All-to-all personalized exchange in generalized shuffle-exchange networks

檔案

日期

2010-03-28

類型

期刊名稱

THEORETICAL COMPUTER SCIENCE

卷期與頁次

第 411 卷第 16-18 期,頁 1669–1684

ISSN

0304-3975

語言

英文

摘要

An all-to-all communication algorithm is said to be optimal if it has the smallest communication delay. Previous all-to-all personalized exchange algorithms are mainly for hypercube, mesh, and torus. In Yang and Wang (2000) [13], Yang and Wang proved that a multistage interconnection network (MIN) is a better choice for implementing all-to-all personalized exchange and they proposed optimal all-to-all personalized exchange algorithms for MINs. In Massini (2003)[9], Massini proposed a new optimal algorithm for MINs, which is independent of the network topology. Do notice that the algorithms in [9] and [13] work only for MINs with the unique path property (meaning that there is a unique path between each pair of source and destination) and satisfying N = 2(n), in which N is the number of processors, 2 means all the switches are of size 2 x 2, and n is the number of stages. In Padmanabhan (1991) [10], Padmanabhan proposed the generalized shuffle-exchange network (GSEN), which is a generalization of the shuffle-exchange network. Since a GSEN does not have the unique path property, the algorithms in [9] and [13] cannot be used. The purpose of this paper is to consider the all-to-all personalized exchange problem in GSENs. An optimal algorithm and several bounds will be proposed. (C) 2010 Published by Elsevier B.V.

所屬典藏

期刊論文
顯示完整詮釋資料 統計資料

引用此條目

Chou, W. Y., & Chen, C. (2010). All-to-all personalized exchange in generalized shuffle-exchange networks. THEORETICAL COMPUTER SCIENCE, 411(16-18), 1669–1684. https://doi.org/10.1016/j.tcs.2009.10.026

BibTeX RIS

引用文字依 APA 第 7 版格式自動產生,使用前請再核對。

分享

永久網址:https://ir.lib.nycu.edu.tw/handle/11536/5625