Abstract
In this paper, we start with presenting and defining scalability of algorithm-architecture combinations based on the fixed ratio of computation time to communication cost, analyze the performance and scalability of a number of parallel matrix multiplication algorithms, and compare them with the related work. The performance analysis and the analytical scalability expressions for these algorithms show that our scalability metric is better than the isoefficiency metric.
Keywords
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.
This work is supported by Chinese National 863 Hi-Tech R&D Project
This is a preview of subscription content, log in via an institution.
Preview
Unable to display preview. Download preview PDF.
References
Berntsen, J.: Communication efficient matrix multiplication on hypercubes, Parallel Computing 12 (1989) 335–342
Cannon, L.E.: A cellular computer to implement the Kalman Filter Algorithm, PH.D. Thesis, Montana State University (1969)
Dekel, E., Nassimi, D., and S. Sahni, S.: Parallel matrix and graph algorithms, SIAM Journal of Computing 10 (1981) 657–673
Fox, G.C., et al.: Matrix algorithms on a hypercube I: Matrix multiplication, Parallel Computing 4 (1987) 17–31
Grama, A.Y., et al.: Isoefficiency: Measuring the scalability of parallel algorithms and architectures, IEEE Parallel and Distributed Technology (1993) 12–21
Gupta, A., V. Kumar, V.: Scalability of Parallel Algorithms for Matrix Multiplication, in: Proc. of 1993 Intern. Conf. on Parallel Processing 115–123
Kumar, V., et al.: Introduction to Parallel Computing-Design and Analysis of Algorithms, The Benjamin/ Cummings Publishing Company, Inc. (1994)
Wu, Xingfu, Li, Wei: Performance Models for Scalable Cluster Computing, Journal of Systems Architecture, Elsevier Science Publishers B.V.(North-Holland) (1997)
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1997 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Wu, X. (1997). An approach to scalability of parallel matrix multiplication algorithms. In: Jiang, T., Lee, D.T. (eds) Computing and Combinatorics. COCOON 1997. Lecture Notes in Computer Science, vol 1276. Springer, Berlin, Heidelberg. https://doi.org/10.1007/BFb0045116
Download citation
DOI: https://doi.org/10.1007/BFb0045116
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-63357-0
Online ISBN: 978-3-540-69522-6
eBook Packages: Springer Book Archive