Abstract
The phenomenon of a disproportionate decrease in execution time of p 2 over p 1 processors executing a task in parallel, where p 2 > p 1, is referred to as superunitary speedup. An analogous phenomenon that we call superunitary ‘success ratio’ occurs in dealing with tasks that can either succeed or fail, when there is a disproportionate increase in the success of p 2 over p 1 processors. We identify a range of conditions which may lead to superunitary speedup or superunitary success ratio, and propose several new paradigms for problems which admit such superunitary behaviour. Our results suggest that a new theory of parallel computation may be required to accommodate these new paradigms.
Preview
Unable to display preview. Download preview PDF.
References
S.G. Akl, The Design and Analysis of Parallel Algorithms, Prentice Hall, Englewood Cliffs, New Jersey, 1989.
S.G. Akl, M. Cosnard and A.G. Ferreira, Data-movement-intensive problems: two folk theorems in parallel computation revisited, Theoretical Computer Science 95, pp. 323–337, 1992.
R.P. Brent, The parallel evaluation of general arithmetic expressions, Journal of the ACM 21(2), pp. 201–206, April 1974.
R. Cole and U. Vishkin, Faster Optimal Parallel Prefix Sums and List Ranking, Information and Control 81(3), pp. 334–352, 1989.
T.H. Cormen, C.E. Leiserson and R.L. Rivest, Introduction to Algorithms, MIT Press, Cambridge, Massachusetts, 1990.
V. Faber, O.M. Lubeck and A.B. White, Jr., Superlinear speedup of an efficient sequential algorithm is not possible, Parallel Computing 3, pp. 259–260, 1986.
D. Fischer, On superlinear speedups, Parallel Computing 17, pp. 695–697, 1991.
A. Gibbons and W. Rytter, Efficient Parallel Algorithms, Cambridge University Press, Cambridge, 1988.
D.P. Helmbold and C.E. McDowell, Modeling Speedup(n) greater than n, Proc. Int. Conf. Parallel Processing, Vol. III pp. 219–225, 1989.
J. JáJá, An Introduction to Parallel Algorithms, Addison-Wesley, Reading, Massachusetts, 1992.
R. Janβen, A note on superlinear speedup, Parallel Computing 4, pp. 211–213, 1987.
R.M. Karp and V. Ramachandran, Parallel Algorithms for Shared-Memory Machines, pp. 869–941, Handbook of Theoretical Computer Science, J. van Leeuwen, ed., MIT Press, 1990.
T. Lai and S. Sahni, Anomalies in parallel branch and bound algorithms, Comm. ACM 27(6), pp. 594–602, June 1984.
F.T. Leighton, Introduction to Parallel Algorithms and Architectures: Arrays, Trees, Hypercubes, Morgan Kaufmann, San Mateo, California, 1992.
R. Mehrotra and E.F. Gehringer, Superlinear Speedup Through Randomized Algorithms, Proc. 1985 Int. Conf. on Parallel Processing, pp. 291–300, 1985.
D. Parkinson, Parallel efficiency can be greater than unity, Parallel Computing 3, pp. 261–262, 1986.
M.J. Quinn, Designing Efficient Algorithms for Parallel Computers, McGraw-Hill, New York, 1987.
V.N. Rao and V. Kumar, On the efficiency of parallel backtracking, IEEE Trans. on Parallel and Distributed Systems 4(4), pp. 427–437, April 1993.
J.H. Reif, ed., Synthesis of Parallel Algorithms, Morgan Kaufmann, San Mateo, California, 1993.
P.B. Schneck, Superlinear Speed-Up and the Halting Problem, Software—Practice and Experience 16(8), pp. 781–782, Aug. 1986.
J.R. Smith, The Design and Analysis of Parallel Algorithms, Oxford University Press, New York, 1993.
E. Speckenmeyer, B. Monien and O. Vornberger, Superlinear Speedup for Parallel Backtracking, Proc. Int. Conf. Supercomputing, Springer LNCS 297, pp. 985–993, 1988.
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1994 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Akl, S.G., Lindon, L.F. (1994). Paradigms admitting superunitary behaviour in parallel computation. In: Buchberger, B., Volkert, J. (eds) Parallel Processing: CONPAR 94 — VAPP VI. VAPP CONPAR 1994 1994. Lecture Notes in Computer Science, vol 854. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-58430-7_27
Download citation
DOI: https://doi.org/10.1007/3-540-58430-7_27
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-58430-8
Online ISBN: 978-3-540-48789-0
eBook Packages: Springer Book Archive