High-Performance Numerical Optimization on Multicore Clusters

  • Panagiotis E. Hadjidoukas
  • Constantinos Voglis
  • Vassilios V. Dimakopoulos
  • Isaac E. Lagaris
  • Dimitris G. Papageorgiou
Part of the Lecture Notes in Computer Science book series (LNCS, volume 6853)


This paper presents a software infrastructure for high performance numerical optimization on clusters of multicore systems. At the core, a runtime system implements a programming and execution environment for irregular and adaptive task-based parallelism. Building on this, we extract and exploit the parallelism of a global optimization application at multiple levels, which include Hessian calculations and Newton-based local optimizations. We discuss parallel implementations details and task distribution schemes for managing nested parallelism. Finally, we report experimental performance results for all the components of our software system on a multicore cluster.


task parallelism message passing numerical differentiation global optimization 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Rinnooy Kan, A.H.G., Timmer, G.T.: Stochastic global optimization methods part I: Clustering methods. Math. Progr. 39, 27–56 (1987)CrossRefzbMATHGoogle Scholar
  2. 2.
    Voglis, C., Lagaris, I.E.: Towards ideal multistart, A stochastic approach for locating the minima of a continuous function inside a bounded domain. Applied Math. and Comput. 213, 216–229 (2009)CrossRefMathSciNetzbMATHGoogle Scholar
  3. 3.
    Hadjidoukas, P.E., Dimakopoulos, V.V.: TORC: a tasking library for multicore clusters. Technical Report TR-2011-6, Dept. of Computer Science, University of Ioannina, Greece (2011)Google Scholar
  4. 4.
    Voglis, C., Hadjidoukas, P.E., Dimakopoulos, V.V., Lagaris, I.E., Papageorgiou, D.G.: Task-parallel global optimization with application to protein folding. In: 9th Int’l Conf. on High Perf. Comput. and Simul., Istanbul, Turkey (2011)Google Scholar
  5. 5.
    Schutte, J.F., Reinbolt, J.A., Fregly, B.J., Haftka, R.T., George, A.D.: Parallel global optimization with the particle swarm algorithm. Int’l J. Numerical Methods in Engin. 61(13), 2296–2315 (2004)CrossRefzbMATHGoogle Scholar
  6. 6.
    Byrd, R.H., Eskow, E., van der Hoek, A., Schnabel, R.B., Oldenkamp, K.P.B.: A Parallel global optimization method for solving molecular cluster and polymer conformation problems. In: 7th Siam Conf. on Parallel Processing for Scientific Comput., pp. 72–77. SIAM, Philadelphia (1995)Google Scholar
  7. 7.
    Kozola, S.: Improving optimization performance with parallel computing. MATLAB Digest (2009)Google Scholar
  8. 8.
    Eriksson, J., Lindstrom, P.: A parallel interval method implementation for global optimization using dynamic load balancing. Rel. Comput. 1/2, 77–91 (1995)CrossRefzbMATHGoogle Scholar
  9. 9.
    He, K., Zheng, L., Dong, S., Tang, L., Wu, J., Zheng, C.: PGO: a parallel computing platform for global optimization based on genetic algorithm. Computers & Geosciences 33(3), 357–366 (2006)CrossRefGoogle Scholar
  10. 10.
    Wahib, M., Munetomo, M., Munawar, A., Akama, K.: Mhgrid: Towards an ideal optimization environment for global optimization problems using grid computing. In: 8th Int’l Conf. on Parallel and Distr. Comput., Applic. and Technologies, pp. 167–168. IEEE Computer Society, Washington, DC (2007)Google Scholar
  11. 11.
    Günay, A., Öztoprak, F., Birbil, Ş., Yolum, P.: Solving global optimization problems using MANGO. In: 3rd KES Int’l Symp. on Agent and Multi-Agent Systems: Technologies and Applic., Upsalla, Sweden, pp. 783–792 (2009)Google Scholar
  12. 12.
    Biscani, F., Izzo, D., Yam, C.: A global optimisation toolbox for massively parallel engineering optimisation. In: 4th Int’l Conf. on Astrodynamics Tools and Techniques, Madrid, Spain (2010)Google Scholar
  13. 13.
    GSL, GNU Scientific Library (2010),
  14. 14.
    NAG Fortran Library, D04 Numerical Differentiation, subroutine D04AAFGoogle Scholar
  15. 15.
    Krishnan, M., Alexeev, Y., Windus, T.L., Nieplocha, J.: Multilevel parallelism in computational chemistry using Common Component Architecture and Global Arrays. In: ACM/IEEE Supercomp. Conf., Seattle, WA, p. 23 (2005)Google Scholar
  16. 16.
    Staveley, M.S., Poirier, R.A., Bungay, S.D.: An evaluation of parallel numerical Hessian calculations. In: High Perf. Comput. Symp., Kingston, ON, Canada, pp. 196–214 (2009)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2011

Authors and Affiliations

  • Panagiotis E. Hadjidoukas
    • 1
  • Constantinos Voglis
    • 1
  • Vassilios V. Dimakopoulos
    • 1
  • Isaac E. Lagaris
    • 1
  • Dimitris G. Papageorgiou
    • 2
  1. 1.Department of Computer ScienceUniversity of IoanninaIoanninaGreece
  2. 2.Department of Materials Science and EngineeringUniversity of IoanninaIoanninaGreece

Personalised recommendations