Kingston Technical Report, KGN-68, January 1987.
• 4: Csanady G. T., 1982: Circulation in the Coastal Ocean. D. Reidel Publishing Company, Dordrecht, Holland 245 pp.
• 5: Darema F., 1978: Parallel Applications Development for Shared Memory Systems. Parallel Systems and Corn, putations, 237-254.
• 6: A. GarciaL, D. Foster, R. Freitas. "The Advanced Computing Environment Multiprocessor Workstation''. IBM Research Report RC. 14491, March 1989.
• 7: Gottlicb D., 'and S. A. Orszag, 1977: Numerical Anali/sis of Spectral Methods: Theory and Applications. SIAM, Philadelphia, PA, 200 pp.
• 8: Haltin(;r G. J., and R. T. Williams, 1979. Numerical Prediction and Dynamic Meteorology., Wiley, 477 pp.
• 9: Neumann G. and W. J. Pierson Jr., 1966: Principles of l~h,#.sical Oceanography. Prendice-Hall, 545 pp.
• 10: ()rszag S. A., 1972: Comparison ofpseudospectraJ and spectral approximation. Stud. Appl. Math., 51,253-259.
• 11: Pcdlosky J. 1979: Geophysical Fluid Dynamics. Springcr-Verlag, New York 624 pp.
• 12: Raclin G. 1983: The 801 Minicomputer, IBM ,Journal of Rc,~earch and Development, Vol 27, No. 3, pp. 237-246.
• 13: Yanenco N. A., 1971: The Method of Fractional steps. Springer-Vcrlag, Heidelberg, Germany 160 pp.
• 14: Yu T. W., 1988: A Method for Determining Equivalent Depths of the Atmospheric Boundary Layer Over the Oceans. J. Geophys. Res., 93(C4), 3655-3661, 1988.
• 15: Zlatev Z., R. Berkowicz and L. Prahm, 1983: Three-dimensional Advection-Diffusion Modeling for R egioi~al Scale. Atmospheric Environment, 17, 491-.t99.

INDEX TERMS

Primary Classification:
  F. Theory of Computation
  F.1 COMPUTATION BY ABSTRACT DEVICES
      F.1.2 Modes of Computation
          Subjects: Parallelism and concurrency

Additional Classification:
  C. Computer Systems Organization
  C.1 PROCESSOR ARCHITECTURES
  C.5 COMPUTER SYSTEM IMPLEMENTATION
      C.5.1 Large and Medium ("Mainframe") Computers
          Subjects: Super (very large) computers

  F. Theory of Computation
  F.2 ANALYSIS OF ALGORITHMS AND PROBLEM COMPLEXITY
      F.2.1 Numerical Algorithms and Problems
          Subjects: Computation of transforms (e.g., fast Fourier transform)

  J. Computer Applications
  J.2 PHYSICAL SCIENCES AND ENGINEERING
      Subjects: Earth and atmospheric sciences

General Terms:
Algorithms, Design, Measurement, Performance, Theory