Skip to main content
SpringerLink
Log in

Priority Based Messaging for Software Distributed Shared Memory

  • Published:
Cluster Computing Aims and scope Submit manuscript

Abstract

Software Distributed Shared Memory (DSM) systems can be used to provide a coherent shared address space on multicomputers and other parallel systems without support for shared memory in hardware. The coherency software automatically translates shared memory accesses to explicit messages exchanged among the nodes in the system. Many applications exhibit a good performance on such systems but it has been shown that, for some applications, performance critical messages can be delayed behind less important messages because of the enqueuing behavior in the communication libraries used in current systems. We present in this paper a new portable communication library that supports priorities to remedy this situation. We describe an implementation of the communication library and a quantitative model that is used to estimate the performance impact of priorities for a typical situation. Using the model, we show that the use of high-priority communication reduces the latency of performance critical messages substantially over a wide range of network design parameters. The latency is reduced with up to 10–25% for each delaying low priority message in the queue ahead.

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. C. Amza, A.L. Cox, S. Dwarkadas, P. Keleher, H. Lu, R. Rajamony, W. Yu and W. Zwaenepoel, TreadMarks: Shared memory computing on networks of workstations, IEEE Computer 29(2) (1996) 18–28.

    Google Scholar 

  2. A. Bilas, L. Iftode and J.P. Singh, Evaluation of hardware write propagation support for next-generation shared virtual memory clusters, in: Proceedings of 1998 International Conference on Supercomputing (1998) pp. 274–281.

  3. A. Bilas, C. Liao and J.P. Singh, Using network interface support to avoid asynchronous protocol processing in shared virtual memory systems, in: Proceedings of the 26th International Symposium on Computer Architecture, Atlanda, Georgia, May 1999, pp. 282–293.

  4. N.J. Boden, D. Cohen, R.E. Felderman, A.E. Kulawik, C.L. Seitz, J.N. Seizovic and W.-K. Su, Myrinet: A gigabit-per-second local area network, IEEE Micro 15(1) (February 1995) 29–36.

    Google Scholar 

  5. Compaq Computer Corp. et al., VI Architecure Specification V1.0 (December 1997).

  6. Dolphin Interconnect Solutions Inc., PCI-SCI Adapter Card D320/D321 Functional Overview, version 1.01 (November 1999).

  7. Dubnicki et al., Design and implementation of virtual memory-mapped communication on Myrinet, in: Proceedings of 1997 International Parallel Processing Symposium (IEEE Computer Society Press, Los Alamitos, CA, 1997) pp. 388–396.

    Google Scholar 

  8. InfiniBand Trade Association, InfiniBand specification 1.0.a (June 2001) available at http://www.infinibandta.org.

  9. Information Sciences Institute, University of Southern California, RFC 793: Transmission Control Protocol (September 1980).

  10. S. Karlsson and M. Brorsson, A comparative characterization of message communication in applications using MPI and shared memory on an IBM SP2, in: Proceedings of 1998 Workshop on Communication, Architecture, and Applications for Network-Based Parallel Computing, Las Vegas, 31 January–1 February 1998, pp. 189–201.

  11. S. Karlsson and M. Brorsson, An infrastructure for portable and efficient software DSM, in: Proceedings of 1st Workshop on Software Distributed Shared Memory (WSDSM'99), Rhodes, Greece, 25 June 1999; also available from Department of Information Technology, Lund University, PO Box 118, SE-221 00 Lund, Sweden.

  12. P. Keleher, Lazy release consistency for distributed shared memory, Ph.D. thesis, Rice University (1994).

  13. Message Passing Interface Forum, MPI: A Message-Passing Interface Standard, version 1.1 (12 June 1995).

  14. Motorola Semiconductor, RapidIO: An Embedded System Component Network Architecture (February 2000).

  15. K. Omang and B. Parady, Scalability of SCI workstation clusters, a preliminary study, in: Proceedings of the 11th IEEE International Parallel Processing Symposium (IPPS'97), Geneve, April 1997, pp. 750–755.

  16. S. Pakin, M. Lauria and A. Chien, High performance messaging on workstations: Illinois FastMessages (FM) for Myrinet, in: Proceedings of Supercomputing '95 (1995).

  17. L. Prylli and B. Tourancheau, BIP: A new protocol designed for high performance, in: Proceedings of PC-NOW Workshop, Held in Parallel with IPPS/SPDP'98, Orlando, USA, 30 March–3 April 1998, pp. 272–485.

  18. R. Samanta, A. Bilas, L. Iftode and J.P. Singh, Home-based SVM protocols for SMP clusters: Design and performance, in: Proceedings of the 4th IEEE Symposium on High-Performance Computer Architecture (HPCA-4), Las Vegas, Nevada, January 1998, pp. 113–124.

  19. Scali AS, ScaMPI Installation and User's Guide, version 1.6 (1999).

  20. G. Shah et al., Performance and experience with LAPI-a new highperformance communication library for the IBM RS/6000 SP, in: Proceedings of IPPS/SPDP'98, Orlando, FL, 30 March–3 April 1998, pp. 260–266.

  21. J.P. Singh, W.-D. Weber and A. Gupta, SPLASH: Stanford parallel applications for shared-memory, Computer Architecture News 20(1) (March 1992) 5–44.

    Google Scholar 

  22. R. Stets et al., CASHMERE-2L: Software coherent shared memory on a clustered remote-write network, in: Proceedings of SOSP '97, Saint Malo, France, October 1997, pp. 170–182.

  23. H. Tezuka, A. Hori and Y. Ishikawa, PM: A high-performance communication library for multi-user parallel environments, Technical report TR-96015, Real World Computing Partnership (1996).

  24. T. von Eicken, D.E. Culler, S.C. Goldstein and K.E. Schauser, Active messages: A mechanism for integrated communication and computation, in: Proceedings of the 19th International Symposium on Computer Architecture, Gold Coast, Qld., Australia, May 1992, pp. 256–266.

  25. W. Weber et al., Mercury interconnect architecture: A cost-effective infrastructure for high-performance servers, in: Proceedings of the 24th Annual International Symposium on Computer Architecture (ISCA), Denver, Colorado, May 1997, pp. 98–107.

Download references

Author information

Authors and Affiliations

  1. Department of Microelectronics and Information Technology, Royal Institute of Technology, Stockholm, Sweden

    Sven Karlsson & Mats Brorsson

Authors
  1. Sven Karlsson
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Mats Brorsson
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Sven Karlsson.

Rights and permissions

Reprints and permissions

About this article

Cite this article

Karlsson, S., Brorsson, M. Priority Based Messaging for Software Distributed Shared Memory. Cluster Computing 6, 161–169 (2003). https://doi.org/10.1023/A:1022808723380

Download citation

  • Issue Date:

  • DOI: https://doi.org/10.1023/A:1022808723380

Search

Navigation