版权所有:内蒙古大学图书馆 技术提供:维普资讯• 智图
内蒙古自治区呼和浩特市赛罕区大学西街235号 邮编: 010021
作者机构:Department of Computer Science and Engineering Indian Institute of Technology Madras 600 036 India
出 版 物:《International Journal of High Speed Computing》
年 卷 期:1990年第2卷第3期
页 面:257-264页
主 题:Parallel algorithms linear systems hypercubes
摘 要:Solving large, linear systems is among the most important and most frequently encountered problems in computational mathematics and computer science. This paper presents efficient parallel Jacobi and Gauss-Seidel algorithms, in spite of the apparent inherent sequentiality of the latter, for the iterative solution of large linear systems on hypercube machines. To evaluate their performance, expressions for the speedup factor of the algorithms are derived. The results show that the hypercubes are highly effective in solving large systems of dense linear algebraic equations. Finally, the suitability of the hypercubes for solving sparse linear systems is discussed.