Skip to main content
SpringerLink
Log in

Design and implementation of a massively parallel version of DIRECT

  • Published:
Computational Optimization and Applications Aims and scope Submit manuscript

Abstract

This paper describes several massively parallel implementations for a global search algorithm DIRECT. Two parallel schemes take different approaches to address DIRECT’s design challenges imposed by memory requirements and data dependency. Three design aspects in topology, data structures, and task allocation are compared in detail. The goal is to analytically investigate the strengths and weaknesses of these parallel schemes, identify several key sources of inefficiency, and experimentally evaluate a number of improvements in the latest parallel DIRECT implementation. The performance studies demonstrate improved data structure efficiency and load balancing on a 2200 processor cluster.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Similar content being viewed by others

References

  1. Atkinson, M.D., Sack, J.-R., Santoro, N., Strothotte, T.: Min-max heap and generalized priority queues. Commun. ACM 29(10), 996–1000 (1986)

    Article  MATH  Google Scholar 

  2. Baker, C.A., Watson, L.T., Grossman, B., Haftka, R.T., Mason, W.H.: Parallel global aircraft configuration design space exploration. In: Tentner, A. (ed.) High Performance Computing Symposium 2000, Soc. for Computer Simulation Internat, San Diego, CA, pp. 101–106 (2000)

  3. Bartholomew-Biggs, M.C., Parkhurst, S.C., Wilson, S.P.: Global optimization approaches to an aircraft routing problem. EUR J. Oper. Res. 146(2), 417–431 (2003)

    Article  MATH  MathSciNet  Google Scholar 

  4. Chandra, R., Dagum, L., Kohr, D., Maydan, D., McDonald, J., Menon, R.: Parallel Programming in OpenMP. Morgan Kaufmann, San Francisco (2001)

    Google Scholar 

  5. Cray Research, Inc.: SHMEM Technical Note for C, SG-2516 2.3 (October 1994)

  6. Esposito, W.R., Floudas, C.A.: Global optimization in parameter estimation of nonlinear algebraic models via the Error-In-Variables approach. Ind. Eng. Chem. Res. 37, 1841–1858 (1998)

    Article  Google Scholar 

  7. Gablonsky, J.M.: Modifications of the DIRECT algorithm. PhD thesis, Department of Mathematics, North Carolina State University, Raleigh, NC (2001)

  8. Gau, C., Stadtherr, M.A.: Nonlinear parameter estimation using interval analysis. In: AIchE Symposium, vol. 94, no. 320, pp. 445–450 (1999)

  9. Grama, A., Gupta, A., Karypis, G., Kumar, V.: Introduction to Parallel Computing, 2nd edn. Pearson Education, Upper Saddle River (2003)

    Google Scholar 

  10. Gropp, W., Lusk, E., Thakur, R.: Using MPI-2: Advanced Features of the Message-Passing Interface. MIT Press, Cambridge (1999)

    Book  Google Scholar 

  11. He, J., Verstak, A., Watson, L.T., Rappaport, T.S., Anderson, C.R., Ramakrishnan, N., Shaffer, C.A., Tranter, W.H., Bae, K., Jiang, J.: Global optimization of transmitter placement in wireless communication systems. In: Tentner, A. (ed.) Proc. High Performance Computing Symposium 2002, Soc. for Modeling and Simulation International, San Diego, CA, pp. 328–333 (2002)

  12. He, J., Watson, L.T., Ramakrishnan, N., Shaffer, C.A., Verstak, A., Jiang, J., Bae, K., Tranter, W.H.: Dynamic data structures for a direct search algorithm. Comput. Optim. Appl. 23(1), 5–25 (2002)

    Article  MATH  MathSciNet  Google Scholar 

  13. He, J., Sosonkina, M., Shaffer, C.A., Tyson, J.J., Watson, L.T., Zwolak, J.W.: A hierarchical parallel scheme for global parameter estimation in systems biology. In: Proc. 18th Internat. Parallel & Distributed Processing Symp., CD-ROM, IEEE Computer Soc., Los Alamitos, CA (2004)

  14. He, J., Sosonkina, M., Watson, L.T., Verstak, A., Zwolak, J.W.: Data-distributed parallelism with dynamic task allocation for a global search algorithm. In: Parashar, M., Watson, L. (eds.) Proc. High Performance Computing Symposium 2005, Soc. for Modeling and Simulation Internat., San Diego, CA, pp. 164–172 (2005)

  15. Jones, D.R.: The DIRECT global optimization algorithm. In: Encyclopedia of Optimization, vol. 1, pp. 431–440. Kluwer Academic, Boston (2001)

    Chapter  Google Scholar 

  16. Jones, D.R., Perttunen, C.D., Stuckman, B.E.: Lipschitzian optimization without the Lipschitz constant. J.  Optim. Theory Appl. 79(1), 157–181 (1993)

    Article  MATH  MathSciNet  Google Scholar 

  17. Moles, C.G., Mendes, P., Banga, J.R.: Parameter estimation in biochemical pathways: a comparison of global optimization methods. Genome Res. 13, 2467–2474 (2003)

    Article  Google Scholar 

  18. Nieplocha, J., Carpenter, B.: ARMCI: a portable remote memory copy library for distributed array libraries and compiler run-time systems. In: 3rd Workshop on Runtime Systems for Parallel Programming (RTSPP) of International Parallel Processing Symposium, IPPS/SDP’99, CDROM (1999)

  19. Nieplocha, J., Harrison, R.J., Littlefield, R.J.: Global arrays: a nonuniform memory access programming model for high-performance computers. J. Supercomput. 10(2), 169–189 (1996)

    Google Scholar 

  20. Panning, T.D., Watson, L.T., Allen, N.A., Chen, K.C., Shaffer, C.A., Tyson, J.J.: Deterministic global parameter estimation for a model of the budding yeast cell cycle, J. Glob. Optim. (to appear)

  21. Parzyszek, K., Nieplocha, J., Kendall, R.A.: A generalized portable SHMEM library for high performance computing. In: 12th IASTED International Conference Parallel and Distributed Computing and Systems (PDCS), pp. 401–406 (2000)

  22. Watson, L.T., Baker, C.A.: A fully-distributed parallel global search algorithm. Eng. Comput. 18(1/2), 155–169 (2001)

    Article  MATH  Google Scholar 

  23. Zhou, J., Deng, X., Dymond, P.: A 2-D parallel convex hull algorithm with optimal communication phases. Parallel Comput. 27(3), 243–255 (2001)

    Article  MATH  MathSciNet  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Department of Computer Science, Virginia Polytechnic Institute and State University, Blacksburg, VA, 24061, USA

    Jian He & Alex Verstak

  2. Departments of Computer Science and Mathematics, Virginia Polytechnic Institute and State University, Blacksburg, VA, 24061, USA

    Layne T. Watson

  3. Ames Laboratory, Iowa State University, Ames, IA, 50011, USA

    Masha Sosonkina

Authors
  1. Jian He
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Alex Verstak
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Layne T. Watson
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Masha Sosonkina
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Layne T. Watson.

Rights and permissions

Reprints and permissions

About this article

Cite this article

He, J., Verstak, A., Watson, L.T. et al. Design and implementation of a massively parallel version of DIRECT. Comput Optim Appl 40, 217–245 (2008). https://doi.org/10.1007/s10589-007-9092-2

Download citation

  • Received:

  • Revised:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s10589-007-9092-2

Keywords

Search

Navigation