Skip to main content

Adaptive Strategy for One-Sided Communication in MPICH2

  • Conference paper
Recent Advances in the Message Passing Interface (EuroMPI 2012)

Part of the book series: Lecture Notes in Computer Science ((LNPSE,volume 7490))

Included in the following conference series:

Abstract

The one-sided communication model supported by MPI-2 can be more convenient to use than the regular two-sided communication model and has potential to provide better performance. The MPI-2 standard gives flexibility about when RMA operations can be issued and completed. The current MPICH2 implementation employs a lazy approach, in which operations are queued up and issued in the later synchronization phase. This has certain benefits for small data transfers because of reduced network operations, but for large data transfers, issuing operations in an eager fashion could achieve better performance. In this paper we describe our design and implementation of an adaptive strategy for one-sided operations and synchronization mechanisms (fence, post-start-complete-wait, lock-unlock) supported by MPI-2, which combines benefits from both lazy and eager approaches. Our performance results demonstrate that our approach performs as well as the lazy approach for small data transfers and achieves similar performance as the eager approach for large data transfers. In addition, it achieves good overlap of communication with computation.

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. Message Passing Interface Forum, MPI-2: A Message Passing Interface Standard. High Performance Computing Applications 12, 1–299 (1988)

    Google Scholar 

  2. Argonne National Laboratory, MPICH2, http://www-unix.mcs.anl.gov/mpi/mpich2/

  3. Barrett, B.W., Shipman, G.M., Lumsdaine, A.: Analysis of Implementation Options for MPI-2 One-Sided. In: Cappello, F., Herault, T., Dongarra, J. (eds.) PVM/MPI 2007. LNCS, vol. 4757, pp. 242–250. Springer, Heidelberg (2007)

    Chapter  Google Scholar 

  4. Traff, J., Ritzdorf, H., Hempel, R.: The Implementation of MPI-2 One-Sided Communication for the NEC SX. In: Proceedings of Supercomputing 2000 (2000)

    Google Scholar 

  5. Cray Research Inc., Cray T3E C and C++ optimization guide (1994)

    Google Scholar 

  6. Nieplocha, J., Carpenter, B.: ARMCI: A Portable Remote Memory Copy Library for Distributed Array Libraries and Compiler Run-Time Systems. In: Rolim, J.D.P. (ed.) IPPS-WS 1999 and SPDP-WS 1999. LNCS, vol. 1586, pp. 533–546. Springer, Heidelberg (1999)

    Google Scholar 

  7. Bonachea, D.: GASNet Specification, v1.1. Technical Report UCB/CSD-02-1207, Computer Science Division, University of California at Berkeley (October 2002)

    Google Scholar 

  8. Goudreau, M., Lang, K., Rao, S.B., Suel, T., Tsantilas, T.: Portable and Efficient Parallel Computing Using the BSP Model. IEEE Transactions on Computers, 670–689 (1999)

    Google Scholar 

  9. Hill, J.M.D.: Lessons learned from Implementing BSP. Oxford University Technical Laboratory, Technical report 21-96

    Google Scholar 

  10. Hill, J.M.D., McColl, B., Stefanescu, D.C., Goudreau, M.W., Lang, K., Rao, S.B., Suel, T., Tsantilas, T., Bisseling, R.H.: BSPlib: The BSP programming library. Parallel Computing 24(14), 1947–1980 (1998)

    Article  Google Scholar 

  11. Gropp, W.D., Thakur, R.: Revealing the Performance of MPI RMA Implementations. In: Cappello, F., Herault, T., Dongarra, J. (eds.) PVM/MPI 2007. LNCS, vol. 4757, pp. 272–280. Springer, Heidelberg (2007)

    Chapter  Google Scholar 

  12. Gropp, W.D., Thakur, R.: An Evaluation of Implementation Options for MPI One-Sided Communication. In: Di Martino, B., Kranzlmüller, D., Dongarra, J. (eds.) EuroPVM/MPI 2005. LNCS, vol. 3666, pp. 415–424. Springer, Heidelberg (2005)

    Chapter  Google Scholar 

  13. Thakur, R., Gropp, W.D., Toonen, B.: Minimizing Synchronization Overhead in the Implementation of MPI One-Sided Communication. In: Kranzlmüller, D., Kacsuk, P., Dongarra, J. (eds.) EuroPVM/MPI 2004. LNCS, vol. 3241, pp. 57–67. Springer, Heidelberg (2004)

    Chapter  Google Scholar 

  14. Liu, J., Jiang, W., Jin, H.-W., Panda, D.K., Gropp, W., Thakur, R.: High Performance MPI-2 One-Sided Communication over InfiniBand. In: International Symposium on Cluster Computing and the Grid (CCGrid 2004) (April 2004)

    Google Scholar 

  15. Jiang, W., Liu, J., Jin, H.-W., Panda, D.K., Buntinas, D., Thakur, R., Gropp, W.D.: Efficient Implementation of MPI-2 Passive One-Sided Communication on InfiniBand Clusters. In: Kranzlmüller, D., Kacsuk, P., Dongarra, J. (eds.) EuroPVM/MPI 2004. LNCS, vol. 3241, pp. 68–76. Springer, Heidelberg (2004)

    Chapter  Google Scholar 

  16. Santhanaraman, G., Narravula, S., Panda, D.K.: Designing passive synchronization for MPI-2 one-sided communication to maximize overlap. In: IPDPS 2008 (April 2008)

    Google Scholar 

  17. Santhanaraman, G., Balaji, P., Gopalakrishnan, K., Thakur, R., Gropp, W., Panda, D.K.: Natively Supporting True One-sided Communication in MPI on Multi-core Systems with InfiniBand. In: CCGRID 2009 (May 2009)

    Google Scholar 

  18. Traff, J.L., Gropp, W.D., Thakur, R.: Self-Consistent MPI Performance Guidelines. IEEE Trans. Parallel Distrib. Syst., 698–709 (2010)

    Google Scholar 

  19. The Graph 500 List, http://www.graph500.org/index.html/

  20. Argonne National Laboratory, MPPTEST - Measuring MPI Performance, http://www.mcs.anl.gov/research/projects/mpi/mpptest/

Download references

Author information

Authors and Affiliations

Authors

Editor information

Editors and Affiliations

Rights and permissions

Reprints and permissions

Copyright information

© 2012 Springer-Verlag Berlin Heidelberg

About this paper

Cite this paper

Zhao, X., Santhanaraman, G., Gropp, W. (2012). Adaptive Strategy for One-Sided Communication in MPICH2. In: Träff, J.L., Benkner, S., Dongarra, J.J. (eds) Recent Advances in the Message Passing Interface. EuroMPI 2012. Lecture Notes in Computer Science, vol 7490. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-33518-1_7

Download citation

  • DOI: https://doi.org/10.1007/978-3-642-33518-1_7

  • Publisher Name: Springer, Berlin, Heidelberg

  • Print ISBN: 978-3-642-33517-4

  • Online ISBN: 978-3-642-33518-1

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics