Skip to main content
SpringerLink
Log in

Superlinear Performance in Real-Time Parallel Computation

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

Abstract

Can a parallel computer with n processors solve a computational problem more than n times faster than a sequential computer? Can it solve it more than n times better? New computational paradigms offer an affirmative answer to the above questions through concrete examples in which the improvement in speed or quality is superlinear in the number of processors used by the parallel computer. Furthermore, the improvement is consistent and provable. All examples are characterized by the presence of one or several real-time input streams. In one of the examples, an exponential improvement in speed is achieved despite the fact that the processors of the parallel computer are significantly slower than their sequential counterpart. In another example, the improvement in quality is unbounded. A metaphor from everyday life motivates each computational paradigm in which a superlinear improvement in performance is exhibited.

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. S. G. Akl. Parallel real-time computation: Sometimes quantity means quality. Proceedings of the International Symposium on Parallel Architectures, Algorithms and Networks, pp. 2–11, Dallas, Texas, December 2000.

  2. S. G. Akl. Parallel Computation: Models and Methods, Prentice-Hall, Upper Saddle River, New Jersey, 1997.

    Google Scholar 

  3. S. G. Akl and S. D. Bruda. Parallel real-time optimization: Beyond speedup. Parallel Processing Letters, 9:499–509, 1999.

    Google Scholar 

  4. S. G. Akl and L. Fava Lindon. Paradigms for superunitary behavior in parallel computations. Journal of Parallel Algorithms and Applications, 11:129–153, 1997.

    Google Scholar 

  5. R. S. Barr and B. L. Hickman. Parallel simplex for large pure network problems: Computational testing and sources of speedup. Operations Research, 42:65–80, 1994.

    Google Scholar 

  6. A. Bestavros and V. Fay-Wolfe, eds., Real-Time Database and Information Systems, Kluwer Academic Publishers, Boston, 1997.

    Google Scholar 

  7. S. D. Bruda and S. G. Akl. A case study in real-time parallel computation: Correcting algorithms. Journal of Parallel and Distributed Computing, 61:688–708, 2001.

    Google Scholar 

  8. S. D. Bruda and S. G. Akl. Real-time computation: A formal definition and its applications. Proceedings of the Workshop on Advances in Parallel and Distributed Computational Models, 8 pages, San Francisco, California, cd-rom publication, April 2001.

    Google Scholar 

  9. S. D. Bruda and S. G. Akl. The characterization of data-accumulating algorithms. Theory of Computing Systems, 33:85–96, 2000.

    Google Scholar 

  10. J. L. Gustafson. Reevaluating Amdahl's law. Communications of the ACM, 31:532–533, 1988.

    Google Scholar 

  11. D. P. Helmbold and C. E. McDowell. Modeling speedup(n) greater than n. IEEE Transactions on Parallel and Distributed Systems, 1:250–256, 1990.

    Google Scholar 

  12. R. Janssen. A note on superlinear speedup. Parallel Computing, 4:211–213, 1987.

    Google Scholar 

  13. T. H. Lai and S. Sahni. Anomalies in parallel branch and bound algorithms. Communications of the ACM, 27:594–602, 1984.

    Google Scholar 

  14. H. W. Lawson. Parallel Processing in Industrial Real-Time Applications, Prentice Hall, Englewood Cliffs, New Jersey, 1992.

    Google Scholar 

  15. H. R. Lewis and C. H. Papadimitriou. Elements of the Theory of Computation, Prentice-Hall, Englewood Cliffs, New Jersey, 1981.

    Google Scholar 

  16. F. Luccio and L. Pagli. The p-shovelers problem (computing with time-varying data). Proceedings of the Fourth Symposium on Parallel and Distributed Computing, pp. 188–193, Arlington, Texas, December 1992.

  17. F. Luccio and L. Pagli. Computing with time-varying data: Sequential complexity and parallel speedup. Theory of Computing Systems, 31:5–26, 1998.

    Google Scholar 

  18. F. Luccio, L. Pagli, and G. Pucci. Three non-conventional paradigms of parallel computation. Lecture Notes in Computer Science, 678:166–175, 1992.

    Google Scholar 

  19. R. Mehrotra and E. F. Gehringer. Superlinear speedup through randomized algorithms. Proceedings of the International Conference on Parallel Processing, 291–300, 1985.

  20. M. Nagy and S. G. Akl. Real-time minimum vertex cover for two-terminal series-parallel graphs. Proceedings of the Thirteenth Conference on Parallel and Distributed Computing and Systems, pp. 526–534, Anaheim, California, August 2001.

  21. D. Parkinson. Parallel efficiency can be greater than unity. Parallel Computing, 3:261–262, 1986.

    Google Scholar 

  22. M. Thorin. Real-Time Transaction Processing, Macmillan, London, 1992.

Download references

Author information

Authors and Affiliations

  1. School of Computing, Queen's University, Kingston, Ontario, K7L 3N6, Canada

    Selim G. Akl

Authors
  1. Selim G. Akl
    View author publications

    You can also search for this author in PubMed Google Scholar

Rights and permissions

Reprints and permissions

About this article

Cite this article

Akl, S.G. Superlinear Performance in Real-Time Parallel Computation. The Journal of Supercomputing 29, 89–111 (2004). https://doi.org/10.1023/B:SUPE.0000022574.59906.20

Download citation

  • Issue Date:

  • DOI: https://doi.org/10.1023/B:SUPE.0000022574.59906.20

Search

Navigation