Abstract
Two methods are given for constructing total exchange algorithms for hypercubic processor networks. This is done by means of bit sequences with special properties. The algorithms are optimal with respect to a given time model, need no intermediate message buffering and are local in the sense that every processor executes basically the same program.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
D. Bertsekas, C. Özveren, G. Stamoulis, P. Tseng and J. Tsitsiklis,Optimal communication algorithms for hypercubes, Journal of Parallel and Distributed Computing 11, 263–275 (1991).
D. Bertsekas and J. Tsitsiklis,Parallel and Distributed Computation, Numerical Methods (Prentice Hall International Editions, 1989).
K. Coolsaet and V. Fack,Total exchange algorithms on “sandwich graphs”, Computers Math. Applic. 22, 45–48 (1991)
A. Edelman,Optimal matrix transposition and bit reversal on hypercubes: All-to-all personalized communication, Journal of Parallel and Distributed Computing 11, 328–331 (1991).
V. Fack, K. Coolsaet and H. De Meyer,Optimal algorithms for total exchange without buffering on the hypercube, poster presented at VAPP IV — CONPAR 90, Joint Conference on Vector and Parallel Processing, Zürich (Switzerland), September 10–13, 1990.
R. J. McEliece,Finite Fields for Computer Scientists and Engineers (Kluwer Academic Publishers, 1987).
Y. Saad and M. Schultz,Data communication in hypercubes, Journal of Parallel and Distributed Computing 6, 115–135 (1989).
Y. Saad and M. Schultz,Data communication in parallel architectures, Parallel Computing 11, 131–150 (1989).
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Coolsaet, K., de Meyer, H. & Fack, V. Optimal algorithms for total exchange without buffering on the hypercube. BIT 32, 559–569 (1992). https://doi.org/10.1007/BF01994840
Received:
Revised:
Issue Date:
DOI: https://doi.org/10.1007/BF01994840