Advertisement

Multiple data parallelism with HPF and KeLP

  • John H. Merlin
  • Scott B. Baden
  • Stephen J. Fink
  • Barbara M. Chapman
4. HPF+ Workshop
Part of the Lecture Notes in Computer Science book series (LNCS, volume 1401)

Abstract

High Performance Fortran (HPF) is an effective language for implementing regular data parallel applications on distributed memory architectures, but it is not well suited to irregular, block-structured applications such as multiblock and adaptive mesh methods. A solution to this problem is to use a non-HPF SPMD program to coordinate multiple concurrent HPF tasks, each operating on a regular subgrid of an irregular data domain. To this end we have developed an interface between the C++ class library KeLP, which supports irregular, dynamic block-structured applications on distributed systems, and an HPF compiler, SHPF. This allows KeLP to handle the data layout and inter-block communications, and to invoke HPF concurrently on each block. There are a number of advantages to this approach: it combines the strengths of both KeLP and HPF; it is relatively easy to implement; and it involves no extensions to HPF or HPF compilers. This paper describes the KeLP-HPF implementation and programming model, and shows an example KeLP-HPF multiblock solver.

Keywords

Message Passing Interface Class Library Adaptive Mesh Refinement Data Layout Regular Data 
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.
    High Performance Fortran Forum: High Performance Fortran Language Specification version 2.0. URL: http://www.crpc.rice. edu/HPFF/hpf2/ or http://www.vcpc.univie.ac.at/information/mirror/HPFF/hpf2/.Google Scholar
  2. 2.
    Merlin, J. H., Chapman, B. M.: High Performance Fortran 2.0, in Proc. Sommerschule über Moderne Programmiersprachen und Programmiermodelle, Technical University of Hamburg-Harburg, Sept 15-19, 1997. To appear. Also at URL: ftp://ftp.vcpc.univie.ac.at/vcpc/jhm/proc/hpf2.ps.gzGoogle Scholar
  3. 3.
    Berger, M. J., Oliger J.: Adaptive Mesh Refinement for Hyperbolic Partial Differential Equations, Jnl. of Computational Physics, 53, 3 (March 1984), 484–512.Google Scholar
  4. 4.
    Berger, M. J., Colella P.: Local Adaptive Mesh Refinement for Shock Hydrodynamics, Jnl. of Computational Physics, 82, 1 (May 1989), 64–84.Google Scholar
  5. 5.
    Mehrotra, P., Van Rosendale, J., Zima, H.: High Performance Fortran: History, Status and Future, Parallel Computing, Special Issue on Languages and Compilers for Parallel Computers, 1997.Google Scholar
  6. 6.
    Fink, S. J., Baden, S. B., Kohn, S. R.: Flexible Communication Mechanisms for Dynamic Structured Applications, in Proc. 3rd Int'l Workshop IRREGULAR '96, 203–215, Aug. 1996.Google Scholar
  7. 7.
    Fink, S. J., Kohn, S. R., Baden, S. B.: Efficient Run-time Support for Irregular Block-Structured Applications, Jnl. of Parallel and Distrib. Computing, 1998. To appear.Google Scholar
  8. 8.
    Merlin, J. H., Carpenter, D. B., Hey, A. J. G.: SHPF: a Subset High Performance Fortran Compilation System, Fortran Journal (March / April 1996), 2–6.Google Scholar
  9. 9.
    Message Passing Interface Forum: MPI: A Message-Passing Interface Standard, Technical report, University of Tennessee, Knoxville, TN, June 1995.Google Scholar
  10. 10.
    Zhang, G., Carpenter, D. B., Fox, G., Li, X., Li, X., Wen, Y.: PCRC-based HPF Compilation, in 10th International Workshop on Languages and Compilers for Parallel Computing, 1997, To appear in Lecture Notes in Computer Science.Google Scholar
  11. 11.
    Baden, S. B., Koelbel, C.: Proposed Extension for SPMD calling HPF, HPF Forum proposal,1996.ftp://ftp.cs.ucsd.edu/pub/baden/tr/MDP/spmd-hpf.ps.gz.Google Scholar
  12. 12.
    Foster, I., Kohr, D., Krishnaiyer, R., Choudhary, A.: Double standards: Bringing task parallelism to HPF via the Message Passing Interface, Proc. Supercomputing '96, Pittsburg, PA, November 1996.Google Scholar
  13. 13.
    Fink., S. J., Baden, S. B.: Runtime Support for Multi-Tier Programming of Block-Structured Applications on SMP Clusters, in Proc. Int'l Scientific Computing in Object-Oriented Parallel Environments Conf, Dec 1997, Marina del Rey, CA.Google Scholar
  14. 14.
    Chapman, B., Haines, M., Mehrotra, P., Van Rosendale, J., Zima, H.: Opus: A Coordination Language for Multidisciplinary Applications, Sci. Prog., 1997.Google Scholar
  15. 15.
    Gross, T., O'Halloran, D., Subhlok, J.: Task Parallelism in a High Performance Fortran Framework, IEEE Parallel and Distributed Technology, 2 (1994), 16–26.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1998

Authors and Affiliations

  • John H. Merlin
    • 1
  • Scott B. Baden
    • 2
  • Stephen J. Fink
    • 2
  • Barbara M. Chapman
    • 1
  1. 1.VCPC, Institute for Software Technology and Parallel SystemsUniversity of ViennaViennaAustria
  2. 2.Department of Computer Science and EngineeringUniversity of CaliforniaSan Diego, La JollaUSA

Personalised recommendations