Skip to main content

Dynamic Load Balancing on Dedicated Heterogeneous Systems

  • Conference paper
Book cover Recent Advances in Parallel Virtual Machine and Message Passing Interface (EuroPVM/MPI 2008)

Abstract

Parallel computing in heterogeneous environments is drawing considerable attention due to the growing number of these kind of systems. Adapting existing code and libraries to such systems is a fundamental problem. The performance of this code is affected by the large interdependence between the code and these parallel architectures. We have developed a dynamic load balancing library that allows parallel code to be adapted to heterogeneous systems for a wide variety of problems. The overhead introduced by our system is minimal and the cost to the programmer negligible. The strategy was validated on several problems to confirm the soundness of our proposal.

This work has been supported by the EC (FEDER) and the Spanish MEC with the I+D+I contract number: TIN2005-09037-C02-01.

An Erratum for this chapter can be fount at http://dx.doi.org/10.1007/978-3-540-87475-1_50

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

Access this chapter

Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 39.99
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 54.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. Top500 Org: Systems under development (2006), http://www.top500.org/orsc/2006/comes.html

  2. Dongarra, J., Bosilca, G., Chen, Z., Eijkhout, V., Fagg, G.E., Fuentes, E., Langou, J., Luszczek, P., Pjesivac-Grbovic, J., Seymour, K., You, H., Vadhiyar, S.S.: Self-adapting numerical software (sans) effort. IBM Journal of Research and Development 50(2-3), 223–238 (2006)

    Article  Google Scholar 

  3. Kalinov, A., Lastovetsky, A.L., Robert, Y.: Heterogeneous computing. Parallel Computing 31(7), 649–652 (2005)

    Article  Google Scholar 

  4. Cuenca, J., Giménez, D., Martinez, J.P.: Heuristics for work distribution of a homogeneous parallel dynamic programming scheme on heterogeneous systems. Parallel Comput. 31(7), 711–735 (2005)

    Article  Google Scholar 

  5. Wilkinson, B., Allen, M.: Parallel Programming: Techniques and Applications Using Networked Workstations and Parallel Computers. Prentice Hall, Englewood Cliffs (2004)

    Google Scholar 

  6. Alba, E., Almeida, F., Blesa, M.J., Cotta, C., Díaz, M., Dorta, I., Gabarró, J., León, C., Luque, G., Petit, J.: Efficient parallel lan/wan algorithms for optimization. The mallba project. Parallel Computing 32(5-6), 415–440 (2006)

    Article  Google Scholar 

  7. Kalinov, A.: Scalability of heterogeneous parallel systems. Programming and Computer Software 32(1), 1–7 (2006)

    Article  MathSciNet  MATH  Google Scholar 

  8. Aliaga, J.I., Almeida, F., Badía-Contelles, J.M., Barrachina-Mir, S., Blanco, V., Castillo, M.I., Dorta, U., Mayo, R., Quintana-Ortí, E.S., Quintana-Ortí, G., Rodríguez, C., de Sande, F.: Parallelization of the gnu scientific library on heterogeneous systems. In: ISPDC/HeteroPar, pp. 338–345. IEEE Computer Society, Los Alamitos (2004)

    Google Scholar 

  9. Almeida, F., González, D., Moreno, L.M.: The master-slave paradigm on heterogeneous systems: A dynamic programming approach for the optimal mapping. Journal of Systems Architecture 52(2), 105–116 (2006)

    Article  Google Scholar 

  10. Wu, X.: Performance Evaluation, Prediction and Visualization of Parallel Systems. Kluwer Academic Publishers, Dordrecht (1999)

    Book  MATH  Google Scholar 

  11. Al-Jaroodi, J., Mohamed, N., Jiang, H., Swanson, D.R.: Modeling parallel applications performance on heterogeneous systems. In: IPDPS, p. 160. IEEE Computer Society, Los Alamitos (2003)

    Google Scholar 

  12. Lastovetsky, A.: Adaptive parallel computing on heterogeneous networks with mpc. Parallel computing 28, 1369–1407 (2002)

    Article  MATH  Google Scholar 

  13. mpC: parallel programming language for heterogeneous networks of computers, http://hcl.ucd.ie/Projects/mpC

  14. Lastovetsky, A., Reddy, R.: Heterompi: Towards a message-passing library for heterogeneous networks of computers. Journal of Parallel and Distributed Computing 66, 197–220 (2006)

    Article  MATH  Google Scholar 

  15. HeteroMPI: Mpi extension for heterogeneous networks of computers, http://hcl.ucd.ie/Projects/HeteroMPI

  16. Huang, C., Lawlor, O., Kale, L.: Adaptive mpi (2003)

    Google Scholar 

  17. Weatherly, D., Lowenthal, D., Lowenthal, F.: Dyn-mpi: Supporting mpi on non dedicated clusters (2003)

    Google Scholar 

  18. charm++ System, http://charm.cs.uiuc.edu/research/charm/index.shtml#Papers

  19. Bosque, J.L., Marcos, D.G., Pastor, L.: Dynamic load balancing in heterogeneous clusters. In: Hamza, M.H. (ed.) Parallel and Distributed Computing and Networks, pp. 37–42. IASTED/ACTA Press (2004)

    Google Scholar 

Download references

Author information

Authors and Affiliations

Authors

Editor information

Alexey Lastovetsky Tahar Kechadi Jack Dongarra

Rights and permissions

Reprints and permissions

Copyright information

© 2008 Springer-Verlag Berlin Heidelberg

About this paper

Cite this paper

Galindo, I., Almeida, F., Badía-Contelles, J.M. (2008). Dynamic Load Balancing on Dedicated Heterogeneous Systems . In: Lastovetsky, A., Kechadi, T., Dongarra, J. (eds) Recent Advances in Parallel Virtual Machine and Message Passing Interface. EuroPVM/MPI 2008. Lecture Notes in Computer Science, vol 5205. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-87475-1_14

Download citation

  • DOI: https://doi.org/10.1007/978-3-540-87475-1_14

  • Publisher Name: Springer, Berlin, Heidelberg

  • Print ISBN: 978-3-540-87474-4

  • Online ISBN: 978-3-540-87475-1

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics