Abstract
On practical parallel computers, the time for routing a distribution of sufficiently large packets can be approximated by max{T f ,T b }. Here T f is proportional to the maximum number of bytes a PU sends and receives, and Tb is proportional to the maximum number of bytes a connection in the network has to transfer. We show that several important routing patterns can be performed by a sequence of balanced all-to-all routings and analyze how to optimally perform these under the above cost-model. We concentrate on dimension-order routing on meshes, and assume that the routing pattern must be decomposed into a sequence of permutations. The developed strategy has been implemented on the Intel Paragon. In comparison with the trivial strategy, in which PU; routes to PU (i+t)mod P to permutation t, 1 ≤ t < P, one gains between 10 and 20%.
Preview
Unable to display preview. Download preview PDF.
References
Ding, K.-S., C.-T. Ho, J. J. Tsay, ‘Matrix Transpose on Meshes with Wormhole and XY Routing,’ Proc. 6th Symposium on Parallel and Distributed Processing, pp. 656–663, IEEE, 1994.
Hambrusch, S.E., F. Hameed, A. Khokhar, ‘Communication Operations on Coarse-Grained Architectures,’ Parallel Computing, 21, pp. 731–751, 1995.
Kaufmann, M., U. Meyer, J.F. Sibeyn, ‘Matrix Transpose on Meshes: Theory and Practice,’ Proc. 11th International Parallel Processing Symposium, IEEE, 1997, to appear.
Scott, D.S., ‘Efficient All-to-All Communication Patterns in Hypercube and Mesh Topologies,’ Proc. 6th Distributed Memory Computing Conference, pp. 398–403, 1991.
Sibeyn, J.F., F. Guillaume, T. Seidel, ‘Practical Parallel List Ranking,’ Proc. 4th Symposium on Solving Irregularly Structured Problems in Parallel, LNCS, Springer-Verlag, 1997. To appear.
Stricker, T.M., J.C. Hardwick, ‘From AAPC Algorithms to High Performance Permutation Routing and Sorting,’ Proc. 8th Symp. on Parallel Algorithms and Architectures, pp. 200–203, ACM, 1996.
Valiant, L.G., G.J. Brebner, ‘Universal Schemes for Parallel Communication,’ Proc. 13th Symposium on Theory of Computing, pp. 263–277, ACM, 1981.
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1997 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Sibeyn, J.F. (1997). Routing with finite speeds of memory and network. In: Prívara, I., Ružička, P. (eds) Mathematical Foundations of Computer Science 1997. MFCS 1997. Lecture Notes in Computer Science, vol 1295. Springer, Berlin, Heidelberg. https://doi.org/10.1007/BFb0029992
Download citation
DOI: https://doi.org/10.1007/BFb0029992
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-63437-9
Online ISBN: 978-3-540-69547-9
eBook Packages: Springer Book Archive