摘要
对求解线性规划问题的松弛算法进行了修正 ,在此基础上提出了一种基于 Cluster结构的并行算法 ,分析了算法的性能 ;基于曙光— 30 0 0大规模并行计算机 ,给出了算法用于求解线性规划问题实例的实验结果 .理论分析和实验结果表明 :修正算法改进了松弛算法的实际性能 ,同时具有较好的并行性和稳定性 。
The relaxation algorithm for linear programming is revised in this paper. Based on Cluster structure, a parallel revised algorithm is presented. Its performance is analyzed. The experimental results on DAWNING 3000 are also given. Theoretical analysis and experimental results show that the revised relaxation algorithm improves the performance of the relaxation algorithm, and it has good parallelism and is very robust. Therefore, it can expect to be applied to the solution of the large scale linear programming problems rising from practical application.
出处
《小型微型计算机系统》
CSCD
北大核心
2004年第10期1772-1775,共4页
Journal of Chinese Computer Systems
基金
国家自然科学基金 ( 60 2 73 0 75 )资助
国家"863"高技术研究发展计划 ( 863 -3 0 6ZD-11-0 1-0 6)资助
国家高性能计算基金资助
关键词
线性规划
松弛法
并行算法
高性能计算
linear programming
relaxation method
parallel algorithm
supercomputing
