Skip to main content

A Scalable Flow Control Algorithm for the Fast Messages Communication Library

  • Conference paper
Network-Based Parallel Computing. Communication, Architecture, and Applications (CANPC 1999)

Abstract

The evolution of the Fast Messages (FM) communication library has shown the importance of flow control to deliver the raw hardware performance of currently available interconnection networks to the applications. However, the credit-based solution used in FM to provide flow control, though simple and efficient for systems of limited dimension, does not scale well when the dimension of the parallel system increases. In this paper, we propose an extension to the FM flow control algorithm where credits can be assigned on-demand to communicating nodes. The experimental results reported in the paper demonstrate that the performance of this new scheme is virtually insensitive to system dimension providing that messages are long enough and there are not communication hot spots in the system. In presence of more general communication patterns, the proposed dynamic credit assignment mechanism can be used to implement adaptive credit allocation policies.

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. Dubnicki, C., Iftode, L., Felten, E., Li, K.: Software support for virtual memory-mapped communication. In: Procs. of the 1996 International Parallel Processing Symposium (August 1996)

    Google Scholar 

  2. von Eicken, T., Culler, D., Goldstein, S., Scliauser, K.: Active Messages: a mechanism for integrated communication and computation. In: Procs. of the International Symposium on Computer Architecture (May 1992)

    Google Scholar 

  3. von Eicken, T., Basil, A., Buch, V., Vogels, W.: U-Net: a user-level network interface for parallel and distributed computing. In: Procs. of the 15th ACM Symposium on Operating System Principles (December 1995)

    Google Scholar 

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

    Google Scholar 

  5. Canonico, R., Cristaldi, R., Iannello, G.: Credit On-Demand: a scalable flow control protocol for the Fast Messages communication library", Tech. Report, DIS (September 1998)

    Google Scholar 

  6. Culler, D.E., Karp, R.M., Patterson, D.A., Sahay, A., Schauser, K.E., Santos, E., Subramonian, R., von Eicken, T.: LogP: towards a realistic model of parallel computation. In: Procs. of the 4th SIGPLAN Symp. on Principles and Practices of Parallel Programming. ACM, New York (1993)

    Google Scholar 

  7. Karp, R.M., Sahay, A., Santos, E.E., Schauser, K.E.: Optimal Broadcast and Summation in the LogP Model. In: Procs. of the 5th Annual ACM Symp. on Parallel Algorithms and Architectures, June 1993, pp. 142–153 (1993)

    Google Scholar 

  8. Kung, H.T., Morris, R.: Credit-Based Flow Control for ATM Networks. IEEE Networks (March/April 1995)

    Google Scholar 

  9. Lauria, M., Chien, A.: MPI-FM: High performance MPI on workstation clusters. Journal of Parallel and Distributed Computing 40(1), 4–18 (1997)

    Article  Google Scholar 

  10. Lauria, M., Pakin, S., Chien, A.A.: Efficient Layering for High Speed Communication: Fast Messages 2.x In: Procs. of the 7th High Performance Distributed Computing Conference (HPDC7), Chicago, Illinois, July 28-31 (1998)

    Google Scholar 

  11. Pakin, S., Lauria, M., Chien, A.A.: High performance messaging on workstation: Illinois Fast Messages (FM) for Myrinet. In: Procs. Supercomputing 1995 (December 1995)

    Google Scholar 

  12. Prylli, L.: Draft: BIP messages user manual for bip 0.94 (1997), http://lhpca.univ-lyonl.fr/bip.html

  13. Tanenbaum, A.: Computer Networks, 3rd edn. Prentice Hall International, Englewood Cliffs (1996)

    Google Scholar 

Download references

Author information

Authors and Affiliations

Authors

Editor information

Editors and Affiliations

Rights and permissions

Reprints and permissions

Copyright information

© 1999 Springer-Verlag Berlin Heidelberg

About this paper

Cite this paper

Canonico, R., Cristaldi, R., Iannello, G. (1999). A Scalable Flow Control Algorithm for the Fast Messages Communication Library. In: Sivasubramaniam, A., Lauria, M. (eds) Network-Based Parallel Computing. Communication, Architecture, and Applications. CANPC 1999. Lecture Notes in Computer Science, vol 1602. Springer, Berlin, Heidelberg. https://doi.org/10.1007/10704826_6

Download citation

  • DOI: https://doi.org/10.1007/10704826_6

  • Publisher Name: Springer, Berlin, Heidelberg

  • Print ISBN: 978-3-540-65915-0

  • Online ISBN: 978-3-540-48869-9

  • eBook Packages: Springer Book Archive

Publish with us

Policies and ethics