Skip to main content
SpringerLink
Log in

Adaptive load balancing of iterative computation on heterogeneous nondedicated systems

  • Published:
The Journal of Supercomputing Aims and scope Submit manuscript

Abstract

Dynamic load balancing in heterogeneous systems is a fundamental research topic in parallel computing due to the high availability of such systems. The efficient utilization of the heterogeneous resources can significantly enhance the performance of the parallel system. At the same time, adapting parallel codes to state-of-the-art parallel computers composed of heterogeneous multinode–multicore processors becomes a very hard task because parallel codes are highly dependent on the parallel architectures. That means that applications must be tailored requiring a great deal of programming effort. We have developed the ALBIC (Adaptive Load Balancing of Iterative Computation) system that allows for the dynamic load balancing of iterative codes in heterogeneous dedicated and nondedicated Linux based systems. In order to validate the system several parallel codes have been analyzed in different scenarios. The results show that the ALBIC approach achieves better performance than the other proposal. This lightweighted library eases porting homogeneous parallel codes to heterogeneous platforms, since the code intrusion is low and the programming effort is quite reduced.

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

    Google Scholar 

  2. Almeida F, González D, Moreno LM (2006) The master-slave paradigm on heterogeneous systems: a dynamic programming approach for the optimal mapping. J Syst Archit 52(2):105–116

    Article  Google Scholar 

  3. Beltrán M, Guzmán A, Bosque JL (2006) Dealing with heterogeneity in load balancing algorithms. In: ISPDC. IEEE Computer Society, Los Alamitos, pp 123–132

    Google Scholar 

  4. Bosque JL, Marcos D Gil, Pastor L (2004) Dynamic load balancing in heterogeneous clusters. In: Hamza MH (ed) Parallel and distributed computing and networks. IASTED/ACTA Press, Anaheim, pp 37–42

    Google Scholar 

  5. Bovet D, Cesati M (2002) Understanding the linux kernel, 2nd edn. O’Reilly & Associates, Sebastopol

    Google Scholar 

  6. Chen Z, Yang M, Francia GA III, Dongarra J (2007) Self adaptive application level fault tolerance for parallel and distributed computing. In: IPDPS. IEEE Press, New York, pp 1–8

    Google Scholar 

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

    Article  Google Scholar 

  8. Dongarra J, Bosilca G, Chen Z, Eijkhout V, Fagg GE, Fuentes E, Langou J, Luszczek P, Pjesivac-Grbovic J, Seymour K, You H, Vadhiyar SS (2006) Self-adapting numerical software (sans) effort. IBM J Res Dev 50(2–3):223–238

    Article  Google Scholar 

  9. Galindo I, Almeida F, Blanco V, Badía JM Dynamic load balancing on dedicated heterogeneous system. In: Grosspietsch E, Klöckner K (eds) 16th euromicro international conference on parallel, distributed and network-based processing, vol SEA-SR-18, Toulouse, France, February 2008. Institute for Systems Engineering and Automation

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

  11. Huang C, Lawlor O, Kale L (2003) Adaptive MPI. In: 16th international workshop on languages and compilers for parallel computing (LCPC). LNCS, vol 2958, pp 306–322

    Chapter  Google Scholar 

  12. Kalinov A (2006) Scalability of heterogeneous parallel systems. Program Comput Softw 32(1):1–7

    Article  MathSciNet  MATH  Google Scholar 

  13. Kalinov A, Lastovetsky AL, Robert Y (2005) Heterogeneous computing. Parallel Comput 31(7):649–652

    Article  Google Scholar 

  14. Lastovetsky A, Reddy R (2006) HeteroMPI: Towards a message-passing library for heterogeneous networks of computers. J Parallel Distrib Comput 66:197–220

    Article  MATH  Google Scholar 

  15. Martíne JA, Garzón EM, Plaza A, García I (2009) Automatic tuning of iterative computation on heterogeneous multiprocessors with ADITHE. J Supercomput. doi:10.1007/s11227-009-0350-1

    Google Scholar 

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

  17. Weatherly D, Lowenthal DK, Nakazawa M, Lowenthal F (2006) Dyn-MPI: Supporting MPI on medium-scale, non-dedicated clusters. J Parallel Distrib Comput 66(6):822–838

    Article  MATH  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Department of Computer Architecture and Electronics, University of Almería, Ctra Sacramento s/n, 04120, Almería, Spain

    J. A. Martínez & E. M. Garzón

  2. HPC Group, ETS de Ingeniería Informática, Universidad de La Laguna, La Laguna, 38270, Tenerife, Spain

    F. Almeida, A. Acosta & V. Blanco

Authors
  1. J. A. Martínez
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. F. Almeida
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. E. M. Garzón
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. A. Acosta
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. V. Blanco
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to E. M. Garzón.

Additional information

This work has been supported by the EC (FEDER), the Spanish Ministry of Science and Innovation with the I+D+I TIN2008-01117 and TIN2008-06570-C04 contracts; Junta de Andalucia with P08-TIC-3518, P10-TIC-6002 contracts, and Canary Government with SolSubC200801000307 contract and developed in the framework of the network (CAPAP-H) TIN2009-08058-E.

Rights and permissions

Reprints and permissions

About this article

Cite this article

Martínez, J.A., Almeida, F., Garzón, E.M. et al. Adaptive load balancing of iterative computation on heterogeneous nondedicated systems. J Supercomput 58, 385–393 (2011). https://doi.org/10.1007/s11227-011-0595-3

Download citation

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11227-011-0595-3

Keywords

Search

Navigation